summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-12 12:33:17 +0000
committerduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-12 12:33:17 +0000
commit7b66f0bae9ee8f41b8765b175c9ccbb825a294cf (patch)
tree146508685a39d0ca3b5058c156f391c7ae0c8fe6
parentfd2c613b1cec46d0b02df722bb00ae01154d5dc3 (diff)
* enc/iso_8859_3.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for ISO-8859-3, by Takuya Miyamoto. * test/ruby/enc/test_case_comprehensive.rb: Extend special treatment for Turkic. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55642 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r--ChangeLog8
-rw-r--r--enc/iso_8859_3.c62
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb13
3 files changed, 78 insertions, 5 deletions
diff --git a/ChangeLog b/ChangeLog
index 1232a33a885..1748653cc67 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,11 @@
+Tue Jul 12 21:33:10 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+
+ * enc/iso_8859_3.c, test/ruby/enc/test_case_comprehensive.rb:
+ Implement non-ASCII case conversion for ISO-8859-3, by Takuya Miyamoto.
+
+ * test/ruby/enc/test_case_comprehensive.rb: Extend special treatment
+ for Turkic.
+
Tue Jul 12 01:25:09 2016 NAKAMURA Usaku <usa@ruby-lang.org>
* configure.in, lib/mkmf.rb, win32/Makefile.sub (CSRCFLAG): make the
diff --git a/enc/iso_8859_3.c b/enc/iso_8859_3.c
index e6dee1042a1..6f882eff74d 100644
--- a/enc/iso_8859_3.c
+++ b/enc/iso_8859_3.c
@@ -56,7 +56,7 @@ static const UChar EncISO_8859_3_ToLowerCaseTable[256] = {
'\220', '\221', '\222', '\223', '\224', '\225', '\226', '\227',
'\230', '\231', '\232', '\233', '\234', '\235', '\236', '\237',
'\240', '\261', '\242', '\243', '\244', '\245', '\266', '\247',
- '\250', '\271', '\272', '\273', '\274', '\255', '\256', '\277',
+ '\250', '\151', '\272', '\273', '\274', '\255', '\256', '\277',
'\260', '\261', '\262', '\263', '\264', '\265', '\266', '\267',
'\270', '\271', '\272', '\273', '\274', '\275', '\276', '\277',
'\340', '\341', '\342', '\303', '\344', '\345', '\346', '\347',
@@ -220,6 +220,64 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag,
flag, p, end, items);
}
+#ifdef ONIG_CASE_MAPPING
+#define DOTLESS_i (0xB9)
+#define I_WITH_DOT_ABOVE (0xA9)
+static int
+case_map (OnigCaseFoldType* flagP, const OnigUChar** pp,
+ const OnigUChar* end, OnigUChar* to, OnigUChar* to_end,
+ const struct OnigEncodingTypeST* enc)
+{
+ OnigCodePoint code;
+ OnigUChar *to_start = to;
+ OnigCaseFoldType flags = *flagP;
+
+ while (*pp<end && to<to_end) {
+ code = *(*pp)++;
+ if (code==SHARP_s) {
+ if (flags&ONIGENC_CASE_UPCASE) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ *to++ = 'S';
+ code = (flags&ONIGENC_CASE_TITLECASE) ? 's' : 'S';
+ }
+ else if (flags&ONIGENC_CASE_FOLD) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ *to++ = 's';
+ code = 's';
+ }
+ }
+ else if (code==0xB5) ;
+ else if ((EncISO_8859_3_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if (code=='I')
+ code = flags&ONIGENC_CASE_FOLD_TURKISH_AZERI ? DOTLESS_i : 'i';
+ else
+ code = ENC_ISO_8859_3_TO_LOWER_CASE(code);
+ }
+ else if ((EncISO_8859_3_CtypeTable[code]&BIT_CTYPE_LOWER)
+ && (flags&ONIGENC_CASE_UPCASE)) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if (code=='i')
+ code = flags&ONIGENC_CASE_FOLD_TURKISH_AZERI ? I_WITH_DOT_ABOVE : 'I';
+ else if (code==DOTLESS_i)
+ code = 'I';
+ else if (code>=0xB0 && code<=0xBF ) {
+ code -= 0x10;
+ }
+ else {
+ code -= 0x20;
+ }
+ }
+ *to++ = code;
+ if (flags&ONIGENC_CASE_TITLECASE) /* switch from titlecase to lowercase for capitalize */
+ flags ^= (ONIGENC_CASE_UPCASE|ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_TITLECASE);
+ }
+ *flagP = flags;
+ return (int)(to-to_start);
+}
+#endif /* ONIG_CASE_MAPPING */
+
OnigEncodingDefine(iso_8859_3, ISO_8859_3) = {
onigenc_single_byte_mbc_enc_len,
"ISO-8859-3", /* name */
@@ -240,7 +298,7 @@ OnigEncodingDefine(iso_8859_3, ISO_8859_3) = {
0,
ONIGENC_FLAG_NONE,
#ifdef ONIG_CASE_MAPPING
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
#endif /* ONIG_CASE_MAPPING */
};
ENC_ALIAS("ISO8859-3", "ISO-8859-3")
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index 9a5c17724de..8d202ca148e 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -168,8 +168,15 @@ class TestComprehensiveCaseFold
begin
target = "#{test.first_data[code]}#{test.follow_data[code]*4}".encode(encoding)
rescue Encoding::UndefinedConversionError
- raise if code =~ /i|I/ # special case for Turkic
- target = source
+ if test.first_data[code]=="i\u0307" or test.follow_data[code]=="i\u0307" # explicit dot above
+ first_data = test.first_data[code]=="i\u0307" ? 'i' : test.first_data[code]
+ follow_data = test.follow_data[code]=="i\u0307" ? 'i' : test.follow_data[code]
+ target = "#{first_data}#{follow_data*4}".encode(encoding)
+ elsif code =~ /i|I/ # special case for Turkic
+ raise
+ else
+ target = source
+ end
end
result = source.send(test.method_name, *test.attributes)
assert_equal target, result,
@@ -244,7 +251,7 @@ class TestComprehensiveCaseFold
end
generate_ascii_only_case_mapping_tests 'ISO-8859-2'
- generate_ascii_only_case_mapping_tests 'ISO-8859-3'
+ generate_case_mapping_tests 'ISO-8859-3'
generate_case_mapping_tests 'ISO-8859-4'
generate_ascii_only_case_mapping_tests 'ISO-8859-5'
generate_ascii_only_case_mapping_tests 'ISO-8859-7'