duerst	2016-07-30 12:00:09 +0900 (Sat, 30 Jul 2016)

  New Revision: 55775

  https://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=55775

  Log:
    * enc/iso_8859_2.c, test/ruby/enc/test_case_comprehensive.rb:
      Implement non-ASCII case conversion for ISO-8859-2, by Yushiro Ishii.

  Modified files:
    trunk/ChangeLog
    trunk/enc/iso_8859_2.c
    trunk/test/ruby/enc/test_case_comprehensive.rb
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 55774)
+++ ChangeLog	(revision 55775)
@@ -1,3 +1,8 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Sat Jul 30 12:00:01 2016  Martin Duerst  <duerst@i...>
+
+	* enc/iso_8859_2.c, test/ruby/enc/test_case_comprehensive.rb:
+	  Implement non-ASCII case conversion for ISO-8859-2, by Yushiro Ishii.
+
 Fri Jul 29 20:57:12 2016  chuanshuo  <lilijreey@1...>
 
 	* *.c: rename rb_funcall2 to rb_funcallv, except for extensions
Index: enc/iso_8859_2.c
===================================================================
--- enc/iso_8859_2.c	(revision 55774)
+++ enc/iso_8859_2.c	(revision 55775)
@@ -1,4 +1,4 @@ https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_2.c#L1
-/**********************************************************************
+    /**********************************************************************
   iso8859_2.c -  Oniguruma (regular expression library)
 **********************************************************************/
 /*-
@@ -220,6 +220,53 @@ is_code_ctype(OnigCodePoint code, unsign https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_2.c#L220
     return FALSE;
 }
 
+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 ((EncISO_8859_2_CtypeTable[code] & BIT_CTYPE_UPPER)
+	     && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+      flags |= ONIGENC_CASE_MODIFIED;
+      code = ENC_ISO_8859_2_TO_LOWER_CASE(code);
+    }
+    else if ((EncISO_8859_2_CtypeTable[code]&BIT_CTYPE_LOWER)
+       && (flags&ONIGENC_CASE_UPCASE)) {
+      if (code>=0xB1 && code<=0xBF){
+	flags |= ONIGENC_CASE_MODIFIED;
+	code -= 0x10;
+      }
+      else{
+	flags |= ONIGENC_CASE_MODIFIED;
+	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(iso_8859_2, ISO_8859_2) = {
   onigenc_single_byte_mbc_enc_len,
   "ISO-8859-2",  /* name */
@@ -239,6 +286,6 @@ OnigEncodingDefine(iso_8859_2, ISO_8859_ https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_2.c#L286
   onigenc_always_true_is_allowed_reverse_match,
   0,
   ONIGENC_FLAG_NONE,
-  onigenc_single_byte_ascii_only_case_map,
+  case_map,
 };
 ENC_ALIAS("ISO8859-2", "ISO-8859-2")
Index: test/ruby/enc/test_case_comprehensive.rb
===================================================================
--- test/ruby/enc/test_case_comprehensive.rb	(revision 55774)
+++ test/ruby/enc/test_case_comprehensive.rb	(revision 55775)
@@ -262,7 +262,7 @@ TestComprehensiveCaseFold.data_files_ava https://github.com/ruby/ruby/blob/trunk/test/ruby/enc/test_case_comprehensive.rb#L262
   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-8859-2'
   generate_case_mapping_tests 'ISO-8859-3'
   generate_case_mapping_tests 'ISO-8859-4'
   generate_case_mapping_tests 'ISO-8859-5'

--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/