* string.c: Added UTF-16BE/LE and UTF-32BE/LE to supported encodings

for Unicode case mapping.
* test/ruby/enc/test_case_comprehensive.rb: Tests for above
  functionality; fixed an encoding issue in assertion error message.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55296 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

ChangeLog

@@ -1,3 +1,11 @@
+Mon Jun  6 18:36:34 2016  Martin Duerst  <duerst@it.aoyama.ac.jp>
+
+	* string.c: Added UTF-16BE/LE and UTF-32BE/LE to supported encodings
+	  for Unicode case mapping.
+
+	* test/ruby/enc/test_case_comprehensive.rb: Tests for above
+	  functionality; fixed an encoding issue in assertion error message.
+
 Mon Jun  6 17:29:35 2016  Martin Duerst  <duerst@it.aoyama.ac.jp>
 
 	* test/ruby/enc/test_case_comprehensive.rb: Speed up testing for small

string.c

@@ -5858,7 +5858,7 @@ rb_str_upcase_bang(int argc, VALUE *argv, VALUE str)
     enc = STR_ENC_GET(str);
     rb_str_check_dummy_enc(enc);
     s = RSTRING_PTR(str); send = RSTRING_END(str);
-    if (enc==rb_utf8_encoding()) {
+    if (rb_enc_unicode_p(enc)) {
 	str_shared_replace(str, rb_str_casemap(str, &flags, enc));
 	modify = ONIGENC_CASE_MODIFIED & flags;
     }
@@ -5948,7 +5948,7 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
     enc = STR_ENC_GET(str);
     rb_str_check_dummy_enc(enc);
     s = RSTRING_PTR(str); send = RSTRING_END(str);
-    if (enc==rb_utf8_encoding()) {
+    if (rb_enc_unicode_p(enc)) {
 	str_shared_replace(str, rb_str_casemap(str, &flags, enc));
 	modify = ONIGENC_CASE_MODIFIED & flags;
     }
@@ -6037,8 +6037,9 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
  *  normalization (i.e. String#unicode_normalize) is not necessarily maintained
  *  by case mapping operations.
  *
- *  Non-ASCII case mapping/folding is currently only supported for UTF-8
- *  Strings/Symbols, but this support will be extended to other encodings.
+ *  Non-ASCII case mapping/folding is currently supported for UTF-8,
+ *  UTF-16BE/LE, and UTF-32BE/LE Strings/Symbols.
+ *  This support will be extended to other encodings.
  *
  *     "hEllO".downcase   #=> "hello"
  */
@@ -6083,7 +6084,7 @@ rb_str_capitalize_bang(int argc, VALUE *argv, VALUE str)
     enc = STR_ENC_GET(str);
     rb_str_check_dummy_enc(enc);
     if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
-    if (enc==rb_utf8_encoding()) {
+    if (rb_enc_unicode_p(enc)) {
 	str_shared_replace(str, rb_str_casemap(str, &flags, enc));
 	modify = ONIGENC_CASE_MODIFIED & flags;
     }
@@ -6159,7 +6160,7 @@ rb_str_swapcase_bang(int argc, VALUE *argv, VALUE str)
     enc = STR_ENC_GET(str);
     rb_str_check_dummy_enc(enc);
     s = RSTRING_PTR(str); send = RSTRING_END(str);
-    if (enc==rb_utf8_encoding()) {
+    if (rb_enc_unicode_p(enc)) {
 	str_shared_replace(str, rb_str_casemap(str, &flags, enc));
 	modify = ONIGENC_CASE_MODIFIED & flags;
     }

test/ruby/enc/test_case_comprehensive.rb

@@ -119,7 +119,7 @@ class TestComprehensiveCaseFold < Test::Unit::TestCase
             target = test.first_data[code].encode(encoding) + test.follow_data[code].encode(encoding) * 4
             result = source.send(test.method_name, *test.attributes)
             assert_equal target, result,
-              "from #{source} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
+              "from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
           rescue Encoding::UndefinedConversionError
           end
         end
@@ -139,4 +139,8 @@ class TestComprehensiveCaseFold < Test::Unit::TestCase
   generate_casefold_tests 'US-ASCII'
   generate_casefold_tests 'ASCII-8BIT'
   generate_casefold_tests 'UTF-8'
+  generate_casefold_tests 'UTF-16BE'
+  generate_casefold_tests 'UTF-16LE'
+  generate_casefold_tests 'UTF-32BE'
+  generate_casefold_tests 'UTF-32LE'
 end