From 1495c2f8e9ddaae20665926506705c69231e5b38 Mon Sep 17 00:00:00 2001
From: nobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Thu, 18 Sep 2014 14:51:08 +0000
Subject: [PATCH] string.c: UTF-8 string function

* string.c (rb_utf8_str_new, rb_utf8_str_new_cstr): make UTF-8
  string.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@47625 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 include/ruby/intern.h |  8 ++++++++
 string.c              | 17 +++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/include/ruby/intern.h b/include/ruby/intern.h
index f9858537e1..1517023610 100644
--- a/include/ruby/intern.h
+++ b/include/ruby/intern.h
@@ -707,6 +707,8 @@ VALUE rb_str_buf_new2(const char*);
 VALUE rb_str_tmp_new(long);
 VALUE rb_usascii_str_new(const char*, long);
 VALUE rb_usascii_str_new_cstr(const char*);
+VALUE rb_utf8_str_new(const char*, long);
+VALUE rb_utf8_str_new_cstr(const char*);
 void rb_str_free(VALUE);
 void rb_str_shared_replace(VALUE, VALUE);
 VALUE rb_str_buf_append(VALUE, VALUE);
@@ -787,6 +789,12 @@ VALUE rb_str_scrub(VALUE, VALUE);
 	rb_usascii_str_new((str), (long)strlen(str)) : \
 	rb_usascii_str_new_cstr(str);	       \
 })
+#define rb_utf8_str_new_cstr(str) __extension__ ( \
+{						\
+    (__builtin_constant_p(str)) ?		\
+	rb_utf8_str_new((str), (long)strlen(str)) : \
+	rb_utf8_str_new_cstr(str);		\
+})
 #define rb_external_str_new_cstr(str) __extension__ ( \
 {						\
     (__builtin_constant_p(str)) ?		\
diff --git a/string.c b/string.c
index 05e4e802cd..9c562ff78d 100644
--- a/string.c
+++ b/string.c
@@ -34,6 +34,7 @@
 #undef rb_str_new_cstr
 #undef rb_tainted_str_new_cstr
 #undef rb_usascii_str_new_cstr
+#undef rb_utf8_str_new_cstr
 #undef rb_enc_str_new_cstr
 #undef rb_external_str_new_cstr
 #undef rb_locale_str_new_cstr
@@ -588,6 +589,14 @@ rb_usascii_str_new(const char *ptr, long len)
     return str;
 }
 
+VALUE
+rb_utf8_str_new(const char *ptr, long len)
+{
+    VALUE str = str_new(rb_cString, ptr, len);
+    rb_enc_associate_index(str, rb_utf8_encindex());
+    return str;
+}
+
 VALUE
 rb_enc_str_new(const char *ptr, long len, rb_encoding *enc)
 {
@@ -615,6 +624,14 @@ rb_usascii_str_new_cstr(const char *ptr)
     return str;
 }
 
+VALUE
+rb_utf8_str_new_cstr(const char *ptr)
+{
+    VALUE str = rb_str_new_cstr(ptr);
+    rb_enc_associate_index(str, rb_utf8_encindex());
+    return str;
+}
+
 VALUE
 rb_enc_str_new_cstr(const char *ptr, rb_encoding *enc)
 {