summaryrefslogtreecommitdiff
path: root/enc/iso_8859_14.c
diff options
context:
space:
mode:
authorduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-06 10:54:24 +0000
committerduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-06 10:54:24 +0000
commit1edb021b5ced5c8cff609c1a6181825b829f053b (patch)
treec78ead6d3473775ab26e4d3da1f2195ab12798df /enc/iso_8859_14.c
parent5636291d383ecfa538dce431e51d72d411a09b24 (diff)
* enc/iso_8859_14.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for ISO-8859-14, by Yutaro Tada. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55595 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'enc/iso_8859_14.c')
-rw-r--r--enc/iso_8859_14.c72
1 files changed, 71 insertions, 1 deletions
diff --git a/enc/iso_8859_14.c b/enc/iso_8859_14.c
index bfe374b608..31380a999b 100644
--- a/enc/iso_8859_14.c
+++ b/enc/iso_8859_14.c
@@ -226,6 +226,76 @@ 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==0xAA || code==0xBA) ;
+ else if ((EncISO_8859_14_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if (code == 0xA1 || code == 0xA4 || code == 0xB0 || code == 0xB2 || code == 0xB4 || code == 0xBD)
+ code += 0x1;
+ else if(code == 0xA6)
+ code += 0x5;
+ else if(code == 0xAF)
+ code += 0x50;
+ else if(code == 0xB7)
+ code += 0x2;
+ else if(code == 0xBB)
+ code += 0x4;
+ else if(code == 0xA8 || code == 0xAA || code == 0xAC)
+ code += 0x10;
+ else
+ code += 0x20;
+ }
+ else if ((EncISO_8859_14_CtypeTable[code]&BIT_CTYPE_LOWER)
+ && (flags&ONIGENC_CASE_UPCASE)) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if(code == 0xA2 || code == 0xA5 || code == 0xB1 || code == 0xB3 || code == 0xB5 || code == 0xBE)
+ code -= 0x1;
+ else if(code == 0xAB)
+ code -= 0x5;
+ else if(code == 0xFF)
+ code -= 0x50;
+ else if(code == 0xB9)
+ code -= 0x2;
+ else if(code == 0xBF)
+ code -= 0x4;
+ else if(code == 0xB8 || code == 0xBA || code == 0xBC)
+ 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_14, ISO_8859_14) = {
onigenc_single_byte_mbc_enc_len,
"ISO-8859-14", /* name */
@@ -246,7 +316,7 @@ OnigEncodingDefine(iso_8859_14, ISO_8859_14) = {
0,
ONIGENC_FLAG_NONE,
#ifdef ONIG_CASE_MAPPING
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
#endif /* ONIG_CASE_MAPPING */
};
ENC_ALIAS("ISO8859-14", "ISO-8859-14")