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

* enc/windows_1252.c, test/ruby/enc/test_case_comprehensive.rb:

Browse source 
Implement non-ASCII case conversion for Windows-1252, by Serina Tai.
* test/ruby/enc/test_case_comprehensive.rb: Fix order of encodings.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55665 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
duerst 2016-07-13 08:21:29 +00:00
parent 6a52a5488a
commit 9f74ae4cf5
3 changed files with 59 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ChangeLog
View file

@ -1,3 +1,10 @@
Wed Jul 13 17:21:24 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* enc/windows_1252.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for Windows-1252, by Serina Tai.
* test/ruby/enc/test_case_comprehensive.rb: Fix order of encodings.
Wed Jul 13 16:19:14 2016 Martin Duerst <duerst@it.aoyama.ac.jp> Wed Jul 13 16:19:14 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* enc/iso_8859_7.c, test/ruby/enc/test_case_comprehensive.rb: * enc/iso_8859_7.c, test/ruby/enc/test_case_comprehensive.rb:

54
enc/windows_1252.c
View file

@ -1,5 +1,5 @@
/********************************************************************** /**********************************************************************
windows_1252.c - Oniguruma (regular expression library) cp1252.c - Oniguruma (regular expression library)
**********************************************************************/ **********************************************************************/
/*- /*-
* Copyright (c) 2006-2007 Byte <byte AT mail DOT kna DOT ru> * Copyright (c) 2006-2007 Byte <byte AT mail DOT kna DOT ru>
@ -29,6 +29,7 @@
*/ */
#include "regenc.h" #include "regenc.h"
#include "iso_8859.h"
#define ENC_CP1252_TO_LOWER_CASE(c) EncCP1252_ToLowerCaseTable[c] #define ENC_CP1252_TO_LOWER_CASE(c) EncCP1252_ToLowerCaseTable[c]
#define ENC_IS_CP1252_CTYPE(code,ctype) \ #define ENC_IS_CP1252_CTYPE(code,ctype) \
@ -114,7 +115,6 @@ cp1252_mbc_case_fold(OnigCaseFoldType flag ARG_UNUSED,
(*pp)++; (*pp)++;
return 1; return 1;
} }
static int static int
cp1252_is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc ARG_UNUSED) cp1252_is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc ARG_UNUSED)
{ {
@ -180,6 +180,54 @@ cp1252_get_case_fold_codes_by_str(OnigCaseFoldType flag,
sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 1, sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 1,
flag, p, end, items); 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 ((EncCP1252_CtypeTable[code] & BIT_CTYPE_UPPER)
&& (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
flags |= ONIGENC_CASE_MODIFIED;
code = ENC_CP1252_TO_LOWER_CASE(code);
}
else if (code==0x83 || code==0xAA || code==0xBA || code==0xB5) ;
else if ((EncCP1252_CtypeTable[code]&BIT_CTYPE_LOWER)
&& (flags&ONIGENC_CASE_UPCASE)) {
flags |= ONIGENC_CASE_MODIFIED;
if (code==0x9A || code==0x9C || code==0x9E)
code -= 0x10;
else if (code==0xFF)
code -= 0x60;
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(windows_1252, Windows_1252) = { OnigEncodingDefine(windows_1252, Windows_1252) = {
onigenc_single_byte_mbc_enc_len, onigenc_single_byte_mbc_enc_len,
@ -201,7 +249,7 @@ OnigEncodingDefine(windows_1252, Windows_1252) = {
0, 0,
ONIGENC_FLAG_NONE, ONIGENC_FLAG_NONE,
#ifdef ONIG_CASE_MAPPING #ifdef ONIG_CASE_MAPPING
onigenc_single_byte_ascii_only_case_map, case_map,
#endif /* ONIG_CASE_MAPPING */ #endif /* ONIG_CASE_MAPPING */
}; };
/* /*

2
test/ruby/enc/test_case_comprehensive.rb
View file

@ -279,7 +279,7 @@ class TestComprehensiveCaseFold
generate_ascii_only_case_mapping_tests 'Windows-31J' generate_ascii_only_case_mapping_tests 'Windows-31J'
generate_ascii_only_case_mapping_tests 'Windows-1250' generate_ascii_only_case_mapping_tests 'Windows-1250'
generate_ascii_only_case_mapping_tests 'Windows-1251' generate_ascii_only_case_mapping_tests 'Windows-1251'
generate_ascii_only_case_mapping_tests 'Windows-1252' generate_case_mapping_tests 'Windows-1252'
generate_ascii_only_case_mapping_tests 'Windows-1253' generate_ascii_only_case_mapping_tests 'Windows-1253'
generate_ascii_only_case_mapping_tests 'Windows-1254' generate_ascii_only_case_mapping_tests 'Windows-1254'
generate_case_mapping_tests 'Windows-1255' generate_case_mapping_tests 'Windows-1255'