[前][次][番号順一覧][スレッド一覧]

ruby-changes:43551

From: duerst <ko1@a...>
Date: Sun, 10 Jul 2016 17:05:46 +0900 (JST)
Subject: [ruby-changes:43551] duerst:r55624 (trunk): * enc/iso_8859_4.c, test/ruby/enc/test_case_comprehensive.rb:

duerst	2016-07-10 17:05:39 +0900 (Sun, 10 Jul 2016)

  New Revision: 55624

  https://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=55624

  Log:
    * enc/iso_8859_4.c, test/ruby/enc/test_case_comprehensive.rb:
      Implement non-ASCII case conversion for ISO-8859-4, by Kotaro Yoshida.

  Modified files:
    trunk/ChangeLog
    trunk/enc/iso_8859_4.c
    trunk/test/ruby/enc/test_case_comprehensive.rb
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 55623)
+++ ChangeLog	(revision 55624)
@@ -1,3 +1,8 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Sun Jul 10 17:05:36 2016  Martin Duerst  <duerst@i...>
+
+	* enc/iso_8859_4.c, test/ruby/enc/test_case_comprehensive.rb:
+	  Implement non-ASCII case conversion for ISO-8859-4, by Kotaro Yoshida.
+
 Sun Jul 10 16:17:47 2016  Martin Duerst  <duerst@i...>
 
 	* test/ruby/enc/test_case_comprehensive.rb: Fixed a comment
Index: enc/iso_8859_4.c
===================================================================
--- enc/iso_8859_4.c	(revision 55623)
+++ enc/iso_8859_4.c	(revision 55624)
@@ -223,6 +223,65 @@ get_case_fold_codes_by_str(OnigCaseFoldT https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_4.c#L223
 	     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==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_4_CtypeTable[code] & BIT_CTYPE_UPPER)
+	     && (flags & (ONIGENC_CASE_DOWNCASE|ONIGENC_CASE_FOLD))) {
+      flags |= ONIGENC_CASE_MODIFIED;
+      if (code>=0xA0 && code<=0xBF) {
+	if (code==0xBD)
+	  code += 0x02; 
+	else
+	  code += 0x10;
+      }
+      else
+	code += 0x20;
+    }
+    else if ((EncISO_8859_4_CtypeTable[code]&BIT_CTYPE_LOWER)
+	     && (flags&ONIGENC_CASE_UPCASE)) {
+      flags |= ONIGENC_CASE_MODIFIED;
+      if (code>=0xA0&&code<=0xBF) {
+	if (code==0xBF)
+	  code -= 0x02;
+	else if (code==0xA2)
+	  ;
+	else
+	  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);
+}
+#endif   /* ONIG_CASE_MAPPING */
+
 OnigEncodingDefine(iso_8859_4, ISO_8859_4) = {
   onigenc_single_byte_mbc_enc_len,
   "ISO-8859-4",  /* name */
@@ -243,7 +302,7 @@ OnigEncodingDefine(iso_8859_4, ISO_8859_ https://github.com/ruby/ruby/blob/trunk/enc/iso_8859_4.c#L302
   0,
   ONIGENC_FLAG_NONE,
 #ifdef ONIG_CASE_MAPPING
-  onigenc_single_byte_ascii_only_case_map,
+  case_map,
 #endif   /* ONIG_CASE_MAPPING */
 };
 ENC_ALIAS("ISO8859-4", "ISO-8859-4")
Index: test/ruby/enc/test_case_comprehensive.rb
===================================================================
--- test/ruby/enc/test_case_comprehensive.rb	(revision 55623)
+++ test/ruby/enc/test_case_comprehensive.rb	(revision 55624)
@@ -240,7 +240,7 @@ class TestComprehensiveCaseFold https://github.com/ruby/ruby/blob/trunk/test/ruby/enc/test_case_comprehensive.rb#L240
 
   generate_ascii_only_case_mapping_tests 'ISO-8859-2'
   generate_ascii_only_case_mapping_tests 'ISO-8859-3'
-  generate_ascii_only_case_mapping_tests 'ISO-8859-4'
+  generate_case_mapping_tests 'ISO-8859-4'
   generate_ascii_only_case_mapping_tests 'ISO-8859-5'
   generate_ascii_only_case_mapping_tests 'ISO-8859-7'
   generate_ascii_only_case_mapping_tests 'ISO-8859-9'

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

[前][次][番号順一覧][スレッド一覧]