summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--ChangeLog5
-rw-r--r--enc/windows_1257.c56
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb2
3 files changed, 61 insertions, 2 deletions
diff --git a/ChangeLog b/ChangeLog
index b8c1f43dbad..7700b87f562 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+Tue Jul 26 16:33:16 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+
+ * enc/windows_1257.c, test/ruby/enc/test_case_comprehensive.rb:
+ Implement non-ASCII case conversion for Windows-1257, by Sho Koike.
+
Tue Jul 26 16:19:41 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* enc/windows_1250.c, test/ruby/enc/test_case_comprehensive.rb:
diff --git a/enc/windows_1257.c b/enc/windows_1257.c
index 557d4c00d76..40cdb969aa0 100644
--- a/enc/windows_1257.c
+++ b/enc/windows_1257.c
@@ -225,6 +225,60 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag,
flag, p, end, items);
}
+#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)
+{
+ 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==0xB5) ;
+ else if ((EncCP1252_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ 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_MODIFIED;
+ 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 )
+ 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_1257, Windows_1257) = {
onigenc_single_byte_mbc_enc_len,
"Windows-1257", /* name */
@@ -244,7 +298,7 @@ OnigEncodingDefine(windows_1257, Windows_1257) = {
onigenc_always_true_is_allowed_reverse_match,
0,
ONIGENC_FLAG_NONE,
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
};
ENC_ALIAS("CP1257", "Windows-1257")
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index 094abe627a3..e424d5a76da 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -293,7 +293,7 @@ TestComprehensiveCaseFold.data_files_available? and class TestComprehensiveCase
generate_ascii_only_case_mapping_tests 'Windows-1254'
generate_case_mapping_tests 'Windows-1255'
generate_ascii_only_case_mapping_tests 'Windows-1256'
- generate_ascii_only_case_mapping_tests 'Windows-1257'
+ generate_case_mapping_tests 'Windows-1257'
generate_unicode_case_mapping_tests 'UTF-8'
generate_unicode_case_mapping_tests 'UTF-16BE'
generate_unicode_case_mapping_tests 'UTF-16LE'