* include/ruby/encoding.h (rb_enc_str_asciionly_p): declared.

  (rb_enc_str_asciicompat_p): defined.

* re.c (rb_reg_initialize_str): use rb_enc_str_asciionly_p.
  (rb_reg_quote): return ascii-8bit string if the argument is
  ascii-only to generate encoding generic regexp if possible.
  (rb_reg_s_union): fix encoding handling.  [ruby-dev:32094]

* string.c (rb_enc_str_asciionly_p): defined.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14013 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 17 insertions, 0 deletions

diff --git a/string.c b/string.c
index 286c56a93a..20ce81963c 100644
--- a/string.c
+++ b/string.c
@@ -129,6 +129,23 @@ rb_enc_str_coderange(VALUE str)
     return cr;
 }
 
+int rb_enc_str_asciionly_p(VALUE str)
+{
+    rb_encoding *enc = rb_enc_get(str);
+
+    if (rb_enc_asciicompat(enc) &&
+        rb_enc_str_coderange(str) == ENC_CODERANGE_SINGLE) {
+        char *ptr = RSTRING_PTR(str);
+        long len = RSTRING_LEN(str);
+        long i;
+        for (i = 0; i < len; i++)
+            if (ptr[i] & 0x80)
+                return Qfalse;
+        return Qtrue;
+    }
+    return Qfalse;
+}
+
 static inline void
 str_mod_check(VALUE s, char *p, long len)
 {