Mongolian Vowel Separator isn't whitespace The character U+180E Mongolian Vowel Separator isn't whitespace since Unicode 6.3.0.
Project: http://git-wip-us.apache.org/repos/asf/lucy-clownfish/repo Commit: http://git-wip-us.apache.org/repos/asf/lucy-clownfish/commit/a8ca118b Tree: http://git-wip-us.apache.org/repos/asf/lucy-clownfish/tree/a8ca118b Diff: http://git-wip-us.apache.org/repos/asf/lucy-clownfish/diff/a8ca118b Branch: refs/heads/master Commit: a8ca118b84fd0ac10ecb870aa74198caf4b72352 Parents: 814aea8 Author: Nick Wellnhofer <wellnho...@aevum.de> Authored: Wed Feb 3 14:22:47 2016 +0100 Committer: Nick Wellnhofer <wellnho...@aevum.de> Committed: Wed Feb 3 15:35:36 2016 +0100 ---------------------------------------------------------------------- runtime/core/Clownfish/Test/TestString.c | 6 +++--- runtime/core/Clownfish/Test/Util/TestStringHelper.c | 4 +--- runtime/core/Clownfish/Util/StringHelper.c | 1 - 3 files changed, 4 insertions(+), 7 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/lucy-clownfish/blob/a8ca118b/runtime/core/Clownfish/Test/TestString.c ---------------------------------------------------------------------- diff --git a/runtime/core/Clownfish/Test/TestString.c b/runtime/core/Clownfish/Test/TestString.c index 86103e2..64d686c 100644 --- a/runtime/core/Clownfish/Test/TestString.c +++ b/runtime/core/Clownfish/Test/TestString.c @@ -52,9 +52,9 @@ static String* S_smiley_with_whitespace(int *num_spaces_ptr) { int32_t spaces[] = { ' ', '\t', '\r', '\n', 0x000B, 0x000C, 0x000D, 0x0085, - 0x00A0, 0x1680, 0x180E, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, - 0x2005, 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x2028, 0x2029, - 0x202F, 0x205F, 0x3000 + 0x00A0, 0x1680, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, + 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x2028, 0x2029, 0x202F, + 0x205F, 0x3000 }; int num_spaces = sizeof(spaces) / sizeof(uint32_t); http://git-wip-us.apache.org/repos/asf/lucy-clownfish/blob/a8ca118b/runtime/core/Clownfish/Test/Util/TestStringHelper.c ---------------------------------------------------------------------- diff --git a/runtime/core/Clownfish/Test/Util/TestStringHelper.c b/runtime/core/Clownfish/Test/Util/TestStringHelper.c index a9c2464..b26dc24 100644 --- a/runtime/core/Clownfish/Test/Util/TestStringHelper.c +++ b/runtime/core/Clownfish/Test/Util/TestStringHelper.c @@ -263,8 +263,6 @@ test_is_whitespace(TestBatchRunner *runner) { TEST_TRUE(runner, StrHelp_is_whitespace('\t'), "tab is whitespace"); TEST_TRUE(runner, StrHelp_is_whitespace('\v'), "vertical tab is whitespace"); - TEST_TRUE(runner, StrHelp_is_whitespace(0x180E), - "Mongolian vowel separator is whitespace"); TEST_FALSE(runner, StrHelp_is_whitespace('a'), "'a' isn't whitespace"); TEST_FALSE(runner, StrHelp_is_whitespace(0), "NULL isn't whitespace"); TEST_FALSE(runner, StrHelp_is_whitespace(0x263A), @@ -287,7 +285,7 @@ test_back_utf8_char(TestBatchRunner *runner) { void TestStrHelp_Run_IMP(TestStringHelper *self, TestBatchRunner *runner) { - TestBatchRunner_Plan(runner, (TestBatch*)self, 40); + TestBatchRunner_Plan(runner, (TestBatch*)self, 39); test_overlap(runner); test_to_base36(runner); test_utf8_round_trip(runner); http://git-wip-us.apache.org/repos/asf/lucy-clownfish/blob/a8ca118b/runtime/core/Clownfish/Util/StringHelper.c ---------------------------------------------------------------------- diff --git a/runtime/core/Clownfish/Util/StringHelper.c b/runtime/core/Clownfish/Util/StringHelper.c index a2ccdc6..085d8a5 100644 --- a/runtime/core/Clownfish/Util/StringHelper.c +++ b/runtime/core/Clownfish/Util/StringHelper.c @@ -135,7 +135,6 @@ StrHelp_is_whitespace(int32_t code_point) { case 0x0085: // <control-0085> case 0x00A0: // NO-BREAK SPACE case 0x1680: // OGHAM SPACE MARK - case 0x180E: // MONGOLIAN VOWEL SEPARATOR // EN QUAD..HAIR SPACE case 0x2000: case 0x2001: case 0x2002: case 0x2003: case 0x2004: case 0x2005: case 0x2006: case 0x2007: case 0x2008: case 0x2009: