summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--ChangeLog7
-rw-r--r--enc/iso_8859_5.c36
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb16
3 files changed, 50 insertions, 9 deletions
diff --git a/ChangeLog b/ChangeLog
index 2adbd80de8..fe417e89ad 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+Wed Jul 13 14:40:04 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+
+ * enc/iso_8859_5.c, test/ruby/enc/test_case_comprehensive.rb:
+ Implement non-ASCII case conversion for ISO-8859-5, by Masaru Onodera.
+
+ * test/ruby/enc/test_case_comprehensive.rb: Fix order of encodings.
+
Wed Jul 13 14:28:33 2016 NARUSE, Yui <naruse@ruby-lang.org>
* math.c (rb_math_sqrt): r55646 must use f_signbit.
diff --git a/enc/iso_8859_5.c b/enc/iso_8859_5.c
index c538d56e31..a4e860db14 100644
--- a/enc/iso_8859_5.c
+++ b/enc/iso_8859_5.c
@@ -209,6 +209,40 @@ 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 ((EncISO_8859_5_CtypeTable[code] & BIT_CTYPE_UPPER)
+ && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ code = ENC_ISO_8859_5_TO_LOWER_CASE(code);
+ }
+ else if ((EncISO_8859_5_CtypeTable[code]&BIT_CTYPE_LOWER)
+ && (flags&ONIGENC_CASE_UPCASE)) {
+ flags |= ONIGENC_CASE_MODIFIED;
+ if (0xF1<=code && code<=0xFF)
+ code -= 0x50;
+ 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_5, ISO_8859_5) = {
onigenc_single_byte_mbc_enc_len,
"ISO-8859-5", /* name */
@@ -229,7 +263,7 @@ OnigEncodingDefine(iso_8859_5, ISO_8859_5) = {
0,
ONIGENC_FLAG_NONE,
#ifdef ONIG_CASE_MAPPING
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
#endif /* ONIG_CASE_MAPPING */
};
ENC_ALIAS("ISO8859-5", "ISO-8859-5")
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index 5796c5172c..bad02d0446 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -250,13 +250,19 @@ class TestComprehensiveCaseFold
end
end
+ generate_case_mapping_tests 'US-ASCII'
+ generate_case_mapping_tests 'ASCII-8BIT'
+ generate_case_mapping_tests 'ISO-8859-1'
generate_ascii_only_case_mapping_tests 'ISO-8859-2'
generate_case_mapping_tests 'ISO-8859-3'
generate_case_mapping_tests 'ISO-8859-4'
- generate_ascii_only_case_mapping_tests 'ISO-8859-5'
+ 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-8859-8'
generate_ascii_only_case_mapping_tests 'ISO-8859-9'
generate_case_mapping_tests 'ISO-8859-10'
+ generate_case_mapping_tests 'ISO-8859-11'
generate_case_mapping_tests 'ISO-8859-13'
generate_case_mapping_tests 'ISO-8859-14'
generate_case_mapping_tests 'ISO-8859-15'
@@ -276,15 +282,9 @@ class TestComprehensiveCaseFold
generate_ascii_only_case_mapping_tests 'Windows-1252'
generate_ascii_only_case_mapping_tests 'Windows-1253'
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 'ISO-8859-1'
- generate_case_mapping_tests 'US-ASCII'
- generate_case_mapping_tests 'ASCII-8BIT'
- generate_case_mapping_tests 'ISO-8859-11'
- generate_case_mapping_tests 'ISO-8859-8'
- generate_case_mapping_tests 'ISO-8859-6'
- generate_case_mapping_tests 'Windows-1255'
generate_unicode_case_mapping_tests 'UTF-8'
generate_unicode_case_mapping_tests 'UTF-16BE'
generate_unicode_case_mapping_tests 'UTF-16LE'