* enc/iso_8859_1.c: Implement non-ASCII case mapping.

* test/ruby/enc/test_case_comprehensive.rb: Tests for above.
* string.c: Add iso-8859-1 to supported encodings.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55373 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

4 files changed, 54 insertions, 3 deletions

diff --git a/ChangeLog b/ChangeLog
index 3034535dbe..c30abd86cc 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,11 @@
+Sat Jun 11 09:46:17 2016  Martin Duerst  <duerst@it.aoyama.ac.jp>
+
+	* enc/iso_8859_1.c: Implement non-ASCII case mapping.
+
+	* test/ruby/enc/test_case_comprehensive.rb: Tests for above.
+
+	* string.c: Add iso-8859-1 to supported encodings.
+
 Sat Jun 11 09:31:28 2016  Nobuyoshi Nakada  <nobu@ruby-lang.org>
 
 	* lib/forwardable.rb (_delegator_method): leave the backtrace
diff --git a/enc/iso_8859_1.c b/enc/iso_8859_1.c
index 10f63cc28e..5f0d3f91ab 100644
--- a/enc/iso_8859_1.c
+++ b/enc/iso_8859_1.c
@@ -254,6 +254,49 @@ is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc ARG_UNUSE
     return FALSE;
 }
 
+#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, lower;
+  OnigUChar *to_start = to;
+  OnigCaseFoldType flags = *flagP;
+
+  while (*pp<end && to<to_end) {
+    code = *(*pp)++;
+    if (code==0xdf) {  /* 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 ((lower=ONIGENC_ISO_8859_1_TO_LOWER_CASE(code)) != code)
+	     && (flags&ONIGENC_CASE_UPCASE)) {
+	flags |= ONIGENC_CASE_MODIFIED;
+	code = lower;
+    }
+    else if ((EncISO_8859_1_CtypeTable[code]&BIT_CTYPE_LOWER)
+	     && (flags&ONIGENC_CASE_UPCASE)) {
+	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);
+}
+#endif   /* ONIG_CASE_MAPPING */
+
 OnigEncodingDefine(iso_8859_1, ISO_8859_1) = {
   onigenc_single_byte_mbc_enc_len,
   "ISO-8859-1",  /* name */
@@ -274,7 +317,7 @@ OnigEncodingDefine(iso_8859_1, ISO_8859_1) = {
   0,
   ONIGENC_FLAG_NONE,
 #ifdef ONIG_CASE_MAPPING
-  onigenc_single_byte_ascii_only_case_map,
+  case_map,
 #endif   /* ONIG_CASE_MAPPING */
 };
 ENC_ALIAS("ISO8859-1", "ISO-8859-1")
diff --git a/string.c b/string.c
index 4567ce2af3..eb02189dd8 100644
--- a/string.c
+++ b/string.c
@@ -6011,7 +6011,7 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
  *  by case mapping operations.
  *
  *  Non-ASCII case mapping/folding is currently supported for UTF-8,
- *  UTF-16BE/LE, and UTF-32BE/LE Strings/Symbols.
+ *  UTF-16BE/LE, UTF-32BE/LE, and ISO-8859-1 Strings/Symbols.
  *  This support will be extended to other encodings.
  *
  *     "hEllO".downcase   #=> "hello"
diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb
index c3d639cb10..6e1f894d79 100644
--- a/test/ruby/enc/test_case_comprehensive.rb
+++ b/test/ruby/enc/test_case_comprehensive.rb
@@ -186,7 +186,6 @@ class TestComprehensiveCaseFold < Test::Unit::TestCase
     %w[UnicodeData CaseFolding SpecialCasing].each { |f| check_file_available f }
   end
 
-  generate_ascii_only_case_mapping_tests 'ISO-8859-1'
   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'
@@ -215,6 +214,7 @@ class TestComprehensiveCaseFold < Test::Unit::TestCase
   generate_ascii_only_case_mapping_tests 'Windows-1254'
   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 'UTF-8'