diff options
author | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-06-11 00:46:21 +0000 |
---|---|---|
committer | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-06-11 00:46:21 +0000 |
commit | 89c6644b5f464e3a07529cb4869528b45ae2ee65 (patch) | |
tree | c32a0bd7e9732f3f387ece638559ef79149c2b44 /enc | |
parent | 2cd23467fece5c4dfcaa0aba30065d1b48a890e0 (diff) | |
download | ruby-89c6644b5f464e3a07529cb4869528b45ae2ee65.tar.gz |
* enc/iso_8859_1.c: Implement non-ASCII case mapping.
* test/ruby/enc/test_case_comprehensive.rb: Tests for above.
* string.c: Add iso-8859-1 to supported encodings.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55373 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'enc')
-rw-r--r-- | enc/iso_8859_1.c | 45 |
1 files changed, 44 insertions, 1 deletions
diff --git a/enc/iso_8859_1.c b/enc/iso_8859_1.c index 10f63cc28e..5f0d3f91ab 100644 --- a/enc/iso_8859_1.c +++ b/enc/iso_8859_1.c @@ -254,6 +254,49 @@ is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc ARG_UNUSE return FALSE; } +#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, lower; + OnigUChar *to_start = to; + OnigCaseFoldType flags = *flagP; + + while (*pp<end && to<to_end) { + code = *(*pp)++; + if (code==0xdf) { /* 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 ((lower=ONIGENC_ISO_8859_1_TO_LOWER_CASE(code)) != code) + && (flags&ONIGENC_CASE_UPCASE)) { + flags |= ONIGENC_CASE_MODIFIED; + code = lower; + } + else if ((EncISO_8859_1_CtypeTable[code]&BIT_CTYPE_LOWER) + && (flags&ONIGENC_CASE_UPCASE)) { + 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); +} +#endif /* ONIG_CASE_MAPPING */ + OnigEncodingDefine(iso_8859_1, ISO_8859_1) = { onigenc_single_byte_mbc_enc_len, "ISO-8859-1", /* name */ @@ -274,7 +317,7 @@ OnigEncodingDefine(iso_8859_1, ISO_8859_1) = { 0, ONIGENC_FLAG_NONE, #ifdef ONIG_CASE_MAPPING - onigenc_single_byte_ascii_only_case_map, + case_map, #endif /* ONIG_CASE_MAPPING */ }; ENC_ALIAS("ISO8859-1", "ISO-8859-1") |