* include/ruby/intern.h (rb_uv_to_utf8): declared.

* re.c (rb_reg_preprocess): new function for dynamic regexp with
  \u{} such as Regexp.new("\\u{6666}").
  (rb_reg_prepare_re): preprocess regexp for recompiling.
  (read_escaped_byte): new function.
  (unescape_escaped_nonascii): new function.
  (append_utf8): new function.
  (unescape_unicode_list): new function.
  (unescape_unicode_bmp): new function.
  (unescape_nonascii): new function.
  (rb_reg_initialize): preprocess regexp.

* pack.c (rb_uv_to_utf8): renamed from uv_to_utf8.

* parse.y (STR_NEW3): take func instead of has8 and hasmb.
  (parser_str_new): use default coderange mechanism except for regexp.
  (parser_tokadd_utf8): copy regexp source as-is.
  (parser_read_escape): UTF-8 stuff removed.
  (parser_tokadd_escape): has8bit and hasmb removed.
  (parser_tokadd_string): fix 8-bit single byte character with \u.
  (parser_parse_string): has8bit and hasmb removed.
  (parser_here_document): has8bit and hasmb removed.
  (parser_yylex): call parser_tokadd_utf8 instead of read_escape for
  UTF-8 character.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14072 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 3 insertions, 4 deletions

diff --git a/pack.c b/pack.c
index 4cab476bd2..b1d7268850 100644
--- a/pack.c
+++ b/pack.c
@@ -365,7 +365,6 @@ static const char toofew[] = "too few arguments";
 static void encodes(VALUE,const char*,long,int);
 static void qpencode(VALUE,VALUE,long);
 
-static int uv_to_utf8(char*,unsigned long);
 static unsigned long utf8_to_uv(const char*,long*);
 
 /*
@@ -872,7 +871,7 @@ pack_pack(VALUE ary, VALUE fmt)
 		if (l < 0) {
 		    rb_raise(rb_eRangeError, "pack(U): value out of range");
 		}
-		le = uv_to_utf8(buf, l);
+		le = rb_uv_to_utf8(buf, l);
 		rb_str_buf_cat(res, (char*)buf, le);
 	    }
 	    break;
@@ -1991,8 +1990,8 @@ pack_unpack(VALUE str, VALUE fmt)
 
 #define BYTEWIDTH 8
 
-static int
-uv_to_utf8(char *buf, unsigned long uv)
+int
+rb_uv_to_utf8(char buf[6], unsigned long uv)
 {
     if (uv <= 0x7f) {
 	buf[0] = (char)uv;