diff options
| -rw-r--r-- | ChangeLog | 5 | ||||
| -rw-r--r-- | enc/iso_8859_2.c | 51 | ||||
| -rw-r--r-- | test/ruby/enc/test_case_comprehensive.rb | 2 |
3 files changed, 55 insertions, 3 deletions
@@ -1,3 +1,8 @@ +Sat Jul 30 12:00:01 2016 Martin Duerst <duerst@it.aoyama.ac.jp> + + * enc/iso_8859_2.c, test/ruby/enc/test_case_comprehensive.rb: + Implement non-ASCII case conversion for ISO-8859-2, by Yushiro Ishii. + Fri Jul 29 20:57:12 2016 chuanshuo <lilijreey@126.com> * *.c: rename rb_funcall2 to rb_funcallv, except for extensions diff --git a/enc/iso_8859_2.c b/enc/iso_8859_2.c index f0a74ee7e8..faac882819 100644 --- a/enc/iso_8859_2.c +++ b/enc/iso_8859_2.c @@ -1,4 +1,4 @@ -/********************************************************************** + /********************************************************************** iso8859_2.c - Oniguruma (regular expression library) **********************************************************************/ /*- @@ -220,6 +220,53 @@ is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc ARG_UNUSE return FALSE; } +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 ((EncISO_8859_2_CtypeTable[code] & BIT_CTYPE_UPPER) + && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) { + flags |= ONIGENC_CASE_MODIFIED; + code = ENC_ISO_8859_2_TO_LOWER_CASE(code); + } + else if ((EncISO_8859_2_CtypeTable[code]&BIT_CTYPE_LOWER) + && (flags&ONIGENC_CASE_UPCASE)) { + if (code>=0xB1 && code<=0xBF){ + flags |= ONIGENC_CASE_MODIFIED; + code -= 0x10; + } + else{ + flags |= ONIGENC_CASE_MODIFIED; + 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); +} + OnigEncodingDefine(iso_8859_2, ISO_8859_2) = { onigenc_single_byte_mbc_enc_len, "ISO-8859-2", /* name */ @@ -239,6 +286,6 @@ OnigEncodingDefine(iso_8859_2, ISO_8859_2) = { onigenc_always_true_is_allowed_reverse_match, 0, ONIGENC_FLAG_NONE, - onigenc_single_byte_ascii_only_case_map, + case_map, }; ENC_ALIAS("ISO8859-2", "ISO-8859-2") diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb index e424d5a76d..5e0bd2d92d 100644 --- a/test/ruby/enc/test_case_comprehensive.rb +++ b/test/ruby/enc/test_case_comprehensive.rb @@ -262,7 +262,7 @@ TestComprehensiveCaseFold.data_files_available? and class TestComprehensiveCase generate_case_mapping_tests 'US-ASCII' generate_case_mapping_tests 'ASCII-8BIT' generate_case_mapping_tests 'ISO-8859-1' - generate_ascii_only_case_mapping_tests 'ISO-8859-2' + generate_case_mapping_tests 'ISO-8859-2' generate_case_mapping_tests 'ISO-8859-3' generate_case_mapping_tests 'ISO-8859-4' generate_case_mapping_tests 'ISO-8859-5' |