summaryrefslogtreecommitdiff
path: root/parse.y
diff options
context:
space:
mode:
authorJeremy Evans <code@jeremyevans.net>2021-05-12 12:37:55 -0700
committerJeremy Evans <code@jeremyevans.net>2021-05-12 18:55:43 -0700
commit11ae581a4a7f5d5f5ec6378872eab8f25381b1b9 (patch)
treef250c8418f155fb0ee7f578085e2354bdbb7036a /parse.y
parent9484f9ebdf675f71811a5583c1af2415b26c932f (diff)
Fix handling of control/meta escapes in literal regexps
Ruby uses a recursive algorithm for handling control/meta escapes in strings (read_escape). However, the equivalent code for regexps (tokadd_escape) in did not use a recursive algorithm. Due to this, Handling of control/meta escapes in regexp did not have the same behavior as in strings, leading to behavior such as the following returning nil: ```ruby /\c\xFF/ =~ "\c\xFF" ``` Switch the code for handling \c, \C and \M in literal regexps to use the same code as for strings (read_escape), to keep behavior consistent between the two. Fixes [Bug #14367]
Notes
Notes: Merged: https://github.com/ruby/ruby/pull/4495
Diffstat (limited to 'parse.y')
-rw-r--r--parse.y50
1 files changed, 17 insertions, 33 deletions
diff --git a/parse.y b/parse.y
index fc1fbd7fd92..66813e5ecb7 100644
--- a/parse.y
+++ b/parse.y
@@ -6902,10 +6902,8 @@ static int
tokadd_escape(struct parser_params *p, rb_encoding **encp)
{
int c;
- int flags = 0;
size_t numlen;
- first:
switch (c = nextc(p)) {
case '\n':
return 0; /* just ignore */
@@ -6928,37 +6926,6 @@ tokadd_escape(struct parser_params *p, rb_encoding **encp)
}
return 0;
- case 'M':
- if (flags & ESCAPE_META) goto eof;
- if ((c = nextc(p)) != '-') {
- pushback(p, c);
- goto eof;
- }
- tokcopy(p, 3);
- flags |= ESCAPE_META;
- goto escaped;
-
- case 'C':
- if (flags & ESCAPE_CONTROL) goto eof;
- if ((c = nextc(p)) != '-') {
- pushback(p, c);
- goto eof;
- }
- tokcopy(p, 3);
- goto escaped;
-
- case 'c':
- if (flags & ESCAPE_CONTROL) goto eof;
- tokcopy(p, 2);
- flags |= ESCAPE_CONTROL;
- escaped:
- if ((c = nextc(p)) == '\\') {
- goto first;
- }
- else if (c == -1) goto eof;
- tokadd(p, c);
- return 0;
-
eof:
case -1:
yyerror0("Invalid escape character syntax");
@@ -7151,6 +7118,23 @@ tokadd_string(struct parser_params *p,
goto non_ascii;
}
if (func & STR_FUNC_REGEXP) {
+ switch (c) {
+ case 'c':
+ case 'C':
+ case 'M': {
+ pushback(p, c);
+ c = read_escape(p, 0, enc);
+
+ int i;
+ char escbuf[5];
+ snprintf(escbuf, sizeof(escbuf), "\\x%02X", c);
+ for(i = 0; i < 4; i++) {
+ tokadd(p, escbuf[i]);
+ }
+ continue;
+ }
+ }
+
if (c == term && !simple_re_meta(c)) {
tokadd(p, c);
continue;