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

parse.y: check multibyte char

Browse source 
* parse.y (parser_precise_mbclen): check invalid multibyte char at
  skipping strings following `?x` literal string, not to stuck in
  a infinite loop.  [ruby-core:81746] [Bug #13672]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@59161 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2017-06-23 11:20:29 +00:00
parent f61e8084bb
commit d391697331
2 changed files with 17 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
parse.y
View file

@ -4947,7 +4947,6 @@ ripper_dispatch_delayed_token(struct parser_params *parser, int t)
#define parser_encoding_name() (current_enc->name)
#define parser_mbclen() mbclen((lex_p-1),lex_pend,current_enc)
#define parser_precise_mbclen() rb_enc_precise_mbclen((lex_p-1),lex_pend,current_enc)
#define is_identchar(p,e,enc) (rb_enc_isalnum((unsigned char)(*(p)),(enc)) || (*(p)) == '_' || !ISASCII(*(p)))
#define parser_is_identchar() (!parser->eofp && is_identchar((lex_p-1),lex_pend,current_enc))
@ -5018,6 +5017,17 @@ token_info_pop_gen(struct parser_params *parser, const char *token, size_t len)
xfree(ptinfo);
}
static int
parser_precise_mbclen(struct parser_params *parser, const char *p)
{
int len = rb_enc_precise_mbclen(p, lex_pend, current_enc);
if (!MBCLEN_CHARFOUND_P(len)) {
compile_error(PARSER_ARG "invalid multibyte char (%s)", parser_encoding_name());
return -1;
}
return len;
}
static int
parser_yyerror(struct parser_params *parser, const char *msg)
{
@ -5930,11 +5940,8 @@ dispose_string(VALUE str)
static int
parser_tokadd_mbchar(struct parser_params *parser, int c)
{
int len = parser_precise_mbclen();
if (!MBCLEN_CHARFOUND_P(len)) {
compile_error(PARSER_ARG "invalid multibyte char (%s)", parser_encoding_name());
return -1;
}
int len = parser_precise_mbclen(parser, lex_p-1);
if (len < 0) return -1;
tokadd(c);
lex_p += --len;
if (len > 0) tokcopy(len);
@ -7426,7 +7433,8 @@ parse_qmark(struct parser_params *parser, int space_seen)
if (space_seen) {
const char *start = lex_p - 1, *p = start;
do {
int n = rb_enc_precise_mbclen(p, lex_pend, current_enc);
int n = parser_precise_mbclen(parser, p);
if (n < 0) return -1;
p += n;
} while (p < lex_pend && is_identchar(p, lex_pend, current_enc));
rb_warn2("`?' just followed by `%.*s' is interpreted as" \

2
test/ruby/test_parse.rb
View file

@ -512,6 +512,8 @@ class TestParse < Test::Unit::TestCase
assert_raise(SyntaxError) { eval("?\v") }
assert_raise(SyntaxError) { eval("?\r") }
assert_raise(SyntaxError) { eval("?\f") }
assert_raise(SyntaxError) { eval("?\f") }
assert_raise(SyntaxError) { eval(" ?a\x8a".force_encoding("utf-8")) }
assert_equal("\u{1234}", eval("?\u{1234}"))
assert_equal("\u{1234}", eval('?\u{1234}'))
end