kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

* re.c (unescape_nonascii): add has_property argument not to

Browse source 
raise error by /\p{Hiragana}\u{3042}/ in EUC-JP script.
  (rb_reg_preprocess): use has_property argument to make regexp
  encoding fixed.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@17884 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
akr 2008-07-04 23:50:33 +00:00
parent 3d0bd1c626
commit 1a32af4e7a
3 changed files with 24 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
ChangeLog
View file

@ -1,3 +1,10 @@
Sat Jul 5 08:48:05 2008 Tanaka Akira <akr@fsij.org>
* re.c (unescape_nonascii): add has_property argument not to
raise error by /\p{Hiragana}\u{3042}/ in EUC-JP script.
(rb_reg_preprocess): use has_property argument to make regexp
encoding fixed.
Sat Jul 5 08:29:47 2008 Tanaka Akira <akr@fsij.org> Sat Jul 5 08:29:47 2008 Tanaka Akira <akr@fsij.org>
* re.c (unescape_nonascii): make regexp fixed_encoding if \p is used. * re.c (unescape_nonascii): make regexp fixed_encoding if \p is used.

12
re.c
View file

@ -2085,7 +2085,8 @@ unescape_unicode_bmp(const char **pp, const char *end,
static int static int
unescape_nonascii(const char *p, const char *end, rb_encoding *enc, unescape_nonascii(const char *p, const char *end, rb_encoding *enc,
VALUE buf, rb_encoding **encp, onig_errmsg_buffer err) VALUE buf, rb_encoding **encp, int *has_property,
onig_errmsg_buffer err)
{ {
char c; char c;
char smallbuf[2]; char smallbuf[2];
@ -2165,7 +2166,7 @@ unescape_nonascii(const char *p, const char *end, rb_encoding *enc,
case 'p': /* \p{Hiragana} */ case 'p': /* \p{Hiragana} */
if (!*encp) { if (!*encp) {
*encp = enc; *has_property = 1;
} }
goto escape_asis; goto escape_asis;
@ -2192,6 +2193,7 @@ rb_reg_preprocess(const char *p, const char *end, rb_encoding *enc,
rb_encoding **fixed_enc, onig_errmsg_buffer err) rb_encoding **fixed_enc, onig_errmsg_buffer err)
{ {
VALUE buf; VALUE buf;
int has_property = 0;
buf = rb_str_buf_new(0); buf = rb_str_buf_new(0);
@ -2202,9 +2204,13 @@ rb_reg_preprocess(const char *p, const char *end, rb_encoding *enc,
rb_enc_associate(buf, enc); rb_enc_associate(buf, enc);
} }
if (unescape_nonascii(p, end, enc, buf, fixed_enc, err) != 0) if (unescape_nonascii(p, end, enc, buf, fixed_enc, &has_property, err) != 0)
return Qnil; return Qnil;
if (has_property && !*fixed_enc) {
*fixed_enc = enc;
}
if (*fixed_enc) { if (*fixed_enc) {
rb_enc_associate(buf, *fixed_enc); rb_enc_associate(buf, *fixed_enc);
} }

8
test/ruby/test_m17n.rb
View file

@ -510,6 +510,14 @@ class TestM17N < Test::Unit::TestCase
r = /\p{Hiragana}/e r = /\p{Hiragana}/e
assert(r.fixed_encoding?) assert(r.fixed_encoding?)
assert_match(r, "\xa4\xa2".force_encoding("euc-jp")) assert_match(r, "\xa4\xa2".force_encoding("euc-jp"))
r = eval('/\u{3042}\p{Hiragana}/'.force_encoding("euc-jp"))
assert(r.fixed_encoding?)
assert_equal(Encoding::UTF_8, r.encoding)
r = eval('/\p{Hiragana}\u{3042}/'.force_encoding("euc-jp"))
assert(r.fixed_encoding?)
assert_equal(Encoding::UTF_8, r.encoding)
end end
def test_regexp_embed_preprocess def test_regexp_embed_preprocess