diff options
author | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-07-13 07:19:25 +0000 |
---|---|---|
committer | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-07-13 07:19:25 +0000 |
commit | 1e773600ba29f13070a6f1c7c94bea7f147576d1 (patch) | |
tree | 9049c8e7dddf9fbb40e2d29057da9f7eb49f084d /enc/iso_8859_7.c | |
parent | 4474e843ae46757fab05ed6bf2432e2069b05685 (diff) | |
download | ruby-1e773600ba29f13070a6f1c7c94bea7f147576d1.tar.gz |
* enc/iso_8859_7.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for ISO-8859-7, by Kosuke Kurihara.
* test/ruby/enc/test_case_comprehensive.rb: Fix order of encodings.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55664 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'enc/iso_8859_7.c')
-rw-r--r-- | enc/iso_8859_7.c | 58 |
1 files changed, 57 insertions, 1 deletions
diff --git a/enc/iso_8859_7.c b/enc/iso_8859_7.c index bf4235c7f9..aae9cb0c76 100644 --- a/enc/iso_8859_7.c +++ b/enc/iso_8859_7.c @@ -205,6 +205,62 @@ 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==0xF2) { + if (flags&ONIGENC_CASE_UPCASE) { + flags |= ONIGENC_CASE_MODIFIED; + code = 0xD3; + } + else if (flags&ONIGENC_CASE_FOLD) { + flags |= ONIGENC_CASE_MODIFIED; + code = 0xF3; + } + } + else if ((EncISO_8859_7_CtypeTable[code] & BIT_CTYPE_UPPER) + && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) { + flags |= ONIGENC_CASE_MODIFIED; + code = ENC_ISO_8859_7_TO_LOWER_CASE(code); + } + else if (code==0xC0 || code==0xE0) + ; + else if ((EncISO_8859_7_CtypeTable[code]&BIT_CTYPE_LOWER) + && (flags&ONIGENC_CASE_UPCASE)) { + flags |= ONIGENC_CASE_MODIFIED; + if (code==0xDC) { + code-=0x26; + } + else if (code>=0xDD && code<=0xDF) { + code-=0x25; + } + else if (code==0xFC) { + code-=0x40; + } + else if (code==0xFD || code==0xFE) { + code-=0x3F; + } + 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_7, ISO_8859_7) = { onigenc_single_byte_mbc_enc_len, @@ -226,7 +282,7 @@ OnigEncodingDefine(iso_8859_7, ISO_8859_7) = { 0, ONIGENC_FLAG_NONE, #ifdef ONIG_CASE_MAPPING - onigenc_single_byte_ascii_only_case_map, + case_map, #endif /* ONIG_CASE_MAPPING */ }; ENC_ALIAS("ISO8859-7", "ISO-8859-7") |