From fdd86bdf62e38e8db9d70ab19f157b45c4a2a9a6 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 | 59 ++++++++++++++++++++++++++++++++++++++++++++++++ src/util/sss_utf8.c | 48 +++++++++++++++++++++++++++++++++++++++ src/util/sss_utf8.h | 4 +++ 3 files changed, 111 insertions(+), 0 deletions(-) diff --git a/src/tests/util-tests.c b/src/tests/util-tests.c index 52d3027..cf9edd9 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 +313,56 @@ 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 }; + const uint8_t *lcase; + TALLOC_CTX *test_ctx; + + test_ctx = talloc_new(NULL); + + lcase = sss_utf8_tolower(test_ctx, 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 +375,15 @@ 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_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 4a98233..2cfd56d 100644 --- a/src/util/sss_utf8.c +++ b/src/util/sss_utf8.c @@ -24,6 +24,54 @@ #include "sss_utf8.h" #ifdef HAVE_LIBUNISTRING +uint8_t *sss_utf8_tolower(TALLOC_CTX *mem_ctx, const uint8_t *s) +{ + size_t len, llen; + uint8_t *lower; + uint8_t *ret; + + len = u8_strlen(s); + lower = u8_tolower(s, len, NULL, NULL, NULL, &llen); + if (!lower) return NULL; + + ret = talloc_array(mem_ctx, uint8_t, llen+1); + if (!ret) return NULL; + + memcpy(ret, lower, llen); + ret[llen] = '\0'; + + free(lower); + return ret; +} + +#elif HAVE_GLIB2 +uint8_t *sss_utf8_tolower(TALLOC_CTX *mem_ctx, const uint8_t *s) +{ + gchar *lower; + const gchar *gs; + gssize llen; + uint8_t *ret; + + gs = (const gchar *) s; + + lower = g_utf8_strdown(gs, -1); + if (!lower) return NULL; + llen = g_utf8_strlen(lower, -1); + + ret = talloc_array(mem_ctx, uint8_t, llen+1); + if (!ret) return NULL; + + memcpy(ret, lower, llen); + ret[llen] = '\0'; + + free(lower); + return ret; +} +#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 37dcff9..89160f6 100644 --- a/src/util/sss_utf8.h +++ b/src/util/sss_utf8.h @@ -35,6 +35,10 @@ #define ENOMATCH -1 #endif +uint8_t *sss_utf8_tolower(TALLOC_CTX *mem_ctx, const uint8_t *s); +#define sss_utf8_string_tolower(mem_ctx, s) \ + (const char *) sss_utf8_tolower(mem_ctx, (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); -- 1.7.7.3