merge revision(s) 65954,65955,65958: [Backport #15337]

	Don't use single byte optimization on grapheme clusters

	Unicode Text Segmentation considers CRLF as a character. [Bug #15337]

	add tests using Unicode test data for grapheme clusters

	Add file test/ruby/enc/test_grapheme_breaks.rb to test String#each_grapheme_cluster
	and \X extended grapheme cluster matcher in regular expressions against test data
	provided by Unicode (ucd/auxiliary/GraphemeBreakTest.txt).

	Some lines in the data file are ignored, as follows:
	- Lines with a surrogate, because Ruby doesn't handle these
	- The case of "\r\n", because there is a bug (#15337) in the implementation

	remove guard against bug #15337, because it is fixed

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_2_5@66073 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 2 insertions, 2 deletions

diff --git a/string.c b/string.c
index 80749c22a0..56db697e3c 100644
--- a/string.c
+++ b/string.c
@@ -8342,7 +8342,7 @@ rb_str_each_grapheme_cluster_size(VALUE str, VALUE args, VALUE eobj)
     rb_encoding *enc = rb_enc_from_index(ENCODING_GET(str));
     const char *ptr, *end;
 
-    if (!rb_enc_unicode_p(enc) || single_byte_optimizable(str)) {
+    if (!rb_enc_unicode_p(enc)) {
 	return rb_str_length(str);
     }
 
@@ -8370,7 +8370,7 @@ rb_str_enumerate_grapheme_clusters(VALUE str, VALUE ary)
     rb_encoding *enc = rb_enc_from_index(ENCODING_GET(str));
     const char *ptr, *end;
 
-    if (!rb_enc_unicode_p(enc) || single_byte_optimizable(str)) {
+    if (!rb_enc_unicode_p(enc)) {
 	return rb_str_enumerate_chars(str, ary);
     }