summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--ChangeLog5
-rw-r--r--enc/windows_1251.c43
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb2
3 files changed, 48 insertions, 2 deletions
diff --git a/ChangeLog b/ChangeLog
index 01b4554..1a50c3d 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+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_1251.c b/enc/windows_1251.c
index b9675cf..0f9b7fa 100644
--- a/enc/windows_1251.c
+++ b/enc/windows_1251.c
@@ -180,6 +180,47 @@ cp1251_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 ((EncCP1251_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ code = ENC_CP1251_TO_LOWER_CASE(code);
+ }
+ else if (code==0xB5) ;
+ else if ((EncCP1251_CtypeTable[code]&BIT_CTYPE_LOWER)
+ && (flags&ONIGENC_CASE_UPCASE)) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if ((0x61<=code && code<=0x7A) || (0xE0<=code && code<=0xFF))
+ code -= 0x20;
+ else if (code==0xA2 || code==0xB3 || code==0xBE)
+ code -= 0x01;
+ else if (code==0x83)
+ code = 0x81;
+ else if (code==0xBC)
+ code = 0xA3;
+ else if (code==0xB4)
+ code = 0xA5;
+ else
+ code -= 0x10;
+ }
+ *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_1251, Windows_1251) = {
onigenc_single_byte_mbc_enc_len,
"Windows-1251", /* name */
@@ -199,7 +240,7 @@ OnigEncodingDefine(windows_1251, Windows_1251) = {
onigenc_always_true_is_allowed_reverse_match,
0,
ONIGENC_FLAG_NONE,
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
};
/*
* Name: windows-1251
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index 13c61ba..dabe727 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -287,7 +287,7 @@ TestComprehensiveCaseFold.data_files_available? and class TestComprehensiveCase
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_ascii_only_case_mapping_tests 'Windows-1251'
+ generate_case_mapping_tests 'Windows-1251'
generate_case_mapping_tests 'Windows-1252'
generate_ascii_only_case_mapping_tests 'Windows-1253'
generate_ascii_only_case_mapping_tests 'Windows-1254'