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: fixed escaped multibyte char

Browse source 
* re.c (unescape_nonascii): escaped multibyte character should be
  copied as-is, just with checking if the encoding matches.
  https://twitter.com/sakuro/status/972014409986883584

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62718 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2018-03-11 00:05:12 +00:00
parent 724878c913
commit 5fade63482
2 changed files with 14 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
re.c
View file

@ -2537,11 +2537,13 @@ unescape_nonascii(const char *p, const char *end, rb_encoding *enc,
while (p < end) { while (p < end) {
int chlen = rb_enc_precise_mbclen(p, end, enc); int chlen = rb_enc_precise_mbclen(p, end, enc);
if (!MBCLEN_CHARFOUND_P(chlen)) { if (!MBCLEN_CHARFOUND_P(chlen)) {
invalid_multibyte:
errcpy(err, "invalid multibyte character"); errcpy(err, "invalid multibyte character");
return -1; return -1;
} }
chlen = MBCLEN_CHARFOUND_LEN(chlen); chlen = MBCLEN_CHARFOUND_LEN(chlen);
if (1 < chlen || (*p & 0x80)) { if (1 < chlen || (*p & 0x80)) {
multibyte:
rb_str_buf_cat(buf, p, chlen); rb_str_buf_cat(buf, p, chlen);
p += chlen; p += chlen;
if (*encp == 0) if (*encp == 0)
@ -2559,6 +2561,16 @@ unescape_nonascii(const char *p, const char *end, rb_encoding *enc,
errcpy(err, "too short escape sequence"); errcpy(err, "too short escape sequence");
return -1; return -1;
} }
chlen = rb_enc_precise_mbclen(p, end, enc);
if (!MBCLEN_CHARFOUND_P(chlen)) {
goto invalid_multibyte;
}
if ((chlen = MBCLEN_CHARFOUND_LEN(chlen)) > 1) {
/* include the previous backslash */
--p;
++chlen;
goto multibyte;
}
switch (c = *p++) { switch (c = *p++) {
case '1': case '2': case '3': case '1': case '2': case '3':
case '4': case '5': case '6': case '7': /* \O, \OO, \OOO or backref */ case '4': case '5': case '6': case '7': /* \O, \OO, \OOO or backref */

2
test/ruby/test_regexp.rb
View file

@ -515,6 +515,8 @@ class TestRegexp < Test::Unit::TestCase
s = ".........." s = ".........."
5.times { s.sub!(".", "") } 5.times { s.sub!(".", "") }
assert_equal(".....", s) assert_equal(".....", s)
assert_equal("\\\u{3042}", Regexp.new("\\\u{3042}").source)
end end
def test_equal def test_equal