Skip to content

regex: Fix parsing of character classes #18282

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 29, 2014
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 27 additions & 24 deletions src/libregex/parse.rs
Original file line number Diff line number Diff line change
Expand Up @@ -374,16 +374,12 @@ impl<'a> Parser<'a> {
let mut ranges: Vec<(char, char)> = vec!();
let mut alts: Vec<Ast> = vec!();

if self.peek_is(1, ']') {
try!(self.expect(']'))
ranges.push((']', ']'))
}
while self.peek_is(1, '-') {
try!(self.expect('-'))
try!(self.expect('-'));
ranges.push(('-', '-'))
}
loop {
try!(self.noteof("a closing ']' or a non-empty character class)"))
try!(self.noteof("a closing ']' or a non-empty character class)"));
let mut c = self.cur();
match c {
'[' =>
Expand Down Expand Up @@ -411,10 +407,7 @@ impl<'a> Parser<'a> {
ast => fail!("Unexpected AST item '{}'", ast),
}
}
_ => {},
}
match c {
']' => {
']' if ranges.len() > 0 || alts.len() > 0 => {
if ranges.len() > 0 {
let flags = negated | (self.flags & FLAG_NOCASE);
let mut ast = AstClass(combine_ranges(ranges), flags);
Expand All @@ -431,22 +424,32 @@ impl<'a> Parser<'a> {
}
return Ok(())
}
c => {
if self.peek_is(1, '-') && !self.peek_is(2, ']') {
try!(self.expect('-'))
try!(self.noteof("not a ']'"))
let c2 = self.cur();
if c2 < c {
return self.err(format!("Invalid character class \
range '{}-{}'",
c,
c2).as_slice())
}
ranges.push((c, self.cur()))
} else {
ranges.push((c, c))
_ => {}
}

if self.peek_is(1, '-') && !self.peek_is(2, ']') {
try!(self.expect('-'));
// The regex can't end here.
try!(self.noteof("not a ']'"));
// End the range with a single character or character escape.
let mut c2 = self.cur();
if c2 == '\\' {
match try!(self.parse_escape()) {
Literal(c3, _) => c2 = c3, // allow literal escapes below
ast =>
return self.err(format!("Expected a literal, but got {}.",
ast).as_slice()),
}
}
if c2 < c {
return self.err(format!("Invalid character class \
range '{}-{}'",
c,
c2).as_slice())
}
ranges.push((c, self.cur()))
} else {
ranges.push((c, c))
}
}
}
Expand Down
28 changes: 28 additions & 0 deletions src/libregex/test/tests.rs
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,30 @@ fn empty_regex_nonempty_match() {
assert_eq!(ms, vec![(0, 0), (1, 1), (2, 2), (3, 3)]);
}

#[test]
fn quoted_bracket_set() {
let re = regex!(r"([\x{5b}\x{5d}])");
let ms = re.find_iter("[]").collect::<Vec<(uint, uint)>>();
assert_eq!(ms, vec![(0, 1), (1, 2)]);
let re = regex!(r"([\[\]])");
let ms = re.find_iter("[]").collect::<Vec<(uint, uint)>>();
assert_eq!(ms, vec![(0, 1), (1, 2)]);
}

#[test]
fn first_range_starts_with_left_bracket() {
let re = regex!(r"([[-z])");
let ms = re.find_iter("[]").collect::<Vec<(uint, uint)>>();
assert_eq!(ms, vec![(0, 1), (1, 2)]);
}

#[test]
fn range_ends_with_escape() {
let re = regex!(r"([\[-\x{5d}])");
let ms = re.find_iter("[]").collect::<Vec<(uint, uint)>>();
assert_eq!(ms, vec![(0, 1), (1, 2)]);
}

macro_rules! replace(
($name:ident, $which:ident, $re:expr,
$search:expr, $replace:expr, $result:expr) => (
Expand Down Expand Up @@ -114,6 +138,10 @@ noparse!(fail_double_neg, "(?-i-i)")
noparse!(fail_neg_empty, "(?i-)")
noparse!(fail_empty_group, "()")
noparse!(fail_dupe_named, "(?P<a>.)(?P<a>.)")
noparse!(fail_range_end_no_class, "[a-[:lower:]]")
noparse!(fail_range_end_no_begin, r"[a-\A]")
noparse!(fail_range_end_no_end, r"[a-\z]")
noparse!(fail_range_end_no_boundary, r"[a-\b]")

macro_rules! mat(
($name:ident, $re:expr, $text:expr, $($loc:tt)+) => (
Expand Down