duerst	2016-07-26 16:33:18 +0900 (Tue, 26 Jul 2016)

  New Revision: 55752

  https://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=55752

  Log:
    * enc/windows_1257.c, test/ruby/enc/test_case_comprehensive.rb:
      Implement non-ASCII case conversion for Windows-1257, by Sho Koike.

  Modified files:
    trunk/ChangeLog
    trunk/enc/windows_1257.c
    trunk/test/ruby/enc/test_case_comprehensive.rb
Index: test/ruby/enc/test_case_comprehensive.rb
===================================================================
--- test/ruby/enc/test_case_comprehensive.rb	(revision 55751)
+++ test/ruby/enc/test_case_comprehensive.rb	(revision 55752)
@@ -293,7 +293,7 @@ TestComprehensiveCaseFold.data_files_ava https://github.com/ruby/ruby/blob/trunk/test/ruby/enc/test_case_comprehensive.rb#L293
   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'
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 55751)
+++ ChangeLog	(revision 55752)
@@ -1,3 +1,8 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Tue Jul 26 16:33:16 2016  Martin Duerst  <duerst@i...>
+
+	* 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@i...>
 
 	* enc/windows_1250.c, test/ruby/enc/test_case_comprehensive.rb:
Index: enc/windows_1257.c
===================================================================
--- enc/windows_1257.c	(revision 55751)
+++ enc/windows_1257.c	(revision 55752)
@@ -225,6 +225,60 @@ get_case_fold_codes_by_str(OnigCaseFoldT https://github.com/ruby/ruby/blob/trunk/enc/windows_1257.c#L225
 	     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 https://github.com/ruby/ruby/blob/trunk/enc/windows_1257.c#L298
   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")

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