summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-13 09:09:47 +0000
committerduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-07-13 09:09:47 +0000
commit2ac58e689131e368a0148b05856054c0e04d7409 (patch)
tree4ce21f007c86f0c509ed804e7c876420d2b206cd
parent9f74ae4cf5ae8a53d0c00532f27d96e9c981f8ff (diff)
* enc/iso_8859_9.c, test/ruby/enc/test_case_comprehensive.rb:
Implement non-ASCII case conversion for ISO-8859-9, by Kazuki Iijima. * enc/iso_8859_9.c: Exclude dotless i/I with dot from case-insensitive matching because they are not a case pair. * test/ruby/enc/test_iso_8859.rb: Make test coverage for ISO-8859-9 a bit more complete. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55666 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r--ChangeLog11
-rw-r--r--enc/iso_8859_9.c60
-rw-r--r--test/ruby/enc/test_case_comprehensive.rb2
-rw-r--r--test/ruby/enc/test_iso_8859.rb2
4 files changed, 70 insertions, 5 deletions
diff --git a/ChangeLog b/ChangeLog
index aa1e670e4a6..8ada3a49624 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,14 @@
+Wed Jul 13 18:09:42 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
+
+ * enc/iso_8859_9.c, test/ruby/enc/test_case_comprehensive.rb:
+ Implement non-ASCII case conversion for ISO-8859-9, by Kazuki Iijima.
+
+ * enc/iso_8859_9.c: Exclude dotless i/I with dot from case-insensitive
+ matching because they are not a case pair.
+
+ * test/ruby/enc/test_iso_8859.rb: Make test coverage for ISO-8859-9
+ a bit more complete.
+
Wed Jul 13 17:21:24 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* enc/windows_1252.c, test/ruby/enc/test_case_comprehensive.rb:
diff --git a/enc/iso_8859_9.c b/enc/iso_8859_9.c
index 668168daa9a..5b80ebe0fe0 100644
--- a/enc/iso_8859_9.c
+++ b/enc/iso_8859_9.c
@@ -62,7 +62,7 @@ static const UChar EncISO_8859_9_ToLowerCaseTable[256] = {
'\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
'\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357',
'\360', '\361', '\362', '\363', '\364', '\365', '\366', '\327',
- '\370', '\371', '\372', '\373', '\374', '\335', '\376', '\337',
+ '\370', '\371', '\372', '\373', '\374', '\151', '\376', '\337',
'\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
'\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357',
'\360', '\361', '\362', '\363', '\364', '\365', '\366', '\367',
@@ -188,7 +188,7 @@ static const OnigPairCaseFoldCodes CaseFoldMap[] = {
{ 0xda, 0xfa },
{ 0xdb, 0xfb },
{ 0xdc, 0xfc },
- { 0xdd, 0xfd },
+ /*{ 0xdd, 0xfd }, exclude dotless i/I with dot; not a case pair */
{ 0xde, 0xfe }
};
@@ -213,6 +213,60 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag,
flag, p, end, items);
}
+#ifdef ONIG_CASE_MAPPING
+#define DOTLESS_i (0xFD)
+#define I_WITH_DOT_ABOVE (0xDD)
+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==0xAA || code==0xB5 || code==0xBA || code==0xFF) ;
+ else if ((EncISO_8859_9_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_ISO_8859_9_TO_LOWER_CASE(code);
+ }
+ else if ((EncISO_8859_9_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
+ 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_9, ISO_8859_9) = {
onigenc_single_byte_mbc_enc_len,
"ISO-8859-9", /* name */
@@ -233,7 +287,7 @@ OnigEncodingDefine(iso_8859_9, ISO_8859_9) = {
0,
ONIGENC_FLAG_NONE,
#ifdef ONIG_CASE_MAPPING
- onigenc_single_byte_ascii_only_case_map,
+ case_map,
#endif /* ONIG_CASE_MAPPING */
};
ENC_ALIAS("ISO8859-9", "ISO-8859-9")
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index 62e2121e843..40f4327e63d 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -260,7 +260,7 @@ class TestComprehensiveCaseFold
generate_case_mapping_tests 'ISO-8859-6'
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-8859-9'
generate_case_mapping_tests 'ISO-8859-10'
generate_case_mapping_tests 'ISO-8859-11'
generate_case_mapping_tests 'ISO-8859-13'
diff --git a/test/ruby/enc/test_iso_8859.rb b/test/ruby/enc/test_iso_8859.rb
index 067c375f510..ed663be2430 100644
--- a/test/ruby/enc/test_iso_8859.rb
+++ b/test/ruby/enc/test_iso_8859.rb
@@ -123,7 +123,7 @@ class TestISO8859 < Test::Unit::TestCase
assert_match(/^[\xdfz]+$/i, "sszzsszz")
assert_match(/^SS$/i, "\xdf")
assert_match(/^Ss$/i, "\xdf")
- ([*(0xc0..0xdc)] - [0xd7]).each do |c|
+ ([*(0xc0..0xde)] - [0xd7, 0xdd]).each do |c|
c1 = c.chr("iso8859-9")
c2 = (c + 0x20).chr("iso8859-9")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)