summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--ChangeLog7
-rw-r--r--enc/iso_8859_7.c58
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb2
3 files changed, 65 insertions, 2 deletions
diff --git a/ChangeLog b/ChangeLog
index 654f971..ea4ca0b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+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:
+ Implement non-ASCII case conversion for ISO-8859-7, by Kosuke Kurihara.
+
+ * test/ruby/enc/test_case_comprehensive.rb: Fix order of encodings.
+
Wed Jul 13 16:08:08 2016 Koichi Sasada <ko1@atdot.net>
* gc.c (gc_mark_roots): should mark the VM object itself to mark
diff --git a/enc/iso_8859_7.c b/enc/iso_8859_7.c
index bf4235c..aae9cb0 100644
--- a/enc/iso_8859_7.c
+++ b/enc/iso_8859_7.c
@@ -205,6 +205,62 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag,
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==0xF2) {
+ if (flags&ONIGENC_CASE_UPCASE) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ code = 0xD3;
+ }
+ else if (flags&ONIGENC_CASE_FOLD) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ code = 0xF3;
+ }
+ }
+ else if ((EncISO_8859_7_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ code = ENC_ISO_8859_7_TO_LOWER_CASE(code);
+ }
+ else if (code==0xC0 || code==0xE0)
+ ;
+ else if ((EncISO_8859_7_CtypeTable[code]&BIT_CTYPE_LOWER)
+ && (flags&ONIGENC_CASE_UPCASE)) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if (code==0xDC) {
+ code-=0x26;
+ }
+ else if (code>=0xDD && code<=0xDF) {
+ code-=0x25;
+ }
+ else if (code==0xFC) {
+ code-=0x40;
+ }
+ else if (code==0xFD || code==0xFE) {
+ code-=0x3F;
+ }
+ 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(iso_8859_7, ISO_8859_7) = {
onigenc_single_byte_mbc_enc_len,
@@ -226,7 +282,7 @@ OnigEncodingDefine(iso_8859_7, ISO_8859_7) = {
0,
ONIGENC_FLAG_NONE,
#ifdef ONIG_CASE_MAPPING
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
#endif /* ONIG_CASE_MAPPING */
};
ENC_ALIAS("ISO8859-7", "ISO-8859-7")
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index bad02d0..e8e1064 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -258,7 +258,7 @@ class TestComprehensiveCaseFold
generate_case_mapping_tests 'ISO-8859-4'
generate_case_mapping_tests 'ISO-8859-5'
generate_case_mapping_tests 'ISO-8859-6'
- generate_ascii_only_case_mapping_tests 'ISO-8859-7'
+ generate_case_mapping_tests 'ISO-8859-7'
generate_case_mapping_tests 'ISO-8859-8'
generate_ascii_only_case_mapping_tests 'ISO-8859-9'
generate_case_mapping_tests 'ISO-8859-10'