ruby-changes:43518
From: duerst <ko1@a...>
Date: Wed, 6 Jul 2016 18:59:28 +0900 (JST)
Subject: [ruby-changes:43518] duerst:r55591 (trunk): * enc/iso_8859_15.c, test/ruby/enc/test_case_comprehensive.rb:
duerst 2016-07-06 18:59:23 +0900 (Wed, 06 Jul 2016) New Revision: 55591 https://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=55591 Log: * enc/iso_8859_15.c, test/ruby/enc/test_case_comprehensive.rb: Implement non-ASCII case conversion for ISO-8859-15, by Maho Harada. Modified files: trunk/ChangeLog trunk/enc/iso_8859_15.c trunk/test/ruby/enc/test_case_comprehensive.rb Index: test/ruby/enc/test_case_comprehensive.rb =================================================================== --- test/ruby/enc/test_case_comprehensive.rb (revision 55590) +++ test/ruby/enc/test_case_comprehensive.rb (revision 55591) @@ -247,7 +247,7 @@ class TestComprehensiveCaseFold https://github.com/ruby/ruby/blob/trunk/test/ruby/enc/test_case_comprehensive.rb#L247 generate_ascii_only_case_mapping_tests 'ISO-8859-10' generate_ascii_only_case_mapping_tests 'ISO-8859-13' generate_ascii_only_case_mapping_tests 'ISO-8859-14' - generate_ascii_only_case_mapping_tests 'ISO-8859-15' + generate_case_mapping_tests 'ISO-8859-15' generate_case_mapping_tests 'ISO-8859-16' generate_ascii_only_case_mapping_tests 'KOI8-R' generate_ascii_only_case_mapping_tests 'KOI8-U' Index: ChangeLog =================================================================== --- ChangeLog (revision 55590) +++ ChangeLog (revision 55591) @@ -1,3 +1,8 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1 +Wed Jul 6 18:59:13 2016 Martin Duerst <duerst@i...> + + * enc/iso_8859_15.c, test/ruby/enc/test_case_comprehensive.rb: + Implement non-ASCII case conversion for ISO-8859-15, by Maho Harada. + Wed Jul 6 18:34:21 2016 Martin Duerst <duerst@i...> * enc/iso_8859_16.c, test/ruby/enc/test_case_comprehensive.rb: Index: enc/iso_8859_15.c =================================================================== --- enc/iso_8859_15.c (revision 55590) +++ enc/iso_8859_15.c (revision 55591) @@ -220,6 +220,69 @@ get_case_fold_codes_by_str(OnigCaseFoldT https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_15.c#L220 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 (code==0xAA || code==0xBA) ; + else if ((EncISO_8859_15_CtypeTable[code] & BIT_CTYPE_UPPER) + && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) { + flags |= ONIGENC_CASE_MODIFIED; + if (code==0xA6) + code += 2; + else if (code==0xB4) + code += 4; + else if (code==0xBC) + code += 1; + else if (code==0xBE) + code += 0x41; + else + code += 0x20; + } + else if ((EncISO_8859_15_CtypeTable[code]&BIT_CTYPE_LOWER) + && (flags&ONIGENC_CASE_UPCASE)) { + flags |= ONIGENC_CASE_MODIFIED; + if (code==0xA8) + code -= 2; + else if (code==0xB8) + code -= 4; + else if (code==0xBD) + code -= 1; + else if (code==0xFF) + code -= 0x41; + 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_15, ISO_8859_15) = { onigenc_single_byte_mbc_enc_len, "ISO-8859-15", /* name */ @@ -240,7 +303,7 @@ OnigEncodingDefine(iso_8859_15, ISO_8859 https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_15.c#L303 0, ONIGENC_FLAG_NONE, #ifdef ONIG_CASE_MAPPING - onigenc_single_byte_ascii_only_case_map, + case_map, #endif /* ONIG_CASE_MAPPING */ }; ENC_ALIAS("ISO8859-15", "ISO-8859-15") -- ML: ruby-changes@q... Info: http://www.atdot.net/~ko1/quickml/