1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00

Merge Onigmo 6.0.0

* https://github.com/k-takata/Onigmo/blob/Onigmo-6.0.0/HISTORY
* fix for ruby 2.4: https://github.com/k-takata/Onigmo/pull/78
* suppress warning: https://github.com/k-takata/Onigmo/pull/79
* include/ruby/oniguruma.h: include onigmo.h.
* template/encdb.h.tmpl: ignore duplicated definition of EUC-CN in
  enc/euc_kr.c. It is defined in enc/gb2313.c with CRuby macro.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57045 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
naruse 2016-12-10 17:47:04 +00:00
parent 42a677c895
commit 2873edeafb
57 changed files with 3098 additions and 3173 deletions

View file

@ -216,9 +216,9 @@ apply_all_case_fold(OnigCaseFoldType flag,
static int
get_case_fold_codes_by_str(OnigCaseFoldType flag,
const OnigUChar* p, const OnigUChar* end,
OnigCaseFoldCodeItem items[],
OnigEncoding enc ARG_UNUSED)
const OnigUChar* p, const OnigUChar* end,
OnigCaseFoldCodeItem items[],
OnigEncoding enc ARG_UNUSED)
{
return onigenc_get_case_fold_codes_by_str_with_map(
numberof(CaseFoldMap), CaseFoldMap, 1,
@ -228,55 +228,56 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag,
#define DOTLESS_i (0xB9)
#define I_WITH_DOT_ABOVE (0xA9)
static int
case_map (OnigCaseFoldType* flagP, const OnigUChar** pp,
const OnigUChar* end, OnigUChar* to, OnigUChar* to_end,
const struct OnigEncodingTypeST* enc)
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) {
while (*pp < end && to < to_end) {
code = *(*pp)++;
if (code==SHARP_s) {
if (flags&ONIGENC_CASE_UPCASE) {
if (code == SHARP_s) {
if (flags & ONIGENC_CASE_UPCASE) {
flags |= ONIGENC_CASE_MODIFIED;
*to++ = 'S';
code = (flags&ONIGENC_CASE_TITLECASE) ? 's' : 'S';
code = (flags & ONIGENC_CASE_TITLECASE) ? 's' : 'S';
}
else if (flags&ONIGENC_CASE_FOLD) {
else if (flags & ONIGENC_CASE_FOLD) {
flags |= ONIGENC_CASE_MODIFIED;
*to++ = 's';
code = 's';
}
}
else if (code==0xB5) ;
else if (code == 0xB5)
;
else if ((EncCP1252_CtypeTable[code] & BIT_CTYPE_UPPER)
&& (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
&& (flags & (ONIGENC_CASE_DOWNCASE | ONIGENC_CASE_FOLD))) {
flags |= ONIGENC_CASE_MODIFIED;
if (code=='I')
code = flags&ONIGENC_CASE_FOLD_TURKISH_AZERI ? DOTLESS_i : 'i';
if (code == 'I')
code = flags & ONIGENC_CASE_FOLD_TURKISH_AZERI ? DOTLESS_i : 'i';
else
code = ENC_CP1252_TO_LOWER_CASE(code);
}
else if ((EncCP1252_CtypeTable[code]&BIT_CTYPE_LOWER)
&& (flags&ONIGENC_CASE_UPCASE)) {
&& (flags & ONIGENC_CASE_UPCASE)) {
flags |= ONIGENC_CASE_MODIFIED;
if (code=='i')
code = flags&ONIGENC_CASE_FOLD_TURKISH_AZERI ? I_WITH_DOT_ABOVE : 'I';
else if (code==DOTLESS_i)
if (code == 'i')
code = flags & ONIGENC_CASE_FOLD_TURKISH_AZERI ? I_WITH_DOT_ABOVE : 'I';
else if (code == DOTLESS_i)
code = 'I';
else if (code>=0xB0 && code<=0xBF )
else if (code >= 0xB0 && 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);
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);
return (int )(to - to_start);
}
OnigEncodingDefine(windows_1257, Windows_1257) = {
@ -296,9 +297,8 @@ OnigEncodingDefine(windows_1257, Windows_1257) = {
onigenc_not_support_get_ctype_code_range,
onigenc_single_byte_left_adjust_char_head,
onigenc_always_true_is_allowed_reverse_match,
case_map,
0,
ONIGENC_FLAG_NONE,
case_map,
};
ENC_ALIAS("CP1257", "Windows-1257")