java/code
by Justin Sherrill
java/code/src/com/redhat/rhn/frontend/xmlrpc/kickstart/profile/ProfileHandler.java | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
New commits:
commit 36730b6175ebd8a6194b130d8a4d1fb1952f1a06
Author: Justin Sherrill <jsherril(a)redhat.com>
Date: Wed Jan 27 16:02:08 2010 -0500
fixing api doc
diff --git a/java/code/src/com/redhat/rhn/frontend/xmlrpc/kickstart/profile/ProfileHandler.java b/java/code/src/com/redhat/rhn/frontend/xmlrpc/kickstart/profile/ProfileHandler.java
index e7a5f40..c9bf512 100644
--- a/java/code/src/com/redhat/rhn/frontend/xmlrpc/kickstart/profile/ProfileHandler.java
+++ b/java/code/src/com/redhat/rhn/frontend/xmlrpc/kickstart/profile/ProfileHandler.java
@@ -114,9 +114,9 @@ public class ProfileHandler extends BaseHandler {
* @xmlrpc.param #param_desc("string", "kslabel", "Label of kickstart
* profile to be changed.")
* @xmlrpc.param #param_desc("boolean", "pre", "whether or not to log
- * the pre section of a kickstart to /root/ks-pre.log
+ * the pre section of a kickstart to /root/ks-pre.log")
* @xmlrpc.param #param_desc("boolean", "post", "whether or not to log
- * the pre section of a kickstart to /root/ks-post.log
+ * the pre section of a kickstart to /root/ks-post.log")
* @xmlrpc.returntype #return_int_success()
*/
public int setLogging(String sessionKey, String kslabel, boolean pre, boolean post) {
12Â years, 6Â months
backend/server
by Michael Mraka
backend/server/repomd/view.py | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
New commits:
commit 60ae2d46c6f3c059840aefc7cc283e3541c21d91
Author: Michael Mraka <michael.mraka(a)redhat.com>
Date: Wed Jan 27 19:18:50 2010 +0100
rhel5.2 wants 'sha1' checksum labeled 'sha'
diff --git a/backend/server/repomd/view.py b/backend/server/repomd/view.py
index f1f79fb..fb58137 100644
--- a/backend/server/repomd/view.py
+++ b/backend/server/repomd/view.py
@@ -27,7 +27,10 @@ class RepoView:
self.groups = groups
self.fileobj = fileobj
- self.checksum_type = checksum_type
+ if checksum_type == 'sha1':
+ self.checksum_type = 'sha'
+ else:
+ self.checksum_type = checksum_type
def _get_data(self, data_type, data_obj):
output = []
12Â years, 6Â months
Changes to 'refs/tags/spacewalk-java-0.8.7-1'
by Michael Mraka
Tag 'spacewalk-java-0.8.7-1' created by Michael Mraka <michael.mraka(a)redhat.com> at 2010-01-27 18:09 +0000
Tagging package [spacewalk-java] version [0.8.7-1] in directory [java/].
Changes since spacewalk-backend-0.8.38-1:
Michael Mraka (2):
rhel5.2 wants 'sha1' checksum labeled 'sha'
Automatic commit of package [spacewalk-java] release [0.8.7-1].
---
java/code/src/com/redhat/rhn/taskomatic/task/repomd/RepositoryWriter.java | 18 ++++++----
java/spacewalk-java.spec | 13 ++++++-
rel-eng/packages/spacewalk-java | 2 -
3 files changed, 25 insertions(+), 8 deletions(-)
---
12Â years, 6Â months
java/spacewalk-java.spec rel-eng/packages
by Michael Mraka
java/spacewalk-java.spec | 13 ++++++++++++-
rel-eng/packages/spacewalk-java | 2 +-
2 files changed, 13 insertions(+), 2 deletions(-)
New commits:
commit 67d01c2d2021ac758a6119bad4938c578eb7bab9
Author: Michael Mraka <michael.mraka(a)redhat.com>
Date: Wed Jan 27 19:09:32 2010 +0100
Automatic commit of package [spacewalk-java] release [0.8.7-1].
diff --git a/java/spacewalk-java.spec b/java/spacewalk-java.spec
index 14f8e81..c940aaa 100644
--- a/java/spacewalk-java.spec
+++ b/java/spacewalk-java.spec
@@ -12,7 +12,7 @@ Name: spacewalk-java
Summary: Spacewalk Java site packages
Group: Applications/Internet
License: GPLv2
-Version: 0.8.6
+Version: 0.8.7
Release: 1%{?dist}
URL: https://fedorahosted.org/spacewalk
Source0: https://fedorahosted.org/releases/s/p/spacewalk/%{name}-%{version}.tar.gz
@@ -283,6 +283,17 @@ fi
%{jardir}/postgresql-jdbc.jar
%changelog
+* Wed Jan 27 2010 Michael Mraka <michael.mraka(a)redhat.com> 0.8.7-1
+- 529460 - fixing detection of disconnected satellite
+- 530177 - moving cobbler snippet usage before user %post scripts
+- 543879 - support for downloading kickstart profiles through a proxy
+- 493176 - introducing kickstart.tree.getDetails API call
+- 382561 - fixing daily status message to be formatted correctly
+- 543184 - ability to change logging on a kickstart file from the api
+- 513716 - prefix check simplification
+- 506279 - speeding up channel.software.addPackages
+- 518127 - adding a configchannel.deployAllSystems api call
+
* Fri Jan 15 2010 Tomas Lestach <tlestach(a)redhat.com> 0.8.6-1
- removing logic for channel checksum type completion (tlestach(a)redhat.com)
- 549752 - fix for check "channel in set" in UpdateChildChannelsCommand
diff --git a/rel-eng/packages/spacewalk-java b/rel-eng/packages/spacewalk-java
index 6bfc9de..7043e52 100644
--- a/rel-eng/packages/spacewalk-java
+++ b/rel-eng/packages/spacewalk-java
@@ -1 +1 @@
-0.8.6-1 java/
+0.8.7-1 java/
12Â years, 6Â months
java/code
by Michael Mraka
java/code/src/com/redhat/rhn/taskomatic/task/repomd/RepositoryWriter.java | 18 ++++++----
1 file changed, 12 insertions(+), 6 deletions(-)
New commits:
commit 12d3621e45872a4bce86fc417b823920bf9388c3
Author: Michael Mraka <michael.mraka(a)redhat.com>
Date: Wed Jan 27 19:00:24 2010 +0100
rhel5.2 wants 'sha1' checksum labeled 'sha'
diff --git a/java/code/src/com/redhat/rhn/taskomatic/task/repomd/RepositoryWriter.java b/java/code/src/com/redhat/rhn/taskomatic/task/repomd/RepositoryWriter.java
index 469f979..05b4610 100644
--- a/java/code/src/com/redhat/rhn/taskomatic/task/repomd/RepositoryWriter.java
+++ b/java/code/src/com/redhat/rhn/taskomatic/task/repomd/RepositoryWriter.java
@@ -108,12 +108,18 @@ public class RepositoryWriter {
log.info("Checksum Type Value" + this.checksumtype);
- // available digests: MD2, MD5, SHA-1, SHA-256, SHA-384, SHA-512
+ // java.security.MessageDigest recognizes:
+ // MD2, MD5, SHA-1, SHA-256, SHA-384, SHA-512
String checksumAlgo = this.checksumtype;
if (checksumAlgo.toUpperCase().startsWith("SHA")) {
checksumAlgo = this.checksumtype.substring(0, 3) + "-" +
this.checksumtype.substring(3);
}
+ // translate sha1 to sha for xml repo files
+ String checksumLabel = this.checksumtype;
+ if (checksumLabel == "sha1") {
+ checksumLabel = "sha";
+ }
try {
primaryFile = new CompressingDigestOutputWriter(
@@ -196,15 +202,15 @@ public class RepositoryWriter {
RepomdIndexData groupsData = loadCompsFile(channel, checksumAlgo);
//Set the type so yum can read and perform checksum
- primaryData.setType(this.checksumtype);
- filelistsData.setType(this.checksumtype);
- otherData.setType(this.checksumtype);
+ primaryData.setType(checksumLabel);
+ filelistsData.setType(checksumLabel);
+ otherData.setType(checksumLabel);
if (updateinfoData != null) {
- updateinfoData.setType(this.checksumtype);
+ updateinfoData.setType(checksumLabel);
}
if (groupsData != null) {
- groupsData.setType(this.checksumtype);
+ groupsData.setType(checksumLabel);
}
log.info("Primary xml's type" + primaryData.getType());
12Â years, 6Â months
Changes to 'refs/tags/spacewalk-backend-0.8.38-1'
by Michael Mraka
Tag 'spacewalk-backend-0.8.38-1' created by Michael Mraka <michael.mraka(a)redhat.com> at 2010-01-27 14:53 +0000
Tagging package [spacewalk-backend] version [0.8.38-1] in directory [backend/].
Changes since rhnpush-5.4.9-1:
Michael Mraka (2):
fixed packaging of wsgi handler files
Automatic commit of package [spacewalk-backend] release [0.8.38-1].
Miroslav Suchý (1):
move spacewalk-search server to its own directory so we do not pack to spacewalk-search.tar.gz content of spacewalk-doc-indexes
---
backend/server/Makefile | 2
backend/server/wsgi/Makefile | 10
backend/spacewalk-backend.spec | 25
dev/null |binary
rel-eng/packages/spacewalk-backend | 2
search-server/Makefile | 2
search-server/README | 17
search-server/build.properties | 22
search-server/build.xml | 241
search-server/buildconf/LICENSE.txt | 14
search-server/buildconf/build-utils.xml | 19
search-server/buildconf/exclude | 2
search-server/checkstyle.xml | 233
search-server/ivy.xml | 28
search-server/nutch/crawl_jsp.sh | 35
search-server/nutch/crawl_jsp/conf/automaton-urlfilter.txt | 34
search-server/nutch/crawl_jsp/conf/common-terms.utf8 | 28
search-server/nutch/crawl_jsp/conf/configuration.xsl | 40
search-server/nutch/crawl_jsp/conf/context.xsl | 88
search-server/nutch/crawl_jsp/conf/crawl-tool.xml | 59
search-server/nutch/crawl_jsp/conf/crawl-urlfilter.txt | 61
search-server/nutch/crawl_jsp/conf/domain-suffixes.xml | 4354 ----------
search-server/nutch/crawl_jsp/conf/domain-suffixes.xsd | 130
search-server/nutch/crawl_jsp/conf/hadoop-env.sh | 33
search-server/nutch/crawl_jsp/conf/hadoop-site.xml | 8
search-server/nutch/crawl_jsp/conf/httpclient-auth.xml | 61
search-server/nutch/crawl_jsp/conf/log4j.properties | 82
search-server/nutch/crawl_jsp/conf/logging.properties | 4
search-server/nutch/crawl_jsp/conf/masters | 1
search-server/nutch/crawl_jsp/conf/nutch-conf.xsl | 24
search-server/nutch/crawl_jsp/conf/nutch-default.xml | 1205 --
search-server/nutch/crawl_jsp/conf/nutch-site.xml | 58
search-server/nutch/crawl_jsp/conf/parse-plugins.dtd | 12
search-server/nutch/crawl_jsp/conf/parse-plugins.xml | 221
search-server/nutch/crawl_jsp/conf/prefix-urlfilter.txt | 21
search-server/nutch/crawl_jsp/conf/regex-normalize.xml | 66
search-server/nutch/crawl_jsp/conf/regex-urlfilter.txt | 38
search-server/nutch/crawl_jsp/conf/slaves | 1
search-server/nutch/crawl_jsp/conf/subcollections.xml | 28
search-server/nutch/crawl_jsp/conf/suffix-urlfilter.txt | 91
search-server/nutch/crawl_jsp/conf/tika-mimetypes.xml | 367
search-server/nutch/crawl_jsp/urls/urls.txt | 7
search-server/rhn_search_daemon_dev.conf | 45
search-server/run.sh | 17
search-server/scripts/Reindex.groovy | 43
search-server/scripts/build.properties | 22
search-server/scripts/build.xml | 256
search-server/scripts/buildconf/LICENSE.txt | 14
search-server/scripts/buildconf/build-utils.xml | 19
search-server/scripts/checkstyle.xml | 233
search-server/scripts/ivy.xml | 28
search-server/scripts/maketar.sh | 30
search-server/scripts/reindex.sh | 15
search-server/scripts/search.admin.updateIndex.test.py | 15
search-server/scripts/search.py | 69
search-server/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java | 304
search-server/scripts/webCrawl.sh | 17
search-server/spacewalk-search.spec | 255
search-server/spacewalk-search/Makefile | 2
search-server/spacewalk-search/README | 17
search-server/spacewalk-search/build.properties | 22
search-server/spacewalk-search/build.xml | 241
search-server/spacewalk-search/buildconf/LICENSE.txt | 14
search-server/spacewalk-search/buildconf/build-utils.xml | 19
search-server/spacewalk-search/buildconf/exclude | 2
search-server/spacewalk-search/buildconf/tempjars/hadoop-0.18.1-core.jar |binary
search-server/spacewalk-search/buildconf/tempjars/ibatis-2.3.0.677.jar |binary
search-server/spacewalk-search/buildconf/tempjars/lucene-analyzers-2.3.2.jar |binary
search-server/spacewalk-search/buildconf/tempjars/lucene-core-2.3.2.jar |binary
search-server/spacewalk-search/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar |binary
search-server/spacewalk-search/buildconf/tempjars/picocontainer-1.3.jar |binary
search-server/spacewalk-search/buildconf/tempjars/simple-core-3.1.3.jar |binary
search-server/spacewalk-search/checkstyle.xml | 233
search-server/spacewalk-search/ivy.xml | 28
search-server/spacewalk-search/libsrc/hadoop-0.16.4-src.jar |binary
search-server/spacewalk-search/libsrc/ibatis-2.3.0.677-src.zip |binary
search-server/spacewalk-search/libsrc/icu4j-3_8_1-src.jar |binary
search-server/spacewalk-search/libsrc/log4j-1.2.8-src.jar |binary
search-server/spacewalk-search/libsrc/lucene-2.3.2-src.zip |binary
search-server/spacewalk-search/libsrc/nutch-1.0dev_2008_05_14-src.jar |binary
search-server/spacewalk-search/libsrc/nutch-2008-12-01_04-01-21-src.zip |binary
search-server/spacewalk-search/libsrc/quartz-1.5.1-src.jar |binary
search-server/spacewalk-search/libsrc/redstone-xmlrpc-1.1_20071120-src.jar |binary
search-server/spacewalk-search/libsrc/simple-3.1.3-src.zip |binary
search-server/spacewalk-search/libsrc/tanukiwrapper-3.1.2-src.jar |binary
search-server/spacewalk-search/nutch/crawl_jsp.sh | 35
search-server/spacewalk-search/nutch/crawl_jsp/conf/automaton-urlfilter.txt | 34
search-server/spacewalk-search/nutch/crawl_jsp/conf/common-terms.utf8 | 28
search-server/spacewalk-search/nutch/crawl_jsp/conf/configuration.xsl | 40
search-server/spacewalk-search/nutch/crawl_jsp/conf/context.xsl | 88
search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-tool.xml | 59
search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-urlfilter.txt | 61
search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xml | 4354 ++++++++++
search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xsd | 130
search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-env.sh | 33
search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-site.xml | 8
search-server/spacewalk-search/nutch/crawl_jsp/conf/httpclient-auth.xml | 61
search-server/spacewalk-search/nutch/crawl_jsp/conf/log4j.properties | 82
search-server/spacewalk-search/nutch/crawl_jsp/conf/logging.properties | 4
search-server/spacewalk-search/nutch/crawl_jsp/conf/masters | 1
search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-conf.xsl | 24
search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-default.xml | 1205 ++
search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-site.xml | 58
search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.dtd | 12
search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.xml | 221
search-server/spacewalk-search/nutch/crawl_jsp/conf/prefix-urlfilter.txt | 21
search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-normalize.xml | 66
search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-urlfilter.txt | 38
search-server/spacewalk-search/nutch/crawl_jsp/conf/slaves | 1
search-server/spacewalk-search/nutch/crawl_jsp/conf/subcollections.xml | 28
search-server/spacewalk-search/nutch/crawl_jsp/conf/suffix-urlfilter.txt | 91
search-server/spacewalk-search/nutch/crawl_jsp/conf/tika-mimetypes.xml | 367
search-server/spacewalk-search/nutch/crawl_jsp/urls/urls.txt | 7
search-server/spacewalk-search/rhn_search_daemon_dev.conf | 45
search-server/spacewalk-search/run.sh | 17
search-server/spacewalk-search/scripts/Reindex.groovy | 43
search-server/spacewalk-search/scripts/build.properties | 22
search-server/spacewalk-search/scripts/build.xml | 256
search-server/spacewalk-search/scripts/buildconf/LICENSE.txt | 14
search-server/spacewalk-search/scripts/buildconf/build-utils.xml | 19
search-server/spacewalk-search/scripts/checkstyle.xml | 233
search-server/spacewalk-search/scripts/ivy.xml | 28
search-server/spacewalk-search/scripts/lukeall-0.8.1.jar |binary
search-server/spacewalk-search/scripts/maketar.sh | 30
search-server/spacewalk-search/scripts/reindex.sh | 15
search-server/spacewalk-search/scripts/search.admin.updateIndex.test.py | 15
search-server/spacewalk-search/scripts/search.py | 69
search-server/spacewalk-search/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java | 304
search-server/spacewalk-search/scripts/webCrawl.sh | 17
search-server/spacewalk-search/spacewalk-search.spec | 255
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/config.xml | 39
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/errata.xml | 67
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/errata_handler.xml | 49
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/hwdevice.xml | 53
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/package.xml | 85
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/server.xml | 105
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/server_custom_info.xml | 48
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/snapshot_tag.xml | 53
search-server/spacewalk-search/src/config/etc/logrotate.d/rhn-search | 9
search-server/spacewalk-search/src/config/log4j.properties | 35
search-server/spacewalk-search/src/config/log4j.test.properties | 17
search-server/spacewalk-search/src/config/rhn-search | 395
search-server/spacewalk-search/src/config/search/rhn_search.conf | 15
search-server/spacewalk-search/src/config/search/rhn_search_daemon.conf | 86
search-server/spacewalk-search/src/config/test.properties | 5
search-server/spacewalk-search/src/java/com/redhat/satellite/search/ContainerRunner.java | 62
search-server/spacewalk-search/src/java/com/redhat/satellite/search/DeleteIndexes.java | 187
search-server/spacewalk-search/src/java/com/redhat/satellite/search/Main.java | 89
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/ConfigException.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/Configuration.java | 622 +
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/KeyTranslator.java | 39
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/tests/ConfigurationTest.java | 137
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/translator/HibernateToSearchTranslator.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/translator/TranslatorRegistry.java | 60
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/Connection.java | 97
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/DatabaseManager.java | 94
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/Query.java | 95
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/ResultHandler.java | 35
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/WriteQuery.java | 83
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/Errata.java | 323
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/GenericRecord.java | 35
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/HardwareDevice.java | 183
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/RhnPackage.java | 176
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/Server.java | 698 +
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/ServerCustomInfo.java | 146
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/SnapshotTag.java | 128
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/tests/DatabaseManagerTest.java | 45
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/DocResult.java | 119
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/HardwareDeviceResult.java | 71
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/IndexManager.java | 837 +
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/IndexingException.java | 66
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/KeywordAnalyzer.java | 48
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/MatchingField.java | 119
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/QueryParseException.java | 54
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/Result.java | 152
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ServerCustomInfoResult.java | 86
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/SnapshotTagResult.java | 89
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/BuilderFactory.java | 67
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/DocumentBuilder.java | 36
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/ErrataDocumentBuilder.java | 60
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/HardwareDeviceDocumentBuilder.java | 59
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/PackageDocumentBuilder.java | 59
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/ServerCustomInfoDocumentBuilder.java | 64
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/ServerDocumentBuilder.java | 71
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/SnapshotTagDocumentBuilder.java | 64
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/BuilderFactoryTest.java | 68
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/ErrataDocumentBuilderTest.java | 82
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/HardwareDeviceDocumentBuilderTest.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/PackageDocumentBuilderTest.java | 57
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/ServerCustomInfoDocumentBuilderTest.java | 50
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/ServerDocumentBuilderTest.java | 51
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/SnapshotTagDocumentBuilderTest.java | 48
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/NGramAnalyzer.java | 70
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/NGramQuery.java | 76
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/NGramQueryParser.java | 149
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramAnalyzerTest.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryParserTest.java | 210
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryTest.java | 46
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramTestSetup.java | 163
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/tests/IndexManagerTest.java | 93
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/tests/KeywordAnalyzerTest.java | 26
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/RpcServer.java | 159
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/XmlRpcInvoker.java | 96
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/AdminHandler.java | 58
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/DatabaseHandler.java | 177
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/IndexHandler.java | 221
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/VisibilityResultsHandler.java | 54
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/tests/DatabaseHandlerTest.java | 61
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/tests/IndexHandlerTest.java | 62
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/tests/RpcServerTest.java | 19
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/ScheduleManager.java | 202
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/GenericIndexTask.java | 286
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexDocumentsTask.java | 140
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexErrataTask.java | 178
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexHardwareDevicesTask.java | 117
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexPackagesTask.java | 163
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexServerCustomInfoTask.java | 167
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSnapshotTagsTask.java | 110
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSystemsTask.java | 155
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexErrataTaskTest.java | 185
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexSystemsTaskTest.java | 186
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tests/ScheduleManagerTest.java | 48
search-server/spacewalk-search/src/java/com/redhat/satellite/search/tests/BaseTestCase.java | 33
search-server/spacewalk-search/src/java/com/redhat/satellite/search/tests/TestUtil.java | 133
search-server/spacewalk-search/task-lib/ant-contrib-1.0.jar |binary
search-server/spacewalk-search/task-lib/antlr-2.7.6.jar |binary
search-server/spacewalk-search/task-lib/checkstyle-4.1.jar |binary
search-server/spacewalk-search/task-lib/commons-beanutils-1.7.0.jar |binary
search-server/spacewalk-search/task-lib/commons-logging-1.0.4.jar |binary
search-server/spacewalk-search/task-lib/emma-20040713.jar |binary
search-server/spacewalk-search/task-lib/emma_ant-20040713.jar |binary
search-server/spacewalk-search/task-lib/ivy.jar |binary
search-server/spacewalk-search/task-lib/junit-3.8.1.jar |binary
search-server/spacewalk-search/task-lib/regexp-1.3.jar |binary
search-server/src/config/com/redhat/satellite/search/db/config.xml | 39
search-server/src/config/com/redhat/satellite/search/db/errata.xml | 67
search-server/src/config/com/redhat/satellite/search/db/errata_handler.xml | 49
search-server/src/config/com/redhat/satellite/search/db/hwdevice.xml | 53
search-server/src/config/com/redhat/satellite/search/db/package.xml | 85
search-server/src/config/com/redhat/satellite/search/db/server.xml | 105
search-server/src/config/com/redhat/satellite/search/db/server_custom_info.xml | 48
search-server/src/config/com/redhat/satellite/search/db/snapshot_tag.xml | 53
search-server/src/config/etc/logrotate.d/rhn-search | 9
search-server/src/config/log4j.properties | 35
search-server/src/config/log4j.test.properties | 17
search-server/src/config/rhn-search | 395
search-server/src/config/search/rhn_search.conf | 15
search-server/src/config/search/rhn_search_daemon.conf | 86
search-server/src/config/test.properties | 5
search-server/src/java/com/redhat/satellite/search/ContainerRunner.java | 62
search-server/src/java/com/redhat/satellite/search/DeleteIndexes.java | 187
search-server/src/java/com/redhat/satellite/search/Main.java | 89
search-server/src/java/com/redhat/satellite/search/config/ConfigException.java | 49
search-server/src/java/com/redhat/satellite/search/config/Configuration.java | 622 -
search-server/src/java/com/redhat/satellite/search/config/KeyTranslator.java | 39
search-server/src/java/com/redhat/satellite/search/config/tests/ConfigurationTest.java | 137
search-server/src/java/com/redhat/satellite/search/config/translator/HibernateToSearchTranslator.java | 49
search-server/src/java/com/redhat/satellite/search/config/translator/TranslatorRegistry.java | 60
search-server/src/java/com/redhat/satellite/search/db/Connection.java | 97
search-server/src/java/com/redhat/satellite/search/db/DatabaseManager.java | 94
search-server/src/java/com/redhat/satellite/search/db/Query.java | 95
search-server/src/java/com/redhat/satellite/search/db/ResultHandler.java | 35
search-server/src/java/com/redhat/satellite/search/db/WriteQuery.java | 83
search-server/src/java/com/redhat/satellite/search/db/models/Errata.java | 323
search-server/src/java/com/redhat/satellite/search/db/models/GenericRecord.java | 35
search-server/src/java/com/redhat/satellite/search/db/models/HardwareDevice.java | 183
search-server/src/java/com/redhat/satellite/search/db/models/RhnPackage.java | 176
search-server/src/java/com/redhat/satellite/search/db/models/Server.java | 698 -
search-server/src/java/com/redhat/satellite/search/db/models/ServerCustomInfo.java | 146
search-server/src/java/com/redhat/satellite/search/db/models/SnapshotTag.java | 128
search-server/src/java/com/redhat/satellite/search/db/tests/DatabaseManagerTest.java | 45
search-server/src/java/com/redhat/satellite/search/index/DocResult.java | 119
search-server/src/java/com/redhat/satellite/search/index/HardwareDeviceResult.java | 71
search-server/src/java/com/redhat/satellite/search/index/IndexManager.java | 837 -
search-server/src/java/com/redhat/satellite/search/index/IndexingException.java | 66
search-server/src/java/com/redhat/satellite/search/index/KeywordAnalyzer.java | 48
search-server/src/java/com/redhat/satellite/search/index/MatchingField.java | 119
search-server/src/java/com/redhat/satellite/search/index/QueryParseException.java | 54
search-server/src/java/com/redhat/satellite/search/index/Result.java | 152
search-server/src/java/com/redhat/satellite/search/index/ServerCustomInfoResult.java | 86
search-server/src/java/com/redhat/satellite/search/index/SnapshotTagResult.java | 89
search-server/src/java/com/redhat/satellite/search/index/builder/BuilderFactory.java | 67
search-server/src/java/com/redhat/satellite/search/index/builder/DocumentBuilder.java | 36
search-server/src/java/com/redhat/satellite/search/index/builder/ErrataDocumentBuilder.java | 60
search-server/src/java/com/redhat/satellite/search/index/builder/HardwareDeviceDocumentBuilder.java | 59
search-server/src/java/com/redhat/satellite/search/index/builder/PackageDocumentBuilder.java | 59
search-server/src/java/com/redhat/satellite/search/index/builder/ServerCustomInfoDocumentBuilder.java | 64
search-server/src/java/com/redhat/satellite/search/index/builder/ServerDocumentBuilder.java | 71
search-server/src/java/com/redhat/satellite/search/index/builder/SnapshotTagDocumentBuilder.java | 64
search-server/src/java/com/redhat/satellite/search/index/builder/tests/BuilderFactoryTest.java | 68
search-server/src/java/com/redhat/satellite/search/index/builder/tests/ErrataDocumentBuilderTest.java | 82
search-server/src/java/com/redhat/satellite/search/index/builder/tests/HardwareDeviceDocumentBuilderTest.java | 49
search-server/src/java/com/redhat/satellite/search/index/builder/tests/PackageDocumentBuilderTest.java | 57
search-server/src/java/com/redhat/satellite/search/index/builder/tests/ServerCustomInfoDocumentBuilderTest.java | 50
search-server/src/java/com/redhat/satellite/search/index/builder/tests/ServerDocumentBuilderTest.java | 51
search-server/src/java/com/redhat/satellite/search/index/builder/tests/SnapshotTagDocumentBuilderTest.java | 48
search-server/src/java/com/redhat/satellite/search/index/ngram/NGramAnalyzer.java | 70
search-server/src/java/com/redhat/satellite/search/index/ngram/NGramQuery.java | 76
search-server/src/java/com/redhat/satellite/search/index/ngram/NGramQueryParser.java | 149
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramAnalyzerTest.java | 49
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryParserTest.java | 210
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryTest.java | 46
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramTestSetup.java | 163
search-server/src/java/com/redhat/satellite/search/index/tests/IndexManagerTest.java | 93
search-server/src/java/com/redhat/satellite/search/index/tests/KeywordAnalyzerTest.java | 26
search-server/src/java/com/redhat/satellite/search/rpc/RpcServer.java | 159
search-server/src/java/com/redhat/satellite/search/rpc/XmlRpcInvoker.java | 96
search-server/src/java/com/redhat/satellite/search/rpc/handlers/AdminHandler.java | 58
search-server/src/java/com/redhat/satellite/search/rpc/handlers/DatabaseHandler.java | 177
search-server/src/java/com/redhat/satellite/search/rpc/handlers/IndexHandler.java | 221
search-server/src/java/com/redhat/satellite/search/rpc/handlers/VisibilityResultsHandler.java | 54
search-server/src/java/com/redhat/satellite/search/rpc/handlers/tests/DatabaseHandlerTest.java | 61
search-server/src/java/com/redhat/satellite/search/rpc/handlers/tests/IndexHandlerTest.java | 62
search-server/src/java/com/redhat/satellite/search/rpc/tests/RpcServerTest.java | 19
search-server/src/java/com/redhat/satellite/search/scheduler/ScheduleManager.java | 202
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/GenericIndexTask.java | 286
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexDocumentsTask.java | 140
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexErrataTask.java | 178
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexHardwareDevicesTask.java | 117
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexPackagesTask.java | 163
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexServerCustomInfoTask.java | 167
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSnapshotTagsTask.java | 110
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSystemsTask.java | 155
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexErrataTaskTest.java | 185
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexSystemsTaskTest.java | 186
search-server/src/java/com/redhat/satellite/search/scheduler/tests/ScheduleManagerTest.java | 48
search-server/src/java/com/redhat/satellite/search/tests/BaseTestCase.java | 33
search-server/src/java/com/redhat/satellite/search/tests/TestUtil.java | 133
328 files changed, 20062 insertions(+), 20033 deletions(-)
---
12Â years, 6Â months
2 commits - backend/server backend/spacewalk-backend.spec rel-eng/packages
by Michael Mraka
backend/server/Makefile | 2 +-
backend/server/wsgi/Makefile | 10 ++++++++++
backend/spacewalk-backend.spec | 25 ++++++++++++++++++++++---
rel-eng/packages/spacewalk-backend | 2 +-
4 files changed, 34 insertions(+), 5 deletions(-)
New commits:
commit ee9bb0263ac830640c4f4e119a9de36c897cb325
Author: Michael Mraka <michael.mraka(a)redhat.com>
Date: Wed Jan 27 15:53:49 2010 +0100
Automatic commit of package [spacewalk-backend] release [0.8.38-1].
diff --git a/backend/spacewalk-backend.spec b/backend/spacewalk-backend.spec
index ece8a03..8e471b8 100644
--- a/backend/spacewalk-backend.spec
+++ b/backend/spacewalk-backend.spec
@@ -8,7 +8,7 @@ Name: spacewalk-backend
Summary: Common programs needed to be installed on the Spacewalk servers/proxies
Group: Applications/Internet
License: GPLv2
-Version: 0.8.37
+Version: 0.8.38
Release: 1%{?dist}
URL: https://fedorahosted.org/spacewalk
Source0: https://fedorahosted.org/releases/s/p/spacewalk/%{name}-%{version}.tar.gz
@@ -625,6 +625,9 @@ rm -f %{rhnconf}/rhnSecret.py*
# $Id$
%changelog
+* Wed Jan 27 2010 Michael Mraka <michael.mraka(a)redhat.com> 0.8.38-1
+- fixed packaging of wsgi handler files
+
* Tue Jan 26 2010 Michael Mraka <michael.mraka(a)redhat.com> 0.8.37-1
- fixed HTTP 404 on package download
- execute commands through shell
diff --git a/rel-eng/packages/spacewalk-backend b/rel-eng/packages/spacewalk-backend
index b761b78..350f6cf 100644
--- a/rel-eng/packages/spacewalk-backend
+++ b/rel-eng/packages/spacewalk-backend
@@ -1 +1 @@
-0.8.37-1 backend/
+0.8.38-1 backend/
commit e4cfbe9dab9af5e4b4984d185145ced31a5ee9a3
Author: Michael Mraka <michael.mraka(a)redhat.com>
Date: Wed Jan 27 15:28:31 2010 +0100
fixed packaging of wsgi handler files
diff --git a/backend/server/Makefile b/backend/server/Makefile
index f94f387..3b74982 100644
--- a/backend/server/Makefile
+++ b/backend/server/Makefile
@@ -21,6 +21,6 @@ FILES = __init__ \
rhnSession rhnUser rhnVirtualization taskomatic
SUBDIRS = rhnSQL rhnServer action \
handlers importlib action_extra_data \
- config_common repomd
+ config_common repomd wsgi
include $(TOP)/Makefile.defs
diff --git a/backend/server/wsgi/Makefile b/backend/server/wsgi/Makefile
new file mode 100644
index 0000000..b458c7c
--- /dev/null
+++ b/backend/server/wsgi/Makefile
@@ -0,0 +1,10 @@
+# Makefile for the wsgi module
+
+TOP = ../..
+
+SUBDIR = server/wsgi
+
+FILES = __init__ app applet config config_tool package_push package_upload \
+ sat sat_dump wsgiHandler wsgiRequest xmlrpc xp
+
+include $(TOP)/Makefile.defs
diff --git a/backend/spacewalk-backend.spec b/backend/spacewalk-backend.spec
index 0cc6ec6..ece8a03 100644
--- a/backend/spacewalk-backend.spec
+++ b/backend/spacewalk-backend.spec
@@ -259,9 +259,10 @@ export PYTHON_MODULE_VERSION=%{version}
%{__python} setup.py install -O1 --root $RPM_BUILD_ROOT --prefix=%{_prefix}
%if 0%{?rhel} && 0%{?rhel} < 6
-rm $RPM_BUILD_ROOT/%{apacheconfd}/zz-spacewalk-server-wsgi.conf
+rm -v $RPM_BUILD_ROOT/%{apacheconfd}/zz-spacewalk-server-wsgi.conf
+rm -rfv $RPM_BUILD_ROOT/%{rhnroot}/server/wsgi
%else
-rm $RPM_BUILD_ROOT/%{apacheconfd}/zz-spacewalk-server-python.conf
+rm -v $RPM_BUILD_ROOT/%{apacheconfd}/zz-spacewalk-server-python.conf
%endif
@@ -403,7 +404,22 @@ rm -f %{rhnconf}/rhnSecret.py*
%if 0%{?rhel} && 0%{?rhel} < 6
%attr(640,root,apache) %config %{apacheconfd}/zz-spacewalk-server-python.conf
%else
+# wsgi stuff
%attr(640,root,apache) %config %{apacheconfd}/zz-spacewalk-server-wsgi.conf
+%dir %{rhnroot}/server/wsgi
+%{rhnroot}/server/wsgi/__init__.py*
+%{rhnroot}/server/wsgi/app.py*
+%{rhnroot}/server/wsgi/applet.py*
+%{rhnroot}/server/wsgi/config.py*
+%{rhnroot}/server/wsgi/config_tool.py*
+%{rhnroot}/server/wsgi/package_push.py*
+%{rhnroot}/server/wsgi/package_upload.py*
+%{rhnroot}/server/wsgi/sat.py*
+%{rhnroot}/server/wsgi/sat_dump.py*
+%{rhnroot}/server/wsgi/wsgiHandler.py*
+%{rhnroot}/server/wsgi/wsgiRequest.py*
+%{rhnroot}/server/wsgi/xmlrpc.py*
+%{rhnroot}/server/wsgi/xp.py*
%endif
# logs and other stuff
12Â years, 6Â months
search-server/buildconf search-server/build.properties search-server/build.xml search-server/checkstyle.xml search-server/ivy.xml search-server/libsrc search-server/Makefile search-server/nutch search-server/README search-server/rhn_search_daemon_dev.conf search-server/run.sh search-server/scripts search-server/spacewalk-search search-server/spacewalk-search.spec search-server/src search-server/task-lib
by Miroslav Suchý
dev/null |binary
search-server/Makefile | 2
search-server/README | 17
search-server/build.properties | 22
search-server/build.xml | 241
search-server/buildconf/LICENSE.txt | 14
search-server/buildconf/build-utils.xml | 19
search-server/buildconf/exclude | 2
search-server/checkstyle.xml | 233
search-server/ivy.xml | 28
search-server/nutch/crawl_jsp.sh | 35
search-server/nutch/crawl_jsp/conf/automaton-urlfilter.txt | 34
search-server/nutch/crawl_jsp/conf/common-terms.utf8 | 28
search-server/nutch/crawl_jsp/conf/configuration.xsl | 40
search-server/nutch/crawl_jsp/conf/context.xsl | 88
search-server/nutch/crawl_jsp/conf/crawl-tool.xml | 59
search-server/nutch/crawl_jsp/conf/crawl-urlfilter.txt | 61
search-server/nutch/crawl_jsp/conf/domain-suffixes.xml | 4354 ----------
search-server/nutch/crawl_jsp/conf/domain-suffixes.xsd | 130
search-server/nutch/crawl_jsp/conf/hadoop-env.sh | 33
search-server/nutch/crawl_jsp/conf/hadoop-site.xml | 8
search-server/nutch/crawl_jsp/conf/httpclient-auth.xml | 61
search-server/nutch/crawl_jsp/conf/log4j.properties | 82
search-server/nutch/crawl_jsp/conf/logging.properties | 4
search-server/nutch/crawl_jsp/conf/masters | 1
search-server/nutch/crawl_jsp/conf/nutch-conf.xsl | 24
search-server/nutch/crawl_jsp/conf/nutch-default.xml | 1205 --
search-server/nutch/crawl_jsp/conf/nutch-site.xml | 58
search-server/nutch/crawl_jsp/conf/parse-plugins.dtd | 12
search-server/nutch/crawl_jsp/conf/parse-plugins.xml | 221
search-server/nutch/crawl_jsp/conf/prefix-urlfilter.txt | 21
search-server/nutch/crawl_jsp/conf/regex-normalize.xml | 66
search-server/nutch/crawl_jsp/conf/regex-urlfilter.txt | 38
search-server/nutch/crawl_jsp/conf/slaves | 1
search-server/nutch/crawl_jsp/conf/subcollections.xml | 28
search-server/nutch/crawl_jsp/conf/suffix-urlfilter.txt | 91
search-server/nutch/crawl_jsp/conf/tika-mimetypes.xml | 367
search-server/nutch/crawl_jsp/urls/urls.txt | 7
search-server/rhn_search_daemon_dev.conf | 45
search-server/run.sh | 17
search-server/scripts/Reindex.groovy | 43
search-server/scripts/build.properties | 22
search-server/scripts/build.xml | 256
search-server/scripts/buildconf/LICENSE.txt | 14
search-server/scripts/buildconf/build-utils.xml | 19
search-server/scripts/checkstyle.xml | 233
search-server/scripts/ivy.xml | 28
search-server/scripts/maketar.sh | 30
search-server/scripts/reindex.sh | 15
search-server/scripts/search.admin.updateIndex.test.py | 15
search-server/scripts/search.py | 69
search-server/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java | 304
search-server/scripts/webCrawl.sh | 17
search-server/spacewalk-search.spec | 255
search-server/spacewalk-search/Makefile | 2
search-server/spacewalk-search/README | 17
search-server/spacewalk-search/build.properties | 22
search-server/spacewalk-search/build.xml | 241
search-server/spacewalk-search/buildconf/LICENSE.txt | 14
search-server/spacewalk-search/buildconf/build-utils.xml | 19
search-server/spacewalk-search/buildconf/exclude | 2
search-server/spacewalk-search/buildconf/tempjars/hadoop-0.18.1-core.jar |binary
search-server/spacewalk-search/buildconf/tempjars/ibatis-2.3.0.677.jar |binary
search-server/spacewalk-search/buildconf/tempjars/lucene-analyzers-2.3.2.jar |binary
search-server/spacewalk-search/buildconf/tempjars/lucene-core-2.3.2.jar |binary
search-server/spacewalk-search/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar |binary
search-server/spacewalk-search/buildconf/tempjars/picocontainer-1.3.jar |binary
search-server/spacewalk-search/buildconf/tempjars/simple-core-3.1.3.jar |binary
search-server/spacewalk-search/checkstyle.xml | 233
search-server/spacewalk-search/ivy.xml | 28
search-server/spacewalk-search/libsrc/hadoop-0.16.4-src.jar |binary
search-server/spacewalk-search/libsrc/ibatis-2.3.0.677-src.zip |binary
search-server/spacewalk-search/libsrc/icu4j-3_8_1-src.jar |binary
search-server/spacewalk-search/libsrc/log4j-1.2.8-src.jar |binary
search-server/spacewalk-search/libsrc/lucene-2.3.2-src.zip |binary
search-server/spacewalk-search/libsrc/nutch-1.0dev_2008_05_14-src.jar |binary
search-server/spacewalk-search/libsrc/nutch-2008-12-01_04-01-21-src.zip |binary
search-server/spacewalk-search/libsrc/quartz-1.5.1-src.jar |binary
search-server/spacewalk-search/libsrc/redstone-xmlrpc-1.1_20071120-src.jar |binary
search-server/spacewalk-search/libsrc/simple-3.1.3-src.zip |binary
search-server/spacewalk-search/libsrc/tanukiwrapper-3.1.2-src.jar |binary
search-server/spacewalk-search/nutch/crawl_jsp.sh | 35
search-server/spacewalk-search/nutch/crawl_jsp/conf/automaton-urlfilter.txt | 34
search-server/spacewalk-search/nutch/crawl_jsp/conf/common-terms.utf8 | 28
search-server/spacewalk-search/nutch/crawl_jsp/conf/configuration.xsl | 40
search-server/spacewalk-search/nutch/crawl_jsp/conf/context.xsl | 88
search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-tool.xml | 59
search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-urlfilter.txt | 61
search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xml | 4354 ++++++++++
search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xsd | 130
search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-env.sh | 33
search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-site.xml | 8
search-server/spacewalk-search/nutch/crawl_jsp/conf/httpclient-auth.xml | 61
search-server/spacewalk-search/nutch/crawl_jsp/conf/log4j.properties | 82
search-server/spacewalk-search/nutch/crawl_jsp/conf/logging.properties | 4
search-server/spacewalk-search/nutch/crawl_jsp/conf/masters | 1
search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-conf.xsl | 24
search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-default.xml | 1205 ++
search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-site.xml | 58
search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.dtd | 12
search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.xml | 221
search-server/spacewalk-search/nutch/crawl_jsp/conf/prefix-urlfilter.txt | 21
search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-normalize.xml | 66
search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-urlfilter.txt | 38
search-server/spacewalk-search/nutch/crawl_jsp/conf/slaves | 1
search-server/spacewalk-search/nutch/crawl_jsp/conf/subcollections.xml | 28
search-server/spacewalk-search/nutch/crawl_jsp/conf/suffix-urlfilter.txt | 91
search-server/spacewalk-search/nutch/crawl_jsp/conf/tika-mimetypes.xml | 367
search-server/spacewalk-search/nutch/crawl_jsp/urls/urls.txt | 7
search-server/spacewalk-search/rhn_search_daemon_dev.conf | 45
search-server/spacewalk-search/run.sh | 17
search-server/spacewalk-search/scripts/Reindex.groovy | 43
search-server/spacewalk-search/scripts/build.properties | 22
search-server/spacewalk-search/scripts/build.xml | 256
search-server/spacewalk-search/scripts/buildconf/LICENSE.txt | 14
search-server/spacewalk-search/scripts/buildconf/build-utils.xml | 19
search-server/spacewalk-search/scripts/checkstyle.xml | 233
search-server/spacewalk-search/scripts/ivy.xml | 28
search-server/spacewalk-search/scripts/lukeall-0.8.1.jar |binary
search-server/spacewalk-search/scripts/maketar.sh | 30
search-server/spacewalk-search/scripts/reindex.sh | 15
search-server/spacewalk-search/scripts/search.admin.updateIndex.test.py | 15
search-server/spacewalk-search/scripts/search.py | 69
search-server/spacewalk-search/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java | 304
search-server/spacewalk-search/scripts/webCrawl.sh | 17
search-server/spacewalk-search/spacewalk-search.spec | 255
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/config.xml | 39
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/errata.xml | 67
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/errata_handler.xml | 49
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/hwdevice.xml | 53
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/package.xml | 85
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/server.xml | 105
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/server_custom_info.xml | 48
search-server/spacewalk-search/src/config/com/redhat/satellite/search/db/snapshot_tag.xml | 53
search-server/spacewalk-search/src/config/etc/logrotate.d/rhn-search | 9
search-server/spacewalk-search/src/config/log4j.properties | 35
search-server/spacewalk-search/src/config/log4j.test.properties | 17
search-server/spacewalk-search/src/config/rhn-search | 395
search-server/spacewalk-search/src/config/search/rhn_search.conf | 15
search-server/spacewalk-search/src/config/search/rhn_search_daemon.conf | 86
search-server/spacewalk-search/src/config/test.properties | 5
search-server/spacewalk-search/src/java/com/redhat/satellite/search/ContainerRunner.java | 62
search-server/spacewalk-search/src/java/com/redhat/satellite/search/DeleteIndexes.java | 187
search-server/spacewalk-search/src/java/com/redhat/satellite/search/Main.java | 89
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/ConfigException.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/Configuration.java | 622 +
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/KeyTranslator.java | 39
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/tests/ConfigurationTest.java | 137
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/translator/HibernateToSearchTranslator.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/config/translator/TranslatorRegistry.java | 60
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/Connection.java | 97
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/DatabaseManager.java | 94
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/Query.java | 95
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/ResultHandler.java | 35
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/WriteQuery.java | 83
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/Errata.java | 323
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/GenericRecord.java | 35
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/HardwareDevice.java | 183
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/RhnPackage.java | 176
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/Server.java | 698 +
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/ServerCustomInfo.java | 146
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/models/SnapshotTag.java | 128
search-server/spacewalk-search/src/java/com/redhat/satellite/search/db/tests/DatabaseManagerTest.java | 45
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/DocResult.java | 119
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/HardwareDeviceResult.java | 71
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/IndexManager.java | 837 +
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/IndexingException.java | 66
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/KeywordAnalyzer.java | 48
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/MatchingField.java | 119
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/QueryParseException.java | 54
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/Result.java | 152
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ServerCustomInfoResult.java | 86
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/SnapshotTagResult.java | 89
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/BuilderFactory.java | 67
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/DocumentBuilder.java | 36
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/ErrataDocumentBuilder.java | 60
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/HardwareDeviceDocumentBuilder.java | 59
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/PackageDocumentBuilder.java | 59
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/ServerCustomInfoDocumentBuilder.java | 64
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/ServerDocumentBuilder.java | 71
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/SnapshotTagDocumentBuilder.java | 64
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/BuilderFactoryTest.java | 68
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/ErrataDocumentBuilderTest.java | 82
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/HardwareDeviceDocumentBuilderTest.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/PackageDocumentBuilderTest.java | 57
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/ServerCustomInfoDocumentBuilderTest.java | 50
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/ServerDocumentBuilderTest.java | 51
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/builder/tests/SnapshotTagDocumentBuilderTest.java | 48
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/NGramAnalyzer.java | 70
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/NGramQuery.java | 76
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/NGramQueryParser.java | 149
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramAnalyzerTest.java | 49
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryParserTest.java | 210
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryTest.java | 46
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/ngram/tests/NGramTestSetup.java | 163
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/tests/IndexManagerTest.java | 93
search-server/spacewalk-search/src/java/com/redhat/satellite/search/index/tests/KeywordAnalyzerTest.java | 26
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/RpcServer.java | 159
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/XmlRpcInvoker.java | 96
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/AdminHandler.java | 58
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/DatabaseHandler.java | 177
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/IndexHandler.java | 221
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/VisibilityResultsHandler.java | 54
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/tests/DatabaseHandlerTest.java | 61
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/handlers/tests/IndexHandlerTest.java | 62
search-server/spacewalk-search/src/java/com/redhat/satellite/search/rpc/tests/RpcServerTest.java | 19
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/ScheduleManager.java | 202
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/GenericIndexTask.java | 286
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexDocumentsTask.java | 140
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexErrataTask.java | 178
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexHardwareDevicesTask.java | 117
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexPackagesTask.java | 163
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexServerCustomInfoTask.java | 167
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSnapshotTagsTask.java | 110
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSystemsTask.java | 155
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexErrataTaskTest.java | 185
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexSystemsTaskTest.java | 186
search-server/spacewalk-search/src/java/com/redhat/satellite/search/scheduler/tests/ScheduleManagerTest.java | 48
search-server/spacewalk-search/src/java/com/redhat/satellite/search/tests/BaseTestCase.java | 33
search-server/spacewalk-search/src/java/com/redhat/satellite/search/tests/TestUtil.java | 133
search-server/spacewalk-search/task-lib/ant-contrib-1.0.jar |binary
search-server/spacewalk-search/task-lib/antlr-2.7.6.jar |binary
search-server/spacewalk-search/task-lib/checkstyle-4.1.jar |binary
search-server/spacewalk-search/task-lib/commons-beanutils-1.7.0.jar |binary
search-server/spacewalk-search/task-lib/commons-logging-1.0.4.jar |binary
search-server/spacewalk-search/task-lib/emma-20040713.jar |binary
search-server/spacewalk-search/task-lib/emma_ant-20040713.jar |binary
search-server/spacewalk-search/task-lib/ivy.jar |binary
search-server/spacewalk-search/task-lib/junit-3.8.1.jar |binary
search-server/spacewalk-search/task-lib/regexp-1.3.jar |binary
search-server/src/config/com/redhat/satellite/search/db/config.xml | 39
search-server/src/config/com/redhat/satellite/search/db/errata.xml | 67
search-server/src/config/com/redhat/satellite/search/db/errata_handler.xml | 49
search-server/src/config/com/redhat/satellite/search/db/hwdevice.xml | 53
search-server/src/config/com/redhat/satellite/search/db/package.xml | 85
search-server/src/config/com/redhat/satellite/search/db/server.xml | 105
search-server/src/config/com/redhat/satellite/search/db/server_custom_info.xml | 48
search-server/src/config/com/redhat/satellite/search/db/snapshot_tag.xml | 53
search-server/src/config/etc/logrotate.d/rhn-search | 9
search-server/src/config/log4j.properties | 35
search-server/src/config/log4j.test.properties | 17
search-server/src/config/rhn-search | 395
search-server/src/config/search/rhn_search.conf | 15
search-server/src/config/search/rhn_search_daemon.conf | 86
search-server/src/config/test.properties | 5
search-server/src/java/com/redhat/satellite/search/ContainerRunner.java | 62
search-server/src/java/com/redhat/satellite/search/DeleteIndexes.java | 187
search-server/src/java/com/redhat/satellite/search/Main.java | 89
search-server/src/java/com/redhat/satellite/search/config/ConfigException.java | 49
search-server/src/java/com/redhat/satellite/search/config/Configuration.java | 622 -
search-server/src/java/com/redhat/satellite/search/config/KeyTranslator.java | 39
search-server/src/java/com/redhat/satellite/search/config/tests/ConfigurationTest.java | 137
search-server/src/java/com/redhat/satellite/search/config/translator/HibernateToSearchTranslator.java | 49
search-server/src/java/com/redhat/satellite/search/config/translator/TranslatorRegistry.java | 60
search-server/src/java/com/redhat/satellite/search/db/Connection.java | 97
search-server/src/java/com/redhat/satellite/search/db/DatabaseManager.java | 94
search-server/src/java/com/redhat/satellite/search/db/Query.java | 95
search-server/src/java/com/redhat/satellite/search/db/ResultHandler.java | 35
search-server/src/java/com/redhat/satellite/search/db/WriteQuery.java | 83
search-server/src/java/com/redhat/satellite/search/db/models/Errata.java | 323
search-server/src/java/com/redhat/satellite/search/db/models/GenericRecord.java | 35
search-server/src/java/com/redhat/satellite/search/db/models/HardwareDevice.java | 183
search-server/src/java/com/redhat/satellite/search/db/models/RhnPackage.java | 176
search-server/src/java/com/redhat/satellite/search/db/models/Server.java | 698 -
search-server/src/java/com/redhat/satellite/search/db/models/ServerCustomInfo.java | 146
search-server/src/java/com/redhat/satellite/search/db/models/SnapshotTag.java | 128
search-server/src/java/com/redhat/satellite/search/db/tests/DatabaseManagerTest.java | 45
search-server/src/java/com/redhat/satellite/search/index/DocResult.java | 119
search-server/src/java/com/redhat/satellite/search/index/HardwareDeviceResult.java | 71
search-server/src/java/com/redhat/satellite/search/index/IndexManager.java | 837 -
search-server/src/java/com/redhat/satellite/search/index/IndexingException.java | 66
search-server/src/java/com/redhat/satellite/search/index/KeywordAnalyzer.java | 48
search-server/src/java/com/redhat/satellite/search/index/MatchingField.java | 119
search-server/src/java/com/redhat/satellite/search/index/QueryParseException.java | 54
search-server/src/java/com/redhat/satellite/search/index/Result.java | 152
search-server/src/java/com/redhat/satellite/search/index/ServerCustomInfoResult.java | 86
search-server/src/java/com/redhat/satellite/search/index/SnapshotTagResult.java | 89
search-server/src/java/com/redhat/satellite/search/index/builder/BuilderFactory.java | 67
search-server/src/java/com/redhat/satellite/search/index/builder/DocumentBuilder.java | 36
search-server/src/java/com/redhat/satellite/search/index/builder/ErrataDocumentBuilder.java | 60
search-server/src/java/com/redhat/satellite/search/index/builder/HardwareDeviceDocumentBuilder.java | 59
search-server/src/java/com/redhat/satellite/search/index/builder/PackageDocumentBuilder.java | 59
search-server/src/java/com/redhat/satellite/search/index/builder/ServerCustomInfoDocumentBuilder.java | 64
search-server/src/java/com/redhat/satellite/search/index/builder/ServerDocumentBuilder.java | 71
search-server/src/java/com/redhat/satellite/search/index/builder/SnapshotTagDocumentBuilder.java | 64
search-server/src/java/com/redhat/satellite/search/index/builder/tests/BuilderFactoryTest.java | 68
search-server/src/java/com/redhat/satellite/search/index/builder/tests/ErrataDocumentBuilderTest.java | 82
search-server/src/java/com/redhat/satellite/search/index/builder/tests/HardwareDeviceDocumentBuilderTest.java | 49
search-server/src/java/com/redhat/satellite/search/index/builder/tests/PackageDocumentBuilderTest.java | 57
search-server/src/java/com/redhat/satellite/search/index/builder/tests/ServerCustomInfoDocumentBuilderTest.java | 50
search-server/src/java/com/redhat/satellite/search/index/builder/tests/ServerDocumentBuilderTest.java | 51
search-server/src/java/com/redhat/satellite/search/index/builder/tests/SnapshotTagDocumentBuilderTest.java | 48
search-server/src/java/com/redhat/satellite/search/index/ngram/NGramAnalyzer.java | 70
search-server/src/java/com/redhat/satellite/search/index/ngram/NGramQuery.java | 76
search-server/src/java/com/redhat/satellite/search/index/ngram/NGramQueryParser.java | 149
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramAnalyzerTest.java | 49
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryParserTest.java | 210
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramQueryTest.java | 46
search-server/src/java/com/redhat/satellite/search/index/ngram/tests/NGramTestSetup.java | 163
search-server/src/java/com/redhat/satellite/search/index/tests/IndexManagerTest.java | 93
search-server/src/java/com/redhat/satellite/search/index/tests/KeywordAnalyzerTest.java | 26
search-server/src/java/com/redhat/satellite/search/rpc/RpcServer.java | 159
search-server/src/java/com/redhat/satellite/search/rpc/XmlRpcInvoker.java | 96
search-server/src/java/com/redhat/satellite/search/rpc/handlers/AdminHandler.java | 58
search-server/src/java/com/redhat/satellite/search/rpc/handlers/DatabaseHandler.java | 177
search-server/src/java/com/redhat/satellite/search/rpc/handlers/IndexHandler.java | 221
search-server/src/java/com/redhat/satellite/search/rpc/handlers/VisibilityResultsHandler.java | 54
search-server/src/java/com/redhat/satellite/search/rpc/handlers/tests/DatabaseHandlerTest.java | 61
search-server/src/java/com/redhat/satellite/search/rpc/handlers/tests/IndexHandlerTest.java | 62
search-server/src/java/com/redhat/satellite/search/rpc/tests/RpcServerTest.java | 19
search-server/src/java/com/redhat/satellite/search/scheduler/ScheduleManager.java | 202
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/GenericIndexTask.java | 286
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexDocumentsTask.java | 140
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexErrataTask.java | 178
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexHardwareDevicesTask.java | 117
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexPackagesTask.java | 163
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexServerCustomInfoTask.java | 167
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSnapshotTagsTask.java | 110
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/IndexSystemsTask.java | 155
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexErrataTaskTest.java | 185
search-server/src/java/com/redhat/satellite/search/scheduler/tasks/tests/IndexSystemsTaskTest.java | 186
search-server/src/java/com/redhat/satellite/search/scheduler/tests/ScheduleManagerTest.java | 48
search-server/src/java/com/redhat/satellite/search/tests/BaseTestCase.java | 33
search-server/src/java/com/redhat/satellite/search/tests/TestUtil.java | 133
324 files changed, 20028 insertions(+), 20028 deletions(-)
New commits:
commit de91ecc6876c661298116975ec70b66d034b29c4
Author: Miroslav SuchÜ <msuchy(a)redhat.com>
Date: Wed Jan 27 13:54:18 2010 +0100
move spacewalk-search server to its own directory so we do not pack to spacewalk-search.tar.gz content of spacewalk-doc-indexes
diff --git a/search-server/Makefile b/search-server/Makefile
deleted file mode 100644
index 700fc9e..0000000
--- a/search-server/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-
-include ../rel-eng/Makefile
diff --git a/search-server/README b/search-server/README
deleted file mode 100644
index b6f3d23..0000000
--- a/search-server/README
+++ /dev/null
@@ -1,17 +0,0 @@
-search-server is the new server used to search packages, and ultimately all
-content including systems, errata, and documentation.
-
-build.properties - build configuration
-build.xml - master ant build script
-buildconf/exclude - list of files excluded from compilation (temp solution)
-buildconf/build-utils.xml - ant macro definitions
-checkstyle.xml - checkstyle code style definition
-ivy.xml - ivy repo configuration file
-libsrc - src code for the libraries used
-nutch - configuration files for nutch crawler (not currently used)
-spacewalk-search.spec - search server RPM spec file
-rhn_search_daemon_dev.conf - development based configuration file
-run.sh - script used to run the software, especially during development
-scripts - useful scripts
-src - the source code
-task-lib - the libraries used by the search-server
diff --git a/search-server/build.properties b/search-server/build.properties
deleted file mode 100644
index b8fd474..0000000
--- a/search-server/build.properties
+++ /dev/null
@@ -1,22 +0,0 @@
-java.src.dir=src/java
-config.src.dir=src/config
-java.lib.dir=lib
-java.task.lib.dir=task-lib
-report.dir=report
-build.dir=build
-build.instrument.dir=instrumented
-dist.dir=dist
-jar.name=spacewalk-search
-jar.version=1.0
-jar.file.name=${jar.name}-${jar.version}.jar
-ivyserver= http://jmrodri.fedorapeople.org
-ivy.log.module.when.found=false
-ivy.log.resolved.revision=false
-# Checkstyle config entries
-checkstyle.cache.file=.checkstyle_cache
-checkstyle.header.file=./buildconf/LICENSE.txt
-javadoc.method.scope=public
-javadoc.type.scope=package
-javadoc.var.scope=package
-javadoc.lazy=true
-jpackage.jars="commons-lang commons-logging redstone-xmlrpc redstone-xmlrpc-client quartz tanukiwrapper log4j commons-httpclient oro commons-cli commons-codec"
diff --git a/search-server/build.xml b/search-server/build.xml
deleted file mode 100644
index de8e25f..0000000
--- a/search-server/build.xml
+++ /dev/null
@@ -1,241 +0,0 @@
-<project name="search-server" basedir="." default="all">
- <import file="buildconf/build-utils.xml" />
-
- <property file="build.properties" />
-
- <path id="project.taskjars">
- <fileset dir="${java.task.lib.dir}" includes="**/*.jar" />
- </path>
-
- <path id="project.classpath">
- <fileset dir="${java.lib.dir}" includes="**/*.jar" />
- <fileset dir="${java.task.lib.dir}" >
- <include name="junit*.jar" />
- <include name="emma*.jar" />
- </fileset>
- </path>
-
- <path id="test.classpath">
- <pathelement location="${build.dir}" />
- <path refid="project.classpath" />
- <pathelement location="${basedir}/src/config" />
- </path>
-
- <target name="init-tasks">
- <taskdef name="ivy-retrieve"
- classname="fr.jayasoft.ivy.ant.IvyRetrieve"
- classpathref="project.taskjars"/>
- <taskdef name="ivy-configure"
- classname="fr.jayasoft.ivy.ant.IvyConfigure"
- classpathref="project.taskjars"/>
- <taskdef name="ivy-resolve"
- classname="fr.jayasoft.ivy.ant.IvyResolve"
- classpathref="project.taskjars"/>
- <taskdef name="ivy-publish"
- classname="fr.jayasoft.ivy.ant.IvyPublish"
- classpathref="project.taskjars"/>
- <taskdef resource="checkstyletask.properties">
- <classpath>
- <pathelement path="${java.task.lib.dir}/checkstyle-4.1.jar" />
- <pathelement path="${java.task.lib.dir}/commons-beanutils-1.7.0.jar" />
- <pathelement path="${java.task.lib.dir}/commons-logging-1.0.4.jar" />
- <pathelement path="${java.task.lib.dir}/antlr-2.7.6.jar" />
- <pathelement path="${java.task.lib.dir}/regexp-1.3.jar" />
- </classpath>
- </taskdef>
- <taskdef resource="emma_ant.properties" classpathref="project.taskjars" />
- <taskdef resource="net/sf/antcontrib/antlib.xml">
- <classpath>
- <pathelement location="${java.task.lib.dir}/ant-contrib-1.0.jar"/>
- </classpath>
- </taskdef>
- </target>
-
- <target name="check-testcase-name" if="testcase" depends="init-tasks">
- <propertyregex property="valid.testcase"
- input="${testcase}"
- regexp="(.*)Test$"
- select="\1"
- casesensitive="true" />
- </target>
-
- <target name="check-testcase" depends="check-testcase-name" if="testcase"
- unless="valid.testcase">
- <fail message="Invalid testcase name: ${testcase}. Class name must look like .*Test"/>
- </target>
-
- <target name="test" depends="compile, check-testcase"
- description="Run the tests (use -Dtestcase=<testcase>)">
- <mkdir dir="${report.dir}" />
- <!-- set testcase to wildcard "*" to test everything, unless
- a specific testcase name was supplied. -->
- <if>
- <not>
- <isset property="${testcase}" />
- </not>
- <then>
- <property name="testcase" value="*Test"/>
- </then>
- </if>
- <junit>
- <sysproperty key="rhn.config.dir" value="/etc/rhn" />
- <sysproperty key="search.config.dir" value="src/config/search" />
- <sysproperty key="log4j.configuration" value="log4j.test.properties" />
- <classpath refid="test.classpath" />
- <formatter type="brief" usefile="false" />
- <formatter type="xml" />
- <batchtest fork="yes" todir="${report.dir}">
- <fileset dir="${build.dir}" includes="**/${testcase}.class" />
- </batchtest>
- </junit>
- </target>
-
- <target name="checkstyle" depends="init-tasks, package">
- <delete dir="${report.dir}" />
- <mkdir dir="${report.dir}" />
- <checkstyle config="checkstyle.xml" failOnViolation="true" >
- <property key="javadoc.method.scope" value="public" />
- <property key="javadoc.type.scope" value="package" />
- <property key="javadoc.var.scope" value="package" />
- <property key="javadoc.lazy" value="${javadoc.lazy}" />
- <fileset dir="${java.src.dir}" >
- <include name="**/*.java" />
- <exclude name="**/tests/**" />
- </fileset>
- <classpath>
- <fileset dir="${java.lib.dir}" includes="**/*.jar" />
- <fileset dir="${java.task.lib.dir}" includes="junit*.jar" />
- <fileset dir="${dist.dir}" includes="${jar.file.name}" />
- </classpath>
- <formatter type="plain" />
- <formatter type="xml" toFile="${report.dir}/checkstyle_report.xml" />
- </checkstyle>
- </target>
-
- <target name="resolve-local" description="resolve jars via jpackage" if="installbuild">
- <copy toDir="${java.lib.dir}" overwrite="true">
- <fileset dir="buildconf/tempjars">
- <include name="**/*.jar" />
- </fileset>
- </copy>
-
- <jpackage-deps jars="${jpackage.jars}" dir="${java.lib.dir}" />
- </target>
-
- <target name="resolve-ivy" description="retrieve dependencies with ivy"
- depends="init-tasks" unless="installbuild">
- <!-- properties set here to show we are overriding default ivy values -->
- <property name="ivy.default.ivy.user.dir" value="${user.home}/.ivy/search-server"/>
- <property name="ivy.local.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
- <property name="ivy.ivyrep.default.ivy.root" value="${ivyserver}/ivy/" />
- <property name="ivy.ivyrep.default.artifact.root" value="${ivyserver}/ivy/" />
- <property name="ivy.ivyrep.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
- <ivy-retrieve/>
- </target>
-
- <target name="resolve" depends="resolve-ivy,resolve-local" />
-
- <target name="prep">
- <mkdir dir="${build.dir}" />
- <mkdir dir="${dist.dir}" />
- <mkdir dir="${java.lib.dir}" />
- </target>
-
- <target name="clean">
- <delete dir="${build.dir}" />
- <delete dir="${build.instrument.dir}" />
- <delete dir="${dist.dir}" />
- <delete dir="${java.lib.dir}" />
- <delete dir="${report.dir}" />
- <delete file="coverage.ec" />
- <delete file="rhn_search_daemon.log" />
- </target>
-
- <target name="compile" depends="prep, resolve">
- <javac srcdir="${java.src.dir}"
- classpathref="project.classpath"
- destdir="${build.dir}"
- deprecation="on"
- excludesfile="buildconf/exclude"
- debug="on" />
- <copy todir="${build.dir}/com/redhat/satellite/search/db">
- <fileset dir="${config.src.dir}/com/redhat/satellite/search/db/">
- <include name="*.xml" />
- </fileset>
- </copy>
- <copy file="${config.src.dir}/log4j.properties" todir="${build.dir}" />
- </target>
-
- <target name="package" depends="compile">
- <jar basedir="${build.dir}"
- destfile="${dist.dir}/${jar.file.name}"
- excludes="**/tests/**"
- includes="**/**" />
- </target>
-
- <target name="create-local-repo" description="Create a local Ivy repo">
- <mkdir dir="${user.home}/.ivy/search-server/local/" />
- </target>
-
- <target name="clean-cache" description="Removes the Ivy jar cache">
- <delete dir="${lib.dir}" quiet="true" />
- <delete dir="${user.home}/.ivy/search-server/cache/" quiet="true" />
- </target>
-
- <target name="all" depends="package" />
-
- <target name="init-install">
- <property name="installbuild" value="true"/>
- </target>
-
- <target name="install" depends="init-install,package" />
-
- <target name="instrument" depends="init-tasks">
- <mkdir dir="${report.dir}" />
- <mkdir dir="${build.instrument.dir}" />
-
- <emma enabled="true">
- <instr merge="no"
- mode="overwrite"
- instrpath="${build.dir}"
- outfile="${report.dir}/coverage.em" >
- <filter excludes="*Exception" />
- <filter excludes="*.tests.*" />
- </instr>
- <!--
- <instr outdir="${build.instrument.dir}" merge="no"
- instrpath="${build.dir}"
- mode="fullcopy"
- outfile="${report.dir}/coverage.em" >
- <filter excludes="*Exception" />
- <filter excludes="*.tests.*" />
- </instr>
- -->
- </emma>
-
- <!--
- <copy toDir="${build.instrument.dir}/classes">
- <fileset dir="${build.dir}">
- <include name="**/*.xml" />
- </fileset>
- </copy>
- -->
- </target>
-
- <target name="coverage-report" depends="instrument">
- <emma enabled="true">
- <report sourcepath="${java.src.dir}"
- sort="+block,+name,+method,+class"
- metrics="method:70,block:80,line:80,class:100">
- <fileset dir="${report.dir}" includes="*.em" />
- <fileset dir="." includes="*.ec" />
- <html outfile="${report.dir}/emma.html"
- depth="method"
- columns="name,class,method,block,line" />
- <xml outfile="${report.dir}/emma.xml"
- depth="method"
- columns="name,class,method,block,line" />
- </report>
- </emma>
- </target>
-</project>
diff --git a/search-server/buildconf/LICENSE.txt b/search-server/buildconf/LICENSE.txt
deleted file mode 100644
index 629462a..0000000
--- a/search-server/buildconf/LICENSE.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-/**
- * Copyright (c) 2008 Red Hat, Inc.
- *
- * This software is licensed to you under the GNU General Public License,
- * version 2 (GPLv2). There is NO WARRANTY for this software, express or
- * implied, including the implied warranties of MERCHANTABILITY or FITNESS
- * FOR A PARTICULAR PURPOSE. You should have received a copy of GPLv2
- * along with this software; if not, see
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt .
- *
- * Red Hat trademarks are not licensed under GPLv2. No permission is
- * granted to use or replicate Red Hat trademarks that are incorporated
- * in this software or its documentation.
- */
diff --git a/search-server/buildconf/build-utils.xml b/search-server/buildconf/build-utils.xml
deleted file mode 100644
index 0011a83..0000000
--- a/search-server/buildconf/build-utils.xml
+++ /dev/null
@@ -1,19 +0,0 @@
-<project name="build-utils.xml">
- <!--
- creates symlinks for jpackage jars
- requires: jpackage-utils
- other: requires rpms of the jars specified to be installed
- -->
- <macrodef name="jpackage-deps">
- <attribute name="jars" />
- <attribute name="dir" />
-
- <sequential>
- <exec executable="build-jar-repository" failonerror="true" >
- <arg value="--preserve-naming" />
- <arg value="-s @{dir}" />
- <arg line="@{jars}" />
- </exec>
- </sequential>
- </macrodef>
-</project>
diff --git a/search-server/buildconf/exclude b/search-server/buildconf/exclude
deleted file mode 100644
index 7873251..0000000
--- a/search-server/buildconf/exclude
+++ /dev/null
@@ -1,2 +0,0 @@
-**/WebCrawl.java
-**/IndexDocumentsTask.java
diff --git a/search-server/buildconf/tempjars/hadoop-0.18.1-core.jar b/search-server/buildconf/tempjars/hadoop-0.18.1-core.jar
deleted file mode 100644
index a024c3c..0000000
Binary files a/search-server/buildconf/tempjars/hadoop-0.18.1-core.jar and /dev/null differ
diff --git a/search-server/buildconf/tempjars/ibatis-2.3.0.677.jar b/search-server/buildconf/tempjars/ibatis-2.3.0.677.jar
deleted file mode 100644
index 72dbe19..0000000
Binary files a/search-server/buildconf/tempjars/ibatis-2.3.0.677.jar and /dev/null differ
diff --git a/search-server/buildconf/tempjars/lucene-analyzers-2.3.2.jar b/search-server/buildconf/tempjars/lucene-analyzers-2.3.2.jar
deleted file mode 100644
index cf0d296..0000000
Binary files a/search-server/buildconf/tempjars/lucene-analyzers-2.3.2.jar and /dev/null differ
diff --git a/search-server/buildconf/tempjars/lucene-core-2.3.2.jar b/search-server/buildconf/tempjars/lucene-core-2.3.2.jar
deleted file mode 100644
index 639f750..0000000
Binary files a/search-server/buildconf/tempjars/lucene-core-2.3.2.jar and /dev/null differ
diff --git a/search-server/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar b/search-server/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar
deleted file mode 100644
index 4bdec09..0000000
Binary files a/search-server/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar and /dev/null differ
diff --git a/search-server/buildconf/tempjars/picocontainer-1.3.jar b/search-server/buildconf/tempjars/picocontainer-1.3.jar
deleted file mode 100644
index 9a3f670..0000000
Binary files a/search-server/buildconf/tempjars/picocontainer-1.3.jar and /dev/null differ
diff --git a/search-server/buildconf/tempjars/simple-core-3.1.3.jar b/search-server/buildconf/tempjars/simple-core-3.1.3.jar
deleted file mode 100644
index 80b44c1..0000000
Binary files a/search-server/buildconf/tempjars/simple-core-3.1.3.jar and /dev/null differ
diff --git a/search-server/checkstyle.xml b/search-server/checkstyle.xml
deleted file mode 100644
index 89cde80..0000000
--- a/search-server/checkstyle.xml
+++ /dev/null
@@ -1,233 +0,0 @@
-<?xml version="1.0"?>
-<!DOCTYPE module PUBLIC
- "-//Puppy Crawl//DTD Check Configuration 1.1//EN"
- "http://www.puppycrawl.com/dtds/configuration_1_1.dtd ">
-
-<!--
-
- Checkstyle configuration that checks the sun coding conventions from:
-
- - the Java Language Specification at
- http://java.sun.com/docs/books/jls/second_edition/html/index.html
-
- - the Sun Code Conventions at http://java.sun.com/docs/codeconv/
-
- - the Javadoc guidelines at
- http://java.sun.com/j2se/javadoc/writingdoccomments/index.html
-
- - the JDK Api documentation http://java.sun.com/j2se/docs/api/index.html
-
- - some best practices
-
- Checkstyle is very configurable. Be sure to read the documentation at
- http://checkstyle.sf.net (or in your downloaded distribution).
-
- Most Checks are configurable, be sure to consult the documentation.
-
- To completely disable a check, just comment it out or delete it from the file.
-
- Finally, it is worth reading the documentation.
-
--->
-
-<module name="Checker">
-
- <!-- Checks that a package.html file exists for each package. -->
- <!-- See http://checkstyle.sf.net/config_javadoc.html#PackageHtml -->
-<!-- <module name="PackageHtml"/> -->
-
- <!-- Checks whether files end with a new line. -->
- <!-- See http://checkstyle.sf.net/config_misc.html#NewlineAtEndOfFile -->
- <module name="NewlineAtEndOfFile"/>
-
- <!-- Checks that property files contain the same keys. -->
- <!-- See http://checkstyle.sf.net/config_misc.html#Translation -->
- <module name="Translation"/>
-
- <module name="TreeWalker">
-
- <property name="cacheFile" value="${checkstyle.cache.file}"/>
-
- <!-- ************************************************************** -->
- <!-- Checks that are different from the sun coding conventions ones -->
- <!-- ************************************************************** -->
- <property name="tabWidth" value="4"/>
- <module name="LeftCurly" />
- <module name="RightCurly">
- <property name="option" value="alone"/>
- </module>
- <module name="LineLength">
- <property name="ignorePattern" value="import"/>
- <property name="max" value="92"/>
- </module>
-
- <!-- ************************************************************** -->
- <!-- Default Sun coding conventions checks -->
- <!-- ************************************************************** -->
-
- <!-- Checks for Javadoc comments. -->
- <!-- See http://checkstyle.sf.net/config_javadoc.html -->
- <module name="JavadocMethod">
- <property name="scope" value="${javadoc.method.scope}" />
- <property name="allowUndeclaredRTE" value="true" />
- <property name="allowThrowsTagsForSubclasses" value="${javadoc.lazy}" />
- <property name="allowMissingParamTags" value="${javadoc.lazy}" />
- <property name="allowMissingThrowsTags" value="${javadoc.lazy}" />
- <property name="allowMissingReturnTag" value="${javadoc.lazy}" />
- </module>
- <module name="JavadocType">
- <property name="versionFormat" value="\$Rev.*\$"/>
- <property name="scope" value="${javadoc.type.scope}" />
- </module>
- <module name="JavadocVariable">
- <property name="scope" value="${javadoc.var.scope}" />
- <property name="severity" value="ignore"/>
- </module>
-
-<!-- JavadocStyle not supported by some versions. -->
-<!-- <module name="JavadocStyle"/> -->
-
-
- <!-- Checks for Naming Conventions. -->
- <!-- See http://checkstyle.sf.net/config_naming.html -->
- <module name="ConstantName"/>
- <module name="LocalFinalVariableName"/>
- <module name="LocalVariableName"/>
- <module name="MethodName"/>
- <module name="PackageName">
- <property name="format" value="^[a-z]+(\.[A-Za-z][A-Za-z0-9]*)*$"/>
- </module>
- <module name="ParameterName"/>
- <module name="StaticVariableName"/>
- <module name="TypeName"/>
-
-
- <!-- Checks for Headers -->
- <!-- See http://checkstyle.sf.net/config_header.html -->
- <module name="Header">
- <!-- The follow property value demonstrates the ability -->
- <!-- to have access to ANT properties. In this case it uses -->
- <!-- the ${basedir} property to allow Checkstyle to be run -->
- <!-- from any directory within a project. -->
- <property name="headerFile" value="${checkstyle.header.file}"/>
- </module>
-
- <!-- Following interprets the header file as regular expressions. -->
- <!-- <module name="RegexpHeader"/> -->
-
-
-
- <!-- Checks for imports -->
- <!-- See http://checkstyle.sf.net/config_import.html -->
- <module name="AvoidStarImport"/>
- <module name="IllegalImport"/> <!-- defaults to sun.* packages -->
- <module name="RedundantImport"/>
- <module name="UnusedImports"/>
-
-
- <!-- Checks for Size Violations. -->
- <!-- See http://checkstyle.sf.net/config_sizes.html -->
- <module name="MethodLength">
- <property name="tokens" value="METHOD_DEF"/>
- <property name="max" value="150"/>
- <property name="countEmpty" value="false"/>
- </module>
- <module name="ParameterNumber"/>
-
-
- <!-- Checks for whitespace -->
- <!-- See http://checkstyle.sf.net/config_whitespace.html -->
- <module name="EmptyForIteratorPad"/>
- <module name="NoWhitespaceAfter">
- <property name="tokens" value="BNOT, DEC, DOT, INC, LNOT, UNARY_MINUS, UNARY_PLUS, TYPECAST, GENERIC_START"/>
- </module>
- <module name="NoWhitespaceBefore">
- <property name="tokens" value="SEMI, POST_DEC, POST_INC, GENERIC_START, GENERIC_END"/>
- </module>
- <module name="OperatorWrap">
- <property name="option" value="eol" />
- </module>
- <module name="ParenPad"/>
-<!-- <module name="TypecastParenPad"/> -->
- <module name="TabCharacter"/>
- <module name="WhitespaceAfter">
- <property name="tokens" value="COMMA, SEMI, GENERIC_END"/>
- </module>
- <module name="WhitespaceAround">
- <property name="tokens" value="ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN, BXOR, BXOR_ASSIGN,
-COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LCURLY, LE, LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
-LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE, LOR, LT, MINUS,
-MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL, PLUS, PLUS_ASSIGN, QUESTION, RCURLY, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN, STAR, STAR_ASSIGN, TYPE_EXTENSION_AND, WILDCARD_TYPE"/>
- </module>
- <module name="MethodParamPad">
- <property name="allowLineBreaks" value="true"/>
- </module>
-
-
- <!-- Modifier Checks -->
- <!-- See http://checkstyle.sf.net/config_modifiers.html -->
- <module name="ModifierOrder"/>
- <module name="RedundantModifier"/>
-
-
- <!-- Checks for blocks. You know, those {}'s -->
- <!-- See http://checkstyle.sf.net/config_blocks.html -->
- <module name="AvoidNestedBlocks"/>
- <module name="EmptyBlock">
- <property name="option" value="text"/>
- </module>
-
- <module name="NeedBraces"/>
-
-
- <!-- Checks for common coding problems -->
- <!-- See http://checkstyle.sf.net/config_coding.html -->
- <!-- <module name="AvoidInlineConditionals"/> -->
-<!-- <module name="CovariantEquals"/> -->
- <module name="DoubleCheckedLocking"/> <!-- MY FAVOURITE -->
- <module name="EmptyStatement"/>
- <module name="EqualsHashCode"/>
- <module name="HiddenField"/>
- <module name="IllegalInstantiation"/>
- <module name="InnerAssignment"/>
- <!-- <module name="MagicNumber" /> -->
- <module name="MissingSwitchDefault"/>
-<!-- <module name="RedundantThrows"/> -->
- <module name="SimplifyBooleanExpression"/>
- <module name="SimplifyBooleanReturn"/>
-<!-- <module name="IllegalCatch"/> -->
-<!-- <module name="PackageDeclaration"/> -->
-
- <!-- Checks for class design -->
- <!-- See http://checkstyle.sf.net/config_design.html -->
-<!-- <module name="DesignForExtension"/>-->
-<!-- <module name="FinalClass"/> -->
- <module name="HideUtilityClassConstructor"/>
- <module name="InterfaceIsType"/>
- <module name="VisibilityModifier">
- <property name="protectedAllowed" value="true" />
- </module>
-
-
- <!-- Miscellaneous other checks. -->
- <!-- See http://checkstyle.sf.net/config_misc.html -->
- <module name="ArrayTypeStyle"/>
-<!-- <module name="FinalParameters"/> -->
-<!--
- <module name="GenericIllegalRegexp">
- <property name="format" value="System\.out\.println"/>
- </module>
--->
- <module name="UpperEll"/>
-
- <!-- Optional Checks -->
- <!-- (gack, not available until version 3 of checkstyle -->
-<!--
- <module name="usage.OneMethodPrivateField"/>
- <module name="usage.UnusedLocalVariable"/>
- <module name="usage.UnusedParameter"/>
- <module name="usage.UnusedPrivateField"/>
--->
- </module>
-
-</module>
diff --git a/search-server/ivy.xml b/search-server/ivy.xml
deleted file mode 100644
index aec44ca..0000000
--- a/search-server/ivy.xml
+++ /dev/null
@@ -1,28 +0,0 @@
-<ivy-module version="1.0">
- <info organisation="redhat" module="rhn-java" />
- <dependencies>
- <dependency org="redhat" name="simple-core" rev="3.1.3" />
- <dependency org="redhat" name="lucene-core" rev="2.3.2" />
- <dependency org="redhat" name="lucene-analyzers" rev="2.3.2" />
- <dependency org="redhat" name="commons-lang" rev="2.0" />
- <dependency org="redhat" name="commons-logging" rev="1.1" />
- <dependency org="redhat" name="redstone-xmlrpc" rev="1.1_20071120" />
- <dependency org="redhat" name="redstone-xmlrpc-client" rev="1.1_20071120" />
- <dependency org="redhat" name="ibatis" rev="2.3.0.677" />
- <dependency org="redhat" name="ojdbc14" rev="1.10" />
- <dependency org="redhat" name="quartz" rev="1.5.1" />
- <dependency org="redhat" name="picocontainer" rev="1.3" />
- <dependency org="redhat" name="tanukiwrapper" rev="3.1.2" />
- <dependency org="redhat" name="log4j" rev="1.2.8" />
- <dependency org="redhat" name="logdriver" rev="0.1" />
- <dependency org="redhat" name="nutch" rev="2008-12-01_04-01-21" />
- <dependency org="redhat" name="hadoop" rev="0.18.1-core" />
- <!-- dependency org="redhat" name="commons-httpclient" rev="3.0" / -->
- <!-- dependency org="redhat" name="oro" rev="2.0.8" / -->
- <!-- dependency org="redhat" name="commons-cli" rev="1.0" / -->
- <!-- dependency org="redhat" name="commons-codec" rev="1.2" / -->
- <!-- dependency org="redhat" name="tika" rev="0.1-incubating" / -->
- <!-- dependency org="redhat" name="icu4j" rev="3_8_1" / -->
- <!-- dependency org="redhat" name="icu4j-charsets" rev="3_8_1" / -->
- </dependencies>
-</ivy-module>
diff --git a/search-server/libsrc/hadoop-0.16.4-src.jar b/search-server/libsrc/hadoop-0.16.4-src.jar
deleted file mode 100644
index c941a7c..0000000
Binary files a/search-server/libsrc/hadoop-0.16.4-src.jar and /dev/null differ
diff --git a/search-server/libsrc/ibatis-2.3.0.677-src.zip b/search-server/libsrc/ibatis-2.3.0.677-src.zip
deleted file mode 100644
index 8c3274b..0000000
Binary files a/search-server/libsrc/ibatis-2.3.0.677-src.zip and /dev/null differ
diff --git a/search-server/libsrc/icu4j-3_8_1-src.jar b/search-server/libsrc/icu4j-3_8_1-src.jar
deleted file mode 100644
index 19dd665..0000000
Binary files a/search-server/libsrc/icu4j-3_8_1-src.jar and /dev/null differ
diff --git a/search-server/libsrc/log4j-1.2.8-src.jar b/search-server/libsrc/log4j-1.2.8-src.jar
deleted file mode 100644
index b36df55..0000000
Binary files a/search-server/libsrc/log4j-1.2.8-src.jar and /dev/null differ
diff --git a/search-server/libsrc/lucene-2.3.2-src.zip b/search-server/libsrc/lucene-2.3.2-src.zip
deleted file mode 100644
index b49b9b6..0000000
Binary files a/search-server/libsrc/lucene-2.3.2-src.zip and /dev/null differ
diff --git a/search-server/libsrc/nutch-1.0dev_2008_05_14-src.jar b/search-server/libsrc/nutch-1.0dev_2008_05_14-src.jar
deleted file mode 100644
index 372eca5..0000000
Binary files a/search-server/libsrc/nutch-1.0dev_2008_05_14-src.jar and /dev/null differ
diff --git a/search-server/libsrc/nutch-2008-12-01_04-01-21-src.zip b/search-server/libsrc/nutch-2008-12-01_04-01-21-src.zip
deleted file mode 100644
index 268a010..0000000
Binary files a/search-server/libsrc/nutch-2008-12-01_04-01-21-src.zip and /dev/null differ
diff --git a/search-server/libsrc/quartz-1.5.1-src.jar b/search-server/libsrc/quartz-1.5.1-src.jar
deleted file mode 100644
index 79edf1a..0000000
Binary files a/search-server/libsrc/quartz-1.5.1-src.jar and /dev/null differ
diff --git a/search-server/libsrc/redstone-xmlrpc-1.1_20071120-src.jar b/search-server/libsrc/redstone-xmlrpc-1.1_20071120-src.jar
deleted file mode 100644
index 2dc7cf7..0000000
Binary files a/search-server/libsrc/redstone-xmlrpc-1.1_20071120-src.jar and /dev/null differ
diff --git a/search-server/libsrc/simple-3.1.3-src.zip b/search-server/libsrc/simple-3.1.3-src.zip
deleted file mode 100644
index cdd83c6..0000000
Binary files a/search-server/libsrc/simple-3.1.3-src.zip and /dev/null differ
diff --git a/search-server/libsrc/tanukiwrapper-3.1.2-src.jar b/search-server/libsrc/tanukiwrapper-3.1.2-src.jar
deleted file mode 100644
index 9436fbd..0000000
Binary files a/search-server/libsrc/tanukiwrapper-3.1.2-src.jar and /dev/null differ
diff --git a/search-server/nutch/crawl_jsp.sh b/search-server/nutch/crawl_jsp.sh
deleted file mode 100755
index d7a7e19..0000000
--- a/search-server/nutch/crawl_jsp.sh
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/bin/bash
-
-
-if [ "${JAVA_HOME}" = "" ]; then
- export JAVA_HOME=/usr/lib/jvm/java
- echo "Setting JAVA_HOME to: ${JAVA_HOME}"
-fi
-
-export NUTCH_HOME=/usr/share/nutch
-export NUTCH_CONF_DIR=`pwd`/crawl_jsp/conf
-export NUTCH_OPTS=-Djava.util.logging.config.file="${NUTCH_CONF}/logging.properties"
-export NUTCH_LOG_DIR=`pwd`/logs
-export NUTCH_LOG_FILE=$0.log
-export OUTPUT_DIR=`pwd`/data/crawl_jsp
-
-echo "NUTCH_HOME = ${NUTCH_HOME}"
-echo "NUTCH_CONF_DIR = ${NUTCH_CONF_DIR}"
-echo "NUTCH_OPTS = ${NUTCH_OPTS}"
-echo "NUTCH_LOG_DIR = ${NUTCH_LOG_DIR}"
-echo "NUTCH_LOG_FILE = ${NUTCH_LOG_FILE}"
-echo "OUTPUT_DIR = ${OUTPUT_DIR}"
-
-if [ ! -d ${NUTCH_LOG_DIR} ]; then
- echo "Creating log directory ${NUTCH_LOG_DIR}"
- mkdir ${NUTCH_LOG_DIR}
-fi
-
-
-if [ ! -d ${OUTPUT_DIR} ]; then
- echo "Creating output directory ${OUTPUT_DIR}"
- mkdir -p ${OUTPUT_DIR}
-fi
-#Need to adjust nutch RPM so it's scripts under bin are executable by all
-
-${NUTCH_HOME}/bin/nutch crawl ${NUTCH_CONF_DIR}/../urls -dir ${OUTPUT_DIR} -depth 10 -threads 50
diff --git a/search-server/nutch/crawl_jsp/conf/automaton-urlfilter.txt b/search-server/nutch/crawl_jsp/conf/automaton-urlfilter.txt
deleted file mode 100644
index 84cf8fa..0000000
--- a/search-server/nutch/crawl_jsp/conf/automaton-urlfilter.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# The default url filter.
-# Better for whole-internet crawling.
-
-# Each non-comment, non-blank line contains a regular expression
-# prefixed by '+' or '-'. The first matching pattern in the file
-# determines whether a URL is included or ignored. If no pattern
-# matches, the URL is ignored.
-
-# skip file: ftp: and mailto: urls
--(file|ftp|mailto):.*
-
-# skip image and other suffixes we can't yet parse
--.*\.(gif|GIF|jpg|JPG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe)
-
-# skip URLs containing certain characters as probable queries, etc.
--.*[?*!(a)=].*
-
-# accept anything else
-+.*
diff --git a/search-server/nutch/crawl_jsp/conf/common-terms.utf8 b/search-server/nutch/crawl_jsp/conf/common-terms.utf8
deleted file mode 100644
index 220d1da..0000000
--- a/search-server/nutch/crawl_jsp/conf/common-terms.utf8
+++ /dev/null
@@ -1,28 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Common terms and phrases which will be indexed in n-grams
-# in order to optimize search.
-content:a
-content:and
-content:for
-content:in
-content:of
-content:the
-content:to
-url:com
-url:http
-url:http-www
-url:www
diff --git a/search-server/nutch/crawl_jsp/conf/configuration.xsl b/search-server/nutch/crawl_jsp/conf/configuration.xsl
deleted file mode 100644
index 79141dc..0000000
--- a/search-server/nutch/crawl_jsp/conf/configuration.xsl
+++ /dev/null
@@ -1,40 +0,0 @@
-<?xml version="1.0"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform " version="1.0">
-<xsl:output method="html"/>
-<xsl:template match="configuration">
-<html>
-<body>
-<table border="1">
-<tr>
- <td>name</td>
- <td>value</td>
- <td>description</td>
-</tr>
-<xsl:for-each select="property">
-<tr>
- <td><a name="{name}"><xsl:value-of select="name"/></a></td>
- <td><xsl:value-of select="value"/></td>
- <td><xsl:value-of select="description"/></td>
-</tr>
-</xsl:for-each>
-</table>
-</body>
-</html>
-</xsl:template>
-</xsl:stylesheet>
diff --git a/search-server/nutch/crawl_jsp/conf/context.xsl b/search-server/nutch/crawl_jsp/conf/context.xsl
deleted file mode 100644
index fbb3bc6..0000000
--- a/search-server/nutch/crawl_jsp/conf/context.xsl
+++ /dev/null
@@ -1,88 +0,0 @@
-<?xml version="1.0" encoding="ISO-8859-1"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
-
- Author : Chris Mattmann
- Auhtor : Jérôme Charron
- Description: This xsl file is used to transform dynamic properties out of the
- nutch-default.xml file into a deployable Context.xml file for configuring
- the Nutch war file in a servlet container.
--->
-
-<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform ">
-
-<xsl:template match="/">
-<Context path="/nutch" docBase="nutch-0.9-dev.war"
- debug="5" reloadable="true" crossContext="true">
-
-<xsl:for-each select="configuration/property">
-
-<!-- "searcher." properties -->
-<xsl:call-template name="parameter">
- <xsl:with-param name="property" select="current()"/>
- <xsl:with-param name="filter" select="'searcher.'"/>
-</xsl:call-template>
-
-<!-- "plugin." properties -->
-<xsl:call-template name="parameter">
- <xsl:with-param name="property" select="current()"/>
- <xsl:with-param name="filter" select="'plugin.'"/>
-</xsl:call-template>
-
-<!-- "extension.clustering." properties -->
-<xsl:call-template name="parameter">
- <xsl:with-param name="property" select="current()"/>
- <xsl:with-param name="filter" select="'extension.clustering.'"/>
-</xsl:call-template>
-
-<!-- "extension.ontology." properties -->
-<xsl:call-template name="parameter">
- <xsl:with-param name="property" select="current()"/>
- <xsl:with-param name="filter" select="'extension.ontology.'"/>
-</xsl:call-template>
-
-<!-- "query." properties -->
-<xsl:call-template name="parameter">
- <xsl:with-param name="property" select="current()"/>
- <xsl:with-param name="filter" select="'query.'"/>
-</xsl:call-template>
-
-</xsl:for-each>
-
-</Context>
-</xsl:template>
-
-
-<!--
- ! Template used to write out a parameter if the property's
- ! name contains the specified filter string.
- !-->
-<xsl:template name="parameter">
- <xsl:param name="property"/>
- <xsl:param name="filter"/>
- <xsl:if test="contains(name, $filter)">
- <Parameter override="false">
- <xsl:attribute name="name">
- <xsl:value-of select="name"/>
- </xsl:attribute>
- <xsl:attribute name="value">
- <xsl:value-of select="value"/>
- </xsl:attribute>
- </Parameter>
- </xsl:if>
-</xsl:template>
-
-</xsl:stylesheet>
diff --git a/search-server/nutch/crawl_jsp/conf/crawl-tool.xml b/search-server/nutch/crawl_jsp/conf/crawl-tool.xml
deleted file mode 100644
index 9f6d667..0000000
--- a/search-server/nutch/crawl_jsp/conf/crawl-tool.xml
+++ /dev/null
@@ -1,59 +0,0 @@
-<?xml version="1.0" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
-
-<!-- Overidden defaults for intranet use. -->
-
-<!-- Do not modify this file directly. Instead, copy entries that you -->
-<!-- wish to modify from this file into nutch-site.xml and change them -->
-<!-- there. If nutch-site.xml does not already exist, create it. -->
-
-<configuration>
-
-<property>
- <name>urlfilter.regex.file</name>
- <value>crawl-urlfilter.txt</value>
-</property>
-
-<property>
- <name>db.ignore.internal.links</name>
- <value>false</value>
- <description>If true, when adding new links to a page, links from
- the same host are ignored. This is an effective way to limit the
- size of the link database, keeping the only the highest quality
- links.
- </description>
-</property>
-
-<property>
- <name>fetcher.server.delay</name>
- <value>1.0</value>
- <description>The number of seconds the fetcher will delay between
- successive requests to the same server.</description>
-</property>
-
-<property>
- <name>http.max.delays</name>
- <value>1000</value>
- <description>The number of times a thread will delay when trying to
- fetch a page. When using the crawl tool there are likely to be very
- few different hosts, so we need to be willing to wait longer for
- each.</description>
-</property>
-
-</configuration>
diff --git a/search-server/nutch/crawl_jsp/conf/crawl-urlfilter.txt b/search-server/nutch/crawl_jsp/conf/crawl-urlfilter.txt
deleted file mode 100644
index 2698c17..0000000
--- a/search-server/nutch/crawl_jsp/conf/crawl-urlfilter.txt
+++ /dev/null
@@ -1,61 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-
-# The url filter file used by the crawl command.
-
-# Better for intranet crawling.
-# Be sure to change MY.DOMAIN.NAME to your domain name.
-
-# Each non-comment, non-blank line contains a regular expression
-# prefixed by '+' or '-'. The first matching pattern in the file
-# determines whether a URL is included or ignored. If no pattern
-# matches, the URL is ignored.
-
-# skip file:, ftp:, & mailto: urls
-#-^(file|ftp|mailto):
--^(http|ftp|mailto):
-
-# skip image and other suffixes we can't yet parse
--\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP|pdf)$
-
-# skip URLs containing certain characters as probable queries, etc.
--[?*!@=]
-
-# skip URLs with slash-delimited segment that repeats 3+ times, to break loops
--.*(/[^/]+)/[^/]+\1/[^/]+\1/
-
-# accept hosts in MY.DOMAIN.NAME
-#+^http://([a-z0-9]*\.)*MY.DOMAIN.NAME/
-#+^http://([a-z0-9]*\.)*redhat.com/
-
-# skip everything else
-#-
-
-
-#accept everything else
-#+.*
-
-#ingore all svn entries
--.*\.svn
-#only read in english docs from these locations
-+.*/docs/guides/channel-mgmt/en/
-+.*/docs/guides/client-config/en/
-+.*/docs/guides/proxy/rhn511/en/
-+.*/docs/release-notes/satellite/rhn510/en-US/
-+.*/docs/guides/satellite/en/
-+.*/docs/guides/reference/en/
-#skip everything else
--.*
diff --git a/search-server/nutch/crawl_jsp/conf/domain-suffixes.xml b/search-server/nutch/crawl_jsp/conf/domain-suffixes.xml
deleted file mode 100644
index 635f5a2..0000000
--- a/search-server/nutch/crawl_jsp/conf/domain-suffixes.xml
+++ /dev/null
@@ -1,4354 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- Document : domain-suffixes.xml
- Author : Enis Soztutar - enis.soz.nutch(a)gmail.com
- Description: This document contains top level domains
- as described by the Internet Assigned Numbers
- Authotiry (IANA), and second or third level domains that
- are known to be managed by domain registerers. People at
- Mozilla community call these public suffixes or effective
- tlds. There is no algorithmic way of knowing whether a suffix
- is a public domain suffix, or not. So this large file is used
- for this purpose. The entries in the file is used to find the
- domain of a url, which may not the same thing as the host of
- the url. For example for "http://lucene.apache.org/nutch " the
- hostname is lucene.apache.org , however the domain name for this
- url would be apache.org . Domain names can be quite handy for
- statistical analysis, and fighting against spam.
-
- The list of TLDs is constructed from IANA, and the
- list of "effective tlds" are constructed from Wikipedia,
- http://wiki.mozilla.org/TLD_List , and http://publicsuffix.org/
- The list may not include all the suffixes, but some
- effort has been spent to make it comprehensive. Please forward
- any improvements for this list to nutch-dev mailing list, or
- nutch JIRA.
-
- Top level domains(tlds) are grouped
- to three, namely infrastrusture, generic and country
- code tlds. Infrastrusture tlds are only used for
- technical reasons. Generic tlds represents the type
- of the organization that they represent. Those in
- current use and those waiting for approval is listed.
- Most of the country code tlds correspond to the two
- letter ISO-3166-1 country codes.
- Each tld is listed with its domain (such as com), a
- status enumeration describing the status of the tld,
- and optionally a description or description for convenience.
- cctlds are listed with additional country name field.
-
- status and boost elements are optional, with default values IN_USE
- and 1.0 respectively. see domain-suffixes.xsd for the xml schema.
-
-
- References :
- http://www.iana.org
- http://www.iana.org/gtld/gtld.htm
- http://www.iana.org/root-whois/index.html
- http://en.wikipedia.org/wiki/Top-level_domain
- http://en.wikipedia.org/wiki/List_of_Internet_top-level_domains
- http://wiki.mozilla.org/TLD_List
- http://publicsuffix.org/
- https://bugzilla.mozilla.org/show_bug.cgi?id=331510
- http://www.neuhaus.com/domaincheck/domain_list.htm
--->
-
-<domains xmlns="http://lucene.apache.org/nutch "
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance "
- xsi:schemaLocation="http://lucene.apache.org/nutch domain-suffixes.xsd">
-
- <tlds>
- <!-- Infrastructure Top Level Domains -->
- <itlds>
- <tld domain="root">
- <status>INFRASTRUCTURE</status>
- <description>
- (from http://en.wikipedia.org/wiki/.root )
- vrsn-end-of-zone-marker-dummy-record.root is a domain name
- listed in the DNS root zone as a diagnostic marker, whose
- presence demonstrates the root zone was not truncated upon
- loading by a root nameserver. It could be argued it represents
- a top-level domain of .root, although technically no such
- delegation exists.
- </description>
- </tld>
-
- <tld domain="arpa">
- <status>INFRASTRUCTURE</status>
- <description>
- (from http://en.wikipedia.org/wiki/.arpa ) .arpa is an Internet
- top-level domain (TLD) used exclusively for
- Internet-infrastructure purposes. It does not function as a
- normal TLD where websites are registered, but rather as a
- meta-TLD used to look up addresses, and for other purposes.
- </description>
- </tld>
- </itlds><!-- Generic Top Level Domains -->
- <gtlds>
- <!--
- The following gTLDs are in actual use
- -->
-
- <tld domain="aero">
- <status>SPONSORED</status>
- <description>for the air transport industry</description>
- </tld>
-
- <tld domain="biz">
- <status>UNSPONSORED</status>
- <description>for business use</description>
- </tld>
-
- <tld domain="cat">
- <status>SPONSORED</status>
- <description>for Catalan language/culture</description>
- </tld>
-
- <tld domain="com">
- <status>UNSPONSORED</status>
- <description>
- for commercial organizations, but unrestricted
- </description>
- </tld>
-
- <tld domain="coop">
- <status>SPONSORED</status>
- <description>for cooperatives</description>
- </tld>
-
- <tld domain="edu">
- <status>UNSPONSORED</status>
- <boost>1.0</boost>
- <description>
- for post-secondary educational establishments
- </description>
- </tld>
-
- <tld domain="gov">
- <status>UNSPONSORED</status>
- <description>
- for governments and their agencies in the United States
- </description>
- </tld>
-
- <tld domain="info">
- <status>UNSPONSORED</status>
- <description>
- for informational sites, but unrestricted
- </description>
- </tld>
-
- <tld domain="int">
- <status>UNSPONSORED</status>
- <description>
- for international organizations established by treaty
- </description>
- </tld>
-
- <tld domain="jobs">
- <status>SPONSORED</status>
- <description>for employment-related sites</description>
- </tld>
-
- <tld domain="mil">
- <status>UNSPONSORED</status>
- <description>for the US military</description>
- </tld>
-
- <tld domain="mobi">
- <status>SPONSORED</status>
- <description>for sites catering to mobile devices</description>
- </tld>
-
- <tld domain="museum">
- <status>SPONSORED</status>
- <description>for museums</description>
- </tld>
-
- <tld domain="name">
- <status>UNSPONSORED</status>
- <description>for families and individuals</description>
- </tld>
-
- <tld domain="net">
- <status>UNSPONSORED</status>
- <description>
- originally for network infrastructures, now unrestricted
- </description>
- </tld>
-
- <tld domain="org">
- <status>UNSPONSORED</status>
- <description>
- originally for organizations not clearly falling within the
- other gTLDs, now unrestricted
- </description>
- </tld>
-
- <tld domain="pro">
- <status>SPONSORED</status>
- <description>for certain professions</description>
- </tld>
-
- <tld domain="travel">
- <status>SPONSORED</status>
- <description>
- for travel agents, airlines, hoteliers, tourism bureaus, etc.
- </description>
- </tld>
-
- <!--
- The following gTLDs are in the process of being approved,
- and may be added to the root nameservers in the near future
- -->
-
- <tld domain="asia">
- <status>STARTUP</status>
- <description>for the Asian community</description>
- </tld>
-
- <tld domain="post">
- <status>PROPOSED</status>
- <description>for postal services</description>
- </tld>
-
- <tld domain="tel">
- <status>STARTUP</status>
- <description>
- for services involving connections between the telephone
- network and the Internet
- </description>
- </tld>
-
- <tld domain="geo">
- <status>PROPOSED</status>
- <description>for geographically related sites</description>
- </tld>
-
- <tld domain="gal">
- <status>PROPOSED</status>
- <description>for Galicia, a country within Spain</description>
- </tld>
-
- <tld domain="cym">
- <status>PROPOSED</status>
- <description>for Wales, a country within the UK</description>
- </tld>
-
- <tld domain="sco">
- <status>PROPOSED</status>
- <description>for Scotland, a country within the UK</description>
- </tld>
-
- <tld domain="kid">
- <status>PROPOSED</status>
- <description>for websites designed for children</description>
- </tld>
-
- <tld domain="kids">
- <status>PROPOSED</status>
- <description>for websites designed for children</description>
- </tld>
-
- <tld domain="mail">
- <status>PROPOSED</status>
- <description>http://en.wikipedia.org/wiki/.mail </description>
- </tld>
-
- <tld domain="web">
- <status>PROPOSED</status>
- <description>For Web sites of all sorts</description>
- </tld>
-
- <tld domain="xxx">
- <status>PROPOSED</status>
- <description>For Adult entertainment sites</description>
- </tld>
-
- <!--
- The following gTLDs are removed from the registry
- -->
- <tld domain="nato">
- <status>DELETED</status>
- <description>
- for NATO sites and operations. Replaced by .int
- </description>
- </tld>
-
- <!--
- The following gTLDs are PSEUDO_DOMAINs
- -->
- <tld domain="bitnet">
- <status>PSEUDO_DOMAIN</status>
- <description>
- identifying a hostname not connected directly to the Internet,
- but a bitnet network
- </description>
- </tld>
-
- <tld domain="csnet">
- <status>PSEUDO_DOMAIN</status>
- <description>
- identifying a hostname not connected directly to the Internet,
- but a csnet network
- </description>
- </tld>
-
- <tld domain="uucp">
- <status>PSEUDO_DOMAIN</status>
- <description>
- identifying a hostname not connected directly to the Internet,
- but a bitnet network
- </description>
- </tld>
-
- <tld domain="local">
- <status>PSEUDO_DOMAIN</status>
- <description>
- .local is a pseudo top-level domain used by Apple, Inc.'s
- Bonjour protocol.
- </description>
- </tld>
-
- <tld domain="internal">
- <status>PSEUDO_DOMAIN</status>
- <description>alias of .local</description>
- </tld>
-
- <tld domain="onion">
- <status>PSEUDO_DOMAIN</status>
- <description>
- designates an anonymous or pseudonymous address reachable via
- the Tor network.
- </description>
- </tld>
- </gtlds><!-- Country Code Top Level Domains -->
-
- <cctlds>
- <tld domain="ac">
- <country>Ascension Island</country>
- </tld>
-
- <tld domain="ad">
- <country>Andorra</country>
- </tld>
-
- <tld domain="ae">
- <country>United Arab Emirates</country>
- </tld>
-
- <tld domain="af">
- <country>Afghanistan</country>
- </tld>
-
- <tld domain="ag">
- <country>Antigua and Barbuda</country>
- </tld>
-
- <tld domain="ai">
- <country>Anguilla</country>
- </tld>
-
- <tld domain="al">
- <country>Albania</country>
- </tld>
-
- <tld domain="am">
- <country>Armenia</country>
- </tld>
-
- <tld domain="an">
- <country>Netherlands Antilles</country>
- </tld>
-
- <tld domain="ao">
- <country>Angola</country>
- </tld>
-
- <tld domain="aq">
- <country>Antarctica</country>
- </tld>
-
- <tld domain="ar">
- <country>Argentina</country>
- </tld>
-
- <tld domain="as">
- <country>American Samoa</country>
- </tld>
-
- <tld domain="at">
- <country>Austria</country>
- </tld>
-
- <tld domain="au">
- <country>Australia</country>
- </tld>
-
- <tld domain="aw">
- <country>Aruba</country>
- </tld>
-
- <tld domain="ax">
- <country>Aland Islands</country>
- </tld>
-
- <tld domain="az">
- <country>Azerbaijan</country>
- </tld>
-
- <tld domain="ba">
- <country>Bosnia and Herzegovina</country>
- </tld>
-
- <tld domain="bb">
- <country>Barbados</country>
- </tld>
-
- <tld domain="bd">
- <country>Bangladesh</country>
- </tld>
-
- <tld domain="be">
- <country>Belgium</country>
- </tld>
-
- <tld domain="bf">
- <country>Burkina Faso</country>
- </tld>
-
- <tld domain="bg">
- <country>Bulgaria</country>
- </tld>
-
- <tld domain="bh">
- <country>Bahrain</country>
- </tld>
-
- <tld domain="bi">
- <country>Burundi</country>
- </tld>
-
- <tld domain="bj">
- <country>Benin</country>
- </tld>
-
- <tld domain="bm">
- <country>Bermuda</country>
- </tld>
-
- <tld domain="bn">
- <country>Brunei</country>
- </tld>
-
- <tld domain="bo">
- <country>Bolivia</country>
- </tld>
-
- <tld domain="br">
- <country>Brazil</country>
- </tld>
-
- <tld domain="bs">
- <country>Bahamas</country>
- </tld>
-
- <tld domain="bt">
- <country>Bhutan</country>
- </tld>
-
- <tld domain="bu">
- <country>Burma</country>
- <status>NOT_IN_USE</status>
- <description>
- not in use since re-naming of country to Myanmar, see .mm
- </description>
- </tld>
-
- <tld domain="bv">
- <country>Bouvet Island</country>
- <status>NOT_IN_USE</status>
- <description>not in use; no registrations</description>
- </tld>
-
- <tld domain="bw">
- <country>Botswana</country>
- </tld>
-
- <tld domain="by">
- <country>Belarus</country>
- </tld>
-
- <tld domain="bz">
- <country>Belize</country>
- </tld>
-
- <tld domain="ca">
- <country>Canada</country>
- </tld>
-
- <tld domain="cc">
- <country>Cocos Keeling Islands</country>
- </tld>
-
- <tld domain="cd">
- <country>Democratic Republic of the Congo</country>
- <description>formerly .zr - Zaire</description>
- </tld>
-
- <tld domain="cf">
- <country>Central African Republic</country>
- </tld>
-
- <tld domain="cg">
- <country>Republic of the Congo</country>
- </tld>
-
- <tld domain="ch">
- <country>Switzerland</country>
- </tld>
-
- <tld domain="ci">
- <country>CÃŽte d'Ivoire</country>
- <description>Ivory Coast</description>
- </tld>
-
- <tld domain="ck">
- <country>Cook Islands</country>
- </tld>
-
- <tld domain="cl">
- <country>Chile</country>
- </tld>
-
- <tld domain="cm">
- <country>Cameroon</country>
- </tld>
-
- <tld domain="cn">
- <country>People s Republic of China</country>
- </tld>
-
- <tld domain="co">
- <country>Colombia</country>
- </tld>
-
- <tld domain="cr">
- <country>Costa Rica</country>
- </tld>
-
- <tld domain="cs">
- <country>Serbia and Montenegro</country>
- <status>DELETED</status>
- <description>
- formerly .yu - Yugoslavia; description: on June 3, 2006,
- Montenegro declared independence, thus dissolving the state
- union) (.cs code not assigned; no DNS) (.cs code previously
- used for Czechoslovakia
- </description>
- </tld>
-
- <tld domain="cu">
- <country>Cuba</country>
- </tld>
-
- <tld domain="cv">
- <country>Cape Verde</country>
- </tld>
-
- <tld domain="cx">
- <country>Christmas Island</country>
- </tld>
-
- <tld domain="cy">
- <country>Cyprus</country>
- </tld>
-
- <tld domain="cz">
- <country>Czech Republic</country>
- </tld>
-
- <tld domain="dd">
- <country>German Democratic Republic(East Germany)</country>
- <status>DELETED</status>
- <description>deleted in 1990</description>
- </tld>
-
- <tld domain="de">
- <country>Germany</country>
- </tld>
-
- <tld domain="dj">
- <country>Djibouti</country>
- </tld>
-
- <tld domain="dk">
- <country>Denmark</country>
- </tld>
-
- <tld domain="dm">
- <country>Dominica</country>
- </tld>
-
- <tld domain="do">
- <country>Dominican Republic</country>
- </tld>
-
- <tld domain="dz">
- <country>Algeria</country>
- </tld>
-
- <tld domain="ec">
- <country>Ecuador</country>
- </tld>
-
- <tld domain="ee">
- <country>Estonia</country>
- </tld>
-
- <tld domain="eg">
- <country>Egypt</country>
- </tld>
-
- <tld domain="eh">
- <country>Western Sahara</country>
- <status>NOT_IN_USE</status>
- <description>not assigned; no DNS</description>
- </tld>
-
- <tld domain="er">
- <country>Eritrea</country>
- </tld>
-
- <tld domain="es">
- <country>Spain</country>
- </tld>
-
- <tld domain="et">
- <country>Ethiopia</country>
- </tld>
-
- <tld domain="eu">
- <country>European Union</country>
- <description>
- code "exceptionally reserved" by ISO 3166-1
- </description>
- </tld>
-
- <tld domain="fi">
- <country>Finland</country>
- </tld>
-
- <tld domain="fj">
- <country>Fiji</country>
- </tld>
-
- <tld domain="fk">
- <country>Falkland Islands</country>
- </tld>
-
- <tld domain="fm">
- <country>Federated States of Micronesia</country>
- </tld>
-
- <tld domain="fo">
- <country>Faroe Islands</country>
- </tld>
-
- <tld domain="fr">
- <country>France</country>
- </tld>
-
- <tld domain="ga">
- <country>Gabon</country>
- </tld>
-
- <tld domain="gb">
- <country>United Kingdom</country>
- <description>
- Reserved domain by IANA; deprecated – see .uk
- </description>
- </tld>
-
- <tld domain="gd">
- <country>Grenada</country>
- </tld>
-
- <tld domain="ge">
- <country>Georgia</country>
- </tld>
-
- <tld domain="gf">
- <country>French Guiana</country>
- </tld>
-
- <tld domain="gg">
- <country>Guernsey</country>
- </tld>
-
- <tld domain="gh">
- <country>Ghana</country>
- </tld>
-
- <tld domain="gi">
- <country>Gibraltar</country>
- </tld>
-
- <tld domain="gl">
- <country>Greenland</country>
- </tld>
-
- <tld domain="gm">
- <country>Gambia</country>
- </tld>
-
- <tld domain="gn">
- <country>Guinea</country>
- </tld>
-
- <tld domain="gp">
- <country>Guadeloupe</country>
- </tld>
-
- <tld domain="gq">
- <country>Equatorial Guinea</country>
- </tld>
-
- <tld domain="gr">
- <country>Greece</country>
- </tld>
-
- <tld domain="gs">
- <country>South Georgia and the South Sandwich Islands</country>
- </tld>
-
- <tld domain="gt">
- <country>Guatemala</country>
- </tld>
-
- <tld domain="gu">
- <country>Guam</country>
- </tld>
-
- <tld domain="gw">
- <country>Guinea Bissau</country>
- </tld>
-
- <tld domain="gy">
- <country>Guyana</country>
- </tld>
-
- <tld domain="hk">
- <country>Hong Kong</country>
- </tld>
-
- <tld domain="hm">
- <country>Heard Island and McDonald Islands</country>
- </tld>
-
- <tld domain="hn">
- <country>Honduras</country>
- </tld>
-
- <tld domain="hr">
- <country>Croatia</country>
- </tld>
-
- <tld domain="ht">
- <country>Haiti</country>
- </tld>
-
- <tld domain="hu">
- <country>Hungary</country>
- </tld>
-
- <tld domain="id">
- <country>Indonesia</country>
- </tld>
-
- <tld domain="ie">
- <country>Ireland</country>
- </tld>
-
- <tld domain="il">
- <country>Israel</country>
- </tld>
-
- <tld domain="im">
- <country>Isle of Man</country>
- </tld>
-
- <tld domain="in">
- <country>India</country>
- </tld>
-
- <tld domain="io">
- <country>British Indian Ocean Territory</country>
- </tld>
-
- <tld domain="iq">
- <country>Iraq</country>
- </tld>
-
- <tld domain="ir">
- <country>Iran</country>
- </tld>
-
- <tld domain="is">
- <country>Iceland</country>
- </tld>
-
- <tld domain="it">
- <country>Italy</country>
- </tld>
-
- <tld domain="je">
- <country>Jersey</country>
- </tld>
-
- <tld domain="jm">
- <country>Jamaica</country>
- </tld>
-
- <tld domain="jo">
- <country>Jordan</country>
- </tld>
-
- <tld domain="jp">
- <country>Japan</country>
- </tld>
-
- <tld domain="ke">
- <country>Kenya</country>
- </tld>
-
- <tld domain="kg">
- <country>Kyrgyzstan</country>
- </tld>
-
- <tld domain="kh">
- <country>Cambodia</country>
- </tld>
-
- <tld domain="ki">
- <country>Kiribati</country>
- </tld>
-
- <tld domain="km">
- <country>Comoros</country>
- </tld>
-
- <tld domain="kn">
- <country>Saint Kitts and Nevis</country>
- </tld>
-
- <tld domain="kp">
- <country>North Korea</country>
- <status>NOT_IN_USE</status>
-
- <description>not assigned; no DNS</description>
- </tld>
-
- <tld domain="kr">
- <country>South Korea</country>
- </tld>
-
- <tld domain="kw">
- <country>Kuwait</country>
- </tld>
-
- <tld domain="ky">
- <country>Cayman Islands</country>
- </tld>
-
- <tld domain="kz">
- <country>Kazakhstan</country>
- </tld>
-
- <tld domain="la">
- <country>Laos</country>
- </tld>
-
- <tld domain="lb">
- <country>Lebanon</country>
- </tld>
-
- <tld domain="lc">
- <country>Saint Lucia</country>
- </tld>
-
- <tld domain="li">
- <country>Liechtenstein</country>
- </tld>
-
- <tld domain="lk">
- <country>Sri Lanka</country>
- </tld>
-
- <tld domain="lr">
- <country>Liberia</country>
- </tld>
-
- <tld domain="ls">
- <country>Lesotho</country>
- </tld>
-
- <tld domain="lt">
- <country>Lithuania</country>
- </tld>
-
- <tld domain="lu">
- <country>Luxembourg</country>
- </tld>
-
- <tld domain="lv">
- <country>Latvia</country>
- </tld>
-
- <tld domain="ly">
- <country>Libya</country>
- </tld>
-
- <tld domain="ma">
- <country>Morocco</country>
- </tld>
-
- <tld domain="mc">
- <country>Monaco</country>
- </tld>
-
- <tld domain="md">
- <country>Moldova</country>
- </tld>
-
- <tld domain="me">
- <country>Montenegro</country>
- </tld>
-
- <tld domain="mg">
- <country>Madagascar</country>
- </tld>
-
- <tld domain="mh">
- <country>Marshall Islands</country>
- </tld>
-
- <tld domain="mk">
- <country>Republic of Macedonia</country>
- </tld>
-
- <tld domain="ml">
- <country>Mali</country>
- </tld>
-
- <tld domain="mm">
- <country>Myanmar</country>
- <description>formerly .bu - Burma</description>
- </tld>
-
- <tld domain="mn">
- <country>Mongolia</country>
- </tld>
-
- <tld domain="mo">
- <country>Macau</country>
- </tld>
-
- <tld domain="mp">
- <country>Northern Mariana Islands</country>
- </tld>
-
- <tld domain="mq">
- <country>Martinique</country>
- </tld>
-
- <tld domain="mr">
- <country>Mauritania</country>
- </tld>
-
- <tld domain="ms">
- <country>Montserrat</country>
- </tld>
-
- <tld domain="mt">
- <country>Malta</country>
- </tld>
-
- <tld domain="mu">
- <country>Mauritius</country>
- </tld>
-
- <tld domain="mv">
- <country>Maldives</country>
- </tld>
-
- <tld domain="mw">
- <country>Malawi</country>
- </tld>
-
- <tld domain="mx">
- <country>Mexico</country>
- </tld>
-
- <tld domain="my">
- <country>Malaysia</country>
- </tld>
-
- <tld domain="mz">
- <country>Mozambique</country>
- </tld>
-
- <tld domain="na">
- <country>Namibia</country>
- </tld>
-
- <tld domain="nc">
- <country>New Caledonia</country>
- </tld>
-
- <tld domain="ne">
- <country>Niger</country>
- </tld>
-
- <tld domain="nf">
- <country>Norfolk Island</country>
- </tld>
-
- <tld domain="ng">
- <country>Nigeria</country>
- </tld>
-
- <tld domain="ni">
- <country>Nicaragua</country>
- </tld>
-
- <tld domain="nl">
- <country>Netherlands</country>
- </tld>
-
- <tld domain="no">
- <country>Norway</country>
- </tld>
-
- <tld domain="np">
- <country>Nepal</country>
- </tld>
-
- <tld domain="nr">
- <country>Nauru</country>
- </tld>
-
- <tld domain="nu">
- <country>Niue</country>
- </tld>
-
- <tld domain="nz">
- <country>New Zealand</country>
- </tld>
-
- <tld domain="om">
- <country>Oman</country>
- </tld>
-
- <tld domain="pa">
- <country>Panama</country>
- </tld>
-
- <tld domain="pe">
- <country>Peru</country>
- </tld>
-
- <tld domain="pf">
- <country>French Polynesia</country>
- </tld>
-
- <tld domain="pg">
- <country>Papua New Guinea</country>
- </tld>
-
- <tld domain="ph">
- <country>Philippines</country>
- </tld>
-
- <tld domain="pk">
- <country>Pakistan</country>
- </tld>
-
- <tld domain="pl">
- <country>Poland</country>
- </tld>
-
- <tld domain="pm">
- <country>Saint Pierre and Miquelon</country>
- </tld>
-
- <tld domain="pn">
- <country>Pitcairn Islands</country>
- </tld>
-
- <tld domain="pr">
- <country>Puerto Rico</country>
- </tld>
-
- <tld domain="ps">
- <country>Palestinian territories</country>
- </tld>
-
- <tld domain="pt">
- <country>Portugal</country>
- </tld>
-
- <tld domain="pw">
- <country>Palau</country>
- </tld>
-
- <tld domain="py">
- <country>Paraguay</country>
- </tld>
-
- <tld domain="qa">
- <country>Qatar</country>
- </tld>
-
- <tld domain="re">
- <country>Réunion</country>
- </tld>
-
- <tld domain="ro">
- <country>Romania</country>
- </tld>
-
- <tld domain="rs">
- <country>Serbia</country>
- </tld>
-
- <tld domain="ru">
- <country>Russia</country>
- </tld>
-
- <tld domain="rw">
- <country>Rwanda</country>
- </tld>
-
- <tld domain="sa">
- <country>Saudi Arabia</country>
- </tld>
-
- <tld domain="sb">
- <country>Solomon Islands</country>
- </tld>
-
- <tld domain="sc">
- <country>Seychelles</country>
- </tld>
-
- <tld domain="sd">
- <country>Sudan</country>
- </tld>
-
- <tld domain="se">
- <country>Sweden</country>
- </tld>
-
- <tld domain="sg">
- <country>Singapore</country>
- </tld>
-
- <tld domain="sh">
- <country>Saint Helena</country>
- </tld>
-
- <tld domain="si">
- <country>Slovenia</country>
- </tld>
-
- <tld domain="sj">
- <country>Svalbard and Jan Mayen Islands</country>
- <status>NOT_IN_USE</status>
- <description>not in use; no registrations</description>
- </tld>
-
- <tld domain="sk">
- <country>Slovakia</country>
- </tld>
-
- <tld domain="sl">
- <country>Sierra Leone</country>
- </tld>
-
- <tld domain="sm">
- <country>San Marino</country>
- </tld>
-
- <tld domain="sn">
- <country>Senegal</country>
- </tld>
-
- <tld domain="so">
- <country>Somalia</country>
- </tld>
-
- <tld domain="sr">
- <country>Suriname</country>
- </tld>
-
- <tld domain="st">
- <country>São Tomé and PrÃÂncipe</country>
- </tld>
-
- <tld domain="su">
- <country>Soviet Union</country>
- <status>DELETED</status>
- <description>
- deprecated; being phased out; code "transitionally reserved"
- by ISO 3166-1
- </description>
- </tld>
-
- <tld domain="sv">
- <country>El Salvador</country>
- </tld>
-
- <tld domain="sy">
- <country>Syria</country>
- </tld>
-
- <tld domain="sz">
- <country>Swaziland</country>
- </tld>
-
- <tld domain="tc">
- <country>Turks and Caicos Islands</country>
- </tld>
-
- <tld domain="td">
- <country>Chad</country>
- </tld>
-
- <tld domain="tf">
- <country>French Southern Territories</country>
- </tld>
-
- <tld domain="tg">
- <country>Togo</country>
- </tld>
-
- <tld domain="th">
- <country>Thailand</country>
- </tld>
-
- <tld domain="tj">
- <country>Tajikistan</country>
- </tld>
-
- <tld domain="tk">
- <country>Tokelau</country>
- </tld>
-
- <tld domain="tl">
- <country>East Timor</country>
- <description>formerly .tp</description>
- </tld>
-
- <tld domain="tm">
- <country>Turkmenistan</country>
- </tld>
-
- <tld domain="tn">
- <country>Tunisia</country>
- </tld>
-
- <tld domain="to">
- <country>Tonga</country>
- </tld>
-
- <tld domain="tp">
- <country>East Timor</country>
- <status>DELETED</status>
- <description>
- deprecated - use .tl; code "transitionally reserved" by ISO
- 3166-1
- </description>
- </tld>
-
- <tld domain="tr">
- <country>Turkey</country>
- </tld>
-
- <tld domain="tt">
- <country>Trinidad and Tobago</country>
- </tld>
-
- <tld domain="tv">
- <country>Tuvalu</country>
- </tld>
-
- <tld domain="tw">
- <country>Republic of China</country>
- <description>Taiwan</description>
- </tld>
-
- <tld domain="tz">
- <country>Tanzania</country>
- </tld>
-
- <tld domain="ua">
- <country>Ukraine</country>
- </tld>
-
- <tld domain="ug">
- <country>Uganda</country>
- </tld>
-
- <tld domain="uk">
- <country>United Kingdom</country>
- <description>
- code "exceptionally reserved" by ISO 3166-1 (see also .gb)
- </description>
- </tld>
-
- <tld domain="um">
- <country>United States Minor Outlying Islands</country>
- <status>DELETED</status>
- <description>see http://en.wikipedia.org/wiki/.um </description>
- </tld>
-
- <tld domain="us">
- <country>United States</country>
- </tld>
-
- <tld domain="uy">
- <country>Uruguay</country>
- </tld>
-
- <tld domain="uz">
- <country>Uzbekistan</country>
- </tld>
-
- <tld domain="va">
- <country>Vatican City</country>
- </tld>
-
- <tld domain="vc">
- <country>Saint Vincent and the Grenadines</country>
- </tld>
-
- <tld domain="ve">
- <country>Venezuela</country>
- </tld>
-
- <tld domain="vg">
- <country>British Virgin Islands</country>
- </tld>
-
- <tld domain="vi">
- <country>United States Virgin Islands</country>
- </tld>
-
- <tld domain="vn">
- <country>Vietnam</country>
- </tld>
-
- <tld domain="vu">
- <country>Vanuatu</country>
- </tld>
-
- <tld domain="wf">
- <country>Wallis and Futuna</country>
- </tld>
-
- <tld domain="ws">
- <country>Samoa</country>
- <description>formerly Western Samoa</description>
- </tld>
-
- <tld domain="ye">
- <country>Yemen</country>
- </tld>
-
- <tld domain="yt">
- <country>Mayotte</country>
- </tld>
-
- <tld domain="yu">
- <country>Yugoslavia</country>
- <description>
- subsequently renamed Serbia and Montenegro (code officially
- replaced by .cs (see above) but still used; code
- "transitionally reserved" by ISO 3166-1)
- </description>
- </tld>
-
- <tld domain="za">
- <country>South Africa</country>
- </tld>
-
- <tld domain="zm">
- <country>Zambia</country>
- </tld>
-
- <tld domain="zr">
- <country>Zaire</country>
- <status>DELETED</status>
- <description>replaced by .cd</description>
- </tld>
-
- <tld domain="zw">
- <country>Zimbabwe</country>
- </tld>
- </cctlds>
- </tlds>
-
- <!-- Second Level Domains -->
- <suffixes>
-
- <!-- .us Second Level Domains -->
- <suffix domain="as.us" />
- <suffix domain="gu.us" />
- <suffix domain="pr.us" />
- <suffix domain="vi.us" />
-
- <!-- .uk Second Level Domains -->
- <suffix domain="ac.uk" />
- <suffix domain="co.uk" />
- <suffix domain="gov.uk" />
- <suffix domain="ltd.uk" />
- <suffix domain="me.uk" />
- <suffix domain="mod.uk" />
- <suffix domain="net.uk" />
- <suffix domain="nic.uk" />
- <suffix domain="nhs.uk" />
- <suffix domain="org.uk" />
- <suffix domain="pic.uk" />
- <suffix domain="police.uk" />
- <suffix domain="govt.uk">
- <status>DELETED</status>
- </suffix>
- <suffix domain="orgn.uk">
- <status>DELETED</status>
- </suffix>
- <suffix domain="mil.uk">
- <status>DELETED</status>
- </suffix>
- <suffix domain="lea.uk">
- <status>DELETED</status>
- </suffix>
-
-
- <!-- .tr Second Level Domains -->
- <suffix domain="com.tr" />
- <suffix domain="gen.tr" />
- <suffix domain="org.tr"/>
- <suffix domain="biz.tr" />
- <suffix domain="info.tr" />
- <suffix domain="av.tr" />
- <suffix domain="dr.tr" />
- <suffix domain="pol.tr" />
- <suffix domain="bel.tr" />
- <suffix domain="mil.tr" />
- <suffix domain="mil.tr" />
- <suffix domain="bbs.tr" />
- <suffix domain="k12.tr" />
- <suffix domain="edu.tr"/>
- <suffix domain="name.tr" />
- <suffix domain="net.tr" />
- <suffix domain="gov.tr" />
- <suffix domain="gov.tr" />
- <suffix domain="web.tr" />
- <suffix domain="tel.tr" />
- <suffix domain="tv.tr" />
-
- <!-- .hk Second Level Domains -->
- <suffix domain="ust.hk" />
- <suffix domain="hku.hk" />
- <suffix domain="cuhk.hk" />
-
- <!-- .it Second Level Domains -->
-
- <suffix domain="edu.it" />
- <suffix domain="gov.it" />
- <suffix domain="italy.it" />
-
- <!-- .az Second Level Domains -->
- <suffix domain="pro.az" />
-
- <!-- .au Second Level Domains -->
-
- <suffix domain="com.au" />
- <suffix domain="net.au" />
- <suffix domain="gov.au" />
- <suffix domain="org.au" />
- <suffix domain="edu.au" />
- <suffix domain="csiro.au" />
- <suffix domain="asn.au" />
- <suffix domain="id.au" />
- <!-- New second level domains -->
- <suffix domain="act.au" />
- <suffix domain="nsw.au" />
- <suffix domain="nt.au" />
- <suffix domain="qld.au" />
- <suffix domain="sa.au" />
- <suffix domain="tas.au" />
- <suffix domain="vic.au" />
- <suffix domain="wa.au" />
-
- <!-- .int Second Level Domains -->
- <suffix domain="eu.int " />
-
- <!-- .br Second Level Domains -->
- <suffix domain="adm.br" />
- <suffix domain="adv.br" />
- <suffix domain="agr.br" />
- <suffix domain="am.br" />
- <suffix domain="arq.br" />
- <suffix domain="art.br" />
- <suffix domain="ato.br" />
- <suffix domain="bio.br" />
- <suffix domain="blog.br" />
- <suffix domain="bmd.br" />
- <suffix domain="cim.br" />
- <suffix domain="cng.br" />
- <suffix domain="cnt.br" />
- <suffix domain="com.br" />
- <suffix domain="coop.br" />
- <suffix domain="ecn.br" />
- <suffix domain="edu.br" />
- <suffix domain="eng.br" />
- <suffix domain="esp.br" />
- <suffix domain="etc.br" />
- <suffix domain="eti.br" />
- <suffix domain="far.br" />
- <suffix domain="flog.br" />
- <suffix domain="fm.br" />
- <suffix domain="fnd.br" />
- <suffix domain="fot.br" />
- <suffix domain="fst.br" />
- <suffix domain="g12.br" />
- <suffix domain="ggf.br" />
- <suffix domain="gov.br" />
- <suffix domain="imb.br" />
- <suffix domain="ind.br" />
- <suffix domain="inf.br" />
- <suffix domain="jor.br" />
- <suffix domain="lel.br" />
- <suffix domain="mat.br" />
- <suffix domain="med.br" />
- <suffix domain="mil.br" />
- <suffix domain="mus.br" />
- <suffix domain="net.br" />
- <suffix domain="nom.br" />
- <suffix domain="not.br" />
- <suffix domain="ntr.br" />
- <suffix domain="odo.br" />
- <suffix domain="org.br" />
- <suffix domain="ppg.br" />
- <suffix domain="pro.br" />
- <suffix domain="psc.br" />
- <suffix domain="psi.br" />
- <suffix domain="qsl.br" />
- <suffix domain="rec.br" />
- <suffix domain="slg.br" />
- <suffix domain="srv.br" />
- <suffix domain="tmp.br" />
- <suffix domain="trd.br" />
- <suffix domain="tur.br" />
- <suffix domain="tv.br" />
- <suffix domain="vet.br" />
- <suffix domain="vlog.br" />
- <suffix domain="wiki.br" />
- <suffix domain="zlg.br" />
-
- <!--
- Below elements are generated from the file
- at http://publicsuffix.org/ .
- see org.apache.nutch.util.domain.MozillaPublicSuffixListParser.java
- -->
-
- <!-- ac : http://en.wikipedia.org/wiki/.am-- >
- <suffix domain="com.ac" />
- <suffix domain="edu.ac" />
- <suffix domain="gov.ac" />
- <suffix domain="net.ac" />
- <suffix domain="mil.ac" />
- <suffix domain="org.ac" />
-
- <!-- ad : http://en.wikipedia.org/wiki/.ad-- >
- <suffix domain="nom.ad" />
-
- <!-- ae : http://en.wikipedia.org/wiki/.ae-- >
- <suffix domain="net.ae" />
- <suffix domain="gov.ae" />
- <suffix domain="ac.ae" />
- <suffix domain="sch.ae" />
- <suffix domain="org.ae" />
- <suffix domain="mil.ae" />
- <suffix domain="pro.ae" />
- <suffix domain="name.ae" />
-
- <!-- aero : see http://www.information.aero/index.php?id=66-- >
- <suffix domain="accident-investigation.aero" />
- <suffix domain="accident-prevention.aero" />
- <suffix domain="aerobatic.aero" />
- <suffix domain="aeroclub.aero" />
- <suffix domain="aerodrome.aero" />
- <suffix domain="agents.aero" />
- <suffix domain="aircraft.aero" />
- <suffix domain="airline.aero" />
- <suffix domain="airport.aero" />
- <suffix domain="air-surveillance.aero" />
- <suffix domain="airtraffic.aero" />
- <suffix domain="air-traffic-control.aero" />
- <suffix domain="ambulance.aero" />
- <suffix domain="amusement.aero" />
- <suffix domain="association.aero" />
- <suffix domain="author.aero" />
- <suffix domain="ballooning.aero" />
- <suffix domain="broker.aero" />
- <suffix domain="caa.aero" />
- <suffix domain="cargo.aero" />
- <suffix domain="catering.aero" />
- <suffix domain="certification.aero" />
- <suffix domain="championship.aero" />
- <suffix domain="charter.aero" />
- <suffix domain="civilaviation.aero" />
- <suffix domain="club.aero" />
- <suffix domain="conference.aero" />
- <suffix domain="consultant.aero" />
- <suffix domain="consulting.aero" />
- <suffix domain="control.aero" />
- <suffix domain="council.aero" />
- <suffix domain="crew.aero" />
- <suffix domain="design.aero" />
- <suffix domain="dgca.aero" />
- <suffix domain="educator.aero" />
- <suffix domain="emergency.aero" />
- <suffix domain="engine.aero" />
- <suffix domain="engineer.aero" />
- <suffix domain="entertainment.aero" />
- <suffix domain="equipment.aero" />
- <suffix domain="exchange.aero" />
- <suffix domain="express.aero" />
- <suffix domain="federation.aero" />
- <suffix domain="flight.aero" />
- <suffix domain="freight.aero" />
- <suffix domain="fuel.aero" />
- <suffix domain="gliding.aero" />
- <suffix domain="government.aero" />
- <suffix domain="groundhandling.aero" />
- <suffix domain="group.aero" />
- <suffix domain="hanggliding.aero" />
- <suffix domain="homebuilt.aero" />
- <suffix domain="insurance.aero" />
- <suffix domain="journal.aero" />
- <suffix domain="journalist.aero" />
- <suffix domain="leasing.aero" />
- <suffix domain="logistics.aero" />
- <suffix domain="magazine.aero" />
- <suffix domain="maintenance.aero" />
- <suffix domain="marketplace.aero" />
- <suffix domain="media.aero" />
- <suffix domain="microlight.aero" />
- <suffix domain="modelling.aero" />
- <suffix domain="navigation.aero" />
- <suffix domain="parachuting.aero" />
- <suffix domain="paragliding.aero" />
- <suffix domain="passenger-association.aero" />
- <suffix domain="pilot.aero" />
- <suffix domain="press.aero" />
- <suffix domain="production.aero" />
- <suffix domain="recreation.aero" />
- <suffix domain="repbody.aero" />
- <suffix domain="res.aero" />
- <suffix domain="research.aero" />
- <suffix domain="rotorcraft.aero" />
- <suffix domain="safety.aero" />
- <suffix domain="scientist.aero" />
- <suffix domain="services.aero" />
- <suffix domain="show.aero" />
- <suffix domain="skydiving.aero" />
- <suffix domain="software.aero" />
- <suffix domain="student.aero" />
- <suffix domain="taxi.aero" />
- <suffix domain="trader.aero" />
- <suffix domain="trading.aero" />
- <suffix domain="trainer.aero" />
- <suffix domain="union.aero" />
- <suffix domain="workinggroup.aero" />
- <suffix domain="works.aero" />
-
- <!-- af : http://www.nic.af/help.jsp-- >
- <suffix domain="gov.af" />
- <suffix domain="com.af" />
- <suffix domain="org.af" />
- <suffix domain="net.af" />
- <suffix domain="edu.af" />
-
- <!-- ag : http://www.nic.ag/prices.htm-- >
- <suffix domain="com.ag" />
- <suffix domain="org.ag" />
- <suffix domain="net.ag" />
- <suffix domain="co.ag" />
- <suffix domain="nom.ag" />
-
- <!-- ai : http://nic.com.ai/-- >
- <suffix domain="off.ai" />
- <suffix domain="com.ai" />
- <suffix domain="net.ai" />
- <suffix domain="org.ai" />
-
- <!-- al : http://www.inima.al/Domains.html-- >
- <suffix domain="gov.al" />
- <suffix domain="edu.al" />
- <suffix domain="org.al" />
- <suffix domain="com.al" />
- <suffix domain="net.al" />
-
- <!-- am : http://en.wikipedia.org/wiki/.am-- >
-
- <!-- an : http://www.una.an/an_domreg/default.asp-- >
- <suffix domain="com.an" />
- <suffix domain="net.an" />
- <suffix domain="org.an" />
- <suffix domain="edu.an" />
-
- <!-- ao : http://en.wikipedia.org/wiki/.ao-- >
- <!-- list of 2nd level TLDs ?-->
-
- <!-- aq : http://en.wikipedia.org/wiki/.aq-- >
-
- <!-- ar : http://en.wikipedia.org/wiki/.ar-- >
- <suffix domain="congresodelalengua3.ar" />
- <suffix domain="educ.ar" />
- <suffix domain="gobiernoelectronico.ar" />
- <suffix domain="mecon.ar" />
- <suffix domain="nacion.ar" />
- <suffix domain="nic.ar" />
- <suffix domain="promocion.ar" />
- <suffix domain="retina.ar" />
- <suffix domain="uba.ar" />
-
- <!-- arpa : http://en.wikipedia.org/wiki/.arpa-- >
- <suffix domain="e164.arpa" />
- <suffix domain="in-addr.arpa" />
- <suffix domain="ip6.arpa" />
- <suffix domain="uri.arpa" />
- <suffix domain="urn.arpa" />
-
- <!-- as : http://en.wikipedia.org/wiki/.as-- >
-
- <!-- at : http://en.wikipedia.org/wiki/.at-- >
- <suffix domain="gv.at" />
- <suffix domain="ac.at" />
- <suffix domain="co.at" />
- <suffix domain="or.at" />
-
- <!-- au : http://en.wikipedia.org/wiki/.au-- >
- <!-- au geographical names (vic.au etc... are covered above)-->
- <suffix domain="act.edu.au" />
- <suffix domain="nsw.edu.au" />
- <suffix domain="nt.edu.au" />
- <suffix domain="qld.edu.au" />
- <suffix domain="sa.edu.au" />
- <suffix domain="tas.edu.au" />
- <suffix domain="vic.edu.au" />
- <suffix domain="wa.edu.au" />
- <suffix domain="act.gov.au" />
- <suffix domain="nsw.gov.au" />
- <suffix domain="nt.gov.au" />
- <suffix domain="qld.gov.au" />
- <suffix domain="sa.gov.au" />
- <suffix domain="tas.gov.au" />
- <suffix domain="vic.gov.au" />
- <suffix domain="wa.gov.au" />
-
- <!-- aw : http://en.wikipedia.org/wiki/.aw-- >
- <suffix domain="com.aw" />
-
- <!-- ax : http://en.wikipedia.org/wiki/.ax-- >
-
- <!-- az : http://en.wikipedia.org/wiki/.az-- >
- <suffix domain="com.az" />
- <suffix domain="net.az" />
- <suffix domain="int.az" />
- <suffix domain="gov.az" />
- <suffix domain="org.az" />
- <suffix domain="edu.az" />
- <suffix domain="info.az" />
- <suffix domain="pp.az" />
- <suffix domain="mil.az" />
- <suffix domain="name.az" />
- <suffix domain="biz.az" />
-
- <!-- ba : http://en.wikipedia.org/wiki/.ba-- >
- <suffix domain="org.ba" />
- <suffix domain="net.ba" />
- <suffix domain="edu.ba" />
- <suffix domain="gov.ba" />
- <suffix domain="mil.ba" />
- <suffix domain="unsa.ba" />
- <suffix domain="unbi.ba" />
- <suffix domain="co.ba" />
- <suffix domain="com.ba" />
- <suffix domain="rs.ba" />
-
- <!-- bb : http://en.wikipedia.org/wiki/.bb-- >
- <suffix domain="com.bb" />
- <suffix domain="edu.bb" />
- <suffix domain="gov.bb" />
- <suffix domain="net.bb" />
- <suffix domain="org.bb" />
-
- <!-- bd : http://en.wikipedia.org/wiki/.bd-- >
-
- <!-- be : http://en.wikipedia.org/wiki/.be-- >
- <suffix domain="ac.be" />
-
- <!-- bf : http://en.wikipedia.org/wiki/.bf-- >
-
- <!-- bg : http://en.wikipedia.org/wiki/.bg-- >
-
- <!-- bh : http://en.wikipedia.org/wiki/.bh-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- bi : http://en.wikipedia.org/wiki/.bi-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- biz : http://en.wikipedia.org/wiki/.biz-- >
-
- <!-- bj : http://en.wikipedia.org/wiki/.bj-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- bm : http://www.bermudanic.bm/dnr-text.txt-- >
- <suffix domain="com.bm" />
- <suffix domain="edu.bm" />
- <suffix domain="gov.bm" />
- <suffix domain="net.bm" />
- <suffix domain="org.bm" />
-
- <!-- bn : http://en.wikipedia.org/wiki/.bn-- >
-
- <!-- bo : http://www.nic.bo/-- >
- <suffix domain="com.bo" />
- <suffix domain="edu.bo" />
- <suffix domain="gov.bo" />
- <suffix domain="gob.bo" />
- <suffix domain="int.bo" />
- <suffix domain="org.bo" />
- <suffix domain="net.bo" />
- <suffix domain="mil.bo" />
- <suffix domain="tv.bo" />
-
- <!-- br : http://en.wikipedia.org/wiki/.br-- >
-
- <!-- bs : http://www.nic.bs/rules.html-- >
- <suffix domain="com.bs" />
- <suffix domain="net.bs" />
- <suffix domain="org.bs" />
- <suffix domain="edu.bs" />
- <suffix domain="gov.bs" />
-
- <!-- bt : http://en.wikipedia.org/wiki/.bt-- >
-
- <!-- bw : http://en.wikipedia.org/wiki/.bw-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- by : http://en.wikipedia.org/wiki/.by-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- bz : http://en.wikipedia.org/wiki/.bz-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- ca : http://en.wikipedia.org/wiki/.ca-- >
- <!-- ca geographical names-->
- <suffix domain="ab.ca" />
- <suffix domain="bc.ca" />
- <suffix domain="mb.ca" />
- <suffix domain="nb.ca" />
- <suffix domain="nf.ca" />
- <suffix domain="nl.ca" />
- <suffix domain="ns.ca" />
- <suffix domain="nt.ca" />
- <suffix domain="nu.ca" />
- <suffix domain="on.ca" />
- <suffix domain="pe.ca" />
- <suffix domain="qc.ca" />
- <suffix domain="sk.ca" />
- <suffix domain="yk.ca" />
-
- <!-- cat : http://en.wikipedia.org/wiki/.cat-- >
-
- <!-- cc : http://en.wikipedia.org/wiki/.cc-- >
-
- <!-- cd : http://en.wikipedia.org/wiki/.cd-- >
-
- <!-- cf : http://en.wikipedia.org/wiki/.cf-- >
-
- <!-- cg : http://en.wikipedia.org/wiki/.cg-- >
-
- <!-- ch : http://en.wikipedia.org/wiki/.ch-- >
-
- <!-- ci : http://en.wikipedia.org/wiki/.ci-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- ck : http://en.wikipedia.org/wiki/.ck-- >
-
- <!-- cl : http://en.wikipedia.org/wiki/.cl-- >
-
- <!-- cm : http://en.wikipedia.org/wiki/.cm-- >
-
- <!-- cn : http://en.wikipedia.org/wiki/.cn-- >
- <suffix domain="ac.cn" />
- <suffix domain="com.cn" />
- <suffix domain="edu.cn" />
- <suffix domain="gov.cn" />
- <suffix domain="net.cn" />
- <suffix domain="org.cn" />
- <!-- cn geographic names-->
- <suffix domain="ah.cn" />
- <suffix domain="bj.cn" />
- <suffix domain="cq.cn" />
- <suffix domain="fj.cn" />
- <suffix domain="gd.cn" />
- <suffix domain="gs.cn" />
- <suffix domain="gz.cn" />
- <suffix domain="gx.cn" />
- <suffix domain="ha.cn" />
- <suffix domain="hb.cn" />
- <suffix domain="he.cn" />
- <suffix domain="hi.cn" />
- <suffix domain="hl.cn" />
- <suffix domain="hn.cn" />
- <suffix domain="jl.cn" />
- <suffix domain="js.cn" />
- <suffix domain="jx.cn" />
- <suffix domain="ln.cn" />
- <suffix domain="nm.cn" />
- <suffix domain="nx.cn" />
- <suffix domain="qh.cn" />
- <suffix domain="sc.cn" />
- <suffix domain="sd.cn" />
- <suffix domain="sh.cn" />
- <suffix domain="sn.cn" />
- <suffix domain="sx.cn" />
- <suffix domain="tj.cn" />
- <suffix domain="xj.cn" />
- <suffix domain="xz.cn" />
- <suffix domain="yn.cn" />
- <suffix domain="zj.cn" />
-
- <!-- co : http://en.wikipedia.org/wiki/.co-- >
-
- <!-- com : http://en.wikipedia.org/wiki/.com-- >
-
- <!-- coop : http://en.wikipedia.org/wiki/.coop-- >
-
- <!-- cr : http://en.wikipedia.org/wiki/.cr-- >
-
- <!-- cu : http://en.wikipedia.org/wiki/.cu-- >
- <suffix domain="com.cu" />
- <suffix domain="edu.cu" />
- <suffix domain="org.cu" />
- <suffix domain="net.cu" />
- <suffix domain="gov.cu" />
- <suffix domain="inf.cu" />
-
- <!-- cv : http://en.wikipedia.org/wiki/.cv-- >
-
- <!-- cx : http://en.wikipedia.org/wiki/.cx-- >
-
- <!-- cy : http://en.wikipedia.org/wiki/.cy-- >
-
- <!-- cz : http://en.wikipedia.org/wiki/.cz-- >
-
- <!-- de : http://en.wikipedia.org/wiki/.de-- >
-
- <!-- dj : http://en.wikipedia.org/wiki/.dj-- >
-
- <!-- dk : http://en.wikipedia.org/wiki/.dk-- >
-
- <!-- dm : http://en.wikipedia.org/wiki/.dm-- >
- <suffix domain="com.dm" />
- <suffix domain="net.dm" />
- <suffix domain="org.dm" />
-
- <!-- do : http://en.wikipedia.org/wiki/.do-- >
-
- <!-- dz : http://en.wikipedia.org/wiki/.dz-- >
- <suffix domain="com.dz" />
- <suffix domain="org.dz" />
- <suffix domain="net.dz" />
- <suffix domain="gov.dz" />
- <suffix domain="edu.dz" />
- <suffix domain="asso.dz" />
- <suffix domain="pol.dz" />
- <suffix domain="art.dz" />
-
- <!-- ec : http://www.nic.ec/reg/paso1.asp-- >
- <suffix domain="com.ec" />
- <suffix domain="info.ec" />
- <suffix domain="net.ec" />
- <suffix domain="fin.ec" />
- <suffix domain="med.ec" />
- <suffix domain="pro.ec" />
- <suffix domain="org.ec" />
- <suffix domain="edu.ec" />
- <suffix domain="gov.ec" />
- <suffix domain="mil.ec" />
-
- <!-- edu : http://en.wikipedia.org/wiki/.edu-- >
-
- <!-- ee : http://www3.eenet.ee/ee/application.html-- >
- <suffix domain="com.ee" />
- <suffix domain="org.ee" />
- <suffix domain="fie.ee" />
- <suffix domain="pri.ee" />
-
- <!-- eg : http://en.wikipedia.org/wiki/.eg-- >
-
- <!-- er : http://en.wikipedia.org/wiki/.er-- >
-
- <!-- es : https://www.nic.es/site_ingles/ingles/dominios/index.html-- >
- <suffix domain="com.es" />
- <suffix domain="nom.es" />
- <suffix domain="org.es" />
- <suffix domain="gob.es" />
- <suffix domain="edu.es" />
-
- <!-- et : http://en.wikipedia.org/wiki/.et-- >
-
- <!-- eu : http://en.wikipedia.org/wiki/.eu-- >
-
- <!-- fi : http://en.wikipedia.org/wiki/.fi-- >
-
- <!-- fj : http://en.wikipedia.org/wiki/.fj-- >
-
- <!-- fk : http://en.wikipedia.org/wiki/.fk-- >
-
- <!-- fm : http://en.wikipedia.org/wiki/.fm-- >
-
- <!-- fo : http://en.wikipedia.org/wiki/.fo-- >
-
- <!-- fr : http://www.afnic.fr/-- >
- <!-- domaines descriptifs : http://www.afnic.fr/obtenir/chartes/nommage-fr/annexe-descriptifs-- >
- <suffix domain="com.fr" />
- <suffix domain="asso.fr" />
- <suffix domain="nom.fr" />
- <suffix domain="prd.fr" />
- <suffix domain="presse.fr" />
- <suffix domain="tm.fr" />
- <!-- domaines sectoriels : http://www.afnic.fr/obtenir/chartes/nommage-fr/annexe-sectoriels-- >
- <suffix domain="aeroport.fr" />
- <suffix domain="assedic.fr" />
- <suffix domain="avocat.fr" />
- <suffix domain="avoues.fr" />
- <suffix domain="cci.fr" />
- <suffix domain="chambagri.fr" />
- <suffix domain="chirurgiens-dentistes.fr" />
- <suffix domain="experts-comptables.fr" />
- <suffix domain="geometre-expert.fr" />
- <suffix domain="gouv.fr" />
- <suffix domain="greta.fr" />
- <suffix domain="huissier-justice.fr" />
- <suffix domain="medecin.fr" />
- <suffix domain="notaires.fr" />
- <suffix domain="pharmacien.fr" />
- <suffix domain="port.fr" />
- <suffix domain="veterinaire.fr" />
-
- <!-- ga : http://en.wikipedia.org/wiki/.ga-- >
-
- <!-- gd : http://en.wikipedia.org/wiki/.gd-- >
-
- <!-- ge : http://www.nic.net.ge/policy_en.pdf-- >
- <suffix domain="com.ge" />
- <suffix domain="edu.ge" />
- <suffix domain="gov.ge" />
- <suffix domain="org.ge" />
- <suffix domain="mil.ge" />
- <suffix domain="net.ge" />
- <suffix domain="pvt.ge" />
-
- <!-- gf : http://en.wikipedia.org/wiki/.gf-- >
-
- <!-- gg : http://www.channelisles.net/tandc.shtml-- >
- <suffix domain="co.gg" />
- <suffix domain="org.gg" />
- <suffix domain="net.gg" />
- <suffix domain="sch.gg" />
- <suffix domain="gov.gg" />
-
- <!-- gh : http://www.ghana.com/domain.htm-- >
-
- <!-- gi : http://www.nic.gi/rules.html-- >
- <suffix domain="com.gi" />
- <suffix domain="ltd.gi" />
- <suffix domain="gov.gi" />
- <suffix domain="mod.gi" />
- <suffix domain="edu.gi" />
- <suffix domain="org.gi" />
-
- <!-- gl : http://en.wikipedia.org/wiki/.gl-- >
-
- <!-- gm : http://www.nic.gm/htmlpages%5Cgm-policy.htm-- >
-
- <!-- gn : http://psg.com/dns/gn/gn.txt-- >
-
- <!-- gov : http://en.wikipedia.org/wiki/.gov-- >
-
- <!-- gp : http://www.nic.gp/index_en.php?url=charte_en.php-- >
- <suffix domain="com.gp" />
- <suffix domain="net.gp" />
- <suffix domain="edu.gp" />
- <suffix domain="org.gp" />
-
- <!-- gq : http://en.wikipedia.org/wiki/.gq-- >
-
- <!-- gr : https://grweb.ics.forth.gr/english/1617-B-2002.html-- >
- <suffix domain="com.gr" />
- <suffix domain="edu.gr" />
- <suffix domain="net.gr" />
- <suffix domain="org.gr" />
- <suffix domain="gov.gr" />
-
- <!-- gs : http://en.wikipedia.org/wiki/.gs-- >
-
- <!-- gt : http://www.gt/politicas.html-- >
-
- <!-- gu : http://gadao.gov.gu/registration.txt-- >
-
- <!-- gw : http://en.wikipedia.org/wiki/.gw-- >
-
- <!-- gy : http://en.wikipedia.org/wiki/.gy-- >
-
- <!-- hk : http://en.wikipedia.org/wiki/.hk-- >
- <suffix domain="com.hk" />
- <suffix domain="edu.hk" />
- <suffix domain="gov.hk" />
- <suffix domain="idv.hk" />
- <suffix domain="net.hk" />
- <suffix domain="org.hk" />
-
- <!-- hm : http://en.wikipedia.org/wiki/.hm-- >
-
- <!-- hn : http://www.nic.hn/politicas/ps02,,05.html-- >
- <suffix domain="com.hn" />
- <suffix domain="edu.hn" />
- <suffix domain="org.hn" />
- <suffix domain="net.hn" />
- <suffix domain="mil.hn" />
- <suffix domain="gob.hn" />
-
- <!-- hr : http://www.dns.hr/documents/pdf/HRTLD-regulations.pdf-- >
- <suffix domain="iz.hr" />
- <suffix domain="from.hr" />
- <suffix domain="name.hr" />
- <suffix domain="com.hr" />
-
- <!-- ht : http://www.nic.ht/info/charte.cfm-- >
- <suffix domain="com.ht" />
- <suffix domain="shop.ht" />
- <suffix domain="firm.ht" />
- <suffix domain="info.ht" />
- <suffix domain="adult.ht" />
- <suffix domain="net.ht" />
- <suffix domain="pro.ht" />
- <suffix domain="org.ht" />
- <suffix domain="med.ht" />
- <suffix domain="art.ht" />
- <suffix domain="coop.ht" />
- <suffix domain="pol.ht" />
- <suffix domain="asso.ht" />
- <suffix domain="edu.ht" />
- <suffix domain="rel.ht" />
- <suffix domain="gouv.ht" />
- <suffix domain="perso.ht" />
-
- <!-- hu : http://www.domain.hu/domain/English/sld.html-- >
- <suffix domain="co.hu" />
- <suffix domain="info.hu" />
- <suffix domain="org.hu" />
- <suffix domain="priv.hu" />
- <suffix domain="sport.hu" />
- <suffix domain="tm.hu" />
- <suffix domain="2000.hu" />
- <suffix domain="agrar.hu" />
- <suffix domain="bolt.hu" />
- <suffix domain="casino.hu" />
- <suffix domain="city.hu" />
- <suffix domain="erotica.hu" />
- <suffix domain="erotika.hu" />
- <suffix domain="film.hu" />
- <suffix domain="forum.hu" />
- <suffix domain="games.hu" />
- <suffix domain="hotel.hu" />
- <suffix domain="ingatlan.hu" />
- <suffix domain="jogasz.hu" />
- <suffix domain="konyvelo.hu" />
- <suffix domain="lakas.hu" />
- <suffix domain="media.hu" />
- <suffix domain="news.hu" />
- <suffix domain="reklam.hu" />
- <suffix domain="sex.hu" />
- <suffix domain="shop.hu" />
- <suffix domain="suli.hu" />
- <suffix domain="szex.hu" />
- <suffix domain="tozsde.hu" />
- <suffix domain="utazas.hu" />
- <suffix domain="video.hu" />
-
- <!-- id : http://en.wikipedia.org/wiki/.id-- >
-
- <!-- ie : http://en.wikipedia.org/wiki/.ie-- >
-
- <!-- il : http://en.wikipedia.org/wiki/.il-- >
-
- <!-- im : https://www.nic.im/pdfs/imfaqs.pdf-- >
- <suffix domain="co.im" />
- <suffix domain="ltd.co.im" />
- <suffix domain="plc.co.im" />
- <suffix domain="net.im" />
- <suffix domain="gov.im" />
- <suffix domain="org.im" />
- <suffix domain="nic.im" />
- <suffix domain="ac.im" />
-
- <!-- in : http://en.wikipedia.org/wiki/.in-- >
- <suffix domain="co.in" />
- <suffix domain="firm.in" />
- <suffix domain="net.in" />
- <suffix domain="org.in" />
- <suffix domain="gen.in" />
- <suffix domain="ind.in" />
- <suffix domain="nic.in" />
- <suffix domain="ac.in" />
- <suffix domain="edu.in" />
- <suffix domain="res.in" />
- <suffix domain="gov.in" />
- <suffix domain="mil.in" />
-
- <!-- info : http://en.wikipedia.org/wiki/.info-- >
-
- <!-- int : http://en.wikipedia.org/wiki/.int-- >
-
- <!-- io : http://www.nic.io/rules.html-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- iq : http://en.wikipedia.org/wiki/.iq-- >
- <!-- no registrar website found, but google shows .gov.iq and .edu.iq websites-->
- <suffix domain="gov.iq" />
- <suffix domain="edu.iq" />
-
- <!-- ir : http://www.nic.ir/ascii/Appendix1.htm-- >
- <suffix domain="ac.ir" />
- <suffix domain="co.ir" />
- <suffix domain="gov.ir" />
- <suffix domain="id.ir" />
- <suffix domain="net.ir" />
- <suffix domain="org.ir" />
- <suffix domain="sch.ir" />
-
- <!-- is : http://www.isnic.is/domain/rules.php-- >
- <suffix domain="net.is" />
- <suffix domain="com.is" />
- <suffix domain="edu.is" />
- <suffix domain="gov.is" />
- <suffix domain="org.is" />
- <suffix domain="int.is" />
-
- <!-- it : http://en.wikipedia.org/wiki/.it-- >
- <suffix domain="gov.edu " />
- <!-- geo-names found at http://www.nic.it/RA/en/domini/regole/nomi-riservati.pdf-- >
- <suffix domain="agrigento.it" />
- <suffix domain="ag.it" />
- <suffix domain="alessandria.it" />
- <suffix domain="al.it" />
- <suffix domain="ancona.it" />
- <suffix domain="an.it" />
- <suffix domain="aosta.it" />
- <suffix domain="aoste.it" />
- <suffix domain="ao.it" />
- <suffix domain="arezzo.it" />
- <suffix domain="ar.it" />
- <suffix domain="ascoli-piceno.it" />
- <suffix domain="ascolipiceno.it" />
- <suffix domain="ap.it" />
- <suffix domain="asti.it" />
- <suffix domain="at.it" />
- <suffix domain="avellino.it" />
- <suffix domain="av.it" />
- <suffix domain="bari.it" />
- <suffix domain="ba.it" />
- <suffix domain="barlettaandriatrani.it" />
- <suffix domain="barletta-andria-trani.it" />
- <suffix domain="belluno.it" />
- <suffix domain="bl.it" />
- <suffix domain="benevento.it" />
- <suffix domain="bn.it" />
- <suffix domain="bergamo.it" />
- <suffix domain="bg.it" />
- <suffix domain="biella.it" />
- <suffix domain="bi.it" />
- <suffix domain="bologna.it" />
- <suffix domain="bo.it" />
- <suffix domain="bolzano.it" />
- <suffix domain="bozen.it" />
- <suffix domain="balsan.it" />
- <suffix domain="alto-adige.it" />
- <suffix domain="altoadige.it" />
- <suffix domain="suedtirol.it" />
- <suffix domain="bz.it" />
- <suffix domain="brescia.it" />
- <suffix domain="bs.it" />
- <suffix domain="brindisi.it" />
- <suffix domain="br.it" />
- <suffix domain="cagliari.it" />
- <suffix domain="ca.it" />
- <suffix domain="caltanissetta.it" />
- <suffix domain="cl.it" />
- <suffix domain="campobasso.it" />
- <suffix domain="cb.it" />
- <suffix domain="caserta.it" />
- <suffix domain="ce.it" />
- <suffix domain="catania.it" />
- <suffix domain="ct.it" />
- <suffix domain="catanzaro.it" />
- <suffix domain="cz.it" />
- <suffix domain="chieti.it" />
- <suffix domain="ch.it" />
- <suffix domain="como.it" />
- <suffix domain="co.it" />
- <suffix domain="cosenza.it" />
- <suffix domain="cs.it" />
- <suffix domain="cremona.it" />
- <suffix domain="cr.it" />
- <suffix domain="crotone.it" />
- <suffix domain="kr.it" />
- <suffix domain="cuneo.it" />
- <suffix domain="cn.it" />
- <suffix domain="enna.it" />
- <suffix domain="en.it" />
- <suffix domain="fermo.it" />
- <suffix domain="ferrara.it" />
- <suffix domain="fe.it" />
- <suffix domain="firenze.it" />
- <suffix domain="florence.it" />
- <suffix domain="fi.it" />
- <suffix domain="foggia.it" />
- <suffix domain="fg.it" />
- <suffix domain="forli-cesena.it" />
- <suffix domain="forlicesena.it" />
- <suffix domain="fc.it" />
- <suffix domain="frosinone.it" />
- <suffix domain="fr.it" />
- <suffix domain="genova.it" />
- <suffix domain="genoa.it" />
- <suffix domain="ge.it" />
- <suffix domain="gorizia.it" />
- <suffix domain="go.it" />
- <suffix domain="grosseto.it" />
- <suffix domain="gr.it" />
- <suffix domain="imperia.it" />
- <suffix domain="im.it" />
- <suffix domain="isernia.it" />
- <suffix domain="is.it" />
- <suffix domain="laquila.it" />
- <suffix domain="aquila.it" />
- <suffix domain="aq.it" />
- <suffix domain="la-spezia.it" />
- <suffix domain="laspezia.it" />
- <suffix domain="sp.it" />
- <suffix domain="latina.it" />
- <suffix domain="lt.it" />
- <suffix domain="lecce.it" />
- <suffix domain="le.it" />
- <suffix domain="lecco.it" />
- <suffix domain="lc.it" />
- <suffix domain="livorno.it" />
- <suffix domain="li.it" />
- <suffix domain="lodi.it" />
- <suffix domain="lo.it" />
- <suffix domain="lucca.it" />
- <suffix domain="lu.it" />
- <suffix domain="macerata.it" />
- <suffix domain="mc.it" />
- <suffix domain="mantova.it" />
- <suffix domain="mn.it" />
- <suffix domain="massa-carrara.it" />
- <suffix domain="massacarrara.it" />
- <suffix domain="ms.it" />
- <suffix domain="matera.it" />
- <suffix domain="mt.it" />
- <suffix domain="messina.it" />
- <suffix domain="me.it" />
- <suffix domain="milano.it" />
- <suffix domain="milan.it" />
- <suffix domain="mi.it" />
- <suffix domain="modena.it" />
- <suffix domain="mo.it" />
- <suffix domain="monza.it" />
- <suffix domain="napoli.it" />
- <suffix domain="naples.it" />
- <suffix domain="na.it" />
- <suffix domain="novara.it" />
- <suffix domain="no.it" />
- <suffix domain="nuoro.it" />
- <suffix domain="nu.it" />
- <suffix domain="oristano.it" />
- <suffix domain="or.it" />
- <suffix domain="padova.it" />
- <suffix domain="padua.it" />
- <suffix domain="pd.it" />
- <suffix domain="palermo.it" />
- <suffix domain="pa.it" />
- <suffix domain="parma.it" />
- <suffix domain="pr.it" />
- <suffix domain="pavia.it" />
- <suffix domain="pv.it" />
- <suffix domain="perugia.it" />
- <suffix domain="pg.it" />
- <suffix domain="pescara.it" />
- <suffix domain="pe.it" />
- <suffix domain="pesaro-urbino.it" />
- <suffix domain="pesarourbino.it" />
- <suffix domain="pu.it" />
- <suffix domain="piacenza.it" />
- <suffix domain="pc.it" />
- <suffix domain="pisa.it" />
- <suffix domain="pi.it" />
- <suffix domain="pistoia.it" />
- <suffix domain="pt.it" />
- <suffix domain="pordenone.it" />
- <suffix domain="pn.it" />
- <suffix domain="potenza.it" />
- <suffix domain="pz.it" />
- <suffix domain="prato.it" />
- <suffix domain="po.it" />
- <suffix domain="ragusa.it" />
- <suffix domain="rg.it" />
- <suffix domain="ravenna.it" />
- <suffix domain="ra.it" />
- <suffix domain="reggio-calabria.it" />
- <suffix domain="reggiocalabria.it" />
- <suffix domain="rc.it" />
- <suffix domain="reggio-emilia.it" />
- <suffix domain="reggioemilia.it" />
- <suffix domain="re.it" />
- <suffix domain="rieti.it" />
- <suffix domain="ri.it" />
- <suffix domain="rimini.it" />
- <suffix domain="rn.it" />
- <suffix domain="roma.it" />
- <suffix domain="rome.it" />
- <suffix domain="rm.it" />
- <suffix domain="rovigo.it" />
- <suffix domain="ro.it" />
- <suffix domain="salerno.it" />
- <suffix domain="sa.it" />
- <suffix domain="sassari.it" />
- <suffix domain="ss.it" />
- <suffix domain="savona.it" />
- <suffix domain="sv.it" />
- <suffix domain="siena.it" />
- <suffix domain="si.it" />
- <suffix domain="siracusa.it" />
- <suffix domain="sr.it" />
- <suffix domain="sondrio.it" />
- <suffix domain="so.it" />
- <suffix domain="taranto.it" />
- <suffix domain="ta.it" />
- <suffix domain="teramo.it" />
- <suffix domain="te.it" />
- <suffix domain="terni.it" />
- <suffix domain="tr.it" />
- <suffix domain="torino.it" />
- <suffix domain="turin.it" />
- <suffix domain="to.it" />
- <suffix domain="trapani.it" />
- <suffix domain="tp.it" />
- <suffix domain="trento.it" />
- <suffix domain="trentino.it" />
- <suffix domain="tn.it" />
- <suffix domain="treviso.it" />
- <suffix domain="tv.it" />
- <suffix domain="trieste.it" />
- <suffix domain="ts.it" />
- <suffix domain="udine.it" />
- <suffix domain="ud.it" />
- <suffix domain="varese.it" />
- <suffix domain="va.it" />
- <suffix domain="venezia.it" />
- <suffix domain="venice.it" />
- <suffix domain="ve.it" />
- <suffix domain="verbania.it" />
- <suffix domain="vb.it" />
- <suffix domain="vercelli.it" />
- <suffix domain="vc.it" />
- <suffix domain="verona.it" />
- <suffix domain="vr.it" />
- <suffix domain="vibo-valentia.it" />
- <suffix domain="vibovalentia.it" />
- <suffix domain="vv.it" />
- <suffix domain="vicenza.it" />
- <suffix domain="vi.it" />
- <suffix domain="viterbo.it" />
- <suffix domain="vt.it" />
-
- <!-- je : http://www.channelisles.net/tandc.shtml-- >
- <suffix domain="co.je" />
- <suffix domain="org.je" />
- <suffix domain="net.je" />
- <suffix domain="sch.je" />
- <suffix domain="gov.je" />
-
- <!-- jm : http://www.com.jm/register.html-- >
-
- <!-- jo : http://www.nis.gov.jo/dns/reg.html-- >
- <suffix domain="com.jo" />
- <suffix domain="org.jo" />
- <suffix domain="net.jo" />
- <suffix domain="edu.jo" />
- <suffix domain="gov.jo" />
- <suffix domain="mil.jo" />
- <suffix domain="myname.jo" />
-
- <!-- jobs : http://en.wikipedia.org/wiki/.jobs-- >
-
- <!-- jp : http://en.wikipedia.org/wiki/.jp-- >
- <suffix domain="ac.jp" />
- <suffix domain="ad.jp" />
- <suffix domain="co.jp" />
- <suffix domain="ed.jp" />
- <suffix domain="go.jp" />
- <suffix domain="gr.jp" />
- <suffix domain="lg.jp" />
- <suffix domain="ne.jp" />
- <suffix domain="or.jp" />
- <!-- jp geographical names-->
- <!-- I can't find an official english explanantrion, but used https://bugzilla.mozilla.org/show_bug.cgi?id=252342#c31-- >
- <suffix domain="aichi.jp" />
- <suffix domain="akita.jp" />
- <suffix domain="aomori.jp" />
- <suffix domain="chiba.jp" />
- <suffix domain="ehime.jp" />
- <suffix domain="fukui.jp" />
- <suffix domain="fukuoka.jp" />
- <suffix domain="fukushima.jp" />
- <suffix domain="gifu.jp" />
- <suffix domain="gunma.jp" />
- <suffix domain="hiroshima.jp" />
- <suffix domain="hokkaido.jp" />
- <suffix domain="hyogo.jp" />
- <suffix domain="ibaraki.jp" />
- <suffix domain="ishikawa.jp" />
- <suffix domain="iwate.jp" />
- <suffix domain="kagawa.jp" />
- <suffix domain="kagoshima.jp" />
- <suffix domain="kanagawa.jp" />
- <suffix domain="kawasaki.jp" />
- <suffix domain="kitakyushu.jp" />
- <suffix domain="kobe.jp" />
- <suffix domain="kochi.jp" />
- <suffix domain="kumamoto.jp" />
- <suffix domain="kyoto.jp" />
- <suffix domain="mie.jp" />
- <suffix domain="miyagi.jp" />
- <suffix domain="miyazaki.jp" />
- <suffix domain="nagano.jp" />
- <suffix domain="nagasaki.jp" />
- <suffix domain="nagoya.jp" />
- <suffix domain="nara.jp" />
- <suffix domain="niigata.jp" />
- <suffix domain="oita.jp" />
- <suffix domain="okayama.jp" />
- <suffix domain="okinawa.jp" />
- <suffix domain="osaka.jp" />
- <suffix domain="saga.jp" />
- <suffix domain="saitama.jp" />
- <suffix domain="sapporo.jp" />
- <suffix domain="sendai.jp" />
- <suffix domain="shiga.jp" />
- <suffix domain="shimane.jp" />
- <suffix domain="shizuoka.jp" />
- <suffix domain="tochigi.jp" />
- <suffix domain="tokushima.jp" />
- <suffix domain="tokyo.jp" />
- <suffix domain="tottori.jp" />
- <suffix domain="toyama.jp" />
- <suffix domain="wakayama.jp" />
- <suffix domain="yamagata.jp" />
- <suffix domain="yamaguchi.jp" />
- <suffix domain="yamanashi.jp" />
- <suffix domain="yokohama.jp" />
- <suffix domain="metro.tokyo.jp" />
- <suffix domain="pref.aichi.jp" />
- <suffix domain="pref.akita.jp" />
- <suffix domain="pref.aomori.jp" />
- <suffix domain="pref.chiba.jp" />
- <suffix domain="pref.ehime.jp" />
- <suffix domain="pref.fukui.jp" />
- <suffix domain="pref.fukuoka.jp" />
- <suffix domain="pref.fukushima.jp" />
- <suffix domain="pref.gifu.jp" />
- <suffix domain="pref.gunma.jp" />
- <suffix domain="pref.hiroshima.jp" />
- <suffix domain="pref.hokkaido.jp" />
- <suffix domain="pref.hyogo.jp" />
- <suffix domain="pref.ibaraki.jp" />
- <suffix domain="pref.ishikawa.jp" />
- <suffix domain="pref.iwate.jp" />
- <suffix domain="pref.kagawa.jp" />
- <suffix domain="pref.kagoshima.jp" />
- <suffix domain="pref.kanagawa.jp" />
- <suffix domain="pref.kochi.jp" />
- <suffix domain="pref.kumamoto.jp" />
- <suffix domain="pref.kyoto.jp" />
- <suffix domain="pref.mie.jp" />
- <suffix domain="pref.miyagi.jp" />
- <suffix domain="pref.miyazaki.jp" />
- <suffix domain="pref.nagano.jp" />
- <suffix domain="pref.nagasaki.jp" />
- <suffix domain="pref.nara.jp" />
- <suffix domain="pref.niigata.jp" />
- <suffix domain="pref.oita.jp" />
- <suffix domain="pref.okayama.jp" />
- <suffix domain="pref.okinawa.jp" />
- <suffix domain="pref.osaka.jp" />
- <suffix domain="pref.saga.jp" />
- <suffix domain="pref.saitama.jp" />
- <suffix domain="pref.shiga.jp" />
- <suffix domain="pref.shimane.jp" />
- <suffix domain="pref.shizuoka.jp" />
- <suffix domain="pref.tochigi.jp" />
- <suffix domain="pref.tokushima.jp" />
- <suffix domain="pref.tottori.jp" />
- <suffix domain="pref.toyama.jp" />
- <suffix domain="pref.wakayama.jp" />
- <suffix domain="pref.yamagata.jp" />
- <suffix domain="pref.yamaguchi.jp" />
- <suffix domain="pref.yamanashi.jp" />
- <suffix domain="city.chiba.jp" />
- <suffix domain="city.fukuoka.jp" />
- <suffix domain="city.hiroshima.jp" />
- <suffix domain="city.kawasaki.jp" />
- <suffix domain="city.kitakyushu.jp" />
- <suffix domain="city.kobe.jp" />
- <suffix domain="city.kyoto.jp" />
- <suffix domain="city.nagoya.jp" />
- <suffix domain="city.osaka.jp" />
- <suffix domain="city.saitama.jp" />
- <suffix domain="city.sapporo.jp" />
- <suffix domain="city.sendai.jp" />
- <suffix domain="city.shizuoka.jp" />
- <suffix domain="city.yokohama.jp" />
-
- <!-- ke : http://www.kenic.or.ke/index.php?option=com_content&task=view&id=117&Item... >
-
- <!-- kg : http://www.domain.kg/dmn_n.html-- >
- <suffix domain="org.kg" />
- <suffix domain="net.kg" />
- <suffix domain="com.kg" />
- <suffix domain="edu.kg" />
- <suffix domain="gov.kg" />
- <suffix domain="mil.kg" />
-
- <!-- kh : http://www.mptc.gov.kh/dns_registration.htm-- >
-
- <!-- ki : http://www.ki/dns/index.html-- >
- <suffix domain="edu.ki" />
- <suffix domain="biz.ki" />
- <suffix domain="net.ki" />
- <suffix domain="org.ki" />
- <suffix domain="gov.ki" />
- <suffix domain="info.ki" />
- <suffix domain="com.ki" />
-
- <!-- km : http://en.wikipedia.org/wiki/.km-- >
-
- <!-- kn : http://en.wikipedia.org/wiki/.kn-- >
-
- <!-- kr : http://domain.nida.or.kr/eng/structure.jsp-- >
- <suffix domain="ac.kr" />
- <suffix domain="co.kr" />
- <suffix domain="go.kr" />
- <suffix domain="ne.kr" />
- <suffix domain="or.kr" />
- <suffix domain="re.kr" />
- <suffix domain="pe.kr" />
- <suffix domain="՜Ꞁ.kr" />
-
- <!-- kw : http://en.wikipedia.org/wiki/.kw-- >
-
- <!-- ky : http://www.icta.ky/da_ky_reg_dom.php-- >
- <suffix domain="edu.ky" />
- <suffix domain="gov.ky" />
- <suffix domain="com.ky" />
- <suffix domain="org.ky" />
- <suffix domain="net.ky" />
-
- <!-- kz : http://en.wikipedia.org/wiki/.kz-- >
- <suffix domain="org.kz" />
- <suffix domain="edu.kz" />
- <suffix domain="net.kz" />
- <suffix domain="gov.kz" />
- <suffix domain="mil.kz" />
- <suffix domain="com.kz" />
-
- <!-- la : http://en.wikipedia.org/wiki/.la-- >
-
- <!-- lb : http://en.wikipedia.org/wiki/.lb-- >
-
- <!-- lc : http://en.wikipedia.org/wiki/.lc-- >
- <suffix domain="com.lc" />
- <suffix domain="org.lc" />
- <suffix domain="edu.lc" />
- <suffix domain="gov.lc" />
-
- <!-- li : http://en.wikipedia.org/wiki/.li-- >
-
- <!-- lk : http://www.nic.lk/seclevpr.html-- >
- <suffix domain="gov.lk" />
- <suffix domain="sch.lk" />
- <suffix domain="net.lk" />
- <suffix domain="int.lk" />
- <suffix domain="com.lk" />
- <suffix domain="org.lk" />
- <suffix domain="edu.lk" />
- <suffix domain="ngo.lk" />
- <suffix domain="soc.lk" />
- <suffix domain="web.lk" />
- <suffix domain="ltd.lk" />
- <suffix domain="assn.lk" />
- <suffix domain="grp.lk" />
- <suffix domain="hotel.lk" />
-
- <!-- lr : http://psg.com/dns/lr/lr.txt-- >
-
- <!-- ls : http://en.wikipedia.org/wiki/.ls-- >
- <suffix domain="co.ls" />
- <suffix domain="org.ls" />
-
- <!-- lt : http://en.wikipedia.org/wiki/.lt-- >
-
- <!-- lu : http://www.dns.lu/en/-- >
-
- <!-- lv : http://www.nic.lv/DNS/En/generic.php-- >
- <suffix domain="com.lv" />
- <suffix domain="edu.lv" />
- <suffix domain="gov.lv" />
- <suffix domain="org.lv" />
- <suffix domain="mil.lv" />
- <suffix domain="id.lv" />
- <suffix domain="net.lv" />
- <suffix domain="asn.lv" />
- <suffix domain="conf.lv" />
-
- <!-- ly : http://www.nic.ly/regulations.php-- >
- <suffix domain="com.ly" />
- <suffix domain="net.ly" />
- <suffix domain="gov.ly" />
- <suffix domain="plc.ly" />
- <suffix domain="edu.ly" />
- <suffix domain="sch.ly" />
- <suffix domain="med.ly" />
- <suffix domain="org.ly" />
- <suffix domain="id.ly" />
-
- <!-- ma : http://en.wikipedia.org/wiki/.ma-- >
- <!-- list of 2nd level tlds ?-->
- <suffix domain="co.ma" />
- <suffix domain="net.ma" />
- <suffix domain="gov.ma" />
- <suffix domain="org.ma" />
-
- <!-- mc : http://www.nic.mc/-- >
- <suffix domain="tm.mc" />
- <suffix domain="asso.mc" />
-
- <!-- md : http://en.wikipedia.org/wiki/.md-- >
-
- <!-- mg : http://www.nic.mg/tarif.htm-- >
- <suffix domain="org.mg" />
- <suffix domain="nom.mg" />
- <suffix domain="gov.mg" />
- <suffix domain="prd.mg" />
- <suffix domain="tm.mg" />
- <suffix domain="edu.mg" />
- <suffix domain="mil.mg" />
- <suffix domain="com.mg" />
-
- <!-- mh : http://en.wikipedia.org/wiki/.mh-- >
-
- <!-- mil : http://en.wikipedia.org/wiki/.mil-- >
-
- <!-- mk : http://en.wikipedia.org/wiki/.mk-- >
- <!-- list of 2nd level tlds ?-->
- <suffix domain="com.mk" />
- <suffix domain="gov.mk" />
- <suffix domain="org.mk" />
- <suffix domain="net.mk" />
- <suffix domain="edu.mk" />
-
- <!-- ml : http://www.gobin.info/domainname/ml-template.doc-- >
-
- <!-- mm : http://en.wikipedia.org/wiki/.mm-- >
-
- <!-- mn : http://en.wikipedia.org/wiki/.mn-- >
- <suffix domain="gov.mn" />
- <suffix domain="edu.mn" />
- <suffix domain="org.mn" />
-
- <!-- mo : http://www.monic.net.mo/-- >
- <suffix domain="com.mo" />
- <suffix domain="net.mo" />
- <suffix domain="org.mo" />
- <suffix domain="edu.mo" />
- <suffix domain="gov.mo" />
-
- <!-- mobi : http://en.wikipedia.org/wiki/.mobi-- >
-
- <!-- mp : http://www.dot.mp/-- >
-
- <!-- mq : http://en.wikipedia.org/wiki/.mq-- >
-
- <!-- mr : http://en.wikipedia.org/wiki/.mr-- >
-
- <!-- ms : http://en.wikipedia.org/wiki/.ms-- >
-
- <!-- mt : https://www.nic.org.mt/dotmt/-- >
-
- <!-- mu : http://en.wikipedia.org/wiki/.mu-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- museum : http://about.museum/naming/-- >
- <!-- there are 2nd-level TLD's, but there's no list-->
-
- <!-- mv : http://en.wikipedia.org/wiki/.mv-- >
-
- <!-- mw : http://www.registrar.mw/-- >
- <suffix domain="ac.mw" />
- <suffix domain="biz.mw" />
- <suffix domain="co.mw" />
- <suffix domain="com.mw" />
- <suffix domain="coop.mw" />
- <suffix domain="edu.mw" />
- <suffix domain="gov.mw" />
- <suffix domain="int.mw" />
- <suffix domain="net.mw" />
- <suffix domain="org.mw" />
-
- <!-- mx : http://www.nic.mx/-- >
-
- <!-- my : http://www.mynic.net.my/-- >
-
- <!-- mz : http://www.gobin.info/domainname/mz-template.doc-- >
-
- <!-- na : http://www.na-nic.com.na/-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- name : has 2nd-level tlds, but there's no list of them-->
-
- <!-- nc : http://www.cctld.nc/-- >
-
- <!-- ne : http://en.wikipedia.org/wiki/.ne-- >
-
- <!-- net : http://en.wikipedia.org/wiki/.net-- >
-
- <!-- nf : http://en.wikipedia.org/wiki/.nf-- >
- <suffix domain="com.nf" />
- <suffix domain="net.nf" />
- <suffix domain="per.nf" />
- <suffix domain="rec.nf" />
- <suffix domain="web.nf" />
- <suffix domain="arts.nf" />
- <suffix domain="firm.nf" />
- <suffix domain="info.nf" />
- <suffix domain="other.nf" />
- <suffix domain="store.nf" />
-
- <!-- ng : http://psg.com/dns/ng/-- >
-
- <!-- ni : http://www.nic.ni/dominios.htm-- >
-
- <!-- nl : http://www.domain-registry.nl/ace.php/c,728,122,,,,Home.html-- >
-
- <!-- no : http://www.norid.no/regelverk/index.en.html-- >
- <suffix domain="fhs.no" />
- <suffix domain="vgs.no" />
- <suffix domain="fylkesbibl.no" />
- <suffix domain="folkebibl.no" />
- <suffix domain="museum.no" />
- <suffix domain="idrett.no" />
- <suffix domain="mil.no" />
- <suffix domain="stat.no" />
- <suffix domain="dep.no" />
- <suffix domain="kommune.no" />
- <suffix domain="herad.no" />
- <suffix domain="priv.no" />
- <!-- no geographical names : http://www.norid.no/regelverk/vedlegg-b.en.html-- >
- <!-- counties-->
- <suffix domain="aa.no" />
- <suffix domain="ah.no" />
- <suffix domain="bu.no" />
- <suffix domain="fm.no" />
- <suffix domain="hl.no" />
- <suffix domain="hm.no" />
- <suffix domain="jan-mayen.no" />
- <suffix domain="mr.no" />
- <suffix domain="nl.no" />
- <suffix domain="nt.no" />
- <suffix domain="of.no" />
- <suffix domain="ol.no" />
- <suffix domain="oslo.no" />
- <suffix domain="rl.no" />
- <suffix domain="sf.no" />
- <suffix domain="st.no" />
- <suffix domain="svalbard.no" />
- <suffix domain="tm.no" />
- <suffix domain="tr.no" />
- <suffix domain="va.no" />
- <suffix domain="vf.no" />
- <!-- primary and lower secondary schools per county-->
- <suffix domain="gs.aa.no" />
- <suffix domain="gs.ah.no" />
- <suffix domain="gs.bu.no" />
- <suffix domain="gs.fm.no" />
- <suffix domain="gs.hl.no" />
- <suffix domain="gs.hm.no" />
- <suffix domain="gs.jan-mayen.no" />
- <suffix domain="gs.mr.no" />
- <suffix domain="gs.nl.no" />
- <suffix domain="gs.nt.no" />
- <suffix domain="gs.of.no" />
- <suffix domain="gs.ol.no" />
- <suffix domain="gs.oslo.no" />
- <suffix domain="gs.rl.no" />
- <suffix domain="gs.sf.no" />
- <suffix domain="gs.st.no" />
- <suffix domain="gs.svalbard.no" />
- <suffix domain="gs.tm.no" />
- <suffix domain="gs.tr.no" />
- <suffix domain="gs.va.no" />
- <suffix domain="gs.vf.no" />
- <!-- cities-->
- <suffix domain="akrehamn.no" />
- <suffix domain="Ã¥krehamn.no" />
- <suffix domain="algard.no" />
- <suffix domain="ålgård.no" />
- <suffix domain="arna.no" />
- <suffix domain="brumunddal.no" />
- <suffix domain="bryne.no" />
- <suffix domain="bronnoysund.no" />
- <suffix domain="brÞnnÞysund.no" />
- <suffix domain="drobak.no" />
- <suffix domain="drÞbak.no" />
- <suffix domain="egersund.no" />
- <suffix domain="fetsund.no" />
- <suffix domain="floro.no" />
- <suffix domain="florÞ.no" />
- <suffix domain="fredrikstad.no" />
- <suffix domain="hokksund.no" />
- <suffix domain="honefoss.no" />
- <suffix domain="hÞnefoss.no" />
- <suffix domain="jessheim.no" />
- <suffix domain="jorpeland.no" />
- <suffix domain="jÞrpeland.no" />
- <suffix domain="kirkenes.no" />
- <suffix domain="kopervik.no" />
- <suffix domain="krokstadelva.no" />
- <suffix domain="langevag.no" />
- <suffix domain="langevåg.no" />
- <suffix domain="leirvik.no" />
- <suffix domain="mjondalen.no" />
- <suffix domain="mjÞndalen.no" />
- <suffix domain="mo-i-rana.no" />
- <suffix domain="mosjoen.no" />
- <suffix domain="mosjÞen.no" />
- <suffix domain="nesoddtangen.no" />
- <suffix domain="orkanger.no" />
- <suffix domain="osoyro.no" />
- <suffix domain="osÞyro.no" />
- <suffix domain="raholt.no" />
- <suffix domain="råholt.no" />
- <suffix domain="sandnessjoen.no" />
- <suffix domain="sandnessjÞen.no" />
- <suffix domain="skedsmokorset.no" />
- <suffix domain="slattum.no" />
- <suffix domain="spjelkavik.no" />
- <suffix domain="stathelle.no" />
- <suffix domain="stavern.no" />
- <suffix domain="stjordalshalsen.no" />
- <suffix domain="stjÞrdalshalsen.no" />
- <suffix domain="tananger.no" />
- <suffix domain="tranby.no" />
- <suffix domain="vossevangen.no" />
- <!-- communities-->
- <suffix domain="afjord.no" />
- <suffix domain="Ã¥fjord.no" />
- <suffix domain="agdenes.no" />
- <suffix domain="al.no" />
- <suffix domain="Ã¥l.no" />
- <suffix domain="alesund.no" />
- <suffix domain="Ã¥lesund.no" />
- <suffix domain="alstahaug.no" />
- <suffix domain="alta.no" />
- <suffix domain="áltá.no" />
- <suffix domain="alaheadju.no" />
- <suffix domain="álaheadju.no" />
- <suffix domain="alvdal.no" />
- <suffix domain="amli.no" />
- <suffix domain="Ã¥mli.no" />
- <suffix domain="amot.no" />
- <suffix domain="Ã¥mot.no" />
- <suffix domain="andebu.no" />
- <suffix domain="andoy.no" />
- <suffix domain="andÞy.no" />
- <suffix domain="andasuolo.no" />
- <suffix domain="ardal.no" />
- <suffix domain="Ã¥rdal.no" />
- <suffix domain="aremark.no" />
- <suffix domain="arendal.no" />
- <suffix domain="Ã¥s.no" />
- <suffix domain="aseral.no" />
- <suffix domain="Ã¥seral.no" />
- <suffix domain="asker.no" />
- <suffix domain="askim.no" />
- <suffix domain="askvoll.no" />
- <suffix domain="askoy.no" />
- <suffix domain="askÞy.no" />
- <suffix domain="asnes.no" />
- <suffix domain="Ã¥snes.no" />
- <suffix domain="audnedaln.no" />
- <suffix domain="aukra.no" />
- <suffix domain="aure.no" />
- <suffix domain="aurland.no" />
- <suffix domain="aurskog-holand.no" />
- <suffix domain="aurskog-hÞland.no" />
- <suffix domain="austevoll.no" />
- <suffix domain="austrheim.no" />
- <suffix domain="averoy.no" />
- <suffix domain="averÞy.no" />
- <suffix domain="balestrand.no" />
- <suffix domain="ballangen.no" />
- <suffix domain="balat.no" />
- <suffix domain="bálát.no" />
- <suffix domain="balsfjord.no" />
- <suffix domain="bahccavuotna.no" />
- <suffix domain="báhccavuotna.no" />
- <suffix domain="bamble.no" />
- <suffix domain="bardu.no" />
- <suffix domain="beardu.no" />
- <suffix domain="beiarn.no" />
- <suffix domain="bajddar.no" />
- <suffix domain="bájddar.no" />
- <suffix domain="baidar.no" />
- <suffix domain="báidár.no" />
- <suffix domain="berg.no" />
- <suffix domain="bergen.no" />
- <suffix domain="berlevag.no" />
- <suffix domain="berlevåg.no" />
- <suffix domain="bearalvahki.no" />
- <suffix domain="bearalváhki.no" />
- <suffix domain="bindal.no" />
- <suffix domain="birkenes.no" />
- <suffix domain="bjarkoy.no" />
- <suffix domain="bjarkÞy.no" />
- <suffix domain="bjerkreim.no" />
- <suffix domain="bjugn.no" />
- <suffix domain="bodo.no" />
- <suffix domain="bodÞ.no" />
- <suffix domain="badaddja.no" />
- <suffix domain="bådåddjå.no" />
- <suffix domain="budejju.no" />
- <suffix domain="bokn.no" />
- <suffix domain="bremanger.no" />
- <suffix domain="bronnoy.no" />
- <suffix domain="brÞnnÞy.no" />
- <suffix domain="bygland.no" />
- <suffix domain="bykle.no" />
- <suffix domain="barum.no" />
- <suffix domain="bÊrum.no" />
- <suffix domain="bo.telemark.no" />
- <suffix domain="bÞ.telemark.no" />
- <suffix domain="bo.nordland.no" />
- <suffix domain="bÞ.nordland.no" />
- <suffix domain="bievat.no" />
- <suffix domain="bievát.no" />
- <suffix domain="bomlo.no" />
- <suffix domain="bÞmlo.no" />
- <suffix domain="batsfjord.no" />
- <suffix domain="båtsfjord.no" />
- <suffix domain="bahcavuotna.no" />
- <suffix domain="báhcavuotna.no" />
- <suffix domain="dovre.no" />
- <suffix domain="drammen.no" />
- <suffix domain="drangedal.no" />
- <suffix domain="dyroy.no" />
- <suffix domain="dyrÞy.no" />
- <suffix domain="donna.no" />
- <suffix domain="dÞnna.no" />
- <suffix domain="eid.no" />
- <suffix domain="eidfjord.no" />
- <suffix domain="eidsberg.no" />
- <suffix domain="eidskog.no" />
- <suffix domain="eidsvoll.no" />
- <suffix domain="eigersund.no" />
- <suffix domain="elverum.no" />
- <suffix domain="enebakk.no" />
- <suffix domain="engerdal.no" />
- <suffix domain="etne.no" />
- <suffix domain="etnedal.no" />
- <suffix domain="evenes.no" />
- <suffix domain="evenassi.no" />
- <suffix domain="evenášši.no" />
- <suffix domain="evje-og-hornnes.no" />
- <suffix domain="farsund.no" />
- <suffix domain="fauske.no" />
- <suffix domain="fuossko.no" />
- <suffix domain="fuoisku.no" />
- <suffix domain="fedje.no" />
- <suffix domain="fet.no" />
- <suffix domain="finnoy.no" />
- <suffix domain="finnÞy.no" />
- <suffix domain="fitjar.no" />
- <suffix domain="fjaler.no" />
- <suffix domain="fjell.no" />
- <suffix domain="flakstad.no" />
- <suffix domain="flatanger.no" />
- <suffix domain="flekkefjord.no" />
- <suffix domain="flesberg.no" />
- <suffix domain="flora.no" />
- <suffix domain="fla.no" />
- <suffix domain="flå.no" />
- <suffix domain="folldal.no" />
- <suffix domain="forsand.no" />
- <suffix domain="fosnes.no" />
- <suffix domain="fredrikstad.no" />
- <suffix domain="frei.no" />
- <suffix domain="frogn.no" />
- <suffix domain="froland.no" />
- <suffix domain="frosta.no" />
- <suffix domain="frana.no" />
- <suffix domain="frÊna.no" />
- <suffix domain="froya.no" />
- <suffix domain="frÞya.no" />
- <suffix domain="fusa.no" />
- <suffix domain="fyresdal.no" />
- <suffix domain="forde.no" />
- <suffix domain="fÞrde.no" />
- <suffix domain="gamvik.no" />
- <suffix domain="gangaviika.no" />
- <suffix domain="gaular.no" />
- <suffix domain="gausdal.no" />
- <suffix domain="gildeskal.no" />
- <suffix domain="gildeskål.no" />
- <suffix domain="giske.no" />
- <suffix domain="gjemnes.no" />
- <suffix domain="gjerdrum.no" />
- <suffix domain="gjerstad.no" />
- <suffix domain="gjesdal.no" />
- <suffix domain="gjovik.no" />
- <suffix domain="gjÞvik.no" />
- <suffix domain="gloppen.no" />
- <suffix domain="gol.no" />
- <suffix domain="gran.no" />
- <suffix domain="grane.no" />
- <suffix domain="granvin.no" />
- <suffix domain="gratangen.no" />
- <suffix domain="grimstad.no" />
- <suffix domain="grong.no" />
- <suffix domain="kraanghke.no" />
- <suffix domain="kråanghke.no" />
- <suffix domain="grue.no" />
- <suffix domain="gulen.no" />
- <suffix domain="hadsel.no" />
- <suffix domain="halden.no" />
- <suffix domain="halsa.no" />
- <suffix domain="hamar.no" />
- <suffix domain="hamaroy.no" />
- <suffix domain="habmer.no" />
- <suffix domain="hábmer.no" />
- <suffix domain="hapmir.no" />
- <suffix domain="hápmir.no" />
- <suffix domain="hammerfest.no" />
- <suffix domain="hammarfeasta.no" />
- <suffix domain="hámmárfeasta.no" />
- <suffix domain="haram.no" />
- <suffix domain="hareid.no" />
- <suffix domain="harstad.no" />
- <suffix domain="hasvik.no" />
- <suffix domain="aknoluokta.no" />
- <suffix domain="ákŋoluokta.no" />
- <suffix domain="hattfjelldal.no" />
- <suffix domain="aarborte.no" />
- <suffix domain="haugesund.no" />
- <suffix domain="hemne.no" />
- <suffix domain="hemnes.no" />
- <suffix domain="hemsedal.no" />
- <suffix domain="heroy.more-og-romsdal.no" />
- <suffix domain="herÞy.mÞre-og-romsdal.no" />
- <suffix domain="heroy.nordland.no" />
- <suffix domain="herÞy.nordland.no" />
- <suffix domain="hitra.no" />
- <suffix domain="hjartdal.no" />
- <suffix domain="hjelmeland.no" />
- <suffix domain="hobol.no" />
- <suffix domain="hobÞl.no" />
- <suffix domain="hof.no" />
- <suffix domain="hol.no" />
- <suffix domain="hole.no" />
- <suffix domain="holmestrand.no" />
- <suffix domain="holtalen.no" />
- <suffix domain="holtålen.no" />
- <suffix domain="hornindal.no" />
- <suffix domain="horten.no" />
- <suffix domain="hurdal.no" />
- <suffix domain="hurum.no" />
- <suffix domain="hvaler.no" />
- <suffix domain="hyllestad.no" />
- <suffix domain="hagebostad.no" />
- <suffix domain="hÊgebostad.no" />
- <suffix domain="hoyanger.no" />
- <suffix domain="hÞyanger.no" />
- <suffix domain="hoylandet.no" />
- <suffix domain="hÞylandet.no" />
- <suffix domain="ha.no" />
- <suffix domain="hå.no" />
- <suffix domain="ibestad.no" />
- <suffix domain="inderoy.no" />
- <suffix domain="inderÞy.no" />
- <suffix domain="iveland.no" />
- <suffix domain="jevnaker.no" />
- <suffix domain="jondal.no" />
- <suffix domain="jolster.no" />
- <suffix domain="jÞlster.no" />
- <suffix domain="karasjok.no" />
- <suffix domain="karasjohka.no" />
- <suffix domain="kárášjohka.no" />
- <suffix domain="karlsoy.no" />
- <suffix domain="galsa.no" />
- <suffix domain="gálsá.no" />
- <suffix domain="karmoy.no" />
- <suffix domain="karmÞy.no" />
- <suffix domain="kautokeino.no" />
- <suffix domain="guovdageaidnu.no" />
- <suffix domain="klepp.no" />
- <suffix domain="klabu.no" />
- <suffix domain="klÊbu.no" />
- <suffix domain="kongsberg.no" />
- <suffix domain="kongsvinger.no" />
- <suffix domain="kragero.no" />
- <suffix domain="kragerÞ.no" />
- <suffix domain="kristiansand.no" />
- <suffix domain="kristiansund.no" />
- <suffix domain="krodsherad.no" />
- <suffix domain="krÞdsherad.no" />
- <suffix domain="kvalsund.no" />
- <suffix domain="rahkkeravju.no" />
- <suffix domain="ráhkkerávju.no" />
- <suffix domain="kvam.no" />
- <suffix domain="kvinesdal.no" />
- <suffix domain="kvinnherad.no" />
- <suffix domain="kviteseid.no" />
- <suffix domain="kvitsoy.no" />
- <suffix domain="kvitsÞy.no" />
- <suffix domain="kvafjord.no" />
- <suffix domain="kvÊfjord.no" />
- <suffix domain="giehtavuoatna.no" />
- <suffix domain="kvanangen.no" />
- <suffix domain="kvÊnangen.no" />
- <suffix domain="navuotna.no" />
- <suffix domain="návuotna.no" />
- <suffix domain="kafjord.no" />
- <suffix domain="kåfjord.no" />
- <suffix domain="gaivuotna.no" />
- <suffix domain="gáivuotna.no" />
- <suffix domain="larvik.no" />
- <suffix domain="lavangen.no" />
- <suffix domain="lavagis.no" />
- <suffix domain="loabat.no" />
- <suffix domain="loabát.no" />
- <suffix domain="lebesby.no" />
- <suffix domain="davvesiida.no" />
- <suffix domain="leikanger.no" />
- <suffix domain="leirfjord.no" />
- <suffix domain="leka.no" />
- <suffix domain="leksvik.no" />
- <suffix domain="lenvik.no" />
- <suffix domain="leangaviika.no" />
- <suffix domain="lea?gaviika.no" />
- <suffix domain="lesja.no" />
- <suffix domain="levanger.no" />
- <suffix domain="lier.no" />
- <suffix domain="lierne.no" />
- <suffix domain="lillehammer.no" />
- <suffix domain="lillesand.no" />
- <suffix domain="lindesnes.no" />
- <suffix domain="lindas.no" />
- <suffix domain="lindås.no" />
- <suffix domain="lom.no" />
- <suffix domain="loppa.no" />
- <suffix domain="lahppi.no" />
- <suffix domain="láhppi.no" />
- <suffix domain="lund.no" />
- <suffix domain="lunner.no" />
- <suffix domain="luroy.no" />
- <suffix domain="lurÞy.no" />
- <suffix domain="luster.no" />
- <suffix domain="lyngdal.no" />
- <suffix domain="lyngen.no" />
- <suffix domain="ivgu.no" />
- <suffix domain="lardal.no" />
- <suffix domain="lerdal.no" />
- <suffix domain="lÊrdal.no" />
- <suffix domain="lodingen.no" />
- <suffix domain="lÞdingen.no" />
- <suffix domain="lorenskog.no" />
- <suffix domain="lÞrenskog.no" />
- <suffix domain="loten.no" />
- <suffix domain="lÞten.no" />
- <suffix domain="malvik.no" />
- <suffix domain="masoy.no" />
- <suffix domain="måsÞy.no" />
- <suffix domain="muosat.no" />
- <suffix domain="muosát.no" />
- <suffix domain="mandal.no" />
- <suffix domain="marker.no" />
- <suffix domain="marnardal.no" />
- <suffix domain="masfjorden.no" />
- <suffix domain="meland.no" />
- <suffix domain="meldal.no" />
- <suffix domain="melhus.no" />
- <suffix domain="meloy.no" />
- <suffix domain="melÞy.no" />
- <suffix domain="meraker.no" />
- <suffix domain="meråker.no" />
- <suffix domain="moareke.no" />
- <suffix domain="moåreke.no" />
- <suffix domain="midsund.no" />
- <suffix domain="midtre-gauldal.no" />
- <suffix domain="modalen.no" />
- <suffix domain="modum.no" />
- <suffix domain="molde.no" />
- <suffix domain="moskenes.no" />
- <suffix domain="moss.no" />
- <suffix domain="mosvik.no" />
- <suffix domain="malselv.no" />
- <suffix domain="målselv.no" />
- <suffix domain="malatvuopmi.no" />
- <suffix domain="málatvuopmi.no" />
- <suffix domain="namdalseid.no" />
- <suffix domain="aejrie.no" />
- <suffix domain="namsos.no" />
- <suffix domain="namsskogan.no" />
- <suffix domain="naamesjevuemie.no" />
- <suffix domain="nååmesjevuemie.no" />
- <suffix domain="laakesvuemie.no" />
- <suffix domain="nannestad.no" />
- <suffix domain="narvik.no" />
- <suffix domain="narviika.no" />
- <suffix domain="naustdal.no" />
- <suffix domain="nedre-eiker.no" />
- <suffix domain="nes.akershus.no" />
- <suffix domain="nes.buskerud.no" />
- <suffix domain="nesna.no" />
- <suffix domain="nesodden.no" />
- <suffix domain="nesseby.no" />
- <suffix domain="unjarga.no" />
- <suffix domain="unjárga.no" />
- <suffix domain="nesset.no" />
- <suffix domain="nissedal.no" />
- <suffix domain="nittedal.no" />
- <suffix domain="nord-aurdal.no" />
- <suffix domain="nord-fron.no" />
- <suffix domain="nord-odal.no" />
- <suffix domain="norddal.no" />
- <suffix domain="nordkapp.no" />
- <suffix domain="davvenjarga.no" />
- <suffix domain="davvenjárga.no" />
- <suffix domain="nordre-land.no" />
- <suffix domain="nordreisa.no" />
- <suffix domain="raisa.no" />
- <suffix domain="ráisa.no" />
- <suffix domain="nore-og-uvdal.no" />
- <suffix domain="notodden.no" />
- <suffix domain="naroy.no" />
- <suffix domain="nÊrÞy.no" />
- <suffix domain="notteroy.no" />
- <suffix domain="nÞtterÞy.no" />
- <suffix domain="odda.no" />
- <suffix domain="oksnes.no" />
- <suffix domain="`Þksnes.no" />
- <suffix domain="oppdal.no" />
- <suffix domain="oppegard.no" />
- <suffix domain="oppegård.no" />
- <suffix domain="orkdal.no" />
- <suffix domain="orland.no" />
- <suffix domain="Þrland.no" />
- <suffix domain="orskog.no" />
- <suffix domain="Þrskog.no" />
- <suffix domain="orsta.no" />
- <suffix domain="Þrsta.no" />
- <suffix domain="os.hedmark.no" />
- <suffix domain="os.hordaland.no" />
- <suffix domain="osen.no" />
- <suffix domain="osteroy.no" />
- <suffix domain="osterÞy.no" />
- <suffix domain="ostre-toten.no" />
- <suffix domain="Þstre-toten.no" />
- <suffix domain="overhalla.no" />
- <suffix domain="ovre-eiker.no" />
- <suffix domain="Þvre-eiker.no" />
- <suffix domain="oyer.no" />
- <suffix domain="Þyer.no" />
- <suffix domain="oygarden.no" />
- <suffix domain="Þygarden.no" />
- <suffix domain="oystre-slidre.no" />
- <suffix domain="Þystre-slidre.no" />
- <suffix domain="porsanger.no" />
- <suffix domain="porsangu.no" />
- <suffix domain="porsáŋgu.no" />
- <suffix domain="porsgrunn.no" />
- <suffix domain="radoy.no" />
- <suffix domain="radÞy.no" />
- <suffix domain="rakkestad.no" />
- <suffix domain="rana.no" />
- <suffix domain="ruovat.no" />
- <suffix domain="randaberg.no" />
- <suffix domain="rauma.no" />
- <suffix domain="rendalen.no" />
- <suffix domain="rennebu.no" />
- <suffix domain="rennesoy.no" />
- <suffix domain="rennesÞy.no" />
- <suffix domain="rindal.no" />
- <suffix domain="ringebu.no" />
- <suffix domain="ringerike.no" />
- <suffix domain="ringsaker.no" />
- <suffix domain="rissa.no" />
- <suffix domain="risor.no" />
- <suffix domain="risÞr.no" />
- <suffix domain="roan.no" />
- <suffix domain="rollag.no" />
- <suffix domain="rygge.no" />
- <suffix domain="ralingen.no" />
- <suffix domain="rÊlingen.no" />
- <suffix domain="rodoy.no" />
- <suffix domain="rÞdÞy.no" />
- <suffix domain="romskog.no" />
- <suffix domain="rÞmskog.no" />
- <suffix domain="roros.no" />
- <suffix domain="rÞros.no" />
- <suffix domain="rost.no" />
- <suffix domain="rÞst.no" />
- <suffix domain="royken.no" />
- <suffix domain="rÞyken.no" />
- <suffix domain="royrvik.no" />
- <suffix domain="rÞyrvik.no" />
- <suffix domain="rade.no" />
- <suffix domain="råde.no" />
- <suffix domain="salangen.no" />
- <suffix domain="siellak.no" />
- <suffix domain="saltdal.no" />
- <suffix domain="sálát.no" />
- <suffix domain="sálat.no" />
- <suffix domain="samnanger.no" />
- <suffix domain="sande.more-og-romsdal.no" />
- <suffix domain="sande.mÞre-og-romsdal.no" />
- <suffix domain="sande.vestfold.no" />
- <suffix domain="sandefjord.no" />
- <suffix domain="sandnes.no" />
- <suffix domain="sandoy.no" />
- <suffix domain="sandÞy.no" />
- <suffix domain="sarpsborg.no" />
- <suffix domain="sauda.no" />
- <suffix domain="sauherad.no" />
- <suffix domain="sel.no" />
- <suffix domain="selbu.no" />
- <suffix domain="selje.no" />
- <suffix domain="seljord.no" />
- <suffix domain="sigdal.no" />
- <suffix domain="siljan.no" />
- <suffix domain="sirdal.no" />
- <suffix domain="skaun.no" />
- <suffix domain="skedsmo.no" />
- <suffix domain="ski.no" />
- <suffix domain="skien.no" />
- <suffix domain="skiptvet.no" />
- <suffix domain="skjervoy.no" />
- <suffix domain="skjervÞy.no" />
- <suffix domain="skierva.no" />
- <suffix domain="skiervá.no" />
- <suffix domain="skjak.no" />
- <suffix domain="skjåk.no" />
- <suffix domain="skodje.no" />
- <suffix domain="skanland.no" />
- <suffix domain="skånland.no" />
- <suffix domain="skanit.no" />
- <suffix domain="skánit.no" />
- <suffix domain="smola.no" />
- <suffix domain="smÞla.no" />
- <suffix domain="snillfjord.no" />
- <suffix domain="snasa.no" />
- <suffix domain="snåsa.no" />
- <suffix domain="snoasa.no" />
- <suffix domain="snaase.no" />
- <suffix domain="snåase.no" />
- <suffix domain="sogndal.no" />
- <suffix domain="sokndal.no" />
- <suffix domain="sola.no" />
- <suffix domain="solund.no" />
- <suffix domain="songdalen.no" />
- <suffix domain="sortland.no" />
- <suffix domain="spydeberg.no" />
- <suffix domain="stange.no" />
- <suffix domain="stavanger.no" />
- <suffix domain="steigen.no" />
- <suffix domain="steinkjer.no" />
- <suffix domain="stjordal.no" />
- <suffix domain="stjÞrdal.no" />
- <suffix domain="stokke.no" />
- <suffix domain="stor-elvdal.no" />
- <suffix domain="stord.no" />
- <suffix domain="stordal.no" />
- <suffix domain="storfjord.no" />
- <suffix domain="omasvuotna.no" />
- <suffix domain="strand.no" />
- <suffix domain="stranda.no" />
- <suffix domain="stryn.no" />
- <suffix domain="sula.no" />
- <suffix domain="suldal.no" />
- <suffix domain="sund.no" />
- <suffix domain="sunndal.no" />
- <suffix domain="surnadal.no" />
- <suffix domain="sveio.no" />
- <suffix domain="svelvik.no" />
- <suffix domain="sykkylven.no" />
- <suffix domain="sogne.no" />
- <suffix domain="sÞgne.no" />
- <suffix domain="somna.no" />
- <suffix domain="sÞmna.no" />
- <suffix domain="sondre-land.no" />
- <suffix domain="sÞndre-land.no" />
- <suffix domain="sor-aurdal.no" />
- <suffix domain="sÞr-aurdal.no" />
- <suffix domain="sor-fron.no" />
- <suffix domain="sÞr-fron.no" />
- <suffix domain="sor-odal.no" />
- <suffix domain="sÞr-odal.no" />
- <suffix domain="sor-varanger.no" />
- <suffix domain="sÞr-varanger.no" />
- <suffix domain="matta-varjjat.no" />
- <suffix domain="mátta-várjjat.no" />
- <suffix domain="sorfold.no" />
- <suffix domain="sÞrfold.no" />
- <suffix domain="sorreisa.no" />
- <suffix domain="sÞrreisa.no" />
- <suffix domain="sorum.no" />
- <suffix domain="sÞrum.no" />
- <suffix domain="tana.no" />
- <suffix domain="deatnu.no" />
- <suffix domain="time.no" />
- <suffix domain="tingvoll.no" />
- <suffix domain="tinn.no" />
- <suffix domain="tjeldsund.no" />
- <suffix domain="dielddanuorri.no" />
- <suffix domain="tjome.no" />
- <suffix domain="tjÞme.no" />
- <suffix domain="tokke.no" />
- <suffix domain="tolga.no" />
- <suffix domain="torsken.no" />
- <suffix domain="tranoy.no" />
- <suffix domain="tranÞy.no" />
- <suffix domain="tromso.no" />
- <suffix domain="tromsÞ.no" />
- <suffix domain="tromsa.no" />
- <suffix domain="romsa.no" />
- <suffix domain="trondheim.no" />
- <suffix domain="troandin.no" />
- <suffix domain="trysil.no" />
- <suffix domain="trana.no" />
- <suffix domain="trÊna.no" />
- <suffix domain="trogstad.no" />
- <suffix domain="trÞgstad.no" />
- <suffix domain="tvedestrand.no" />
- <suffix domain="tydal.no" />
- <suffix domain="tynset.no" />
- <suffix domain="tysfjord.no" />
- <suffix domain="divtasvuodna.no" />
- <suffix domain="divttasvuotna.no" />
- <suffix domain="tysnes.no" />
- <suffix domain="tysvar.no" />
- <suffix domain="tysvÊr.no" />
- <suffix domain="tonsberg.no" />
- <suffix domain="tÞnsberg.no" />
- <suffix domain="ullensaker.no" />
- <suffix domain="ullensvang.no" />
- <suffix domain="ulvik.no" />
- <suffix domain="utsira.no" />
- <suffix domain="vadso.no" />
- <suffix domain="vadsÞ.no" />
- <suffix domain="cahcesuolo.no" />
- <suffix domain="cáhcesuolo.no" />
- <suffix domain="vaksdal.no" />
- <suffix domain="valle.no" />
- <suffix domain="vang.no" />
- <suffix domain="vanylven.no" />
- <suffix domain="vardo.no" />
- <suffix domain="vardÞ.no" />
- <suffix domain="varggat.no" />
- <suffix domain="várggát.no" />
- <suffix domain="vefsn.no" />
- <suffix domain="vaapste.no" />
- <suffix domain="vega.no" />
- <suffix domain="vegarshei.no" />
- <suffix domain="vegårshei.no" />
- <suffix domain="vennesla.no" />
- <suffix domain="verdal.no" />
- <suffix domain="verran.no" />
- <suffix domain="vestby.no" />
- <suffix domain="vestnes.no" />
- <suffix domain="vestre-slidre.no" />
- <suffix domain="vestre-toten.no" />
- <suffix domain="vestvagoy.no" />
- <suffix domain="vestvågÞy.no" />
- <suffix domain="vevelstad.no" />
- <suffix domain="vik.no" />
- <suffix domain="vikna.no" />
- <suffix domain="vindafjord.no" />
- <suffix domain="volda.no" />
- <suffix domain="voss.no" />
- <suffix domain="varoy.no" />
- <suffix domain="vÊrÞy.no" />
- <suffix domain="vagan.no" />
- <suffix domain="vågan.no" />
- <suffix domain="voagat.no" />
- <suffix domain="vagsoy.no" />
- <suffix domain="vågsÞy.no" />
- <suffix domain="vaga.no" />
- <suffix domain="vågå.no" />
- <suffix domain="valer.ostfold.no" />
- <suffix domain="våler.Þstfold.no" />
- <suffix domain="valer.hedmark.no" />
- <suffix domain="våler.hedmark.no" />
-
- <!-- np : http://www.mos.com.np/register.html-- >
-
- <!-- nr : http://cenpac.net.nr/dns/index.html-- >
- <suffix domain="biz.nr" />
- <suffix domain="info.nr" />
- <suffix domain="gov.nr" />
- <suffix domain="edu.nr" />
- <suffix domain="org.nr" />
- <suffix domain="net.nr" />
- <suffix domain="com.nr" />
-
- <!-- nu : http://en.wikipedia.org/wiki/.nu-- >
-
- <!-- nz : http://en.wikipedia.org/wiki/.nz-- >
-
- <!-- om : http://en.wikipedia.org/wiki/.om-- >
-
- <!-- org : http://en.wikipedia.org/wiki/.og-- >
-
- <!-- pa : http://www.nic.pa/-- >
-
- <!-- pe : http://www.nic.pe/normas-proced-i.htm-- >
-
- <!-- pf : http://www.gobin.info/domainname/formulaire-pf.pdf-- >
- <suffix domain="com.pf" />
- <suffix domain="org.pf" />
- <suffix domain="edu.pf" />
-
- <!-- pg : http://en.wikipedia.org/wiki/.pg-- >
-
- <!-- ph : http://www.domains.ph/FAQ2.asp-- >
- <!-- list of 2nd level tlds ?-->
- <suffix domain="com.ph" />
- <suffix domain="net.ph" />
- <suffix domain="org.ph" />
- <suffix domain="gov.ph" />
- <suffix domain="edu.ph" />
- <suffix domain="ngo.ph" />
- <suffix domain="mil.ph" />
-
- <!-- pk : http://pk5.pknic.net.pk/pk5/msgNamepk.PK-- >
- <suffix domain="com.pk" />
- <suffix domain="net.pk" />
- <suffix domain="edu.pk" />
- <suffix domain="org.pk" />
- <suffix domain="fam.pk" />
- <suffix domain="biz.pk" />
- <suffix domain="web.pk" />
- <suffix domain="gov.pk" />
- <suffix domain="gob.pk" />
- <suffix domain="gok.pk" />
- <suffix domain="gon.pk" />
- <suffix domain="gop.pk" />
- <suffix domain="gos.pk" />
- <suffix domain="goa.pk" />
- <suffix domain="info.pk" />
-
- <!-- pl : http://www.dns.pl/english/-- >
- <!-- NASK functional domains (nask.pl / dns.pl) : http://www.dns.pl/english/dns-funk.html-- >
- <suffix domain="aid.pl" />
- <suffix domain="agro.pl" />
- <suffix domain="atm.pl" />
- <suffix domain="auto.pl" />
- <suffix domain="biz.pl" />
- <suffix domain="com.pl" />
- <suffix domain="edu.pl" />
- <suffix domain="gmina.pl" />
- <suffix domain="gsm.pl" />
- <suffix domain="info.pl" />
- <suffix domain="mail.pl" />
- <suffix domain="miasta.pl" />
- <suffix domain="media.pl" />
- <suffix domain="mil.pl" />
- <suffix domain="net.pl" />
- <suffix domain="nieruchomosci.pl" />
- <suffix domain="nom.pl" />
- <suffix domain="org.pl" />
- <suffix domain="pc.pl" />
- <suffix domain="powiat.pl" />
- <suffix domain="priv.pl" />
- <suffix domain="realestate.pl" />
- <suffix domain="rel.pl" />
- <suffix domain="sex.pl" />
- <suffix domain="shop.pl" />
- <suffix domain="sklep.pl" />
- <suffix domain="sos.pl" />
- <suffix domain="szkola.pl" />
- <suffix domain="targi.pl" />
- <suffix domain="tm.pl" />
- <suffix domain="tourism.pl" />
- <suffix domain="travel.pl" />
- <suffix domain="turystyka.pl" />
- <!-- ICM functional domains (icm.edu.pl)-->
- <suffix domain="6bone.pl" />
- <suffix domain="art.pl" />
- <suffix domain="mbone.pl" />
- <!-- Government domains (administred by ippt.gov.pl)-->
- <suffix domain="gov.pl" />
- <suffix domain="uw.gov.pl" />
- <suffix domain="um.gov.pl" />
- <suffix domain="ug.gov.pl" />
- <suffix domain="upow.gov.pl" />
- <suffix domain="starostwo.gov.pl" />
- <suffix domain="so.gov.pl" />
- <suffix domain="sr.gov.pl" />
- <suffix domain="po.gov.pl" />
- <suffix domain="pa.gov.pl" />
- <!-- other functional domains-->
- <suffix domain="med.pl" />
- <suffix domain="ngo.pl" />
- <suffix domain="irc.pl" />
- <suffix domain="usenet.pl" />
- <!-- NASK geographical domains : http://www.dns.pl/english/dns-regiony.html-- >
- <suffix domain="augustow.pl" />
- <suffix domain="babia-gora.pl" />
- <suffix domain="bedzin.pl" />
- <suffix domain="beskidy.pl" />
- <suffix domain="bialowieza.pl" />
- <suffix domain="bialystok.pl" />
- <suffix domain="bielawa.pl" />
- <suffix domain="bieszczady.pl" />
- <suffix domain="boleslawiec.pl" />
- <suffix domain="bydgoszcz.pl" />
- <suffix domain="bytom.pl" />
- <suffix domain="cieszyn.pl" />
- <suffix domain="czeladz.pl" />
- <suffix domain="czest.pl" />
- <suffix domain="dlugoleka.pl" />
- <suffix domain="elblag.pl" />
- <suffix domain="elk.pl" />
- <suffix domain="glogow.pl" />
- <suffix domain="gniezno.pl" />
- <suffix domain="gorlice.pl" />
- <suffix domain="grajewo.pl" />
- <suffix domain="ilawa.pl" />
- <suffix domain="jaworzno.pl" />
- <suffix domain="jelenia-gora.pl" />
- <suffix domain="jgora.pl" />
- <suffix domain="kalisz.pl" />
- <suffix domain="kazimierz-dolny.pl" />
- <suffix domain="karpacz.pl" />
- <suffix domain="kartuzy.pl" />
- <suffix domain="kaszuby.pl" />
- <suffix domain="katowice.pl" />
- <suffix domain="kepno.pl" />
- <suffix domain="ketrzyn.pl" />
- <suffix domain="klodzko.pl" />
- <suffix domain="kobierzyce.pl" />
- <suffix domain="kolobrzeg.pl" />
- <suffix domain="konin.pl" />
- <suffix domain="konskowola.pl" />
- <suffix domain="kutno.pl" />
- <suffix domain="lapy.pl" />
- <suffix domain="lebork.pl" />
- <suffix domain="legnica.pl" />
- <suffix domain="lezajsk.pl" />
- <suffix domain="limanowa.pl" />
- <suffix domain="lomza.pl" />
- <suffix domain="lowicz.pl" />
- <suffix domain="lubin.pl" />
- <suffix domain="lukow.pl" />
- <suffix domain="malbork.pl" />
- <suffix domain="malopolska.pl" />
- <suffix domain="mazowsze.pl" />
- <suffix domain="mazury.pl" />
- <suffix domain="mielec.pl" />
- <suffix domain="mielno.pl" />
- <suffix domain="mragowo.pl" />
- <suffix domain="naklo.pl" />
- <suffix domain="nowaruda.pl" />
- <suffix domain="nysa.pl" />
- <suffix domain="olawa.pl" />
- <suffix domain="olecko.pl" />
- <suffix domain="olkusz.pl" />
- <suffix domain="olsztyn.pl" />
- <suffix domain="opoczno.pl" />
- <suffix domain="opole.pl" />
- <suffix domain="ostroda.pl" />
- <suffix domain="ostroleka.pl" />
- <suffix domain="ostrowiec.pl" />
- <suffix domain="ostrowwlkp.pl" />
- <suffix domain="pila.pl" />
- <suffix domain="pisz.pl" />
- <suffix domain="podhale.pl" />
- <suffix domain="podlasie.pl" />
- <suffix domain="polkowice.pl" />
- <suffix domain="pomorze.pl" />
- <suffix domain="pomorskie.pl" />
- <suffix domain="prochowice.pl" />
- <suffix domain="pruszkow.pl" />
- <suffix domain="przeworsk.pl" />
- <suffix domain="pulawy.pl" />
- <suffix domain="radom.pl" />
- <suffix domain="rawa-maz.pl" />
- <suffix domain="rybnik.pl" />
- <suffix domain="rzeszow.pl" />
- <suffix domain="sanok.pl" />
- <suffix domain="sejny.pl" />
- <suffix domain="slask.pl" />
- <suffix domain="slupsk.pl" />
- <suffix domain="sosnowiec.pl" />
- <suffix domain="stalowa-wola.pl" />
- <suffix domain="skoczow.pl" />
- <suffix domain="starachowice.pl" />
- <suffix domain="stargard.pl" />
- <suffix domain="suwalki.pl" />
- <suffix domain="swidnica.pl" />
- <suffix domain="swiebodzin.pl" />
- <suffix domain="swinoujscie.pl" />
- <suffix domain="szczecin.pl" />
- <suffix domain="szczytno.pl" />
- <suffix domain="tarnobrzeg.pl" />
- <suffix domain="tgory.pl" />
- <suffix domain="turek.pl" />
- <suffix domain="tychy.pl" />
- <suffix domain="ustka.pl" />
- <suffix domain="walbrzych.pl" />
- <suffix domain="warmia.pl" />
- <suffix domain="warszawa.pl" />
- <suffix domain="waw.pl" />
- <suffix domain="wegrow.pl" />
- <suffix domain="wielun.pl" />
- <suffix domain="wlocl.pl" />
- <suffix domain="wloclawek.pl" />
- <suffix domain="wodzislaw.pl" />
- <suffix domain="wolomin.pl" />
- <suffix domain="wroclaw.pl" />
- <suffix domain="zachpomor.pl" />
- <suffix domain="zagan.pl" />
- <suffix domain="zarow.pl" />
- <suffix domain="zgora.pl" />
- <suffix domain="zgorzelec.pl" />
- <!-- TASK geographical domains (www.task.gda.pl/uslugi/dns)-- >
- <suffix domain="gda.pl" />
- <suffix domain="gdansk.pl" />
- <suffix domain="gdynia.pl" />
- <suffix domain="sopot.pl" />
- <!-- other geographical domains-->
- <suffix domain="gliwice.pl" />
- <suffix domain="krakow.pl" />
- <suffix domain="poznan.pl" />
- <suffix domain="wroc.pl" />
- <suffix domain="zakopane.pl" />
-
- <!-- pn : http://www.government.pn/PnRegistry/policies.htm-- >
- <suffix domain="gov.pn" />
- <suffix domain="co.pn" />
- <suffix domain="org.pn" />
- <suffix domain="edu.pn" />
- <suffix domain="net.pn" />
-
- <!-- pr : http://www.nic.pr/index.asp?f=1-- >
- <suffix domain="com.pr" />
- <suffix domain="net.pr" />
- <suffix domain="org.pr" />
- <suffix domain="gov.pr" />
- <suffix domain="edu.pr" />
- <suffix domain="isla.pr" />
- <suffix domain="pro.pr" />
- <suffix domain="biz.pr" />
- <suffix domain="info.pr" />
- <suffix domain="name.pr" />
- <!-- these aren't mentioned on nic.pr, but on http://en.wikipedia.org/wiki/.pr-- >
- <suffix domain="est.pr" />
- <suffix domain="prof.pr" />
- <suffix domain="ac.pr" />
-
- <!-- pro : http://www.nic.pro/support_faq.htm-- >
- <suffix domain="aca.pro" />
- <suffix domain="bar.pro" />
- <suffix domain="cpa.pro" />
- <suffix domain="jur.pro" />
- <suffix domain="law.pro" />
- <suffix domain="med.pro" />
- <suffix domain="eng.pro" />
-
- <!-- ps : http://en.wikipedia.org/wiki/.ps-- >
- <!-- list of 2nd level tlds ?-->
- <suffix domain="edu.ps" />
- <suffix domain="gov.ps" />
- <suffix domain="sec.ps" />
- <suffix domain="plo.ps" />
- <suffix domain="com.ps" />
- <suffix domain="org.ps" />
- <suffix domain="net.ps" />
-
- <!-- pt : http://online.dns.pt/dns/start_dns-- >
- <suffix domain="net.pt" />
- <suffix domain="gov.pt" />
- <suffix domain="org.pt" />
- <suffix domain="edu.pt" />
- <suffix domain="int.pt" />
- <suffix domain="publ.pt" />
- <suffix domain="com.pt" />
- <suffix domain="nome.pt" />
-
- <!-- pw : http://en.wikipedia.org/wiki/.pw-- >
-
- <!-- py : http://www.nic.py/faq_a.html#faq_b-- >
-
- <!-- qa : http://www.qatar.net.qa/services/virtual.htm-- >
-
- <!-- re : http://www.afnic.re/obtenir/chartes/nommage-re/annexe-descriptifs-- >
- <suffix domain="com.re" />
- <suffix domain="asso.re" />
- <suffix domain="nom.re" />
-
- <!-- ro : http://www.rotld.ro/-- >
- <suffix domain="com.ro" />
- <suffix domain="org.ro" />
- <suffix domain="tm.ro" />
- <suffix domain="nt.ro" />
- <suffix domain="nom.ro" />
- <suffix domain="info.ro" />
- <suffix domain="rec.ro" />
- <suffix domain="arts.ro" />
- <suffix domain="firm.ro" />
- <suffix domain="store.ro" />
- <suffix domain="www.ro " />
-
- <!-- ru : http://en.wikipedia.org/wiki/.ru-- >
- <suffix domain="com.ru" />
- <suffix domain="net.ru" />
- <suffix domain="org.ru" />
- <suffix domain="pp.ru" />
- <suffix domain="int.ru" />
- <!-- there should be geo-names like msk.ru, but I didn't find a list-->
-
- <!-- rw : http://www.nic.rw/cgi-bin/policy.pl-- >
- <suffix domain="gov.rw" />
- <suffix domain="net.rw" />
- <suffix domain="edu.rw" />
- <suffix domain="ac.rw" />
- <suffix domain="com.rw" />
- <suffix domain="co.rw" />
- <suffix domain="int.rw" />
- <suffix domain="mil.rw" />
- <suffix domain="gouv.rw" />
-
- <!-- sa : http://www.saudinic.net.sa/page.php?page=1&lang=1-- >
-
- <!-- sb : http://www.sbnic.net.sb/-- >
-
- <!-- sc : http://www.nic.sc/-- >
- <suffix domain="com.sc" />
- <suffix domain="gov.sc" />
- <suffix domain="net.sc" />
- <suffix domain="org.sc" />
- <suffix domain="edu.sc" />
-
- <!-- sd : http://www.isoc.sd/sudanic.isoc.sd/billing_pricing.htm-- >
- <suffix domain="com.sd" />
- <suffix domain="net.sd" />
- <suffix domain="org.sd" />
- <suffix domain="edu.sd" />
- <suffix domain="med.sd" />
- <suffix domain="tv.sd" />
- <suffix domain="gov.sd" />
- <suffix domain="info.sd" />
-
- <!-- se : http://en.wikipedia.org/wiki/.se-- >
- <suffix domain="org.se" />
- <suffix domain="pp.se" />
- <suffix domain="tm.se" />
- <suffix domain="parti.se" />
- <suffix domain="press.se" />
- <suffix domain="mil.se" />
- <!-- se geographical names-->
- <suffix domain="ab.se" />
- <suffix domain="c.se" />
- <suffix domain="d.se" />
- <suffix domain="e.se" />
- <suffix domain="f.se" />
- <suffix domain="g.se" />
- <suffix domain="h.se" />
- <suffix domain="i.se" />
- <suffix domain="k.se" />
- <suffix domain="m.se" />
- <suffix domain="n.se" />
- <suffix domain="o.se" />
- <suffix domain="s.se" />
- <suffix domain="t.se" />
- <suffix domain="u.se" />
- <suffix domain="w.se" />
- <suffix domain="x.se" />
- <suffix domain="y.se" />
- <suffix domain="z.se" />
- <suffix domain="ac.se" />
- <suffix domain="bd.se" />
-
- <!-- sg : http://www.nic.net.sg/sub_policies_agreement/2ld.html-- >
- <suffix domain="com.sg" />
- <suffix domain="net.sg" />
- <suffix domain="org.sg" />
- <suffix domain="gov.sg" />
- <suffix domain="edu.sg" />
- <suffix domain="per.sg" />
-
- <!-- sh : http://www.nic.sh/rules.html-- >
- <!-- list of 2nd level domains ?-->
-
- <!-- si : http://en.wikipedia.org/wiki/.si-- >
-
- <!-- sk : http://en.wikipedia.org/wiki/.sk-- >
-
- <!-- sl : http://en.wikipedia.org/wiki/.sl-- >
- <!-- list of 2nd level domains ?-->
-
- <!-- sm : http://en.wikipedia.org/wiki/.sm-- >
-
- <!-- sn : http://en.wikipedia.org/wiki/.sn-- >
- <!-- list of 2nd level domains ?-->
-
- <!-- sr : http://en.wikipedia.org/wiki/.sr-- >
-
- <!-- st : http://www.nic.st/html/policyrules/-- >
-
- <!-- su : http://en.wikipedia.org/wiki/.su-- >
-
- <!-- sv : http://www.svnet.org.sv/svpolicy.html-- >
-
- <!-- sy : http://www.gobin.info/domainname/sy.doc-- >
-
- <!-- sz : http://en.wikipedia.org/wiki/.sz-- >
- <!-- list of 2nd level domains ?-->
-
- <!-- tc : http://en.wikipedia.org/wiki/.tc-- >
-
- <!-- td : http://en.wikipedia.org/wiki/.td-- >
-
- <!-- tf : http://en.wikipedia.org/wiki/.tf-- >
-
- <!-- tg : http://en.wikipedia.org/wiki/.tg-- >
- <!-- list of 2nd level domains ?-->
-
- <!-- th : http://en.wikipedia.org/wiki/.th-- >
-
- <!-- tj : http://www.nic.tj/policy.htm-- >
- <suffix domain="ac.tj" />
- <suffix domain="biz.tj" />
- <suffix domain="com.tj" />
- <suffix domain="co.tj" />
- <suffix domain="edu.tj" />
- <suffix domain="int.tj" />
- <suffix domain="name.tj" />
- <suffix domain="net.tj" />
- <suffix domain="org.tj" />
- <suffix domain="web.tj" />
- <suffix domain="gov.tj" />
- <suffix domain="go.tj" />
- <suffix domain="mil.tj" />
-
- <!-- tk : http://en.wikipedia.org/wiki/.tk-- >
-
- <!-- tl : http://en.wikipedia.org/wiki/.tl-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- tm : http://www.nic.tm/rules.html-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- tn : http://en.wikipedia.org/wiki/.tn-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- to : http://en.wikipedia.org/wiki/.to-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- tr : http://en.wikipedia.org/wiki/.tr-- >
-
- <!-- travel : http://en.wikipedia.org/wiki/.travel-- >
-
- <!-- tt : http://www.nic.tt/-- >
- <suffix domain="co.tt" />
- <suffix domain="com.tt" />
- <suffix domain="org.tt" />
- <suffix domain="net.tt" />
- <suffix domain="biz.tt" />
- <suffix domain="info.tt" />
- <suffix domain="pro.tt" />
- <suffix domain="int.tt" />
- <suffix domain="coop.tt" />
- <suffix domain="jobs.tt" />
- <suffix domain="mobi.tt" />
- <suffix domain="travel.tt" />
- <suffix domain="museum.tt" />
- <suffix domain="aero.tt" />
- <suffix domain="name.tt" />
- <suffix domain="gov.tt" />
- <suffix domain="edu.tt" />
-
- <!-- tv : http://en.wikipedia.org/wiki/.tv-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- tw : http://en.wikipedia.org/wiki/.tw-- >
- <suffix domain="edu.tw" />
- <suffix domain="gov.tw" />
- <suffix domain="mil.tw" />
- <suffix domain="com.tw" />
- <suffix domain="net.tw" />
- <suffix domain="org.tw" />
- <suffix domain="idv.tw" />
- <suffix domain="game.tw" />
- <suffix domain="ebiz.tw" />
- <suffix domain="club.tw" />
- <suffix domain="網路.tw" />
- <suffix domain="組織.tw" />
- <suffix domain="商æ¥Â.tw" />
-
- <!-- tz : http://en.wikipedia.org/wiki/.tz-- >
-
- <!-- ua : http://www.nic.net.ua/-- >
- <suffix domain="com.ua" />
- <suffix domain="edu.ua" />
- <suffix domain="gov.ua" />
- <suffix domain="net.ua" />
- <suffix domain="org.ua" />
- <!-- ua geo-names-->
- <suffix domain="cherkassy.ua" />
- <suffix domain="chernigov.ua" />
- <suffix domain="chernovtsy.ua" />
- <suffix domain="ck.ua" />
- <suffix domain="cn.ua" />
- <suffix domain="crimea.ua" />
- <suffix domain="cv.ua" />
- <suffix domain="dn.ua" />
- <suffix domain="dnepropetrovsk.ua" />
- <suffix domain="donetsk.ua" />
- <suffix domain="dp.ua" />
- <suffix domain="if.ua" />
- <suffix domain="ivano-frankivsk.ua" />
- <suffix domain="kh.ua" />
- <suffix domain="kharkov.ua" />
- <suffix domain="kherson.ua" />
- <suffix domain="kiev.ua" />
- <suffix domain="kirovograd.ua" />
- <suffix domain="km.ua" />
- <suffix domain="kr.ua" />
- <suffix domain="ks.ua" />
- <suffix domain="lg.ua" />
- <suffix domain="lugansk.ua" />
- <suffix domain="lutsk.ua" />
- <suffix domain="lviv.ua" />
- <suffix domain="mk.ua" />
- <suffix domain="nikolaev.ua" />
- <suffix domain="od.ua" />
- <suffix domain="odessa.ua" />
- <suffix domain="pl.ua" />
- <suffix domain="poltava.ua" />
- <suffix domain="rovno.ua" />
- <suffix domain="rv.ua" />
- <suffix domain="sebastopol.ua" />
- <suffix domain="sumy.ua" />
- <suffix domain="te.ua" />
- <suffix domain="ternopil.ua" />
- <suffix domain="vinnica.ua" />
- <suffix domain="vn.ua" />
- <suffix domain="zaporizhzhe.ua" />
- <suffix domain="zp.ua" />
- <suffix domain="uz.ua" />
- <suffix domain="uzhgorod.ua" />
- <suffix domain="zhitomir.ua" />
- <suffix domain="zt.ua" />
-
- <!-- ug : http://www.registry.co.ug/-- >
- <suffix domain="co.ug" />
- <suffix domain="ac.ug" />
- <suffix domain="sc.ug" />
- <suffix domain="go.ug" />
- <suffix domain="ne.ug" />
- <suffix domain="or.ug" />
-
- <!-- uk : http://en.wikipedia.org/wiki/.uk-- >
- <suffix domain="sch.uk" />
- <suffix domain="bl.uk" />
- <suffix domain="british-library.uk" />
- <suffix domain="icnet.uk" />
- <suffix domain="jet.uk" />
- <suffix domain="nel.uk" />
- <suffix domain="nls.uk" />
- <suffix domain="national-library-scotland.uk" />
- <suffix domain="parliament.uk" />
-
- <!-- us : http://en.wikipedia.org/wiki/.us-- >
- <suffix domain="dni.us" />
- <suffix domain="fed.us" />
- <suffix domain="isa.us" />
- <suffix domain="kids.us" />
- <suffix domain="nsn.us" />
- <!-- us geographic names-->
- <suffix domain="ak.us" />
- <suffix domain="al.us" />
- <suffix domain="ar.us" />
- <suffix domain="az.us" />
- <suffix domain="ca.us" />
- <suffix domain="co.us" />
- <suffix domain="ct.us" />
- <suffix domain="dc.us" />
- <suffix domain="de.us" />
- <suffix domain="fl.us" />
- <suffix domain="ga.us" />
- <suffix domain="hi.us" />
- <suffix domain="ia.us" />
- <suffix domain="id.us" />
- <suffix domain="il.us" />
- <suffix domain="in.us" />
- <suffix domain="ks.us" />
- <suffix domain="ky.us" />
- <suffix domain="la.us" />
- <suffix domain="ma.us" />
- <suffix domain="md.us" />
- <suffix domain="me.us" />
- <suffix domain="mi.us" />
- <suffix domain="mn.us" />
- <suffix domain="mo.us" />
- <suffix domain="ms.us" />
- <suffix domain="mt.us" />
- <suffix domain="nc.us" />
- <suffix domain="nd.us" />
- <suffix domain="ne.us" />
- <suffix domain="nh.us" />
- <suffix domain="nj.us" />
- <suffix domain="nm.us" />
- <suffix domain="nv.us" />
- <suffix domain="ny.us" />
- <suffix domain="oh.us" />
- <suffix domain="ok.us" />
- <suffix domain="or.us" />
- <suffix domain="pa.us" />
- <suffix domain="ri.us" />
- <suffix domain="sc.us" />
- <suffix domain="sd.us" />
- <suffix domain="tn.us" />
- <suffix domain="tx.us" />
- <suffix domain="ut.us" />
- <suffix domain="vt.us" />
- <suffix domain="va.us" />
- <suffix domain="wa.us" />
- <suffix domain="wi.us" />
- <suffix domain="wv.us" />
- <suffix domain="wy.us" />
- <!-- the following rules would be only valid under the geo-name, but we can't express that-->
- <!-- *.*.us cities, counties, parishes, and townships (locality.state.us)-->
- <!-- !ci.*.*.us city government agencies (subdomain under locality)-->
- <!-- !town.*.*.us town government agencies (subdomain under locality)-->
- <!-- !co.*.*.us county government agencies (subdomain under locality)-->
- <!-- k12.*.us public school districts-->
- <!-- pvt.k12.*.us private schools-->
- <!-- cc.*.us community colleges-->
- <!-- tec.*.us technical and vocational schools-->
- <!-- lib.*.us state, regional, city, and county libraries-->
- <!-- state.*.us state government agencies-->
- <!-- gen.*.us general independent entities (groups not fitting into the above categories)-->
-
- <!-- uy : http://www.antel.com.uy/-- >
-
- <!-- uz : http://www.reg.uz/registerr.html-- >
- <!-- are there other 2nd level tlds ?-->
- <suffix domain="com.uz" />
- <suffix domain="co.uz" />
-
- <!-- va : http://en.wikipedia.org/wiki/.va-- >
-
- <!-- vc : http://en.wikipedia.org/wiki/.vc-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- ve : http://registro.nic.ve/nicve/registro/index.html-- >
-
- <!-- vg : http://en.wikipedia.org/wiki/.vg-- >
-
- <!-- vi : http://www.nic.vi/Domain_Rules/body_domain_rules.html-- >
- <suffix domain="com.vi" />
- <suffix domain="org.vi" />
- <suffix domain="edu.vi" />
- <suffix domain="gov.vi" />
-
- <!-- vn : https://www.dot.vn/vnnic/vnnic/domainregistration.jsp-- >
- <suffix domain="com.vn" />
- <suffix domain="net.vn" />
- <suffix domain="org.vn" />
- <suffix domain="edu.vn" />
- <suffix domain="gov.vn" />
- <suffix domain="int.vn" />
- <suffix domain="ac.vn" />
- <suffix domain="biz.vn" />
- <suffix domain="info.vn" />
- <suffix domain="name.vn" />
- <suffix domain="pro.vn" />
- <suffix domain="health.vn" />
-
- <!-- vu : http://en.wikipedia.org/wiki/.vu-- >
- <!-- list of 2nd level tlds ?-->
-
- <!-- ws : http://en.wikipedia.org/wiki/.ws-- >
-
- <!-- ye : http://www.y.net.ye/services/domain_name.htm-- >
-
- <!-- yu : http://www.nic.yu/pravilnik-e.html-- >
-
- <!-- za : http://www.zadna.org.za/slds.html-- >
-
- <!-- zm : http://en.wikipedia.org/wiki/.zm-- >
-
- <!-- zw : http://en.wikipedia.org/wiki/.zw-- >
-
- </suffixes>
-</domains>
diff --git a/search-server/nutch/crawl_jsp/conf/domain-suffixes.xsd b/search-server/nutch/crawl_jsp/conf/domain-suffixes.xsd
deleted file mode 100644
index ba68d62..0000000
--- a/search-server/nutch/crawl_jsp/conf/domain-suffixes.xsd
+++ /dev/null
@@ -1,130 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- Document : domain-suffixes.xsd
- Author : Enis Soztutar - enis.soz.nutch(a)gmail.com
- Description: This document is the schema for valid domain-suffixes
- definitions. For successful parsing of domain-suffixes xml files,
- the xml file should be validated with this xsd.
- See : org.apache.nutch.util.domain.DomainSuffixesReader.java
--->
-
-<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema "
- targetNamespace="http://lucene.apache.org/nutch "
- xmlns="http://lucene.apache.org/nutch "
- elementFormDefault="qualified">
-
- <xs:element name="domains">
- <xs:complexType>
- <xs:sequence>
- <xs:element name="tlds">
- <xs:complexType>
- <xs:sequence>
- <xs:element name="itlds">
- <xs:complexType>
- <xs:sequence>
- <xs:element name="tld" maxOccurs="unbounded"
- type="gtld" />
- </xs:sequence>
- </xs:complexType>
- </xs:element>
-
- <xs:element name="gtlds">
- <xs:complexType>
- <xs:sequence>
- <xs:element name="tld" maxOccurs="unbounded"
- type="gtld" />
- </xs:sequence>
- </xs:complexType>
- </xs:element>
-
- <xs:element name="cctlds">
- <xs:complexType>
- <xs:sequence>
- <xs:element name="tld" maxOccurs="unbounded"
- type="cctld" />
- </xs:sequence>
- </xs:complexType>
- </xs:element>
-
- </xs:sequence>
- </xs:complexType>
- </xs:element>
-
- <xs:element name="suffixes">
- <xs:complexType>
- <xs:sequence>
- <xs:element name="suffix" maxOccurs="unbounded"
- type="sldType" />
- </xs:sequence>
- </xs:complexType>
- </xs:element>
- </xs:sequence>
- </xs:complexType>
- </xs:element>
-
- <xs:complexType name="gtld">
- <xs:sequence>
- <xs:element name="status" minOccurs="0">
- <xs:simpleType>
- <xs:restriction base="xs:string">
- <xs:enumeration value="INFRASTRUCTURE" />
- <xs:enumeration value="SPONSORED" />
- <xs:enumeration value="UNSPONSORED" />
- <xs:enumeration value="STARTUP" />
- <xs:enumeration value="PROPOSED" />
- <xs:enumeration value="DELETED" />
- <xs:enumeration value="PSEUDO_DOMAIN" />
- </xs:restriction>
- </xs:simpleType>
- </xs:element>
- <xs:element name="boost" type="xs:float" minOccurs="0" />
- <xs:element name="description" type="xs:string" minOccurs="0" />
- </xs:sequence>
- <xs:attribute name="domain" type="xs:string" />
- </xs:complexType>
-
- <xs:complexType name="cctld">
- <xs:sequence>
- <xs:element name="country" type="xs:string" />
- <xs:element name="status" type="statusType" minOccurs="0" />
- <xs:element name="boost" type="xs:float" minOccurs="0" />
- <xs:element name="description" type="xs:string" minOccurs="0" />
- </xs:sequence>
- <xs:attribute name="domain" type="xs:string" />
- </xs:complexType>
-
- <xs:complexType name="sldType">
- <xs:sequence>
- <xs:element name="status" type="statusType" minOccurs="0" />
- <xs:element name="boost" type="xs:float" minOccurs="0" />
- <xs:element name="description" type="xs:string" minOccurs="0" />
- </xs:sequence>
- <xs:attribute name="domain" type="xs:string" />
- </xs:complexType>
-
- <xs:simpleType name="statusType">
- <xs:restriction base="xs:string">
- <xs:enumeration value="IN_USE" />
- <xs:enumeration value="NOT_IN_USE" />
- <xs:enumeration value="DELETED" />
- </xs:restriction>
- </xs:simpleType>
-
-</xs:schema>
diff --git a/search-server/nutch/crawl_jsp/conf/hadoop-env.sh b/search-server/nutch/crawl_jsp/conf/hadoop-env.sh
deleted file mode 100644
index 9050a6e..0000000
--- a/search-server/nutch/crawl_jsp/conf/hadoop-env.sh
+++ /dev/null
@@ -1,33 +0,0 @@
-# Set Hadoop-specific environment variables here.
-
-# The only required environment variable is JAVA_HOME. All others are
-# optional. When running a distributed configuration it is best to
-# set JAVA_HOME in this file, so that it is correctly defined on
-# remote nodes.
-
-# The java implementation to use. Required.
-# export JAVA_HOME=/usr/bin/java
-
-# The maximum amount of heap to use, in MB. Default is 1000.
-# export HADOOP_HEAPSIZE=2000
-
-# Extra Java runtime options. Empty by default.
-# export HADOOP_OPTS=-server
-
-# Extra ssh options. Default: '-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR'.
-# export HADOOP_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR"
-
-# Where log files are stored. $HADOOP_HOME/logs by default.
-# export HADOOP_LOG_DIR=${HADOOP_HOME}/logs
-
-# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.
-# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
-
-# host:path where hadoop code should be rsync'd from. Unset by default.
-# export HADOOP_MASTER=master:/home/$USER/src/hadoop
-
-# The directory where pid files are stored. /tmp by default.
-# export HADOOP_PID_DIR=/var/hadoop/pids
-
-# A string representing this instance of hadoop. $USER by default.
-# export HADOOP_IDENT_STRING=$USER
diff --git a/search-server/nutch/crawl_jsp/conf/hadoop-site.xml b/search-server/nutch/crawl_jsp/conf/hadoop-site.xml
deleted file mode 100644
index 970c8fe..0000000
--- a/search-server/nutch/crawl_jsp/conf/hadoop-site.xml
+++ /dev/null
@@ -1,8 +0,0 @@
-<?xml version="1.0"?>
-<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
-
-<!-- Put site-specific property overrides in this file. -->
-
-<configuration>
-
-</configuration>
diff --git a/search-server/nutch/crawl_jsp/conf/httpclient-auth.xml b/search-server/nutch/crawl_jsp/conf/httpclient-auth.xml
deleted file mode 100644
index 60d45b9..0000000
--- a/search-server/nutch/crawl_jsp/conf/httpclient-auth.xml
+++ /dev/null
@@ -1,61 +0,0 @@
-<?xml version="1.0"?>
-<!--
- This is the authentication configuration file for protocol-httpclient.
- Different credentials for different authentication scopes can be
- configured in this file. If a set of credentials is configured for a
- particular authentication scope (i.e. particular host, port number,
- scheme and realm), then that set of credentials would be sent only to
- servers falling under the specified authentication scope. Apart from
- this at most one set of credentials can be configured as 'default'.
-
- When authentication is required to fetch a resource from a web-server,
- the authentication-scope is determined from the host, port, scheme and
- realm (if present) obtained from the URL of the page and the
- authentication headers in the HTTP response. If it matches any
- 'authscope' in this configuration file, then the 'credentials' for
- that 'authscope' is used for authentication. Otherwise, it would use
- the 'default' set of credentials (with an exception which is described
- in the next paragraph), if present. If any attribute is missing, it
- would match all values for that attribute.
-
- If there are several pages having different authentication realms and
- schemes on the same web-server (same host and port, but different
- realms and schemes), and credentials for one or more of the realms and
- schemes for that web-server is specified, then the 'default'
- credentials would be ignored completely for that web-server (for that
- host and port). So, credentials to handle all realms and schemes for
- that server may be specified explicitly by adding an extra 'authscope'
- tag with the 'realm' and 'scheme' attributes missing for that server.
- This is demonstrated by the last 'authscope' tag for 'example:8080' in
- the following example.
-
- Example:-
- <credentials username="susam" password="masus">
- <default realm="sso"/>
- <authscope host="192.168.101.33" port="80" realm="login"/>
- <authscope host="example" port="8080" realm="blogs"/>
- <authscope host="example" port="8080" realm="wiki"/>
- <authscope host="example" port="80" realm="quiz" scheme="NTLM"/>
- </credentials>
- <credentials username="admin" password="nimda">
- <authscope host="example" port="8080"/>
- </credentials>
-
- In the above example, 'example:8080' server has pages with multiple
- authentication realms. The first set of credentials would be used for
- 'blogs' and 'wiki' authentication realms. The second set of
- credentials would be used for all other realms. For 'login' realm of
- '192.168.101.33', the first set of credentials would be used. For any
- other realm of '192.168.101.33' authentication would not be done. For
- the NTLM authentication required by 'example:80', the first set of
- credentials would be used. For 'sso' realms of all other servers, the
- first set of credentials would be used, since it is configured as
- 'default'.
-
- NTLM does not use the notion of realms. The domain name may be
- specified as the value for 'realm' attribute in case of NTLM.
--->
-
-<auth-configuration>
-
-</auth-configuration>
diff --git a/search-server/nutch/crawl_jsp/conf/log4j.properties b/search-server/nutch/crawl_jsp/conf/log4j.properties
deleted file mode 100644
index 5a985ab..0000000
--- a/search-server/nutch/crawl_jsp/conf/log4j.properties
+++ /dev/null
@@ -1,82 +0,0 @@
-# Define some default values that can be overridden by system properties
-hadoop.log.dir=.
-hadoop.log.file=hadoop.log
-
-# RootLogger - DailyRollingFileAppender
-log4j.rootLogger=ALL,DRFA
-
-# Logging Threshold
-log4j.threshhold=ALL
-
-#special logging requirements for some commandline tools
-log4j.logger.org.apache.nutch.crawl.Crawl=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.Injector=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.Generator=INFO,cmdstdout
-log4j.logger.org.apache.nutch.fetcher.Fetcher=INFO,cmdstdout
-log4j.logger.org.apache.nutch.parse.ParseSegment=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.CrawlDbReader=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.CrawlDbMerger=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.LinkDbReader=INFO,cmdstdout
-log4j.logger.org.apache.nutch.segment.SegmentReader=INFO,cmdstdout
-log4j.logger.org.apache.nutch.segment.SegmentMerger=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.CrawlDb=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.LinkDb=INFO,cmdstdout
-log4j.logger.org.apache.nutch.crawl.LinkDbMerger=INFO,cmdstdout
-log4j.logger.org.apache.nutch.indexer.Indexer=INFO,cmdstdout
-log4j.logger.org.apache.nutch.indexer.DeleteDuplicates=INFO,cmdstdout
-log4j.logger.org.apache.nutch.indexer.IndexMerger=INFO,cmdstdout
-
-log4j.logger.org.apache.nutch=INFO
-log4j.logger.org.apache.hadoop=WARN
-
-#
-# Daily Rolling File Appender
-#
-
-log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
-log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
-
-# Rollver at midnight
-log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
-
-# 30-day backup
-#log4j.appender.DRFA.MaxBackupIndex=30
-log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
-
-# Pattern format: Date LogLevel LoggerName LogMessage
-log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
-# Debugging Pattern format: Date LogLevel LoggerName (FileName:MethodName:LineNo) LogMessage
-#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
-
-
-#
-# stdout
-# Add *stdout* to rootlogger above if you want to use this
-#
-
-log4j.appender.stdout=org.apache.log4j.ConsoleAppender
-log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
-log4j.appender.stdout.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
-
-#
-# plain layout used for commandline tools to output to console
-#
-log4j.appender.cmdstdout=org.apache.log4j.ConsoleAppender
-log4j.appender.cmdstdout.layout=org.apache.log4j.PatternLayout
-log4j.appender.cmdstdout.layout.ConversionPattern=%m%n
-
-#
-# Rolling File Appender
-#
-
-#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
-#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
-
-# Logfile size and and 30-day backups
-#log4j.appender.RFA.MaxFileSize=1MB
-#log4j.appender.RFA.MaxBackupIndex=30
-
-#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
-#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
-#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
-
diff --git a/search-server/nutch/crawl_jsp/conf/logging.properties b/search-server/nutch/crawl_jsp/conf/logging.properties
deleted file mode 100644
index 67b4a73..0000000
--- a/search-server/nutch/crawl_jsp/conf/logging.properties
+++ /dev/null
@@ -1,4 +0,0 @@
-handlers= java.util.logging.ConsoleHandler
-.level= FINE
-
-
diff --git a/search-server/nutch/crawl_jsp/conf/masters b/search-server/nutch/crawl_jsp/conf/masters
deleted file mode 100644
index 2fbb50c..0000000
--- a/search-server/nutch/crawl_jsp/conf/masters
+++ /dev/null
@@ -1 +0,0 @@
-localhost
diff --git a/search-server/nutch/crawl_jsp/conf/nutch-conf.xsl b/search-server/nutch/crawl_jsp/conf/nutch-conf.xsl
deleted file mode 100644
index 36a2275..0000000
--- a/search-server/nutch/crawl_jsp/conf/nutch-conf.xsl
+++ /dev/null
@@ -1,24 +0,0 @@
-<?xml version="1.0"?>
-<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform " version="1.0">
-<xsl:output method="html"/>
-<xsl:template match="nutch-conf">
-<html>
-<body>
-<table border="1">
-<tr>
- <td>name</td>
- <td>value</td>
- <td>description</td>
-</tr>
-<xsl:for-each select="property">
-<tr>
- <td><xsl:value-of select="name"/></td>
- <td><xsl:value-of select="value"/></td>
- <td><xsl:value-of select="description"/></td>
-</tr>
-</xsl:for-each>
-</table>
-</body>
-</html>
-</xsl:template>
-</xsl:stylesheet>
diff --git a/search-server/nutch/crawl_jsp/conf/nutch-default.xml b/search-server/nutch/crawl_jsp/conf/nutch-default.xml
deleted file mode 100644
index 2bf0e1e..0000000
--- a/search-server/nutch/crawl_jsp/conf/nutch-default.xml
+++ /dev/null
@@ -1,1205 +0,0 @@
-<?xml version="1.0"?>
-<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-<!-- Do not modify this file directly. Instead, copy entries that you -->
-<!-- wish to modify from this file into nutch-site.xml and change them -->
-<!-- there. If nutch-site.xml does not already exist, create it. -->
-
-<configuration>
-
-<!-- file properties -->
-
-<property>
- <name>file.content.limit</name>
- <value>65536</value>
- <description>The length limit for downloaded content, in bytes.
- If this value is nonnegative (>=0), content longer than it will be truncated;
- otherwise, no truncation at all.
- </description>
-</property>
-
-<property>
- <name>file.content.ignored</name>
- <value>true</value>
- <description>If true, no file content will be saved during fetch.
- And it is probably what we want to set most of time, since file:// URLs
- are meant to be local and we can always use them directly at parsing
- and indexing stages. Otherwise file contents will be saved.
- !! NO IMPLEMENTED YET !!
- </description>
-</property>
-
-<!-- HTTP properties -->
-
-<property>
- <name>http.agent.name</name>
- <value></value>
- <description>HTTP 'User-Agent' request header. MUST NOT be empty -
- please set this to a single word uniquely related to your organization.
-
- NOTE: You should also check other related properties:
-
- http.robots.agents
- http.agent.description
- http.agent.url
- http.agent.email
- http.agent.version
-
- and set their values appropriately.
-
- </description>
-</property>
-
-<property>
- <name>http.robots.agents</name>
- <value>*</value>
- <description>The agent strings we'll look for in robots.txt files,
- comma-separated, in decreasing order of precedence. You should
- put the value of http.agent.name as the first agent name, and keep the
- default * at the end of the list. E.g.: BlurflDev,Blurfl,*
- </description>
-</property>
-
-<property>
- <name>http.robots.403.allow</name>
- <value>true</value>
- <description>Some servers return HTTP status 403 (Forbidden) if
- /robots.txt doesn't exist. This should probably mean that we are
- allowed to crawl the site nonetheless. If this is set to false,
- then such sites will be treated as forbidden.</description>
-</property>
-
-<property>
- <name>http.agent.description</name>
- <value></value>
- <description>Further description of our bot- this text is used in
- the User-Agent header. It appears in parenthesis after the agent name.
- </description>
-</property>
-
-<property>
- <name>http.agent.url</name>
- <value></value>
- <description>A URL to advertise in the User-Agent header. This will
- appear in parenthesis after the agent name. Custom dictates that this
- should be a URL of a page explaining the purpose and behavior of this
- crawler.
- </description>
-</property>
-
-<property>
- <name>http.agent.email</name>
- <value></value>
- <description>An email address to advertise in the HTTP 'From' request
- header and User-Agent header. A good practice is to mangle this
- address (e.g. 'info at example dot com') to avoid spamming.
- </description>
-</property>
-
-<property>
- <name>http.agent.version</name>
- <value>Nutch-1.0-dev</value>
- <description>A version string to advertise in the User-Agent
- header.</description>
-</property>
-
-<property>
- <name>http.agent.host</name>
- <value></value>
- <description>Name or IP address of the host on which the Nutch crawler
- would be running. Currently this is used by 'protocol-httpclient'
- plugin.
- </description>
-</property>
-
-<property>
- <name>http.timeout</name>
- <value>10000</value>
- <description>The default network timeout, in milliseconds.</description>
-</property>
-
-<property>
- <name>http.max.delays</name>
- <value>100</value>
- <description>The number of times a thread will delay when trying to
- fetch a page. Each time it finds that a host is busy, it will wait
- fetcher.server.delay. After http.max.delays attepts, it will give
- up on the page for now.</description>
-</property>
-
-<property>
- <name>http.content.limit</name>
- <value>65536</value>
- <description>The length limit for downloaded content, in bytes.
- If this value is nonnegative (>=0), content longer than it will be truncated;
- otherwise, no truncation at all.
- </description>
-</property>
-
-<property>
- <name>http.proxy.host</name>
- <value></value>
- <description>The proxy hostname. If empty, no proxy is used.</description>
-</property>
-
-<property>
- <name>http.proxy.port</name>
- <value></value>
- <description>The proxy port.</description>
-</property>
-
-<property>
- <name>http.proxy.username</name>
- <value></value>
- <description>Username for proxy. This will be used by
- 'protocol-httpclient', if the proxy server requests basic, digest
- and/or NTLM authentication. To use this, 'protocol-httpclient' must
- be present in the value of 'plugin.includes' property.
- NOTE: For NTLM authentication, do not prefix the username with the
- domain, i.e. 'susam' is correct whereas 'DOMAIN\susam' is incorrect.
- </description>
-</property>
-
-<property>
- <name>http.proxy.password</name>
- <value></value>
- <description>Password for proxy. This will be used by
- 'protocol-httpclient', if the proxy server requests basic, digest
- and/or NTLM authentication. To use this, 'protocol-httpclient' must
- be present in the value of 'plugin.includes' property.
- </description>
-</property>
-
-<property>
- <name>http.proxy.realm</name>
- <value></value>
- <description>Authentication realm for proxy. Do not define a value
- if realm is not required or authentication should take place for any
- realm. NTLM does not use the notion of realms. Specify the domain name
- of NTLM authentication as the value for this property. To use this,
- 'protocol-httpclient' must be present in the value of
- 'plugin.includes' property.
- </description>
-</property>
-
-<property>
- <name>http.auth.file</name>
- <value>httpclient-auth.xml</value>
- <description>Authentication configuration file for
- 'protocol-httpclient' plugin.
- </description>
-</property>
-
-<property>
- <name>http.verbose</name>
- <value>false</value>
- <description>If true, HTTP will log more verbosely.</description>
-</property>
-
-<property>
- <name>http.redirect.max</name>
- <value>0</value>
- <description>The maximum number of redirects the fetcher will follow when
- trying to fetch a page. If set to negative or 0, fetcher won't immediately
- follow redirected URLs, instead it will record them for later fetching.
- </description>
-</property>
-
-<property>
- <name>http.useHttp11</name>
- <value>false</value>
- <description>NOTE: at the moment this works only for protocol-httpclient.
- If true, use HTTP 1.1, if false use HTTP 1.0 .
- </description>
-</property>
-
-<!-- FTP properties -->
-
-<property>
- <name>ftp.username</name>
- <value>anonymous</value>
- <description>ftp login username.</description>
-</property>
-
-<property>
- <name>ftp.password</name>
- <value>anonymous(a)example.com</value>
- <description>ftp login password.</description>
-</property>
-
-<property>
- <name>ftp.content.limit</name>
- <value>65536</value>
- <description>The length limit for downloaded content, in bytes.
- If this value is nonnegative (>=0), content longer than it will be truncated;
- otherwise, no truncation at all.
- Caution: classical ftp RFCs never defines partial transfer and, in fact,
- some ftp servers out there do not handle client side forced close-down very
- well. Our implementation tries its best to handle such situations smoothly.
- </description>
-</property>
-
-<property>
- <name>ftp.timeout</name>
- <value>60000</value>
- <description>Default timeout for ftp client socket, in millisec.
- Please also see ftp.keep.connection below.</description>
-</property>
-
-<property>
- <name>ftp.server.timeout</name>
- <value>100000</value>
- <description>An estimation of ftp server idle time, in millisec.
- Typically it is 120000 millisec for many ftp servers out there.
- Better be conservative here. Together with ftp.timeout, it is used to
- decide if we need to delete (annihilate) current ftp.client instance and
- force to start another ftp.client instance anew. This is necessary because
- a fetcher thread may not be able to obtain next request from queue in time
- (due to idleness) before our ftp client times out or remote server
- disconnects. Used only when ftp.keep.connection is true (please see below).
- </description>
-</property>
-
-<property>
- <name>ftp.keep.connection</name>
- <value>false</value>
- <description>Whether to keep ftp connection. Useful if crawling same host
- again and again. When set to true, it avoids connection, login and dir list
- parser setup for subsequent urls. If it is set to true, however, you must
- make sure (roughly):
- (1) ftp.timeout is less than ftp.server.timeout
- (2) ftp.timeout is larger than (fetcher.threads.fetch * fetcher.server.delay)
- Otherwise there will be too many "delete client because idled too long"
- messages in thread logs.</description>
-</property>
-
-<property>
- <name>ftp.follow.talk</name>
- <value>false</value>
- <description>Whether to log dialogue between our client and remote
- server. Useful for debugging.</description>
-</property>
-
-<!-- web db properties -->
-
-<property>
- <name>db.default.fetch.interval</name>
- <value>30</value>
- <description>(DEPRECATED) The default number of days between re-fetches of a page.
- </description>
-</property>
-
-<property>
- <name>db.fetch.interval.default</name>
- <value>2592000</value>
- <description>The default number of seconds between re-fetches of a page (30 days).
- </description>
-</property>
-
-<property>
- <name>db.fetch.interval.max</name>
- <value>7776000</value>
- <description>The maximum number of seconds between re-fetches of a page
- (90 days). After this period every page in the db will be re-tried, no
- matter what is its status.
- </description>
-</property>
-
-<property>
- <name>db.fetch.schedule.class</name>
- <value>org.apache.nutch.crawl.DefaultFetchSchedule</value>
- <description>The implementation of fetch schedule. DefaultFetchSchedule simply
- adds the original fetchInterval to the last fetch time, regardless of
- page changes.</description>
-</property>
-
-<property>
- <name>db.fetch.schedule.adaptive.inc_rate</name>
- <value>0.4</value>
- <description>If a page is unmodified, its fetchInterval will be
- increased by this rate. This value should not
- exceed 0.5, otherwise the algorithm becomes unstable.</description>
-</property>
-
-<property>
- <name>db.fetch.schedule.adaptive.dec_rate</name>
- <value>0.2</value>
- <description>If a page is modified, its fetchInterval will be
- decreased by this rate. This value should not
- exceed 0.5, otherwise the algorithm becomes unstable.</description>
-</property>
-
-<property>
- <name>db.fetch.schedule.adaptive.min_interval</name>
- <value>60.0</value>
- <description>Minimum fetchInterval, in seconds.</description>
-</property>
-
-<property>
- <name>db.fetch.schedule.adaptive.max_interval</name>
- <value>31536000.0</value>
- <description>Maximum fetchInterval, in seconds (365 days).
- NOTE: this is limited by db.fetch.interval.max. Pages with
- fetchInterval larger than db.fetch.interval.max
- will be fetched anyway.</description>
-</property>
-
-<property>
- <name>db.fetch.schedule.adaptive.sync_delta</name>
- <value>true</value>
- <description>If true, try to synchronize with the time of page change.
- by shifting the next fetchTime by a fraction (sync_rate) of the difference
- between the last modification time, and the last fetch time.</description>
-</property>
-
-<property>
- <name>db.fetch.schedule.adaptive.sync_delta_rate</name>
- <value>0.3</value>
- <description>See sync_delta for description. This value should not
- exceed 0.5, otherwise the algorithm becomes unstable.</description>
-</property>
-
-<property>
- <name>db.update.additions.allowed</name>
- <value>true</value>
- <description>If true, updatedb will add newly discovered URLs, if false
- only already existing URLs in the CrawlDb will be updated and no new
- URLs will be added.
- </description>
-</property>
-
-<property>
- <name>db.ignore.internal.links</name>
- <value>true</value>
- <description>If true, when adding new links to a page, links from
- the same host are ignored. This is an effective way to limit the
- size of the link database, keeping only the highest quality
- links.
- </description>
-</property>
-
-<property>
- <name>db.ignore.external.links</name>
- <value>false</value>
- <description>If true, outlinks leading from a page to external hosts
- will be ignored. This is an effective way to limit the crawl to include
- only initially injected hosts, without creating complex URLFilters.
- </description>
-</property>
-
-<property>
- <name>db.score.injected</name>
- <value>1.0</value>
- <description>The score of new pages added by the injector.
- </description>
-</property>
-
-<property>
- <name>db.score.link.external</name>
- <value>1.0</value>
- <description>The score factor for new pages added due to a link from
- another host relative to the referencing page's score. Scoring plugins
- may use this value to affect initial scores of external links.
- </description>
-</property>
-
-<property>
- <name>db.score.link.internal</name>
- <value>1.0</value>
- <description>The score factor for pages added due to a link from the
- same host, relative to the referencing page's score. Scoring plugins
- may use this value to affect initial scores of internal links.
- </description>
-</property>
-
-<property>
- <name>db.score.count.filtered</name>
- <value>false</value>
- <description>The score value passed to newly discovered pages is
- calculated as a fraction of the original page score divided by the
- number of outlinks. If this option is false, only the outlinks that passed
- URLFilters will count, if it's true then all outlinks will count.
- </description>
-</property>
-
-<property>
- <name>db.max.inlinks</name>
- <value>10000</value>
- <description>Maximum number of Inlinks per URL to be kept in LinkDb.
- If "invertlinks" finds more inlinks than this number, only the first
- N inlinks will be stored, and the rest will be discarded.
- </description>
-</property>
-
-<property>
- <name>db.max.outlinks.per.page</name>
- <value>100</value>
- <description>The maximum number of outlinks that we'll process for a page.
- If this value is nonnegative (>=0), at most db.max.outlinks.per.page outlinks
- will be processed for a page; otherwise, all outlinks will be processed.
- </description>
-</property>
-
-<property>
- <name>db.max.anchor.length</name>
- <value>100</value>
- <description>The maximum number of characters permitted in an anchor.
- </description>
-</property>
-
-<property>
- <name>db.fetch.retry.max</name>
- <value>3</value>
- <description>The maximum number of times a url that has encountered
- recoverable errors is generated for fetch.</description>
-</property>
-
-<property>
- <name>db.signature.class</name>
- <value>org.apache.nutch.crawl.MD5Signature</value>
- <description>The default implementation of a page signature. Signatures
- created with this implementation will be used for duplicate detection
- and removal.</description>
-</property>
-
-<property>
- <name>db.signature.text_profile.min_token_len</name>
- <value>2</value>
- <description>Minimum token length to be included in the signature.
- </description>
-</property>
-
-<property>
- <name>db.signature.text_profile.quant_rate</name>
- <value>0.01</value>
- <description>Profile frequencies will be rounded down to a multiple of
- QUANT = (int)(QUANT_RATE * maxFreq), where maxFreq is a maximum token
- frequency. If maxFreq > 1 then QUANT will be at least 2, which means that
- for longer texts tokens with frequency 1 will always be discarded.
- </description>
-</property>
-
-<!-- generate properties -->
-
-<property>
- <name>generate.max.per.host</name>
- <value>-1</value>
- <description>The maximum number of urls per host in a single
- fetchlist. -1 if unlimited.</description>
-</property>
-
-<property>
- <name>generate.max.per.host.by.ip</name>
- <value>false</value>
- <description>If false, same host names are counted. If true,
- hosts' IP addresses are resolved and the same IP-s are counted.
-
- -+-+-+- WARNING !!! -+-+-+-
- When set to true, Generator will create a lot of DNS lookup
- requests, rapidly. This may cause a DOS attack on
- remote DNS servers, not to mention increased external traffic
- and latency. For these reasons when using this option it is
- required that a local caching DNS be used.</description>
-</property>
-
-<property>
- <name>generate.update.crawldb</name>
- <value>false</value>
- <description>For highly-concurrent environments, where several
- generate/fetch/update cycles may overlap, setting this to true ensures
- that generate will create different fetchlists even without intervening
- updatedb-s, at the cost of running an additional job to update CrawlDB.
- If false, running generate twice without intervening
- updatedb will generate identical fetchlists.</description>
-</property>
-
-<!-- fetcher properties -->
-
-<property>
- <name>fetcher.server.delay</name>
- <value>5.0</value>
- <description>The number of seconds the fetcher will delay between
- successive requests to the same server.</description>
-</property>
-
-<property>
- <name>fetcher.server.min.delay</name>
- <value>0.0</value>
- <description>The minimum number of seconds the fetcher will delay between
- successive requests to the same server. This value is applicable ONLY
- if fetcher.threads.per.host is greater than 1 (i.e. the host blocking
- is turned off).</description>
-</property>
-
-<property>
- <name>fetcher.max.crawl.delay</name>
- <value>30</value>
- <description>
- If the Crawl-Delay in robots.txt is set to greater than this value (in
- seconds) then the fetcher will skip this page, generating an error report.
- If set to -1 the fetcher will never skip such pages and will wait the
- amount of time retrieved from robots.txt Crawl-Delay, however long that
- might be.
- </description>
-</property>
-
-<property>
- <name>fetcher.threads.fetch</name>
- <value>10</value>
- <description>The number of FetcherThreads the fetcher should use.
- This is also determines the maximum number of requests that are
- made at once (each FetcherThread handles one connection).</description>
-</property>
-
-<property>
- <name>fetcher.threads.per.host</name>
- <value>1</value>
- <description>This number is the maximum number of threads that
- should be allowed to access a host at one time.</description>
-</property>
-
-<property>
- <name>fetcher.threads.per.host.by.ip</name>
- <value>true</value>
- <description>If true, then fetcher will count threads by IP address,
- to which the URL's host name resolves. If false, only host name will be
- used. NOTE: this should be set to the same value as
- "generate.max.per.host.by.ip" - default settings are different only for
- reasons of backward-compatibility.</description>
-</property>
-
-<property>
- <name>fetcher.verbose</name>
- <value>false</value>
- <description>If true, fetcher will log more verbosely.</description>
-</property>
-
-<property>
- <name>fetcher.parse</name>
- <value>true</value>
- <description>If true, fetcher will parse content.</description>
-</property>
-
-<property>
- <name>fetcher.store.content</name>
- <value>true</value>
- <description>If true, fetcher will store content.</description>
-</property>
-
-<!-- indexer properties -->
-
-<property>
- <name>indexer.score.power</name>
- <value>0.5</value>
- <description>Determines the power of link analyis scores. Each
- pages's boost is set to <i>score<sup>scorePower</sup></i> where
- <i>score</i> is its link analysis score and <i>scorePower</i> is the
- value of this parameter. This is compiled into indexes, so, when
- this is changed, pages must be re-indexed for it to take
- effect.</description>
-</property>
-
-<property>
- <name>indexer.max.title.length</name>
- <value>100</value>
- <description>The maximum number of characters of a title that are indexed.
- </description>
-</property>
-
-<property>
- <name>indexer.max.tokens</name>
- <value>10000</value>
- <description>
- The maximum number of tokens that will be indexed for a single field
- in a document. This limits the amount of memory required for
- indexing, so that collections with very large files will not crash
- the indexing process by running out of memory.
-
- Note that this effectively truncates large documents, excluding
- from the index tokens that occur further in the document. If you
- know your source documents are large, be sure to set this value
- high enough to accomodate the expected size. If you set it to
- -1, then the only limit is your memory, but you should anticipate
- an OutOfMemoryError.
- </description>
-</property>
-
-<property>
- <name>indexer.mergeFactor</name>
- <value>50</value>
- <description>The factor that determines the frequency of Lucene segment
- merges. This must not be less than 2, higher values increase indexing
- speed but lead to increased RAM usage, and increase the number of
- open file handles (which may lead to "Too many open files" errors).
- NOTE: the "segments" here have nothing to do with Nutch segments, they
- are a low-level data unit used by Lucene.
- </description>
-</property>
-
-<property>
- <name>indexer.minMergeDocs</name>
- <value>50</value>
- <description>This number determines the minimum number of Lucene
- Documents buffered in memory between Lucene segment merges. Larger
- values increase indexing speed and increase RAM usage.
- </description>
-</property>
-
-<property>
- <name>indexer.maxMergeDocs</name>
- <value>2147483647</value>
- <description>This number determines the maximum number of Lucene
- Documents to be merged into a new Lucene segment. Larger values
- increase batch indexing speed and reduce the number of Lucene segments,
- which reduces the number of open file handles; however, this also
- decreases incremental indexing performance.
- </description>
-</property>
-
-<property>
- <name>indexer.termIndexInterval</name>
- <value>128</value>
- <description>Determines the fraction of terms which Lucene keeps in
- RAM when searching, to facilitate random-access. Smaller values use
- more memory but make searches somewhat faster. Larger values use
- less memory but make searches somewhat slower.
- </description>
-</property>
-
-<!-- indexingfilter plugin properties -->
-
-<property>
- <name>indexingfilter.order</name>
- <value></value>
- <description>The order by which index filters are applied.
- If empty, all available index filters (as dictated by properties
- plugin-includes and plugin-excludes above) are loaded and applied in system
- defined order. If not empty, only named filters are loaded and applied
- in given order. For example, if this property has value:
- org.apache.nutch.indexer.basic.BasicIndexingFilter org.apache.nutch.indexer.more.MoreIndexingFilter
- then BasicIndexingFilter is applied first, and MoreIndexingFilter second.
-
- Filter ordering might have impact on result if one filter depends on output of
- another filter.
- </description>
-</property>
-
-
-<!-- analysis properties -->
-
-<property>
- <name>analysis.common.terms.file</name>
- <value>common-terms.utf8</value>
- <description>The name of a file containing a list of common terms
- that should be indexed in n-grams.</description>
-</property>
-
-<!-- searcher properties -->
-
-<property>
- <name>searcher.dir</name>
- <value>crawl</value>
- <description>
- Path to root of crawl. This directory is searched (in
- order) for either the file search-servers.txt, containing a list of
- distributed search servers, or the directory "index" containing
- merged indexes, or the directory "segments" containing segment
- indexes.
- </description>
-</property>
-
-<property>
- <name>searcher.filter.cache.size</name>
- <value>16</value>
- <description>
- Maximum number of filters to cache. Filters can accelerate certain
- field-based queries, like language, document format, etc. Each
- filter requires one bit of RAM per page. So, with a 10 million page
- index, a cache size of 16 consumes two bytes per page, or 20MB.
- </description>
-</property>
-
-<property>
- <name>searcher.filter.cache.threshold</name>
- <value>0.05</value>
- <description>
- Filters are cached when their term is matched by more than this
- fraction of pages. For example, with a threshold of 0.05, and 10
- million pages, the term must match more than 1/20, or 50,000 pages.
- So, if out of 10 million pages, 50% of pages are in English, and 2%
- are in Finnish, then, with a threshold of 0.05, searches for
- "lang:en" will use a cached filter, while searches for "lang:fi"
- will score all 20,000 finnish documents.
- </description>
-</property>
-
-<property>
- <name>searcher.hostgrouping.rawhits.factor</name>
- <value>2.0</value>
- <description>
- A factor that is used to determine the number of raw hits
- initially fetched, before host grouping is done.
- </description>
-</property>
-
-<property>
- <name>searcher.summary.context</name>
- <value>5</value>
- <description>
- The number of context terms to display preceding and following
- matching terms in a hit summary.
- </description>
-</property>
-
-<property>
- <name>searcher.summary.length</name>
- <value>20</value>
- <description>
- The total number of terms to display in a hit summary.
- </description>
-</property>
-
-<property>
- <name>searcher.max.hits</name>
- <value>-1</value>
- <description>If positive, search stops after this many hits are
- found. Setting this to small, positive values (e.g., 1000) can make
- searches much faster. With a sorted index, the quality of the hits
- suffers little.</description>
-</property>
-
-<property>
- <name>searcher.max.time.tick_count</name>
- <value>-1</value>
- <description>If positive value is defined here, limit search time for
- every request to this number of elapsed ticks (see the tick_length
- property below). The total maximum time for any search request will be
- then limited to tick_count * tick_length milliseconds. When search time
- is exceeded, partial results will be returned, and the total number of
- hits will be estimated.
- </description>
-</property>
-
-<property>
- <name>searcher.max.time.tick_length</name>
- <value>200</value>
- <description>The number of milliseconds between ticks. Larger values
- reduce the timer granularity (precision). Smaller values bring more
- overhead.
- </description>
-</property>
-
-<property>
- <name>searcher.num.handlers</name>
- <value>10</value>
- <description>The number of handlers for the distributed search server.
- </description>
-</property>
-
-<property>
- <name>searcher.max.hits.per.page</name>
- <value>1000</value>
- <description> The maximum number of hits to show per page. -1 if
- unlimited. If the number of hits requested by the user (via
- hitsPerPage parameter in the query string) is more than the value
- specified in this property, then this value is assumed as the number
- of hits per page.
- </description>
-</property>
-
-<!-- URL normalizer properties -->
-
-<property>
- <name>urlnormalizer.order</name>
- <value>org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer org.apache.nutch.net.urlnormalizer.regex.RegexURLNormalizer</value>
- <description>Order in which normalizers will run. If any of these isn't
- activated it will be silently skipped. If other normalizers not on the
- list are activated, they will run in random order after the ones
- specified here are run.
- </description>
-</property>
-
-<property>
- <name>urlnormalizer.regex.file</name>
- <value>regex-normalize.xml</value>
- <description>Name of the config file used by the RegexUrlNormalizer class.
- </description>
-</property>
-
-<property>
- <name>urlnormalizer.loop.count</name>
- <value>1</value>
- <description>Optionally loop through normalizers several times, to make
- sure that all transformations have been performed.
- </description>
-</property>
-
-<!-- mime properties -->
-
-<property>
- <name>mime.types.file</name>
- <value>tika-mimetypes.xml</value>
- <description>Name of file in CLASSPATH containing filename extension and
- magic sequence to mime types mapping information</description>
-</property>
-
-<property>
- <name>mime.type.magic</name>
- <value>true</value>
- <description>Defines if the mime content type detector uses magic resolution.
- </description>
-</property>
-
-<!-- plugin properties -->
-
-<property>
- <name>plugin.folders</name>
- <value>plugins</value>
- <description>Directories where nutch plugins are located. Each
- element may be a relative or absolute path. If absolute, it is used
- as is. If relative, it is searched for on the classpath.</description>
-</property>
-
-<property>
- <name>plugin.auto-activation</name>
- <value>true</value>
- <description>Defines if some plugins that are not activated regarding
- the plugin.includes and plugin.excludes properties must be automaticaly
- activated if they are needed by some actived plugins.
- </description>
-</property>
-
-<property>
- <name>plugin.includes</name>
- <value>protocol-http|urlfilter-regex|parse-(text|html|js)|index-(basic|anchor)|query-(basic|site|url)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
- <description>Regular expression naming plugin directory names to
- include. Any plugin not matching this expression is excluded.
- In any case you need at least include the nutch-extensionpoints plugin. By
- default Nutch includes crawling just HTML and plain text via HTTP,
- and basic indexing and search plugins. In order to use HTTPS please enable
- protocol-httpclient, but be aware of possible intermittent problems with the
- underlying commons-httpclient library.
- </description>
-</property>
-
-<property>
- <name>plugin.excludes</name>
- <value></value>
- <description>Regular expression naming plugin directory names to exclude.
- </description>
-</property>
-
-<!-- parser properties -->
-
-<property>
- <name>parse.plugin.file</name>
- <value>parse-plugins.xml</value>
- <description>The name of the file that defines the associations between
- content-types and parsers.</description>
-</property>
-
-<property>
- <name>parser.character.encoding.default</name>
- <value>windows-1252</value>
- <description>The character encoding to fall back to when no other information
- is available</description>
-</property>
-
-<property>
- <name>encodingdetector.charset.min.confidence</name>
- <value>-1</value>
- <description>A integer between 0-100 indicating minimum confidence value
- for charset auto-detection. Any negative value disables auto-detection.
- </description>
-</property>
-
-<property>
- <name>parser.caching.forbidden.policy</name>
- <value>content</value>
- <description>If a site (or a page) requests through its robot metatags
- that it should not be shown as cached content, apply this policy. Currently
- three keywords are recognized: "none" ignores any "noarchive" directives.
- "content" doesn't show the content, but shows summaries (snippets).
- "all" doesn't show either content or summaries.</description>
-</property>
-
-
-<property>
- <name>parser.html.impl</name>
- <value>neko</value>
- <description>HTML Parser implementation. Currently the following keywords
- are recognized: "neko" uses NekoHTML, "tagsoup" uses TagSoup.
- </description>
-</property>
-
-<property>
- <name>parser.html.form.use_action</name>
- <value>false</value>
- <description>If true, HTML parser will collect URLs from form action
- attributes. This may lead to undesirable behavior (submitting empty
- forms during next fetch cycle). If false, form action attribute will
- be ignored.</description>
-</property>
-
-<property>
- <name>parser.html.outlinks.ignore_tags</name>
- <value></value>
- <description>Comma separated list of HTML tags, from which outlinks
- shouldn't be extracted. Nutch takes links from: a, area, form, frame,
- iframe, script, link, img. If you add any of those tags here, it
- won't be taken. Default is empty list. Probably reasonable value
- for most people would be "img,script,link".</description>
-</property>
-
-
-<!-- urlfilter plugin properties -->
-
-<property>
- <name>urlfilter.regex.file</name>
- <value>regex-urlfilter.txt</value>
- <description>Name of file on CLASSPATH containing regular expressions
- used by urlfilter-regex (RegexURLFilter) plugin.</description>
-</property>
-
-<property>
- <name>urlfilter.automaton.file</name>
- <value>automaton-urlfilter.txt</value>
- <description>Name of file on CLASSPATH containing regular expressions
- used by urlfilter-automaton (AutomatonURLFilter) plugin.</description>
-</property>
-
-<property>
- <name>urlfilter.prefix.file</name>
- <value>prefix-urlfilter.txt</value>
- <description>Name of file on CLASSPATH containing url prefixes
- used by urlfilter-prefix (PrefixURLFilter) plugin.</description>
-</property>
-
-<property>
- <name>urlfilter.suffix.file</name>
- <value>suffix-urlfilter.txt</value>
- <description>Name of file on CLASSPATH containing url suffixes
- used by urlfilter-suffix (SuffixURLFilter) plugin.</description>
-</property>
-
-<property>
- <name>urlfilter.order</name>
- <value></value>
- <description>The order by which url filters are applied.
- If empty, all available url filters (as dictated by properties
- plugin-includes and plugin-excludes above) are loaded and applied in system
- defined order. If not empty, only named filters are loaded and applied
- in given order. For example, if this property has value:
- org.apache.nutch.urlfilter.regex.RegexURLFilter org.apache.nutch.urlfilter.prefix.PrefixURLFilter
- then RegexURLFilter is applied first, and PrefixURLFilter second.
- Since all filters are AND'ed, filter ordering does not have impact
- on end result, but it may have performance implication, depending
- on relative expensiveness of filters.
- </description>
-</property>
-
-<!-- scoring filters properties -->
-
-<property>
- <name>scoring.filter.order</name>
- <value></value>
- <description>The order in which scoring filters are applied.
- This may be left empty (in which case all available scoring
- filters will be applied in the order defined in plugin-includes
- and plugin-excludes), or a space separated list of implementation
- classes.
- </description>
-</property>
-
-<!-- clustering extension properties -->
-
-<property>
- <name>extension.clustering.hits-to-cluster</name>
- <value>100</value>
- <description>Number of snippets retrieved for the clustering extension
- if clustering extension is available and user requested results
- to be clustered.</description>
-</property>
-
-<property>
- <name>extension.clustering.extension-name</name>
- <value></value>
- <description>Use the specified online clustering extension. If empty,
- the first available extension will be used. The "name" here refers to an 'id'
- attribute of the 'implementation' element in the plugin descriptor XML
- file.</description>
-</property>
-
-<!-- ontology extension properties -->
-
-<property>
- <name>extension.ontology.extension-name</name>
- <value></value>
- <description>Use the specified online ontology extension. If empty,
- the first available extension will be used. The "name" here refers to an 'id'
- attribute of the 'implementation' element in the plugin descriptor XML
- file.</description>
-</property>
-
-<property>
- <name>extension.ontology.urls</name>
- <value>
- </value>
- <description>Urls of owl files, separated by spaces, such as
- http://www.example.com/ontology/time.owl
- http://www.example.com/ontology/space.owl
- http://www.example.com/ontology/wine.owl
- Or
- file:/ontology/time.owl
- file:/ontology/space.owl
- file:/ontology/wine.owl
- You have to make sure each url is valid.
- By default, there is no owl file, so query refinement based on ontology
- is silently ignored.
- </description>
-</property>
-
-<!-- query-basic plugin properties -->
-
-<property>
- <name>query.url.boost</name>
- <value>4.0</value>
- <description> Used as a boost for url field in Lucene query.
- </description>
-</property>
-
-<property>
- <name>query.anchor.boost</name>
- <value>2.0</value>
- <description> Used as a boost for anchor field in Lucene query.
- </description>
-</property>
-
-<property>
- <name>query.title.boost</name>
- <value>1.5</value>
- <description> Used as a boost for title field in Lucene query.
- </description>
-</property>
-
-<property>
- <name>query.host.boost</name>
- <value>2.0</value>
- <description> Used as a boost for host field in Lucene query.
- </description>
-</property>
-
-<property>
- <name>query.phrase.boost</name>
- <value>1.0</value>
- <description> Used as a boost for phrase in Lucene query.
- Multiplied by boost for field phrase is matched in.
- </description>
-</property>
-
-<!-- creative-commons plugin properties -->
-
-<property>
- <name>query.cc.boost</name>
- <value>0.0</value>
- <description> Used as a boost for cc field in Lucene query.
- </description>
-</property>
-
-<!-- query-more plugin properties -->
-
-<property>
- <name>query.type.boost</name>
- <value>0.0</value>
- <description> Used as a boost for type field in Lucene query.
- </description>
-</property>
-
-<!-- query-site plugin properties -->
-
-<property>
- <name>query.site.boost</name>
- <value>0.0</value>
- <description> Used as a boost for site field in Lucene query.
- </description>
-</property>
-
-<!-- microformats-reltag plugin properties -->
-
-<property>
- <name>query.tag.boost</name>
- <value>1.0</value>
- <description> Used as a boost for tag field in Lucene query.
- </description>
-</property>
-
-<!-- language-identifier plugin properties -->
-
-<property>
- <name>lang.ngram.min.length</name>
- <value>1</value>
- <description> The minimum size of ngrams to uses to identify
- language (must be between 1 and lang.ngram.max.length).
- The larger is the range between lang.ngram.min.length and
- lang.ngram.max.length, the better is the identification, but
- the slowest it is.
- </description>
-</property>
-
-<property>
- <name>lang.ngram.max.length</name>
- <value>4</value>
- <description> The maximum size of ngrams to uses to identify
- language (must be between lang.ngram.min.length and 4).
- The larger is the range between lang.ngram.min.length and
- lang.ngram.max.length, the better is the identification, but
- the slowest it is.
- </description>
-</property>
-
-<property>
- <name>lang.analyze.max.length</name>
- <value>2048</value>
- <description> The maximum bytes of data to uses to indentify
- the language (0 means full content analysis).
- The larger is this value, the better is the analysis, but the
- slowest it is.
- </description>
-</property>
-
-<property>
- <name>query.lang.boost</name>
- <value>0.0</value>
- <description> Used as a boost for lang field in Lucene query.
- </description>
-</property>
-
-<!-- Temporary Hadoop 0.17.x workaround. -->
-
-<property>
- <name>hadoop.job.history.user.location</name>
- <value>${hadoop.log.dir}/history/user</value>
- <description>Hadoop 0.17.x comes with a default setting to create
- user logs inside the output path of the job. This breaks some
- Hadoop classes, which expect the output to contain only
- part-XXXXX files. This setting changes the output to a
- subdirectory of the regular log directory.
- </description>
-</property>
-
-</configuration>
diff --git a/search-server/nutch/crawl_jsp/conf/nutch-site.xml b/search-server/nutch/crawl_jsp/conf/nutch-site.xml
deleted file mode 100644
index 70975c2..0000000
--- a/search-server/nutch/crawl_jsp/conf/nutch-site.xml
+++ /dev/null
@@ -1,58 +0,0 @@
-<?xml version="1.0"?>
-<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
-
-<!-- Put site-specific property overrides in this file. -->
-
-<configuration>
-
-<property>
- <name>http.agent.name</name>
- <value>Spacewalk</value>
- <description>HTTP 'User-Agent' request header. MUST NOT be empty -
- please set this to a single word uniquely related to your organization.
-
- NOTE: You should also check other related properties:
-
- http.robots.agents
- http.agent.description
- http.agent.url
- http.agent.email
- http.agent.version
-
- and set their values appropriately.
-
- </description>
-</property>
-
-<property>
- <name>fetcher.server.delay</name>
- <value>0</value>
- <description>The number of seconds the fetcher will delay between
- successive requests to the same server.</description>
-</property>
-
-<property>
- <name>fetcher.threads.per.host</name>
- <value>50</value>
- <description>This number is the maximum number of threads that
- should be allowed to access a host at one time.</description>
-</property>
-
-<property>
- <name>plugin.folders</name>
- <value>/usr/share/nutch/plugins</value>
- <description>Directories where nutch plugins are located. Each
- element may be a relative or absolute path. If absolute, it is used
- as is. If relative, it is searched for on the classpath.</description>
-</property>
-
-<property>
-<name>plugin.includes</name>
- <value>protocol-file|urlfilter-regex|parse-(xml|text|html|js|pdf)|index-basic|query-(basic|site|url)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
-</property>
-
-<property>
- <name>file.content.limit</name> <value>-1</value>
-</property>
-
-</configuration>
diff --git a/search-server/nutch/crawl_jsp/conf/parse-plugins.dtd b/search-server/nutch/crawl_jsp/conf/parse-plugins.dtd
deleted file mode 100644
index ae21045..0000000
--- a/search-server/nutch/crawl_jsp/conf/parse-plugins.dtd
+++ /dev/null
@@ -1,12 +0,0 @@
-<!ELEMENT parse-plugins (mimeType+,aliases)>
-<!ELEMENT mimeType (plugin+)>
-<!ATTLIST mimeType name CDATA #REQUIRED>
-
-<!ELEMENT plugin EMPTY>
-<!ATTLIST plugin id CDATA #REQUIRED>
-<!ATTLIST plugin order CDATA ''>
-
-<!ELEMENT aliases (alias+)>
-<!ELEMENT alias EMPTY>
-<!ATTLIST alias name CDATA #REQUIRED>
-<!ATTLIST alias extension-id CDATA #REQUIRED>
\ No newline at end of file
diff --git a/search-server/nutch/crawl_jsp/conf/parse-plugins.xml b/search-server/nutch/crawl_jsp/conf/parse-plugins.xml
deleted file mode 100644
index 876d188..0000000
--- a/search-server/nutch/crawl_jsp/conf/parse-plugins.xml
+++ /dev/null
@@ -1,221 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
-
- Author : mattmann
- Description: This xml file represents a natural ordering for which parsing
- plugin should get called for a particular mimeType.
--->
-
-<parse-plugins>
-
- <mimeType name="application/msword">
- <plugin id="parse-msword" />
- </mimeType>
-
- <mimeType name="application/pdf">
- <plugin id="parse-pdf" />
- </mimeType>
-
- <mimeType name="application/postscript">
- <plugin id="parse-pdf" />
- </mimeType>
-
- <mimeType name="application/rss+xml">
- <plugin id="parse-rss" />
- <plugin id="feed" />
- </mimeType>
-
- <mimeType name="application/vnd.ms-excel">
- <plugin id="parse-msexcel" />
- </mimeType>
-
- <mimeType name="application/vnd.ms-powerpoint">
- <plugin id="parse-mspowerpoint" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.text">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.text-template">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.text-master">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.text-web">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.presentation">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.presentation-template">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.spreadsheet">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.oasis.opendocument.spreadsheet-template">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.sun.xml.calc">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.sun.xml.calc.template">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.sun.xml.impress">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.sun.xml.impress.template">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.sun.xml.writer">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/vnd.sun.xml.writer.template">
- <plugin id="parse-oo" />
- </mimeType>
-
- <mimeType name="application/xhtml+xml">
- <plugin id="parse-html" />
- </mimeType>
-
- <mimeType name="application/x-bzip2">
- <!-- try and parse it with the zip parser -->
- <plugin id="parse-zip" />
- </mimeType>
-
- <mimeType name="application/x-csh">
- <plugin id="parse-text" />
- </mimeType>
-
- <mimeType name="application/x-gzip">
- <!-- try and parse it with the zip parser -->
- <plugin id="parse-zip" />
- </mimeType>
-
- <mimeType name="application/x-javascript">
- <plugin id="parse-js" />
- </mimeType>
-
- <mimeType name="application/x-kword">
- <!-- try and parse it with the word parser -->
- <plugin id="parse-msword" />
- </mimeType>
-
- <mimeType name="application/x-kspread">
- <!-- try and parse it with the msexcel parser -->
- <plugin id="parse-msexcel" />
- </mimeType>
-
- <mimeType name="application/x-shockwave-flash">
- <plugin id="parse-swf" />
- </mimeType>
-
- <mimeType name="application/zip">
- <plugin id="parse-zip" />
- </mimeType>
-
- <mimeType name="text/html">
- <plugin id="parse-html" />
- </mimeType>
-
- <mimeType name="text/plain">
- <plugin id="parse-text" />
- </mimeType>
-
- <mimeType name="text/richtext">
- <plugin id="parse-rtf" />
- <plugin id="parse-msword" />
- </mimeType>
-
- <mimeType name="text/rtf">
- <plugin id="parse-rtf" />
- <plugin id="parse-msword" />
- </mimeType>
-
- <mimeType name="text/sgml">
- <plugin id="parse-html" />
- </mimeType>
-
- <mimeType name="text/tab-separated-values">
- <plugin id="parse-msexcel" />
- </mimeType>
-
- <mimeType name="text/xml">
- <plugin id="parse-html" />
- <plugin id="parse-rss" />
- <plugin id="feed" />
- </mimeType>
-
- <!-- Types for parse-ext plugin: required for unit tests to pass. -->
-
- <mimeType name="application/vnd.nutch.example.cat">
- <plugin id="parse-ext" />
- </mimeType>
-
- <mimeType name="application/vnd.nutch.example.md5sum">
- <plugin id="parse-ext" />
- </mimeType>
-
- <!-- alias mappings for parse-xxx names to the actual extension implementation
- ids described in each plugin's plugin.xml file -->
- <aliases>
- <alias name="parse-ext" extension-id="ExtParser" />
- <alias name="parse-html"
- extension-id="org.apache.nutch.parse.html.HtmlParser" />
- <alias name="parse-js" extension-id="JSParser" />
- <alias name="parse-mp3"
- extension-id="org.apache.nutch.parse.mp3.MP3Parser" />
- <alias name="parse-msexcel"
- extension-id="org.apache.nutch.parse.msexcel.MSExcelParser" />
- <alias name="parse-mspowerpoint"
- extension-id="org.apache.nutch.parse.mspowerpoint.MSPowerPointParser" />
- <alias name="parse-msword"
- extension-id="org.apache.nutch.parse.msword.MSWordParser" />
- <alias name="parse-oo"
- extension-id="org.apache.nutch.parse.oo.OpenDocument.Text" />
- <alias name="parse-pdf"
- extension-id="org.apache.nutch.parse.pdf.PdfParser" />
- <alias name="parse-rss"
- extension-id="org.apache.nutch.parse.rss.RSSParser" />
- <alias name="feed"
- extension-id="org.apache.nutch.parse.feed.FeedParser" />
- <alias name="parse-rtf"
- extension-id="org.apache.nutch.parse.rtf.RTFParseFactory" />
- <alias name="parse-swf"
- extension-id="org.apache.nutch.parse.swf.SWFParser" />
- <alias name="parse-text"
- extension-id="org.apache.nutch.parse.text.TextParser" />
- <alias name="parse-zip"
- extension-id="org.apache.nutch.parse.zip.ZipParser" />
- </aliases>
-
-</parse-plugins>
diff --git a/search-server/nutch/crawl_jsp/conf/prefix-urlfilter.txt b/search-server/nutch/crawl_jsp/conf/prefix-urlfilter.txt
deleted file mode 100644
index 491dc1f..0000000
--- a/search-server/nutch/crawl_jsp/conf/prefix-urlfilter.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# config file for urlfilter-prefix plugin
-
-http://
-https://
-ftp://
-file://
diff --git a/search-server/nutch/crawl_jsp/conf/regex-normalize.xml b/search-server/nutch/crawl_jsp/conf/regex-normalize.xml
deleted file mode 100644
index 8d8bad1..0000000
--- a/search-server/nutch/crawl_jsp/conf/regex-normalize.xml
+++ /dev/null
@@ -1,66 +0,0 @@
-<?xml version="1.0"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-<!-- This is the configuration file for the RegexUrlNormalize Class.
- This is intended so that users can specify substitutions to be
- done on URLs. The regex engine that is used is Perl5 compatible.
- The rules are applied to URLs in the order they occur in this file. -->
-
-<!-- WATCH OUT: an xml parser reads this file an ampersands must be
- expanded to & -->
-
-<!-- The following rules show how to strip out session IDs, default pages,
- interpage anchors, etc. Order does matter! -->
-<regex-normalize>
-
-<!-- removes session ids from urls (such as jsessionid and PHPSESSID) -->
-<regex>
- <pattern>([;_]?((?i)l|j|bv_)?((?i)sid|phpsessid|sessionid)=.*?)(\?|&|#|$)</pattern>
- <substitution>$4</substitution>
-</regex>
-
-<!-- changes default pages into standard for /index.html, etc. into /
-<regex>
- <pattern>/((?i)index|default)\.((?i)js[pf]{1}?[afx]?|cgi|cfm|asp[x]?|[psx]?htm[l]?|php[3456]?)(\?|&|#|$)</pattern>
- <substitution>/$3</substitution>
-</regex> -->
-
-<!-- removes interpage href anchors such as site.com#location -->
-<regex>
- <pattern>#.*?(\?|&|$)</pattern>
- <substitution>$1</substitution>
-</regex>
-
-<!-- cleans ?&var=value into ?var=value -->
-<regex>
- <pattern>\?&</pattern>
- <substitution>\?</substitution>
-</regex>
-
-<!-- cleans multiple sequential ampersands into a single ampersand -->
-<regex>
- <pattern>&{2,}</pattern>
- <substitution>&</substitution>
-</regex>
-
-<!-- removes trailing ? -->
-<regex>
- <pattern>[\?&\.]$</pattern>
- <substitution></substitution>
-</regex>
-
-</regex-normalize>
diff --git a/search-server/nutch/crawl_jsp/conf/regex-urlfilter.txt b/search-server/nutch/crawl_jsp/conf/regex-urlfilter.txt
deleted file mode 100644
index fe56603..0000000
--- a/search-server/nutch/crawl_jsp/conf/regex-urlfilter.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-
-# The default url filter.
-# Better for whole-internet crawling.
-
-# Each non-comment, non-blank line contains a regular expression
-# prefixed by '+' or '-'. The first matching pattern in the file
-# determines whether a URL is included or ignored. If no pattern
-# matches, the URL is ignored.
-
-# skip file: ftp: and mailto: urls
--^(file|ftp|mailto):
-
-# skip image and other suffixes we can't yet parse
--\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP)$
-
-# skip URLs containing certain characters as probable queries, etc.
--[?*!@=]
-
-# skip URLs with slash-delimited segment that repeats 3+ times, to break loops
--.*(/[^/]+)/[^/]+\1/[^/]+\1/
-
-# accept anything else
-+.
diff --git a/search-server/nutch/crawl_jsp/conf/slaves b/search-server/nutch/crawl_jsp/conf/slaves
deleted file mode 100644
index 2fbb50c..0000000
--- a/search-server/nutch/crawl_jsp/conf/slaves
+++ /dev/null
@@ -1 +0,0 @@
-localhost
diff --git a/search-server/nutch/crawl_jsp/conf/subcollections.xml b/search-server/nutch/crawl_jsp/conf/subcollections.xml
deleted file mode 100644
index 7b8805d..0000000
--- a/search-server/nutch/crawl_jsp/conf/subcollections.xml
+++ /dev/null
@@ -1,28 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-<subcollections>
- <subcollection>
- <name>nutch</name>
- <id>nutch</id>
- <whitelist>
-http://lucene.apache.org/nutch/
-http://wiki.apache.org/nutch/
- </whitelist>
- <blacklist />
- </subcollection>
-</subcollections>
diff --git a/search-server/nutch/crawl_jsp/conf/suffix-urlfilter.txt b/search-server/nutch/crawl_jsp/conf/suffix-urlfilter.txt
deleted file mode 100644
index b510d4a..0000000
--- a/search-server/nutch/crawl_jsp/conf/suffix-urlfilter.txt
+++ /dev/null
@@ -1,91 +0,0 @@
-# config file for urlfilter-suffix plugin
-
-# case-insensitive, allow unknown suffixes
-+I
-# uncomment the line below to filter on url path
-#+P
-
-### prohibit these
-# pictures
-.gif
-.jpg
-.jpeg
-.bmp
-.png
-.tif
-.tiff
-.ico
-.eps
-.ps
-.wmf
-.fpx
-.cur
-.ani
-.img
-.lwf
-.pcd
-.psp
-.psd
-.tga
-.xbm
-.xpm
-
-# web-formats
-.css
-
-# archives/packages
-.arj
-.arc
-.7z
-.cab
-.lzw
-.lha
-.lzh
-.zip
-.gz
-.tar
-.tgz
-.sit
-.rpm
-.deb
-.pkg
-
-# audio/video
-.mid
-.midi
-.rmi
-.mpeg
-.mpg
-.mpe
-.mp3
-.mp2
-.aac
-.mov
-.fla
-.flv
-.ra
-.ram
-.rm
-.rmv
-.wma
-.wmv
-.wav
-.wave
-.ogg
-.avi
-.au
-.snd
-
-# executables
-.exe
-.com
-
-# windows links
-.lnk
-
-# typo3-extensions
-.t3x
-
-# disc-images
-.iso
-.bin
diff --git a/search-server/nutch/crawl_jsp/conf/tika-mimetypes.xml b/search-server/nutch/crawl_jsp/conf/tika-mimetypes.xml
deleted file mode 100644
index ce84078..0000000
--- a/search-server/nutch/crawl_jsp/conf/tika-mimetypes.xml
+++ /dev/null
@@ -1,367 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
-
- Description: This xml file defines the valid mime types used by Tika.
- The mime types within this file are based on the types in the mime-types.xml
- file available in Apache Nutch.
--->
-
-<mime-info>
-
- <mime-type type="text/plain">
- <magic priority="50">
- <match value="This is TeX," type="string" offset="0" />
- <match value="This is METAFONT," type="string" offset="0" />
- </magic>
- <glob pattern="*.txt" />
- <glob pattern="*.asc" />
- </mime-type>
-
- <mime-type type="text/html">
- <magic priority="50">
- <match value="<!DOCTYPE HTML" type="string"
- offset="0:64" />
- <match value="<!doctype html" type="string"
- offset="0:64" />
- <match value="<HEAD" type="string" offset="0:64" />
- <match value="<head" type="string" offset="0:64" />
- <match value="<TITLE" type="string" offset="0:64" />
- <match value="<title" type="string" offset="0:64" />
- <match value="<html" type="string" offset="0:64" />
- <match value="<HTML" type="string" offset="0:64" />
- <match value="<BODY" type="string" offset="0" />
- <match value="<body" type="string" offset="0" />
- <match value="<TITLE" type="string" offset="0" />
- <match value="<title" type="string" offset="0" />
- <match value="<!--" type="string" offset="0" />
- <match value="<h1" type="string" offset="0" />
- <match value="<H1" type="string" offset="0" />
- <match value="<!doctype HTML" type="string" offset="0" />
- <match value="<!DOCTYPE html" type="string" offset="0" />
- </magic>
- <glob pattern="*.html" />
- <glob pattern="*.htm" />
- </mime-type>
-
- <mime-type type="application/xhtml+xml">
- <glob pattern="*.xhtml" />
- <root-XML namespaceURI='http://www.w3.org/1999/xhtml '
- localName='html' />
- </mime-type>
-
- <mime-type type="application/vnd.ms-powerpoint">
- <glob pattern="*.ppz" />
- <glob pattern="*.ppt" />
- <glob pattern="*.pps" />
- <glob pattern="*.pot" />
- <magic priority="50">
- <match value="0xcfd0e011" type="little32" offset="0" />
- </magic>
- </mime-type>
-
- <mime-type type="application/vnd.ms-excel">
- <magic priority="50">
- <match value="Microsoft Excel 5.0 Worksheet" type="string"
- offset="2080" />
- </magic>
- <glob pattern="*.xls" />
- <glob pattern="*.xlc" />
- <glob pattern="*.xll" />
- <glob pattern="*.xlm" />
- <glob pattern="*.xlw" />
- <glob pattern="*.xla" />
- <glob pattern="*.xlt" />
- <glob pattern="*.xld" />
- <alias type="application/msexcel" />
- </mime-type>
-
- <mime-type type="application/vnd.oasis.opendocument.text">
- <glob pattern="*.odt" />
- </mime-type>
-
-
- <mime-type type="application/zip">
- <alias type="application/x-zip-compressed" />
- <magic priority="40">
- <match value="PK\003\004" type="string" offset="0" />
- </magic>
- <glob pattern="*.zip" />
- </mime-type>
-
- <mime-type type="application/vnd.oasis.opendocument.text">
- <glob pattern="*.oth" />
- </mime-type>
-
- <mime-type type="application/msword">
- <magic priority="50">
- <match value="\x31\xbe\x00\x00" type="string" offset="0" />
- <match value="PO^Q`" type="string" offset="0" />
- <match value="\376\067\0\043" type="string" offset="0" />
- <match value="\333\245-\0\0\0" type="string" offset="0" />
- <match value="Microsoft Word 6.0 Document" type="string"
- offset="2080" />
- <match value="Microsoft Word document data" type="string"
- offset="2112" />
- </magic>
- <glob pattern="*.doc" />
- <alias type="application/vnd.ms-word" />
- </mime-type>
-
- <mime-type type="application/octet-stream">
- <magic priority="50">
- <match value="\037\036" type="string" offset="0" />
- <match value="017437" type="host16" offset="0" />
- <match value="0x1fff" type="host16" offset="0" />
- <match value="\377\037" type="string" offset="0" />
- <match value="0145405" type="host16" offset="0" />
- </magic>
- <glob pattern="*.bin" />
- </mime-type>
-
- <mime-type type="application/pdf">
- <magic priority="50">
- <match value="%PDF-" type="string" offset="0" />
- </magic>
- <glob pattern="*.pdf" />
- <alias type="application/x-pdf" />
- </mime-type>
-
- <mime-type type="application/atom+xml">
- <root-XML localName="feed"
- namespaceURI="http://purl.org/atom/ns# " />
- </mime-type>
-
- <mime-type type="application/mac-binhex40">
- <glob pattern="*.hqx" />
- </mime-type>
-
- <mime-type type="application/mac-compactpro">
- <glob pattern="*.cpt" />
- </mime-type>
-
- <mime-type type="application/rtf">
- <glob pattern="*.rtf"/>
- <alias type="text/rtf" />
- </mime-type>
-
- <mime-type type="application/rss+xml">
- <alias type="text/rss" />
- <root-XML localName="rss" />
- <root-XML namespaceURI="http://purl.org/rss/1.0/ " />
- <glob pattern="*.rss" />
- </mime-type>
-
- <!-- added in by mattmann -->
- <mime-type type="application/xml">
- <alias type="text/xml" />
- <glob pattern="*.xml" />
- </mime-type>
-
- <mime-type type="application/x-mif">
- <alias type="application/vnd.mif" />
- </mime-type>
-
- <mime-type type="application/vnd.wap.wbxml">
- <glob pattern="*.wbxml" />
- </mime-type>
-
- <mime-type type="application/vnd.wap.wmlc">
- <_comment>Compiled WML Document</_comment>
- <glob pattern="*.wmlc" />
- </mime-type>
-
- <mime-type type="application/vnd.wap.wmlscriptc">
- <_comment>Compiled WML Script</_comment>
- <glob pattern="*.wmlsc" />
- </mime-type>
-
- <mime-type type="text/vnd.wap.wmlscript">
- <_comment>WML Script</_comment>
- <glob pattern="*.wmls" />
- </mime-type>
-
- <mime-type type="application/x-bzip">
- <alias type="application/x-bzip2" />
- </mime-type>
-
- <mime-type type="application/x-bzip-compressed-tar">
- <glob pattern="*.tbz" />
- <glob pattern="*.tbz2" />
- </mime-type>
-
- <mime-type type="application/x-cdlink">
- <_comment>Virtual CD-ROM CD Image File</_comment>
- <glob pattern="*.vcd" />
- </mime-type>
-
- <mime-type type="application/x-director">
- <_comment>Shockwave Movie</_comment>
- <glob pattern="*.dcr" />
- <glob pattern="*.dir" />
- <glob pattern="*.dxr" />
- </mime-type>
-
- <mime-type type="application/x-futuresplash">
- <_comment>Macromedia FutureSplash File</_comment>
- <glob pattern="*.spl" />
- </mime-type>
-
- <mime-type type="application/x-java">
- <alias type="application/java" />
- </mime-type>
-
- <mime-type type="application/x-koan">
- <_comment>SSEYO Koan File</_comment>
- <glob pattern="*.skp" />
- <glob pattern="*.skd" />
- <glob pattern="*.skt" />
- <glob pattern="*.skm" />
- </mime-type>
-
- <mime-type type="application/x-latex">
- <_comment>LaTeX Source Document</_comment>
- <glob pattern="*.latex" />
- </mime-type>
-
- <!-- JC CHANGED
- <mime-type type="application/x-mif">
- <_comment>FrameMaker MIF document</_comment>
- <glob pattern="*.mif"/>
- </mime-type> -->
-
- <mime-type type="application/x-ms-dos-executable">
- <alias type="application/x-dosexec" />
- </mime-type>
-
- <mime-type type="application/ogg">
- <alias type="application/x-ogg" />
- </mime-type>
-
- <mime-type type="application/x-rar">
- <alias type="application/x-rar-compressed" />
- </mime-type>
-
- <mime-type type="application/x-shellscript">
- <alias type="application/x-sh" />
- </mime-type>
-
- <mime-type type="application/xhtml+xml">
- <glob pattern="*.xht" />
- </mime-type>
-
- <mime-type type="audio/midi">
- <glob pattern="*.kar" />
- </mime-type>
-
- <mime-type type="audio/x-pn-realaudio">
- <alias type="audio/x-realaudio" />
- </mime-type>
-
- <mime-type type="image/tiff">
- <magic priority="50">
- <match value="0x4d4d2a00" type="string" offset="0" />
- <match value="0x49492a00" type="string" offset="0" />
- </magic>
- </mime-type>
-
- <mime-type type="message/rfc822">
- <magic priority="50">
- <match type="string" value="Relay-Version:" offset="0" />
- <match type="string" value="#! rnews" offset="0" />
- <match type="string" value="N#! rnews" offset="0" />
- <match type="string" value="Forward to" offset="0" />
- <match type="string" value="Pipe to" offset="0" />
- <match type="string" value="Return-Path:" offset="0" />
- <match type="string" value="From:" offset="0" />
- <match type="string" value="Message-ID:" offset="0" />
- <match type="string" value="Date:" offset="0" />
- </magic>
- </mime-type>
-
- <mime-type type="application/x-javascript">
- <glob pattern="*.js" />
- </mime-type>
-
-
- <mime-type type="image/vnd.wap.wbmp">
- <_comment>Wireless Bitmap File Format</_comment>
- <glob pattern="*.wbmp" />
- </mime-type>
-
- <mime-type type="image/x-psd">
- <alias type="image/photoshop" />
- </mime-type>
-
- <mime-type type="image/x-xcf">
- <alias type="image/xcf" />
- <magic priority="50">
- <match type="string" value="gimp xcf " offset="0" />
- </magic>
- </mime-type>
-
- <mime-type type="application/x-shockwave-flash">
- <glob pattern="*.swf"/>
- <magic priority="50">
- <match type="string" value="FWS" offset="0"/>
- <match type="string" value="CWS" offset="0"/>
- </magic>
- </mime-type>
-
- <mime-type type="model/iges">
- <_comment>
- Initial Graphics Exchange Specification Format
- </_comment>
- <glob pattern="*.igs" />
- <glob pattern="*.iges" />
- </mime-type>
-
- <mime-type type="model/mesh">
- <glob pattern="*.msh" />
- <glob pattern="*.mesh" />
- <glob pattern="*.silo" />
- </mime-type>
-
- <mime-type type="model/vrml">
- <glob pattern="*.vrml" />
- </mime-type>
-
- <mime-type type="text/x-tcl">
- <alias type="application/x-tcl" />
- </mime-type>
-
- <mime-type type="text/x-tex">
- <alias type="application/x-tex" />
- </mime-type>
-
- <mime-type type="text/x-texinfo">
- <alias type="application/x-texinfo" />
- </mime-type>
-
- <mime-type type="text/x-troff-me">
- <alias type="application/x-troff-me" />
- </mime-type>
-
- <mime-type type="video/vnd.mpegurl">
- <glob pattern="*.mxu" />
- </mime-type>
-
- <mime-type type="x-conference/x-cooltalk">
- <_comment>Cooltalk Audio</_comment>
- <glob pattern="*.ice" />
- </mime-type>
-
-</mime-info>
diff --git a/search-server/nutch/crawl_jsp/urls/urls.txt b/search-server/nutch/crawl_jsp/urls/urls.txt
deleted file mode 100644
index 020ed3b..0000000
--- a/search-server/nutch/crawl_jsp/urls/urls.txt
+++ /dev/null
@@ -1,7 +0,0 @@
-file:///shared/repo/trunk/eng/docs/guides/channel-mgmt/en/
-file:///shared/repo/trunk/eng/docs/guides/client-config/en/
-file:///shared/repo/trunk/eng/docs/guides/proxy/rhn511/en/
-file:///shared/repo/trunk/eng/docs/guides/reference/en/
-file:///shared/repo/trunk/eng/docs/guides/satellite/en/
-file:///shared/repo/trunk/eng/docs/release-notes/satellite/rhn510/en-US/
-
diff --git a/search-server/rhn_search_daemon_dev.conf b/search-server/rhn_search_daemon_dev.conf
deleted file mode 100644
index 964fe46..0000000
--- a/search-server/rhn_search_daemon_dev.conf
+++ /dev/null
@@ -1,45 +0,0 @@
-wrapper.java.command=/usr/bin/java
-wrapper.java.mainclass=com.redhat.satellite.search.Main
-wrapper.java.classpath.1=%PWD%/build/
-wrapper.java.classpath.2=%PWD%/lib/commons-lang-2.0.jar
-wrapper.java.classpath.3=%PWD%/lib/commons-logging-1.1.jar
-wrapper.java.classpath.4=%PWD%/lib/ibatis-2.3.0.677.jar
-wrapper.java.classpath.5=%PWD%/lib/log4j-1.2.8.jar
-wrapper.java.classpath.6=%PWD%/lib/lucene-core-2.3.2.jar
-wrapper.java.classpath.7=%PWD%/lib/ojdbc14-1.10.jar
-wrapper.java.classpath.8=%PWD%/lib/picocontainer-1.3.jar
-wrapper.java.classpath.9=%PWD%/lib/quartz-1.5.1.jar
-wrapper.java.classpath.10=%PWD%/lib/redstone-xmlrpc-1.1_20071120.jar
-wrapper.java.classpath.11=%PWD%/lib/redstone-xmlrpc-client-1.1_20071120.jar
-wrapper.java.classpath.12=%PWD%/lib/simple-core-3.1.3.jar
-wrapper.java.classpath.13=/usr/share/java/tanukiwrapper.jar
-wrapper.java.classpath.14=%PWD%/lib/logdriver-0.1.jar
-wrapper.java.classpath.15=%PWD%/lib/lucene-analyzers-2.3.2.jar
-wrapper.java.classpath.16=/usr/share/nutch
-wrapper.java.classpath.17=/usr/share/nutch/conf
-wrapper.java.classpath.18=%PWD%/lib/nutch-2008-12-01_04-01-21.jar
-wrapper.java.classpath.19=%PWD%/lib/hadoop-0.18.1-core.jar
-wrapper.java.classpath.20=%PWD%/lib/commons-httpclient-3.0.jar
-wrapper.java.classpath.21=%PWD%/lib/oro-2.0.8.jar
-wrapper.java.classpath.22=%PWD%/lib/icu4j-3_8_1.jar
-wrapper.java.classpath.23=%PWD%/lib/icu4j-charsets-3_8_1.jar
-wrapper.java.classpath.24=%PWD%/lib/commons-cli-1.0.jar
-wrapper.java.classpath.25=%PWD%/lib/commons-codec-1.2.jar
-wrapper.java.classpath.26=%PWD%/lib/tika-0.1-incubating.jar
-
-
-wrapper.java.library.path.1=/usr/lib
-wrapper.java.library.path.2=/usr/lib64
-wrapper.console.format=PM
-wrapper.console.loglevel=INFO
-wrapper.logfile=%PWD%/rhn_search_daemon.log
-wrapper.logfile.format=LPTM
-wrapper.logfile.loglevel=DEBUG
-wrapper.logfile.maxsize=5m
-wrapper.logfile.maxfiles=0
-wrapper.syslog.loglevel=DEBUG
-
-wrapper.java.additional.1=-Dsearch.config.dir=%PWD%/src/config/search
-wrapper.java.additional.2=-Xdebug
-wrapper.java.additional.3=-Xnoagent
-wrapper.java.additional.4=-Xrunjdwp:transport=dt_socket,address=9999,server=y,suspend=n
diff --git a/search-server/run.sh b/search-server/run.sh
deleted file mode 100755
index 0bbf58a..0000000
--- a/search-server/run.sh
+++ /dev/null
@@ -1,17 +0,0 @@
-#!/bin/bash
-rpm -q tanukiwrapper > /dev/null
-RETURN_VAL=$?
-if [ ! "$RETURN_VAL" -eq "0" ]; then
- echo "Please install tanukiwrapper: up2date tanukiwrapper or yum install tanukiwrapper"
- exit 1;
-fi
-
-if [ ! -r "/etc/rhn/search/rhn_search.conf" ]; then
- echo "you need to symlink rhn_search.conf as /etc/rhn/search/rhn_search.conf"
- exit 2;
-fi
-
-echo "starting server"
-export CLASSPATH=`pwd`/build
-#java -Djava.library.path=/usr/lib -classpath `build-classpath-directory lib dist` com.redhat.satellite.search.Main
-/usr/sbin/tanukiwrapper `pwd`/rhn_search_daemon_dev.conf wrapper.pidfile=`pwd`/rhn-search.pid wrapper.daemonize=FALSE
diff --git a/search-server/scripts/Reindex.groovy b/search-server/scripts/Reindex.groovy
deleted file mode 100644
index 49e94e0..0000000
--- a/search-server/scripts/Reindex.groovy
+++ /dev/null
@@ -1,43 +0,0 @@
-import com.redhat.satellite.search.db.DatabaseManager;
-import com.redhat.satellite.search.db.WriteQuery;
-import com.redhat.satellite.search.config.Configuration;
-
-def deleteQuery(config, queryName) {
- DatabaseManager databaseManager = new DatabaseManager(config)
- WriteQuery query = null;
- try {
- query = databaseManager.getWriterQuery(queryName);
- query.delete(null);
- }
- finally {
- query.close();
- }
-}
-
-/**
- Currently, only handles Errata and Packages
- Need to add: User, System, Docs
- **/
-Configuration config = new Configuration()
-deleteQueries = ["deleteLastErrata", "deleteLastPackage",
- "deleteLastServer", "deleteLastHardwareDevice",
- "deleteLastSnapshotTag", "deleteLastServerCustomInfo"]
-deleteQueries.each{deleteQuery(config, it)}
-
-println "Database has been prepared so we can re-index."
-
-indexWorkDir = config.getString("search.index_work_dir", null);
-println "Previous indexes will be deleted on filesystem under ${indexWorkDir}"
-
-dirs = [indexWorkDir+"/package", indexWorkDir+"/errata",
- indexWorkDir+"/server", indexWorkDir+"/hwdevice",
- indexWorkDir+"/snapshotTag", indexWorkDir+"/serverCustomInfo"]
-dirs.each {
- cmd = "rm -r $it"
- def proc = cmd.execute()
- proc.waitFor()
-}
-
-
-
-
diff --git a/search-server/scripts/build.properties b/search-server/scripts/build.properties
deleted file mode 100644
index 6dcc9ac..0000000
--- a/search-server/scripts/build.properties
+++ /dev/null
@@ -1,22 +0,0 @@
-java.src.dir=src/java
-config.src.dir=src/config
-java.lib.dir=lib
-java.task.lib.dir=../task-lib
-report.dir=report
-build.dir=build
-build.instrument.dir=instrumented
-dist.dir=dist
-jar.name=spacewalk-search-scripts
-jar.version=1.0
-jar.file.name=${jar.name}-${jar.version}.jar
-ivyserver= http://jmrodri.fedorapeople.org
-ivy.log.module.when.found=false
-ivy.log.resolved.revision=false
-# Checkstyle config entries
-checkstyle.cache.file=.checkstyle_cache
-checkstyle.header.file=./buildconf/LICENSE.txt
-javadoc.method.scope=public
-javadoc.type.scope=package
-javadoc.var.scope=package
-javadoc.lazy=true
-jpackage.jars="commons-lang commons-logging redstone-xmlrpc redstone-xmlrpc-client quartz tanukiwrapper log4j commons-httpclient oro commons-cli commons-codec"
diff --git a/search-server/scripts/build.xml b/search-server/scripts/build.xml
deleted file mode 100644
index f45e670..0000000
--- a/search-server/scripts/build.xml
+++ /dev/null
@@ -1,256 +0,0 @@
-<project name="search-server" basedir="." default="all">
- <import file="./buildconf/build-utils.xml" />
-
- <property file="build.properties" />
-
- <path id="project.taskjars">
- <fileset dir="${java.task.lib.dir}" includes="**/*.jar" />
- </path>
-
- <path id="project.classpath">
- <fileset dir="${java.lib.dir}" includes="**/*.jar" />
- <fileset dir="${java.task.lib.dir}" >
- <include name="junit*.jar" />
- <include name="emma*.jar" />
- </fileset>
- </path>
-
- <path id="test.classpath">
- <pathelement location="${build.dir}" />
- <path refid="project.classpath" />
- <pathelement location="${basedir}/src/config" />
- </path>
-
- <path id="run.classpath">
- <path refid="project.classpath" />
- <pathelement location="${dist.dir}/${jar.file.name}"/>
- </path>
-
- <target name="init-tasks">
- <taskdef name="ivy-retrieve"
- classname="fr.jayasoft.ivy.ant.IvyRetrieve"
- classpathref="project.taskjars"/>
- <taskdef name="ivy-configure"
- classname="fr.jayasoft.ivy.ant.IvyConfigure"
- classpathref="project.taskjars"/>
- <taskdef name="ivy-resolve"
- classname="fr.jayasoft.ivy.ant.IvyResolve"
- classpathref="project.taskjars"/>
- <taskdef name="ivy-publish"
- classname="fr.jayasoft.ivy.ant.IvyPublish"
- classpathref="project.taskjars"/>
- <taskdef resource="checkstyletask.properties">
- <classpath>
- <pathelement path="${java.task.lib.dir}/checkstyle-4.1.jar" />
- <pathelement path="${java.task.lib.dir}/commons-beanutils-1.7.0.jar" />
- <pathelement path="${java.task.lib.dir}/commons-logging-1.0.4.jar" />
- <pathelement path="${java.task.lib.dir}/antlr-2.7.6.jar" />
- <pathelement path="${java.task.lib.dir}/regexp-1.3.jar" />
- </classpath>
- </taskdef>
- <taskdef resource="emma_ant.properties" classpathref="project.taskjars" />
- <taskdef resource="net/sf/antcontrib/antlib.xml">
- <classpath>
- <pathelement location="${java.task.lib.dir}/ant-contrib-1.0.jar"/>
- </classpath>
- </taskdef>
- </target>
-
- <target name="check-testcase-name" if="testcase" depends="init-tasks">
- <propertyregex property="valid.testcase"
- input="${testcase}"
- regexp="(.*)Test$"
- select="\1"
- casesensitive="true" />
- </target>
-
- <target name="check-testcase" depends="check-testcase-name" if="testcase"
- unless="valid.testcase">
- <fail message="Invalid testcase name: ${testcase}. Class name must look like .*Test"/>
- </target>
-
- <target name="test" depends="compile, check-testcase"
- description="Run the tests (use -Dtestcase=<testcase>)">
- <mkdir dir="${report.dir}" />
- <!-- set testcase to wildcard "*" to test everything, unless
- a specific testcase name was supplied. -->
- <if>
- <not>
- <isset property="${testcase}" />
- </not>
- <then>
- <property name="testcase" value="*Test"/>
- </then>
- </if>
- <junit>
- <sysproperty key="rhn.config.dir" value="/etc/rhn" />
- <sysproperty key="search.config.dir" value="src/config/search" />
- <sysproperty key="log4j.configuration" value="log4j.test.properties" />
- <classpath refid="test.classpath" />
- <formatter type="brief" usefile="false" />
- <formatter type="xml" />
- <batchtest fork="yes" todir="${report.dir}">
- <fileset dir="${build.dir}" includes="**/${testcase}.class" />
- </batchtest>
- </junit>
- </target>
-
- <target name="checkstyle" depends="init-tasks, package">
- <delete dir="${report.dir}" />
- <mkdir dir="${report.dir}" />
- <checkstyle config="checkstyle.xml" failOnViolation="true" >
- <property key="javadoc.method.scope" value="public" />
- <property key="javadoc.type.scope" value="package" />
- <property key="javadoc.var.scope" value="package" />
- <property key="javadoc.lazy" value="${javadoc.lazy}" />
- <fileset dir="${java.src.dir}" >
- <include name="**/*.java" />
- <exclude name="**/tests/**" />
- </fileset>
- <classpath>
- <fileset dir="${java.lib.dir}" includes="**/*.jar" />
- <fileset dir="${java.task.lib.dir}" includes="junit*.jar" />
- <fileset dir="${dist.dir}" includes="${jar.file.name}" />
- </classpath>
- <formatter type="plain" />
- <formatter type="xml" toFile="${report.dir}/checkstyle_report.xml" />
- </checkstyle>
- </target>
-
- <target name="resolve-local" description="resolve jars via jpackage" if="installbuild">
- <copy toDir="${java.lib.dir}" overwrite="true">
- <fileset dir="buildconf/tempjars">
- <include name="**/*.jar" />
- </fileset>
- </copy>
-
- <jpackage-deps jars="${jpackage.jars}" dir="${java.lib.dir}" />
- </target>
-
- <target name="resolve-ivy" description="retrieve dependencies with ivy"
- depends="init-tasks" unless="installbuild">
- <!-- properties set here to show we are overriding default ivy values -->
- <property name="ivy.default.ivy.user.dir" value="${user.home}/.ivy/search-server"/>
- <property name="ivy.local.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
- <property name="ivy.ivyrep.default.ivy.root" value="${ivyserver}/ivy/" />
- <property name="ivy.ivyrep.default.artifact.root" value="${ivyserver}/ivy/" />
- <property name="ivy.ivyrep.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
- <ivy-retrieve/>
- </target>
-
- <target name="resolve" depends="resolve-ivy,resolve-local" />
-
- <target name="prep">
- <mkdir dir="${build.dir}" />
- <mkdir dir="${dist.dir}" />
- <mkdir dir="${java.lib.dir}" />
- </target>
-
- <target name="clean">
- <delete dir="${build.dir}" />
- <delete dir="${build.instrument.dir}" />
- <delete dir="${dist.dir}" />
- <delete dir="${java.lib.dir}" />
- <delete dir="${report.dir}" />
- <delete file="coverage.ec" />
- <delete file="rhn_search_daemon.log" />
- </target>
-
- <target name="compile" depends="prep, resolve">
- <javac srcdir="${java.src.dir}"
- classpathref="project.classpath"
- destdir="${build.dir}"
- deprecation="on"
- excludesfile="buildconf/exclude"
- debug="on" />
- <copy file="${config.src.dir}/log4j.properties" todir="${build.dir}" />
- </target>
-
- <target name="package" depends="compile">
- <jar basedir="${build.dir}"
- destfile="${dist.dir}/${jar.file.name}"
- excludes="**/tests/**"
- includes="**/**" />
- </target>
-
- <target name="create-local-repo" description="Create a local Ivy repo">
- <mkdir dir="${user.home}/.ivy/search-server/local/" />
- </target>
-
- <target name="clean-cache" description="Removes the Ivy jar cache">
- <delete dir="${lib.dir}" quiet="true" />
- <delete dir="${user.home}/.ivy/search-server/cache/" quiet="true" />
- </target>
-
- <target name="all" depends="package" />
-
- <target name="init-install">
- <property name="installbuild" value="true"/>
- </target>
-
- <target name="install" depends="init-install,package" />
-
- <target name="instrument" depends="init-tasks">
- <mkdir dir="${report.dir}" />
- <mkdir dir="${build.instrument.dir}" />
-
- <emma enabled="true">
- <instr merge="no"
- mode="overwrite"
- instrpath="${build.dir}"
- outfile="${report.dir}/coverage.em" >
- <filter excludes="*Exception" />
- <filter excludes="*.tests.*" />
- </instr>
- <!--
- <instr outdir="${build.instrument.dir}" merge="no"
- instrpath="${build.dir}"
- mode="fullcopy"
- outfile="${report.dir}/coverage.em" >
- <filter excludes="*Exception" />
- <filter excludes="*.tests.*" />
- </instr>
- -->
- </emma>
-
- <!--
- <copy toDir="${build.instrument.dir}/classes">
- <fileset dir="${build.dir}">
- <include name="**/*.xml" />
- </fileset>
- </copy>
- -->
- </target>
-
- <target name="coverage-report" depends="instrument">
- <emma enabled="true">
- <report sourcepath="${java.src.dir}"
- sort="+block,+name,+method,+class"
- metrics="method:70,block:80,line:80,class:100">
- <fileset dir="${report.dir}" includes="*.em" />
- <fileset dir="." includes="*.ec" />
- <html outfile="${report.dir}/emma.html"
- depth="method"
- columns="name,class,method,block,line" />
- <xml outfile="${report.dir}/emma.xml"
- depth="method"
- columns="name,class,method,block,line" />
- </report>
- </emma>
- </target>
-
-
- <target name="indexDocs" depends="package"
- description="Crawls help docs with nutch and generates a lucene index">
- <java
- classname="com.redhat.satellite.search.index.docs.WebCrawl"
- dir="${basedir}"
- fork="true"
- failonerror="true">
-
- <arg value="-h"/>
- <classpath refid="run.classpath" />
- </java>
- </target>
-
-</project>
diff --git a/search-server/scripts/buildconf/LICENSE.txt b/search-server/scripts/buildconf/LICENSE.txt
deleted file mode 100644
index 629462a..0000000
--- a/search-server/scripts/buildconf/LICENSE.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-/**
- * Copyright (c) 2008 Red Hat, Inc.
- *
- * This software is licensed to you under the GNU General Public License,
- * version 2 (GPLv2). There is NO WARRANTY for this software, express or
- * implied, including the implied warranties of MERCHANTABILITY or FITNESS
- * FOR A PARTICULAR PURPOSE. You should have received a copy of GPLv2
- * along with this software; if not, see
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt .
- *
- * Red Hat trademarks are not licensed under GPLv2. No permission is
- * granted to use or replicate Red Hat trademarks that are incorporated
- * in this software or its documentation.
- */
diff --git a/search-server/scripts/buildconf/build-utils.xml b/search-server/scripts/buildconf/build-utils.xml
deleted file mode 100644
index d428618..0000000
--- a/search-server/scripts/buildconf/build-utils.xml
+++ /dev/null
@@ -1,19 +0,0 @@
-<project name="build-utils.xml">
- <!--
- creates symlinks for jpackage jars
- requires: jpackage-utils
- other: requires rpms of the jars specified to be installed
- -->
- <macrodef name="jpackage-deps">
- <attribute name="jars" />
- <attribute name="dir" />
-
- <sequential>
- <exec executable="build-jar-repository" failonerror="true" >
- <arg value="--preserve-naming" />
- <arg value="-s @{dir}" />
- <arg line="@{jars}" />
- </exec>
- </sequential>
- </macrodef>
-</project>
diff --git a/search-server/scripts/buildconf/exclude b/search-server/scripts/buildconf/exclude
deleted file mode 100644
index e69de29..0000000
diff --git a/search-server/scripts/checkstyle.xml b/search-server/scripts/checkstyle.xml
deleted file mode 100644
index 2cb51d5..0000000
--- a/search-server/scripts/checkstyle.xml
+++ /dev/null
@@ -1,233 +0,0 @@
-<?xml version="1.0"?>
-<!DOCTYPE module PUBLIC
- "-//Puppy Crawl//DTD Check Configuration 1.1//EN"
- "http://www.puppycrawl.com/dtds/configuration_1_1.dtd ">
-
-<!--
-
- Checkstyle configuration that checks the sun coding conventions from:
-
- - the Java Language Specification at
- http://java.sun.com/docs/books/jls/second_edition/html/index.html
-
- - the Sun Code Conventions at http://java.sun.com/docs/codeconv/
-
- - the Javadoc guidelines at
- http://java.sun.com/j2se/javadoc/writingdoccomments/index.html
-
- - the JDK Api documentation http://java.sun.com/j2se/docs/api/index.html
-
- - some best practices
-
- Checkstyle is very configurable. Be sure to read the documentation at
- http://checkstyle.sf.net (or in your downloaded distribution).
-
- Most Checks are configurable, be sure to consult the documentation.
-
- To completely disable a check, just comment it out or delete it from the file.
-
- Finally, it is worth reading the documentation.
-
--->
-
-<module name="Checker">
-
- <!-- Checks that a package.html file exists for each package. -->
- <!-- See http://checkstyle.sf.net/config_javadoc.html#PackageHtml -->
-<!-- <module name="PackageHtml"/> -->
-
- <!-- Checks whether files end with a new line. -->
- <!-- See http://checkstyle.sf.net/config_misc.html#NewlineAtEndOfFile -->
- <module name="NewlineAtEndOfFile"/>
-
- <!-- Checks that property files contain the same keys. -->
- <!-- See http://checkstyle.sf.net/config_misc.html#Translation -->
- <module name="Translation"/>
-
- <module name="TreeWalker">
-
- <property name="cacheFile" value="${checkstyle.cache.file}"/>
-
- <!-- ************************************************************** -->
- <!-- Checks that are different from the sun coding conventions ones -->
- <!-- ************************************************************** -->
- <property name="tabWidth" value="4"/>
- <module name="LeftCurly" />
- <module name="RightCurly">
- <property name="option" value="alone"/>
- </module>
- <module name="LineLength">
- <property name="ignorePattern" value="import"/>
- <property name="max" value="92"/>
- </module>
-
- <!-- ************************************************************** -->
- <!-- Default Sun coding conventions checks -->
- <!-- ************************************************************** -->
-
- <!-- Checks for Javadoc comments. -->
- <!-- See http://checkstyle.sf.net/config_javadoc.html -->
- <module name="JavadocMethod">
- <property name="scope" value="${javadoc.method.scope}" />
- <property name="allowUndeclaredRTE" value="true" />
- <property name="allowThrowsTagsForSubclasses" value="${javadoc.lazy}" />
- <property name="allowMissingParamTags" value="${javadoc.lazy}" />
- <property name="allowMissingThrowsTags" value="${javadoc.lazy}" />
- <property name="allowMissingReturnTag" value="${javadoc.lazy}" />
- </module>
- <module name="JavadocType">
- <property name="versionFormat" value="\$Rev.*\$"/>
- <property name="scope" value="${javadoc.type.scope}" />
- </module>
- <module name="JavadocVariable">
- <property name="scope" value="${javadoc.var.scope}" />
- <property name="severity" value="ignore"/>
- </module>
-
-<!-- JavadocStyle not supported by some versions. -->
-<!-- <module name="JavadocStyle"/> -->
-
-
- <!-- Checks for Naming Conventions. -->
- <!-- See http://checkstyle.sf.net/config_naming.html -->
- <module name="ConstantName"/>
- <module name="LocalFinalVariableName"/>
- <module name="LocalVariableName"/>
- <module name="MethodName"/>
- <module name="PackageName">
- <property name="format" value="^[a-z]+(\.[A-Za-z][A-Za-z0-9]*)*$"/>
- </module>
- <module name="ParameterName"/>
- <module name="StaticVariableName"/>
- <module name="TypeName"/>
-
-
- <!-- Checks for Headers -->
- <!-- See http://checkstyle.sf.net/config_header.html -->
- <module name="Header">
- <!-- The follow property value demonstrates the ability -->
- <!-- to have access to ANT properties. In this case it uses -->
- <!-- the ${basedir} property to allow Checkstyle to be run -->
- <!-- from any directory within a project. -->
- <property name="headerFile" value="${checkstyle.header.file}"/>
- </module>
-
- <!-- Following interprets the header file as regular expressions. -->
- <!-- <module name="RegexpHeader"/> -->
-
-
-
- <!-- Checks for imports -->
- <!-- See http://checkstyle.sf.net/config_import.html -->
- <module name="AvoidStarImport"/>
- <module name="IllegalImport"/> <!-- defaults to sun.* packages -->
- <module name="RedundantImport"/>
- <module name="UnusedImports"/>
-
-
- <!-- Checks for Size Violations. -->
- <!-- See http://checkstyle.sf.net/config_sizes.html -->
- <module name="MethodLength">
- <property name="tokens" value="METHOD_DEF"/>
- <property name="max" value="150"/>
- <property name="countEmpty" value="false"/>
- </module>
- <module name="ParameterNumber"/>
-
-
- <!-- Checks for whitespace -->
- <!-- See http://checkstyle.sf.net/config_whitespace.html -->
- <module name="EmptyForIteratorPad"/>
- <module name="NoWhitespaceAfter">
- <property name="tokens" value="BNOT, DEC, DOT, INC, LNOT, UNARY_MINUS, UNARY_PLUS, TYPECAST, GENERIC_START"/>
- </module>
- <module name="NoWhitespaceBefore">
- <property name="tokens" value="SEMI, POST_DEC, POST_INC, GENERIC_START, GENERIC_END"/>
- </module>
- <module name="OperatorWrap">
- <property name="option" value="eol" />
- </module>
- <module name="ParenPad"/>
-<!-- <module name="TypecastParenPad"/> -->
- <module name="TabCharacter"/>
- <module name="WhitespaceAfter">
- <property name="tokens" value="COMMA, SEMI, GENERIC_END"/>
- </module>
- <module name="WhitespaceAround">
- <property name="tokens" value="ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN, BXOR, BXOR_ASSIGN,
-COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LCURLY, LE, LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
-LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE, LOR, LT, MINUS,
-MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL, PLUS, PLUS_ASSIGN, QUESTION, RCURLY, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN, STAR, STAR_ASSIGN, TYPE_EXTENSION_AND, WILDCARD_TYPE"/>
- </module>
- <module name="MethodParamPad">
- <property name="allowLineBreaks" value="true"/>
- </module>
-
-
- <!-- Modifier Checks -->
- <!-- See http://checkstyle.sf.net/config_modifiers.html -->
- <module name="ModifierOrder"/>
- <module name="RedundantModifier"/>
-
-
- <!-- Checks for blocks. You know, those {}'s -->
- <!-- See http://checkstyle.sf.net/config_blocks.html -->
- <module name="AvoidNestedBlocks"/>
- <module name="EmptyBlock">
- <property name="option" value="text"/>
- </module>
-
- <module name="NeedBraces"/>
-
-
- <!-- Checks for common coding problems -->
- <!-- See http://checkstyle.sf.net/config_coding.html -->
- <!-- <module name="AvoidInlineConditionals"/> -->
-<!-- <module name="CovariantEquals"/> -->
- <module name="DoubleCheckedLocking"/> <!-- MY FAVOURITE -->
- <module name="EmptyStatement"/>
- <module name="EqualsHashCode"/>
- <module name="HiddenField"/>
- <module name="IllegalInstantiation"/>
- <module name="InnerAssignment"/>
- <!-- <module name="MagicNumber" /> -->
- <module name="MissingSwitchDefault"/>
-<!-- <module name="RedundantThrows"/> -->
- <module name="SimplifyBooleanExpression"/>
- <module name="SimplifyBooleanReturn"/>
-<!-- <module name="IllegalCatch"/> -->
-<!-- <module name="PackageDeclaration"/> -->
-
- <!-- Checks for class design -->
- <!-- See http://checkstyle.sf.net/config_design.html -->
-<!-- <module name="DesignForExtension"/>-->
-<!-- <module name="FinalClass"/> -->
- <module name="HideUtilityClassConstructor"/>
- <module name="InterfaceIsType"/>
- <module name="VisibilityModifier">
- <property name="protectedAllowed" value="true" />
- </module>
-
-
- <!-- Miscellaneous other checks. -->
- <!-- See http://checkstyle.sf.net/config_misc.html -->
- <module name="ArrayTypeStyle"/>
-<!-- <module name="FinalParameters"/> -->
-<!--
- <module name="GenericIllegalRegexp">
- <property name="format" value="System\.out\.println"/>
- </module>
--->
- <module name="UpperEll"/>
-
- <!-- Optional Checks -->
- <!-- (gack, not available until version 3 of checkstyle -->
-<!--
- <module name="usage.OneMethodPrivateField"/>
- <module name="usage.UnusedLocalVariable"/>
- <module name="usage.UnusedParameter"/>
- <module name="usage.UnusedPrivateField"/>
--->
- </module>
-
-</module>
diff --git a/search-server/scripts/ivy.xml b/search-server/scripts/ivy.xml
deleted file mode 100644
index cffd1c1..0000000
--- a/search-server/scripts/ivy.xml
+++ /dev/null
@@ -1,28 +0,0 @@
-<ivy-module version="1.0">
- <info organisation="redhat" module="rhn-java" />
- <dependencies>
- <dependency org="redhat" name="simple-core" rev="3.1.3" />
- <dependency org="redhat" name="lucene-core" rev="2.3.2" />
- <dependency org="redhat" name="lucene-analyzers" rev="2.3.2" />
- <dependency org="redhat" name="commons-lang" rev="2.0" />
- <dependency org="redhat" name="commons-logging" rev="1.1" />
- <dependency org="redhat" name="redstone-xmlrpc" rev="1.1_20071120" />
- <dependency org="redhat" name="redstone-xmlrpc-client" rev="1.1_20071120" />
- <dependency org="redhat" name="ibatis" rev="2.3.0.677" />
- <dependency org="redhat" name="ojdbc14" rev="1.10" />
- <dependency org="redhat" name="quartz" rev="1.5.1" />
- <dependency org="redhat" name="picocontainer" rev="1.3" />
- <dependency org="redhat" name="tanukiwrapper" rev="3.1.2" />
- <dependency org="redhat" name="log4j" rev="1.2.8" />
- <dependency org="redhat" name="logdriver" rev="0.1" />
- <dependency org="redhat" name="nutch" rev="1.0dev_2008_05_14" />
- <dependency org="redhat" name="hadoop" rev="0.16.4-core" />
- <dependency org="redhat" name="commons-cli" rev="1.0" />
- <!-- dependency org="redhat" name="commons-httpclient" rev="3.0" / -->
- <!-- dependency org="redhat" name="oro" rev="2.0.8" / -->
- <!-- dependency org="redhat" name="commons-codec" rev="1.2" / -->
- <!-- dependency org="redhat" name="tika" rev="0.1-incubating" / -->
- <!-- dependency org="redhat" name="icu4j" rev="3_8_1" / -->
- <!-- dependency org="redhat" name="icu4j-charsets" rev="3_8_1" / -->
- </dependencies>
-</ivy-module>
diff --git a/search-server/scripts/lukeall-0.8.1.jar b/search-server/scripts/lukeall-0.8.1.jar
deleted file mode 100644
index 347aee6..0000000
Binary files a/search-server/scripts/lukeall-0.8.1.jar and /dev/null differ
diff --git a/search-server/scripts/maketar.sh b/search-server/scripts/maketar.sh
deleted file mode 100755
index 6a389be..0000000
--- a/search-server/scripts/maketar.sh
+++ /dev/null
@@ -1,30 +0,0 @@
-if [ -a version ]; then
- version=`cat version | awk '/^[0-9]\.[0-9]\.[0-9]* / { print $1 }'`
-
- if [ "$version" == "" ]; then
- echo "Version not found"
- exit -1
- fi
-
- echo "Creating /tmp/rhn-search-$version"
- mkdir /tmp/rhn-search-$version
-
- echo "Copying repo to /tmp/rhn-search-$version/"
- cp -R * /tmp/rhn-search-$version/
-
- cd /tmp/
- rm -f rhn-search-$version/scripts/maketar.sh
- echo "Creating /tmp/rhn-search-$version.tar.gz file"
- tar -czf /tmp/rhn-search-$version.tar.gz rhn-search-$version/ --exclude .svn
- cd -
-
- echo "Removing /tmp/rhn-search-$version"
- rm -rf /tmp/rhn-search-$version
-
- echo ""
- echo "You can find your tar at /tmp/rhn-search-$version.tar.gz"
- echo ""
-
-else
- echo "You moron, you gotta run this from the directory containing the version file."
-fi
diff --git a/search-server/scripts/reindex.sh b/search-server/scripts/reindex.sh
deleted file mode 100755
index cc7b312..0000000
--- a/search-server/scripts/reindex.sh
+++ /dev/null
@@ -1,15 +0,0 @@
-#!/usr/bin/env sh
-
-RHN_SEARCH_HOME="../"
-
-for f in $RHN_SEARCH_HOME/lib/*.jar; do
- CLASSPATH=${CLASSPATH}:$f;
-done
-for f in $RHN_SEARCH_HOME/dist/*.jar; do
- CLASSPATH=${CLASSPATH}:$f;
-done
-export CLASSPATH
-
-groovy Reindex.groovy
-
-
diff --git a/search-server/scripts/search.admin.updateIndex.test.py b/search-server/scripts/search.admin.updateIndex.test.py
deleted file mode 100755
index 8962c9d..0000000
--- a/search-server/scripts/search.admin.updateIndex.test.py
+++ /dev/null
@@ -1,15 +0,0 @@
-#!/usr/bin/env python
-
-import sys
-import xmlrpclib
-
-if __name__ == "__main__":
- if len(sys.argv) < 2:
- print "Usage: %s INDEX_NAME" % (sys.argv[0])
- sys.exit(1)
- port = 2828
- addr = "http://127.0.0.1:%s " % (port)
- client = xmlrpclib.ServerProxy(addr)
- indexName = sys.argv[1]
- result = client.admin.updateIndex(indexName)
- print "Return from admin.updateIndex(%s) = %s" % (indexName, result)
diff --git a/search-server/scripts/search.py b/search-server/scripts/search.py
deleted file mode 100755
index c8d0a04..0000000
--- a/search-server/scripts/search.py
+++ /dev/null
@@ -1,69 +0,0 @@
-#!/usr/bin/python
-
-import xmlrpclib
-from optparse import OptionParser
-
-indexName = "package"
-usage = "usage: %prog [options] search term"
-desc = "%prog searches for package (default) or systems with the given \
-search criteria"
-
-parser = OptionParser(usage=usage, description=desc)
-parser.add_option("--sessionid", dest="sessionid", type="int", help="PXT sessionid")
-parser.add_option("--package", action="store_true", dest="package",
- help="search packages", default=True)
-parser.add_option("--system", action="store_true", dest="system",
- help="search systems", default=False)
-parser.add_option("--indexName", dest="indexName", type="string",
- help="lucene index name to search ex: package server hwdevice snapshotTag errata")
-parser.add_option("--serverAddr", dest="serverAddr", type="string", default="localhost",
- help="Server to authenticate to, NOT WHERE SEARCH SERVER RUNS")
-parser.add_option("--username", dest="username", type="string", help="username")
-parser.add_option("--password", dest="password", type="string", help="password")
-parser.add_option("--debug", action="store_true", dest="debug", default=False,
- help="enable debug output")
-
-(options, terms) = parser.parse_args()
-if len(terms) < 1:
- parser.error("please supply a search term\n" + str(parser.print_help()))
-
-if not options.sessionid and (not options.username or not options.password):
- print parser.print_help()
- parser.exit()
-
-
-if options.package:
- indexName = "package"
-
-if options.system:
- indexName = "server"
-
-if options.indexName:
- indexName = options.indexName
-
-
-sessionid = None
-if options.sessionid:
- sessionid = options.sessionid
- print "Using passed in authentication info, sessionid = %s" % (sessionid)
-else:
- xmlrpcURL = "http://%s/rhn/rpc/api" % (options.serverAddr)
- print "Getting authentication information from: %s" % (xmlrpcURL)
- rhnclient = xmlrpclib.Server(xmlrpcURL)
- authSessionId = rhnclient.auth.login(options.username, options.password)
- sessionid = int(authSessionId.split('x')[0])
-
-url = "http://localhost:2828/RPC2 "
-print "Connecting to SearchServer: (%s)" % url
-client = xmlrpclib.Server(url, verbose=options.debug)
-
-term = " ".join(terms)
-print "searching for (%s) matching criteria: (%s)" % (indexName, str(term))
-items = client.index.search(sessionid, indexName, term)
-
-print "We got (%d) items back." % len(items)
-print items
-
-#Remember to logout if the user didn't supply the sessionid
-if not options.sessionid:
- rhnclient.auth.logout(authSessionId)
diff --git a/search-server/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java b/search-server/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java
deleted file mode 100644
index 7a9f671..0000000
--- a/search-server/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java
+++ /dev/null
@@ -1,304 +0,0 @@
-/**
- * Copyright (c) 2008 Red Hat, Inc.
- *
- * This software is licensed to you under the GNU General Public License,
- * version 2 (GPLv2). There is NO WARRANTY for this software, express or
- * implied, including the implied warranties of MERCHANTABILITY or FITNESS
- * FOR A PARTICULAR PURPOSE. You should have received a copy of GPLv2
- * along with this software; if not, see
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt .
- *
- * Red Hat trademarks are not licensed under GPLv2. No permission is
- * granted to use or replicate Red Hat trademarks that are incorporated
- * in this software or its documentation.
- */
-package com.redhat.satellite.search.index.docs;
-
-import org.apache.nutch.crawl.Injector;
-import org.apache.nutch.crawl.Generator;
-import org.apache.nutch.crawl.CrawlDb;
-import org.apache.nutch.crawl.LinkDb;
-import org.apache.nutch.fetcher.Fetcher;
-import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.mapred.JobConf;
-import org.apache.hadoop.fs.Path;
-import org.apache.hadoop.fs.FileSystem;
-import org.apache.nutch.parse.ParseSegment;
-import org.apache.nutch.indexer.DeleteDuplicates;
-import org.apache.nutch.indexer.IndexMerger;
-import org.apache.nutch.indexer.Indexer;
-import org.apache.nutch.util.HadoopFSUtil;
-import org.apache.nutch.util.NutchConfiguration;
-import org.apache.nutch.util.NutchJob;
-
-import org.apache.commons.cli.CommandLine;
-import org.apache.commons.cli.CommandLineParser;
-import org.apache.commons.cli.PosixParser;
-import org.apache.commons.cli.HelpFormatter;
-import org.apache.commons.cli.Options;
-
-import org.apache.commons.cli.ParseException;
-
-import org.apache.log4j.Logger;
-
-import java.text.SimpleDateFormat;
-import java.util.Date;
-import java.io.IOException;
-
-
-/**
-Crawls a set of urls and indexes their content.
-Based off of nutch's crawl
- *
- * @version $Rev: $
- */
-public class WebCrawl {
- private static Logger log = Logger.getLogger(WebCrawl.class);
-
- private Configuration conf;
- private JobConf job;
- private String inputUrlFile;
- private String tmpCrawlDir;
- private String outputIndexDir;
-
- private int depth;
- private int threads;
- private long topN;
-
- /**
- * Constructor
- */
- public WebCrawl() {
- conf = NutchConfiguration.create();
- conf.addResource("crawl-tool.xml");
- job = new NutchJob(conf);
- threads = job.getInt("fetcher.threads.fetch", 10);
- depth = 5;
- topN = Long.MAX_VALUE;
- }
-
- /**
- * @return Returns the dir used to store tmp crawl data
- */
- public String getTmpCrawlDir() {
- return tmpCrawlDir;
- }
- /**
- * @param tmpCrawlDirIn the dir used to store tmp crawl data
- */
- public void setTmpCrawlDir(String tmpCrawlDirIn) {
- tmpCrawlDir = tmpCrawlDirIn;
- }
- /**
- * @return Returns the file used to seed the url crawl
- */
- public String getInputUrlFile() {
- return inputUrlFile;
- }
- /**
- * @param inputUrlFileIn file used to seed the url crawl
- */
- public void setInputUrlFile(String inputUrlFileIn) {
- inputUrlFile = inputUrlFileIn;
- }
- /**
- * @return Returns the dir to store the index of the crawled docs
- */
- public String getOutputIndexDir() {
- return outputIndexDir;
- }
- /**
- * @param outputIndexDirIn the dir to store the index of the crawled docs
- */
- public void setOutputIndexDir(String outputIndexDirIn) {
- outputIndexDir = outputIndexDirIn;
- }
- /**
- * @return Returns the maximum depth of recursion allowed
- */
- public int getDepth() {
- return depth;
- }
- /**
- * @param depthIn the maximum depth of recursion allowed
- */
- public void setDepth(int depthIn) {
- depth = depthIn;
- }
- /**
- * @return Returns the maximum number of fetcher threads used
- */
- public int getThreads() {
- return threads;
- }
- /**
- * @param threadsIn the maximum number of fetcher threads used
- */
- public void setThreads(int threadsIn) {
- threads = threadsIn;
- }
- /**
- * @return Returns the maximum number of "out links" to follow in any given page
- */
- public long getTopN() {
- return topN;
- }
- /**
- * @param topNIn the maximum number of "out links" to follow in any given page
- */
- public void setTopN(long topNIn) {
- topN = topNIn;
- }
-
- protected String getDate() {
- return new SimpleDateFormat("yyyyMMddHHmmss").format(
- new Date(System.currentTimeMillis()));
- }
-
- /**
- * Uses nutch to crawl a list of ulrs defined in "inputUrlFile"
- * Temporary scratch storage is held at "tmpCrawlDir"
- * The desired output is an index of crawled pages, stored at "outputIndexDir"
- *
- * @return true when urls successfully crawled/indexed
- */
- @SuppressWarnings("deprecation")
- public boolean crawl() throws IOException {
- log.info("Performing crawl with following config options: ");
- log.info("inputUrlFile = " + inputUrlFile);
- log.info("tmpCrawlDir = " + tmpCrawlDir);
- log.info("outputIndexDir = " + outputIndexDir);
- log.info("threads = " + threads);
- log.info("depth = " + depth);
- log.info("topN = " + topN);
-
- Path inputPath = new Path(inputUrlFile);
- Path linkDb = new Path(tmpCrawlDir + "/linkdb");
- Path segments = new Path(tmpCrawlDir + "/segments");
- Path indexes = new Path(tmpCrawlDir + "/indexes");
- Path index = new Path(outputIndexDir);
- Path crawlDb = new Path(tmpCrawlDir + "/crawldb");
-
- Path tmpDir = job.getLocalPath("crawl" + Path.SEPARATOR + getDate());
- Injector injector = new Injector(conf);
- Generator generator = new Generator(conf);
- Fetcher fetcher = new Fetcher(conf);
- ParseSegment parseSegment = new ParseSegment(conf);
- CrawlDb crawlDbTool = new CrawlDb(conf);
- LinkDb linkDbTool = new LinkDb(conf);
- Indexer indexer = new Indexer(conf);
- DeleteDuplicates dedup = new DeleteDuplicates(conf);
- IndexMerger merger = new IndexMerger(conf);
-
- FileSystem fs = FileSystem.get(job);
-
- log.info("Create a new database (crawlDB) of link information");
- injector.inject(crawlDb, inputPath);
-
- for (int i = 0; i < depth; i++) {
- log.info("Generate a fetch list from info in the crawlDB.");
- Path segment = generator.generate(crawlDb, segments, -1, topN,
- System.currentTimeMillis());
- if (segment == null) {
- log.info("Stopping at depth = " + i + " instead of " + (depth - 1) +
- " - no more URLs to fetch.");
- break;
- }
- log.info("Fetch links");
- fetcher.fetch(segment, threads); // fetch it
- if (!Fetcher.isParsing(job)) {
- log.info("Parsing Segment");
- parseSegment.parse(segment); // parse it, if needed
- }
- Path[] p = new Path[1];
- p[0] = segment;
- log.info("Update CrawlDB");
- crawlDbTool.update(crawlDb, p, true, true); // update crawldb
- }
-
- linkDbTool.invert(linkDb, segments, true, true, false); // invert links
-
- // Delete old indexes
- if (fs.exists(indexes)) {
- log.info("Deleting old indexes: $indexes");
- fs.delete(indexes);
- }
-
- // Delete old index
- if (fs.exists(index)) {
- log.info("Deleting old merged index: $index");
- fs.delete(index);
- }
-
- // index, dedup & merge
- indexer.index(indexes, crawlDb, linkDb,
- fs.listPaths(segments, HadoopFSUtil.getPassAllFilter()));
-
- Path[] p = new Path[1];
- p[0] = indexes;
- dedup.dedup(p);
- merger.merge(fs.listPaths(indexes, HadoopFSUtil.getPassAllFilter()),
- index, tmpDir);
- log.info("Crawl finished");
- return true;
- }
-
-
- /**
- * Performs a web crawl:
- * @param args command line arguments
- */
- public static void main(String[] args) throws IOException {
-
- WebCrawl wCrawl = new WebCrawl();
-
- Options options = new Options();
- options.addOption("i", "inputUrlFile", true,
- "file holding 'urls' file to seed web page crawling");
- options.addOption("o", "outputDir", true, "temp crawl output dir");
- options.addOption("x", "docsIndexDir", true, "docs index output dir");
- options.addOption("t", "threads", true, "number of threads");
- options.addOption("d", "depth", true, "depth to recurse towards");
- options.addOption("n", "topN", true, "maximum number of out links to follow");
- options.addOption("h", "help", false, "print help message");
-
- CommandLineParser parser = new PosixParser();
- try {
- CommandLine line = parser.parse(options, args);
-
- if (line.hasOption("h")) {
- HelpFormatter formatter = new HelpFormatter();
- formatter.printHelp("WebCrawl", options);
- return;
- }
- if (line.hasOption("i")) {
- wCrawl.setInputUrlFile(line.getOptionValue("i"));
- }
- if (line.hasOption("x")) {
- wCrawl.setOutputIndexDir(line.getOptionValue("x"));
- }
- if (line.hasOption("o")) {
- wCrawl.setTmpCrawlDir(line.getOptionValue("o"));
- }
- if (line.hasOption("t")) {
- wCrawl.setThreads(Integer.parseInt(line.getOptionValue("t")));
- }
- if (line.hasOption("d)")) {
- wCrawl.setDepth(Integer.parseInt(line.getOptionValue("d")));
- }
- if (line.hasOption("n")) {
- wCrawl.setTopN(Integer.parseInt(line.getOptionValue("n")));
- }
-
- }
- catch (ParseException exp) {
- System.err.println("Parsing failed. Reason: " + exp.getMessage());
- }
-
- if (!wCrawl.crawl()) {
- System.err.println("Error -- WebCrawl.crawl() Failed!");
- }
- }
-
-
-}
diff --git a/search-server/scripts/webCrawl.sh b/search-server/scripts/webCrawl.sh
deleted file mode 100755
index da352f6..0000000
--- a/search-server/scripts/webCrawl.sh
+++ /dev/null
@@ -1,17 +0,0 @@
-#!/bin/sh
-SEARCH_HOME=..
-NUTCH_HOME=/usr/share/nutch
-
-CLASSPATH=${CLASSPATH}:${SEARCH_HOME}/build
-#Put our nutch/conf dir before the NUTCH_HOME so ensure our config files are used
-CLASSPATH=${CLASSPATH}:${SEARCH_HOME}/nutch/conf
-CLASSPATH=${CLASSPATH}:${NUTCH_HOME}
-for f in ${SEARCH_HOME}/lib/*.jar; do
- CLASSPATH=${CLASSPATH}:$f;
-done
-
-java -cp ${CLASSPATH} com.redhat.satellite.search.scheduler.tasks.crawl.WebCrawl --inputUrlFile ${SEARCH_HOME}/nutch/urls --outputDir ./crawl_output --docsIndexDir ./docsIndexDir --depth 2 --threads 4
-
-
-
-
diff --git a/search-server/spacewalk-search.spec b/search-server/spacewalk-search.spec
deleted file mode 100644
index fcc3580..0000000
--- a/search-server/spacewalk-search.spec
+++ /dev/null
@@ -1,255 +0,0 @@
-%{!?__redhat_release:%define __redhat_release UNKNOWN}
-
-Name: spacewalk-search
-Summary: Spacewalk Full Text Search Server
-Group: Applications/Internet
-License: GPLv2
-Version: 0.8.1
-Release: 1%{?dist}
-# This src.rpm is cannonical upstream
-# You can obtain it using this set of commands
-# git clone git://git.fedorahosted.org/git/spacewalk.git/
-# cd search-server
-# make test-srpm
-URL: https://fedorahosted.org/spacewalk
-Source0: %{name}-%{version}.tar.gz
-BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root-%(%{__id_u} -n)
-BuildArch: noarch
-
-#Requires: apache-ibatis-sqlmap
-Requires: doc-indexes
-Requires: jakarta-commons-cli
-Requires: jakarta-commons-codec
-Requires: jakarta-commons-httpclient
-Requires: jakarta-commons-lang >= 0:2.1
-Requires: jakarta-commons-logging
-Requires: jpackage-utils >= 0:1.5
-Requires: log4j
-Requires: oro
-#Requires: lucene
-Requires: quartz
-Requires: redstone-xmlrpc
-#Requires: picocontainer
-Requires: tanukiwrapper
-Obsoletes: rhn-search < 5.3.0
-BuildRequires: ant
-#BuildRequires: apache-ibatis-sqlmap
-BuildRequires: jakarta-commons-cli
-BuildRequires: jakarta-commons-codec
-BuildRequires: jakarta-commons-httpclient
-BuildRequires: jakarta-commons-lang >= 0:2.1
-BuildRequires: jakarta-commons-logging
-BuildRequires: java-devel >= 1.6.0
-BuildRequires: log4j
-BuildRequires: oro
-#BuildRequires: lucene
-BuildRequires: quartz
-BuildRequires: redstone-xmlrpc
-#BuildRequires: picocontainer
-BuildRequires: tanukiwrapper
-Requires(post): chkconfig
-Requires(preun): chkconfig
-# This is for /sbin/service
-Requires(preun): initscripts
-
-%description
-This package contains the code for the Full Text Search Server for
-Spacewalk Server.
-
-%prep
-%setup -n %{name}-%{version}
-
-%install
-rm -fr ${RPM_BUILD_ROOT}
-ant -Djar.version=%{version} install
-install -d -m 755 $RPM_BUILD_ROOT%{_sysconfdir}/rhn/search
-install -d -m 755 $RPM_BUILD_ROOT%{_prefix}/share/rhn/search
-install -d -m 755 $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/indexes
-install -d -m 755 $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/lib
-install -d -m 755 $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/classes/com/redhat/satellite/search/db
-install -d -m 755 $RPM_BUILD_ROOT%{_initrddir}
-install -d -m 755 $RPM_BUILD_ROOT%{_bindir}
-install -d -m 755 $RPM_BUILD_ROOT%{_var}/log/rhn/search
-install -d -m 755 $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/nutch
-install -d -m 755 $RPM_BUILD_ROOT%{_sysconfdir}/logrotate.d
-install -p -m 644 dist/%{name}-%{version}.jar $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/lib/
-# using install -m does not preserve the symlinks
-cp -d lib/* $RPM_BUILD_ROOT/%{_prefix}/share/rhn/search/lib
-install -p -m 644 src/config/log4j.properties $RPM_BUILD_ROOT/%{_prefix}/share/rhn/search/classes/log4j.properties
-install -p -m 644 src/config/etc/logrotate.d/rhn-search $RPM_BUILD_ROOT%{_sysconfdir}/logrotate.d/rhn-search
-install -p -m 644 src/config/com/redhat/satellite/search/db/* $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/classes/com/redhat/satellite/search/db
-install -p -m 755 src/config/rhn-search $RPM_BUILD_ROOT%{_initrddir}
-ln -s -f /usr/sbin/tanukiwrapper $RPM_BUILD_ROOT%{_bindir}/rhnsearchd
-install -p -m 644 src/config/search/rhn_search.conf $RPM_BUILD_ROOT%{_sysconfdir}/rhn/search/rhn_search.conf
-install -p -m 644 src/config/search/rhn_search_daemon.conf $RPM_BUILD_ROOT%{_sysconfdir}/rhn/search/rhn_search_daemon.conf
-ln -s -f %{_prefix}/share/rhn/search/lib/spacewalk-search-%{version}.jar $RPM_BUILD_ROOT%{_prefix}/share/rhn/search/lib/spacewalk-search.jar
-
-%clean
-rm -rf $RPM_BUILD_ROOT
-
-%post
-# This adds the proper /etc/rc*.d links for the script
-/sbin/chkconfig --add rhn-search
-
-%preun
-if [ $1 = 0 ] ; then
- /sbin/service rhn-search stop >/dev/null 2>&1
- /sbin/chkconfig --del rhn-search
-fi
-
-%files
-%defattr(644,root,root,755)
-%attr(755, root, root) %{_var}/log/rhn/search
-%{_prefix}/share/rhn/search/lib/*
-%{_prefix}/share/rhn/search/classes/log4j.properties
-%{_prefix}/share/rhn/search/classes/com/*
-%attr(755, root, root) %{_prefix}/share/rhn/search/indexes
-%attr(755, root, root) %{_initrddir}/rhn-search
-%attr(755, root, root) %{_bindir}/rhnsearchd
-%dir %{_sysconfdir}/rhn/search/
-%config(noreplace) %{_sysconfdir}/rhn/search/rhn_search.conf
-%config(noreplace) %{_sysconfdir}/rhn/search/rhn_search_daemon.conf
-%{_sysconfdir}/logrotate.d/rhn-search
-
-%changelog
-* Fri Jan 15 2010 Michael Mraka <michael.mraka(a)redhat.com> 0.8.1-1
-- rebuild for spacewalk 0.8
-
-* Wed Dec 2 2009 Miroslav SuchÜ <msuchy(a)redhat.com> 0.7.3-1
-- 480342 - move init script from /etc/init.d to /etc/rc.d/init.d
-
-* Wed Nov 25 2009 Miroslav SuchÜ <msuchy(a)redhat.com> 0.7.1-1
-- 516872 - Fixed search server's log properties (paji(a)redhat.com)
-- Update doc indexes to reside in "en-US" (jmatthew(a)redhat.com)
-- bumping versions to 0.7.0 (jmatthew(a)redhat.com)
-
-* Thu Jun 25 2009 John Matthews <jmatthew(a)redhat.com> 0.6.11-1
-- 487014 - SystemSearch remove score requirement to redirect to SDC on 1 result
- (jmatthew(a)redhat.com)
-- DocumentationSearch fixing returned links so they are relative and update for
- segment dir (jmatthew(a)redhat.com)
-
-* Mon Jun 01 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.10-1
-- added java debugger options for local dev config (jesusr(a)redhat.com)
-- store pid file locally. (jesusr(a)redhat.com)
-- 487014 - SystemSearch reducing scrore threshold for a single result to
- redirect to SDC page (jmatthew(a)redhat.com)
-
-* Tue May 26 2009 Devan Goodwin <dgoodwin(a)redhat.com> 0.6.9-1
-- 501925 - "rhn-search cleanindex" will now restart search after cleaning index
- (jmatthew(a)redhat.com)
-
-* Thu May 21 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.8-1
-- 457350 - added package search apis to match functionality webui provides (jmatthew(a)redhat.com)
-- Fixing "free form" search. Adding a boolean flag which when passed (jmatthew(a)redhat.com)
-
-* Fri May 08 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.7-1
-- clean up javadoc in AdminHandler (jesusr(a)redhat.com)
-
-* Tue May 05 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.6-1
-- cleanup ScheduleManager, fix potential null pointer, added a testcase.
-
-* Wed Apr 22 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.5-1
-- Add /etc/rhn/search/ %dir directive in search spec. (dgoodwin(a)redhat.com)
-
-* Fri Apr 17 2009 Devan Goodwin <dgoodwin(a)redhat.com> 0.6.4-1
-- Search server adding a xmlrpc call that will allow updates to be triggered
- immediately (jmatthew(a)redhat.com)
-- 487209 - enhanced system search for hardware devices (jmatthew(a)redhat.com)
-- 495921 - Limit results returned from Errata Search by Advisory
- (jmatthew(a)redhat.com)
-- 487158 - SystemSearch fixed search by customInfo (jmatthew(a)redhat.com)
-- Search Server adding a debug option to print out explanation of searches
- (jmatthew(a)redhat.com)
-- 442439 - enhancing csv for systemsearch (jmatthew(a)redhat.com)
-- 487189 - System Search fixed search by checkin (jmatthew(a)redhat.com)
-
-* Sun Apr 05 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.3-1
-- 487424 - add logrotate to %%files section (jesusr(a)redhat.com)
-
-* Sat Apr 04 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.6.2-1
-- install logrotate.d directory
-- remove / after RPM_BUILD_ROOT it's not needed
-- search requires doc-indexes, sw-doc-indexes provides doc-indexes (jesusr(a)redhat.com)
-- 492624 - "rhn-search cleanindex" checks db connection is up (jmatthew(a)redhat.com)
-- bump Versions to 0.6.0 (jesusr(a)redhat.com)
-
-* Tue Mar 31 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.10-1
-- 487424 - defined logrotate for rhn_search.log
-
-* Thu Mar 31 2009 jesus m. rodriguez <jesusr(a)redhat.com>
-- 487424 - define logrotate for rhn_search.log
-
-* Thu Feb 26 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.9-1
-- systems query changed to no longer require anything more than rhnServer.
-
-* Thu Feb 19 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.8-1
-- Fixing problem which broke unique documents in the lucene index.
-- SearchServer - SystemSearch lowering minimum score threshold
-
-* Thu Feb 19 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.7-1
-- 486182 - SystemSearch "id" is now tokenized, allows flexible 'ngram' s
-- 485820 - System Search: Isn't reindexing when system data is modified
-
-* Thu Feb 12 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.6-1
-- 484610 - doc search results were reversed, displaying worst results first
-- Cleaned up "tabs" which got added into some files previously.
-- Removed "orig" as a field from DocResults
-
-* Thu Feb 05 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.5-1
-- 479541, 483867 - replaced runuser with /sbin/runuser
-
-* Mon Jan 26 2009 jesus m. rodriguez <jesusr(a)redhat.com> 0.5.4-1
-- allow search-server to run in degraded mode if nutch isn't installed
-- fixing rpmlint warning: summary-ended-with-dot
-- allow multiple language search
-
-* Fri Jan 23 2009 Devan Goodwin <dgoodwin(a)redhat.com> 0.5.3-1
-- Fix bad install command.
-
-* Thu Jan 22 2009 Dennis Gilmore <dennis(a)ausil.us> 0.5.2-1
-- update java-devel BuildRequires to 1.6.0
-- preserve timestamps on install
-
-* Wed Jan 21 2009 Milan Zazrivec <mzazrivec(a)redhat.com> 0.5.1-1
-- obsolete rhn-search before 5.3.0 (for satellite's benefit)
-
-* Tue Jan 13 2009 John Matthews <jmatthews(a)redhat.com> 0.4.10-1
-- Added SystemSearch parameter, running kernel
-
-* Thu Dec 18 2008 John Matthews <jmatthews(a)redhat.com> 0.4.7-1
-- rebuild for spacewalk 0.4
-- added doc search
-
-* Mon Dec 8 2008 John Matthews <jmatthews(a)redhat.com> 0.4.1-1
-- updates for "make test-srpm" to function
-
-* Fri Oct 24 2008 Jesus M. Rodriguez <jesusr(a)redhat.com> 0.3.4-1
-- rebuild
-- added a "cleanindex" option to init.d script for rhn-search
-
-* Tue Oct 21 2008 Michael Mraka <michael.mraka(a)redhat.com> 0.3.3-1
-- resolves #467717 - fixed sysvinit scripts
-- resolves #467877 - use runuser instead of su
-
-* Tue Sep 23 2008 Milan Zazrivec 0.3.1-1
-- fixed package obsoletes
-
-* Wed Sep 3 2008 Milan Zazrivec 0.2.6-1
-- config file needs to point to correct spacewalk-search.jar
-
-* Tue Sep 2 2008 Jesus Rodriguez 0.2.5-1
-- tagged for rebuild
-- includes errata search capability
-- fix setup and source0 to be name-version
-- removed unnecessary bloat from libsrc directory
-- removed apache-ibatis-sqlmap as a requires for now. FIXME
-
-* Mon Aug 11 2008 Jesus Rodriguez 0.1.2-1
-- tagged for rebuild after rename, also bumping version
-
-* Tue Aug 5 2008 Jan Pazdziora 0.1.2-0
-- tagged for rebuild after rename, also bumping version
-
-* Mon Aug 4 2008 Jan Pazdziora 0.1.1-0
-- rebuilt with BuildRequires: java-devel >= 1.5.0
diff --git a/search-server/spacewalk-search/Makefile b/search-server/spacewalk-search/Makefile
new file mode 100644
index 0000000..700fc9e
--- /dev/null
+++ b/search-server/spacewalk-search/Makefile
@@ -0,0 +1,2 @@
+
+include ../rel-eng/Makefile
diff --git a/search-server/spacewalk-search/README b/search-server/spacewalk-search/README
new file mode 100644
index 0000000..b6f3d23
--- /dev/null
+++ b/search-server/spacewalk-search/README
@@ -0,0 +1,17 @@
+search-server is the new server used to search packages, and ultimately all
+content including systems, errata, and documentation.
+
+build.properties - build configuration
+build.xml - master ant build script
+buildconf/exclude - list of files excluded from compilation (temp solution)
+buildconf/build-utils.xml - ant macro definitions
+checkstyle.xml - checkstyle code style definition
+ivy.xml - ivy repo configuration file
+libsrc - src code for the libraries used
+nutch - configuration files for nutch crawler (not currently used)
+spacewalk-search.spec - search server RPM spec file
+rhn_search_daemon_dev.conf - development based configuration file
+run.sh - script used to run the software, especially during development
+scripts - useful scripts
+src - the source code
+task-lib - the libraries used by the search-server
diff --git a/search-server/spacewalk-search/build.properties b/search-server/spacewalk-search/build.properties
new file mode 100644
index 0000000..b8fd474
--- /dev/null
+++ b/search-server/spacewalk-search/build.properties
@@ -0,0 +1,22 @@
+java.src.dir=src/java
+config.src.dir=src/config
+java.lib.dir=lib
+java.task.lib.dir=task-lib
+report.dir=report
+build.dir=build
+build.instrument.dir=instrumented
+dist.dir=dist
+jar.name=spacewalk-search
+jar.version=1.0
+jar.file.name=${jar.name}-${jar.version}.jar
+ivyserver= http://jmrodri.fedorapeople.org
+ivy.log.module.when.found=false
+ivy.log.resolved.revision=false
+# Checkstyle config entries
+checkstyle.cache.file=.checkstyle_cache
+checkstyle.header.file=./buildconf/LICENSE.txt
+javadoc.method.scope=public
+javadoc.type.scope=package
+javadoc.var.scope=package
+javadoc.lazy=true
+jpackage.jars="commons-lang commons-logging redstone-xmlrpc redstone-xmlrpc-client quartz tanukiwrapper log4j commons-httpclient oro commons-cli commons-codec"
diff --git a/search-server/spacewalk-search/build.xml b/search-server/spacewalk-search/build.xml
new file mode 100644
index 0000000..de8e25f
--- /dev/null
+++ b/search-server/spacewalk-search/build.xml
@@ -0,0 +1,241 @@
+<project name="search-server" basedir="." default="all">
+ <import file="buildconf/build-utils.xml" />
+
+ <property file="build.properties" />
+
+ <path id="project.taskjars">
+ <fileset dir="${java.task.lib.dir}" includes="**/*.jar" />
+ </path>
+
+ <path id="project.classpath">
+ <fileset dir="${java.lib.dir}" includes="**/*.jar" />
+ <fileset dir="${java.task.lib.dir}" >
+ <include name="junit*.jar" />
+ <include name="emma*.jar" />
+ </fileset>
+ </path>
+
+ <path id="test.classpath">
+ <pathelement location="${build.dir}" />
+ <path refid="project.classpath" />
+ <pathelement location="${basedir}/src/config" />
+ </path>
+
+ <target name="init-tasks">
+ <taskdef name="ivy-retrieve"
+ classname="fr.jayasoft.ivy.ant.IvyRetrieve"
+ classpathref="project.taskjars"/>
+ <taskdef name="ivy-configure"
+ classname="fr.jayasoft.ivy.ant.IvyConfigure"
+ classpathref="project.taskjars"/>
+ <taskdef name="ivy-resolve"
+ classname="fr.jayasoft.ivy.ant.IvyResolve"
+ classpathref="project.taskjars"/>
+ <taskdef name="ivy-publish"
+ classname="fr.jayasoft.ivy.ant.IvyPublish"
+ classpathref="project.taskjars"/>
+ <taskdef resource="checkstyletask.properties">
+ <classpath>
+ <pathelement path="${java.task.lib.dir}/checkstyle-4.1.jar" />
+ <pathelement path="${java.task.lib.dir}/commons-beanutils-1.7.0.jar" />
+ <pathelement path="${java.task.lib.dir}/commons-logging-1.0.4.jar" />
+ <pathelement path="${java.task.lib.dir}/antlr-2.7.6.jar" />
+ <pathelement path="${java.task.lib.dir}/regexp-1.3.jar" />
+ </classpath>
+ </taskdef>
+ <taskdef resource="emma_ant.properties" classpathref="project.taskjars" />
+ <taskdef resource="net/sf/antcontrib/antlib.xml">
+ <classpath>
+ <pathelement location="${java.task.lib.dir}/ant-contrib-1.0.jar"/>
+ </classpath>
+ </taskdef>
+ </target>
+
+ <target name="check-testcase-name" if="testcase" depends="init-tasks">
+ <propertyregex property="valid.testcase"
+ input="${testcase}"
+ regexp="(.*)Test$"
+ select="\1"
+ casesensitive="true" />
+ </target>
+
+ <target name="check-testcase" depends="check-testcase-name" if="testcase"
+ unless="valid.testcase">
+ <fail message="Invalid testcase name: ${testcase}. Class name must look like .*Test"/>
+ </target>
+
+ <target name="test" depends="compile, check-testcase"
+ description="Run the tests (use -Dtestcase=<testcase>)">
+ <mkdir dir="${report.dir}" />
+ <!-- set testcase to wildcard "*" to test everything, unless
+ a specific testcase name was supplied. -->
+ <if>
+ <not>
+ <isset property="${testcase}" />
+ </not>
+ <then>
+ <property name="testcase" value="*Test"/>
+ </then>
+ </if>
+ <junit>
+ <sysproperty key="rhn.config.dir" value="/etc/rhn" />
+ <sysproperty key="search.config.dir" value="src/config/search" />
+ <sysproperty key="log4j.configuration" value="log4j.test.properties" />
+ <classpath refid="test.classpath" />
+ <formatter type="brief" usefile="false" />
+ <formatter type="xml" />
+ <batchtest fork="yes" todir="${report.dir}">
+ <fileset dir="${build.dir}" includes="**/${testcase}.class" />
+ </batchtest>
+ </junit>
+ </target>
+
+ <target name="checkstyle" depends="init-tasks, package">
+ <delete dir="${report.dir}" />
+ <mkdir dir="${report.dir}" />
+ <checkstyle config="checkstyle.xml" failOnViolation="true" >
+ <property key="javadoc.method.scope" value="public" />
+ <property key="javadoc.type.scope" value="package" />
+ <property key="javadoc.var.scope" value="package" />
+ <property key="javadoc.lazy" value="${javadoc.lazy}" />
+ <fileset dir="${java.src.dir}" >
+ <include name="**/*.java" />
+ <exclude name="**/tests/**" />
+ </fileset>
+ <classpath>
+ <fileset dir="${java.lib.dir}" includes="**/*.jar" />
+ <fileset dir="${java.task.lib.dir}" includes="junit*.jar" />
+ <fileset dir="${dist.dir}" includes="${jar.file.name}" />
+ </classpath>
+ <formatter type="plain" />
+ <formatter type="xml" toFile="${report.dir}/checkstyle_report.xml" />
+ </checkstyle>
+ </target>
+
+ <target name="resolve-local" description="resolve jars via jpackage" if="installbuild">
+ <copy toDir="${java.lib.dir}" overwrite="true">
+ <fileset dir="buildconf/tempjars">
+ <include name="**/*.jar" />
+ </fileset>
+ </copy>
+
+ <jpackage-deps jars="${jpackage.jars}" dir="${java.lib.dir}" />
+ </target>
+
+ <target name="resolve-ivy" description="retrieve dependencies with ivy"
+ depends="init-tasks" unless="installbuild">
+ <!-- properties set here to show we are overriding default ivy values -->
+ <property name="ivy.default.ivy.user.dir" value="${user.home}/.ivy/search-server"/>
+ <property name="ivy.local.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
+ <property name="ivy.ivyrep.default.ivy.root" value="${ivyserver}/ivy/" />
+ <property name="ivy.ivyrep.default.artifact.root" value="${ivyserver}/ivy/" />
+ <property name="ivy.ivyrep.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
+ <ivy-retrieve/>
+ </target>
+
+ <target name="resolve" depends="resolve-ivy,resolve-local" />
+
+ <target name="prep">
+ <mkdir dir="${build.dir}" />
+ <mkdir dir="${dist.dir}" />
+ <mkdir dir="${java.lib.dir}" />
+ </target>
+
+ <target name="clean">
+ <delete dir="${build.dir}" />
+ <delete dir="${build.instrument.dir}" />
+ <delete dir="${dist.dir}" />
+ <delete dir="${java.lib.dir}" />
+ <delete dir="${report.dir}" />
+ <delete file="coverage.ec" />
+ <delete file="rhn_search_daemon.log" />
+ </target>
+
+ <target name="compile" depends="prep, resolve">
+ <javac srcdir="${java.src.dir}"
+ classpathref="project.classpath"
+ destdir="${build.dir}"
+ deprecation="on"
+ excludesfile="buildconf/exclude"
+ debug="on" />
+ <copy todir="${build.dir}/com/redhat/satellite/search/db">
+ <fileset dir="${config.src.dir}/com/redhat/satellite/search/db/">
+ <include name="*.xml" />
+ </fileset>
+ </copy>
+ <copy file="${config.src.dir}/log4j.properties" todir="${build.dir}" />
+ </target>
+
+ <target name="package" depends="compile">
+ <jar basedir="${build.dir}"
+ destfile="${dist.dir}/${jar.file.name}"
+ excludes="**/tests/**"
+ includes="**/**" />
+ </target>
+
+ <target name="create-local-repo" description="Create a local Ivy repo">
+ <mkdir dir="${user.home}/.ivy/search-server/local/" />
+ </target>
+
+ <target name="clean-cache" description="Removes the Ivy jar cache">
+ <delete dir="${lib.dir}" quiet="true" />
+ <delete dir="${user.home}/.ivy/search-server/cache/" quiet="true" />
+ </target>
+
+ <target name="all" depends="package" />
+
+ <target name="init-install">
+ <property name="installbuild" value="true"/>
+ </target>
+
+ <target name="install" depends="init-install,package" />
+
+ <target name="instrument" depends="init-tasks">
+ <mkdir dir="${report.dir}" />
+ <mkdir dir="${build.instrument.dir}" />
+
+ <emma enabled="true">
+ <instr merge="no"
+ mode="overwrite"
+ instrpath="${build.dir}"
+ outfile="${report.dir}/coverage.em" >
+ <filter excludes="*Exception" />
+ <filter excludes="*.tests.*" />
+ </instr>
+ <!--
+ <instr outdir="${build.instrument.dir}" merge="no"
+ instrpath="${build.dir}"
+ mode="fullcopy"
+ outfile="${report.dir}/coverage.em" >
+ <filter excludes="*Exception" />
+ <filter excludes="*.tests.*" />
+ </instr>
+ -->
+ </emma>
+
+ <!--
+ <copy toDir="${build.instrument.dir}/classes">
+ <fileset dir="${build.dir}">
+ <include name="**/*.xml" />
+ </fileset>
+ </copy>
+ -->
+ </target>
+
+ <target name="coverage-report" depends="instrument">
+ <emma enabled="true">
+ <report sourcepath="${java.src.dir}"
+ sort="+block,+name,+method,+class"
+ metrics="method:70,block:80,line:80,class:100">
+ <fileset dir="${report.dir}" includes="*.em" />
+ <fileset dir="." includes="*.ec" />
+ <html outfile="${report.dir}/emma.html"
+ depth="method"
+ columns="name,class,method,block,line" />
+ <xml outfile="${report.dir}/emma.xml"
+ depth="method"
+ columns="name,class,method,block,line" />
+ </report>
+ </emma>
+ </target>
+</project>
diff --git a/search-server/spacewalk-search/buildconf/LICENSE.txt b/search-server/spacewalk-search/buildconf/LICENSE.txt
new file mode 100644
index 0000000..629462a
--- /dev/null
+++ b/search-server/spacewalk-search/buildconf/LICENSE.txt
@@ -0,0 +1,14 @@
+/**
+ * Copyright (c) 2008 Red Hat, Inc.
+ *
+ * This software is licensed to you under the GNU General Public License,
+ * version 2 (GPLv2). There is NO WARRANTY for this software, express or
+ * implied, including the implied warranties of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE. You should have received a copy of GPLv2
+ * along with this software; if not, see
+ * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt .
+ *
+ * Red Hat trademarks are not licensed under GPLv2. No permission is
+ * granted to use or replicate Red Hat trademarks that are incorporated
+ * in this software or its documentation.
+ */
diff --git a/search-server/spacewalk-search/buildconf/build-utils.xml b/search-server/spacewalk-search/buildconf/build-utils.xml
new file mode 100644
index 0000000..0011a83
--- /dev/null
+++ b/search-server/spacewalk-search/buildconf/build-utils.xml
@@ -0,0 +1,19 @@
+<project name="build-utils.xml">
+ <!--
+ creates symlinks for jpackage jars
+ requires: jpackage-utils
+ other: requires rpms of the jars specified to be installed
+ -->
+ <macrodef name="jpackage-deps">
+ <attribute name="jars" />
+ <attribute name="dir" />
+
+ <sequential>
+ <exec executable="build-jar-repository" failonerror="true" >
+ <arg value="--preserve-naming" />
+ <arg value="-s @{dir}" />
+ <arg line="@{jars}" />
+ </exec>
+ </sequential>
+ </macrodef>
+</project>
diff --git a/search-server/spacewalk-search/buildconf/exclude b/search-server/spacewalk-search/buildconf/exclude
new file mode 100644
index 0000000..7873251
--- /dev/null
+++ b/search-server/spacewalk-search/buildconf/exclude
@@ -0,0 +1,2 @@
+**/WebCrawl.java
+**/IndexDocumentsTask.java
diff --git a/search-server/spacewalk-search/buildconf/tempjars/hadoop-0.18.1-core.jar b/search-server/spacewalk-search/buildconf/tempjars/hadoop-0.18.1-core.jar
new file mode 100644
index 0000000..a024c3c
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/hadoop-0.18.1-core.jar differ
diff --git a/search-server/spacewalk-search/buildconf/tempjars/ibatis-2.3.0.677.jar b/search-server/spacewalk-search/buildconf/tempjars/ibatis-2.3.0.677.jar
new file mode 100644
index 0000000..72dbe19
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/ibatis-2.3.0.677.jar differ
diff --git a/search-server/spacewalk-search/buildconf/tempjars/lucene-analyzers-2.3.2.jar b/search-server/spacewalk-search/buildconf/tempjars/lucene-analyzers-2.3.2.jar
new file mode 100644
index 0000000..cf0d296
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/lucene-analyzers-2.3.2.jar differ
diff --git a/search-server/spacewalk-search/buildconf/tempjars/lucene-core-2.3.2.jar b/search-server/spacewalk-search/buildconf/tempjars/lucene-core-2.3.2.jar
new file mode 100644
index 0000000..639f750
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/lucene-core-2.3.2.jar differ
diff --git a/search-server/spacewalk-search/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar b/search-server/spacewalk-search/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar
new file mode 100644
index 0000000..4bdec09
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/nutch-2008-12-01_04-01-21.jar differ
diff --git a/search-server/spacewalk-search/buildconf/tempjars/picocontainer-1.3.jar b/search-server/spacewalk-search/buildconf/tempjars/picocontainer-1.3.jar
new file mode 100644
index 0000000..9a3f670
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/picocontainer-1.3.jar differ
diff --git a/search-server/spacewalk-search/buildconf/tempjars/simple-core-3.1.3.jar b/search-server/spacewalk-search/buildconf/tempjars/simple-core-3.1.3.jar
new file mode 100644
index 0000000..80b44c1
Binary files /dev/null and b/search-server/spacewalk-search/buildconf/tempjars/simple-core-3.1.3.jar differ
diff --git a/search-server/spacewalk-search/checkstyle.xml b/search-server/spacewalk-search/checkstyle.xml
new file mode 100644
index 0000000..89cde80
--- /dev/null
+++ b/search-server/spacewalk-search/checkstyle.xml
@@ -0,0 +1,233 @@
+<?xml version="1.0"?>
+<!DOCTYPE module PUBLIC
+ "-//Puppy Crawl//DTD Check Configuration 1.1//EN"
+ "http://www.puppycrawl.com/dtds/configuration_1_1.dtd ">
+
+<!--
+
+ Checkstyle configuration that checks the sun coding conventions from:
+
+ - the Java Language Specification at
+ http://java.sun.com/docs/books/jls/second_edition/html/index.html
+
+ - the Sun Code Conventions at http://java.sun.com/docs/codeconv/
+
+ - the Javadoc guidelines at
+ http://java.sun.com/j2se/javadoc/writingdoccomments/index.html
+
+ - the JDK Api documentation http://java.sun.com/j2se/docs/api/index.html
+
+ - some best practices
+
+ Checkstyle is very configurable. Be sure to read the documentation at
+ http://checkstyle.sf.net (or in your downloaded distribution).
+
+ Most Checks are configurable, be sure to consult the documentation.
+
+ To completely disable a check, just comment it out or delete it from the file.
+
+ Finally, it is worth reading the documentation.
+
+-->
+
+<module name="Checker">
+
+ <!-- Checks that a package.html file exists for each package. -->
+ <!-- See http://checkstyle.sf.net/config_javadoc.html#PackageHtml -->
+<!-- <module name="PackageHtml"/> -->
+
+ <!-- Checks whether files end with a new line. -->
+ <!-- See http://checkstyle.sf.net/config_misc.html#NewlineAtEndOfFile -->
+ <module name="NewlineAtEndOfFile"/>
+
+ <!-- Checks that property files contain the same keys. -->
+ <!-- See http://checkstyle.sf.net/config_misc.html#Translation -->
+ <module name="Translation"/>
+
+ <module name="TreeWalker">
+
+ <property name="cacheFile" value="${checkstyle.cache.file}"/>
+
+ <!-- ************************************************************** -->
+ <!-- Checks that are different from the sun coding conventions ones -->
+ <!-- ************************************************************** -->
+ <property name="tabWidth" value="4"/>
+ <module name="LeftCurly" />
+ <module name="RightCurly">
+ <property name="option" value="alone"/>
+ </module>
+ <module name="LineLength">
+ <property name="ignorePattern" value="import"/>
+ <property name="max" value="92"/>
+ </module>
+
+ <!-- ************************************************************** -->
+ <!-- Default Sun coding conventions checks -->
+ <!-- ************************************************************** -->
+
+ <!-- Checks for Javadoc comments. -->
+ <!-- See http://checkstyle.sf.net/config_javadoc.html -->
+ <module name="JavadocMethod">
+ <property name="scope" value="${javadoc.method.scope}" />
+ <property name="allowUndeclaredRTE" value="true" />
+ <property name="allowThrowsTagsForSubclasses" value="${javadoc.lazy}" />
+ <property name="allowMissingParamTags" value="${javadoc.lazy}" />
+ <property name="allowMissingThrowsTags" value="${javadoc.lazy}" />
+ <property name="allowMissingReturnTag" value="${javadoc.lazy}" />
+ </module>
+ <module name="JavadocType">
+ <property name="versionFormat" value="\$Rev.*\$"/>
+ <property name="scope" value="${javadoc.type.scope}" />
+ </module>
+ <module name="JavadocVariable">
+ <property name="scope" value="${javadoc.var.scope}" />
+ <property name="severity" value="ignore"/>
+ </module>
+
+<!-- JavadocStyle not supported by some versions. -->
+<!-- <module name="JavadocStyle"/> -->
+
+
+ <!-- Checks for Naming Conventions. -->
+ <!-- See http://checkstyle.sf.net/config_naming.html -->
+ <module name="ConstantName"/>
+ <module name="LocalFinalVariableName"/>
+ <module name="LocalVariableName"/>
+ <module name="MethodName"/>
+ <module name="PackageName">
+ <property name="format" value="^[a-z]+(\.[A-Za-z][A-Za-z0-9]*)*$"/>
+ </module>
+ <module name="ParameterName"/>
+ <module name="StaticVariableName"/>
+ <module name="TypeName"/>
+
+
+ <!-- Checks for Headers -->
+ <!-- See http://checkstyle.sf.net/config_header.html -->
+ <module name="Header">
+ <!-- The follow property value demonstrates the ability -->
+ <!-- to have access to ANT properties. In this case it uses -->
+ <!-- the ${basedir} property to allow Checkstyle to be run -->
+ <!-- from any directory within a project. -->
+ <property name="headerFile" value="${checkstyle.header.file}"/>
+ </module>
+
+ <!-- Following interprets the header file as regular expressions. -->
+ <!-- <module name="RegexpHeader"/> -->
+
+
+
+ <!-- Checks for imports -->
+ <!-- See http://checkstyle.sf.net/config_import.html -->
+ <module name="AvoidStarImport"/>
+ <module name="IllegalImport"/> <!-- defaults to sun.* packages -->
+ <module name="RedundantImport"/>
+ <module name="UnusedImports"/>
+
+
+ <!-- Checks for Size Violations. -->
+ <!-- See http://checkstyle.sf.net/config_sizes.html -->
+ <module name="MethodLength">
+ <property name="tokens" value="METHOD_DEF"/>
+ <property name="max" value="150"/>
+ <property name="countEmpty" value="false"/>
+ </module>
+ <module name="ParameterNumber"/>
+
+
+ <!-- Checks for whitespace -->
+ <!-- See http://checkstyle.sf.net/config_whitespace.html -->
+ <module name="EmptyForIteratorPad"/>
+ <module name="NoWhitespaceAfter">
+ <property name="tokens" value="BNOT, DEC, DOT, INC, LNOT, UNARY_MINUS, UNARY_PLUS, TYPECAST, GENERIC_START"/>
+ </module>
+ <module name="NoWhitespaceBefore">
+ <property name="tokens" value="SEMI, POST_DEC, POST_INC, GENERIC_START, GENERIC_END"/>
+ </module>
+ <module name="OperatorWrap">
+ <property name="option" value="eol" />
+ </module>
+ <module name="ParenPad"/>
+<!-- <module name="TypecastParenPad"/> -->
+ <module name="TabCharacter"/>
+ <module name="WhitespaceAfter">
+ <property name="tokens" value="COMMA, SEMI, GENERIC_END"/>
+ </module>
+ <module name="WhitespaceAround">
+ <property name="tokens" value="ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN, BXOR, BXOR_ASSIGN,
+COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LCURLY, LE, LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
+LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE, LOR, LT, MINUS,
+MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL, PLUS, PLUS_ASSIGN, QUESTION, RCURLY, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN, STAR, STAR_ASSIGN, TYPE_EXTENSION_AND, WILDCARD_TYPE"/>
+ </module>
+ <module name="MethodParamPad">
+ <property name="allowLineBreaks" value="true"/>
+ </module>
+
+
+ <!-- Modifier Checks -->
+ <!-- See http://checkstyle.sf.net/config_modifiers.html -->
+ <module name="ModifierOrder"/>
+ <module name="RedundantModifier"/>
+
+
+ <!-- Checks for blocks. You know, those {}'s -->
+ <!-- See http://checkstyle.sf.net/config_blocks.html -->
+ <module name="AvoidNestedBlocks"/>
+ <module name="EmptyBlock">
+ <property name="option" value="text"/>
+ </module>
+
+ <module name="NeedBraces"/>
+
+
+ <!-- Checks for common coding problems -->
+ <!-- See http://checkstyle.sf.net/config_coding.html -->
+ <!-- <module name="AvoidInlineConditionals"/> -->
+<!-- <module name="CovariantEquals"/> -->
+ <module name="DoubleCheckedLocking"/> <!-- MY FAVOURITE -->
+ <module name="EmptyStatement"/>
+ <module name="EqualsHashCode"/>
+ <module name="HiddenField"/>
+ <module name="IllegalInstantiation"/>
+ <module name="InnerAssignment"/>
+ <!-- <module name="MagicNumber" /> -->
+ <module name="MissingSwitchDefault"/>
+<!-- <module name="RedundantThrows"/> -->
+ <module name="SimplifyBooleanExpression"/>
+ <module name="SimplifyBooleanReturn"/>
+<!-- <module name="IllegalCatch"/> -->
+<!-- <module name="PackageDeclaration"/> -->
+
+ <!-- Checks for class design -->
+ <!-- See http://checkstyle.sf.net/config_design.html -->
+<!-- <module name="DesignForExtension"/>-->
+<!-- <module name="FinalClass"/> -->
+ <module name="HideUtilityClassConstructor"/>
+ <module name="InterfaceIsType"/>
+ <module name="VisibilityModifier">
+ <property name="protectedAllowed" value="true" />
+ </module>
+
+
+ <!-- Miscellaneous other checks. -->
+ <!-- See http://checkstyle.sf.net/config_misc.html -->
+ <module name="ArrayTypeStyle"/>
+<!-- <module name="FinalParameters"/> -->
+<!--
+ <module name="GenericIllegalRegexp">
+ <property name="format" value="System\.out\.println"/>
+ </module>
+-->
+ <module name="UpperEll"/>
+
+ <!-- Optional Checks -->
+ <!-- (gack, not available until version 3 of checkstyle -->
+<!--
+ <module name="usage.OneMethodPrivateField"/>
+ <module name="usage.UnusedLocalVariable"/>
+ <module name="usage.UnusedParameter"/>
+ <module name="usage.UnusedPrivateField"/>
+-->
+ </module>
+
+</module>
diff --git a/search-server/spacewalk-search/ivy.xml b/search-server/spacewalk-search/ivy.xml
new file mode 100644
index 0000000..aec44ca
--- /dev/null
+++ b/search-server/spacewalk-search/ivy.xml
@@ -0,0 +1,28 @@
+<ivy-module version="1.0">
+ <info organisation="redhat" module="rhn-java" />
+ <dependencies>
+ <dependency org="redhat" name="simple-core" rev="3.1.3" />
+ <dependency org="redhat" name="lucene-core" rev="2.3.2" />
+ <dependency org="redhat" name="lucene-analyzers" rev="2.3.2" />
+ <dependency org="redhat" name="commons-lang" rev="2.0" />
+ <dependency org="redhat" name="commons-logging" rev="1.1" />
+ <dependency org="redhat" name="redstone-xmlrpc" rev="1.1_20071120" />
+ <dependency org="redhat" name="redstone-xmlrpc-client" rev="1.1_20071120" />
+ <dependency org="redhat" name="ibatis" rev="2.3.0.677" />
+ <dependency org="redhat" name="ojdbc14" rev="1.10" />
+ <dependency org="redhat" name="quartz" rev="1.5.1" />
+ <dependency org="redhat" name="picocontainer" rev="1.3" />
+ <dependency org="redhat" name="tanukiwrapper" rev="3.1.2" />
+ <dependency org="redhat" name="log4j" rev="1.2.8" />
+ <dependency org="redhat" name="logdriver" rev="0.1" />
+ <dependency org="redhat" name="nutch" rev="2008-12-01_04-01-21" />
+ <dependency org="redhat" name="hadoop" rev="0.18.1-core" />
+ <!-- dependency org="redhat" name="commons-httpclient" rev="3.0" / -->
+ <!-- dependency org="redhat" name="oro" rev="2.0.8" / -->
+ <!-- dependency org="redhat" name="commons-cli" rev="1.0" / -->
+ <!-- dependency org="redhat" name="commons-codec" rev="1.2" / -->
+ <!-- dependency org="redhat" name="tika" rev="0.1-incubating" / -->
+ <!-- dependency org="redhat" name="icu4j" rev="3_8_1" / -->
+ <!-- dependency org="redhat" name="icu4j-charsets" rev="3_8_1" / -->
+ </dependencies>
+</ivy-module>
diff --git a/search-server/spacewalk-search/libsrc/hadoop-0.16.4-src.jar b/search-server/spacewalk-search/libsrc/hadoop-0.16.4-src.jar
new file mode 100644
index 0000000..c941a7c
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/hadoop-0.16.4-src.jar differ
diff --git a/search-server/spacewalk-search/libsrc/ibatis-2.3.0.677-src.zip b/search-server/spacewalk-search/libsrc/ibatis-2.3.0.677-src.zip
new file mode 100644
index 0000000..8c3274b
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/ibatis-2.3.0.677-src.zip differ
diff --git a/search-server/spacewalk-search/libsrc/icu4j-3_8_1-src.jar b/search-server/spacewalk-search/libsrc/icu4j-3_8_1-src.jar
new file mode 100644
index 0000000..19dd665
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/icu4j-3_8_1-src.jar differ
diff --git a/search-server/spacewalk-search/libsrc/log4j-1.2.8-src.jar b/search-server/spacewalk-search/libsrc/log4j-1.2.8-src.jar
new file mode 100644
index 0000000..b36df55
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/log4j-1.2.8-src.jar differ
diff --git a/search-server/spacewalk-search/libsrc/lucene-2.3.2-src.zip b/search-server/spacewalk-search/libsrc/lucene-2.3.2-src.zip
new file mode 100644
index 0000000..b49b9b6
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/lucene-2.3.2-src.zip differ
diff --git a/search-server/spacewalk-search/libsrc/nutch-1.0dev_2008_05_14-src.jar b/search-server/spacewalk-search/libsrc/nutch-1.0dev_2008_05_14-src.jar
new file mode 100644
index 0000000..372eca5
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/nutch-1.0dev_2008_05_14-src.jar differ
diff --git a/search-server/spacewalk-search/libsrc/nutch-2008-12-01_04-01-21-src.zip b/search-server/spacewalk-search/libsrc/nutch-2008-12-01_04-01-21-src.zip
new file mode 100644
index 0000000..268a010
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/nutch-2008-12-01_04-01-21-src.zip differ
diff --git a/search-server/spacewalk-search/libsrc/quartz-1.5.1-src.jar b/search-server/spacewalk-search/libsrc/quartz-1.5.1-src.jar
new file mode 100644
index 0000000..79edf1a
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/quartz-1.5.1-src.jar differ
diff --git a/search-server/spacewalk-search/libsrc/redstone-xmlrpc-1.1_20071120-src.jar b/search-server/spacewalk-search/libsrc/redstone-xmlrpc-1.1_20071120-src.jar
new file mode 100644
index 0000000..2dc7cf7
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/redstone-xmlrpc-1.1_20071120-src.jar differ
diff --git a/search-server/spacewalk-search/libsrc/simple-3.1.3-src.zip b/search-server/spacewalk-search/libsrc/simple-3.1.3-src.zip
new file mode 100644
index 0000000..cdd83c6
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/simple-3.1.3-src.zip differ
diff --git a/search-server/spacewalk-search/libsrc/tanukiwrapper-3.1.2-src.jar b/search-server/spacewalk-search/libsrc/tanukiwrapper-3.1.2-src.jar
new file mode 100644
index 0000000..9436fbd
Binary files /dev/null and b/search-server/spacewalk-search/libsrc/tanukiwrapper-3.1.2-src.jar differ
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp.sh b/search-server/spacewalk-search/nutch/crawl_jsp.sh
new file mode 100755
index 0000000..d7a7e19
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+
+
+if [ "${JAVA_HOME}" = "" ]; then
+ export JAVA_HOME=/usr/lib/jvm/java
+ echo "Setting JAVA_HOME to: ${JAVA_HOME}"
+fi
+
+export NUTCH_HOME=/usr/share/nutch
+export NUTCH_CONF_DIR=`pwd`/crawl_jsp/conf
+export NUTCH_OPTS=-Djava.util.logging.config.file="${NUTCH_CONF}/logging.properties"
+export NUTCH_LOG_DIR=`pwd`/logs
+export NUTCH_LOG_FILE=$0.log
+export OUTPUT_DIR=`pwd`/data/crawl_jsp
+
+echo "NUTCH_HOME = ${NUTCH_HOME}"
+echo "NUTCH_CONF_DIR = ${NUTCH_CONF_DIR}"
+echo "NUTCH_OPTS = ${NUTCH_OPTS}"
+echo "NUTCH_LOG_DIR = ${NUTCH_LOG_DIR}"
+echo "NUTCH_LOG_FILE = ${NUTCH_LOG_FILE}"
+echo "OUTPUT_DIR = ${OUTPUT_DIR}"
+
+if [ ! -d ${NUTCH_LOG_DIR} ]; then
+ echo "Creating log directory ${NUTCH_LOG_DIR}"
+ mkdir ${NUTCH_LOG_DIR}
+fi
+
+
+if [ ! -d ${OUTPUT_DIR} ]; then
+ echo "Creating output directory ${OUTPUT_DIR}"
+ mkdir -p ${OUTPUT_DIR}
+fi
+#Need to adjust nutch RPM so it's scripts under bin are executable by all
+
+${NUTCH_HOME}/bin/nutch crawl ${NUTCH_CONF_DIR}/../urls -dir ${OUTPUT_DIR} -depth 10 -threads 50
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/automaton-urlfilter.txt b/search-server/spacewalk-search/nutch/crawl_jsp/conf/automaton-urlfilter.txt
new file mode 100644
index 0000000..84cf8fa
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/automaton-urlfilter.txt
@@ -0,0 +1,34 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# The default url filter.
+# Better for whole-internet crawling.
+
+# Each non-comment, non-blank line contains a regular expression
+# prefixed by '+' or '-'. The first matching pattern in the file
+# determines whether a URL is included or ignored. If no pattern
+# matches, the URL is ignored.
+
+# skip file: ftp: and mailto: urls
+-(file|ftp|mailto):.*
+
+# skip image and other suffixes we can't yet parse
+-.*\.(gif|GIF|jpg|JPG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe)
+
+# skip URLs containing certain characters as probable queries, etc.
+-.*[?*!(a)=].*
+
+# accept anything else
++.*
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/common-terms.utf8 b/search-server/spacewalk-search/nutch/crawl_jsp/conf/common-terms.utf8
new file mode 100644
index 0000000..220d1da
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/common-terms.utf8
@@ -0,0 +1,28 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Common terms and phrases which will be indexed in n-grams
+# in order to optimize search.
+content:a
+content:and
+content:for
+content:in
+content:of
+content:the
+content:to
+url:com
+url:http
+url:http-www
+url:www
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/configuration.xsl b/search-server/spacewalk-search/nutch/crawl_jsp/conf/configuration.xsl
new file mode 100644
index 0000000..79141dc
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/configuration.xsl
@@ -0,0 +1,40 @@
+<?xml version="1.0"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform " version="1.0">
+<xsl:output method="html"/>
+<xsl:template match="configuration">
+<html>
+<body>
+<table border="1">
+<tr>
+ <td>name</td>
+ <td>value</td>
+ <td>description</td>
+</tr>
+<xsl:for-each select="property">
+<tr>
+ <td><a name="{name}"><xsl:value-of select="name"/></a></td>
+ <td><xsl:value-of select="value"/></td>
+ <td><xsl:value-of select="description"/></td>
+</tr>
+</xsl:for-each>
+</table>
+</body>
+</html>
+</xsl:template>
+</xsl:stylesheet>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/context.xsl b/search-server/spacewalk-search/nutch/crawl_jsp/conf/context.xsl
new file mode 100644
index 0000000..fbb3bc6
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/context.xsl
@@ -0,0 +1,88 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+
+ Author : Chris Mattmann
+ Auhtor : Jérôme Charron
+ Description: This xsl file is used to transform dynamic properties out of the
+ nutch-default.xml file into a deployable Context.xml file for configuring
+ the Nutch war file in a servlet container.
+-->
+
+<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform ">
+
+<xsl:template match="/">
+<Context path="/nutch" docBase="nutch-0.9-dev.war"
+ debug="5" reloadable="true" crossContext="true">
+
+<xsl:for-each select="configuration/property">
+
+<!-- "searcher." properties -->
+<xsl:call-template name="parameter">
+ <xsl:with-param name="property" select="current()"/>
+ <xsl:with-param name="filter" select="'searcher.'"/>
+</xsl:call-template>
+
+<!-- "plugin." properties -->
+<xsl:call-template name="parameter">
+ <xsl:with-param name="property" select="current()"/>
+ <xsl:with-param name="filter" select="'plugin.'"/>
+</xsl:call-template>
+
+<!-- "extension.clustering." properties -->
+<xsl:call-template name="parameter">
+ <xsl:with-param name="property" select="current()"/>
+ <xsl:with-param name="filter" select="'extension.clustering.'"/>
+</xsl:call-template>
+
+<!-- "extension.ontology." properties -->
+<xsl:call-template name="parameter">
+ <xsl:with-param name="property" select="current()"/>
+ <xsl:with-param name="filter" select="'extension.ontology.'"/>
+</xsl:call-template>
+
+<!-- "query." properties -->
+<xsl:call-template name="parameter">
+ <xsl:with-param name="property" select="current()"/>
+ <xsl:with-param name="filter" select="'query.'"/>
+</xsl:call-template>
+
+</xsl:for-each>
+
+</Context>
+</xsl:template>
+
+
+<!--
+ ! Template used to write out a parameter if the property's
+ ! name contains the specified filter string.
+ !-->
+<xsl:template name="parameter">
+ <xsl:param name="property"/>
+ <xsl:param name="filter"/>
+ <xsl:if test="contains(name, $filter)">
+ <Parameter override="false">
+ <xsl:attribute name="name">
+ <xsl:value-of select="name"/>
+ </xsl:attribute>
+ <xsl:attribute name="value">
+ <xsl:value-of select="value"/>
+ </xsl:attribute>
+ </Parameter>
+ </xsl:if>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-tool.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-tool.xml
new file mode 100644
index 0000000..9f6d667
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-tool.xml
@@ -0,0 +1,59 @@
+<?xml version="1.0" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Overidden defaults for intranet use. -->
+
+<!-- Do not modify this file directly. Instead, copy entries that you -->
+<!-- wish to modify from this file into nutch-site.xml and change them -->
+<!-- there. If nutch-site.xml does not already exist, create it. -->
+
+<configuration>
+
+<property>
+ <name>urlfilter.regex.file</name>
+ <value>crawl-urlfilter.txt</value>
+</property>
+
+<property>
+ <name>db.ignore.internal.links</name>
+ <value>false</value>
+ <description>If true, when adding new links to a page, links from
+ the same host are ignored. This is an effective way to limit the
+ size of the link database, keeping the only the highest quality
+ links.
+ </description>
+</property>
+
+<property>
+ <name>fetcher.server.delay</name>
+ <value>1.0</value>
+ <description>The number of seconds the fetcher will delay between
+ successive requests to the same server.</description>
+</property>
+
+<property>
+ <name>http.max.delays</name>
+ <value>1000</value>
+ <description>The number of times a thread will delay when trying to
+ fetch a page. When using the crawl tool there are likely to be very
+ few different hosts, so we need to be willing to wait longer for
+ each.</description>
+</property>
+
+</configuration>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-urlfilter.txt b/search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-urlfilter.txt
new file mode 100644
index 0000000..2698c17
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/crawl-urlfilter.txt
@@ -0,0 +1,61 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+# The url filter file used by the crawl command.
+
+# Better for intranet crawling.
+# Be sure to change MY.DOMAIN.NAME to your domain name.
+
+# Each non-comment, non-blank line contains a regular expression
+# prefixed by '+' or '-'. The first matching pattern in the file
+# determines whether a URL is included or ignored. If no pattern
+# matches, the URL is ignored.
+
+# skip file:, ftp:, & mailto: urls
+#-^(file|ftp|mailto):
+-^(http|ftp|mailto):
+
+# skip image and other suffixes we can't yet parse
+-\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP|pdf)$
+
+# skip URLs containing certain characters as probable queries, etc.
+-[?*!@=]
+
+# skip URLs with slash-delimited segment that repeats 3+ times, to break loops
+-.*(/[^/]+)/[^/]+\1/[^/]+\1/
+
+# accept hosts in MY.DOMAIN.NAME
+#+^http://([a-z0-9]*\.)*MY.DOMAIN.NAME/
+#+^http://([a-z0-9]*\.)*redhat.com/
+
+# skip everything else
+#-
+
+
+#accept everything else
+#+.*
+
+#ingore all svn entries
+-.*\.svn
+#only read in english docs from these locations
++.*/docs/guides/channel-mgmt/en/
++.*/docs/guides/client-config/en/
++.*/docs/guides/proxy/rhn511/en/
++.*/docs/release-notes/satellite/rhn510/en-US/
++.*/docs/guides/satellite/en/
++.*/docs/guides/reference/en/
+#skip everything else
+-.*
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xml
new file mode 100644
index 0000000..635f5a2
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xml
@@ -0,0 +1,4354 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ Document : domain-suffixes.xml
+ Author : Enis Soztutar - enis.soz.nutch(a)gmail.com
+ Description: This document contains top level domains
+ as described by the Internet Assigned Numbers
+ Authotiry (IANA), and second or third level domains that
+ are known to be managed by domain registerers. People at
+ Mozilla community call these public suffixes or effective
+ tlds. There is no algorithmic way of knowing whether a suffix
+ is a public domain suffix, or not. So this large file is used
+ for this purpose. The entries in the file is used to find the
+ domain of a url, which may not the same thing as the host of
+ the url. For example for "http://lucene.apache.org/nutch " the
+ hostname is lucene.apache.org , however the domain name for this
+ url would be apache.org . Domain names can be quite handy for
+ statistical analysis, and fighting against spam.
+
+ The list of TLDs is constructed from IANA, and the
+ list of "effective tlds" are constructed from Wikipedia,
+ http://wiki.mozilla.org/TLD_List , and http://publicsuffix.org/
+ The list may not include all the suffixes, but some
+ effort has been spent to make it comprehensive. Please forward
+ any improvements for this list to nutch-dev mailing list, or
+ nutch JIRA.
+
+ Top level domains(tlds) are grouped
+ to three, namely infrastrusture, generic and country
+ code tlds. Infrastrusture tlds are only used for
+ technical reasons. Generic tlds represents the type
+ of the organization that they represent. Those in
+ current use and those waiting for approval is listed.
+ Most of the country code tlds correspond to the two
+ letter ISO-3166-1 country codes.
+ Each tld is listed with its domain (such as com), a
+ status enumeration describing the status of the tld,
+ and optionally a description or description for convenience.
+ cctlds are listed with additional country name field.
+
+ status and boost elements are optional, with default values IN_USE
+ and 1.0 respectively. see domain-suffixes.xsd for the xml schema.
+
+
+ References :
+ http://www.iana.org
+ http://www.iana.org/gtld/gtld.htm
+ http://www.iana.org/root-whois/index.html
+ http://en.wikipedia.org/wiki/Top-level_domain
+ http://en.wikipedia.org/wiki/List_of_Internet_top-level_domains
+ http://wiki.mozilla.org/TLD_List
+ http://publicsuffix.org/
+ https://bugzilla.mozilla.org/show_bug.cgi?id=331510
+ http://www.neuhaus.com/domaincheck/domain_list.htm
+-->
+
+<domains xmlns="http://lucene.apache.org/nutch "
+ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance "
+ xsi:schemaLocation="http://lucene.apache.org/nutch domain-suffixes.xsd">
+
+ <tlds>
+ <!-- Infrastructure Top Level Domains -->
+ <itlds>
+ <tld domain="root">
+ <status>INFRASTRUCTURE</status>
+ <description>
+ (from http://en.wikipedia.org/wiki/.root )
+ vrsn-end-of-zone-marker-dummy-record.root is a domain name
+ listed in the DNS root zone as a diagnostic marker, whose
+ presence demonstrates the root zone was not truncated upon
+ loading by a root nameserver. It could be argued it represents
+ a top-level domain of .root, although technically no such
+ delegation exists.
+ </description>
+ </tld>
+
+ <tld domain="arpa">
+ <status>INFRASTRUCTURE</status>
+ <description>
+ (from http://en.wikipedia.org/wiki/.arpa ) .arpa is an Internet
+ top-level domain (TLD) used exclusively for
+ Internet-infrastructure purposes. It does not function as a
+ normal TLD where websites are registered, but rather as a
+ meta-TLD used to look up addresses, and for other purposes.
+ </description>
+ </tld>
+ </itlds><!-- Generic Top Level Domains -->
+ <gtlds>
+ <!--
+ The following gTLDs are in actual use
+ -->
+
+ <tld domain="aero">
+ <status>SPONSORED</status>
+ <description>for the air transport industry</description>
+ </tld>
+
+ <tld domain="biz">
+ <status>UNSPONSORED</status>
+ <description>for business use</description>
+ </tld>
+
+ <tld domain="cat">
+ <status>SPONSORED</status>
+ <description>for Catalan language/culture</description>
+ </tld>
+
+ <tld domain="com">
+ <status>UNSPONSORED</status>
+ <description>
+ for commercial organizations, but unrestricted
+ </description>
+ </tld>
+
+ <tld domain="coop">
+ <status>SPONSORED</status>
+ <description>for cooperatives</description>
+ </tld>
+
+ <tld domain="edu">
+ <status>UNSPONSORED</status>
+ <boost>1.0</boost>
+ <description>
+ for post-secondary educational establishments
+ </description>
+ </tld>
+
+ <tld domain="gov">
+ <status>UNSPONSORED</status>
+ <description>
+ for governments and their agencies in the United States
+ </description>
+ </tld>
+
+ <tld domain="info">
+ <status>UNSPONSORED</status>
+ <description>
+ for informational sites, but unrestricted
+ </description>
+ </tld>
+
+ <tld domain="int">
+ <status>UNSPONSORED</status>
+ <description>
+ for international organizations established by treaty
+ </description>
+ </tld>
+
+ <tld domain="jobs">
+ <status>SPONSORED</status>
+ <description>for employment-related sites</description>
+ </tld>
+
+ <tld domain="mil">
+ <status>UNSPONSORED</status>
+ <description>for the US military</description>
+ </tld>
+
+ <tld domain="mobi">
+ <status>SPONSORED</status>
+ <description>for sites catering to mobile devices</description>
+ </tld>
+
+ <tld domain="museum">
+ <status>SPONSORED</status>
+ <description>for museums</description>
+ </tld>
+
+ <tld domain="name">
+ <status>UNSPONSORED</status>
+ <description>for families and individuals</description>
+ </tld>
+
+ <tld domain="net">
+ <status>UNSPONSORED</status>
+ <description>
+ originally for network infrastructures, now unrestricted
+ </description>
+ </tld>
+
+ <tld domain="org">
+ <status>UNSPONSORED</status>
+ <description>
+ originally for organizations not clearly falling within the
+ other gTLDs, now unrestricted
+ </description>
+ </tld>
+
+ <tld domain="pro">
+ <status>SPONSORED</status>
+ <description>for certain professions</description>
+ </tld>
+
+ <tld domain="travel">
+ <status>SPONSORED</status>
+ <description>
+ for travel agents, airlines, hoteliers, tourism bureaus, etc.
+ </description>
+ </tld>
+
+ <!--
+ The following gTLDs are in the process of being approved,
+ and may be added to the root nameservers in the near future
+ -->
+
+ <tld domain="asia">
+ <status>STARTUP</status>
+ <description>for the Asian community</description>
+ </tld>
+
+ <tld domain="post">
+ <status>PROPOSED</status>
+ <description>for postal services</description>
+ </tld>
+
+ <tld domain="tel">
+ <status>STARTUP</status>
+ <description>
+ for services involving connections between the telephone
+ network and the Internet
+ </description>
+ </tld>
+
+ <tld domain="geo">
+ <status>PROPOSED</status>
+ <description>for geographically related sites</description>
+ </tld>
+
+ <tld domain="gal">
+ <status>PROPOSED</status>
+ <description>for Galicia, a country within Spain</description>
+ </tld>
+
+ <tld domain="cym">
+ <status>PROPOSED</status>
+ <description>for Wales, a country within the UK</description>
+ </tld>
+
+ <tld domain="sco">
+ <status>PROPOSED</status>
+ <description>for Scotland, a country within the UK</description>
+ </tld>
+
+ <tld domain="kid">
+ <status>PROPOSED</status>
+ <description>for websites designed for children</description>
+ </tld>
+
+ <tld domain="kids">
+ <status>PROPOSED</status>
+ <description>for websites designed for children</description>
+ </tld>
+
+ <tld domain="mail">
+ <status>PROPOSED</status>
+ <description>http://en.wikipedia.org/wiki/.mail </description>
+ </tld>
+
+ <tld domain="web">
+ <status>PROPOSED</status>
+ <description>For Web sites of all sorts</description>
+ </tld>
+
+ <tld domain="xxx">
+ <status>PROPOSED</status>
+ <description>For Adult entertainment sites</description>
+ </tld>
+
+ <!--
+ The following gTLDs are removed from the registry
+ -->
+ <tld domain="nato">
+ <status>DELETED</status>
+ <description>
+ for NATO sites and operations. Replaced by .int
+ </description>
+ </tld>
+
+ <!--
+ The following gTLDs are PSEUDO_DOMAINs
+ -->
+ <tld domain="bitnet">
+ <status>PSEUDO_DOMAIN</status>
+ <description>
+ identifying a hostname not connected directly to the Internet,
+ but a bitnet network
+ </description>
+ </tld>
+
+ <tld domain="csnet">
+ <status>PSEUDO_DOMAIN</status>
+ <description>
+ identifying a hostname not connected directly to the Internet,
+ but a csnet network
+ </description>
+ </tld>
+
+ <tld domain="uucp">
+ <status>PSEUDO_DOMAIN</status>
+ <description>
+ identifying a hostname not connected directly to the Internet,
+ but a bitnet network
+ </description>
+ </tld>
+
+ <tld domain="local">
+ <status>PSEUDO_DOMAIN</status>
+ <description>
+ .local is a pseudo top-level domain used by Apple, Inc.'s
+ Bonjour protocol.
+ </description>
+ </tld>
+
+ <tld domain="internal">
+ <status>PSEUDO_DOMAIN</status>
+ <description>alias of .local</description>
+ </tld>
+
+ <tld domain="onion">
+ <status>PSEUDO_DOMAIN</status>
+ <description>
+ designates an anonymous or pseudonymous address reachable via
+ the Tor network.
+ </description>
+ </tld>
+ </gtlds><!-- Country Code Top Level Domains -->
+
+ <cctlds>
+ <tld domain="ac">
+ <country>Ascension Island</country>
+ </tld>
+
+ <tld domain="ad">
+ <country>Andorra</country>
+ </tld>
+
+ <tld domain="ae">
+ <country>United Arab Emirates</country>
+ </tld>
+
+ <tld domain="af">
+ <country>Afghanistan</country>
+ </tld>
+
+ <tld domain="ag">
+ <country>Antigua and Barbuda</country>
+ </tld>
+
+ <tld domain="ai">
+ <country>Anguilla</country>
+ </tld>
+
+ <tld domain="al">
+ <country>Albania</country>
+ </tld>
+
+ <tld domain="am">
+ <country>Armenia</country>
+ </tld>
+
+ <tld domain="an">
+ <country>Netherlands Antilles</country>
+ </tld>
+
+ <tld domain="ao">
+ <country>Angola</country>
+ </tld>
+
+ <tld domain="aq">
+ <country>Antarctica</country>
+ </tld>
+
+ <tld domain="ar">
+ <country>Argentina</country>
+ </tld>
+
+ <tld domain="as">
+ <country>American Samoa</country>
+ </tld>
+
+ <tld domain="at">
+ <country>Austria</country>
+ </tld>
+
+ <tld domain="au">
+ <country>Australia</country>
+ </tld>
+
+ <tld domain="aw">
+ <country>Aruba</country>
+ </tld>
+
+ <tld domain="ax">
+ <country>Aland Islands</country>
+ </tld>
+
+ <tld domain="az">
+ <country>Azerbaijan</country>
+ </tld>
+
+ <tld domain="ba">
+ <country>Bosnia and Herzegovina</country>
+ </tld>
+
+ <tld domain="bb">
+ <country>Barbados</country>
+ </tld>
+
+ <tld domain="bd">
+ <country>Bangladesh</country>
+ </tld>
+
+ <tld domain="be">
+ <country>Belgium</country>
+ </tld>
+
+ <tld domain="bf">
+ <country>Burkina Faso</country>
+ </tld>
+
+ <tld domain="bg">
+ <country>Bulgaria</country>
+ </tld>
+
+ <tld domain="bh">
+ <country>Bahrain</country>
+ </tld>
+
+ <tld domain="bi">
+ <country>Burundi</country>
+ </tld>
+
+ <tld domain="bj">
+ <country>Benin</country>
+ </tld>
+
+ <tld domain="bm">
+ <country>Bermuda</country>
+ </tld>
+
+ <tld domain="bn">
+ <country>Brunei</country>
+ </tld>
+
+ <tld domain="bo">
+ <country>Bolivia</country>
+ </tld>
+
+ <tld domain="br">
+ <country>Brazil</country>
+ </tld>
+
+ <tld domain="bs">
+ <country>Bahamas</country>
+ </tld>
+
+ <tld domain="bt">
+ <country>Bhutan</country>
+ </tld>
+
+ <tld domain="bu">
+ <country>Burma</country>
+ <status>NOT_IN_USE</status>
+ <description>
+ not in use since re-naming of country to Myanmar, see .mm
+ </description>
+ </tld>
+
+ <tld domain="bv">
+ <country>Bouvet Island</country>
+ <status>NOT_IN_USE</status>
+ <description>not in use; no registrations</description>
+ </tld>
+
+ <tld domain="bw">
+ <country>Botswana</country>
+ </tld>
+
+ <tld domain="by">
+ <country>Belarus</country>
+ </tld>
+
+ <tld domain="bz">
+ <country>Belize</country>
+ </tld>
+
+ <tld domain="ca">
+ <country>Canada</country>
+ </tld>
+
+ <tld domain="cc">
+ <country>Cocos Keeling Islands</country>
+ </tld>
+
+ <tld domain="cd">
+ <country>Democratic Republic of the Congo</country>
+ <description>formerly .zr - Zaire</description>
+ </tld>
+
+ <tld domain="cf">
+ <country>Central African Republic</country>
+ </tld>
+
+ <tld domain="cg">
+ <country>Republic of the Congo</country>
+ </tld>
+
+ <tld domain="ch">
+ <country>Switzerland</country>
+ </tld>
+
+ <tld domain="ci">
+ <country>CÃŽte d'Ivoire</country>
+ <description>Ivory Coast</description>
+ </tld>
+
+ <tld domain="ck">
+ <country>Cook Islands</country>
+ </tld>
+
+ <tld domain="cl">
+ <country>Chile</country>
+ </tld>
+
+ <tld domain="cm">
+ <country>Cameroon</country>
+ </tld>
+
+ <tld domain="cn">
+ <country>People s Republic of China</country>
+ </tld>
+
+ <tld domain="co">
+ <country>Colombia</country>
+ </tld>
+
+ <tld domain="cr">
+ <country>Costa Rica</country>
+ </tld>
+
+ <tld domain="cs">
+ <country>Serbia and Montenegro</country>
+ <status>DELETED</status>
+ <description>
+ formerly .yu - Yugoslavia; description: on June 3, 2006,
+ Montenegro declared independence, thus dissolving the state
+ union) (.cs code not assigned; no DNS) (.cs code previously
+ used for Czechoslovakia
+ </description>
+ </tld>
+
+ <tld domain="cu">
+ <country>Cuba</country>
+ </tld>
+
+ <tld domain="cv">
+ <country>Cape Verde</country>
+ </tld>
+
+ <tld domain="cx">
+ <country>Christmas Island</country>
+ </tld>
+
+ <tld domain="cy">
+ <country>Cyprus</country>
+ </tld>
+
+ <tld domain="cz">
+ <country>Czech Republic</country>
+ </tld>
+
+ <tld domain="dd">
+ <country>German Democratic Republic(East Germany)</country>
+ <status>DELETED</status>
+ <description>deleted in 1990</description>
+ </tld>
+
+ <tld domain="de">
+ <country>Germany</country>
+ </tld>
+
+ <tld domain="dj">
+ <country>Djibouti</country>
+ </tld>
+
+ <tld domain="dk">
+ <country>Denmark</country>
+ </tld>
+
+ <tld domain="dm">
+ <country>Dominica</country>
+ </tld>
+
+ <tld domain="do">
+ <country>Dominican Republic</country>
+ </tld>
+
+ <tld domain="dz">
+ <country>Algeria</country>
+ </tld>
+
+ <tld domain="ec">
+ <country>Ecuador</country>
+ </tld>
+
+ <tld domain="ee">
+ <country>Estonia</country>
+ </tld>
+
+ <tld domain="eg">
+ <country>Egypt</country>
+ </tld>
+
+ <tld domain="eh">
+ <country>Western Sahara</country>
+ <status>NOT_IN_USE</status>
+ <description>not assigned; no DNS</description>
+ </tld>
+
+ <tld domain="er">
+ <country>Eritrea</country>
+ </tld>
+
+ <tld domain="es">
+ <country>Spain</country>
+ </tld>
+
+ <tld domain="et">
+ <country>Ethiopia</country>
+ </tld>
+
+ <tld domain="eu">
+ <country>European Union</country>
+ <description>
+ code "exceptionally reserved" by ISO 3166-1
+ </description>
+ </tld>
+
+ <tld domain="fi">
+ <country>Finland</country>
+ </tld>
+
+ <tld domain="fj">
+ <country>Fiji</country>
+ </tld>
+
+ <tld domain="fk">
+ <country>Falkland Islands</country>
+ </tld>
+
+ <tld domain="fm">
+ <country>Federated States of Micronesia</country>
+ </tld>
+
+ <tld domain="fo">
+ <country>Faroe Islands</country>
+ </tld>
+
+ <tld domain="fr">
+ <country>France</country>
+ </tld>
+
+ <tld domain="ga">
+ <country>Gabon</country>
+ </tld>
+
+ <tld domain="gb">
+ <country>United Kingdom</country>
+ <description>
+ Reserved domain by IANA; deprecated – see .uk
+ </description>
+ </tld>
+
+ <tld domain="gd">
+ <country>Grenada</country>
+ </tld>
+
+ <tld domain="ge">
+ <country>Georgia</country>
+ </tld>
+
+ <tld domain="gf">
+ <country>French Guiana</country>
+ </tld>
+
+ <tld domain="gg">
+ <country>Guernsey</country>
+ </tld>
+
+ <tld domain="gh">
+ <country>Ghana</country>
+ </tld>
+
+ <tld domain="gi">
+ <country>Gibraltar</country>
+ </tld>
+
+ <tld domain="gl">
+ <country>Greenland</country>
+ </tld>
+
+ <tld domain="gm">
+ <country>Gambia</country>
+ </tld>
+
+ <tld domain="gn">
+ <country>Guinea</country>
+ </tld>
+
+ <tld domain="gp">
+ <country>Guadeloupe</country>
+ </tld>
+
+ <tld domain="gq">
+ <country>Equatorial Guinea</country>
+ </tld>
+
+ <tld domain="gr">
+ <country>Greece</country>
+ </tld>
+
+ <tld domain="gs">
+ <country>South Georgia and the South Sandwich Islands</country>
+ </tld>
+
+ <tld domain="gt">
+ <country>Guatemala</country>
+ </tld>
+
+ <tld domain="gu">
+ <country>Guam</country>
+ </tld>
+
+ <tld domain="gw">
+ <country>Guinea Bissau</country>
+ </tld>
+
+ <tld domain="gy">
+ <country>Guyana</country>
+ </tld>
+
+ <tld domain="hk">
+ <country>Hong Kong</country>
+ </tld>
+
+ <tld domain="hm">
+ <country>Heard Island and McDonald Islands</country>
+ </tld>
+
+ <tld domain="hn">
+ <country>Honduras</country>
+ </tld>
+
+ <tld domain="hr">
+ <country>Croatia</country>
+ </tld>
+
+ <tld domain="ht">
+ <country>Haiti</country>
+ </tld>
+
+ <tld domain="hu">
+ <country>Hungary</country>
+ </tld>
+
+ <tld domain="id">
+ <country>Indonesia</country>
+ </tld>
+
+ <tld domain="ie">
+ <country>Ireland</country>
+ </tld>
+
+ <tld domain="il">
+ <country>Israel</country>
+ </tld>
+
+ <tld domain="im">
+ <country>Isle of Man</country>
+ </tld>
+
+ <tld domain="in">
+ <country>India</country>
+ </tld>
+
+ <tld domain="io">
+ <country>British Indian Ocean Territory</country>
+ </tld>
+
+ <tld domain="iq">
+ <country>Iraq</country>
+ </tld>
+
+ <tld domain="ir">
+ <country>Iran</country>
+ </tld>
+
+ <tld domain="is">
+ <country>Iceland</country>
+ </tld>
+
+ <tld domain="it">
+ <country>Italy</country>
+ </tld>
+
+ <tld domain="je">
+ <country>Jersey</country>
+ </tld>
+
+ <tld domain="jm">
+ <country>Jamaica</country>
+ </tld>
+
+ <tld domain="jo">
+ <country>Jordan</country>
+ </tld>
+
+ <tld domain="jp">
+ <country>Japan</country>
+ </tld>
+
+ <tld domain="ke">
+ <country>Kenya</country>
+ </tld>
+
+ <tld domain="kg">
+ <country>Kyrgyzstan</country>
+ </tld>
+
+ <tld domain="kh">
+ <country>Cambodia</country>
+ </tld>
+
+ <tld domain="ki">
+ <country>Kiribati</country>
+ </tld>
+
+ <tld domain="km">
+ <country>Comoros</country>
+ </tld>
+
+ <tld domain="kn">
+ <country>Saint Kitts and Nevis</country>
+ </tld>
+
+ <tld domain="kp">
+ <country>North Korea</country>
+ <status>NOT_IN_USE</status>
+
+ <description>not assigned; no DNS</description>
+ </tld>
+
+ <tld domain="kr">
+ <country>South Korea</country>
+ </tld>
+
+ <tld domain="kw">
+ <country>Kuwait</country>
+ </tld>
+
+ <tld domain="ky">
+ <country>Cayman Islands</country>
+ </tld>
+
+ <tld domain="kz">
+ <country>Kazakhstan</country>
+ </tld>
+
+ <tld domain="la">
+ <country>Laos</country>
+ </tld>
+
+ <tld domain="lb">
+ <country>Lebanon</country>
+ </tld>
+
+ <tld domain="lc">
+ <country>Saint Lucia</country>
+ </tld>
+
+ <tld domain="li">
+ <country>Liechtenstein</country>
+ </tld>
+
+ <tld domain="lk">
+ <country>Sri Lanka</country>
+ </tld>
+
+ <tld domain="lr">
+ <country>Liberia</country>
+ </tld>
+
+ <tld domain="ls">
+ <country>Lesotho</country>
+ </tld>
+
+ <tld domain="lt">
+ <country>Lithuania</country>
+ </tld>
+
+ <tld domain="lu">
+ <country>Luxembourg</country>
+ </tld>
+
+ <tld domain="lv">
+ <country>Latvia</country>
+ </tld>
+
+ <tld domain="ly">
+ <country>Libya</country>
+ </tld>
+
+ <tld domain="ma">
+ <country>Morocco</country>
+ </tld>
+
+ <tld domain="mc">
+ <country>Monaco</country>
+ </tld>
+
+ <tld domain="md">
+ <country>Moldova</country>
+ </tld>
+
+ <tld domain="me">
+ <country>Montenegro</country>
+ </tld>
+
+ <tld domain="mg">
+ <country>Madagascar</country>
+ </tld>
+
+ <tld domain="mh">
+ <country>Marshall Islands</country>
+ </tld>
+
+ <tld domain="mk">
+ <country>Republic of Macedonia</country>
+ </tld>
+
+ <tld domain="ml">
+ <country>Mali</country>
+ </tld>
+
+ <tld domain="mm">
+ <country>Myanmar</country>
+ <description>formerly .bu - Burma</description>
+ </tld>
+
+ <tld domain="mn">
+ <country>Mongolia</country>
+ </tld>
+
+ <tld domain="mo">
+ <country>Macau</country>
+ </tld>
+
+ <tld domain="mp">
+ <country>Northern Mariana Islands</country>
+ </tld>
+
+ <tld domain="mq">
+ <country>Martinique</country>
+ </tld>
+
+ <tld domain="mr">
+ <country>Mauritania</country>
+ </tld>
+
+ <tld domain="ms">
+ <country>Montserrat</country>
+ </tld>
+
+ <tld domain="mt">
+ <country>Malta</country>
+ </tld>
+
+ <tld domain="mu">
+ <country>Mauritius</country>
+ </tld>
+
+ <tld domain="mv">
+ <country>Maldives</country>
+ </tld>
+
+ <tld domain="mw">
+ <country>Malawi</country>
+ </tld>
+
+ <tld domain="mx">
+ <country>Mexico</country>
+ </tld>
+
+ <tld domain="my">
+ <country>Malaysia</country>
+ </tld>
+
+ <tld domain="mz">
+ <country>Mozambique</country>
+ </tld>
+
+ <tld domain="na">
+ <country>Namibia</country>
+ </tld>
+
+ <tld domain="nc">
+ <country>New Caledonia</country>
+ </tld>
+
+ <tld domain="ne">
+ <country>Niger</country>
+ </tld>
+
+ <tld domain="nf">
+ <country>Norfolk Island</country>
+ </tld>
+
+ <tld domain="ng">
+ <country>Nigeria</country>
+ </tld>
+
+ <tld domain="ni">
+ <country>Nicaragua</country>
+ </tld>
+
+ <tld domain="nl">
+ <country>Netherlands</country>
+ </tld>
+
+ <tld domain="no">
+ <country>Norway</country>
+ </tld>
+
+ <tld domain="np">
+ <country>Nepal</country>
+ </tld>
+
+ <tld domain="nr">
+ <country>Nauru</country>
+ </tld>
+
+ <tld domain="nu">
+ <country>Niue</country>
+ </tld>
+
+ <tld domain="nz">
+ <country>New Zealand</country>
+ </tld>
+
+ <tld domain="om">
+ <country>Oman</country>
+ </tld>
+
+ <tld domain="pa">
+ <country>Panama</country>
+ </tld>
+
+ <tld domain="pe">
+ <country>Peru</country>
+ </tld>
+
+ <tld domain="pf">
+ <country>French Polynesia</country>
+ </tld>
+
+ <tld domain="pg">
+ <country>Papua New Guinea</country>
+ </tld>
+
+ <tld domain="ph">
+ <country>Philippines</country>
+ </tld>
+
+ <tld domain="pk">
+ <country>Pakistan</country>
+ </tld>
+
+ <tld domain="pl">
+ <country>Poland</country>
+ </tld>
+
+ <tld domain="pm">
+ <country>Saint Pierre and Miquelon</country>
+ </tld>
+
+ <tld domain="pn">
+ <country>Pitcairn Islands</country>
+ </tld>
+
+ <tld domain="pr">
+ <country>Puerto Rico</country>
+ </tld>
+
+ <tld domain="ps">
+ <country>Palestinian territories</country>
+ </tld>
+
+ <tld domain="pt">
+ <country>Portugal</country>
+ </tld>
+
+ <tld domain="pw">
+ <country>Palau</country>
+ </tld>
+
+ <tld domain="py">
+ <country>Paraguay</country>
+ </tld>
+
+ <tld domain="qa">
+ <country>Qatar</country>
+ </tld>
+
+ <tld domain="re">
+ <country>Réunion</country>
+ </tld>
+
+ <tld domain="ro">
+ <country>Romania</country>
+ </tld>
+
+ <tld domain="rs">
+ <country>Serbia</country>
+ </tld>
+
+ <tld domain="ru">
+ <country>Russia</country>
+ </tld>
+
+ <tld domain="rw">
+ <country>Rwanda</country>
+ </tld>
+
+ <tld domain="sa">
+ <country>Saudi Arabia</country>
+ </tld>
+
+ <tld domain="sb">
+ <country>Solomon Islands</country>
+ </tld>
+
+ <tld domain="sc">
+ <country>Seychelles</country>
+ </tld>
+
+ <tld domain="sd">
+ <country>Sudan</country>
+ </tld>
+
+ <tld domain="se">
+ <country>Sweden</country>
+ </tld>
+
+ <tld domain="sg">
+ <country>Singapore</country>
+ </tld>
+
+ <tld domain="sh">
+ <country>Saint Helena</country>
+ </tld>
+
+ <tld domain="si">
+ <country>Slovenia</country>
+ </tld>
+
+ <tld domain="sj">
+ <country>Svalbard and Jan Mayen Islands</country>
+ <status>NOT_IN_USE</status>
+ <description>not in use; no registrations</description>
+ </tld>
+
+ <tld domain="sk">
+ <country>Slovakia</country>
+ </tld>
+
+ <tld domain="sl">
+ <country>Sierra Leone</country>
+ </tld>
+
+ <tld domain="sm">
+ <country>San Marino</country>
+ </tld>
+
+ <tld domain="sn">
+ <country>Senegal</country>
+ </tld>
+
+ <tld domain="so">
+ <country>Somalia</country>
+ </tld>
+
+ <tld domain="sr">
+ <country>Suriname</country>
+ </tld>
+
+ <tld domain="st">
+ <country>São Tomé and PrÃÂncipe</country>
+ </tld>
+
+ <tld domain="su">
+ <country>Soviet Union</country>
+ <status>DELETED</status>
+ <description>
+ deprecated; being phased out; code "transitionally reserved"
+ by ISO 3166-1
+ </description>
+ </tld>
+
+ <tld domain="sv">
+ <country>El Salvador</country>
+ </tld>
+
+ <tld domain="sy">
+ <country>Syria</country>
+ </tld>
+
+ <tld domain="sz">
+ <country>Swaziland</country>
+ </tld>
+
+ <tld domain="tc">
+ <country>Turks and Caicos Islands</country>
+ </tld>
+
+ <tld domain="td">
+ <country>Chad</country>
+ </tld>
+
+ <tld domain="tf">
+ <country>French Southern Territories</country>
+ </tld>
+
+ <tld domain="tg">
+ <country>Togo</country>
+ </tld>
+
+ <tld domain="th">
+ <country>Thailand</country>
+ </tld>
+
+ <tld domain="tj">
+ <country>Tajikistan</country>
+ </tld>
+
+ <tld domain="tk">
+ <country>Tokelau</country>
+ </tld>
+
+ <tld domain="tl">
+ <country>East Timor</country>
+ <description>formerly .tp</description>
+ </tld>
+
+ <tld domain="tm">
+ <country>Turkmenistan</country>
+ </tld>
+
+ <tld domain="tn">
+ <country>Tunisia</country>
+ </tld>
+
+ <tld domain="to">
+ <country>Tonga</country>
+ </tld>
+
+ <tld domain="tp">
+ <country>East Timor</country>
+ <status>DELETED</status>
+ <description>
+ deprecated - use .tl; code "transitionally reserved" by ISO
+ 3166-1
+ </description>
+ </tld>
+
+ <tld domain="tr">
+ <country>Turkey</country>
+ </tld>
+
+ <tld domain="tt">
+ <country>Trinidad and Tobago</country>
+ </tld>
+
+ <tld domain="tv">
+ <country>Tuvalu</country>
+ </tld>
+
+ <tld domain="tw">
+ <country>Republic of China</country>
+ <description>Taiwan</description>
+ </tld>
+
+ <tld domain="tz">
+ <country>Tanzania</country>
+ </tld>
+
+ <tld domain="ua">
+ <country>Ukraine</country>
+ </tld>
+
+ <tld domain="ug">
+ <country>Uganda</country>
+ </tld>
+
+ <tld domain="uk">
+ <country>United Kingdom</country>
+ <description>
+ code "exceptionally reserved" by ISO 3166-1 (see also .gb)
+ </description>
+ </tld>
+
+ <tld domain="um">
+ <country>United States Minor Outlying Islands</country>
+ <status>DELETED</status>
+ <description>see http://en.wikipedia.org/wiki/.um </description>
+ </tld>
+
+ <tld domain="us">
+ <country>United States</country>
+ </tld>
+
+ <tld domain="uy">
+ <country>Uruguay</country>
+ </tld>
+
+ <tld domain="uz">
+ <country>Uzbekistan</country>
+ </tld>
+
+ <tld domain="va">
+ <country>Vatican City</country>
+ </tld>
+
+ <tld domain="vc">
+ <country>Saint Vincent and the Grenadines</country>
+ </tld>
+
+ <tld domain="ve">
+ <country>Venezuela</country>
+ </tld>
+
+ <tld domain="vg">
+ <country>British Virgin Islands</country>
+ </tld>
+
+ <tld domain="vi">
+ <country>United States Virgin Islands</country>
+ </tld>
+
+ <tld domain="vn">
+ <country>Vietnam</country>
+ </tld>
+
+ <tld domain="vu">
+ <country>Vanuatu</country>
+ </tld>
+
+ <tld domain="wf">
+ <country>Wallis and Futuna</country>
+ </tld>
+
+ <tld domain="ws">
+ <country>Samoa</country>
+ <description>formerly Western Samoa</description>
+ </tld>
+
+ <tld domain="ye">
+ <country>Yemen</country>
+ </tld>
+
+ <tld domain="yt">
+ <country>Mayotte</country>
+ </tld>
+
+ <tld domain="yu">
+ <country>Yugoslavia</country>
+ <description>
+ subsequently renamed Serbia and Montenegro (code officially
+ replaced by .cs (see above) but still used; code
+ "transitionally reserved" by ISO 3166-1)
+ </description>
+ </tld>
+
+ <tld domain="za">
+ <country>South Africa</country>
+ </tld>
+
+ <tld domain="zm">
+ <country>Zambia</country>
+ </tld>
+
+ <tld domain="zr">
+ <country>Zaire</country>
+ <status>DELETED</status>
+ <description>replaced by .cd</description>
+ </tld>
+
+ <tld domain="zw">
+ <country>Zimbabwe</country>
+ </tld>
+ </cctlds>
+ </tlds>
+
+ <!-- Second Level Domains -->
+ <suffixes>
+
+ <!-- .us Second Level Domains -->
+ <suffix domain="as.us" />
+ <suffix domain="gu.us" />
+ <suffix domain="pr.us" />
+ <suffix domain="vi.us" />
+
+ <!-- .uk Second Level Domains -->
+ <suffix domain="ac.uk" />
+ <suffix domain="co.uk" />
+ <suffix domain="gov.uk" />
+ <suffix domain="ltd.uk" />
+ <suffix domain="me.uk" />
+ <suffix domain="mod.uk" />
+ <suffix domain="net.uk" />
+ <suffix domain="nic.uk" />
+ <suffix domain="nhs.uk" />
+ <suffix domain="org.uk" />
+ <suffix domain="pic.uk" />
+ <suffix domain="police.uk" />
+ <suffix domain="govt.uk">
+ <status>DELETED</status>
+ </suffix>
+ <suffix domain="orgn.uk">
+ <status>DELETED</status>
+ </suffix>
+ <suffix domain="mil.uk">
+ <status>DELETED</status>
+ </suffix>
+ <suffix domain="lea.uk">
+ <status>DELETED</status>
+ </suffix>
+
+
+ <!-- .tr Second Level Domains -->
+ <suffix domain="com.tr" />
+ <suffix domain="gen.tr" />
+ <suffix domain="org.tr"/>
+ <suffix domain="biz.tr" />
+ <suffix domain="info.tr" />
+ <suffix domain="av.tr" />
+ <suffix domain="dr.tr" />
+ <suffix domain="pol.tr" />
+ <suffix domain="bel.tr" />
+ <suffix domain="mil.tr" />
+ <suffix domain="mil.tr" />
+ <suffix domain="bbs.tr" />
+ <suffix domain="k12.tr" />
+ <suffix domain="edu.tr"/>
+ <suffix domain="name.tr" />
+ <suffix domain="net.tr" />
+ <suffix domain="gov.tr" />
+ <suffix domain="gov.tr" />
+ <suffix domain="web.tr" />
+ <suffix domain="tel.tr" />
+ <suffix domain="tv.tr" />
+
+ <!-- .hk Second Level Domains -->
+ <suffix domain="ust.hk" />
+ <suffix domain="hku.hk" />
+ <suffix domain="cuhk.hk" />
+
+ <!-- .it Second Level Domains -->
+
+ <suffix domain="edu.it" />
+ <suffix domain="gov.it" />
+ <suffix domain="italy.it" />
+
+ <!-- .az Second Level Domains -->
+ <suffix domain="pro.az" />
+
+ <!-- .au Second Level Domains -->
+
+ <suffix domain="com.au" />
+ <suffix domain="net.au" />
+ <suffix domain="gov.au" />
+ <suffix domain="org.au" />
+ <suffix domain="edu.au" />
+ <suffix domain="csiro.au" />
+ <suffix domain="asn.au" />
+ <suffix domain="id.au" />
+ <!-- New second level domains -->
+ <suffix domain="act.au" />
+ <suffix domain="nsw.au" />
+ <suffix domain="nt.au" />
+ <suffix domain="qld.au" />
+ <suffix domain="sa.au" />
+ <suffix domain="tas.au" />
+ <suffix domain="vic.au" />
+ <suffix domain="wa.au" />
+
+ <!-- .int Second Level Domains -->
+ <suffix domain="eu.int " />
+
+ <!-- .br Second Level Domains -->
+ <suffix domain="adm.br" />
+ <suffix domain="adv.br" />
+ <suffix domain="agr.br" />
+ <suffix domain="am.br" />
+ <suffix domain="arq.br" />
+ <suffix domain="art.br" />
+ <suffix domain="ato.br" />
+ <suffix domain="bio.br" />
+ <suffix domain="blog.br" />
+ <suffix domain="bmd.br" />
+ <suffix domain="cim.br" />
+ <suffix domain="cng.br" />
+ <suffix domain="cnt.br" />
+ <suffix domain="com.br" />
+ <suffix domain="coop.br" />
+ <suffix domain="ecn.br" />
+ <suffix domain="edu.br" />
+ <suffix domain="eng.br" />
+ <suffix domain="esp.br" />
+ <suffix domain="etc.br" />
+ <suffix domain="eti.br" />
+ <suffix domain="far.br" />
+ <suffix domain="flog.br" />
+ <suffix domain="fm.br" />
+ <suffix domain="fnd.br" />
+ <suffix domain="fot.br" />
+ <suffix domain="fst.br" />
+ <suffix domain="g12.br" />
+ <suffix domain="ggf.br" />
+ <suffix domain="gov.br" />
+ <suffix domain="imb.br" />
+ <suffix domain="ind.br" />
+ <suffix domain="inf.br" />
+ <suffix domain="jor.br" />
+ <suffix domain="lel.br" />
+ <suffix domain="mat.br" />
+ <suffix domain="med.br" />
+ <suffix domain="mil.br" />
+ <suffix domain="mus.br" />
+ <suffix domain="net.br" />
+ <suffix domain="nom.br" />
+ <suffix domain="not.br" />
+ <suffix domain="ntr.br" />
+ <suffix domain="odo.br" />
+ <suffix domain="org.br" />
+ <suffix domain="ppg.br" />
+ <suffix domain="pro.br" />
+ <suffix domain="psc.br" />
+ <suffix domain="psi.br" />
+ <suffix domain="qsl.br" />
+ <suffix domain="rec.br" />
+ <suffix domain="slg.br" />
+ <suffix domain="srv.br" />
+ <suffix domain="tmp.br" />
+ <suffix domain="trd.br" />
+ <suffix domain="tur.br" />
+ <suffix domain="tv.br" />
+ <suffix domain="vet.br" />
+ <suffix domain="vlog.br" />
+ <suffix domain="wiki.br" />
+ <suffix domain="zlg.br" />
+
+ <!--
+ Below elements are generated from the file
+ at http://publicsuffix.org/ .
+ see org.apache.nutch.util.domain.MozillaPublicSuffixListParser.java
+ -->
+
+ <!-- ac : http://en.wikipedia.org/wiki/.am-- >
+ <suffix domain="com.ac" />
+ <suffix domain="edu.ac" />
+ <suffix domain="gov.ac" />
+ <suffix domain="net.ac" />
+ <suffix domain="mil.ac" />
+ <suffix domain="org.ac" />
+
+ <!-- ad : http://en.wikipedia.org/wiki/.ad-- >
+ <suffix domain="nom.ad" />
+
+ <!-- ae : http://en.wikipedia.org/wiki/.ae-- >
+ <suffix domain="net.ae" />
+ <suffix domain="gov.ae" />
+ <suffix domain="ac.ae" />
+ <suffix domain="sch.ae" />
+ <suffix domain="org.ae" />
+ <suffix domain="mil.ae" />
+ <suffix domain="pro.ae" />
+ <suffix domain="name.ae" />
+
+ <!-- aero : see http://www.information.aero/index.php?id=66-- >
+ <suffix domain="accident-investigation.aero" />
+ <suffix domain="accident-prevention.aero" />
+ <suffix domain="aerobatic.aero" />
+ <suffix domain="aeroclub.aero" />
+ <suffix domain="aerodrome.aero" />
+ <suffix domain="agents.aero" />
+ <suffix domain="aircraft.aero" />
+ <suffix domain="airline.aero" />
+ <suffix domain="airport.aero" />
+ <suffix domain="air-surveillance.aero" />
+ <suffix domain="airtraffic.aero" />
+ <suffix domain="air-traffic-control.aero" />
+ <suffix domain="ambulance.aero" />
+ <suffix domain="amusement.aero" />
+ <suffix domain="association.aero" />
+ <suffix domain="author.aero" />
+ <suffix domain="ballooning.aero" />
+ <suffix domain="broker.aero" />
+ <suffix domain="caa.aero" />
+ <suffix domain="cargo.aero" />
+ <suffix domain="catering.aero" />
+ <suffix domain="certification.aero" />
+ <suffix domain="championship.aero" />
+ <suffix domain="charter.aero" />
+ <suffix domain="civilaviation.aero" />
+ <suffix domain="club.aero" />
+ <suffix domain="conference.aero" />
+ <suffix domain="consultant.aero" />
+ <suffix domain="consulting.aero" />
+ <suffix domain="control.aero" />
+ <suffix domain="council.aero" />
+ <suffix domain="crew.aero" />
+ <suffix domain="design.aero" />
+ <suffix domain="dgca.aero" />
+ <suffix domain="educator.aero" />
+ <suffix domain="emergency.aero" />
+ <suffix domain="engine.aero" />
+ <suffix domain="engineer.aero" />
+ <suffix domain="entertainment.aero" />
+ <suffix domain="equipment.aero" />
+ <suffix domain="exchange.aero" />
+ <suffix domain="express.aero" />
+ <suffix domain="federation.aero" />
+ <suffix domain="flight.aero" />
+ <suffix domain="freight.aero" />
+ <suffix domain="fuel.aero" />
+ <suffix domain="gliding.aero" />
+ <suffix domain="government.aero" />
+ <suffix domain="groundhandling.aero" />
+ <suffix domain="group.aero" />
+ <suffix domain="hanggliding.aero" />
+ <suffix domain="homebuilt.aero" />
+ <suffix domain="insurance.aero" />
+ <suffix domain="journal.aero" />
+ <suffix domain="journalist.aero" />
+ <suffix domain="leasing.aero" />
+ <suffix domain="logistics.aero" />
+ <suffix domain="magazine.aero" />
+ <suffix domain="maintenance.aero" />
+ <suffix domain="marketplace.aero" />
+ <suffix domain="media.aero" />
+ <suffix domain="microlight.aero" />
+ <suffix domain="modelling.aero" />
+ <suffix domain="navigation.aero" />
+ <suffix domain="parachuting.aero" />
+ <suffix domain="paragliding.aero" />
+ <suffix domain="passenger-association.aero" />
+ <suffix domain="pilot.aero" />
+ <suffix domain="press.aero" />
+ <suffix domain="production.aero" />
+ <suffix domain="recreation.aero" />
+ <suffix domain="repbody.aero" />
+ <suffix domain="res.aero" />
+ <suffix domain="research.aero" />
+ <suffix domain="rotorcraft.aero" />
+ <suffix domain="safety.aero" />
+ <suffix domain="scientist.aero" />
+ <suffix domain="services.aero" />
+ <suffix domain="show.aero" />
+ <suffix domain="skydiving.aero" />
+ <suffix domain="software.aero" />
+ <suffix domain="student.aero" />
+ <suffix domain="taxi.aero" />
+ <suffix domain="trader.aero" />
+ <suffix domain="trading.aero" />
+ <suffix domain="trainer.aero" />
+ <suffix domain="union.aero" />
+ <suffix domain="workinggroup.aero" />
+ <suffix domain="works.aero" />
+
+ <!-- af : http://www.nic.af/help.jsp-- >
+ <suffix domain="gov.af" />
+ <suffix domain="com.af" />
+ <suffix domain="org.af" />
+ <suffix domain="net.af" />
+ <suffix domain="edu.af" />
+
+ <!-- ag : http://www.nic.ag/prices.htm-- >
+ <suffix domain="com.ag" />
+ <suffix domain="org.ag" />
+ <suffix domain="net.ag" />
+ <suffix domain="co.ag" />
+ <suffix domain="nom.ag" />
+
+ <!-- ai : http://nic.com.ai/-- >
+ <suffix domain="off.ai" />
+ <suffix domain="com.ai" />
+ <suffix domain="net.ai" />
+ <suffix domain="org.ai" />
+
+ <!-- al : http://www.inima.al/Domains.html-- >
+ <suffix domain="gov.al" />
+ <suffix domain="edu.al" />
+ <suffix domain="org.al" />
+ <suffix domain="com.al" />
+ <suffix domain="net.al" />
+
+ <!-- am : http://en.wikipedia.org/wiki/.am-- >
+
+ <!-- an : http://www.una.an/an_domreg/default.asp-- >
+ <suffix domain="com.an" />
+ <suffix domain="net.an" />
+ <suffix domain="org.an" />
+ <suffix domain="edu.an" />
+
+ <!-- ao : http://en.wikipedia.org/wiki/.ao-- >
+ <!-- list of 2nd level TLDs ?-->
+
+ <!-- aq : http://en.wikipedia.org/wiki/.aq-- >
+
+ <!-- ar : http://en.wikipedia.org/wiki/.ar-- >
+ <suffix domain="congresodelalengua3.ar" />
+ <suffix domain="educ.ar" />
+ <suffix domain="gobiernoelectronico.ar" />
+ <suffix domain="mecon.ar" />
+ <suffix domain="nacion.ar" />
+ <suffix domain="nic.ar" />
+ <suffix domain="promocion.ar" />
+ <suffix domain="retina.ar" />
+ <suffix domain="uba.ar" />
+
+ <!-- arpa : http://en.wikipedia.org/wiki/.arpa-- >
+ <suffix domain="e164.arpa" />
+ <suffix domain="in-addr.arpa" />
+ <suffix domain="ip6.arpa" />
+ <suffix domain="uri.arpa" />
+ <suffix domain="urn.arpa" />
+
+ <!-- as : http://en.wikipedia.org/wiki/.as-- >
+
+ <!-- at : http://en.wikipedia.org/wiki/.at-- >
+ <suffix domain="gv.at" />
+ <suffix domain="ac.at" />
+ <suffix domain="co.at" />
+ <suffix domain="or.at" />
+
+ <!-- au : http://en.wikipedia.org/wiki/.au-- >
+ <!-- au geographical names (vic.au etc... are covered above)-->
+ <suffix domain="act.edu.au" />
+ <suffix domain="nsw.edu.au" />
+ <suffix domain="nt.edu.au" />
+ <suffix domain="qld.edu.au" />
+ <suffix domain="sa.edu.au" />
+ <suffix domain="tas.edu.au" />
+ <suffix domain="vic.edu.au" />
+ <suffix domain="wa.edu.au" />
+ <suffix domain="act.gov.au" />
+ <suffix domain="nsw.gov.au" />
+ <suffix domain="nt.gov.au" />
+ <suffix domain="qld.gov.au" />
+ <suffix domain="sa.gov.au" />
+ <suffix domain="tas.gov.au" />
+ <suffix domain="vic.gov.au" />
+ <suffix domain="wa.gov.au" />
+
+ <!-- aw : http://en.wikipedia.org/wiki/.aw-- >
+ <suffix domain="com.aw" />
+
+ <!-- ax : http://en.wikipedia.org/wiki/.ax-- >
+
+ <!-- az : http://en.wikipedia.org/wiki/.az-- >
+ <suffix domain="com.az" />
+ <suffix domain="net.az" />
+ <suffix domain="int.az" />
+ <suffix domain="gov.az" />
+ <suffix domain="org.az" />
+ <suffix domain="edu.az" />
+ <suffix domain="info.az" />
+ <suffix domain="pp.az" />
+ <suffix domain="mil.az" />
+ <suffix domain="name.az" />
+ <suffix domain="biz.az" />
+
+ <!-- ba : http://en.wikipedia.org/wiki/.ba-- >
+ <suffix domain="org.ba" />
+ <suffix domain="net.ba" />
+ <suffix domain="edu.ba" />
+ <suffix domain="gov.ba" />
+ <suffix domain="mil.ba" />
+ <suffix domain="unsa.ba" />
+ <suffix domain="unbi.ba" />
+ <suffix domain="co.ba" />
+ <suffix domain="com.ba" />
+ <suffix domain="rs.ba" />
+
+ <!-- bb : http://en.wikipedia.org/wiki/.bb-- >
+ <suffix domain="com.bb" />
+ <suffix domain="edu.bb" />
+ <suffix domain="gov.bb" />
+ <suffix domain="net.bb" />
+ <suffix domain="org.bb" />
+
+ <!-- bd : http://en.wikipedia.org/wiki/.bd-- >
+
+ <!-- be : http://en.wikipedia.org/wiki/.be-- >
+ <suffix domain="ac.be" />
+
+ <!-- bf : http://en.wikipedia.org/wiki/.bf-- >
+
+ <!-- bg : http://en.wikipedia.org/wiki/.bg-- >
+
+ <!-- bh : http://en.wikipedia.org/wiki/.bh-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- bi : http://en.wikipedia.org/wiki/.bi-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- biz : http://en.wikipedia.org/wiki/.biz-- >
+
+ <!-- bj : http://en.wikipedia.org/wiki/.bj-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- bm : http://www.bermudanic.bm/dnr-text.txt-- >
+ <suffix domain="com.bm" />
+ <suffix domain="edu.bm" />
+ <suffix domain="gov.bm" />
+ <suffix domain="net.bm" />
+ <suffix domain="org.bm" />
+
+ <!-- bn : http://en.wikipedia.org/wiki/.bn-- >
+
+ <!-- bo : http://www.nic.bo/-- >
+ <suffix domain="com.bo" />
+ <suffix domain="edu.bo" />
+ <suffix domain="gov.bo" />
+ <suffix domain="gob.bo" />
+ <suffix domain="int.bo" />
+ <suffix domain="org.bo" />
+ <suffix domain="net.bo" />
+ <suffix domain="mil.bo" />
+ <suffix domain="tv.bo" />
+
+ <!-- br : http://en.wikipedia.org/wiki/.br-- >
+
+ <!-- bs : http://www.nic.bs/rules.html-- >
+ <suffix domain="com.bs" />
+ <suffix domain="net.bs" />
+ <suffix domain="org.bs" />
+ <suffix domain="edu.bs" />
+ <suffix domain="gov.bs" />
+
+ <!-- bt : http://en.wikipedia.org/wiki/.bt-- >
+
+ <!-- bw : http://en.wikipedia.org/wiki/.bw-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- by : http://en.wikipedia.org/wiki/.by-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- bz : http://en.wikipedia.org/wiki/.bz-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- ca : http://en.wikipedia.org/wiki/.ca-- >
+ <!-- ca geographical names-->
+ <suffix domain="ab.ca" />
+ <suffix domain="bc.ca" />
+ <suffix domain="mb.ca" />
+ <suffix domain="nb.ca" />
+ <suffix domain="nf.ca" />
+ <suffix domain="nl.ca" />
+ <suffix domain="ns.ca" />
+ <suffix domain="nt.ca" />
+ <suffix domain="nu.ca" />
+ <suffix domain="on.ca" />
+ <suffix domain="pe.ca" />
+ <suffix domain="qc.ca" />
+ <suffix domain="sk.ca" />
+ <suffix domain="yk.ca" />
+
+ <!-- cat : http://en.wikipedia.org/wiki/.cat-- >
+
+ <!-- cc : http://en.wikipedia.org/wiki/.cc-- >
+
+ <!-- cd : http://en.wikipedia.org/wiki/.cd-- >
+
+ <!-- cf : http://en.wikipedia.org/wiki/.cf-- >
+
+ <!-- cg : http://en.wikipedia.org/wiki/.cg-- >
+
+ <!-- ch : http://en.wikipedia.org/wiki/.ch-- >
+
+ <!-- ci : http://en.wikipedia.org/wiki/.ci-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- ck : http://en.wikipedia.org/wiki/.ck-- >
+
+ <!-- cl : http://en.wikipedia.org/wiki/.cl-- >
+
+ <!-- cm : http://en.wikipedia.org/wiki/.cm-- >
+
+ <!-- cn : http://en.wikipedia.org/wiki/.cn-- >
+ <suffix domain="ac.cn" />
+ <suffix domain="com.cn" />
+ <suffix domain="edu.cn" />
+ <suffix domain="gov.cn" />
+ <suffix domain="net.cn" />
+ <suffix domain="org.cn" />
+ <!-- cn geographic names-->
+ <suffix domain="ah.cn" />
+ <suffix domain="bj.cn" />
+ <suffix domain="cq.cn" />
+ <suffix domain="fj.cn" />
+ <suffix domain="gd.cn" />
+ <suffix domain="gs.cn" />
+ <suffix domain="gz.cn" />
+ <suffix domain="gx.cn" />
+ <suffix domain="ha.cn" />
+ <suffix domain="hb.cn" />
+ <suffix domain="he.cn" />
+ <suffix domain="hi.cn" />
+ <suffix domain="hl.cn" />
+ <suffix domain="hn.cn" />
+ <suffix domain="jl.cn" />
+ <suffix domain="js.cn" />
+ <suffix domain="jx.cn" />
+ <suffix domain="ln.cn" />
+ <suffix domain="nm.cn" />
+ <suffix domain="nx.cn" />
+ <suffix domain="qh.cn" />
+ <suffix domain="sc.cn" />
+ <suffix domain="sd.cn" />
+ <suffix domain="sh.cn" />
+ <suffix domain="sn.cn" />
+ <suffix domain="sx.cn" />
+ <suffix domain="tj.cn" />
+ <suffix domain="xj.cn" />
+ <suffix domain="xz.cn" />
+ <suffix domain="yn.cn" />
+ <suffix domain="zj.cn" />
+
+ <!-- co : http://en.wikipedia.org/wiki/.co-- >
+
+ <!-- com : http://en.wikipedia.org/wiki/.com-- >
+
+ <!-- coop : http://en.wikipedia.org/wiki/.coop-- >
+
+ <!-- cr : http://en.wikipedia.org/wiki/.cr-- >
+
+ <!-- cu : http://en.wikipedia.org/wiki/.cu-- >
+ <suffix domain="com.cu" />
+ <suffix domain="edu.cu" />
+ <suffix domain="org.cu" />
+ <suffix domain="net.cu" />
+ <suffix domain="gov.cu" />
+ <suffix domain="inf.cu" />
+
+ <!-- cv : http://en.wikipedia.org/wiki/.cv-- >
+
+ <!-- cx : http://en.wikipedia.org/wiki/.cx-- >
+
+ <!-- cy : http://en.wikipedia.org/wiki/.cy-- >
+
+ <!-- cz : http://en.wikipedia.org/wiki/.cz-- >
+
+ <!-- de : http://en.wikipedia.org/wiki/.de-- >
+
+ <!-- dj : http://en.wikipedia.org/wiki/.dj-- >
+
+ <!-- dk : http://en.wikipedia.org/wiki/.dk-- >
+
+ <!-- dm : http://en.wikipedia.org/wiki/.dm-- >
+ <suffix domain="com.dm" />
+ <suffix domain="net.dm" />
+ <suffix domain="org.dm" />
+
+ <!-- do : http://en.wikipedia.org/wiki/.do-- >
+
+ <!-- dz : http://en.wikipedia.org/wiki/.dz-- >
+ <suffix domain="com.dz" />
+ <suffix domain="org.dz" />
+ <suffix domain="net.dz" />
+ <suffix domain="gov.dz" />
+ <suffix domain="edu.dz" />
+ <suffix domain="asso.dz" />
+ <suffix domain="pol.dz" />
+ <suffix domain="art.dz" />
+
+ <!-- ec : http://www.nic.ec/reg/paso1.asp-- >
+ <suffix domain="com.ec" />
+ <suffix domain="info.ec" />
+ <suffix domain="net.ec" />
+ <suffix domain="fin.ec" />
+ <suffix domain="med.ec" />
+ <suffix domain="pro.ec" />
+ <suffix domain="org.ec" />
+ <suffix domain="edu.ec" />
+ <suffix domain="gov.ec" />
+ <suffix domain="mil.ec" />
+
+ <!-- edu : http://en.wikipedia.org/wiki/.edu-- >
+
+ <!-- ee : http://www3.eenet.ee/ee/application.html-- >
+ <suffix domain="com.ee" />
+ <suffix domain="org.ee" />
+ <suffix domain="fie.ee" />
+ <suffix domain="pri.ee" />
+
+ <!-- eg : http://en.wikipedia.org/wiki/.eg-- >
+
+ <!-- er : http://en.wikipedia.org/wiki/.er-- >
+
+ <!-- es : https://www.nic.es/site_ingles/ingles/dominios/index.html-- >
+ <suffix domain="com.es" />
+ <suffix domain="nom.es" />
+ <suffix domain="org.es" />
+ <suffix domain="gob.es" />
+ <suffix domain="edu.es" />
+
+ <!-- et : http://en.wikipedia.org/wiki/.et-- >
+
+ <!-- eu : http://en.wikipedia.org/wiki/.eu-- >
+
+ <!-- fi : http://en.wikipedia.org/wiki/.fi-- >
+
+ <!-- fj : http://en.wikipedia.org/wiki/.fj-- >
+
+ <!-- fk : http://en.wikipedia.org/wiki/.fk-- >
+
+ <!-- fm : http://en.wikipedia.org/wiki/.fm-- >
+
+ <!-- fo : http://en.wikipedia.org/wiki/.fo-- >
+
+ <!-- fr : http://www.afnic.fr/-- >
+ <!-- domaines descriptifs : http://www.afnic.fr/obtenir/chartes/nommage-fr/annexe-descriptifs-- >
+ <suffix domain="com.fr" />
+ <suffix domain="asso.fr" />
+ <suffix domain="nom.fr" />
+ <suffix domain="prd.fr" />
+ <suffix domain="presse.fr" />
+ <suffix domain="tm.fr" />
+ <!-- domaines sectoriels : http://www.afnic.fr/obtenir/chartes/nommage-fr/annexe-sectoriels-- >
+ <suffix domain="aeroport.fr" />
+ <suffix domain="assedic.fr" />
+ <suffix domain="avocat.fr" />
+ <suffix domain="avoues.fr" />
+ <suffix domain="cci.fr" />
+ <suffix domain="chambagri.fr" />
+ <suffix domain="chirurgiens-dentistes.fr" />
+ <suffix domain="experts-comptables.fr" />
+ <suffix domain="geometre-expert.fr" />
+ <suffix domain="gouv.fr" />
+ <suffix domain="greta.fr" />
+ <suffix domain="huissier-justice.fr" />
+ <suffix domain="medecin.fr" />
+ <suffix domain="notaires.fr" />
+ <suffix domain="pharmacien.fr" />
+ <suffix domain="port.fr" />
+ <suffix domain="veterinaire.fr" />
+
+ <!-- ga : http://en.wikipedia.org/wiki/.ga-- >
+
+ <!-- gd : http://en.wikipedia.org/wiki/.gd-- >
+
+ <!-- ge : http://www.nic.net.ge/policy_en.pdf-- >
+ <suffix domain="com.ge" />
+ <suffix domain="edu.ge" />
+ <suffix domain="gov.ge" />
+ <suffix domain="org.ge" />
+ <suffix domain="mil.ge" />
+ <suffix domain="net.ge" />
+ <suffix domain="pvt.ge" />
+
+ <!-- gf : http://en.wikipedia.org/wiki/.gf-- >
+
+ <!-- gg : http://www.channelisles.net/tandc.shtml-- >
+ <suffix domain="co.gg" />
+ <suffix domain="org.gg" />
+ <suffix domain="net.gg" />
+ <suffix domain="sch.gg" />
+ <suffix domain="gov.gg" />
+
+ <!-- gh : http://www.ghana.com/domain.htm-- >
+
+ <!-- gi : http://www.nic.gi/rules.html-- >
+ <suffix domain="com.gi" />
+ <suffix domain="ltd.gi" />
+ <suffix domain="gov.gi" />
+ <suffix domain="mod.gi" />
+ <suffix domain="edu.gi" />
+ <suffix domain="org.gi" />
+
+ <!-- gl : http://en.wikipedia.org/wiki/.gl-- >
+
+ <!-- gm : http://www.nic.gm/htmlpages%5Cgm-policy.htm-- >
+
+ <!-- gn : http://psg.com/dns/gn/gn.txt-- >
+
+ <!-- gov : http://en.wikipedia.org/wiki/.gov-- >
+
+ <!-- gp : http://www.nic.gp/index_en.php?url=charte_en.php-- >
+ <suffix domain="com.gp" />
+ <suffix domain="net.gp" />
+ <suffix domain="edu.gp" />
+ <suffix domain="org.gp" />
+
+ <!-- gq : http://en.wikipedia.org/wiki/.gq-- >
+
+ <!-- gr : https://grweb.ics.forth.gr/english/1617-B-2002.html-- >
+ <suffix domain="com.gr" />
+ <suffix domain="edu.gr" />
+ <suffix domain="net.gr" />
+ <suffix domain="org.gr" />
+ <suffix domain="gov.gr" />
+
+ <!-- gs : http://en.wikipedia.org/wiki/.gs-- >
+
+ <!-- gt : http://www.gt/politicas.html-- >
+
+ <!-- gu : http://gadao.gov.gu/registration.txt-- >
+
+ <!-- gw : http://en.wikipedia.org/wiki/.gw-- >
+
+ <!-- gy : http://en.wikipedia.org/wiki/.gy-- >
+
+ <!-- hk : http://en.wikipedia.org/wiki/.hk-- >
+ <suffix domain="com.hk" />
+ <suffix domain="edu.hk" />
+ <suffix domain="gov.hk" />
+ <suffix domain="idv.hk" />
+ <suffix domain="net.hk" />
+ <suffix domain="org.hk" />
+
+ <!-- hm : http://en.wikipedia.org/wiki/.hm-- >
+
+ <!-- hn : http://www.nic.hn/politicas/ps02,,05.html-- >
+ <suffix domain="com.hn" />
+ <suffix domain="edu.hn" />
+ <suffix domain="org.hn" />
+ <suffix domain="net.hn" />
+ <suffix domain="mil.hn" />
+ <suffix domain="gob.hn" />
+
+ <!-- hr : http://www.dns.hr/documents/pdf/HRTLD-regulations.pdf-- >
+ <suffix domain="iz.hr" />
+ <suffix domain="from.hr" />
+ <suffix domain="name.hr" />
+ <suffix domain="com.hr" />
+
+ <!-- ht : http://www.nic.ht/info/charte.cfm-- >
+ <suffix domain="com.ht" />
+ <suffix domain="shop.ht" />
+ <suffix domain="firm.ht" />
+ <suffix domain="info.ht" />
+ <suffix domain="adult.ht" />
+ <suffix domain="net.ht" />
+ <suffix domain="pro.ht" />
+ <suffix domain="org.ht" />
+ <suffix domain="med.ht" />
+ <suffix domain="art.ht" />
+ <suffix domain="coop.ht" />
+ <suffix domain="pol.ht" />
+ <suffix domain="asso.ht" />
+ <suffix domain="edu.ht" />
+ <suffix domain="rel.ht" />
+ <suffix domain="gouv.ht" />
+ <suffix domain="perso.ht" />
+
+ <!-- hu : http://www.domain.hu/domain/English/sld.html-- >
+ <suffix domain="co.hu" />
+ <suffix domain="info.hu" />
+ <suffix domain="org.hu" />
+ <suffix domain="priv.hu" />
+ <suffix domain="sport.hu" />
+ <suffix domain="tm.hu" />
+ <suffix domain="2000.hu" />
+ <suffix domain="agrar.hu" />
+ <suffix domain="bolt.hu" />
+ <suffix domain="casino.hu" />
+ <suffix domain="city.hu" />
+ <suffix domain="erotica.hu" />
+ <suffix domain="erotika.hu" />
+ <suffix domain="film.hu" />
+ <suffix domain="forum.hu" />
+ <suffix domain="games.hu" />
+ <suffix domain="hotel.hu" />
+ <suffix domain="ingatlan.hu" />
+ <suffix domain="jogasz.hu" />
+ <suffix domain="konyvelo.hu" />
+ <suffix domain="lakas.hu" />
+ <suffix domain="media.hu" />
+ <suffix domain="news.hu" />
+ <suffix domain="reklam.hu" />
+ <suffix domain="sex.hu" />
+ <suffix domain="shop.hu" />
+ <suffix domain="suli.hu" />
+ <suffix domain="szex.hu" />
+ <suffix domain="tozsde.hu" />
+ <suffix domain="utazas.hu" />
+ <suffix domain="video.hu" />
+
+ <!-- id : http://en.wikipedia.org/wiki/.id-- >
+
+ <!-- ie : http://en.wikipedia.org/wiki/.ie-- >
+
+ <!-- il : http://en.wikipedia.org/wiki/.il-- >
+
+ <!-- im : https://www.nic.im/pdfs/imfaqs.pdf-- >
+ <suffix domain="co.im" />
+ <suffix domain="ltd.co.im" />
+ <suffix domain="plc.co.im" />
+ <suffix domain="net.im" />
+ <suffix domain="gov.im" />
+ <suffix domain="org.im" />
+ <suffix domain="nic.im" />
+ <suffix domain="ac.im" />
+
+ <!-- in : http://en.wikipedia.org/wiki/.in-- >
+ <suffix domain="co.in" />
+ <suffix domain="firm.in" />
+ <suffix domain="net.in" />
+ <suffix domain="org.in" />
+ <suffix domain="gen.in" />
+ <suffix domain="ind.in" />
+ <suffix domain="nic.in" />
+ <suffix domain="ac.in" />
+ <suffix domain="edu.in" />
+ <suffix domain="res.in" />
+ <suffix domain="gov.in" />
+ <suffix domain="mil.in" />
+
+ <!-- info : http://en.wikipedia.org/wiki/.info-- >
+
+ <!-- int : http://en.wikipedia.org/wiki/.int-- >
+
+ <!-- io : http://www.nic.io/rules.html-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- iq : http://en.wikipedia.org/wiki/.iq-- >
+ <!-- no registrar website found, but google shows .gov.iq and .edu.iq websites-->
+ <suffix domain="gov.iq" />
+ <suffix domain="edu.iq" />
+
+ <!-- ir : http://www.nic.ir/ascii/Appendix1.htm-- >
+ <suffix domain="ac.ir" />
+ <suffix domain="co.ir" />
+ <suffix domain="gov.ir" />
+ <suffix domain="id.ir" />
+ <suffix domain="net.ir" />
+ <suffix domain="org.ir" />
+ <suffix domain="sch.ir" />
+
+ <!-- is : http://www.isnic.is/domain/rules.php-- >
+ <suffix domain="net.is" />
+ <suffix domain="com.is" />
+ <suffix domain="edu.is" />
+ <suffix domain="gov.is" />
+ <suffix domain="org.is" />
+ <suffix domain="int.is" />
+
+ <!-- it : http://en.wikipedia.org/wiki/.it-- >
+ <suffix domain="gov.edu " />
+ <!-- geo-names found at http://www.nic.it/RA/en/domini/regole/nomi-riservati.pdf-- >
+ <suffix domain="agrigento.it" />
+ <suffix domain="ag.it" />
+ <suffix domain="alessandria.it" />
+ <suffix domain="al.it" />
+ <suffix domain="ancona.it" />
+ <suffix domain="an.it" />
+ <suffix domain="aosta.it" />
+ <suffix domain="aoste.it" />
+ <suffix domain="ao.it" />
+ <suffix domain="arezzo.it" />
+ <suffix domain="ar.it" />
+ <suffix domain="ascoli-piceno.it" />
+ <suffix domain="ascolipiceno.it" />
+ <suffix domain="ap.it" />
+ <suffix domain="asti.it" />
+ <suffix domain="at.it" />
+ <suffix domain="avellino.it" />
+ <suffix domain="av.it" />
+ <suffix domain="bari.it" />
+ <suffix domain="ba.it" />
+ <suffix domain="barlettaandriatrani.it" />
+ <suffix domain="barletta-andria-trani.it" />
+ <suffix domain="belluno.it" />
+ <suffix domain="bl.it" />
+ <suffix domain="benevento.it" />
+ <suffix domain="bn.it" />
+ <suffix domain="bergamo.it" />
+ <suffix domain="bg.it" />
+ <suffix domain="biella.it" />
+ <suffix domain="bi.it" />
+ <suffix domain="bologna.it" />
+ <suffix domain="bo.it" />
+ <suffix domain="bolzano.it" />
+ <suffix domain="bozen.it" />
+ <suffix domain="balsan.it" />
+ <suffix domain="alto-adige.it" />
+ <suffix domain="altoadige.it" />
+ <suffix domain="suedtirol.it" />
+ <suffix domain="bz.it" />
+ <suffix domain="brescia.it" />
+ <suffix domain="bs.it" />
+ <suffix domain="brindisi.it" />
+ <suffix domain="br.it" />
+ <suffix domain="cagliari.it" />
+ <suffix domain="ca.it" />
+ <suffix domain="caltanissetta.it" />
+ <suffix domain="cl.it" />
+ <suffix domain="campobasso.it" />
+ <suffix domain="cb.it" />
+ <suffix domain="caserta.it" />
+ <suffix domain="ce.it" />
+ <suffix domain="catania.it" />
+ <suffix domain="ct.it" />
+ <suffix domain="catanzaro.it" />
+ <suffix domain="cz.it" />
+ <suffix domain="chieti.it" />
+ <suffix domain="ch.it" />
+ <suffix domain="como.it" />
+ <suffix domain="co.it" />
+ <suffix domain="cosenza.it" />
+ <suffix domain="cs.it" />
+ <suffix domain="cremona.it" />
+ <suffix domain="cr.it" />
+ <suffix domain="crotone.it" />
+ <suffix domain="kr.it" />
+ <suffix domain="cuneo.it" />
+ <suffix domain="cn.it" />
+ <suffix domain="enna.it" />
+ <suffix domain="en.it" />
+ <suffix domain="fermo.it" />
+ <suffix domain="ferrara.it" />
+ <suffix domain="fe.it" />
+ <suffix domain="firenze.it" />
+ <suffix domain="florence.it" />
+ <suffix domain="fi.it" />
+ <suffix domain="foggia.it" />
+ <suffix domain="fg.it" />
+ <suffix domain="forli-cesena.it" />
+ <suffix domain="forlicesena.it" />
+ <suffix domain="fc.it" />
+ <suffix domain="frosinone.it" />
+ <suffix domain="fr.it" />
+ <suffix domain="genova.it" />
+ <suffix domain="genoa.it" />
+ <suffix domain="ge.it" />
+ <suffix domain="gorizia.it" />
+ <suffix domain="go.it" />
+ <suffix domain="grosseto.it" />
+ <suffix domain="gr.it" />
+ <suffix domain="imperia.it" />
+ <suffix domain="im.it" />
+ <suffix domain="isernia.it" />
+ <suffix domain="is.it" />
+ <suffix domain="laquila.it" />
+ <suffix domain="aquila.it" />
+ <suffix domain="aq.it" />
+ <suffix domain="la-spezia.it" />
+ <suffix domain="laspezia.it" />
+ <suffix domain="sp.it" />
+ <suffix domain="latina.it" />
+ <suffix domain="lt.it" />
+ <suffix domain="lecce.it" />
+ <suffix domain="le.it" />
+ <suffix domain="lecco.it" />
+ <suffix domain="lc.it" />
+ <suffix domain="livorno.it" />
+ <suffix domain="li.it" />
+ <suffix domain="lodi.it" />
+ <suffix domain="lo.it" />
+ <suffix domain="lucca.it" />
+ <suffix domain="lu.it" />
+ <suffix domain="macerata.it" />
+ <suffix domain="mc.it" />
+ <suffix domain="mantova.it" />
+ <suffix domain="mn.it" />
+ <suffix domain="massa-carrara.it" />
+ <suffix domain="massacarrara.it" />
+ <suffix domain="ms.it" />
+ <suffix domain="matera.it" />
+ <suffix domain="mt.it" />
+ <suffix domain="messina.it" />
+ <suffix domain="me.it" />
+ <suffix domain="milano.it" />
+ <suffix domain="milan.it" />
+ <suffix domain="mi.it" />
+ <suffix domain="modena.it" />
+ <suffix domain="mo.it" />
+ <suffix domain="monza.it" />
+ <suffix domain="napoli.it" />
+ <suffix domain="naples.it" />
+ <suffix domain="na.it" />
+ <suffix domain="novara.it" />
+ <suffix domain="no.it" />
+ <suffix domain="nuoro.it" />
+ <suffix domain="nu.it" />
+ <suffix domain="oristano.it" />
+ <suffix domain="or.it" />
+ <suffix domain="padova.it" />
+ <suffix domain="padua.it" />
+ <suffix domain="pd.it" />
+ <suffix domain="palermo.it" />
+ <suffix domain="pa.it" />
+ <suffix domain="parma.it" />
+ <suffix domain="pr.it" />
+ <suffix domain="pavia.it" />
+ <suffix domain="pv.it" />
+ <suffix domain="perugia.it" />
+ <suffix domain="pg.it" />
+ <suffix domain="pescara.it" />
+ <suffix domain="pe.it" />
+ <suffix domain="pesaro-urbino.it" />
+ <suffix domain="pesarourbino.it" />
+ <suffix domain="pu.it" />
+ <suffix domain="piacenza.it" />
+ <suffix domain="pc.it" />
+ <suffix domain="pisa.it" />
+ <suffix domain="pi.it" />
+ <suffix domain="pistoia.it" />
+ <suffix domain="pt.it" />
+ <suffix domain="pordenone.it" />
+ <suffix domain="pn.it" />
+ <suffix domain="potenza.it" />
+ <suffix domain="pz.it" />
+ <suffix domain="prato.it" />
+ <suffix domain="po.it" />
+ <suffix domain="ragusa.it" />
+ <suffix domain="rg.it" />
+ <suffix domain="ravenna.it" />
+ <suffix domain="ra.it" />
+ <suffix domain="reggio-calabria.it" />
+ <suffix domain="reggiocalabria.it" />
+ <suffix domain="rc.it" />
+ <suffix domain="reggio-emilia.it" />
+ <suffix domain="reggioemilia.it" />
+ <suffix domain="re.it" />
+ <suffix domain="rieti.it" />
+ <suffix domain="ri.it" />
+ <suffix domain="rimini.it" />
+ <suffix domain="rn.it" />
+ <suffix domain="roma.it" />
+ <suffix domain="rome.it" />
+ <suffix domain="rm.it" />
+ <suffix domain="rovigo.it" />
+ <suffix domain="ro.it" />
+ <suffix domain="salerno.it" />
+ <suffix domain="sa.it" />
+ <suffix domain="sassari.it" />
+ <suffix domain="ss.it" />
+ <suffix domain="savona.it" />
+ <suffix domain="sv.it" />
+ <suffix domain="siena.it" />
+ <suffix domain="si.it" />
+ <suffix domain="siracusa.it" />
+ <suffix domain="sr.it" />
+ <suffix domain="sondrio.it" />
+ <suffix domain="so.it" />
+ <suffix domain="taranto.it" />
+ <suffix domain="ta.it" />
+ <suffix domain="teramo.it" />
+ <suffix domain="te.it" />
+ <suffix domain="terni.it" />
+ <suffix domain="tr.it" />
+ <suffix domain="torino.it" />
+ <suffix domain="turin.it" />
+ <suffix domain="to.it" />
+ <suffix domain="trapani.it" />
+ <suffix domain="tp.it" />
+ <suffix domain="trento.it" />
+ <suffix domain="trentino.it" />
+ <suffix domain="tn.it" />
+ <suffix domain="treviso.it" />
+ <suffix domain="tv.it" />
+ <suffix domain="trieste.it" />
+ <suffix domain="ts.it" />
+ <suffix domain="udine.it" />
+ <suffix domain="ud.it" />
+ <suffix domain="varese.it" />
+ <suffix domain="va.it" />
+ <suffix domain="venezia.it" />
+ <suffix domain="venice.it" />
+ <suffix domain="ve.it" />
+ <suffix domain="verbania.it" />
+ <suffix domain="vb.it" />
+ <suffix domain="vercelli.it" />
+ <suffix domain="vc.it" />
+ <suffix domain="verona.it" />
+ <suffix domain="vr.it" />
+ <suffix domain="vibo-valentia.it" />
+ <suffix domain="vibovalentia.it" />
+ <suffix domain="vv.it" />
+ <suffix domain="vicenza.it" />
+ <suffix domain="vi.it" />
+ <suffix domain="viterbo.it" />
+ <suffix domain="vt.it" />
+
+ <!-- je : http://www.channelisles.net/tandc.shtml-- >
+ <suffix domain="co.je" />
+ <suffix domain="org.je" />
+ <suffix domain="net.je" />
+ <suffix domain="sch.je" />
+ <suffix domain="gov.je" />
+
+ <!-- jm : http://www.com.jm/register.html-- >
+
+ <!-- jo : http://www.nis.gov.jo/dns/reg.html-- >
+ <suffix domain="com.jo" />
+ <suffix domain="org.jo" />
+ <suffix domain="net.jo" />
+ <suffix domain="edu.jo" />
+ <suffix domain="gov.jo" />
+ <suffix domain="mil.jo" />
+ <suffix domain="myname.jo" />
+
+ <!-- jobs : http://en.wikipedia.org/wiki/.jobs-- >
+
+ <!-- jp : http://en.wikipedia.org/wiki/.jp-- >
+ <suffix domain="ac.jp" />
+ <suffix domain="ad.jp" />
+ <suffix domain="co.jp" />
+ <suffix domain="ed.jp" />
+ <suffix domain="go.jp" />
+ <suffix domain="gr.jp" />
+ <suffix domain="lg.jp" />
+ <suffix domain="ne.jp" />
+ <suffix domain="or.jp" />
+ <!-- jp geographical names-->
+ <!-- I can't find an official english explanantrion, but used https://bugzilla.mozilla.org/show_bug.cgi?id=252342#c31-- >
+ <suffix domain="aichi.jp" />
+ <suffix domain="akita.jp" />
+ <suffix domain="aomori.jp" />
+ <suffix domain="chiba.jp" />
+ <suffix domain="ehime.jp" />
+ <suffix domain="fukui.jp" />
+ <suffix domain="fukuoka.jp" />
+ <suffix domain="fukushima.jp" />
+ <suffix domain="gifu.jp" />
+ <suffix domain="gunma.jp" />
+ <suffix domain="hiroshima.jp" />
+ <suffix domain="hokkaido.jp" />
+ <suffix domain="hyogo.jp" />
+ <suffix domain="ibaraki.jp" />
+ <suffix domain="ishikawa.jp" />
+ <suffix domain="iwate.jp" />
+ <suffix domain="kagawa.jp" />
+ <suffix domain="kagoshima.jp" />
+ <suffix domain="kanagawa.jp" />
+ <suffix domain="kawasaki.jp" />
+ <suffix domain="kitakyushu.jp" />
+ <suffix domain="kobe.jp" />
+ <suffix domain="kochi.jp" />
+ <suffix domain="kumamoto.jp" />
+ <suffix domain="kyoto.jp" />
+ <suffix domain="mie.jp" />
+ <suffix domain="miyagi.jp" />
+ <suffix domain="miyazaki.jp" />
+ <suffix domain="nagano.jp" />
+ <suffix domain="nagasaki.jp" />
+ <suffix domain="nagoya.jp" />
+ <suffix domain="nara.jp" />
+ <suffix domain="niigata.jp" />
+ <suffix domain="oita.jp" />
+ <suffix domain="okayama.jp" />
+ <suffix domain="okinawa.jp" />
+ <suffix domain="osaka.jp" />
+ <suffix domain="saga.jp" />
+ <suffix domain="saitama.jp" />
+ <suffix domain="sapporo.jp" />
+ <suffix domain="sendai.jp" />
+ <suffix domain="shiga.jp" />
+ <suffix domain="shimane.jp" />
+ <suffix domain="shizuoka.jp" />
+ <suffix domain="tochigi.jp" />
+ <suffix domain="tokushima.jp" />
+ <suffix domain="tokyo.jp" />
+ <suffix domain="tottori.jp" />
+ <suffix domain="toyama.jp" />
+ <suffix domain="wakayama.jp" />
+ <suffix domain="yamagata.jp" />
+ <suffix domain="yamaguchi.jp" />
+ <suffix domain="yamanashi.jp" />
+ <suffix domain="yokohama.jp" />
+ <suffix domain="metro.tokyo.jp" />
+ <suffix domain="pref.aichi.jp" />
+ <suffix domain="pref.akita.jp" />
+ <suffix domain="pref.aomori.jp" />
+ <suffix domain="pref.chiba.jp" />
+ <suffix domain="pref.ehime.jp" />
+ <suffix domain="pref.fukui.jp" />
+ <suffix domain="pref.fukuoka.jp" />
+ <suffix domain="pref.fukushima.jp" />
+ <suffix domain="pref.gifu.jp" />
+ <suffix domain="pref.gunma.jp" />
+ <suffix domain="pref.hiroshima.jp" />
+ <suffix domain="pref.hokkaido.jp" />
+ <suffix domain="pref.hyogo.jp" />
+ <suffix domain="pref.ibaraki.jp" />
+ <suffix domain="pref.ishikawa.jp" />
+ <suffix domain="pref.iwate.jp" />
+ <suffix domain="pref.kagawa.jp" />
+ <suffix domain="pref.kagoshima.jp" />
+ <suffix domain="pref.kanagawa.jp" />
+ <suffix domain="pref.kochi.jp" />
+ <suffix domain="pref.kumamoto.jp" />
+ <suffix domain="pref.kyoto.jp" />
+ <suffix domain="pref.mie.jp" />
+ <suffix domain="pref.miyagi.jp" />
+ <suffix domain="pref.miyazaki.jp" />
+ <suffix domain="pref.nagano.jp" />
+ <suffix domain="pref.nagasaki.jp" />
+ <suffix domain="pref.nara.jp" />
+ <suffix domain="pref.niigata.jp" />
+ <suffix domain="pref.oita.jp" />
+ <suffix domain="pref.okayama.jp" />
+ <suffix domain="pref.okinawa.jp" />
+ <suffix domain="pref.osaka.jp" />
+ <suffix domain="pref.saga.jp" />
+ <suffix domain="pref.saitama.jp" />
+ <suffix domain="pref.shiga.jp" />
+ <suffix domain="pref.shimane.jp" />
+ <suffix domain="pref.shizuoka.jp" />
+ <suffix domain="pref.tochigi.jp" />
+ <suffix domain="pref.tokushima.jp" />
+ <suffix domain="pref.tottori.jp" />
+ <suffix domain="pref.toyama.jp" />
+ <suffix domain="pref.wakayama.jp" />
+ <suffix domain="pref.yamagata.jp" />
+ <suffix domain="pref.yamaguchi.jp" />
+ <suffix domain="pref.yamanashi.jp" />
+ <suffix domain="city.chiba.jp" />
+ <suffix domain="city.fukuoka.jp" />
+ <suffix domain="city.hiroshima.jp" />
+ <suffix domain="city.kawasaki.jp" />
+ <suffix domain="city.kitakyushu.jp" />
+ <suffix domain="city.kobe.jp" />
+ <suffix domain="city.kyoto.jp" />
+ <suffix domain="city.nagoya.jp" />
+ <suffix domain="city.osaka.jp" />
+ <suffix domain="city.saitama.jp" />
+ <suffix domain="city.sapporo.jp" />
+ <suffix domain="city.sendai.jp" />
+ <suffix domain="city.shizuoka.jp" />
+ <suffix domain="city.yokohama.jp" />
+
+ <!-- ke : http://www.kenic.or.ke/index.php?option=com_content&task=view&id=117&Item... >
+
+ <!-- kg : http://www.domain.kg/dmn_n.html-- >
+ <suffix domain="org.kg" />
+ <suffix domain="net.kg" />
+ <suffix domain="com.kg" />
+ <suffix domain="edu.kg" />
+ <suffix domain="gov.kg" />
+ <suffix domain="mil.kg" />
+
+ <!-- kh : http://www.mptc.gov.kh/dns_registration.htm-- >
+
+ <!-- ki : http://www.ki/dns/index.html-- >
+ <suffix domain="edu.ki" />
+ <suffix domain="biz.ki" />
+ <suffix domain="net.ki" />
+ <suffix domain="org.ki" />
+ <suffix domain="gov.ki" />
+ <suffix domain="info.ki" />
+ <suffix domain="com.ki" />
+
+ <!-- km : http://en.wikipedia.org/wiki/.km-- >
+
+ <!-- kn : http://en.wikipedia.org/wiki/.kn-- >
+
+ <!-- kr : http://domain.nida.or.kr/eng/structure.jsp-- >
+ <suffix domain="ac.kr" />
+ <suffix domain="co.kr" />
+ <suffix domain="go.kr" />
+ <suffix domain="ne.kr" />
+ <suffix domain="or.kr" />
+ <suffix domain="re.kr" />
+ <suffix domain="pe.kr" />
+ <suffix domain="՜Ꞁ.kr" />
+
+ <!-- kw : http://en.wikipedia.org/wiki/.kw-- >
+
+ <!-- ky : http://www.icta.ky/da_ky_reg_dom.php-- >
+ <suffix domain="edu.ky" />
+ <suffix domain="gov.ky" />
+ <suffix domain="com.ky" />
+ <suffix domain="org.ky" />
+ <suffix domain="net.ky" />
+
+ <!-- kz : http://en.wikipedia.org/wiki/.kz-- >
+ <suffix domain="org.kz" />
+ <suffix domain="edu.kz" />
+ <suffix domain="net.kz" />
+ <suffix domain="gov.kz" />
+ <suffix domain="mil.kz" />
+ <suffix domain="com.kz" />
+
+ <!-- la : http://en.wikipedia.org/wiki/.la-- >
+
+ <!-- lb : http://en.wikipedia.org/wiki/.lb-- >
+
+ <!-- lc : http://en.wikipedia.org/wiki/.lc-- >
+ <suffix domain="com.lc" />
+ <suffix domain="org.lc" />
+ <suffix domain="edu.lc" />
+ <suffix domain="gov.lc" />
+
+ <!-- li : http://en.wikipedia.org/wiki/.li-- >
+
+ <!-- lk : http://www.nic.lk/seclevpr.html-- >
+ <suffix domain="gov.lk" />
+ <suffix domain="sch.lk" />
+ <suffix domain="net.lk" />
+ <suffix domain="int.lk" />
+ <suffix domain="com.lk" />
+ <suffix domain="org.lk" />
+ <suffix domain="edu.lk" />
+ <suffix domain="ngo.lk" />
+ <suffix domain="soc.lk" />
+ <suffix domain="web.lk" />
+ <suffix domain="ltd.lk" />
+ <suffix domain="assn.lk" />
+ <suffix domain="grp.lk" />
+ <suffix domain="hotel.lk" />
+
+ <!-- lr : http://psg.com/dns/lr/lr.txt-- >
+
+ <!-- ls : http://en.wikipedia.org/wiki/.ls-- >
+ <suffix domain="co.ls" />
+ <suffix domain="org.ls" />
+
+ <!-- lt : http://en.wikipedia.org/wiki/.lt-- >
+
+ <!-- lu : http://www.dns.lu/en/-- >
+
+ <!-- lv : http://www.nic.lv/DNS/En/generic.php-- >
+ <suffix domain="com.lv" />
+ <suffix domain="edu.lv" />
+ <suffix domain="gov.lv" />
+ <suffix domain="org.lv" />
+ <suffix domain="mil.lv" />
+ <suffix domain="id.lv" />
+ <suffix domain="net.lv" />
+ <suffix domain="asn.lv" />
+ <suffix domain="conf.lv" />
+
+ <!-- ly : http://www.nic.ly/regulations.php-- >
+ <suffix domain="com.ly" />
+ <suffix domain="net.ly" />
+ <suffix domain="gov.ly" />
+ <suffix domain="plc.ly" />
+ <suffix domain="edu.ly" />
+ <suffix domain="sch.ly" />
+ <suffix domain="med.ly" />
+ <suffix domain="org.ly" />
+ <suffix domain="id.ly" />
+
+ <!-- ma : http://en.wikipedia.org/wiki/.ma-- >
+ <!-- list of 2nd level tlds ?-->
+ <suffix domain="co.ma" />
+ <suffix domain="net.ma" />
+ <suffix domain="gov.ma" />
+ <suffix domain="org.ma" />
+
+ <!-- mc : http://www.nic.mc/-- >
+ <suffix domain="tm.mc" />
+ <suffix domain="asso.mc" />
+
+ <!-- md : http://en.wikipedia.org/wiki/.md-- >
+
+ <!-- mg : http://www.nic.mg/tarif.htm-- >
+ <suffix domain="org.mg" />
+ <suffix domain="nom.mg" />
+ <suffix domain="gov.mg" />
+ <suffix domain="prd.mg" />
+ <suffix domain="tm.mg" />
+ <suffix domain="edu.mg" />
+ <suffix domain="mil.mg" />
+ <suffix domain="com.mg" />
+
+ <!-- mh : http://en.wikipedia.org/wiki/.mh-- >
+
+ <!-- mil : http://en.wikipedia.org/wiki/.mil-- >
+
+ <!-- mk : http://en.wikipedia.org/wiki/.mk-- >
+ <!-- list of 2nd level tlds ?-->
+ <suffix domain="com.mk" />
+ <suffix domain="gov.mk" />
+ <suffix domain="org.mk" />
+ <suffix domain="net.mk" />
+ <suffix domain="edu.mk" />
+
+ <!-- ml : http://www.gobin.info/domainname/ml-template.doc-- >
+
+ <!-- mm : http://en.wikipedia.org/wiki/.mm-- >
+
+ <!-- mn : http://en.wikipedia.org/wiki/.mn-- >
+ <suffix domain="gov.mn" />
+ <suffix domain="edu.mn" />
+ <suffix domain="org.mn" />
+
+ <!-- mo : http://www.monic.net.mo/-- >
+ <suffix domain="com.mo" />
+ <suffix domain="net.mo" />
+ <suffix domain="org.mo" />
+ <suffix domain="edu.mo" />
+ <suffix domain="gov.mo" />
+
+ <!-- mobi : http://en.wikipedia.org/wiki/.mobi-- >
+
+ <!-- mp : http://www.dot.mp/-- >
+
+ <!-- mq : http://en.wikipedia.org/wiki/.mq-- >
+
+ <!-- mr : http://en.wikipedia.org/wiki/.mr-- >
+
+ <!-- ms : http://en.wikipedia.org/wiki/.ms-- >
+
+ <!-- mt : https://www.nic.org.mt/dotmt/-- >
+
+ <!-- mu : http://en.wikipedia.org/wiki/.mu-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- museum : http://about.museum/naming/-- >
+ <!-- there are 2nd-level TLD's, but there's no list-->
+
+ <!-- mv : http://en.wikipedia.org/wiki/.mv-- >
+
+ <!-- mw : http://www.registrar.mw/-- >
+ <suffix domain="ac.mw" />
+ <suffix domain="biz.mw" />
+ <suffix domain="co.mw" />
+ <suffix domain="com.mw" />
+ <suffix domain="coop.mw" />
+ <suffix domain="edu.mw" />
+ <suffix domain="gov.mw" />
+ <suffix domain="int.mw" />
+ <suffix domain="net.mw" />
+ <suffix domain="org.mw" />
+
+ <!-- mx : http://www.nic.mx/-- >
+
+ <!-- my : http://www.mynic.net.my/-- >
+
+ <!-- mz : http://www.gobin.info/domainname/mz-template.doc-- >
+
+ <!-- na : http://www.na-nic.com.na/-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- name : has 2nd-level tlds, but there's no list of them-->
+
+ <!-- nc : http://www.cctld.nc/-- >
+
+ <!-- ne : http://en.wikipedia.org/wiki/.ne-- >
+
+ <!-- net : http://en.wikipedia.org/wiki/.net-- >
+
+ <!-- nf : http://en.wikipedia.org/wiki/.nf-- >
+ <suffix domain="com.nf" />
+ <suffix domain="net.nf" />
+ <suffix domain="per.nf" />
+ <suffix domain="rec.nf" />
+ <suffix domain="web.nf" />
+ <suffix domain="arts.nf" />
+ <suffix domain="firm.nf" />
+ <suffix domain="info.nf" />
+ <suffix domain="other.nf" />
+ <suffix domain="store.nf" />
+
+ <!-- ng : http://psg.com/dns/ng/-- >
+
+ <!-- ni : http://www.nic.ni/dominios.htm-- >
+
+ <!-- nl : http://www.domain-registry.nl/ace.php/c,728,122,,,,Home.html-- >
+
+ <!-- no : http://www.norid.no/regelverk/index.en.html-- >
+ <suffix domain="fhs.no" />
+ <suffix domain="vgs.no" />
+ <suffix domain="fylkesbibl.no" />
+ <suffix domain="folkebibl.no" />
+ <suffix domain="museum.no" />
+ <suffix domain="idrett.no" />
+ <suffix domain="mil.no" />
+ <suffix domain="stat.no" />
+ <suffix domain="dep.no" />
+ <suffix domain="kommune.no" />
+ <suffix domain="herad.no" />
+ <suffix domain="priv.no" />
+ <!-- no geographical names : http://www.norid.no/regelverk/vedlegg-b.en.html-- >
+ <!-- counties-->
+ <suffix domain="aa.no" />
+ <suffix domain="ah.no" />
+ <suffix domain="bu.no" />
+ <suffix domain="fm.no" />
+ <suffix domain="hl.no" />
+ <suffix domain="hm.no" />
+ <suffix domain="jan-mayen.no" />
+ <suffix domain="mr.no" />
+ <suffix domain="nl.no" />
+ <suffix domain="nt.no" />
+ <suffix domain="of.no" />
+ <suffix domain="ol.no" />
+ <suffix domain="oslo.no" />
+ <suffix domain="rl.no" />
+ <suffix domain="sf.no" />
+ <suffix domain="st.no" />
+ <suffix domain="svalbard.no" />
+ <suffix domain="tm.no" />
+ <suffix domain="tr.no" />
+ <suffix domain="va.no" />
+ <suffix domain="vf.no" />
+ <!-- primary and lower secondary schools per county-->
+ <suffix domain="gs.aa.no" />
+ <suffix domain="gs.ah.no" />
+ <suffix domain="gs.bu.no" />
+ <suffix domain="gs.fm.no" />
+ <suffix domain="gs.hl.no" />
+ <suffix domain="gs.hm.no" />
+ <suffix domain="gs.jan-mayen.no" />
+ <suffix domain="gs.mr.no" />
+ <suffix domain="gs.nl.no" />
+ <suffix domain="gs.nt.no" />
+ <suffix domain="gs.of.no" />
+ <suffix domain="gs.ol.no" />
+ <suffix domain="gs.oslo.no" />
+ <suffix domain="gs.rl.no" />
+ <suffix domain="gs.sf.no" />
+ <suffix domain="gs.st.no" />
+ <suffix domain="gs.svalbard.no" />
+ <suffix domain="gs.tm.no" />
+ <suffix domain="gs.tr.no" />
+ <suffix domain="gs.va.no" />
+ <suffix domain="gs.vf.no" />
+ <!-- cities-->
+ <suffix domain="akrehamn.no" />
+ <suffix domain="Ã¥krehamn.no" />
+ <suffix domain="algard.no" />
+ <suffix domain="ålgård.no" />
+ <suffix domain="arna.no" />
+ <suffix domain="brumunddal.no" />
+ <suffix domain="bryne.no" />
+ <suffix domain="bronnoysund.no" />
+ <suffix domain="brÞnnÞysund.no" />
+ <suffix domain="drobak.no" />
+ <suffix domain="drÞbak.no" />
+ <suffix domain="egersund.no" />
+ <suffix domain="fetsund.no" />
+ <suffix domain="floro.no" />
+ <suffix domain="florÞ.no" />
+ <suffix domain="fredrikstad.no" />
+ <suffix domain="hokksund.no" />
+ <suffix domain="honefoss.no" />
+ <suffix domain="hÞnefoss.no" />
+ <suffix domain="jessheim.no" />
+ <suffix domain="jorpeland.no" />
+ <suffix domain="jÞrpeland.no" />
+ <suffix domain="kirkenes.no" />
+ <suffix domain="kopervik.no" />
+ <suffix domain="krokstadelva.no" />
+ <suffix domain="langevag.no" />
+ <suffix domain="langevåg.no" />
+ <suffix domain="leirvik.no" />
+ <suffix domain="mjondalen.no" />
+ <suffix domain="mjÞndalen.no" />
+ <suffix domain="mo-i-rana.no" />
+ <suffix domain="mosjoen.no" />
+ <suffix domain="mosjÞen.no" />
+ <suffix domain="nesoddtangen.no" />
+ <suffix domain="orkanger.no" />
+ <suffix domain="osoyro.no" />
+ <suffix domain="osÞyro.no" />
+ <suffix domain="raholt.no" />
+ <suffix domain="råholt.no" />
+ <suffix domain="sandnessjoen.no" />
+ <suffix domain="sandnessjÞen.no" />
+ <suffix domain="skedsmokorset.no" />
+ <suffix domain="slattum.no" />
+ <suffix domain="spjelkavik.no" />
+ <suffix domain="stathelle.no" />
+ <suffix domain="stavern.no" />
+ <suffix domain="stjordalshalsen.no" />
+ <suffix domain="stjÞrdalshalsen.no" />
+ <suffix domain="tananger.no" />
+ <suffix domain="tranby.no" />
+ <suffix domain="vossevangen.no" />
+ <!-- communities-->
+ <suffix domain="afjord.no" />
+ <suffix domain="Ã¥fjord.no" />
+ <suffix domain="agdenes.no" />
+ <suffix domain="al.no" />
+ <suffix domain="Ã¥l.no" />
+ <suffix domain="alesund.no" />
+ <suffix domain="Ã¥lesund.no" />
+ <suffix domain="alstahaug.no" />
+ <suffix domain="alta.no" />
+ <suffix domain="áltá.no" />
+ <suffix domain="alaheadju.no" />
+ <suffix domain="álaheadju.no" />
+ <suffix domain="alvdal.no" />
+ <suffix domain="amli.no" />
+ <suffix domain="Ã¥mli.no" />
+ <suffix domain="amot.no" />
+ <suffix domain="Ã¥mot.no" />
+ <suffix domain="andebu.no" />
+ <suffix domain="andoy.no" />
+ <suffix domain="andÞy.no" />
+ <suffix domain="andasuolo.no" />
+ <suffix domain="ardal.no" />
+ <suffix domain="Ã¥rdal.no" />
+ <suffix domain="aremark.no" />
+ <suffix domain="arendal.no" />
+ <suffix domain="Ã¥s.no" />
+ <suffix domain="aseral.no" />
+ <suffix domain="Ã¥seral.no" />
+ <suffix domain="asker.no" />
+ <suffix domain="askim.no" />
+ <suffix domain="askvoll.no" />
+ <suffix domain="askoy.no" />
+ <suffix domain="askÞy.no" />
+ <suffix domain="asnes.no" />
+ <suffix domain="Ã¥snes.no" />
+ <suffix domain="audnedaln.no" />
+ <suffix domain="aukra.no" />
+ <suffix domain="aure.no" />
+ <suffix domain="aurland.no" />
+ <suffix domain="aurskog-holand.no" />
+ <suffix domain="aurskog-hÞland.no" />
+ <suffix domain="austevoll.no" />
+ <suffix domain="austrheim.no" />
+ <suffix domain="averoy.no" />
+ <suffix domain="averÞy.no" />
+ <suffix domain="balestrand.no" />
+ <suffix domain="ballangen.no" />
+ <suffix domain="balat.no" />
+ <suffix domain="bálát.no" />
+ <suffix domain="balsfjord.no" />
+ <suffix domain="bahccavuotna.no" />
+ <suffix domain="báhccavuotna.no" />
+ <suffix domain="bamble.no" />
+ <suffix domain="bardu.no" />
+ <suffix domain="beardu.no" />
+ <suffix domain="beiarn.no" />
+ <suffix domain="bajddar.no" />
+ <suffix domain="bájddar.no" />
+ <suffix domain="baidar.no" />
+ <suffix domain="báidár.no" />
+ <suffix domain="berg.no" />
+ <suffix domain="bergen.no" />
+ <suffix domain="berlevag.no" />
+ <suffix domain="berlevåg.no" />
+ <suffix domain="bearalvahki.no" />
+ <suffix domain="bearalváhki.no" />
+ <suffix domain="bindal.no" />
+ <suffix domain="birkenes.no" />
+ <suffix domain="bjarkoy.no" />
+ <suffix domain="bjarkÞy.no" />
+ <suffix domain="bjerkreim.no" />
+ <suffix domain="bjugn.no" />
+ <suffix domain="bodo.no" />
+ <suffix domain="bodÞ.no" />
+ <suffix domain="badaddja.no" />
+ <suffix domain="bådåddjå.no" />
+ <suffix domain="budejju.no" />
+ <suffix domain="bokn.no" />
+ <suffix domain="bremanger.no" />
+ <suffix domain="bronnoy.no" />
+ <suffix domain="brÞnnÞy.no" />
+ <suffix domain="bygland.no" />
+ <suffix domain="bykle.no" />
+ <suffix domain="barum.no" />
+ <suffix domain="bÊrum.no" />
+ <suffix domain="bo.telemark.no" />
+ <suffix domain="bÞ.telemark.no" />
+ <suffix domain="bo.nordland.no" />
+ <suffix domain="bÞ.nordland.no" />
+ <suffix domain="bievat.no" />
+ <suffix domain="bievát.no" />
+ <suffix domain="bomlo.no" />
+ <suffix domain="bÞmlo.no" />
+ <suffix domain="batsfjord.no" />
+ <suffix domain="båtsfjord.no" />
+ <suffix domain="bahcavuotna.no" />
+ <suffix domain="báhcavuotna.no" />
+ <suffix domain="dovre.no" />
+ <suffix domain="drammen.no" />
+ <suffix domain="drangedal.no" />
+ <suffix domain="dyroy.no" />
+ <suffix domain="dyrÞy.no" />
+ <suffix domain="donna.no" />
+ <suffix domain="dÞnna.no" />
+ <suffix domain="eid.no" />
+ <suffix domain="eidfjord.no" />
+ <suffix domain="eidsberg.no" />
+ <suffix domain="eidskog.no" />
+ <suffix domain="eidsvoll.no" />
+ <suffix domain="eigersund.no" />
+ <suffix domain="elverum.no" />
+ <suffix domain="enebakk.no" />
+ <suffix domain="engerdal.no" />
+ <suffix domain="etne.no" />
+ <suffix domain="etnedal.no" />
+ <suffix domain="evenes.no" />
+ <suffix domain="evenassi.no" />
+ <suffix domain="evenášši.no" />
+ <suffix domain="evje-og-hornnes.no" />
+ <suffix domain="farsund.no" />
+ <suffix domain="fauske.no" />
+ <suffix domain="fuossko.no" />
+ <suffix domain="fuoisku.no" />
+ <suffix domain="fedje.no" />
+ <suffix domain="fet.no" />
+ <suffix domain="finnoy.no" />
+ <suffix domain="finnÞy.no" />
+ <suffix domain="fitjar.no" />
+ <suffix domain="fjaler.no" />
+ <suffix domain="fjell.no" />
+ <suffix domain="flakstad.no" />
+ <suffix domain="flatanger.no" />
+ <suffix domain="flekkefjord.no" />
+ <suffix domain="flesberg.no" />
+ <suffix domain="flora.no" />
+ <suffix domain="fla.no" />
+ <suffix domain="flå.no" />
+ <suffix domain="folldal.no" />
+ <suffix domain="forsand.no" />
+ <suffix domain="fosnes.no" />
+ <suffix domain="fredrikstad.no" />
+ <suffix domain="frei.no" />
+ <suffix domain="frogn.no" />
+ <suffix domain="froland.no" />
+ <suffix domain="frosta.no" />
+ <suffix domain="frana.no" />
+ <suffix domain="frÊna.no" />
+ <suffix domain="froya.no" />
+ <suffix domain="frÞya.no" />
+ <suffix domain="fusa.no" />
+ <suffix domain="fyresdal.no" />
+ <suffix domain="forde.no" />
+ <suffix domain="fÞrde.no" />
+ <suffix domain="gamvik.no" />
+ <suffix domain="gangaviika.no" />
+ <suffix domain="gaular.no" />
+ <suffix domain="gausdal.no" />
+ <suffix domain="gildeskal.no" />
+ <suffix domain="gildeskål.no" />
+ <suffix domain="giske.no" />
+ <suffix domain="gjemnes.no" />
+ <suffix domain="gjerdrum.no" />
+ <suffix domain="gjerstad.no" />
+ <suffix domain="gjesdal.no" />
+ <suffix domain="gjovik.no" />
+ <suffix domain="gjÞvik.no" />
+ <suffix domain="gloppen.no" />
+ <suffix domain="gol.no" />
+ <suffix domain="gran.no" />
+ <suffix domain="grane.no" />
+ <suffix domain="granvin.no" />
+ <suffix domain="gratangen.no" />
+ <suffix domain="grimstad.no" />
+ <suffix domain="grong.no" />
+ <suffix domain="kraanghke.no" />
+ <suffix domain="kråanghke.no" />
+ <suffix domain="grue.no" />
+ <suffix domain="gulen.no" />
+ <suffix domain="hadsel.no" />
+ <suffix domain="halden.no" />
+ <suffix domain="halsa.no" />
+ <suffix domain="hamar.no" />
+ <suffix domain="hamaroy.no" />
+ <suffix domain="habmer.no" />
+ <suffix domain="hábmer.no" />
+ <suffix domain="hapmir.no" />
+ <suffix domain="hápmir.no" />
+ <suffix domain="hammerfest.no" />
+ <suffix domain="hammarfeasta.no" />
+ <suffix domain="hámmárfeasta.no" />
+ <suffix domain="haram.no" />
+ <suffix domain="hareid.no" />
+ <suffix domain="harstad.no" />
+ <suffix domain="hasvik.no" />
+ <suffix domain="aknoluokta.no" />
+ <suffix domain="ákŋoluokta.no" />
+ <suffix domain="hattfjelldal.no" />
+ <suffix domain="aarborte.no" />
+ <suffix domain="haugesund.no" />
+ <suffix domain="hemne.no" />
+ <suffix domain="hemnes.no" />
+ <suffix domain="hemsedal.no" />
+ <suffix domain="heroy.more-og-romsdal.no" />
+ <suffix domain="herÞy.mÞre-og-romsdal.no" />
+ <suffix domain="heroy.nordland.no" />
+ <suffix domain="herÞy.nordland.no" />
+ <suffix domain="hitra.no" />
+ <suffix domain="hjartdal.no" />
+ <suffix domain="hjelmeland.no" />
+ <suffix domain="hobol.no" />
+ <suffix domain="hobÞl.no" />
+ <suffix domain="hof.no" />
+ <suffix domain="hol.no" />
+ <suffix domain="hole.no" />
+ <suffix domain="holmestrand.no" />
+ <suffix domain="holtalen.no" />
+ <suffix domain="holtålen.no" />
+ <suffix domain="hornindal.no" />
+ <suffix domain="horten.no" />
+ <suffix domain="hurdal.no" />
+ <suffix domain="hurum.no" />
+ <suffix domain="hvaler.no" />
+ <suffix domain="hyllestad.no" />
+ <suffix domain="hagebostad.no" />
+ <suffix domain="hÊgebostad.no" />
+ <suffix domain="hoyanger.no" />
+ <suffix domain="hÞyanger.no" />
+ <suffix domain="hoylandet.no" />
+ <suffix domain="hÞylandet.no" />
+ <suffix domain="ha.no" />
+ <suffix domain="hå.no" />
+ <suffix domain="ibestad.no" />
+ <suffix domain="inderoy.no" />
+ <suffix domain="inderÞy.no" />
+ <suffix domain="iveland.no" />
+ <suffix domain="jevnaker.no" />
+ <suffix domain="jondal.no" />
+ <suffix domain="jolster.no" />
+ <suffix domain="jÞlster.no" />
+ <suffix domain="karasjok.no" />
+ <suffix domain="karasjohka.no" />
+ <suffix domain="kárášjohka.no" />
+ <suffix domain="karlsoy.no" />
+ <suffix domain="galsa.no" />
+ <suffix domain="gálsá.no" />
+ <suffix domain="karmoy.no" />
+ <suffix domain="karmÞy.no" />
+ <suffix domain="kautokeino.no" />
+ <suffix domain="guovdageaidnu.no" />
+ <suffix domain="klepp.no" />
+ <suffix domain="klabu.no" />
+ <suffix domain="klÊbu.no" />
+ <suffix domain="kongsberg.no" />
+ <suffix domain="kongsvinger.no" />
+ <suffix domain="kragero.no" />
+ <suffix domain="kragerÞ.no" />
+ <suffix domain="kristiansand.no" />
+ <suffix domain="kristiansund.no" />
+ <suffix domain="krodsherad.no" />
+ <suffix domain="krÞdsherad.no" />
+ <suffix domain="kvalsund.no" />
+ <suffix domain="rahkkeravju.no" />
+ <suffix domain="ráhkkerávju.no" />
+ <suffix domain="kvam.no" />
+ <suffix domain="kvinesdal.no" />
+ <suffix domain="kvinnherad.no" />
+ <suffix domain="kviteseid.no" />
+ <suffix domain="kvitsoy.no" />
+ <suffix domain="kvitsÞy.no" />
+ <suffix domain="kvafjord.no" />
+ <suffix domain="kvÊfjord.no" />
+ <suffix domain="giehtavuoatna.no" />
+ <suffix domain="kvanangen.no" />
+ <suffix domain="kvÊnangen.no" />
+ <suffix domain="navuotna.no" />
+ <suffix domain="návuotna.no" />
+ <suffix domain="kafjord.no" />
+ <suffix domain="kåfjord.no" />
+ <suffix domain="gaivuotna.no" />
+ <suffix domain="gáivuotna.no" />
+ <suffix domain="larvik.no" />
+ <suffix domain="lavangen.no" />
+ <suffix domain="lavagis.no" />
+ <suffix domain="loabat.no" />
+ <suffix domain="loabát.no" />
+ <suffix domain="lebesby.no" />
+ <suffix domain="davvesiida.no" />
+ <suffix domain="leikanger.no" />
+ <suffix domain="leirfjord.no" />
+ <suffix domain="leka.no" />
+ <suffix domain="leksvik.no" />
+ <suffix domain="lenvik.no" />
+ <suffix domain="leangaviika.no" />
+ <suffix domain="lea?gaviika.no" />
+ <suffix domain="lesja.no" />
+ <suffix domain="levanger.no" />
+ <suffix domain="lier.no" />
+ <suffix domain="lierne.no" />
+ <suffix domain="lillehammer.no" />
+ <suffix domain="lillesand.no" />
+ <suffix domain="lindesnes.no" />
+ <suffix domain="lindas.no" />
+ <suffix domain="lindås.no" />
+ <suffix domain="lom.no" />
+ <suffix domain="loppa.no" />
+ <suffix domain="lahppi.no" />
+ <suffix domain="láhppi.no" />
+ <suffix domain="lund.no" />
+ <suffix domain="lunner.no" />
+ <suffix domain="luroy.no" />
+ <suffix domain="lurÞy.no" />
+ <suffix domain="luster.no" />
+ <suffix domain="lyngdal.no" />
+ <suffix domain="lyngen.no" />
+ <suffix domain="ivgu.no" />
+ <suffix domain="lardal.no" />
+ <suffix domain="lerdal.no" />
+ <suffix domain="lÊrdal.no" />
+ <suffix domain="lodingen.no" />
+ <suffix domain="lÞdingen.no" />
+ <suffix domain="lorenskog.no" />
+ <suffix domain="lÞrenskog.no" />
+ <suffix domain="loten.no" />
+ <suffix domain="lÞten.no" />
+ <suffix domain="malvik.no" />
+ <suffix domain="masoy.no" />
+ <suffix domain="måsÞy.no" />
+ <suffix domain="muosat.no" />
+ <suffix domain="muosát.no" />
+ <suffix domain="mandal.no" />
+ <suffix domain="marker.no" />
+ <suffix domain="marnardal.no" />
+ <suffix domain="masfjorden.no" />
+ <suffix domain="meland.no" />
+ <suffix domain="meldal.no" />
+ <suffix domain="melhus.no" />
+ <suffix domain="meloy.no" />
+ <suffix domain="melÞy.no" />
+ <suffix domain="meraker.no" />
+ <suffix domain="meråker.no" />
+ <suffix domain="moareke.no" />
+ <suffix domain="moåreke.no" />
+ <suffix domain="midsund.no" />
+ <suffix domain="midtre-gauldal.no" />
+ <suffix domain="modalen.no" />
+ <suffix domain="modum.no" />
+ <suffix domain="molde.no" />
+ <suffix domain="moskenes.no" />
+ <suffix domain="moss.no" />
+ <suffix domain="mosvik.no" />
+ <suffix domain="malselv.no" />
+ <suffix domain="målselv.no" />
+ <suffix domain="malatvuopmi.no" />
+ <suffix domain="málatvuopmi.no" />
+ <suffix domain="namdalseid.no" />
+ <suffix domain="aejrie.no" />
+ <suffix domain="namsos.no" />
+ <suffix domain="namsskogan.no" />
+ <suffix domain="naamesjevuemie.no" />
+ <suffix domain="nååmesjevuemie.no" />
+ <suffix domain="laakesvuemie.no" />
+ <suffix domain="nannestad.no" />
+ <suffix domain="narvik.no" />
+ <suffix domain="narviika.no" />
+ <suffix domain="naustdal.no" />
+ <suffix domain="nedre-eiker.no" />
+ <suffix domain="nes.akershus.no" />
+ <suffix domain="nes.buskerud.no" />
+ <suffix domain="nesna.no" />
+ <suffix domain="nesodden.no" />
+ <suffix domain="nesseby.no" />
+ <suffix domain="unjarga.no" />
+ <suffix domain="unjárga.no" />
+ <suffix domain="nesset.no" />
+ <suffix domain="nissedal.no" />
+ <suffix domain="nittedal.no" />
+ <suffix domain="nord-aurdal.no" />
+ <suffix domain="nord-fron.no" />
+ <suffix domain="nord-odal.no" />
+ <suffix domain="norddal.no" />
+ <suffix domain="nordkapp.no" />
+ <suffix domain="davvenjarga.no" />
+ <suffix domain="davvenjárga.no" />
+ <suffix domain="nordre-land.no" />
+ <suffix domain="nordreisa.no" />
+ <suffix domain="raisa.no" />
+ <suffix domain="ráisa.no" />
+ <suffix domain="nore-og-uvdal.no" />
+ <suffix domain="notodden.no" />
+ <suffix domain="naroy.no" />
+ <suffix domain="nÊrÞy.no" />
+ <suffix domain="notteroy.no" />
+ <suffix domain="nÞtterÞy.no" />
+ <suffix domain="odda.no" />
+ <suffix domain="oksnes.no" />
+ <suffix domain="`Þksnes.no" />
+ <suffix domain="oppdal.no" />
+ <suffix domain="oppegard.no" />
+ <suffix domain="oppegård.no" />
+ <suffix domain="orkdal.no" />
+ <suffix domain="orland.no" />
+ <suffix domain="Þrland.no" />
+ <suffix domain="orskog.no" />
+ <suffix domain="Þrskog.no" />
+ <suffix domain="orsta.no" />
+ <suffix domain="Þrsta.no" />
+ <suffix domain="os.hedmark.no" />
+ <suffix domain="os.hordaland.no" />
+ <suffix domain="osen.no" />
+ <suffix domain="osteroy.no" />
+ <suffix domain="osterÞy.no" />
+ <suffix domain="ostre-toten.no" />
+ <suffix domain="Þstre-toten.no" />
+ <suffix domain="overhalla.no" />
+ <suffix domain="ovre-eiker.no" />
+ <suffix domain="Þvre-eiker.no" />
+ <suffix domain="oyer.no" />
+ <suffix domain="Þyer.no" />
+ <suffix domain="oygarden.no" />
+ <suffix domain="Þygarden.no" />
+ <suffix domain="oystre-slidre.no" />
+ <suffix domain="Þystre-slidre.no" />
+ <suffix domain="porsanger.no" />
+ <suffix domain="porsangu.no" />
+ <suffix domain="porsáŋgu.no" />
+ <suffix domain="porsgrunn.no" />
+ <suffix domain="radoy.no" />
+ <suffix domain="radÞy.no" />
+ <suffix domain="rakkestad.no" />
+ <suffix domain="rana.no" />
+ <suffix domain="ruovat.no" />
+ <suffix domain="randaberg.no" />
+ <suffix domain="rauma.no" />
+ <suffix domain="rendalen.no" />
+ <suffix domain="rennebu.no" />
+ <suffix domain="rennesoy.no" />
+ <suffix domain="rennesÞy.no" />
+ <suffix domain="rindal.no" />
+ <suffix domain="ringebu.no" />
+ <suffix domain="ringerike.no" />
+ <suffix domain="ringsaker.no" />
+ <suffix domain="rissa.no" />
+ <suffix domain="risor.no" />
+ <suffix domain="risÞr.no" />
+ <suffix domain="roan.no" />
+ <suffix domain="rollag.no" />
+ <suffix domain="rygge.no" />
+ <suffix domain="ralingen.no" />
+ <suffix domain="rÊlingen.no" />
+ <suffix domain="rodoy.no" />
+ <suffix domain="rÞdÞy.no" />
+ <suffix domain="romskog.no" />
+ <suffix domain="rÞmskog.no" />
+ <suffix domain="roros.no" />
+ <suffix domain="rÞros.no" />
+ <suffix domain="rost.no" />
+ <suffix domain="rÞst.no" />
+ <suffix domain="royken.no" />
+ <suffix domain="rÞyken.no" />
+ <suffix domain="royrvik.no" />
+ <suffix domain="rÞyrvik.no" />
+ <suffix domain="rade.no" />
+ <suffix domain="råde.no" />
+ <suffix domain="salangen.no" />
+ <suffix domain="siellak.no" />
+ <suffix domain="saltdal.no" />
+ <suffix domain="sálát.no" />
+ <suffix domain="sálat.no" />
+ <suffix domain="samnanger.no" />
+ <suffix domain="sande.more-og-romsdal.no" />
+ <suffix domain="sande.mÞre-og-romsdal.no" />
+ <suffix domain="sande.vestfold.no" />
+ <suffix domain="sandefjord.no" />
+ <suffix domain="sandnes.no" />
+ <suffix domain="sandoy.no" />
+ <suffix domain="sandÞy.no" />
+ <suffix domain="sarpsborg.no" />
+ <suffix domain="sauda.no" />
+ <suffix domain="sauherad.no" />
+ <suffix domain="sel.no" />
+ <suffix domain="selbu.no" />
+ <suffix domain="selje.no" />
+ <suffix domain="seljord.no" />
+ <suffix domain="sigdal.no" />
+ <suffix domain="siljan.no" />
+ <suffix domain="sirdal.no" />
+ <suffix domain="skaun.no" />
+ <suffix domain="skedsmo.no" />
+ <suffix domain="ski.no" />
+ <suffix domain="skien.no" />
+ <suffix domain="skiptvet.no" />
+ <suffix domain="skjervoy.no" />
+ <suffix domain="skjervÞy.no" />
+ <suffix domain="skierva.no" />
+ <suffix domain="skiervá.no" />
+ <suffix domain="skjak.no" />
+ <suffix domain="skjåk.no" />
+ <suffix domain="skodje.no" />
+ <suffix domain="skanland.no" />
+ <suffix domain="skånland.no" />
+ <suffix domain="skanit.no" />
+ <suffix domain="skánit.no" />
+ <suffix domain="smola.no" />
+ <suffix domain="smÞla.no" />
+ <suffix domain="snillfjord.no" />
+ <suffix domain="snasa.no" />
+ <suffix domain="snåsa.no" />
+ <suffix domain="snoasa.no" />
+ <suffix domain="snaase.no" />
+ <suffix domain="snåase.no" />
+ <suffix domain="sogndal.no" />
+ <suffix domain="sokndal.no" />
+ <suffix domain="sola.no" />
+ <suffix domain="solund.no" />
+ <suffix domain="songdalen.no" />
+ <suffix domain="sortland.no" />
+ <suffix domain="spydeberg.no" />
+ <suffix domain="stange.no" />
+ <suffix domain="stavanger.no" />
+ <suffix domain="steigen.no" />
+ <suffix domain="steinkjer.no" />
+ <suffix domain="stjordal.no" />
+ <suffix domain="stjÞrdal.no" />
+ <suffix domain="stokke.no" />
+ <suffix domain="stor-elvdal.no" />
+ <suffix domain="stord.no" />
+ <suffix domain="stordal.no" />
+ <suffix domain="storfjord.no" />
+ <suffix domain="omasvuotna.no" />
+ <suffix domain="strand.no" />
+ <suffix domain="stranda.no" />
+ <suffix domain="stryn.no" />
+ <suffix domain="sula.no" />
+ <suffix domain="suldal.no" />
+ <suffix domain="sund.no" />
+ <suffix domain="sunndal.no" />
+ <suffix domain="surnadal.no" />
+ <suffix domain="sveio.no" />
+ <suffix domain="svelvik.no" />
+ <suffix domain="sykkylven.no" />
+ <suffix domain="sogne.no" />
+ <suffix domain="sÞgne.no" />
+ <suffix domain="somna.no" />
+ <suffix domain="sÞmna.no" />
+ <suffix domain="sondre-land.no" />
+ <suffix domain="sÞndre-land.no" />
+ <suffix domain="sor-aurdal.no" />
+ <suffix domain="sÞr-aurdal.no" />
+ <suffix domain="sor-fron.no" />
+ <suffix domain="sÞr-fron.no" />
+ <suffix domain="sor-odal.no" />
+ <suffix domain="sÞr-odal.no" />
+ <suffix domain="sor-varanger.no" />
+ <suffix domain="sÞr-varanger.no" />
+ <suffix domain="matta-varjjat.no" />
+ <suffix domain="mátta-várjjat.no" />
+ <suffix domain="sorfold.no" />
+ <suffix domain="sÞrfold.no" />
+ <suffix domain="sorreisa.no" />
+ <suffix domain="sÞrreisa.no" />
+ <suffix domain="sorum.no" />
+ <suffix domain="sÞrum.no" />
+ <suffix domain="tana.no" />
+ <suffix domain="deatnu.no" />
+ <suffix domain="time.no" />
+ <suffix domain="tingvoll.no" />
+ <suffix domain="tinn.no" />
+ <suffix domain="tjeldsund.no" />
+ <suffix domain="dielddanuorri.no" />
+ <suffix domain="tjome.no" />
+ <suffix domain="tjÞme.no" />
+ <suffix domain="tokke.no" />
+ <suffix domain="tolga.no" />
+ <suffix domain="torsken.no" />
+ <suffix domain="tranoy.no" />
+ <suffix domain="tranÞy.no" />
+ <suffix domain="tromso.no" />
+ <suffix domain="tromsÞ.no" />
+ <suffix domain="tromsa.no" />
+ <suffix domain="romsa.no" />
+ <suffix domain="trondheim.no" />
+ <suffix domain="troandin.no" />
+ <suffix domain="trysil.no" />
+ <suffix domain="trana.no" />
+ <suffix domain="trÊna.no" />
+ <suffix domain="trogstad.no" />
+ <suffix domain="trÞgstad.no" />
+ <suffix domain="tvedestrand.no" />
+ <suffix domain="tydal.no" />
+ <suffix domain="tynset.no" />
+ <suffix domain="tysfjord.no" />
+ <suffix domain="divtasvuodna.no" />
+ <suffix domain="divttasvuotna.no" />
+ <suffix domain="tysnes.no" />
+ <suffix domain="tysvar.no" />
+ <suffix domain="tysvÊr.no" />
+ <suffix domain="tonsberg.no" />
+ <suffix domain="tÞnsberg.no" />
+ <suffix domain="ullensaker.no" />
+ <suffix domain="ullensvang.no" />
+ <suffix domain="ulvik.no" />
+ <suffix domain="utsira.no" />
+ <suffix domain="vadso.no" />
+ <suffix domain="vadsÞ.no" />
+ <suffix domain="cahcesuolo.no" />
+ <suffix domain="cáhcesuolo.no" />
+ <suffix domain="vaksdal.no" />
+ <suffix domain="valle.no" />
+ <suffix domain="vang.no" />
+ <suffix domain="vanylven.no" />
+ <suffix domain="vardo.no" />
+ <suffix domain="vardÞ.no" />
+ <suffix domain="varggat.no" />
+ <suffix domain="várggát.no" />
+ <suffix domain="vefsn.no" />
+ <suffix domain="vaapste.no" />
+ <suffix domain="vega.no" />
+ <suffix domain="vegarshei.no" />
+ <suffix domain="vegårshei.no" />
+ <suffix domain="vennesla.no" />
+ <suffix domain="verdal.no" />
+ <suffix domain="verran.no" />
+ <suffix domain="vestby.no" />
+ <suffix domain="vestnes.no" />
+ <suffix domain="vestre-slidre.no" />
+ <suffix domain="vestre-toten.no" />
+ <suffix domain="vestvagoy.no" />
+ <suffix domain="vestvågÞy.no" />
+ <suffix domain="vevelstad.no" />
+ <suffix domain="vik.no" />
+ <suffix domain="vikna.no" />
+ <suffix domain="vindafjord.no" />
+ <suffix domain="volda.no" />
+ <suffix domain="voss.no" />
+ <suffix domain="varoy.no" />
+ <suffix domain="vÊrÞy.no" />
+ <suffix domain="vagan.no" />
+ <suffix domain="vågan.no" />
+ <suffix domain="voagat.no" />
+ <suffix domain="vagsoy.no" />
+ <suffix domain="vågsÞy.no" />
+ <suffix domain="vaga.no" />
+ <suffix domain="vågå.no" />
+ <suffix domain="valer.ostfold.no" />
+ <suffix domain="våler.Þstfold.no" />
+ <suffix domain="valer.hedmark.no" />
+ <suffix domain="våler.hedmark.no" />
+
+ <!-- np : http://www.mos.com.np/register.html-- >
+
+ <!-- nr : http://cenpac.net.nr/dns/index.html-- >
+ <suffix domain="biz.nr" />
+ <suffix domain="info.nr" />
+ <suffix domain="gov.nr" />
+ <suffix domain="edu.nr" />
+ <suffix domain="org.nr" />
+ <suffix domain="net.nr" />
+ <suffix domain="com.nr" />
+
+ <!-- nu : http://en.wikipedia.org/wiki/.nu-- >
+
+ <!-- nz : http://en.wikipedia.org/wiki/.nz-- >
+
+ <!-- om : http://en.wikipedia.org/wiki/.om-- >
+
+ <!-- org : http://en.wikipedia.org/wiki/.og-- >
+
+ <!-- pa : http://www.nic.pa/-- >
+
+ <!-- pe : http://www.nic.pe/normas-proced-i.htm-- >
+
+ <!-- pf : http://www.gobin.info/domainname/formulaire-pf.pdf-- >
+ <suffix domain="com.pf" />
+ <suffix domain="org.pf" />
+ <suffix domain="edu.pf" />
+
+ <!-- pg : http://en.wikipedia.org/wiki/.pg-- >
+
+ <!-- ph : http://www.domains.ph/FAQ2.asp-- >
+ <!-- list of 2nd level tlds ?-->
+ <suffix domain="com.ph" />
+ <suffix domain="net.ph" />
+ <suffix domain="org.ph" />
+ <suffix domain="gov.ph" />
+ <suffix domain="edu.ph" />
+ <suffix domain="ngo.ph" />
+ <suffix domain="mil.ph" />
+
+ <!-- pk : http://pk5.pknic.net.pk/pk5/msgNamepk.PK-- >
+ <suffix domain="com.pk" />
+ <suffix domain="net.pk" />
+ <suffix domain="edu.pk" />
+ <suffix domain="org.pk" />
+ <suffix domain="fam.pk" />
+ <suffix domain="biz.pk" />
+ <suffix domain="web.pk" />
+ <suffix domain="gov.pk" />
+ <suffix domain="gob.pk" />
+ <suffix domain="gok.pk" />
+ <suffix domain="gon.pk" />
+ <suffix domain="gop.pk" />
+ <suffix domain="gos.pk" />
+ <suffix domain="goa.pk" />
+ <suffix domain="info.pk" />
+
+ <!-- pl : http://www.dns.pl/english/-- >
+ <!-- NASK functional domains (nask.pl / dns.pl) : http://www.dns.pl/english/dns-funk.html-- >
+ <suffix domain="aid.pl" />
+ <suffix domain="agro.pl" />
+ <suffix domain="atm.pl" />
+ <suffix domain="auto.pl" />
+ <suffix domain="biz.pl" />
+ <suffix domain="com.pl" />
+ <suffix domain="edu.pl" />
+ <suffix domain="gmina.pl" />
+ <suffix domain="gsm.pl" />
+ <suffix domain="info.pl" />
+ <suffix domain="mail.pl" />
+ <suffix domain="miasta.pl" />
+ <suffix domain="media.pl" />
+ <suffix domain="mil.pl" />
+ <suffix domain="net.pl" />
+ <suffix domain="nieruchomosci.pl" />
+ <suffix domain="nom.pl" />
+ <suffix domain="org.pl" />
+ <suffix domain="pc.pl" />
+ <suffix domain="powiat.pl" />
+ <suffix domain="priv.pl" />
+ <suffix domain="realestate.pl" />
+ <suffix domain="rel.pl" />
+ <suffix domain="sex.pl" />
+ <suffix domain="shop.pl" />
+ <suffix domain="sklep.pl" />
+ <suffix domain="sos.pl" />
+ <suffix domain="szkola.pl" />
+ <suffix domain="targi.pl" />
+ <suffix domain="tm.pl" />
+ <suffix domain="tourism.pl" />
+ <suffix domain="travel.pl" />
+ <suffix domain="turystyka.pl" />
+ <!-- ICM functional domains (icm.edu.pl)-->
+ <suffix domain="6bone.pl" />
+ <suffix domain="art.pl" />
+ <suffix domain="mbone.pl" />
+ <!-- Government domains (administred by ippt.gov.pl)-->
+ <suffix domain="gov.pl" />
+ <suffix domain="uw.gov.pl" />
+ <suffix domain="um.gov.pl" />
+ <suffix domain="ug.gov.pl" />
+ <suffix domain="upow.gov.pl" />
+ <suffix domain="starostwo.gov.pl" />
+ <suffix domain="so.gov.pl" />
+ <suffix domain="sr.gov.pl" />
+ <suffix domain="po.gov.pl" />
+ <suffix domain="pa.gov.pl" />
+ <!-- other functional domains-->
+ <suffix domain="med.pl" />
+ <suffix domain="ngo.pl" />
+ <suffix domain="irc.pl" />
+ <suffix domain="usenet.pl" />
+ <!-- NASK geographical domains : http://www.dns.pl/english/dns-regiony.html-- >
+ <suffix domain="augustow.pl" />
+ <suffix domain="babia-gora.pl" />
+ <suffix domain="bedzin.pl" />
+ <suffix domain="beskidy.pl" />
+ <suffix domain="bialowieza.pl" />
+ <suffix domain="bialystok.pl" />
+ <suffix domain="bielawa.pl" />
+ <suffix domain="bieszczady.pl" />
+ <suffix domain="boleslawiec.pl" />
+ <suffix domain="bydgoszcz.pl" />
+ <suffix domain="bytom.pl" />
+ <suffix domain="cieszyn.pl" />
+ <suffix domain="czeladz.pl" />
+ <suffix domain="czest.pl" />
+ <suffix domain="dlugoleka.pl" />
+ <suffix domain="elblag.pl" />
+ <suffix domain="elk.pl" />
+ <suffix domain="glogow.pl" />
+ <suffix domain="gniezno.pl" />
+ <suffix domain="gorlice.pl" />
+ <suffix domain="grajewo.pl" />
+ <suffix domain="ilawa.pl" />
+ <suffix domain="jaworzno.pl" />
+ <suffix domain="jelenia-gora.pl" />
+ <suffix domain="jgora.pl" />
+ <suffix domain="kalisz.pl" />
+ <suffix domain="kazimierz-dolny.pl" />
+ <suffix domain="karpacz.pl" />
+ <suffix domain="kartuzy.pl" />
+ <suffix domain="kaszuby.pl" />
+ <suffix domain="katowice.pl" />
+ <suffix domain="kepno.pl" />
+ <suffix domain="ketrzyn.pl" />
+ <suffix domain="klodzko.pl" />
+ <suffix domain="kobierzyce.pl" />
+ <suffix domain="kolobrzeg.pl" />
+ <suffix domain="konin.pl" />
+ <suffix domain="konskowola.pl" />
+ <suffix domain="kutno.pl" />
+ <suffix domain="lapy.pl" />
+ <suffix domain="lebork.pl" />
+ <suffix domain="legnica.pl" />
+ <suffix domain="lezajsk.pl" />
+ <suffix domain="limanowa.pl" />
+ <suffix domain="lomza.pl" />
+ <suffix domain="lowicz.pl" />
+ <suffix domain="lubin.pl" />
+ <suffix domain="lukow.pl" />
+ <suffix domain="malbork.pl" />
+ <suffix domain="malopolska.pl" />
+ <suffix domain="mazowsze.pl" />
+ <suffix domain="mazury.pl" />
+ <suffix domain="mielec.pl" />
+ <suffix domain="mielno.pl" />
+ <suffix domain="mragowo.pl" />
+ <suffix domain="naklo.pl" />
+ <suffix domain="nowaruda.pl" />
+ <suffix domain="nysa.pl" />
+ <suffix domain="olawa.pl" />
+ <suffix domain="olecko.pl" />
+ <suffix domain="olkusz.pl" />
+ <suffix domain="olsztyn.pl" />
+ <suffix domain="opoczno.pl" />
+ <suffix domain="opole.pl" />
+ <suffix domain="ostroda.pl" />
+ <suffix domain="ostroleka.pl" />
+ <suffix domain="ostrowiec.pl" />
+ <suffix domain="ostrowwlkp.pl" />
+ <suffix domain="pila.pl" />
+ <suffix domain="pisz.pl" />
+ <suffix domain="podhale.pl" />
+ <suffix domain="podlasie.pl" />
+ <suffix domain="polkowice.pl" />
+ <suffix domain="pomorze.pl" />
+ <suffix domain="pomorskie.pl" />
+ <suffix domain="prochowice.pl" />
+ <suffix domain="pruszkow.pl" />
+ <suffix domain="przeworsk.pl" />
+ <suffix domain="pulawy.pl" />
+ <suffix domain="radom.pl" />
+ <suffix domain="rawa-maz.pl" />
+ <suffix domain="rybnik.pl" />
+ <suffix domain="rzeszow.pl" />
+ <suffix domain="sanok.pl" />
+ <suffix domain="sejny.pl" />
+ <suffix domain="slask.pl" />
+ <suffix domain="slupsk.pl" />
+ <suffix domain="sosnowiec.pl" />
+ <suffix domain="stalowa-wola.pl" />
+ <suffix domain="skoczow.pl" />
+ <suffix domain="starachowice.pl" />
+ <suffix domain="stargard.pl" />
+ <suffix domain="suwalki.pl" />
+ <suffix domain="swidnica.pl" />
+ <suffix domain="swiebodzin.pl" />
+ <suffix domain="swinoujscie.pl" />
+ <suffix domain="szczecin.pl" />
+ <suffix domain="szczytno.pl" />
+ <suffix domain="tarnobrzeg.pl" />
+ <suffix domain="tgory.pl" />
+ <suffix domain="turek.pl" />
+ <suffix domain="tychy.pl" />
+ <suffix domain="ustka.pl" />
+ <suffix domain="walbrzych.pl" />
+ <suffix domain="warmia.pl" />
+ <suffix domain="warszawa.pl" />
+ <suffix domain="waw.pl" />
+ <suffix domain="wegrow.pl" />
+ <suffix domain="wielun.pl" />
+ <suffix domain="wlocl.pl" />
+ <suffix domain="wloclawek.pl" />
+ <suffix domain="wodzislaw.pl" />
+ <suffix domain="wolomin.pl" />
+ <suffix domain="wroclaw.pl" />
+ <suffix domain="zachpomor.pl" />
+ <suffix domain="zagan.pl" />
+ <suffix domain="zarow.pl" />
+ <suffix domain="zgora.pl" />
+ <suffix domain="zgorzelec.pl" />
+ <!-- TASK geographical domains (www.task.gda.pl/uslugi/dns)-- >
+ <suffix domain="gda.pl" />
+ <suffix domain="gdansk.pl" />
+ <suffix domain="gdynia.pl" />
+ <suffix domain="sopot.pl" />
+ <!-- other geographical domains-->
+ <suffix domain="gliwice.pl" />
+ <suffix domain="krakow.pl" />
+ <suffix domain="poznan.pl" />
+ <suffix domain="wroc.pl" />
+ <suffix domain="zakopane.pl" />
+
+ <!-- pn : http://www.government.pn/PnRegistry/policies.htm-- >
+ <suffix domain="gov.pn" />
+ <suffix domain="co.pn" />
+ <suffix domain="org.pn" />
+ <suffix domain="edu.pn" />
+ <suffix domain="net.pn" />
+
+ <!-- pr : http://www.nic.pr/index.asp?f=1-- >
+ <suffix domain="com.pr" />
+ <suffix domain="net.pr" />
+ <suffix domain="org.pr" />
+ <suffix domain="gov.pr" />
+ <suffix domain="edu.pr" />
+ <suffix domain="isla.pr" />
+ <suffix domain="pro.pr" />
+ <suffix domain="biz.pr" />
+ <suffix domain="info.pr" />
+ <suffix domain="name.pr" />
+ <!-- these aren't mentioned on nic.pr, but on http://en.wikipedia.org/wiki/.pr-- >
+ <suffix domain="est.pr" />
+ <suffix domain="prof.pr" />
+ <suffix domain="ac.pr" />
+
+ <!-- pro : http://www.nic.pro/support_faq.htm-- >
+ <suffix domain="aca.pro" />
+ <suffix domain="bar.pro" />
+ <suffix domain="cpa.pro" />
+ <suffix domain="jur.pro" />
+ <suffix domain="law.pro" />
+ <suffix domain="med.pro" />
+ <suffix domain="eng.pro" />
+
+ <!-- ps : http://en.wikipedia.org/wiki/.ps-- >
+ <!-- list of 2nd level tlds ?-->
+ <suffix domain="edu.ps" />
+ <suffix domain="gov.ps" />
+ <suffix domain="sec.ps" />
+ <suffix domain="plo.ps" />
+ <suffix domain="com.ps" />
+ <suffix domain="org.ps" />
+ <suffix domain="net.ps" />
+
+ <!-- pt : http://online.dns.pt/dns/start_dns-- >
+ <suffix domain="net.pt" />
+ <suffix domain="gov.pt" />
+ <suffix domain="org.pt" />
+ <suffix domain="edu.pt" />
+ <suffix domain="int.pt" />
+ <suffix domain="publ.pt" />
+ <suffix domain="com.pt" />
+ <suffix domain="nome.pt" />
+
+ <!-- pw : http://en.wikipedia.org/wiki/.pw-- >
+
+ <!-- py : http://www.nic.py/faq_a.html#faq_b-- >
+
+ <!-- qa : http://www.qatar.net.qa/services/virtual.htm-- >
+
+ <!-- re : http://www.afnic.re/obtenir/chartes/nommage-re/annexe-descriptifs-- >
+ <suffix domain="com.re" />
+ <suffix domain="asso.re" />
+ <suffix domain="nom.re" />
+
+ <!-- ro : http://www.rotld.ro/-- >
+ <suffix domain="com.ro" />
+ <suffix domain="org.ro" />
+ <suffix domain="tm.ro" />
+ <suffix domain="nt.ro" />
+ <suffix domain="nom.ro" />
+ <suffix domain="info.ro" />
+ <suffix domain="rec.ro" />
+ <suffix domain="arts.ro" />
+ <suffix domain="firm.ro" />
+ <suffix domain="store.ro" />
+ <suffix domain="www.ro " />
+
+ <!-- ru : http://en.wikipedia.org/wiki/.ru-- >
+ <suffix domain="com.ru" />
+ <suffix domain="net.ru" />
+ <suffix domain="org.ru" />
+ <suffix domain="pp.ru" />
+ <suffix domain="int.ru" />
+ <!-- there should be geo-names like msk.ru, but I didn't find a list-->
+
+ <!-- rw : http://www.nic.rw/cgi-bin/policy.pl-- >
+ <suffix domain="gov.rw" />
+ <suffix domain="net.rw" />
+ <suffix domain="edu.rw" />
+ <suffix domain="ac.rw" />
+ <suffix domain="com.rw" />
+ <suffix domain="co.rw" />
+ <suffix domain="int.rw" />
+ <suffix domain="mil.rw" />
+ <suffix domain="gouv.rw" />
+
+ <!-- sa : http://www.saudinic.net.sa/page.php?page=1&lang=1-- >
+
+ <!-- sb : http://www.sbnic.net.sb/-- >
+
+ <!-- sc : http://www.nic.sc/-- >
+ <suffix domain="com.sc" />
+ <suffix domain="gov.sc" />
+ <suffix domain="net.sc" />
+ <suffix domain="org.sc" />
+ <suffix domain="edu.sc" />
+
+ <!-- sd : http://www.isoc.sd/sudanic.isoc.sd/billing_pricing.htm-- >
+ <suffix domain="com.sd" />
+ <suffix domain="net.sd" />
+ <suffix domain="org.sd" />
+ <suffix domain="edu.sd" />
+ <suffix domain="med.sd" />
+ <suffix domain="tv.sd" />
+ <suffix domain="gov.sd" />
+ <suffix domain="info.sd" />
+
+ <!-- se : http://en.wikipedia.org/wiki/.se-- >
+ <suffix domain="org.se" />
+ <suffix domain="pp.se" />
+ <suffix domain="tm.se" />
+ <suffix domain="parti.se" />
+ <suffix domain="press.se" />
+ <suffix domain="mil.se" />
+ <!-- se geographical names-->
+ <suffix domain="ab.se" />
+ <suffix domain="c.se" />
+ <suffix domain="d.se" />
+ <suffix domain="e.se" />
+ <suffix domain="f.se" />
+ <suffix domain="g.se" />
+ <suffix domain="h.se" />
+ <suffix domain="i.se" />
+ <suffix domain="k.se" />
+ <suffix domain="m.se" />
+ <suffix domain="n.se" />
+ <suffix domain="o.se" />
+ <suffix domain="s.se" />
+ <suffix domain="t.se" />
+ <suffix domain="u.se" />
+ <suffix domain="w.se" />
+ <suffix domain="x.se" />
+ <suffix domain="y.se" />
+ <suffix domain="z.se" />
+ <suffix domain="ac.se" />
+ <suffix domain="bd.se" />
+
+ <!-- sg : http://www.nic.net.sg/sub_policies_agreement/2ld.html-- >
+ <suffix domain="com.sg" />
+ <suffix domain="net.sg" />
+ <suffix domain="org.sg" />
+ <suffix domain="gov.sg" />
+ <suffix domain="edu.sg" />
+ <suffix domain="per.sg" />
+
+ <!-- sh : http://www.nic.sh/rules.html-- >
+ <!-- list of 2nd level domains ?-->
+
+ <!-- si : http://en.wikipedia.org/wiki/.si-- >
+
+ <!-- sk : http://en.wikipedia.org/wiki/.sk-- >
+
+ <!-- sl : http://en.wikipedia.org/wiki/.sl-- >
+ <!-- list of 2nd level domains ?-->
+
+ <!-- sm : http://en.wikipedia.org/wiki/.sm-- >
+
+ <!-- sn : http://en.wikipedia.org/wiki/.sn-- >
+ <!-- list of 2nd level domains ?-->
+
+ <!-- sr : http://en.wikipedia.org/wiki/.sr-- >
+
+ <!-- st : http://www.nic.st/html/policyrules/-- >
+
+ <!-- su : http://en.wikipedia.org/wiki/.su-- >
+
+ <!-- sv : http://www.svnet.org.sv/svpolicy.html-- >
+
+ <!-- sy : http://www.gobin.info/domainname/sy.doc-- >
+
+ <!-- sz : http://en.wikipedia.org/wiki/.sz-- >
+ <!-- list of 2nd level domains ?-->
+
+ <!-- tc : http://en.wikipedia.org/wiki/.tc-- >
+
+ <!-- td : http://en.wikipedia.org/wiki/.td-- >
+
+ <!-- tf : http://en.wikipedia.org/wiki/.tf-- >
+
+ <!-- tg : http://en.wikipedia.org/wiki/.tg-- >
+ <!-- list of 2nd level domains ?-->
+
+ <!-- th : http://en.wikipedia.org/wiki/.th-- >
+
+ <!-- tj : http://www.nic.tj/policy.htm-- >
+ <suffix domain="ac.tj" />
+ <suffix domain="biz.tj" />
+ <suffix domain="com.tj" />
+ <suffix domain="co.tj" />
+ <suffix domain="edu.tj" />
+ <suffix domain="int.tj" />
+ <suffix domain="name.tj" />
+ <suffix domain="net.tj" />
+ <suffix domain="org.tj" />
+ <suffix domain="web.tj" />
+ <suffix domain="gov.tj" />
+ <suffix domain="go.tj" />
+ <suffix domain="mil.tj" />
+
+ <!-- tk : http://en.wikipedia.org/wiki/.tk-- >
+
+ <!-- tl : http://en.wikipedia.org/wiki/.tl-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- tm : http://www.nic.tm/rules.html-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- tn : http://en.wikipedia.org/wiki/.tn-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- to : http://en.wikipedia.org/wiki/.to-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- tr : http://en.wikipedia.org/wiki/.tr-- >
+
+ <!-- travel : http://en.wikipedia.org/wiki/.travel-- >
+
+ <!-- tt : http://www.nic.tt/-- >
+ <suffix domain="co.tt" />
+ <suffix domain="com.tt" />
+ <suffix domain="org.tt" />
+ <suffix domain="net.tt" />
+ <suffix domain="biz.tt" />
+ <suffix domain="info.tt" />
+ <suffix domain="pro.tt" />
+ <suffix domain="int.tt" />
+ <suffix domain="coop.tt" />
+ <suffix domain="jobs.tt" />
+ <suffix domain="mobi.tt" />
+ <suffix domain="travel.tt" />
+ <suffix domain="museum.tt" />
+ <suffix domain="aero.tt" />
+ <suffix domain="name.tt" />
+ <suffix domain="gov.tt" />
+ <suffix domain="edu.tt" />
+
+ <!-- tv : http://en.wikipedia.org/wiki/.tv-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- tw : http://en.wikipedia.org/wiki/.tw-- >
+ <suffix domain="edu.tw" />
+ <suffix domain="gov.tw" />
+ <suffix domain="mil.tw" />
+ <suffix domain="com.tw" />
+ <suffix domain="net.tw" />
+ <suffix domain="org.tw" />
+ <suffix domain="idv.tw" />
+ <suffix domain="game.tw" />
+ <suffix domain="ebiz.tw" />
+ <suffix domain="club.tw" />
+ <suffix domain="網路.tw" />
+ <suffix domain="組織.tw" />
+ <suffix domain="商æ¥Â.tw" />
+
+ <!-- tz : http://en.wikipedia.org/wiki/.tz-- >
+
+ <!-- ua : http://www.nic.net.ua/-- >
+ <suffix domain="com.ua" />
+ <suffix domain="edu.ua" />
+ <suffix domain="gov.ua" />
+ <suffix domain="net.ua" />
+ <suffix domain="org.ua" />
+ <!-- ua geo-names-->
+ <suffix domain="cherkassy.ua" />
+ <suffix domain="chernigov.ua" />
+ <suffix domain="chernovtsy.ua" />
+ <suffix domain="ck.ua" />
+ <suffix domain="cn.ua" />
+ <suffix domain="crimea.ua" />
+ <suffix domain="cv.ua" />
+ <suffix domain="dn.ua" />
+ <suffix domain="dnepropetrovsk.ua" />
+ <suffix domain="donetsk.ua" />
+ <suffix domain="dp.ua" />
+ <suffix domain="if.ua" />
+ <suffix domain="ivano-frankivsk.ua" />
+ <suffix domain="kh.ua" />
+ <suffix domain="kharkov.ua" />
+ <suffix domain="kherson.ua" />
+ <suffix domain="kiev.ua" />
+ <suffix domain="kirovograd.ua" />
+ <suffix domain="km.ua" />
+ <suffix domain="kr.ua" />
+ <suffix domain="ks.ua" />
+ <suffix domain="lg.ua" />
+ <suffix domain="lugansk.ua" />
+ <suffix domain="lutsk.ua" />
+ <suffix domain="lviv.ua" />
+ <suffix domain="mk.ua" />
+ <suffix domain="nikolaev.ua" />
+ <suffix domain="od.ua" />
+ <suffix domain="odessa.ua" />
+ <suffix domain="pl.ua" />
+ <suffix domain="poltava.ua" />
+ <suffix domain="rovno.ua" />
+ <suffix domain="rv.ua" />
+ <suffix domain="sebastopol.ua" />
+ <suffix domain="sumy.ua" />
+ <suffix domain="te.ua" />
+ <suffix domain="ternopil.ua" />
+ <suffix domain="vinnica.ua" />
+ <suffix domain="vn.ua" />
+ <suffix domain="zaporizhzhe.ua" />
+ <suffix domain="zp.ua" />
+ <suffix domain="uz.ua" />
+ <suffix domain="uzhgorod.ua" />
+ <suffix domain="zhitomir.ua" />
+ <suffix domain="zt.ua" />
+
+ <!-- ug : http://www.registry.co.ug/-- >
+ <suffix domain="co.ug" />
+ <suffix domain="ac.ug" />
+ <suffix domain="sc.ug" />
+ <suffix domain="go.ug" />
+ <suffix domain="ne.ug" />
+ <suffix domain="or.ug" />
+
+ <!-- uk : http://en.wikipedia.org/wiki/.uk-- >
+ <suffix domain="sch.uk" />
+ <suffix domain="bl.uk" />
+ <suffix domain="british-library.uk" />
+ <suffix domain="icnet.uk" />
+ <suffix domain="jet.uk" />
+ <suffix domain="nel.uk" />
+ <suffix domain="nls.uk" />
+ <suffix domain="national-library-scotland.uk" />
+ <suffix domain="parliament.uk" />
+
+ <!-- us : http://en.wikipedia.org/wiki/.us-- >
+ <suffix domain="dni.us" />
+ <suffix domain="fed.us" />
+ <suffix domain="isa.us" />
+ <suffix domain="kids.us" />
+ <suffix domain="nsn.us" />
+ <!-- us geographic names-->
+ <suffix domain="ak.us" />
+ <suffix domain="al.us" />
+ <suffix domain="ar.us" />
+ <suffix domain="az.us" />
+ <suffix domain="ca.us" />
+ <suffix domain="co.us" />
+ <suffix domain="ct.us" />
+ <suffix domain="dc.us" />
+ <suffix domain="de.us" />
+ <suffix domain="fl.us" />
+ <suffix domain="ga.us" />
+ <suffix domain="hi.us" />
+ <suffix domain="ia.us" />
+ <suffix domain="id.us" />
+ <suffix domain="il.us" />
+ <suffix domain="in.us" />
+ <suffix domain="ks.us" />
+ <suffix domain="ky.us" />
+ <suffix domain="la.us" />
+ <suffix domain="ma.us" />
+ <suffix domain="md.us" />
+ <suffix domain="me.us" />
+ <suffix domain="mi.us" />
+ <suffix domain="mn.us" />
+ <suffix domain="mo.us" />
+ <suffix domain="ms.us" />
+ <suffix domain="mt.us" />
+ <suffix domain="nc.us" />
+ <suffix domain="nd.us" />
+ <suffix domain="ne.us" />
+ <suffix domain="nh.us" />
+ <suffix domain="nj.us" />
+ <suffix domain="nm.us" />
+ <suffix domain="nv.us" />
+ <suffix domain="ny.us" />
+ <suffix domain="oh.us" />
+ <suffix domain="ok.us" />
+ <suffix domain="or.us" />
+ <suffix domain="pa.us" />
+ <suffix domain="ri.us" />
+ <suffix domain="sc.us" />
+ <suffix domain="sd.us" />
+ <suffix domain="tn.us" />
+ <suffix domain="tx.us" />
+ <suffix domain="ut.us" />
+ <suffix domain="vt.us" />
+ <suffix domain="va.us" />
+ <suffix domain="wa.us" />
+ <suffix domain="wi.us" />
+ <suffix domain="wv.us" />
+ <suffix domain="wy.us" />
+ <!-- the following rules would be only valid under the geo-name, but we can't express that-->
+ <!-- *.*.us cities, counties, parishes, and townships (locality.state.us)-->
+ <!-- !ci.*.*.us city government agencies (subdomain under locality)-->
+ <!-- !town.*.*.us town government agencies (subdomain under locality)-->
+ <!-- !co.*.*.us county government agencies (subdomain under locality)-->
+ <!-- k12.*.us public school districts-->
+ <!-- pvt.k12.*.us private schools-->
+ <!-- cc.*.us community colleges-->
+ <!-- tec.*.us technical and vocational schools-->
+ <!-- lib.*.us state, regional, city, and county libraries-->
+ <!-- state.*.us state government agencies-->
+ <!-- gen.*.us general independent entities (groups not fitting into the above categories)-->
+
+ <!-- uy : http://www.antel.com.uy/-- >
+
+ <!-- uz : http://www.reg.uz/registerr.html-- >
+ <!-- are there other 2nd level tlds ?-->
+ <suffix domain="com.uz" />
+ <suffix domain="co.uz" />
+
+ <!-- va : http://en.wikipedia.org/wiki/.va-- >
+
+ <!-- vc : http://en.wikipedia.org/wiki/.vc-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- ve : http://registro.nic.ve/nicve/registro/index.html-- >
+
+ <!-- vg : http://en.wikipedia.org/wiki/.vg-- >
+
+ <!-- vi : http://www.nic.vi/Domain_Rules/body_domain_rules.html-- >
+ <suffix domain="com.vi" />
+ <suffix domain="org.vi" />
+ <suffix domain="edu.vi" />
+ <suffix domain="gov.vi" />
+
+ <!-- vn : https://www.dot.vn/vnnic/vnnic/domainregistration.jsp-- >
+ <suffix domain="com.vn" />
+ <suffix domain="net.vn" />
+ <suffix domain="org.vn" />
+ <suffix domain="edu.vn" />
+ <suffix domain="gov.vn" />
+ <suffix domain="int.vn" />
+ <suffix domain="ac.vn" />
+ <suffix domain="biz.vn" />
+ <suffix domain="info.vn" />
+ <suffix domain="name.vn" />
+ <suffix domain="pro.vn" />
+ <suffix domain="health.vn" />
+
+ <!-- vu : http://en.wikipedia.org/wiki/.vu-- >
+ <!-- list of 2nd level tlds ?-->
+
+ <!-- ws : http://en.wikipedia.org/wiki/.ws-- >
+
+ <!-- ye : http://www.y.net.ye/services/domain_name.htm-- >
+
+ <!-- yu : http://www.nic.yu/pravilnik-e.html-- >
+
+ <!-- za : http://www.zadna.org.za/slds.html-- >
+
+ <!-- zm : http://en.wikipedia.org/wiki/.zm-- >
+
+ <!-- zw : http://en.wikipedia.org/wiki/.zw-- >
+
+ </suffixes>
+</domains>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xsd b/search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xsd
new file mode 100644
index 0000000..ba68d62
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/domain-suffixes.xsd
@@ -0,0 +1,130 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ Document : domain-suffixes.xsd
+ Author : Enis Soztutar - enis.soz.nutch(a)gmail.com
+ Description: This document is the schema for valid domain-suffixes
+ definitions. For successful parsing of domain-suffixes xml files,
+ the xml file should be validated with this xsd.
+ See : org.apache.nutch.util.domain.DomainSuffixesReader.java
+-->
+
+<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema "
+ targetNamespace="http://lucene.apache.org/nutch "
+ xmlns="http://lucene.apache.org/nutch "
+ elementFormDefault="qualified">
+
+ <xs:element name="domains">
+ <xs:complexType>
+ <xs:sequence>
+ <xs:element name="tlds">
+ <xs:complexType>
+ <xs:sequence>
+ <xs:element name="itlds">
+ <xs:complexType>
+ <xs:sequence>
+ <xs:element name="tld" maxOccurs="unbounded"
+ type="gtld" />
+ </xs:sequence>
+ </xs:complexType>
+ </xs:element>
+
+ <xs:element name="gtlds">
+ <xs:complexType>
+ <xs:sequence>
+ <xs:element name="tld" maxOccurs="unbounded"
+ type="gtld" />
+ </xs:sequence>
+ </xs:complexType>
+ </xs:element>
+
+ <xs:element name="cctlds">
+ <xs:complexType>
+ <xs:sequence>
+ <xs:element name="tld" maxOccurs="unbounded"
+ type="cctld" />
+ </xs:sequence>
+ </xs:complexType>
+ </xs:element>
+
+ </xs:sequence>
+ </xs:complexType>
+ </xs:element>
+
+ <xs:element name="suffixes">
+ <xs:complexType>
+ <xs:sequence>
+ <xs:element name="suffix" maxOccurs="unbounded"
+ type="sldType" />
+ </xs:sequence>
+ </xs:complexType>
+ </xs:element>
+ </xs:sequence>
+ </xs:complexType>
+ </xs:element>
+
+ <xs:complexType name="gtld">
+ <xs:sequence>
+ <xs:element name="status" minOccurs="0">
+ <xs:simpleType>
+ <xs:restriction base="xs:string">
+ <xs:enumeration value="INFRASTRUCTURE" />
+ <xs:enumeration value="SPONSORED" />
+ <xs:enumeration value="UNSPONSORED" />
+ <xs:enumeration value="STARTUP" />
+ <xs:enumeration value="PROPOSED" />
+ <xs:enumeration value="DELETED" />
+ <xs:enumeration value="PSEUDO_DOMAIN" />
+ </xs:restriction>
+ </xs:simpleType>
+ </xs:element>
+ <xs:element name="boost" type="xs:float" minOccurs="0" />
+ <xs:element name="description" type="xs:string" minOccurs="0" />
+ </xs:sequence>
+ <xs:attribute name="domain" type="xs:string" />
+ </xs:complexType>
+
+ <xs:complexType name="cctld">
+ <xs:sequence>
+ <xs:element name="country" type="xs:string" />
+ <xs:element name="status" type="statusType" minOccurs="0" />
+ <xs:element name="boost" type="xs:float" minOccurs="0" />
+ <xs:element name="description" type="xs:string" minOccurs="0" />
+ </xs:sequence>
+ <xs:attribute name="domain" type="xs:string" />
+ </xs:complexType>
+
+ <xs:complexType name="sldType">
+ <xs:sequence>
+ <xs:element name="status" type="statusType" minOccurs="0" />
+ <xs:element name="boost" type="xs:float" minOccurs="0" />
+ <xs:element name="description" type="xs:string" minOccurs="0" />
+ </xs:sequence>
+ <xs:attribute name="domain" type="xs:string" />
+ </xs:complexType>
+
+ <xs:simpleType name="statusType">
+ <xs:restriction base="xs:string">
+ <xs:enumeration value="IN_USE" />
+ <xs:enumeration value="NOT_IN_USE" />
+ <xs:enumeration value="DELETED" />
+ </xs:restriction>
+ </xs:simpleType>
+
+</xs:schema>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-env.sh b/search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-env.sh
new file mode 100644
index 0000000..9050a6e
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-env.sh
@@ -0,0 +1,33 @@
+# Set Hadoop-specific environment variables here.
+
+# The only required environment variable is JAVA_HOME. All others are
+# optional. When running a distributed configuration it is best to
+# set JAVA_HOME in this file, so that it is correctly defined on
+# remote nodes.
+
+# The java implementation to use. Required.
+# export JAVA_HOME=/usr/bin/java
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+# export HADOOP_HEAPSIZE=2000
+
+# Extra Java runtime options. Empty by default.
+# export HADOOP_OPTS=-server
+
+# Extra ssh options. Default: '-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR'.
+# export HADOOP_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR"
+
+# Where log files are stored. $HADOOP_HOME/logs by default.
+# export HADOOP_LOG_DIR=${HADOOP_HOME}/logs
+
+# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.
+# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
+
+# host:path where hadoop code should be rsync'd from. Unset by default.
+# export HADOOP_MASTER=master:/home/$USER/src/hadoop
+
+# The directory where pid files are stored. /tmp by default.
+# export HADOOP_PID_DIR=/var/hadoop/pids
+
+# A string representing this instance of hadoop. $USER by default.
+# export HADOOP_IDENT_STRING=$USER
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-site.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-site.xml
new file mode 100644
index 0000000..970c8fe
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/hadoop-site.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+</configuration>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/httpclient-auth.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/httpclient-auth.xml
new file mode 100644
index 0000000..60d45b9
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/httpclient-auth.xml
@@ -0,0 +1,61 @@
+<?xml version="1.0"?>
+<!--
+ This is the authentication configuration file for protocol-httpclient.
+ Different credentials for different authentication scopes can be
+ configured in this file. If a set of credentials is configured for a
+ particular authentication scope (i.e. particular host, port number,
+ scheme and realm), then that set of credentials would be sent only to
+ servers falling under the specified authentication scope. Apart from
+ this at most one set of credentials can be configured as 'default'.
+
+ When authentication is required to fetch a resource from a web-server,
+ the authentication-scope is determined from the host, port, scheme and
+ realm (if present) obtained from the URL of the page and the
+ authentication headers in the HTTP response. If it matches any
+ 'authscope' in this configuration file, then the 'credentials' for
+ that 'authscope' is used for authentication. Otherwise, it would use
+ the 'default' set of credentials (with an exception which is described
+ in the next paragraph), if present. If any attribute is missing, it
+ would match all values for that attribute.
+
+ If there are several pages having different authentication realms and
+ schemes on the same web-server (same host and port, but different
+ realms and schemes), and credentials for one or more of the realms and
+ schemes for that web-server is specified, then the 'default'
+ credentials would be ignored completely for that web-server (for that
+ host and port). So, credentials to handle all realms and schemes for
+ that server may be specified explicitly by adding an extra 'authscope'
+ tag with the 'realm' and 'scheme' attributes missing for that server.
+ This is demonstrated by the last 'authscope' tag for 'example:8080' in
+ the following example.
+
+ Example:-
+ <credentials username="susam" password="masus">
+ <default realm="sso"/>
+ <authscope host="192.168.101.33" port="80" realm="login"/>
+ <authscope host="example" port="8080" realm="blogs"/>
+ <authscope host="example" port="8080" realm="wiki"/>
+ <authscope host="example" port="80" realm="quiz" scheme="NTLM"/>
+ </credentials>
+ <credentials username="admin" password="nimda">
+ <authscope host="example" port="8080"/>
+ </credentials>
+
+ In the above example, 'example:8080' server has pages with multiple
+ authentication realms. The first set of credentials would be used for
+ 'blogs' and 'wiki' authentication realms. The second set of
+ credentials would be used for all other realms. For 'login' realm of
+ '192.168.101.33', the first set of credentials would be used. For any
+ other realm of '192.168.101.33' authentication would not be done. For
+ the NTLM authentication required by 'example:80', the first set of
+ credentials would be used. For 'sso' realms of all other servers, the
+ first set of credentials would be used, since it is configured as
+ 'default'.
+
+ NTLM does not use the notion of realms. The domain name may be
+ specified as the value for 'realm' attribute in case of NTLM.
+-->
+
+<auth-configuration>
+
+</auth-configuration>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/log4j.properties b/search-server/spacewalk-search/nutch/crawl_jsp/conf/log4j.properties
new file mode 100644
index 0000000..5a985ab
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/log4j.properties
@@ -0,0 +1,82 @@
+# Define some default values that can be overridden by system properties
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+# RootLogger - DailyRollingFileAppender
+log4j.rootLogger=ALL,DRFA
+
+# Logging Threshold
+log4j.threshhold=ALL
+
+#special logging requirements for some commandline tools
+log4j.logger.org.apache.nutch.crawl.Crawl=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.Injector=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.Generator=INFO,cmdstdout
+log4j.logger.org.apache.nutch.fetcher.Fetcher=INFO,cmdstdout
+log4j.logger.org.apache.nutch.parse.ParseSegment=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.CrawlDbReader=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.CrawlDbMerger=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.LinkDbReader=INFO,cmdstdout
+log4j.logger.org.apache.nutch.segment.SegmentReader=INFO,cmdstdout
+log4j.logger.org.apache.nutch.segment.SegmentMerger=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.CrawlDb=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.LinkDb=INFO,cmdstdout
+log4j.logger.org.apache.nutch.crawl.LinkDbMerger=INFO,cmdstdout
+log4j.logger.org.apache.nutch.indexer.Indexer=INFO,cmdstdout
+log4j.logger.org.apache.nutch.indexer.DeleteDuplicates=INFO,cmdstdout
+log4j.logger.org.apache.nutch.indexer.IndexMerger=INFO,cmdstdout
+
+log4j.logger.org.apache.nutch=INFO
+log4j.logger.org.apache.hadoop=WARN
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+# Debugging Pattern format: Date LogLevel LoggerName (FileName:MethodName:LineNo) LogMessage
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# stdout
+# Add *stdout* to rootlogger above if you want to use this
+#
+
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+#
+# plain layout used for commandline tools to output to console
+#
+log4j.appender.cmdstdout=org.apache.log4j.ConsoleAppender
+log4j.appender.cmdstdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.cmdstdout.layout.ConversionPattern=%m%n
+
+#
+# Rolling File Appender
+#
+
+#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Logfile size and and 30-day backups
+#log4j.appender.RFA.MaxFileSize=1MB
+#log4j.appender.RFA.MaxBackupIndex=30
+
+#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/logging.properties b/search-server/spacewalk-search/nutch/crawl_jsp/conf/logging.properties
new file mode 100644
index 0000000..67b4a73
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/logging.properties
@@ -0,0 +1,4 @@
+handlers= java.util.logging.ConsoleHandler
+.level= FINE
+
+
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/masters b/search-server/spacewalk-search/nutch/crawl_jsp/conf/masters
new file mode 100644
index 0000000..2fbb50c
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/masters
@@ -0,0 +1 @@
+localhost
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-conf.xsl b/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-conf.xsl
new file mode 100644
index 0000000..36a2275
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-conf.xsl
@@ -0,0 +1,24 @@
+<?xml version="1.0"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform " version="1.0">
+<xsl:output method="html"/>
+<xsl:template match="nutch-conf">
+<html>
+<body>
+<table border="1">
+<tr>
+ <td>name</td>
+ <td>value</td>
+ <td>description</td>
+</tr>
+<xsl:for-each select="property">
+<tr>
+ <td><xsl:value-of select="name"/></td>
+ <td><xsl:value-of select="value"/></td>
+ <td><xsl:value-of select="description"/></td>
+</tr>
+</xsl:for-each>
+</table>
+</body>
+</html>
+</xsl:template>
+</xsl:stylesheet>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-default.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-default.xml
new file mode 100644
index 0000000..2bf0e1e
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-default.xml
@@ -0,0 +1,1205 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+<!-- Do not modify this file directly. Instead, copy entries that you -->
+<!-- wish to modify from this file into nutch-site.xml and change them -->
+<!-- there. If nutch-site.xml does not already exist, create it. -->
+
+<configuration>
+
+<!-- file properties -->
+
+<property>
+ <name>file.content.limit</name>
+ <value>65536</value>
+ <description>The length limit for downloaded content, in bytes.
+ If this value is nonnegative (>=0), content longer than it will be truncated;
+ otherwise, no truncation at all.
+ </description>
+</property>
+
+<property>
+ <name>file.content.ignored</name>
+ <value>true</value>
+ <description>If true, no file content will be saved during fetch.
+ And it is probably what we want to set most of time, since file:// URLs
+ are meant to be local and we can always use them directly at parsing
+ and indexing stages. Otherwise file contents will be saved.
+ !! NO IMPLEMENTED YET !!
+ </description>
+</property>
+
+<!-- HTTP properties -->
+
+<property>
+ <name>http.agent.name</name>
+ <value></value>
+ <description>HTTP 'User-Agent' request header. MUST NOT be empty -
+ please set this to a single word uniquely related to your organization.
+
+ NOTE: You should also check other related properties:
+
+ http.robots.agents
+ http.agent.description
+ http.agent.url
+ http.agent.email
+ http.agent.version
+
+ and set their values appropriately.
+
+ </description>
+</property>
+
+<property>
+ <name>http.robots.agents</name>
+ <value>*</value>
+ <description>The agent strings we'll look for in robots.txt files,
+ comma-separated, in decreasing order of precedence. You should
+ put the value of http.agent.name as the first agent name, and keep the
+ default * at the end of the list. E.g.: BlurflDev,Blurfl,*
+ </description>
+</property>
+
+<property>
+ <name>http.robots.403.allow</name>
+ <value>true</value>
+ <description>Some servers return HTTP status 403 (Forbidden) if
+ /robots.txt doesn't exist. This should probably mean that we are
+ allowed to crawl the site nonetheless. If this is set to false,
+ then such sites will be treated as forbidden.</description>
+</property>
+
+<property>
+ <name>http.agent.description</name>
+ <value></value>
+ <description>Further description of our bot- this text is used in
+ the User-Agent header. It appears in parenthesis after the agent name.
+ </description>
+</property>
+
+<property>
+ <name>http.agent.url</name>
+ <value></value>
+ <description>A URL to advertise in the User-Agent header. This will
+ appear in parenthesis after the agent name. Custom dictates that this
+ should be a URL of a page explaining the purpose and behavior of this
+ crawler.
+ </description>
+</property>
+
+<property>
+ <name>http.agent.email</name>
+ <value></value>
+ <description>An email address to advertise in the HTTP 'From' request
+ header and User-Agent header. A good practice is to mangle this
+ address (e.g. 'info at example dot com') to avoid spamming.
+ </description>
+</property>
+
+<property>
+ <name>http.agent.version</name>
+ <value>Nutch-1.0-dev</value>
+ <description>A version string to advertise in the User-Agent
+ header.</description>
+</property>
+
+<property>
+ <name>http.agent.host</name>
+ <value></value>
+ <description>Name or IP address of the host on which the Nutch crawler
+ would be running. Currently this is used by 'protocol-httpclient'
+ plugin.
+ </description>
+</property>
+
+<property>
+ <name>http.timeout</name>
+ <value>10000</value>
+ <description>The default network timeout, in milliseconds.</description>
+</property>
+
+<property>
+ <name>http.max.delays</name>
+ <value>100</value>
+ <description>The number of times a thread will delay when trying to
+ fetch a page. Each time it finds that a host is busy, it will wait
+ fetcher.server.delay. After http.max.delays attepts, it will give
+ up on the page for now.</description>
+</property>
+
+<property>
+ <name>http.content.limit</name>
+ <value>65536</value>
+ <description>The length limit for downloaded content, in bytes.
+ If this value is nonnegative (>=0), content longer than it will be truncated;
+ otherwise, no truncation at all.
+ </description>
+</property>
+
+<property>
+ <name>http.proxy.host</name>
+ <value></value>
+ <description>The proxy hostname. If empty, no proxy is used.</description>
+</property>
+
+<property>
+ <name>http.proxy.port</name>
+ <value></value>
+ <description>The proxy port.</description>
+</property>
+
+<property>
+ <name>http.proxy.username</name>
+ <value></value>
+ <description>Username for proxy. This will be used by
+ 'protocol-httpclient', if the proxy server requests basic, digest
+ and/or NTLM authentication. To use this, 'protocol-httpclient' must
+ be present in the value of 'plugin.includes' property.
+ NOTE: For NTLM authentication, do not prefix the username with the
+ domain, i.e. 'susam' is correct whereas 'DOMAIN\susam' is incorrect.
+ </description>
+</property>
+
+<property>
+ <name>http.proxy.password</name>
+ <value></value>
+ <description>Password for proxy. This will be used by
+ 'protocol-httpclient', if the proxy server requests basic, digest
+ and/or NTLM authentication. To use this, 'protocol-httpclient' must
+ be present in the value of 'plugin.includes' property.
+ </description>
+</property>
+
+<property>
+ <name>http.proxy.realm</name>
+ <value></value>
+ <description>Authentication realm for proxy. Do not define a value
+ if realm is not required or authentication should take place for any
+ realm. NTLM does not use the notion of realms. Specify the domain name
+ of NTLM authentication as the value for this property. To use this,
+ 'protocol-httpclient' must be present in the value of
+ 'plugin.includes' property.
+ </description>
+</property>
+
+<property>
+ <name>http.auth.file</name>
+ <value>httpclient-auth.xml</value>
+ <description>Authentication configuration file for
+ 'protocol-httpclient' plugin.
+ </description>
+</property>
+
+<property>
+ <name>http.verbose</name>
+ <value>false</value>
+ <description>If true, HTTP will log more verbosely.</description>
+</property>
+
+<property>
+ <name>http.redirect.max</name>
+ <value>0</value>
+ <description>The maximum number of redirects the fetcher will follow when
+ trying to fetch a page. If set to negative or 0, fetcher won't immediately
+ follow redirected URLs, instead it will record them for later fetching.
+ </description>
+</property>
+
+<property>
+ <name>http.useHttp11</name>
+ <value>false</value>
+ <description>NOTE: at the moment this works only for protocol-httpclient.
+ If true, use HTTP 1.1, if false use HTTP 1.0 .
+ </description>
+</property>
+
+<!-- FTP properties -->
+
+<property>
+ <name>ftp.username</name>
+ <value>anonymous</value>
+ <description>ftp login username.</description>
+</property>
+
+<property>
+ <name>ftp.password</name>
+ <value>anonymous(a)example.com</value>
+ <description>ftp login password.</description>
+</property>
+
+<property>
+ <name>ftp.content.limit</name>
+ <value>65536</value>
+ <description>The length limit for downloaded content, in bytes.
+ If this value is nonnegative (>=0), content longer than it will be truncated;
+ otherwise, no truncation at all.
+ Caution: classical ftp RFCs never defines partial transfer and, in fact,
+ some ftp servers out there do not handle client side forced close-down very
+ well. Our implementation tries its best to handle such situations smoothly.
+ </description>
+</property>
+
+<property>
+ <name>ftp.timeout</name>
+ <value>60000</value>
+ <description>Default timeout for ftp client socket, in millisec.
+ Please also see ftp.keep.connection below.</description>
+</property>
+
+<property>
+ <name>ftp.server.timeout</name>
+ <value>100000</value>
+ <description>An estimation of ftp server idle time, in millisec.
+ Typically it is 120000 millisec for many ftp servers out there.
+ Better be conservative here. Together with ftp.timeout, it is used to
+ decide if we need to delete (annihilate) current ftp.client instance and
+ force to start another ftp.client instance anew. This is necessary because
+ a fetcher thread may not be able to obtain next request from queue in time
+ (due to idleness) before our ftp client times out or remote server
+ disconnects. Used only when ftp.keep.connection is true (please see below).
+ </description>
+</property>
+
+<property>
+ <name>ftp.keep.connection</name>
+ <value>false</value>
+ <description>Whether to keep ftp connection. Useful if crawling same host
+ again and again. When set to true, it avoids connection, login and dir list
+ parser setup for subsequent urls. If it is set to true, however, you must
+ make sure (roughly):
+ (1) ftp.timeout is less than ftp.server.timeout
+ (2) ftp.timeout is larger than (fetcher.threads.fetch * fetcher.server.delay)
+ Otherwise there will be too many "delete client because idled too long"
+ messages in thread logs.</description>
+</property>
+
+<property>
+ <name>ftp.follow.talk</name>
+ <value>false</value>
+ <description>Whether to log dialogue between our client and remote
+ server. Useful for debugging.</description>
+</property>
+
+<!-- web db properties -->
+
+<property>
+ <name>db.default.fetch.interval</name>
+ <value>30</value>
+ <description>(DEPRECATED) The default number of days between re-fetches of a page.
+ </description>
+</property>
+
+<property>
+ <name>db.fetch.interval.default</name>
+ <value>2592000</value>
+ <description>The default number of seconds between re-fetches of a page (30 days).
+ </description>
+</property>
+
+<property>
+ <name>db.fetch.interval.max</name>
+ <value>7776000</value>
+ <description>The maximum number of seconds between re-fetches of a page
+ (90 days). After this period every page in the db will be re-tried, no
+ matter what is its status.
+ </description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.class</name>
+ <value>org.apache.nutch.crawl.DefaultFetchSchedule</value>
+ <description>The implementation of fetch schedule. DefaultFetchSchedule simply
+ adds the original fetchInterval to the last fetch time, regardless of
+ page changes.</description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.adaptive.inc_rate</name>
+ <value>0.4</value>
+ <description>If a page is unmodified, its fetchInterval will be
+ increased by this rate. This value should not
+ exceed 0.5, otherwise the algorithm becomes unstable.</description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.adaptive.dec_rate</name>
+ <value>0.2</value>
+ <description>If a page is modified, its fetchInterval will be
+ decreased by this rate. This value should not
+ exceed 0.5, otherwise the algorithm becomes unstable.</description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.adaptive.min_interval</name>
+ <value>60.0</value>
+ <description>Minimum fetchInterval, in seconds.</description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.adaptive.max_interval</name>
+ <value>31536000.0</value>
+ <description>Maximum fetchInterval, in seconds (365 days).
+ NOTE: this is limited by db.fetch.interval.max. Pages with
+ fetchInterval larger than db.fetch.interval.max
+ will be fetched anyway.</description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.adaptive.sync_delta</name>
+ <value>true</value>
+ <description>If true, try to synchronize with the time of page change.
+ by shifting the next fetchTime by a fraction (sync_rate) of the difference
+ between the last modification time, and the last fetch time.</description>
+</property>
+
+<property>
+ <name>db.fetch.schedule.adaptive.sync_delta_rate</name>
+ <value>0.3</value>
+ <description>See sync_delta for description. This value should not
+ exceed 0.5, otherwise the algorithm becomes unstable.</description>
+</property>
+
+<property>
+ <name>db.update.additions.allowed</name>
+ <value>true</value>
+ <description>If true, updatedb will add newly discovered URLs, if false
+ only already existing URLs in the CrawlDb will be updated and no new
+ URLs will be added.
+ </description>
+</property>
+
+<property>
+ <name>db.ignore.internal.links</name>
+ <value>true</value>
+ <description>If true, when adding new links to a page, links from
+ the same host are ignored. This is an effective way to limit the
+ size of the link database, keeping only the highest quality
+ links.
+ </description>
+</property>
+
+<property>
+ <name>db.ignore.external.links</name>
+ <value>false</value>
+ <description>If true, outlinks leading from a page to external hosts
+ will be ignored. This is an effective way to limit the crawl to include
+ only initially injected hosts, without creating complex URLFilters.
+ </description>
+</property>
+
+<property>
+ <name>db.score.injected</name>
+ <value>1.0</value>
+ <description>The score of new pages added by the injector.
+ </description>
+</property>
+
+<property>
+ <name>db.score.link.external</name>
+ <value>1.0</value>
+ <description>The score factor for new pages added due to a link from
+ another host relative to the referencing page's score. Scoring plugins
+ may use this value to affect initial scores of external links.
+ </description>
+</property>
+
+<property>
+ <name>db.score.link.internal</name>
+ <value>1.0</value>
+ <description>The score factor for pages added due to a link from the
+ same host, relative to the referencing page's score. Scoring plugins
+ may use this value to affect initial scores of internal links.
+ </description>
+</property>
+
+<property>
+ <name>db.score.count.filtered</name>
+ <value>false</value>
+ <description>The score value passed to newly discovered pages is
+ calculated as a fraction of the original page score divided by the
+ number of outlinks. If this option is false, only the outlinks that passed
+ URLFilters will count, if it's true then all outlinks will count.
+ </description>
+</property>
+
+<property>
+ <name>db.max.inlinks</name>
+ <value>10000</value>
+ <description>Maximum number of Inlinks per URL to be kept in LinkDb.
+ If "invertlinks" finds more inlinks than this number, only the first
+ N inlinks will be stored, and the rest will be discarded.
+ </description>
+</property>
+
+<property>
+ <name>db.max.outlinks.per.page</name>
+ <value>100</value>
+ <description>The maximum number of outlinks that we'll process for a page.
+ If this value is nonnegative (>=0), at most db.max.outlinks.per.page outlinks
+ will be processed for a page; otherwise, all outlinks will be processed.
+ </description>
+</property>
+
+<property>
+ <name>db.max.anchor.length</name>
+ <value>100</value>
+ <description>The maximum number of characters permitted in an anchor.
+ </description>
+</property>
+
+<property>
+ <name>db.fetch.retry.max</name>
+ <value>3</value>
+ <description>The maximum number of times a url that has encountered
+ recoverable errors is generated for fetch.</description>
+</property>
+
+<property>
+ <name>db.signature.class</name>
+ <value>org.apache.nutch.crawl.MD5Signature</value>
+ <description>The default implementation of a page signature. Signatures
+ created with this implementation will be used for duplicate detection
+ and removal.</description>
+</property>
+
+<property>
+ <name>db.signature.text_profile.min_token_len</name>
+ <value>2</value>
+ <description>Minimum token length to be included in the signature.
+ </description>
+</property>
+
+<property>
+ <name>db.signature.text_profile.quant_rate</name>
+ <value>0.01</value>
+ <description>Profile frequencies will be rounded down to a multiple of
+ QUANT = (int)(QUANT_RATE * maxFreq), where maxFreq is a maximum token
+ frequency. If maxFreq > 1 then QUANT will be at least 2, which means that
+ for longer texts tokens with frequency 1 will always be discarded.
+ </description>
+</property>
+
+<!-- generate properties -->
+
+<property>
+ <name>generate.max.per.host</name>
+ <value>-1</value>
+ <description>The maximum number of urls per host in a single
+ fetchlist. -1 if unlimited.</description>
+</property>
+
+<property>
+ <name>generate.max.per.host.by.ip</name>
+ <value>false</value>
+ <description>If false, same host names are counted. If true,
+ hosts' IP addresses are resolved and the same IP-s are counted.
+
+ -+-+-+- WARNING !!! -+-+-+-
+ When set to true, Generator will create a lot of DNS lookup
+ requests, rapidly. This may cause a DOS attack on
+ remote DNS servers, not to mention increased external traffic
+ and latency. For these reasons when using this option it is
+ required that a local caching DNS be used.</description>
+</property>
+
+<property>
+ <name>generate.update.crawldb</name>
+ <value>false</value>
+ <description>For highly-concurrent environments, where several
+ generate/fetch/update cycles may overlap, setting this to true ensures
+ that generate will create different fetchlists even without intervening
+ updatedb-s, at the cost of running an additional job to update CrawlDB.
+ If false, running generate twice without intervening
+ updatedb will generate identical fetchlists.</description>
+</property>
+
+<!-- fetcher properties -->
+
+<property>
+ <name>fetcher.server.delay</name>
+ <value>5.0</value>
+ <description>The number of seconds the fetcher will delay between
+ successive requests to the same server.</description>
+</property>
+
+<property>
+ <name>fetcher.server.min.delay</name>
+ <value>0.0</value>
+ <description>The minimum number of seconds the fetcher will delay between
+ successive requests to the same server. This value is applicable ONLY
+ if fetcher.threads.per.host is greater than 1 (i.e. the host blocking
+ is turned off).</description>
+</property>
+
+<property>
+ <name>fetcher.max.crawl.delay</name>
+ <value>30</value>
+ <description>
+ If the Crawl-Delay in robots.txt is set to greater than this value (in
+ seconds) then the fetcher will skip this page, generating an error report.
+ If set to -1 the fetcher will never skip such pages and will wait the
+ amount of time retrieved from robots.txt Crawl-Delay, however long that
+ might be.
+ </description>
+</property>
+
+<property>
+ <name>fetcher.threads.fetch</name>
+ <value>10</value>
+ <description>The number of FetcherThreads the fetcher should use.
+ This is also determines the maximum number of requests that are
+ made at once (each FetcherThread handles one connection).</description>
+</property>
+
+<property>
+ <name>fetcher.threads.per.host</name>
+ <value>1</value>
+ <description>This number is the maximum number of threads that
+ should be allowed to access a host at one time.</description>
+</property>
+
+<property>
+ <name>fetcher.threads.per.host.by.ip</name>
+ <value>true</value>
+ <description>If true, then fetcher will count threads by IP address,
+ to which the URL's host name resolves. If false, only host name will be
+ used. NOTE: this should be set to the same value as
+ "generate.max.per.host.by.ip" - default settings are different only for
+ reasons of backward-compatibility.</description>
+</property>
+
+<property>
+ <name>fetcher.verbose</name>
+ <value>false</value>
+ <description>If true, fetcher will log more verbosely.</description>
+</property>
+
+<property>
+ <name>fetcher.parse</name>
+ <value>true</value>
+ <description>If true, fetcher will parse content.</description>
+</property>
+
+<property>
+ <name>fetcher.store.content</name>
+ <value>true</value>
+ <description>If true, fetcher will store content.</description>
+</property>
+
+<!-- indexer properties -->
+
+<property>
+ <name>indexer.score.power</name>
+ <value>0.5</value>
+ <description>Determines the power of link analyis scores. Each
+ pages's boost is set to <i>score<sup>scorePower</sup></i> where
+ <i>score</i> is its link analysis score and <i>scorePower</i> is the
+ value of this parameter. This is compiled into indexes, so, when
+ this is changed, pages must be re-indexed for it to take
+ effect.</description>
+</property>
+
+<property>
+ <name>indexer.max.title.length</name>
+ <value>100</value>
+ <description>The maximum number of characters of a title that are indexed.
+ </description>
+</property>
+
+<property>
+ <name>indexer.max.tokens</name>
+ <value>10000</value>
+ <description>
+ The maximum number of tokens that will be indexed for a single field
+ in a document. This limits the amount of memory required for
+ indexing, so that collections with very large files will not crash
+ the indexing process by running out of memory.
+
+ Note that this effectively truncates large documents, excluding
+ from the index tokens that occur further in the document. If you
+ know your source documents are large, be sure to set this value
+ high enough to accomodate the expected size. If you set it to
+ -1, then the only limit is your memory, but you should anticipate
+ an OutOfMemoryError.
+ </description>
+</property>
+
+<property>
+ <name>indexer.mergeFactor</name>
+ <value>50</value>
+ <description>The factor that determines the frequency of Lucene segment
+ merges. This must not be less than 2, higher values increase indexing
+ speed but lead to increased RAM usage, and increase the number of
+ open file handles (which may lead to "Too many open files" errors).
+ NOTE: the "segments" here have nothing to do with Nutch segments, they
+ are a low-level data unit used by Lucene.
+ </description>
+</property>
+
+<property>
+ <name>indexer.minMergeDocs</name>
+ <value>50</value>
+ <description>This number determines the minimum number of Lucene
+ Documents buffered in memory between Lucene segment merges. Larger
+ values increase indexing speed and increase RAM usage.
+ </description>
+</property>
+
+<property>
+ <name>indexer.maxMergeDocs</name>
+ <value>2147483647</value>
+ <description>This number determines the maximum number of Lucene
+ Documents to be merged into a new Lucene segment. Larger values
+ increase batch indexing speed and reduce the number of Lucene segments,
+ which reduces the number of open file handles; however, this also
+ decreases incremental indexing performance.
+ </description>
+</property>
+
+<property>
+ <name>indexer.termIndexInterval</name>
+ <value>128</value>
+ <description>Determines the fraction of terms which Lucene keeps in
+ RAM when searching, to facilitate random-access. Smaller values use
+ more memory but make searches somewhat faster. Larger values use
+ less memory but make searches somewhat slower.
+ </description>
+</property>
+
+<!-- indexingfilter plugin properties -->
+
+<property>
+ <name>indexingfilter.order</name>
+ <value></value>
+ <description>The order by which index filters are applied.
+ If empty, all available index filters (as dictated by properties
+ plugin-includes and plugin-excludes above) are loaded and applied in system
+ defined order. If not empty, only named filters are loaded and applied
+ in given order. For example, if this property has value:
+ org.apache.nutch.indexer.basic.BasicIndexingFilter org.apache.nutch.indexer.more.MoreIndexingFilter
+ then BasicIndexingFilter is applied first, and MoreIndexingFilter second.
+
+ Filter ordering might have impact on result if one filter depends on output of
+ another filter.
+ </description>
+</property>
+
+
+<!-- analysis properties -->
+
+<property>
+ <name>analysis.common.terms.file</name>
+ <value>common-terms.utf8</value>
+ <description>The name of a file containing a list of common terms
+ that should be indexed in n-grams.</description>
+</property>
+
+<!-- searcher properties -->
+
+<property>
+ <name>searcher.dir</name>
+ <value>crawl</value>
+ <description>
+ Path to root of crawl. This directory is searched (in
+ order) for either the file search-servers.txt, containing a list of
+ distributed search servers, or the directory "index" containing
+ merged indexes, or the directory "segments" containing segment
+ indexes.
+ </description>
+</property>
+
+<property>
+ <name>searcher.filter.cache.size</name>
+ <value>16</value>
+ <description>
+ Maximum number of filters to cache. Filters can accelerate certain
+ field-based queries, like language, document format, etc. Each
+ filter requires one bit of RAM per page. So, with a 10 million page
+ index, a cache size of 16 consumes two bytes per page, or 20MB.
+ </description>
+</property>
+
+<property>
+ <name>searcher.filter.cache.threshold</name>
+ <value>0.05</value>
+ <description>
+ Filters are cached when their term is matched by more than this
+ fraction of pages. For example, with a threshold of 0.05, and 10
+ million pages, the term must match more than 1/20, or 50,000 pages.
+ So, if out of 10 million pages, 50% of pages are in English, and 2%
+ are in Finnish, then, with a threshold of 0.05, searches for
+ "lang:en" will use a cached filter, while searches for "lang:fi"
+ will score all 20,000 finnish documents.
+ </description>
+</property>
+
+<property>
+ <name>searcher.hostgrouping.rawhits.factor</name>
+ <value>2.0</value>
+ <description>
+ A factor that is used to determine the number of raw hits
+ initially fetched, before host grouping is done.
+ </description>
+</property>
+
+<property>
+ <name>searcher.summary.context</name>
+ <value>5</value>
+ <description>
+ The number of context terms to display preceding and following
+ matching terms in a hit summary.
+ </description>
+</property>
+
+<property>
+ <name>searcher.summary.length</name>
+ <value>20</value>
+ <description>
+ The total number of terms to display in a hit summary.
+ </description>
+</property>
+
+<property>
+ <name>searcher.max.hits</name>
+ <value>-1</value>
+ <description>If positive, search stops after this many hits are
+ found. Setting this to small, positive values (e.g., 1000) can make
+ searches much faster. With a sorted index, the quality of the hits
+ suffers little.</description>
+</property>
+
+<property>
+ <name>searcher.max.time.tick_count</name>
+ <value>-1</value>
+ <description>If positive value is defined here, limit search time for
+ every request to this number of elapsed ticks (see the tick_length
+ property below). The total maximum time for any search request will be
+ then limited to tick_count * tick_length milliseconds. When search time
+ is exceeded, partial results will be returned, and the total number of
+ hits will be estimated.
+ </description>
+</property>
+
+<property>
+ <name>searcher.max.time.tick_length</name>
+ <value>200</value>
+ <description>The number of milliseconds between ticks. Larger values
+ reduce the timer granularity (precision). Smaller values bring more
+ overhead.
+ </description>
+</property>
+
+<property>
+ <name>searcher.num.handlers</name>
+ <value>10</value>
+ <description>The number of handlers for the distributed search server.
+ </description>
+</property>
+
+<property>
+ <name>searcher.max.hits.per.page</name>
+ <value>1000</value>
+ <description> The maximum number of hits to show per page. -1 if
+ unlimited. If the number of hits requested by the user (via
+ hitsPerPage parameter in the query string) is more than the value
+ specified in this property, then this value is assumed as the number
+ of hits per page.
+ </description>
+</property>
+
+<!-- URL normalizer properties -->
+
+<property>
+ <name>urlnormalizer.order</name>
+ <value>org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer org.apache.nutch.net.urlnormalizer.regex.RegexURLNormalizer</value>
+ <description>Order in which normalizers will run. If any of these isn't
+ activated it will be silently skipped. If other normalizers not on the
+ list are activated, they will run in random order after the ones
+ specified here are run.
+ </description>
+</property>
+
+<property>
+ <name>urlnormalizer.regex.file</name>
+ <value>regex-normalize.xml</value>
+ <description>Name of the config file used by the RegexUrlNormalizer class.
+ </description>
+</property>
+
+<property>
+ <name>urlnormalizer.loop.count</name>
+ <value>1</value>
+ <description>Optionally loop through normalizers several times, to make
+ sure that all transformations have been performed.
+ </description>
+</property>
+
+<!-- mime properties -->
+
+<property>
+ <name>mime.types.file</name>
+ <value>tika-mimetypes.xml</value>
+ <description>Name of file in CLASSPATH containing filename extension and
+ magic sequence to mime types mapping information</description>
+</property>
+
+<property>
+ <name>mime.type.magic</name>
+ <value>true</value>
+ <description>Defines if the mime content type detector uses magic resolution.
+ </description>
+</property>
+
+<!-- plugin properties -->
+
+<property>
+ <name>plugin.folders</name>
+ <value>plugins</value>
+ <description>Directories where nutch plugins are located. Each
+ element may be a relative or absolute path. If absolute, it is used
+ as is. If relative, it is searched for on the classpath.</description>
+</property>
+
+<property>
+ <name>plugin.auto-activation</name>
+ <value>true</value>
+ <description>Defines if some plugins that are not activated regarding
+ the plugin.includes and plugin.excludes properties must be automaticaly
+ activated if they are needed by some actived plugins.
+ </description>
+</property>
+
+<property>
+ <name>plugin.includes</name>
+ <value>protocol-http|urlfilter-regex|parse-(text|html|js)|index-(basic|anchor)|query-(basic|site|url)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
+ <description>Regular expression naming plugin directory names to
+ include. Any plugin not matching this expression is excluded.
+ In any case you need at least include the nutch-extensionpoints plugin. By
+ default Nutch includes crawling just HTML and plain text via HTTP,
+ and basic indexing and search plugins. In order to use HTTPS please enable
+ protocol-httpclient, but be aware of possible intermittent problems with the
+ underlying commons-httpclient library.
+ </description>
+</property>
+
+<property>
+ <name>plugin.excludes</name>
+ <value></value>
+ <description>Regular expression naming plugin directory names to exclude.
+ </description>
+</property>
+
+<!-- parser properties -->
+
+<property>
+ <name>parse.plugin.file</name>
+ <value>parse-plugins.xml</value>
+ <description>The name of the file that defines the associations between
+ content-types and parsers.</description>
+</property>
+
+<property>
+ <name>parser.character.encoding.default</name>
+ <value>windows-1252</value>
+ <description>The character encoding to fall back to when no other information
+ is available</description>
+</property>
+
+<property>
+ <name>encodingdetector.charset.min.confidence</name>
+ <value>-1</value>
+ <description>A integer between 0-100 indicating minimum confidence value
+ for charset auto-detection. Any negative value disables auto-detection.
+ </description>
+</property>
+
+<property>
+ <name>parser.caching.forbidden.policy</name>
+ <value>content</value>
+ <description>If a site (or a page) requests through its robot metatags
+ that it should not be shown as cached content, apply this policy. Currently
+ three keywords are recognized: "none" ignores any "noarchive" directives.
+ "content" doesn't show the content, but shows summaries (snippets).
+ "all" doesn't show either content or summaries.</description>
+</property>
+
+
+<property>
+ <name>parser.html.impl</name>
+ <value>neko</value>
+ <description>HTML Parser implementation. Currently the following keywords
+ are recognized: "neko" uses NekoHTML, "tagsoup" uses TagSoup.
+ </description>
+</property>
+
+<property>
+ <name>parser.html.form.use_action</name>
+ <value>false</value>
+ <description>If true, HTML parser will collect URLs from form action
+ attributes. This may lead to undesirable behavior (submitting empty
+ forms during next fetch cycle). If false, form action attribute will
+ be ignored.</description>
+</property>
+
+<property>
+ <name>parser.html.outlinks.ignore_tags</name>
+ <value></value>
+ <description>Comma separated list of HTML tags, from which outlinks
+ shouldn't be extracted. Nutch takes links from: a, area, form, frame,
+ iframe, script, link, img. If you add any of those tags here, it
+ won't be taken. Default is empty list. Probably reasonable value
+ for most people would be "img,script,link".</description>
+</property>
+
+
+<!-- urlfilter plugin properties -->
+
+<property>
+ <name>urlfilter.regex.file</name>
+ <value>regex-urlfilter.txt</value>
+ <description>Name of file on CLASSPATH containing regular expressions
+ used by urlfilter-regex (RegexURLFilter) plugin.</description>
+</property>
+
+<property>
+ <name>urlfilter.automaton.file</name>
+ <value>automaton-urlfilter.txt</value>
+ <description>Name of file on CLASSPATH containing regular expressions
+ used by urlfilter-automaton (AutomatonURLFilter) plugin.</description>
+</property>
+
+<property>
+ <name>urlfilter.prefix.file</name>
+ <value>prefix-urlfilter.txt</value>
+ <description>Name of file on CLASSPATH containing url prefixes
+ used by urlfilter-prefix (PrefixURLFilter) plugin.</description>
+</property>
+
+<property>
+ <name>urlfilter.suffix.file</name>
+ <value>suffix-urlfilter.txt</value>
+ <description>Name of file on CLASSPATH containing url suffixes
+ used by urlfilter-suffix (SuffixURLFilter) plugin.</description>
+</property>
+
+<property>
+ <name>urlfilter.order</name>
+ <value></value>
+ <description>The order by which url filters are applied.
+ If empty, all available url filters (as dictated by properties
+ plugin-includes and plugin-excludes above) are loaded and applied in system
+ defined order. If not empty, only named filters are loaded and applied
+ in given order. For example, if this property has value:
+ org.apache.nutch.urlfilter.regex.RegexURLFilter org.apache.nutch.urlfilter.prefix.PrefixURLFilter
+ then RegexURLFilter is applied first, and PrefixURLFilter second.
+ Since all filters are AND'ed, filter ordering does not have impact
+ on end result, but it may have performance implication, depending
+ on relative expensiveness of filters.
+ </description>
+</property>
+
+<!-- scoring filters properties -->
+
+<property>
+ <name>scoring.filter.order</name>
+ <value></value>
+ <description>The order in which scoring filters are applied.
+ This may be left empty (in which case all available scoring
+ filters will be applied in the order defined in plugin-includes
+ and plugin-excludes), or a space separated list of implementation
+ classes.
+ </description>
+</property>
+
+<!-- clustering extension properties -->
+
+<property>
+ <name>extension.clustering.hits-to-cluster</name>
+ <value>100</value>
+ <description>Number of snippets retrieved for the clustering extension
+ if clustering extension is available and user requested results
+ to be clustered.</description>
+</property>
+
+<property>
+ <name>extension.clustering.extension-name</name>
+ <value></value>
+ <description>Use the specified online clustering extension. If empty,
+ the first available extension will be used. The "name" here refers to an 'id'
+ attribute of the 'implementation' element in the plugin descriptor XML
+ file.</description>
+</property>
+
+<!-- ontology extension properties -->
+
+<property>
+ <name>extension.ontology.extension-name</name>
+ <value></value>
+ <description>Use the specified online ontology extension. If empty,
+ the first available extension will be used. The "name" here refers to an 'id'
+ attribute of the 'implementation' element in the plugin descriptor XML
+ file.</description>
+</property>
+
+<property>
+ <name>extension.ontology.urls</name>
+ <value>
+ </value>
+ <description>Urls of owl files, separated by spaces, such as
+ http://www.example.com/ontology/time.owl
+ http://www.example.com/ontology/space.owl
+ http://www.example.com/ontology/wine.owl
+ Or
+ file:/ontology/time.owl
+ file:/ontology/space.owl
+ file:/ontology/wine.owl
+ You have to make sure each url is valid.
+ By default, there is no owl file, so query refinement based on ontology
+ is silently ignored.
+ </description>
+</property>
+
+<!-- query-basic plugin properties -->
+
+<property>
+ <name>query.url.boost</name>
+ <value>4.0</value>
+ <description> Used as a boost for url field in Lucene query.
+ </description>
+</property>
+
+<property>
+ <name>query.anchor.boost</name>
+ <value>2.0</value>
+ <description> Used as a boost for anchor field in Lucene query.
+ </description>
+</property>
+
+<property>
+ <name>query.title.boost</name>
+ <value>1.5</value>
+ <description> Used as a boost for title field in Lucene query.
+ </description>
+</property>
+
+<property>
+ <name>query.host.boost</name>
+ <value>2.0</value>
+ <description> Used as a boost for host field in Lucene query.
+ </description>
+</property>
+
+<property>
+ <name>query.phrase.boost</name>
+ <value>1.0</value>
+ <description> Used as a boost for phrase in Lucene query.
+ Multiplied by boost for field phrase is matched in.
+ </description>
+</property>
+
+<!-- creative-commons plugin properties -->
+
+<property>
+ <name>query.cc.boost</name>
+ <value>0.0</value>
+ <description> Used as a boost for cc field in Lucene query.
+ </description>
+</property>
+
+<!-- query-more plugin properties -->
+
+<property>
+ <name>query.type.boost</name>
+ <value>0.0</value>
+ <description> Used as a boost for type field in Lucene query.
+ </description>
+</property>
+
+<!-- query-site plugin properties -->
+
+<property>
+ <name>query.site.boost</name>
+ <value>0.0</value>
+ <description> Used as a boost for site field in Lucene query.
+ </description>
+</property>
+
+<!-- microformats-reltag plugin properties -->
+
+<property>
+ <name>query.tag.boost</name>
+ <value>1.0</value>
+ <description> Used as a boost for tag field in Lucene query.
+ </description>
+</property>
+
+<!-- language-identifier plugin properties -->
+
+<property>
+ <name>lang.ngram.min.length</name>
+ <value>1</value>
+ <description> The minimum size of ngrams to uses to identify
+ language (must be between 1 and lang.ngram.max.length).
+ The larger is the range between lang.ngram.min.length and
+ lang.ngram.max.length, the better is the identification, but
+ the slowest it is.
+ </description>
+</property>
+
+<property>
+ <name>lang.ngram.max.length</name>
+ <value>4</value>
+ <description> The maximum size of ngrams to uses to identify
+ language (must be between lang.ngram.min.length and 4).
+ The larger is the range between lang.ngram.min.length and
+ lang.ngram.max.length, the better is the identification, but
+ the slowest it is.
+ </description>
+</property>
+
+<property>
+ <name>lang.analyze.max.length</name>
+ <value>2048</value>
+ <description> The maximum bytes of data to uses to indentify
+ the language (0 means full content analysis).
+ The larger is this value, the better is the analysis, but the
+ slowest it is.
+ </description>
+</property>
+
+<property>
+ <name>query.lang.boost</name>
+ <value>0.0</value>
+ <description> Used as a boost for lang field in Lucene query.
+ </description>
+</property>
+
+<!-- Temporary Hadoop 0.17.x workaround. -->
+
+<property>
+ <name>hadoop.job.history.user.location</name>
+ <value>${hadoop.log.dir}/history/user</value>
+ <description>Hadoop 0.17.x comes with a default setting to create
+ user logs inside the output path of the job. This breaks some
+ Hadoop classes, which expect the output to contain only
+ part-XXXXX files. This setting changes the output to a
+ subdirectory of the regular log directory.
+ </description>
+</property>
+
+</configuration>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-site.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-site.xml
new file mode 100644
index 0000000..70975c2
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/nutch-site.xml
@@ -0,0 +1,58 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+<property>
+ <name>http.agent.name</name>
+ <value>Spacewalk</value>
+ <description>HTTP 'User-Agent' request header. MUST NOT be empty -
+ please set this to a single word uniquely related to your organization.
+
+ NOTE: You should also check other related properties:
+
+ http.robots.agents
+ http.agent.description
+ http.agent.url
+ http.agent.email
+ http.agent.version
+
+ and set their values appropriately.
+
+ </description>
+</property>
+
+<property>
+ <name>fetcher.server.delay</name>
+ <value>0</value>
+ <description>The number of seconds the fetcher will delay between
+ successive requests to the same server.</description>
+</property>
+
+<property>
+ <name>fetcher.threads.per.host</name>
+ <value>50</value>
+ <description>This number is the maximum number of threads that
+ should be allowed to access a host at one time.</description>
+</property>
+
+<property>
+ <name>plugin.folders</name>
+ <value>/usr/share/nutch/plugins</value>
+ <description>Directories where nutch plugins are located. Each
+ element may be a relative or absolute path. If absolute, it is used
+ as is. If relative, it is searched for on the classpath.</description>
+</property>
+
+<property>
+<name>plugin.includes</name>
+ <value>protocol-file|urlfilter-regex|parse-(xml|text|html|js|pdf)|index-basic|query-(basic|site|url)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
+</property>
+
+<property>
+ <name>file.content.limit</name> <value>-1</value>
+</property>
+
+</configuration>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.dtd b/search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.dtd
new file mode 100644
index 0000000..ae21045
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.dtd
@@ -0,0 +1,12 @@
+<!ELEMENT parse-plugins (mimeType+,aliases)>
+<!ELEMENT mimeType (plugin+)>
+<!ATTLIST mimeType name CDATA #REQUIRED>
+
+<!ELEMENT plugin EMPTY>
+<!ATTLIST plugin id CDATA #REQUIRED>
+<!ATTLIST plugin order CDATA ''>
+
+<!ELEMENT aliases (alias+)>
+<!ELEMENT alias EMPTY>
+<!ATTLIST alias name CDATA #REQUIRED>
+<!ATTLIST alias extension-id CDATA #REQUIRED>
\ No newline at end of file
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.xml
new file mode 100644
index 0000000..876d188
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/parse-plugins.xml
@@ -0,0 +1,221 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+
+ Author : mattmann
+ Description: This xml file represents a natural ordering for which parsing
+ plugin should get called for a particular mimeType.
+-->
+
+<parse-plugins>
+
+ <mimeType name="application/msword">
+ <plugin id="parse-msword" />
+ </mimeType>
+
+ <mimeType name="application/pdf">
+ <plugin id="parse-pdf" />
+ </mimeType>
+
+ <mimeType name="application/postscript">
+ <plugin id="parse-pdf" />
+ </mimeType>
+
+ <mimeType name="application/rss+xml">
+ <plugin id="parse-rss" />
+ <plugin id="feed" />
+ </mimeType>
+
+ <mimeType name="application/vnd.ms-excel">
+ <plugin id="parse-msexcel" />
+ </mimeType>
+
+ <mimeType name="application/vnd.ms-powerpoint">
+ <plugin id="parse-mspowerpoint" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.text">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.text-template">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.text-master">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.text-web">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.presentation">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.presentation-template">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.spreadsheet">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.oasis.opendocument.spreadsheet-template">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.sun.xml.calc">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.sun.xml.calc.template">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.sun.xml.impress">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.sun.xml.impress.template">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.sun.xml.writer">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/vnd.sun.xml.writer.template">
+ <plugin id="parse-oo" />
+ </mimeType>
+
+ <mimeType name="application/xhtml+xml">
+ <plugin id="parse-html" />
+ </mimeType>
+
+ <mimeType name="application/x-bzip2">
+ <!-- try and parse it with the zip parser -->
+ <plugin id="parse-zip" />
+ </mimeType>
+
+ <mimeType name="application/x-csh">
+ <plugin id="parse-text" />
+ </mimeType>
+
+ <mimeType name="application/x-gzip">
+ <!-- try and parse it with the zip parser -->
+ <plugin id="parse-zip" />
+ </mimeType>
+
+ <mimeType name="application/x-javascript">
+ <plugin id="parse-js" />
+ </mimeType>
+
+ <mimeType name="application/x-kword">
+ <!-- try and parse it with the word parser -->
+ <plugin id="parse-msword" />
+ </mimeType>
+
+ <mimeType name="application/x-kspread">
+ <!-- try and parse it with the msexcel parser -->
+ <plugin id="parse-msexcel" />
+ </mimeType>
+
+ <mimeType name="application/x-shockwave-flash">
+ <plugin id="parse-swf" />
+ </mimeType>
+
+ <mimeType name="application/zip">
+ <plugin id="parse-zip" />
+ </mimeType>
+
+ <mimeType name="text/html">
+ <plugin id="parse-html" />
+ </mimeType>
+
+ <mimeType name="text/plain">
+ <plugin id="parse-text" />
+ </mimeType>
+
+ <mimeType name="text/richtext">
+ <plugin id="parse-rtf" />
+ <plugin id="parse-msword" />
+ </mimeType>
+
+ <mimeType name="text/rtf">
+ <plugin id="parse-rtf" />
+ <plugin id="parse-msword" />
+ </mimeType>
+
+ <mimeType name="text/sgml">
+ <plugin id="parse-html" />
+ </mimeType>
+
+ <mimeType name="text/tab-separated-values">
+ <plugin id="parse-msexcel" />
+ </mimeType>
+
+ <mimeType name="text/xml">
+ <plugin id="parse-html" />
+ <plugin id="parse-rss" />
+ <plugin id="feed" />
+ </mimeType>
+
+ <!-- Types for parse-ext plugin: required for unit tests to pass. -->
+
+ <mimeType name="application/vnd.nutch.example.cat">
+ <plugin id="parse-ext" />
+ </mimeType>
+
+ <mimeType name="application/vnd.nutch.example.md5sum">
+ <plugin id="parse-ext" />
+ </mimeType>
+
+ <!-- alias mappings for parse-xxx names to the actual extension implementation
+ ids described in each plugin's plugin.xml file -->
+ <aliases>
+ <alias name="parse-ext" extension-id="ExtParser" />
+ <alias name="parse-html"
+ extension-id="org.apache.nutch.parse.html.HtmlParser" />
+ <alias name="parse-js" extension-id="JSParser" />
+ <alias name="parse-mp3"
+ extension-id="org.apache.nutch.parse.mp3.MP3Parser" />
+ <alias name="parse-msexcel"
+ extension-id="org.apache.nutch.parse.msexcel.MSExcelParser" />
+ <alias name="parse-mspowerpoint"
+ extension-id="org.apache.nutch.parse.mspowerpoint.MSPowerPointParser" />
+ <alias name="parse-msword"
+ extension-id="org.apache.nutch.parse.msword.MSWordParser" />
+ <alias name="parse-oo"
+ extension-id="org.apache.nutch.parse.oo.OpenDocument.Text" />
+ <alias name="parse-pdf"
+ extension-id="org.apache.nutch.parse.pdf.PdfParser" />
+ <alias name="parse-rss"
+ extension-id="org.apache.nutch.parse.rss.RSSParser" />
+ <alias name="feed"
+ extension-id="org.apache.nutch.parse.feed.FeedParser" />
+ <alias name="parse-rtf"
+ extension-id="org.apache.nutch.parse.rtf.RTFParseFactory" />
+ <alias name="parse-swf"
+ extension-id="org.apache.nutch.parse.swf.SWFParser" />
+ <alias name="parse-text"
+ extension-id="org.apache.nutch.parse.text.TextParser" />
+ <alias name="parse-zip"
+ extension-id="org.apache.nutch.parse.zip.ZipParser" />
+ </aliases>
+
+</parse-plugins>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/prefix-urlfilter.txt b/search-server/spacewalk-search/nutch/crawl_jsp/conf/prefix-urlfilter.txt
new file mode 100644
index 0000000..491dc1f
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/prefix-urlfilter.txt
@@ -0,0 +1,21 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# config file for urlfilter-prefix plugin
+
+http://
+https://
+ftp://
+file://
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-normalize.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-normalize.xml
new file mode 100644
index 0000000..8d8bad1
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-normalize.xml
@@ -0,0 +1,66 @@
+<?xml version="1.0"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+<!-- This is the configuration file for the RegexUrlNormalize Class.
+ This is intended so that users can specify substitutions to be
+ done on URLs. The regex engine that is used is Perl5 compatible.
+ The rules are applied to URLs in the order they occur in this file. -->
+
+<!-- WATCH OUT: an xml parser reads this file an ampersands must be
+ expanded to & -->
+
+<!-- The following rules show how to strip out session IDs, default pages,
+ interpage anchors, etc. Order does matter! -->
+<regex-normalize>
+
+<!-- removes session ids from urls (such as jsessionid and PHPSESSID) -->
+<regex>
+ <pattern>([;_]?((?i)l|j|bv_)?((?i)sid|phpsessid|sessionid)=.*?)(\?|&|#|$)</pattern>
+ <substitution>$4</substitution>
+</regex>
+
+<!-- changes default pages into standard for /index.html, etc. into /
+<regex>
+ <pattern>/((?i)index|default)\.((?i)js[pf]{1}?[afx]?|cgi|cfm|asp[x]?|[psx]?htm[l]?|php[3456]?)(\?|&|#|$)</pattern>
+ <substitution>/$3</substitution>
+</regex> -->
+
+<!-- removes interpage href anchors such as site.com#location -->
+<regex>
+ <pattern>#.*?(\?|&|$)</pattern>
+ <substitution>$1</substitution>
+</regex>
+
+<!-- cleans ?&var=value into ?var=value -->
+<regex>
+ <pattern>\?&</pattern>
+ <substitution>\?</substitution>
+</regex>
+
+<!-- cleans multiple sequential ampersands into a single ampersand -->
+<regex>
+ <pattern>&{2,}</pattern>
+ <substitution>&</substitution>
+</regex>
+
+<!-- removes trailing ? -->
+<regex>
+ <pattern>[\?&\.]$</pattern>
+ <substitution></substitution>
+</regex>
+
+</regex-normalize>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-urlfilter.txt b/search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-urlfilter.txt
new file mode 100644
index 0000000..fe56603
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/regex-urlfilter.txt
@@ -0,0 +1,38 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+# The default url filter.
+# Better for whole-internet crawling.
+
+# Each non-comment, non-blank line contains a regular expression
+# prefixed by '+' or '-'. The first matching pattern in the file
+# determines whether a URL is included or ignored. If no pattern
+# matches, the URL is ignored.
+
+# skip file: ftp: and mailto: urls
+-^(file|ftp|mailto):
+
+# skip image and other suffixes we can't yet parse
+-\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP)$
+
+# skip URLs containing certain characters as probable queries, etc.
+-[?*!@=]
+
+# skip URLs with slash-delimited segment that repeats 3+ times, to break loops
+-.*(/[^/]+)/[^/]+\1/[^/]+\1/
+
+# accept anything else
++.
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/slaves b/search-server/spacewalk-search/nutch/crawl_jsp/conf/slaves
new file mode 100644
index 0000000..2fbb50c
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/slaves
@@ -0,0 +1 @@
+localhost
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/subcollections.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/subcollections.xml
new file mode 100644
index 0000000..7b8805d
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/subcollections.xml
@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+<subcollections>
+ <subcollection>
+ <name>nutch</name>
+ <id>nutch</id>
+ <whitelist>
+http://lucene.apache.org/nutch/
+http://wiki.apache.org/nutch/
+ </whitelist>
+ <blacklist />
+ </subcollection>
+</subcollections>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/suffix-urlfilter.txt b/search-server/spacewalk-search/nutch/crawl_jsp/conf/suffix-urlfilter.txt
new file mode 100644
index 0000000..b510d4a
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/suffix-urlfilter.txt
@@ -0,0 +1,91 @@
+# config file for urlfilter-suffix plugin
+
+# case-insensitive, allow unknown suffixes
++I
+# uncomment the line below to filter on url path
+#+P
+
+### prohibit these
+# pictures
+.gif
+.jpg
+.jpeg
+.bmp
+.png
+.tif
+.tiff
+.ico
+.eps
+.ps
+.wmf
+.fpx
+.cur
+.ani
+.img
+.lwf
+.pcd
+.psp
+.psd
+.tga
+.xbm
+.xpm
+
+# web-formats
+.css
+
+# archives/packages
+.arj
+.arc
+.7z
+.cab
+.lzw
+.lha
+.lzh
+.zip
+.gz
+.tar
+.tgz
+.sit
+.rpm
+.deb
+.pkg
+
+# audio/video
+.mid
+.midi
+.rmi
+.mpeg
+.mpg
+.mpe
+.mp3
+.mp2
+.aac
+.mov
+.fla
+.flv
+.ra
+.ram
+.rm
+.rmv
+.wma
+.wmv
+.wav
+.wave
+.ogg
+.avi
+.au
+.snd
+
+# executables
+.exe
+.com
+
+# windows links
+.lnk
+
+# typo3-extensions
+.t3x
+
+# disc-images
+.iso
+.bin
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/conf/tika-mimetypes.xml b/search-server/spacewalk-search/nutch/crawl_jsp/conf/tika-mimetypes.xml
new file mode 100644
index 0000000..ce84078
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/conf/tika-mimetypes.xml
@@ -0,0 +1,367 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+
+ Description: This xml file defines the valid mime types used by Tika.
+ The mime types within this file are based on the types in the mime-types.xml
+ file available in Apache Nutch.
+-->
+
+<mime-info>
+
+ <mime-type type="text/plain">
+ <magic priority="50">
+ <match value="This is TeX," type="string" offset="0" />
+ <match value="This is METAFONT," type="string" offset="0" />
+ </magic>
+ <glob pattern="*.txt" />
+ <glob pattern="*.asc" />
+ </mime-type>
+
+ <mime-type type="text/html">
+ <magic priority="50">
+ <match value="<!DOCTYPE HTML" type="string"
+ offset="0:64" />
+ <match value="<!doctype html" type="string"
+ offset="0:64" />
+ <match value="<HEAD" type="string" offset="0:64" />
+ <match value="<head" type="string" offset="0:64" />
+ <match value="<TITLE" type="string" offset="0:64" />
+ <match value="<title" type="string" offset="0:64" />
+ <match value="<html" type="string" offset="0:64" />
+ <match value="<HTML" type="string" offset="0:64" />
+ <match value="<BODY" type="string" offset="0" />
+ <match value="<body" type="string" offset="0" />
+ <match value="<TITLE" type="string" offset="0" />
+ <match value="<title" type="string" offset="0" />
+ <match value="<!--" type="string" offset="0" />
+ <match value="<h1" type="string" offset="0" />
+ <match value="<H1" type="string" offset="0" />
+ <match value="<!doctype HTML" type="string" offset="0" />
+ <match value="<!DOCTYPE html" type="string" offset="0" />
+ </magic>
+ <glob pattern="*.html" />
+ <glob pattern="*.htm" />
+ </mime-type>
+
+ <mime-type type="application/xhtml+xml">
+ <glob pattern="*.xhtml" />
+ <root-XML namespaceURI='http://www.w3.org/1999/xhtml '
+ localName='html' />
+ </mime-type>
+
+ <mime-type type="application/vnd.ms-powerpoint">
+ <glob pattern="*.ppz" />
+ <glob pattern="*.ppt" />
+ <glob pattern="*.pps" />
+ <glob pattern="*.pot" />
+ <magic priority="50">
+ <match value="0xcfd0e011" type="little32" offset="0" />
+ </magic>
+ </mime-type>
+
+ <mime-type type="application/vnd.ms-excel">
+ <magic priority="50">
+ <match value="Microsoft Excel 5.0 Worksheet" type="string"
+ offset="2080" />
+ </magic>
+ <glob pattern="*.xls" />
+ <glob pattern="*.xlc" />
+ <glob pattern="*.xll" />
+ <glob pattern="*.xlm" />
+ <glob pattern="*.xlw" />
+ <glob pattern="*.xla" />
+ <glob pattern="*.xlt" />
+ <glob pattern="*.xld" />
+ <alias type="application/msexcel" />
+ </mime-type>
+
+ <mime-type type="application/vnd.oasis.opendocument.text">
+ <glob pattern="*.odt" />
+ </mime-type>
+
+
+ <mime-type type="application/zip">
+ <alias type="application/x-zip-compressed" />
+ <magic priority="40">
+ <match value="PK\003\004" type="string" offset="0" />
+ </magic>
+ <glob pattern="*.zip" />
+ </mime-type>
+
+ <mime-type type="application/vnd.oasis.opendocument.text">
+ <glob pattern="*.oth" />
+ </mime-type>
+
+ <mime-type type="application/msword">
+ <magic priority="50">
+ <match value="\x31\xbe\x00\x00" type="string" offset="0" />
+ <match value="PO^Q`" type="string" offset="0" />
+ <match value="\376\067\0\043" type="string" offset="0" />
+ <match value="\333\245-\0\0\0" type="string" offset="0" />
+ <match value="Microsoft Word 6.0 Document" type="string"
+ offset="2080" />
+ <match value="Microsoft Word document data" type="string"
+ offset="2112" />
+ </magic>
+ <glob pattern="*.doc" />
+ <alias type="application/vnd.ms-word" />
+ </mime-type>
+
+ <mime-type type="application/octet-stream">
+ <magic priority="50">
+ <match value="\037\036" type="string" offset="0" />
+ <match value="017437" type="host16" offset="0" />
+ <match value="0x1fff" type="host16" offset="0" />
+ <match value="\377\037" type="string" offset="0" />
+ <match value="0145405" type="host16" offset="0" />
+ </magic>
+ <glob pattern="*.bin" />
+ </mime-type>
+
+ <mime-type type="application/pdf">
+ <magic priority="50">
+ <match value="%PDF-" type="string" offset="0" />
+ </magic>
+ <glob pattern="*.pdf" />
+ <alias type="application/x-pdf" />
+ </mime-type>
+
+ <mime-type type="application/atom+xml">
+ <root-XML localName="feed"
+ namespaceURI="http://purl.org/atom/ns# " />
+ </mime-type>
+
+ <mime-type type="application/mac-binhex40">
+ <glob pattern="*.hqx" />
+ </mime-type>
+
+ <mime-type type="application/mac-compactpro">
+ <glob pattern="*.cpt" />
+ </mime-type>
+
+ <mime-type type="application/rtf">
+ <glob pattern="*.rtf"/>
+ <alias type="text/rtf" />
+ </mime-type>
+
+ <mime-type type="application/rss+xml">
+ <alias type="text/rss" />
+ <root-XML localName="rss" />
+ <root-XML namespaceURI="http://purl.org/rss/1.0/ " />
+ <glob pattern="*.rss" />
+ </mime-type>
+
+ <!-- added in by mattmann -->
+ <mime-type type="application/xml">
+ <alias type="text/xml" />
+ <glob pattern="*.xml" />
+ </mime-type>
+
+ <mime-type type="application/x-mif">
+ <alias type="application/vnd.mif" />
+ </mime-type>
+
+ <mime-type type="application/vnd.wap.wbxml">
+ <glob pattern="*.wbxml" />
+ </mime-type>
+
+ <mime-type type="application/vnd.wap.wmlc">
+ <_comment>Compiled WML Document</_comment>
+ <glob pattern="*.wmlc" />
+ </mime-type>
+
+ <mime-type type="application/vnd.wap.wmlscriptc">
+ <_comment>Compiled WML Script</_comment>
+ <glob pattern="*.wmlsc" />
+ </mime-type>
+
+ <mime-type type="text/vnd.wap.wmlscript">
+ <_comment>WML Script</_comment>
+ <glob pattern="*.wmls" />
+ </mime-type>
+
+ <mime-type type="application/x-bzip">
+ <alias type="application/x-bzip2" />
+ </mime-type>
+
+ <mime-type type="application/x-bzip-compressed-tar">
+ <glob pattern="*.tbz" />
+ <glob pattern="*.tbz2" />
+ </mime-type>
+
+ <mime-type type="application/x-cdlink">
+ <_comment>Virtual CD-ROM CD Image File</_comment>
+ <glob pattern="*.vcd" />
+ </mime-type>
+
+ <mime-type type="application/x-director">
+ <_comment>Shockwave Movie</_comment>
+ <glob pattern="*.dcr" />
+ <glob pattern="*.dir" />
+ <glob pattern="*.dxr" />
+ </mime-type>
+
+ <mime-type type="application/x-futuresplash">
+ <_comment>Macromedia FutureSplash File</_comment>
+ <glob pattern="*.spl" />
+ </mime-type>
+
+ <mime-type type="application/x-java">
+ <alias type="application/java" />
+ </mime-type>
+
+ <mime-type type="application/x-koan">
+ <_comment>SSEYO Koan File</_comment>
+ <glob pattern="*.skp" />
+ <glob pattern="*.skd" />
+ <glob pattern="*.skt" />
+ <glob pattern="*.skm" />
+ </mime-type>
+
+ <mime-type type="application/x-latex">
+ <_comment>LaTeX Source Document</_comment>
+ <glob pattern="*.latex" />
+ </mime-type>
+
+ <!-- JC CHANGED
+ <mime-type type="application/x-mif">
+ <_comment>FrameMaker MIF document</_comment>
+ <glob pattern="*.mif"/>
+ </mime-type> -->
+
+ <mime-type type="application/x-ms-dos-executable">
+ <alias type="application/x-dosexec" />
+ </mime-type>
+
+ <mime-type type="application/ogg">
+ <alias type="application/x-ogg" />
+ </mime-type>
+
+ <mime-type type="application/x-rar">
+ <alias type="application/x-rar-compressed" />
+ </mime-type>
+
+ <mime-type type="application/x-shellscript">
+ <alias type="application/x-sh" />
+ </mime-type>
+
+ <mime-type type="application/xhtml+xml">
+ <glob pattern="*.xht" />
+ </mime-type>
+
+ <mime-type type="audio/midi">
+ <glob pattern="*.kar" />
+ </mime-type>
+
+ <mime-type type="audio/x-pn-realaudio">
+ <alias type="audio/x-realaudio" />
+ </mime-type>
+
+ <mime-type type="image/tiff">
+ <magic priority="50">
+ <match value="0x4d4d2a00" type="string" offset="0" />
+ <match value="0x49492a00" type="string" offset="0" />
+ </magic>
+ </mime-type>
+
+ <mime-type type="message/rfc822">
+ <magic priority="50">
+ <match type="string" value="Relay-Version:" offset="0" />
+ <match type="string" value="#! rnews" offset="0" />
+ <match type="string" value="N#! rnews" offset="0" />
+ <match type="string" value="Forward to" offset="0" />
+ <match type="string" value="Pipe to" offset="0" />
+ <match type="string" value="Return-Path:" offset="0" />
+ <match type="string" value="From:" offset="0" />
+ <match type="string" value="Message-ID:" offset="0" />
+ <match type="string" value="Date:" offset="0" />
+ </magic>
+ </mime-type>
+
+ <mime-type type="application/x-javascript">
+ <glob pattern="*.js" />
+ </mime-type>
+
+
+ <mime-type type="image/vnd.wap.wbmp">
+ <_comment>Wireless Bitmap File Format</_comment>
+ <glob pattern="*.wbmp" />
+ </mime-type>
+
+ <mime-type type="image/x-psd">
+ <alias type="image/photoshop" />
+ </mime-type>
+
+ <mime-type type="image/x-xcf">
+ <alias type="image/xcf" />
+ <magic priority="50">
+ <match type="string" value="gimp xcf " offset="0" />
+ </magic>
+ </mime-type>
+
+ <mime-type type="application/x-shockwave-flash">
+ <glob pattern="*.swf"/>
+ <magic priority="50">
+ <match type="string" value="FWS" offset="0"/>
+ <match type="string" value="CWS" offset="0"/>
+ </magic>
+ </mime-type>
+
+ <mime-type type="model/iges">
+ <_comment>
+ Initial Graphics Exchange Specification Format
+ </_comment>
+ <glob pattern="*.igs" />
+ <glob pattern="*.iges" />
+ </mime-type>
+
+ <mime-type type="model/mesh">
+ <glob pattern="*.msh" />
+ <glob pattern="*.mesh" />
+ <glob pattern="*.silo" />
+ </mime-type>
+
+ <mime-type type="model/vrml">
+ <glob pattern="*.vrml" />
+ </mime-type>
+
+ <mime-type type="text/x-tcl">
+ <alias type="application/x-tcl" />
+ </mime-type>
+
+ <mime-type type="text/x-tex">
+ <alias type="application/x-tex" />
+ </mime-type>
+
+ <mime-type type="text/x-texinfo">
+ <alias type="application/x-texinfo" />
+ </mime-type>
+
+ <mime-type type="text/x-troff-me">
+ <alias type="application/x-troff-me" />
+ </mime-type>
+
+ <mime-type type="video/vnd.mpegurl">
+ <glob pattern="*.mxu" />
+ </mime-type>
+
+ <mime-type type="x-conference/x-cooltalk">
+ <_comment>Cooltalk Audio</_comment>
+ <glob pattern="*.ice" />
+ </mime-type>
+
+</mime-info>
diff --git a/search-server/spacewalk-search/nutch/crawl_jsp/urls/urls.txt b/search-server/spacewalk-search/nutch/crawl_jsp/urls/urls.txt
new file mode 100644
index 0000000..020ed3b
--- /dev/null
+++ b/search-server/spacewalk-search/nutch/crawl_jsp/urls/urls.txt
@@ -0,0 +1,7 @@
+file:///shared/repo/trunk/eng/docs/guides/channel-mgmt/en/
+file:///shared/repo/trunk/eng/docs/guides/client-config/en/
+file:///shared/repo/trunk/eng/docs/guides/proxy/rhn511/en/
+file:///shared/repo/trunk/eng/docs/guides/reference/en/
+file:///shared/repo/trunk/eng/docs/guides/satellite/en/
+file:///shared/repo/trunk/eng/docs/release-notes/satellite/rhn510/en-US/
+
diff --git a/search-server/spacewalk-search/rhn_search_daemon_dev.conf b/search-server/spacewalk-search/rhn_search_daemon_dev.conf
new file mode 100644
index 0000000..964fe46
--- /dev/null
+++ b/search-server/spacewalk-search/rhn_search_daemon_dev.conf
@@ -0,0 +1,45 @@
+wrapper.java.command=/usr/bin/java
+wrapper.java.mainclass=com.redhat.satellite.search.Main
+wrapper.java.classpath.1=%PWD%/build/
+wrapper.java.classpath.2=%PWD%/lib/commons-lang-2.0.jar
+wrapper.java.classpath.3=%PWD%/lib/commons-logging-1.1.jar
+wrapper.java.classpath.4=%PWD%/lib/ibatis-2.3.0.677.jar
+wrapper.java.classpath.5=%PWD%/lib/log4j-1.2.8.jar
+wrapper.java.classpath.6=%PWD%/lib/lucene-core-2.3.2.jar
+wrapper.java.classpath.7=%PWD%/lib/ojdbc14-1.10.jar
+wrapper.java.classpath.8=%PWD%/lib/picocontainer-1.3.jar
+wrapper.java.classpath.9=%PWD%/lib/quartz-1.5.1.jar
+wrapper.java.classpath.10=%PWD%/lib/redstone-xmlrpc-1.1_20071120.jar
+wrapper.java.classpath.11=%PWD%/lib/redstone-xmlrpc-client-1.1_20071120.jar
+wrapper.java.classpath.12=%PWD%/lib/simple-core-3.1.3.jar
+wrapper.java.classpath.13=/usr/share/java/tanukiwrapper.jar
+wrapper.java.classpath.14=%PWD%/lib/logdriver-0.1.jar
+wrapper.java.classpath.15=%PWD%/lib/lucene-analyzers-2.3.2.jar
+wrapper.java.classpath.16=/usr/share/nutch
+wrapper.java.classpath.17=/usr/share/nutch/conf
+wrapper.java.classpath.18=%PWD%/lib/nutch-2008-12-01_04-01-21.jar
+wrapper.java.classpath.19=%PWD%/lib/hadoop-0.18.1-core.jar
+wrapper.java.classpath.20=%PWD%/lib/commons-httpclient-3.0.jar
+wrapper.java.classpath.21=%PWD%/lib/oro-2.0.8.jar
+wrapper.java.classpath.22=%PWD%/lib/icu4j-3_8_1.jar
+wrapper.java.classpath.23=%PWD%/lib/icu4j-charsets-3_8_1.jar
+wrapper.java.classpath.24=%PWD%/lib/commons-cli-1.0.jar
+wrapper.java.classpath.25=%PWD%/lib/commons-codec-1.2.jar
+wrapper.java.classpath.26=%PWD%/lib/tika-0.1-incubating.jar
+
+
+wrapper.java.library.path.1=/usr/lib
+wrapper.java.library.path.2=/usr/lib64
+wrapper.console.format=PM
+wrapper.console.loglevel=INFO
+wrapper.logfile=%PWD%/rhn_search_daemon.log
+wrapper.logfile.format=LPTM
+wrapper.logfile.loglevel=DEBUG
+wrapper.logfile.maxsize=5m
+wrapper.logfile.maxfiles=0
+wrapper.syslog.loglevel=DEBUG
+
+wrapper.java.additional.1=-Dsearch.config.dir=%PWD%/src/config/search
+wrapper.java.additional.2=-Xdebug
+wrapper.java.additional.3=-Xnoagent
+wrapper.java.additional.4=-Xrunjdwp:transport=dt_socket,address=9999,server=y,suspend=n
diff --git a/search-server/spacewalk-search/run.sh b/search-server/spacewalk-search/run.sh
new file mode 100755
index 0000000..0bbf58a
--- /dev/null
+++ b/search-server/spacewalk-search/run.sh
@@ -0,0 +1,17 @@
+#!/bin/bash
+rpm -q tanukiwrapper > /dev/null
+RETURN_VAL=$?
+if [ ! "$RETURN_VAL" -eq "0" ]; then
+ echo "Please install tanukiwrapper: up2date tanukiwrapper or yum install tanukiwrapper"
+ exit 1;
+fi
+
+if [ ! -r "/etc/rhn/search/rhn_search.conf" ]; then
+ echo "you need to symlink rhn_search.conf as /etc/rhn/search/rhn_search.conf"
+ exit 2;
+fi
+
+echo "starting server"
+export CLASSPATH=`pwd`/build
+#java -Djava.library.path=/usr/lib -classpath `build-classpath-directory lib dist` com.redhat.satellite.search.Main
+/usr/sbin/tanukiwrapper `pwd`/rhn_search_daemon_dev.conf wrapper.pidfile=`pwd`/rhn-search.pid wrapper.daemonize=FALSE
diff --git a/search-server/spacewalk-search/scripts/Reindex.groovy b/search-server/spacewalk-search/scripts/Reindex.groovy
new file mode 100644
index 0000000..49e94e0
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/Reindex.groovy
@@ -0,0 +1,43 @@
+import com.redhat.satellite.search.db.DatabaseManager;
+import com.redhat.satellite.search.db.WriteQuery;
+import com.redhat.satellite.search.config.Configuration;
+
+def deleteQuery(config, queryName) {
+ DatabaseManager databaseManager = new DatabaseManager(config)
+ WriteQuery query = null;
+ try {
+ query = databaseManager.getWriterQuery(queryName);
+ query.delete(null);
+ }
+ finally {
+ query.close();
+ }
+}
+
+/**
+ Currently, only handles Errata and Packages
+ Need to add: User, System, Docs
+ **/
+Configuration config = new Configuration()
+deleteQueries = ["deleteLastErrata", "deleteLastPackage",
+ "deleteLastServer", "deleteLastHardwareDevice",
+ "deleteLastSnapshotTag", "deleteLastServerCustomInfo"]
+deleteQueries.each{deleteQuery(config, it)}
+
+println "Database has been prepared so we can re-index."
+
+indexWorkDir = config.getString("search.index_work_dir", null);
+println "Previous indexes will be deleted on filesystem under ${indexWorkDir}"
+
+dirs = [indexWorkDir+"/package", indexWorkDir+"/errata",
+ indexWorkDir+"/server", indexWorkDir+"/hwdevice",
+ indexWorkDir+"/snapshotTag", indexWorkDir+"/serverCustomInfo"]
+dirs.each {
+ cmd = "rm -r $it"
+ def proc = cmd.execute()
+ proc.waitFor()
+}
+
+
+
+
diff --git a/search-server/spacewalk-search/scripts/build.properties b/search-server/spacewalk-search/scripts/build.properties
new file mode 100644
index 0000000..6dcc9ac
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/build.properties
@@ -0,0 +1,22 @@
+java.src.dir=src/java
+config.src.dir=src/config
+java.lib.dir=lib
+java.task.lib.dir=../task-lib
+report.dir=report
+build.dir=build
+build.instrument.dir=instrumented
+dist.dir=dist
+jar.name=spacewalk-search-scripts
+jar.version=1.0
+jar.file.name=${jar.name}-${jar.version}.jar
+ivyserver= http://jmrodri.fedorapeople.org
+ivy.log.module.when.found=false
+ivy.log.resolved.revision=false
+# Checkstyle config entries
+checkstyle.cache.file=.checkstyle_cache
+checkstyle.header.file=./buildconf/LICENSE.txt
+javadoc.method.scope=public
+javadoc.type.scope=package
+javadoc.var.scope=package
+javadoc.lazy=true
+jpackage.jars="commons-lang commons-logging redstone-xmlrpc redstone-xmlrpc-client quartz tanukiwrapper log4j commons-httpclient oro commons-cli commons-codec"
diff --git a/search-server/spacewalk-search/scripts/build.xml b/search-server/spacewalk-search/scripts/build.xml
new file mode 100644
index 0000000..f45e670
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/build.xml
@@ -0,0 +1,256 @@
+<project name="search-server" basedir="." default="all">
+ <import file="./buildconf/build-utils.xml" />
+
+ <property file="build.properties" />
+
+ <path id="project.taskjars">
+ <fileset dir="${java.task.lib.dir}" includes="**/*.jar" />
+ </path>
+
+ <path id="project.classpath">
+ <fileset dir="${java.lib.dir}" includes="**/*.jar" />
+ <fileset dir="${java.task.lib.dir}" >
+ <include name="junit*.jar" />
+ <include name="emma*.jar" />
+ </fileset>
+ </path>
+
+ <path id="test.classpath">
+ <pathelement location="${build.dir}" />
+ <path refid="project.classpath" />
+ <pathelement location="${basedir}/src/config" />
+ </path>
+
+ <path id="run.classpath">
+ <path refid="project.classpath" />
+ <pathelement location="${dist.dir}/${jar.file.name}"/>
+ </path>
+
+ <target name="init-tasks">
+ <taskdef name="ivy-retrieve"
+ classname="fr.jayasoft.ivy.ant.IvyRetrieve"
+ classpathref="project.taskjars"/>
+ <taskdef name="ivy-configure"
+ classname="fr.jayasoft.ivy.ant.IvyConfigure"
+ classpathref="project.taskjars"/>
+ <taskdef name="ivy-resolve"
+ classname="fr.jayasoft.ivy.ant.IvyResolve"
+ classpathref="project.taskjars"/>
+ <taskdef name="ivy-publish"
+ classname="fr.jayasoft.ivy.ant.IvyPublish"
+ classpathref="project.taskjars"/>
+ <taskdef resource="checkstyletask.properties">
+ <classpath>
+ <pathelement path="${java.task.lib.dir}/checkstyle-4.1.jar" />
+ <pathelement path="${java.task.lib.dir}/commons-beanutils-1.7.0.jar" />
+ <pathelement path="${java.task.lib.dir}/commons-logging-1.0.4.jar" />
+ <pathelement path="${java.task.lib.dir}/antlr-2.7.6.jar" />
+ <pathelement path="${java.task.lib.dir}/regexp-1.3.jar" />
+ </classpath>
+ </taskdef>
+ <taskdef resource="emma_ant.properties" classpathref="project.taskjars" />
+ <taskdef resource="net/sf/antcontrib/antlib.xml">
+ <classpath>
+ <pathelement location="${java.task.lib.dir}/ant-contrib-1.0.jar"/>
+ </classpath>
+ </taskdef>
+ </target>
+
+ <target name="check-testcase-name" if="testcase" depends="init-tasks">
+ <propertyregex property="valid.testcase"
+ input="${testcase}"
+ regexp="(.*)Test$"
+ select="\1"
+ casesensitive="true" />
+ </target>
+
+ <target name="check-testcase" depends="check-testcase-name" if="testcase"
+ unless="valid.testcase">
+ <fail message="Invalid testcase name: ${testcase}. Class name must look like .*Test"/>
+ </target>
+
+ <target name="test" depends="compile, check-testcase"
+ description="Run the tests (use -Dtestcase=<testcase>)">
+ <mkdir dir="${report.dir}" />
+ <!-- set testcase to wildcard "*" to test everything, unless
+ a specific testcase name was supplied. -->
+ <if>
+ <not>
+ <isset property="${testcase}" />
+ </not>
+ <then>
+ <property name="testcase" value="*Test"/>
+ </then>
+ </if>
+ <junit>
+ <sysproperty key="rhn.config.dir" value="/etc/rhn" />
+ <sysproperty key="search.config.dir" value="src/config/search" />
+ <sysproperty key="log4j.configuration" value="log4j.test.properties" />
+ <classpath refid="test.classpath" />
+ <formatter type="brief" usefile="false" />
+ <formatter type="xml" />
+ <batchtest fork="yes" todir="${report.dir}">
+ <fileset dir="${build.dir}" includes="**/${testcase}.class" />
+ </batchtest>
+ </junit>
+ </target>
+
+ <target name="checkstyle" depends="init-tasks, package">
+ <delete dir="${report.dir}" />
+ <mkdir dir="${report.dir}" />
+ <checkstyle config="checkstyle.xml" failOnViolation="true" >
+ <property key="javadoc.method.scope" value="public" />
+ <property key="javadoc.type.scope" value="package" />
+ <property key="javadoc.var.scope" value="package" />
+ <property key="javadoc.lazy" value="${javadoc.lazy}" />
+ <fileset dir="${java.src.dir}" >
+ <include name="**/*.java" />
+ <exclude name="**/tests/**" />
+ </fileset>
+ <classpath>
+ <fileset dir="${java.lib.dir}" includes="**/*.jar" />
+ <fileset dir="${java.task.lib.dir}" includes="junit*.jar" />
+ <fileset dir="${dist.dir}" includes="${jar.file.name}" />
+ </classpath>
+ <formatter type="plain" />
+ <formatter type="xml" toFile="${report.dir}/checkstyle_report.xml" />
+ </checkstyle>
+ </target>
+
+ <target name="resolve-local" description="resolve jars via jpackage" if="installbuild">
+ <copy toDir="${java.lib.dir}" overwrite="true">
+ <fileset dir="buildconf/tempjars">
+ <include name="**/*.jar" />
+ </fileset>
+ </copy>
+
+ <jpackage-deps jars="${jpackage.jars}" dir="${java.lib.dir}" />
+ </target>
+
+ <target name="resolve-ivy" description="retrieve dependencies with ivy"
+ depends="init-tasks" unless="installbuild">
+ <!-- properties set here to show we are overriding default ivy values -->
+ <property name="ivy.default.ivy.user.dir" value="${user.home}/.ivy/search-server"/>
+ <property name="ivy.local.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
+ <property name="ivy.ivyrep.default.ivy.root" value="${ivyserver}/ivy/" />
+ <property name="ivy.ivyrep.default.artifact.root" value="${ivyserver}/ivy/" />
+ <property name="ivy.ivyrep.default.artifact.pattern" value="[artifact]-[revision].[ext]" />
+ <ivy-retrieve/>
+ </target>
+
+ <target name="resolve" depends="resolve-ivy,resolve-local" />
+
+ <target name="prep">
+ <mkdir dir="${build.dir}" />
+ <mkdir dir="${dist.dir}" />
+ <mkdir dir="${java.lib.dir}" />
+ </target>
+
+ <target name="clean">
+ <delete dir="${build.dir}" />
+ <delete dir="${build.instrument.dir}" />
+ <delete dir="${dist.dir}" />
+ <delete dir="${java.lib.dir}" />
+ <delete dir="${report.dir}" />
+ <delete file="coverage.ec" />
+ <delete file="rhn_search_daemon.log" />
+ </target>
+
+ <target name="compile" depends="prep, resolve">
+ <javac srcdir="${java.src.dir}"
+ classpathref="project.classpath"
+ destdir="${build.dir}"
+ deprecation="on"
+ excludesfile="buildconf/exclude"
+ debug="on" />
+ <copy file="${config.src.dir}/log4j.properties" todir="${build.dir}" />
+ </target>
+
+ <target name="package" depends="compile">
+ <jar basedir="${build.dir}"
+ destfile="${dist.dir}/${jar.file.name}"
+ excludes="**/tests/**"
+ includes="**/**" />
+ </target>
+
+ <target name="create-local-repo" description="Create a local Ivy repo">
+ <mkdir dir="${user.home}/.ivy/search-server/local/" />
+ </target>
+
+ <target name="clean-cache" description="Removes the Ivy jar cache">
+ <delete dir="${lib.dir}" quiet="true" />
+ <delete dir="${user.home}/.ivy/search-server/cache/" quiet="true" />
+ </target>
+
+ <target name="all" depends="package" />
+
+ <target name="init-install">
+ <property name="installbuild" value="true"/>
+ </target>
+
+ <target name="install" depends="init-install,package" />
+
+ <target name="instrument" depends="init-tasks">
+ <mkdir dir="${report.dir}" />
+ <mkdir dir="${build.instrument.dir}" />
+
+ <emma enabled="true">
+ <instr merge="no"
+ mode="overwrite"
+ instrpath="${build.dir}"
+ outfile="${report.dir}/coverage.em" >
+ <filter excludes="*Exception" />
+ <filter excludes="*.tests.*" />
+ </instr>
+ <!--
+ <instr outdir="${build.instrument.dir}" merge="no"
+ instrpath="${build.dir}"
+ mode="fullcopy"
+ outfile="${report.dir}/coverage.em" >
+ <filter excludes="*Exception" />
+ <filter excludes="*.tests.*" />
+ </instr>
+ -->
+ </emma>
+
+ <!--
+ <copy toDir="${build.instrument.dir}/classes">
+ <fileset dir="${build.dir}">
+ <include name="**/*.xml" />
+ </fileset>
+ </copy>
+ -->
+ </target>
+
+ <target name="coverage-report" depends="instrument">
+ <emma enabled="true">
+ <report sourcepath="${java.src.dir}"
+ sort="+block,+name,+method,+class"
+ metrics="method:70,block:80,line:80,class:100">
+ <fileset dir="${report.dir}" includes="*.em" />
+ <fileset dir="." includes="*.ec" />
+ <html outfile="${report.dir}/emma.html"
+ depth="method"
+ columns="name,class,method,block,line" />
+ <xml outfile="${report.dir}/emma.xml"
+ depth="method"
+ columns="name,class,method,block,line" />
+ </report>
+ </emma>
+ </target>
+
+
+ <target name="indexDocs" depends="package"
+ description="Crawls help docs with nutch and generates a lucene index">
+ <java
+ classname="com.redhat.satellite.search.index.docs.WebCrawl"
+ dir="${basedir}"
+ fork="true"
+ failonerror="true">
+
+ <arg value="-h"/>
+ <classpath refid="run.classpath" />
+ </java>
+ </target>
+
+</project>
diff --git a/search-server/spacewalk-search/scripts/buildconf/LICENSE.txt b/search-server/spacewalk-search/scripts/buildconf/LICENSE.txt
new file mode 100644
index 0000000..629462a
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/buildconf/LICENSE.txt
@@ -0,0 +1,14 @@
+/**
+ * Copyright (c) 2008 Red Hat, Inc.
+ *
+ * This software is licensed to you under the GNU General Public License,
+ * version 2 (GPLv2). There is NO WARRANTY for this software, express or
+ * implied, including the implied warranties of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE. You should have received a copy of GPLv2
+ * along with this software; if not, see
+ * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt .
+ *
+ * Red Hat trademarks are not licensed under GPLv2. No permission is
+ * granted to use or replicate Red Hat trademarks that are incorporated
+ * in this software or its documentation.
+ */
diff --git a/search-server/spacewalk-search/scripts/buildconf/build-utils.xml b/search-server/spacewalk-search/scripts/buildconf/build-utils.xml
new file mode 100644
index 0000000..d428618
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/buildconf/build-utils.xml
@@ -0,0 +1,19 @@
+<project name="build-utils.xml">
+ <!--
+ creates symlinks for jpackage jars
+ requires: jpackage-utils
+ other: requires rpms of the jars specified to be installed
+ -->
+ <macrodef name="jpackage-deps">
+ <attribute name="jars" />
+ <attribute name="dir" />
+
+ <sequential>
+ <exec executable="build-jar-repository" failonerror="true" >
+ <arg value="--preserve-naming" />
+ <arg value="-s @{dir}" />
+ <arg line="@{jars}" />
+ </exec>
+ </sequential>
+ </macrodef>
+</project>
diff --git a/search-server/spacewalk-search/scripts/buildconf/exclude b/search-server/spacewalk-search/scripts/buildconf/exclude
new file mode 100644
index 0000000..e69de29
diff --git a/search-server/spacewalk-search/scripts/checkstyle.xml b/search-server/spacewalk-search/scripts/checkstyle.xml
new file mode 100644
index 0000000..2cb51d5
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/checkstyle.xml
@@ -0,0 +1,233 @@
+<?xml version="1.0"?>
+<!DOCTYPE module PUBLIC
+ "-//Puppy Crawl//DTD Check Configuration 1.1//EN"
+ "http://www.puppycrawl.com/dtds/configuration_1_1.dtd ">
+
+<!--
+
+ Checkstyle configuration that checks the sun coding conventions from:
+
+ - the Java Language Specification at
+ http://java.sun.com/docs/books/jls/second_edition/html/index.html
+
+ - the Sun Code Conventions at http://java.sun.com/docs/codeconv/
+
+ - the Javadoc guidelines at
+ http://java.sun.com/j2se/javadoc/writingdoccomments/index.html
+
+ - the JDK Api documentation http://java.sun.com/j2se/docs/api/index.html
+
+ - some best practices
+
+ Checkstyle is very configurable. Be sure to read the documentation at
+ http://checkstyle.sf.net (or in your downloaded distribution).
+
+ Most Checks are configurable, be sure to consult the documentation.
+
+ To completely disable a check, just comment it out or delete it from the file.
+
+ Finally, it is worth reading the documentation.
+
+-->
+
+<module name="Checker">
+
+ <!-- Checks that a package.html file exists for each package. -->
+ <!-- See http://checkstyle.sf.net/config_javadoc.html#PackageHtml -->
+<!-- <module name="PackageHtml"/> -->
+
+ <!-- Checks whether files end with a new line. -->
+ <!-- See http://checkstyle.sf.net/config_misc.html#NewlineAtEndOfFile -->
+ <module name="NewlineAtEndOfFile"/>
+
+ <!-- Checks that property files contain the same keys. -->
+ <!-- See http://checkstyle.sf.net/config_misc.html#Translation -->
+ <module name="Translation"/>
+
+ <module name="TreeWalker">
+
+ <property name="cacheFile" value="${checkstyle.cache.file}"/>
+
+ <!-- ************************************************************** -->
+ <!-- Checks that are different from the sun coding conventions ones -->
+ <!-- ************************************************************** -->
+ <property name="tabWidth" value="4"/>
+ <module name="LeftCurly" />
+ <module name="RightCurly">
+ <property name="option" value="alone"/>
+ </module>
+ <module name="LineLength">
+ <property name="ignorePattern" value="import"/>
+ <property name="max" value="92"/>
+ </module>
+
+ <!-- ************************************************************** -->
+ <!-- Default Sun coding conventions checks -->
+ <!-- ************************************************************** -->
+
+ <!-- Checks for Javadoc comments. -->
+ <!-- See http://checkstyle.sf.net/config_javadoc.html -->
+ <module name="JavadocMethod">
+ <property name="scope" value="${javadoc.method.scope}" />
+ <property name="allowUndeclaredRTE" value="true" />
+ <property name="allowThrowsTagsForSubclasses" value="${javadoc.lazy}" />
+ <property name="allowMissingParamTags" value="${javadoc.lazy}" />
+ <property name="allowMissingThrowsTags" value="${javadoc.lazy}" />
+ <property name="allowMissingReturnTag" value="${javadoc.lazy}" />
+ </module>
+ <module name="JavadocType">
+ <property name="versionFormat" value="\$Rev.*\$"/>
+ <property name="scope" value="${javadoc.type.scope}" />
+ </module>
+ <module name="JavadocVariable">
+ <property name="scope" value="${javadoc.var.scope}" />
+ <property name="severity" value="ignore"/>
+ </module>
+
+<!-- JavadocStyle not supported by some versions. -->
+<!-- <module name="JavadocStyle"/> -->
+
+
+ <!-- Checks for Naming Conventions. -->
+ <!-- See http://checkstyle.sf.net/config_naming.html -->
+ <module name="ConstantName"/>
+ <module name="LocalFinalVariableName"/>
+ <module name="LocalVariableName"/>
+ <module name="MethodName"/>
+ <module name="PackageName">
+ <property name="format" value="^[a-z]+(\.[A-Za-z][A-Za-z0-9]*)*$"/>
+ </module>
+ <module name="ParameterName"/>
+ <module name="StaticVariableName"/>
+ <module name="TypeName"/>
+
+
+ <!-- Checks for Headers -->
+ <!-- See http://checkstyle.sf.net/config_header.html -->
+ <module name="Header">
+ <!-- The follow property value demonstrates the ability -->
+ <!-- to have access to ANT properties. In this case it uses -->
+ <!-- the ${basedir} property to allow Checkstyle to be run -->
+ <!-- from any directory within a project. -->
+ <property name="headerFile" value="${checkstyle.header.file}"/>
+ </module>
+
+ <!-- Following interprets the header file as regular expressions. -->
+ <!-- <module name="RegexpHeader"/> -->
+
+
+
+ <!-- Checks for imports -->
+ <!-- See http://checkstyle.sf.net/config_import.html -->
+ <module name="AvoidStarImport"/>
+ <module name="IllegalImport"/> <!-- defaults to sun.* packages -->
+ <module name="RedundantImport"/>
+ <module name="UnusedImports"/>
+
+
+ <!-- Checks for Size Violations. -->
+ <!-- See http://checkstyle.sf.net/config_sizes.html -->
+ <module name="MethodLength">
+ <property name="tokens" value="METHOD_DEF"/>
+ <property name="max" value="150"/>
+ <property name="countEmpty" value="false"/>
+ </module>
+ <module name="ParameterNumber"/>
+
+
+ <!-- Checks for whitespace -->
+ <!-- See http://checkstyle.sf.net/config_whitespace.html -->
+ <module name="EmptyForIteratorPad"/>
+ <module name="NoWhitespaceAfter">
+ <property name="tokens" value="BNOT, DEC, DOT, INC, LNOT, UNARY_MINUS, UNARY_PLUS, TYPECAST, GENERIC_START"/>
+ </module>
+ <module name="NoWhitespaceBefore">
+ <property name="tokens" value="SEMI, POST_DEC, POST_INC, GENERIC_START, GENERIC_END"/>
+ </module>
+ <module name="OperatorWrap">
+ <property name="option" value="eol" />
+ </module>
+ <module name="ParenPad"/>
+<!-- <module name="TypecastParenPad"/> -->
+ <module name="TabCharacter"/>
+ <module name="WhitespaceAfter">
+ <property name="tokens" value="COMMA, SEMI, GENERIC_END"/>
+ </module>
+ <module name="WhitespaceAround">
+ <property name="tokens" value="ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN, BXOR, BXOR_ASSIGN,
+COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LCURLY, LE, LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
+LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE, LOR, LT, MINUS,
+MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL, PLUS, PLUS_ASSIGN, QUESTION, RCURLY, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN, STAR, STAR_ASSIGN, TYPE_EXTENSION_AND, WILDCARD_TYPE"/>
+ </module>
+ <module name="MethodParamPad">
+ <property name="allowLineBreaks" value="true"/>
+ </module>
+
+
+ <!-- Modifier Checks -->
+ <!-- See http://checkstyle.sf.net/config_modifiers.html -->
+ <module name="ModifierOrder"/>
+ <module name="RedundantModifier"/>
+
+
+ <!-- Checks for blocks. You know, those {}'s -->
+ <!-- See http://checkstyle.sf.net/config_blocks.html -->
+ <module name="AvoidNestedBlocks"/>
+ <module name="EmptyBlock">
+ <property name="option" value="text"/>
+ </module>
+
+ <module name="NeedBraces"/>
+
+
+ <!-- Checks for common coding problems -->
+ <!-- See http://checkstyle.sf.net/config_coding.html -->
+ <!-- <module name="AvoidInlineConditionals"/> -->
+<!-- <module name="CovariantEquals"/> -->
+ <module name="DoubleCheckedLocking"/> <!-- MY FAVOURITE -->
+ <module name="EmptyStatement"/>
+ <module name="EqualsHashCode"/>
+ <module name="HiddenField"/>
+ <module name="IllegalInstantiation"/>
+ <module name="InnerAssignment"/>
+ <!-- <module name="MagicNumber" /> -->
+ <module name="MissingSwitchDefault"/>
+<!-- <module name="RedundantThrows"/> -->
+ <module name="SimplifyBooleanExpression"/>
+ <module name="SimplifyBooleanReturn"/>
+<!-- <module name="IllegalCatch"/> -->
+<!-- <module name="PackageDeclaration"/> -->
+
+ <!-- Checks for class design -->
+ <!-- See http://checkstyle.sf.net/config_design.html -->
+<!-- <module name="DesignForExtension"/>-->
+<!-- <module name="FinalClass"/> -->
+ <module name="HideUtilityClassConstructor"/>
+ <module name="InterfaceIsType"/>
+ <module name="VisibilityModifier">
+ <property name="protectedAllowed" value="true" />
+ </module>
+
+
+ <!-- Miscellaneous other checks. -->
+ <!-- See http://checkstyle.sf.net/config_misc.html -->
+ <module name="ArrayTypeStyle"/>
+<!-- <module name="FinalParameters"/> -->
+<!--
+ <module name="GenericIllegalRegexp">
+ <property name="format" value="System\.out\.println"/>
+ </module>
+-->
+ <module name="UpperEll"/>
+
+ <!-- Optional Checks -->
+ <!-- (gack, not available until version 3 of checkstyle -->
+<!--
+ <module name="usage.OneMethodPrivateField"/>
+ <module name="usage.UnusedLocalVariable"/>
+ <module name="usage.UnusedParameter"/>
+ <module name="usage.UnusedPrivateField"/>
+-->
+ </module>
+
+</module>
diff --git a/search-server/spacewalk-search/scripts/ivy.xml b/search-server/spacewalk-search/scripts/ivy.xml
new file mode 100644
index 0000000..cffd1c1
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/ivy.xml
@@ -0,0 +1,28 @@
+<ivy-module version="1.0">
+ <info organisation="redhat" module="rhn-java" />
+ <dependencies>
+ <dependency org="redhat" name="simple-core" rev="3.1.3" />
+ <dependency org="redhat" name="lucene-core" rev="2.3.2" />
+ <dependency org="redhat" name="lucene-analyzers" rev="2.3.2" />
+ <dependency org="redhat" name="commons-lang" rev="2.0" />
+ <dependency org="redhat" name="commons-logging" rev="1.1" />
+ <dependency org="redhat" name="redstone-xmlrpc" rev="1.1_20071120" />
+ <dependency org="redhat" name="redstone-xmlrpc-client" rev="1.1_20071120" />
+ <dependency org="redhat" name="ibatis" rev="2.3.0.677" />
+ <dependency org="redhat" name="ojdbc14" rev="1.10" />
+ <dependency org="redhat" name="quartz" rev="1.5.1" />
+ <dependency org="redhat" name="picocontainer" rev="1.3" />
+ <dependency org="redhat" name="tanukiwrapper" rev="3.1.2" />
+ <dependency org="redhat" name="log4j" rev="1.2.8" />
+ <dependency org="redhat" name="logdriver" rev="0.1" />
+ <dependency org="redhat" name="nutch" rev="1.0dev_2008_05_14" />
+ <dependency org="redhat" name="hadoop" rev="0.16.4-core" />
+ <dependency org="redhat" name="commons-cli" rev="1.0" />
+ <!-- dependency org="redhat" name="commons-httpclient" rev="3.0" / -->
+ <!-- dependency org="redhat" name="oro" rev="2.0.8" / -->
+ <!-- dependency org="redhat" name="commons-codec" rev="1.2" / -->
+ <!-- dependency org="redhat" name="tika" rev="0.1-incubating" / -->
+ <!-- dependency org="redhat" name="icu4j" rev="3_8_1" / -->
+ <!-- dependency org="redhat" name="icu4j-charsets" rev="3_8_1" / -->
+ </dependencies>
+</ivy-module>
diff --git a/search-server/spacewalk-search/scripts/lukeall-0.8.1.jar b/search-server/spacewalk-search/scripts/lukeall-0.8.1.jar
new file mode 100644
index 0000000..347aee6
Binary files /dev/null and b/search-server/spacewalk-search/scripts/lukeall-0.8.1.jar differ
diff --git a/search-server/spacewalk-search/scripts/maketar.sh b/search-server/spacewalk-search/scripts/maketar.sh
new file mode 100755
index 0000000..6a389be
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/maketar.sh
@@ -0,0 +1,30 @@
+if [ -a version ]; then
+ version=`cat version | awk '/^[0-9]\.[0-9]\.[0-9]* / { print $1 }'`
+
+ if [ "$version" == "" ]; then
+ echo "Version not found"
+ exit -1
+ fi
+
+ echo "Creating /tmp/rhn-search-$version"
+ mkdir /tmp/rhn-search-$version
+
+ echo "Copying repo to /tmp/rhn-search-$version/"
+ cp -R * /tmp/rhn-search-$version/
+
+ cd /tmp/
+ rm -f rhn-search-$version/scripts/maketar.sh
+ echo "Creating /tmp/rhn-search-$version.tar.gz file"
+ tar -czf /tmp/rhn-search-$version.tar.gz rhn-search-$version/ --exclude .svn
+ cd -
+
+ echo "Removing /tmp/rhn-search-$version"
+ rm -rf /tmp/rhn-search-$version
+
+ echo ""
+ echo "You can find your tar at /tmp/rhn-search-$version.tar.gz"
+ echo ""
+
+else
+ echo "You moron, you gotta run this from the directory containing the version file."
+fi
diff --git a/search-server/spacewalk-search/scripts/reindex.sh b/search-server/spacewalk-search/scripts/reindex.sh
new file mode 100755
index 0000000..cc7b312
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/reindex.sh
@@ -0,0 +1,15 @@
+#!/usr/bin/env sh
+
+RHN_SEARCH_HOME="../"
+
+for f in $RHN_SEARCH_HOME/lib/*.jar; do
+ CLASSPATH=${CLASSPATH}:$f;
+done
+for f in $RHN_SEARCH_HOME/dist/*.jar; do
+ CLASSPATH=${CLASSPATH}:$f;
+done
+export CLASSPATH
+
+groovy Reindex.groovy
+
+
diff --git a/search-server/spacewalk-search/scripts/search.admin.updateIndex.test.py b/search-server/spacewalk-search/scripts/search.admin.updateIndex.test.py
new file mode 100755
index 0000000..8962c9d
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/search.admin.updateIndex.test.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+
+import sys
+import xmlrpclib
+
+if __name__ == "__main__":
+ if len(sys.argv) < 2:
+ print "Usage: %s INDEX_NAME" % (sys.argv[0])
+ sys.exit(1)
+ port = 2828
+ addr = "http://127.0.0.1:%s " % (port)
+ client = xmlrpclib.ServerProxy(addr)
+ indexName = sys.argv[1]
+ result = client.admin.updateIndex(indexName)
+ print "Return from admin.updateIndex(%s) = %s" % (indexName, result)
diff --git a/search-server/spacewalk-search/scripts/search.py b/search-server/spacewalk-search/scripts/search.py
new file mode 100755
index 0000000..c8d0a04
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/search.py
@@ -0,0 +1,69 @@
+#!/usr/bin/python
+
+import xmlrpclib
+from optparse import OptionParser
+
+indexName = "package"
+usage = "usage: %prog [options] search term"
+desc = "%prog searches for package (default) or systems with the given \
+search criteria"
+
+parser = OptionParser(usage=usage, description=desc)
+parser.add_option("--sessionid", dest="sessionid", type="int", help="PXT sessionid")
+parser.add_option("--package", action="store_true", dest="package",
+ help="search packages", default=True)
+parser.add_option("--system", action="store_true", dest="system",
+ help="search systems", default=False)
+parser.add_option("--indexName", dest="indexName", type="string",
+ help="lucene index name to search ex: package server hwdevice snapshotTag errata")
+parser.add_option("--serverAddr", dest="serverAddr", type="string", default="localhost",
+ help="Server to authenticate to, NOT WHERE SEARCH SERVER RUNS")
+parser.add_option("--username", dest="username", type="string", help="username")
+parser.add_option("--password", dest="password", type="string", help="password")
+parser.add_option("--debug", action="store_true", dest="debug", default=False,
+ help="enable debug output")
+
+(options, terms) = parser.parse_args()
+if len(terms) < 1:
+ parser.error("please supply a search term\n" + str(parser.print_help()))
+
+if not options.sessionid and (not options.username or not options.password):
+ print parser.print_help()
+ parser.exit()
+
+
+if options.package:
+ indexName = "package"
+
+if options.system:
+ indexName = "server"
+
+if options.indexName:
+ indexName = options.indexName
+
+
+sessionid = None
+if options.sessionid:
+ sessionid = options.sessionid
+ print "Using passed in authentication info, sessionid = %s" % (sessionid)
+else:
+ xmlrpcURL = "http://%s/rhn/rpc/api" % (options.serverAddr)
+ print "Getting authentication information from: %s" % (xmlrpcURL)
+ rhnclient = xmlrpclib.Server(xmlrpcURL)
+ authSessionId = rhnclient.auth.login(options.username, options.password)
+ sessionid = int(authSessionId.split('x')[0])
+
+url = "http://localhost:2828/RPC2 "
+print "Connecting to SearchServer: (%s)" % url
+client = xmlrpclib.Server(url, verbose=options.debug)
+
+term = " ".join(terms)
+print "searching for (%s) matching criteria: (%s)" % (indexName, str(term))
+items = client.index.search(sessionid, indexName, term)
+
+print "We got (%d) items back." % len(items)
+print items
+
+#Remember to logout if the user didn't supply the sessionid
+if not options.sessionid:
+ rhnclient.auth.logout(authSessionId)
diff --git a/search-server/spacewalk-search/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java b/search-server/spacewalk-search/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java
new file mode 100644
index 0000000..7a9f671
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/src/java/com/redhat/satellite/search/index/docs/WebCrawl.java
@@ -0,0 +1,304 @@
+/**
+ * Copyright (c) 2008 Red Hat, Inc.
+ *
+ * This software is licensed to you under the GNU General Public License,
+ * version 2 (GPLv2). There is NO WARRANTY for this software, express or
+ * implied, including the implied warranties of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE. You should have received a copy of GPLv2
+ * along with this software; if not, see
+ * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt .
+ *
+ * Red Hat trademarks are not licensed under GPLv2. No permission is
+ * granted to use or replicate Red Hat trademarks that are incorporated
+ * in this software or its documentation.
+ */
+package com.redhat.satellite.search.index.docs;
+
+import org.apache.nutch.crawl.Injector;
+import org.apache.nutch.crawl.Generator;
+import org.apache.nutch.crawl.CrawlDb;
+import org.apache.nutch.crawl.LinkDb;
+import org.apache.nutch.fetcher.Fetcher;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.nutch.parse.ParseSegment;
+import org.apache.nutch.indexer.DeleteDuplicates;
+import org.apache.nutch.indexer.IndexMerger;
+import org.apache.nutch.indexer.Indexer;
+import org.apache.nutch.util.HadoopFSUtil;
+import org.apache.nutch.util.NutchConfiguration;
+import org.apache.nutch.util.NutchJob;
+
+import org.apache.commons.cli.CommandLine;
+import org.apache.commons.cli.CommandLineParser;
+import org.apache.commons.cli.PosixParser;
+import org.apache.commons.cli.HelpFormatter;
+import org.apache.commons.cli.Options;
+
+import org.apache.commons.cli.ParseException;
+
+import org.apache.log4j.Logger;
+
+import java.text.SimpleDateFormat;
+import java.util.Date;
+import java.io.IOException;
+
+
+/**
+Crawls a set of urls and indexes their content.
+Based off of nutch's crawl
+ *
+ * @version $Rev: $
+ */
+public class WebCrawl {
+ private static Logger log = Logger.getLogger(WebCrawl.class);
+
+ private Configuration conf;
+ private JobConf job;
+ private String inputUrlFile;
+ private String tmpCrawlDir;
+ private String outputIndexDir;
+
+ private int depth;
+ private int threads;
+ private long topN;
+
+ /**
+ * Constructor
+ */
+ public WebCrawl() {
+ conf = NutchConfiguration.create();
+ conf.addResource("crawl-tool.xml");
+ job = new NutchJob(conf);
+ threads = job.getInt("fetcher.threads.fetch", 10);
+ depth = 5;
+ topN = Long.MAX_VALUE;
+ }
+
+ /**
+ * @return Returns the dir used to store tmp crawl data
+ */
+ public String getTmpCrawlDir() {
+ return tmpCrawlDir;
+ }
+ /**
+ * @param tmpCrawlDirIn the dir used to store tmp crawl data
+ */
+ public void setTmpCrawlDir(String tmpCrawlDirIn) {
+ tmpCrawlDir = tmpCrawlDirIn;
+ }
+ /**
+ * @return Returns the file used to seed the url crawl
+ */
+ public String getInputUrlFile() {
+ return inputUrlFile;
+ }
+ /**
+ * @param inputUrlFileIn file used to seed the url crawl
+ */
+ public void setInputUrlFile(String inputUrlFileIn) {
+ inputUrlFile = inputUrlFileIn;
+ }
+ /**
+ * @return Returns the dir to store the index of the crawled docs
+ */
+ public String getOutputIndexDir() {
+ return outputIndexDir;
+ }
+ /**
+ * @param outputIndexDirIn the dir to store the index of the crawled docs
+ */
+ public void setOutputIndexDir(String outputIndexDirIn) {
+ outputIndexDir = outputIndexDirIn;
+ }
+ /**
+ * @return Returns the maximum depth of recursion allowed
+ */
+ public int getDepth() {
+ return depth;
+ }
+ /**
+ * @param depthIn the maximum depth of recursion allowed
+ */
+ public void setDepth(int depthIn) {
+ depth = depthIn;
+ }
+ /**
+ * @return Returns the maximum number of fetcher threads used
+ */
+ public int getThreads() {
+ return threads;
+ }
+ /**
+ * @param threadsIn the maximum number of fetcher threads used
+ */
+ public void setThreads(int threadsIn) {
+ threads = threadsIn;
+ }
+ /**
+ * @return Returns the maximum number of "out links" to follow in any given page
+ */
+ public long getTopN() {
+ return topN;
+ }
+ /**
+ * @param topNIn the maximum number of "out links" to follow in any given page
+ */
+ public void setTopN(long topNIn) {
+ topN = topNIn;
+ }
+
+ protected String getDate() {
+ return new SimpleDateFormat("yyyyMMddHHmmss").format(
+ new Date(System.currentTimeMillis()));
+ }
+
+ /**
+ * Uses nutch to crawl a list of ulrs defined in "inputUrlFile"
+ * Temporary scratch storage is held at "tmpCrawlDir"
+ * The desired output is an index of crawled pages, stored at "outputIndexDir"
+ *
+ * @return true when urls successfully crawled/indexed
+ */
+ @SuppressWarnings("deprecation")
+ public boolean crawl() throws IOException {
+ log.info("Performing crawl with following config options: ");
+ log.info("inputUrlFile = " + inputUrlFile);
+ log.info("tmpCrawlDir = " + tmpCrawlDir);
+ log.info("outputIndexDir = " + outputIndexDir);
+ log.info("threads = " + threads);
+ log.info("depth = " + depth);
+ log.info("topN = " + topN);
+
+ Path inputPath = new Path(inputUrlFile);
+ Path linkDb = new Path(tmpCrawlDir + "/linkdb");
+ Path segments = new Path(tmpCrawlDir + "/segments");
+ Path indexes = new Path(tmpCrawlDir + "/indexes");
+ Path index = new Path(outputIndexDir);
+ Path crawlDb = new Path(tmpCrawlDir + "/crawldb");
+
+ Path tmpDir = job.getLocalPath("crawl" + Path.SEPARATOR + getDate());
+ Injector injector = new Injector(conf);
+ Generator generator = new Generator(conf);
+ Fetcher fetcher = new Fetcher(conf);
+ ParseSegment parseSegment = new ParseSegment(conf);
+ CrawlDb crawlDbTool = new CrawlDb(conf);
+ LinkDb linkDbTool = new LinkDb(conf);
+ Indexer indexer = new Indexer(conf);
+ DeleteDuplicates dedup = new DeleteDuplicates(conf);
+ IndexMerger merger = new IndexMerger(conf);
+
+ FileSystem fs = FileSystem.get(job);
+
+ log.info("Create a new database (crawlDB) of link information");
+ injector.inject(crawlDb, inputPath);
+
+ for (int i = 0; i < depth; i++) {
+ log.info("Generate a fetch list from info in the crawlDB.");
+ Path segment = generator.generate(crawlDb, segments, -1, topN,
+ System.currentTimeMillis());
+ if (segment == null) {
+ log.info("Stopping at depth = " + i + " instead of " + (depth - 1) +
+ " - no more URLs to fetch.");
+ break;
+ }
+ log.info("Fetch links");
+ fetcher.fetch(segment, threads); // fetch it
+ if (!Fetcher.isParsing(job)) {
+ log.info("Parsing Segment");
+ parseSegment.parse(segment); // parse it, if needed
+ }
+ Path[] p = new Path[1];
+ p[0] = segment;
+ log.info("Update CrawlDB");
+ crawlDbTool.update(crawlDb, p, true, true); // update crawldb
+ }
+
+ linkDbTool.invert(linkDb, segments, true, true, false); // invert links
+
+ // Delete old indexes
+ if (fs.exists(indexes)) {
+ log.info("Deleting old indexes: $indexes");
+ fs.delete(indexes);
+ }
+
+ // Delete old index
+ if (fs.exists(index)) {
+ log.info("Deleting old merged index: $index");
+ fs.delete(index);
+ }
+
+ // index, dedup & merge
+ indexer.index(indexes, crawlDb, linkDb,
+ fs.listPaths(segments, HadoopFSUtil.getPassAllFilter()));
+
+ Path[] p = new Path[1];
+ p[0] = indexes;
+ dedup.dedup(p);
+ merger.merge(fs.listPaths(indexes, HadoopFSUtil.getPassAllFilter()),
+ index, tmpDir);
+ log.info("Crawl finished");
+ return true;
+ }
+
+
+ /**
+ * Performs a web crawl:
+ * @param args command line arguments
+ */
+ public static void main(String[] args) throws IOException {
+
+ WebCrawl wCrawl = new WebCrawl();
+
+ Options options = new Options();
+ options.addOption("i", "inputUrlFile", true,
+ "file holding 'urls' file to seed web page crawling");
+ options.addOption("o", "outputDir", true, "temp crawl output dir");
+ options.addOption("x", "docsIndexDir", true, "docs index output dir");
+ options.addOption("t", "threads", true, "number of threads");
+ options.addOption("d", "depth", true, "depth to recurse towards");
+ options.addOption("n", "topN", true, "maximum number of out links to follow");
+ options.addOption("h", "help", false, "print help message");
+
+ CommandLineParser parser = new PosixParser();
+ try {
+ CommandLine line = parser.parse(options, args);
+
+ if (line.hasOption("h")) {
+ HelpFormatter formatter = new HelpFormatter();
+ formatter.printHelp("WebCrawl", options);
+ return;
+ }
+ if (line.hasOption("i")) {
+ wCrawl.setInputUrlFile(line.getOptionValue("i"));
+ }
+ if (line.hasOption("x")) {
+ wCrawl.setOutputIndexDir(line.getOptionValue("x"));
+ }
+ if (line.hasOption("o")) {
+ wCrawl.setTmpCrawlDir(line.getOptionValue("o"));
+ }
+ if (line.hasOption("t")) {
+ wCrawl.setThreads(Integer.parseInt(line.getOptionValue("t")));
+ }
+ if (line.hasOption("d)")) {
+ wCrawl.setDepth(Integer.parseInt(line.getOptionValue("d")));
+ }
+ if (line.hasOption("n")) {
+ wCrawl.setTopN(Integer.parseInt(line.getOptionValue("n")));
+ }
+
+ }
+ catch (ParseException exp) {
+ System.err.println("Parsing failed. Reason: " + exp.getMessage());
+ }
+
+ if (!wCrawl.crawl()) {
+ System.err.println("Error -- WebCrawl.crawl() Failed!");
+ }
+ }
+
+
+}
diff --git a/search-server/spacewalk-search/scripts/webCrawl.sh b/search-server/spacewalk-search/scripts/webCrawl.sh
new file mode 100755
index 0000000..da352f6
--- /dev/null
+++ b/search-server/spacewalk-search/scripts/webCrawl.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+SEARCH_HOME=..
+NUTCH_HOME=/usr/share/nutch
+
+CLASSPATH=${CLASSPATH}:${SEARCH_HOME}/build
+#Put our nutch/conf dir before the NUTCH_HOME so ensure our config files are used
+CLASSPATH=${CLASSPATH}:${SEARCH_HOME}/nutch/conf
+CLASSPATH=${CLASSPATH}:${NUTCH_HOME}
+for f in ${SEARCH_HOME}/lib/*.jar; do
+ CLASSPATH=${CLASSPATH}:$f;
+done
+
+java -cp ${CLASSPATH} com.redhat.satellite.search.scheduler.tasks.crawl.WebCrawl --inputUrlFile ${SEARCH_HOME}/nutch/urls --outputDir ./crawl_output --docsIndexDir ./docsIndexDir --depth 2 --threads 4
+
+
+
+
diff --git a/search-server/spacewalk-search/spacewalk-search.spec b/search-server/spacewalk-search/spacewalk-search.spec
new file mode 100644
index 0000000..fcc3580
--- /dev/null
+++ b/search-server/spacewalk-search/spacewalk-search.spec
@@ -0,0 +1,255 @@
+%{!?__redhat_release:%define __redhat_release UNKNOWN}
+
+Name: spacewalk-search
+Summary: Spacewalk Full Text Search Server
+Group: Applications/Internet
+License: GPLv2
+Version: 0.8.1
+Release: 1%{?dist}
+# This src.rpm is cannonical upstream
+# You can obtain it using this set of commands
+# git clone git://git.fedorahosted.org/git/spacewalk.git/
+# cd search-server
+# make test-srpm
+URL: htt