diff options
author | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-07-10 10:53:45 +0000 |
---|---|---|
committer | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-07-10 10:53:45 +0000 |
commit | b45befaf3c91f2d0da62a68aa9aab202309372fe (patch) | |
tree | 3dc81d9d7d74e574ac77feb814a1a705b0bc02ac | |
parent | 5260ddf810395858150b3608ed7a7f1fa75321a2 (diff) | |
download | ruby-b45befaf3c91f2d0da62a68aa9aab202309372fe.tar.gz |
* enc/iso_8859_10.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for ISO-8859-10, by Toya Hosokawa.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55627 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r-- | ChangeLog | 5 | ||||
-rw-r--r-- | enc/iso_8859_10.c | 52 | ||||
-rw-r--r-- | test/ruby/enc/test_case_comprehensive.rb | 2 |
3 files changed, 57 insertions, 2 deletions
@@ -1,3 +1,8 @@ +Sun Jul 10 19:53:41 2016 Martin Duerst <duerst@it.aoyama.ac.jp> + + * enc/iso_8859_10.c, test/ruby/enc/test_case_comprehensive.rb: + Implement non-ASCII case conversion for ISO-8859-10, by Toya Hosokawa. + Sun Jul 10 19:33:47 2016 Martin Duerst <duerst@it.aoyama.ac.jp> * test/ruby/enc/test_case_comprehensive.rb: Changed testing logic in to diff --git a/enc/iso_8859_10.c b/enc/iso_8859_10.c index 4bebcb5dd1..569c26c264 100644 --- a/enc/iso_8859_10.c +++ b/enc/iso_8859_10.c @@ -224,6 +224,56 @@ 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 (code==0xBD || code==0xFF) ; + else if ((EncISO_8859_10_CtypeTable[code] & BIT_CTYPE_UPPER) + && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) { + flags |= ONIGENC_CASE_MODIFIED; + if (code>=0xA0 && code<=0xBF) + code += 0x10; + else + code += 0x20; + } + else if ((EncISO_8859_10_CtypeTable[code]&BIT_CTYPE_LOWER) + && (flags&ONIGENC_CASE_UPCASE)) { + flags |= ONIGENC_CASE_MODIFIED; + if (code>=0xA0 && 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_10, ISO_8859_10) = { onigenc_single_byte_mbc_enc_len, "ISO-8859-10", /* name */ @@ -244,7 +294,7 @@ OnigEncodingDefine(iso_8859_10, ISO_8859_10) = { 0, ONIGENC_FLAG_NONE, #ifdef ONIG_CASE_MAPPING - onigenc_single_byte_ascii_only_case_map, + case_map, #endif /* ONIG_CASE_MAPPING */ }; ENC_ALIAS("ISO8859-10", "ISO-8859-10") diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb index d1d1c3b282..9a5c17724d 100644 --- a/test/ruby/enc/test_case_comprehensive.rb +++ b/test/ruby/enc/test_case_comprehensive.rb @@ -249,7 +249,7 @@ class TestComprehensiveCaseFold 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' - generate_ascii_only_case_mapping_tests 'ISO-8859-10' + generate_case_mapping_tests 'ISO-8859-10' generate_ascii_only_case_mapping_tests 'ISO-8859-13' generate_case_mapping_tests 'ISO-8859-14' generate_case_mapping_tests 'ISO-8859-15' |