From f477251914f734a8c7e7af03ff396159e246e1ae Mon Sep 17 00:00:00 2001 From: Jakub Hrozek Date: Tue, 6 Dec 2011 14:57:58 +0100 Subject: [PATCH 1/6] sss_utf8_tolower utility function+unit tests --- src/tests/util-tests.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++ src/util/sss_utf8.c | 33 ++++++++++++++++++++++ src/util/sss_utf8.h | 5 +++ src/util/util.c | 13 ++++++++ src/util/util.h | 3 ++ 5 files changed, 126 insertions(+), 0 deletions(-) diff --git a/src/tests/util-tests.c b/src/tests/util-tests.c index 52d302778ed3c819d3ffeef96e7b52c778a15825..d0636651f1abecb10240927aa2a011841e74447b 100644 --- a/src/tests/util-tests.c +++ b/src/tests/util-tests.c @@ -26,6 +26,7 @@ #include #include #include "util/util.h" +#include "util/sss_utf8.h" #include "tests/common.h" START_TEST(test_parse_args) @@ -312,6 +313,68 @@ START_TEST(test_size_t_overflow) } END_TEST +START_TEST(test_utf8_lowercase) +{ + const uint8_t munchen_utf8_upcase[] = { 'M', 0xC3, 0x9C, 'N', 'C', 'H', 'E', 'N', 0x0 }; + const uint8_t munchen_utf8_lowcase[] = { 'm', 0xC3, 0xBC, 'n', 'c', 'h', 'e', 'n', 0x0 }; + uint8_t *lcase; + + lcase = sss_utf8_tolower(munchen_utf8_upcase); + fail_if(memcmp(lcase, munchen_utf8_lowcase, strlen((const char *) lcase))); + sss_utf8_free(lcase); +} +END_TEST + +START_TEST(test_utf8_talloc_lowercase) +{ + const uint8_t munchen_utf8_upcase[] = { 'M', 0xC3, 0x9C, 'N', 'C', 'H', 'E', 'N', 0x0 }; + const uint8_t munchen_utf8_lowcase[] = { 'm', 0xC3, 0xBC, 'n', 'c', 'h', 'e', 'n', 0x0 }; + char *lcase; + + TALLOC_CTX *test_ctx; + test_ctx = talloc_new(NULL); + fail_if(test_ctx == NULL); + + lcase = sss_tc_utf8_tolower(test_ctx, (const char *) munchen_utf8_upcase); + fail_if(memcmp(lcase, munchen_utf8_lowcase, strlen((const char *) lcase))); + talloc_free(test_ctx); +} +END_TEST + +START_TEST(test_utf8_caseeq) +{ + const uint8_t munchen_utf8_upcase[] = { 'M', 0xC3, 0x9C, 'N', 'C', 'H', 'E', 'N', 0x0 }; + const uint8_t munchen_utf8_lowcase[] = { 'm', 0xC3, 0xBC, 'n', 'c', 'h', 'e', 'n', 0x0 }; + const uint8_t czech_utf8_lowcase[] = { 0xC4, 0x8D, 'e', 'c', 'h', 0x0 }; + const uint8_t czech_utf8_upcase[] = { 0xC4, 0x8C, 'e', 'c', 'h', 0x0 }; + const uint8_t czech_utf8_lowcase_neg[] = { 0xC4, 0x8E, 'e', 'c', 'h', 0x0 }; + errno_t ret; + + ret = sss_utf8_case_eq(munchen_utf8_upcase, munchen_utf8_lowcase); + fail_unless(ret == EOK, "Latin 1 Supplement comparison failed\n"); + + ret = sss_utf8_case_eq(czech_utf8_upcase, czech_utf8_lowcase); + fail_unless(ret == EOK, "Latin Extended A comparison failed\n"); + + ret = sss_utf8_case_eq(czech_utf8_upcase, czech_utf8_lowcase_neg); + fail_if(ret == EOK, "Negative test succeeded\n"); +} +END_TEST + +START_TEST(test_utf8_check) +{ + const char *invalid = "ad\351la\357d"; + const uint8_t valid[] = { 'M', 0xC3, 0x9C, 'N', 'C', 'H', 'E', 'N', 0x0 }; + bool ret; + + ret = sss_utf8_check(valid, strlen((const char *) valid)); + fail_unless(ret == true, "Positive test failed\n"); + + ret = sss_utf8_check((const uint8_t *) invalid, strlen(invalid)); + fail_unless(ret == false, "Negative test succeeded\n"); +} +END_TEST + Suite *util_suite(void) { Suite *s = suite_create("util"); @@ -324,7 +387,16 @@ Suite *util_suite(void) tcase_add_test (tc_util, test_parse_args); tcase_set_timeout(tc_util, 60); + TCase *tc_utf8 = tcase_create("utf8"); + tcase_add_test (tc_util, test_utf8_lowercase); + tcase_add_test (tc_util, test_utf8_talloc_lowercase); + tcase_add_test (tc_util, test_utf8_caseeq); + tcase_add_test (tc_util, test_utf8_check); + + tcase_set_timeout(tc_utf8, 60); + suite_add_tcase (s, tc_util); + suite_add_tcase (s, tc_utf8); return s; } diff --git a/src/util/sss_utf8.c b/src/util/sss_utf8.c index 4a98233bb97bbfc77a60bba6a24ef04bf78bfa56..982927d31c48c0bb60f931a57401a145b634d344 100644 --- a/src/util/sss_utf8.c +++ b/src/util/sss_utf8.c @@ -24,6 +24,39 @@ #include "sss_utf8.h" #ifdef HAVE_LIBUNISTRING +void sss_utf8_free(void *ptr) +{ + return free(ptr); +} +#elif HAVE_GLIB2 +void sss_utf8_free(void *ptr) +{ + return g_free(ptr); +} +#else +#error No unicode library +#endif + +#ifdef HAVE_LIBUNISTRING +uint8_t *sss_utf8_tolower(const uint8_t *s) +{ + size_t llen; + uint8_t *lower; + + lower = u8_tolower(s, u8_strlen(s), NULL, NULL, NULL, &llen); + lower[llen] = '\0'; + return lower; +} +#elif HAVE_GLIB2 +uint8_t *sss_utf8_tolower(const uint8_t *s) +{ + return (uint8_t *) g_utf8_strdown((const gchar *) s, -1); +} +#else +#error No unicode library +#endif + +#ifdef HAVE_LIBUNISTRING bool sss_utf8_check(const uint8_t *s, size_t n) { if (u8_check(s, n) == NULL) { diff --git a/src/util/sss_utf8.h b/src/util/sss_utf8.h index 37dcff959b1a86110fba919082b075c7f4963f02..7be54d69b1ca347dd477d6b68cf5eb8af85c4c46 100644 --- a/src/util/sss_utf8.h +++ b/src/util/sss_utf8.h @@ -35,6 +35,11 @@ #define ENOMATCH -1 #endif +void sss_utf8_free(void *ptr); + +/* The result must be freed with sss_utf8_free() */ +uint8_t *sss_utf8_tolower(const uint8_t *s); + bool sss_utf8_check(const uint8_t *s, size_t n); errno_t sss_utf8_case_eq(const uint8_t *s1, const uint8_t *s2); diff --git a/src/util/util.c b/src/util/util.c index b4b1b124317377fe22612576e8e2d8d3256c14ce..fbc77d6fc98180de74f018a5dbbeca99bcff686f 100644 --- a/src/util/util.c +++ b/src/util/util.c @@ -23,6 +23,7 @@ #include "talloc.h" #include "util/util.h" +#include "util/sss_utf8.h" #include "dhash.h" /* split a string into an allocated array of strings. @@ -597,3 +598,15 @@ sss_escape_ip_address(TALLOC_CTX *mem_ctx, int family, const char *addr) return family == AF_INET6 ? talloc_asprintf(mem_ctx, "[%s]", addr) : talloc_strdup(mem_ctx, addr); } + +char * +sss_tc_utf8_tolower(TALLOC_CTX *mem_ctx, const char *s) +{ + uint8_t *ret; + uint8_t *lower; + + lower = sss_utf8_tolower((const uint8_t *) s); + if (!lower) return NULL; + + return talloc_strdup(mem_ctx, (const char *) lower); +} diff --git a/src/util/util.h b/src/util/util.h index 9a00647179b010f7dd1b9744b3aaa013cc6e5769..436692c61ca0b9002ae21744fb27d7d26cd5da18 100644 --- a/src/util/util.h +++ b/src/util/util.h @@ -502,4 +502,7 @@ errno_t sss_filter_sanitize(TALLOC_CTX *mem_ctx, char * sss_escape_ip_address(TALLOC_CTX *mem_ctx, int family, const char *addr); +char * +sss_tc_utf8_tolower(TALLOC_CTX *mem_ctx, const char *s); + #endif /* __SSSD_UTIL_H__ */ -- 1.7.7.3