diff options
| -rw-r--r-- | ChangeLog | 5 | ||||
| -rw-r--r-- | enc/iso_8859_4.c | 61 | ||||
| -rw-r--r-- | test/ruby/enc/test_case_comprehensive.rb | 2 |
3 files changed, 66 insertions, 2 deletions
@@ -1,3 +1,8 @@ +Sun Jul 10 17:05:36 2016 Martin Duerst <duerst@it.aoyama.ac.jp> + + * enc/iso_8859_4.c, test/ruby/enc/test_case_comprehensive.rb: + Implement non-ASCII case conversion for ISO-8859-4, by Kotaro Yoshida. + Sun Jul 10 16:17:47 2016 Martin Duerst <duerst@it.aoyama.ac.jp> * test/ruby/enc/test_case_comprehensive.rb: Fixed a comment diff --git a/enc/iso_8859_4.c b/enc/iso_8859_4.c index 30041d1b62..a7d479bfd7 100644 --- a/enc/iso_8859_4.c +++ b/enc/iso_8859_4.c @@ -223,6 +223,65 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag, flag, p, end, items); } +#ifdef ONIG_CASE_MAPPING +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_4_CtypeTable[code] & BIT_CTYPE_UPPER) + && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) { + flags |= ONIGENC_CASE_MODIFIED; + if (code>=0xA0 && code<=0xBF) { + if (code==0xBD) + code += 0x02; + else + code += 0x10; + } + else + code += 0x20; + } + else if ((EncISO_8859_4_CtypeTable[code]&BIT_CTYPE_LOWER) + && (flags&ONIGENC_CASE_UPCASE)) { + flags |= ONIGENC_CASE_MODIFIED; + if (code>=0xA0&&code<=0xBF) { + if (code==0xBF) + code -= 0x02; + else if (code==0xA2) + ; + else + 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_4, ISO_8859_4) = { onigenc_single_byte_mbc_enc_len, "ISO-8859-4", /* name */ @@ -243,7 +302,7 @@ OnigEncodingDefine(iso_8859_4, ISO_8859_4) = { 0, ONIGENC_FLAG_NONE, #ifdef ONIG_CASE_MAPPING - onigenc_single_byte_ascii_only_case_map, + case_map, #endif /* ONIG_CASE_MAPPING */ }; ENC_ALIAS("ISO8859-4", "ISO-8859-4") diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb index 8af7e4db55..bd30166de3 100644 --- a/test/ruby/enc/test_case_comprehensive.rb +++ b/test/ruby/enc/test_case_comprehensive.rb @@ -240,7 +240,7 @@ class TestComprehensiveCaseFold generate_ascii_only_case_mapping_tests 'ISO-8859-2' generate_ascii_only_case_mapping_tests 'ISO-8859-3' - generate_ascii_only_case_mapping_tests 'ISO-8859-4' + 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' generate_ascii_only_case_mapping_tests 'ISO-8859-9' |