summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-26 07:19:43 +0000
committerduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-26 07:19:43 +0000
commit14dd8a17e84e123299dab248ef4060d817e0d7d6 (patch)
treea737d2f43c2834a45f463096a56be01d73c80f61
parentaec1ac6e5127c19d8db89f464e42cca439333974 (diff)
* enc/windows_1250.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for Windows-1250, by Sho Koike. * ChangeLog: Fixed order of previous two entries. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55751 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r--ChangeLog15
-rw-r--r--enc/windows_1250.c55
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb2
3 files changed, 64 insertions, 8 deletions
diff --git a/ChangeLog b/ChangeLog
index 039f930..b8c1f43 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,13 +1,20 @@
-Tue Jul 26 15:54:17 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+Tue Jul 26 16:19:41 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
- * enc/windows_1251.c, test/ruby/enc/test_case_comprehensive.rb:
- Implement non-ASCII case conversion for Windows-1251, by Shunsuke Sato.
+ * enc/windows_1250.c, test/ruby/enc/test_case_comprehensive.rb:
+ Implement non-ASCII case conversion for Windows-1250, by Sho Koike.
-Tue Jul 26 15:30:37 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+ * ChangeLog: Fixed order of previous two entries.
+
+Tue Jul 26 15:54:17 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* enc/windows_1253.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for Windows-1253, by Takumi Koyama.
+Tue Jul 26 15:30:37 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+
+ * enc/windows_1251.c, test/ruby/enc/test_case_comprehensive.rb:
+ Implement non-ASCII case conversion for Windows-1251, by Shunsuke Sato.
+
Tue Jul 26 13:04:59 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* test/ruby/enc/test_case_comprehensive.rb: Add explicit skip test for
diff --git a/enc/windows_1250.c b/enc/windows_1250.c
index aed293b..47317dd 100644
--- a/enc/windows_1250.c
+++ b/enc/windows_1250.c
@@ -29,6 +29,7 @@
*/
#include "regenc.h"
+#include "iso_8859.h"
#define ENC_CP1250_TO_LOWER_CASE(c) EncCP1250_ToLowerCaseTable[c]
#define ENC_IS_CP1250_CTYPE(code,ctype) \
@@ -101,7 +102,7 @@ static const unsigned short EncCP1250_CtypeTable[256] = {
0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,/* E */
0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,
0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x00a0,/* F */
- 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,
+ 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x00a0,
};
static int
@@ -189,6 +190,55 @@ cp1250_get_case_fold_codes_by_str(OnigCaseFoldType flag,
flag, p, end, items);
}
+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 ((EncCP1250_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ code = ENC_CP1250_TO_LOWER_CASE(code);
+ }
+ else if (code==0xB5) ;
+ else if ((EncCP1250_CtypeTable[code]&BIT_CTYPE_LOWER)
+ && (flags&ONIGENC_CASE_UPCASE)) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if (code==0xB9)
+ code = 0xA5;
+ else if (code==0xBE)
+ code = 0xBC;
+ else if (code >= 0x8A && code <= 0xBF && code!=0xB9)
+ 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);
+}
+
OnigEncodingDefine(windows_1250, Windows_1250) = {
onigenc_single_byte_mbc_enc_len,
"Windows-1250", /* name */
@@ -208,7 +258,7 @@ OnigEncodingDefine(windows_1250, Windows_1250) = {
onigenc_always_true_is_allowed_reverse_match,
0,
ONIGENC_FLAG_NONE,
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
};
/*
* Name: windows-1250
@@ -218,4 +268,3 @@ OnigEncodingDefine(windows_1250, Windows_1250) = {
* Link: http://en.wikipedia.org/wiki/Windows-1250
*/
ENC_ALIAS("CP1250", "Windows-1250")
-
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index 1cbb7eb..094abe6 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -286,7 +286,7 @@ TestComprehensiveCaseFold.data_files_available? and class TestComprehensiveCase
generate_ascii_only_case_mapping_tests 'GBK'
generate_ascii_only_case_mapping_tests 'Shift_JIS'
generate_ascii_only_case_mapping_tests 'Windows-31J'
- generate_ascii_only_case_mapping_tests 'Windows-1250'
+ generate_case_mapping_tests 'Windows-1250'
generate_case_mapping_tests 'Windows-1251'
generate_case_mapping_tests 'Windows-1252'
generate_case_mapping_tests 'Windows-1253'