chris/ruwuma
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

push: Fix regex for word boundaries

Browse Source
This commit is contained in:
Kévin Commaille 2022-06-24 14:42:53 +02:00 committed by Kévin Commaille
parent 1e220a05bf
commit 506a7bdf2e
1 changed files with 25 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
crates/ruma-common/src/push/condition.rs
View File

@ -13,13 +13,6 @@ mod room_member_count_is;
pub use room_member_count_is::{ComparisonOperator, RoomMemberCountIs}; pub use room_member_count_is::{ComparisonOperator, RoomMemberCountIs};
/// The characters that are defined as a word boundary in the [Matrix spec].
///
/// Any character not in the sets `[A-Z]`, `[a-z]`, `[0-9]` or `_`.
///
/// [Matrix spec]: https://spec.matrix.org/v1.3/client-server-api/#conditions-1
const WORD_BOUNDARY_CHARACTERS: &str = "[^A-Za-z0-9_]";
/// A condition that must apply for an associated push rule's action to be taken. /// A condition that must apply for an associated push rule's action to be taken.
#[derive(Clone, Debug, Deserialize, Serialize)] #[derive(Clone, Debug, Deserialize, Serialize)]
#[cfg_attr(not(feature = "unstable-exhaustive-types"), non_exhaustive)] #[cfg_attr(not(feature = "unstable-exhaustive-types"), non_exhaustive)]
@ -279,10 +272,9 @@ impl StrExt for str {
chunks.push(chunk.wildcards_to_regex()); chunks.push(chunk.wildcards_to_regex());
} }
let regex = format!( // The word characters in ASCII compatible mode (with the `-u` flag) match the
"(?:^|{WORD_BOUNDARY_CHARACTERS}){}(?:{WORD_BOUNDARY_CHARACTERS}|$)", // definition in the spec: any character not in the set `[A-Za-z0-9_]`.
chunks.concat() let regex = format!(r"(?-u:^|\W|\b){}(?-u:\b|\W|$)", chunks.concat());
);
Regex::new(&regex).ok().filter(|re| re.is_match(self)).is_some() Regex::new(&regex).ok().filter(|re| re.is_match(self)).is_some()
} else { } else {
match self.find(pattern) { match self.find(pattern) {
@ -530,13 +522,33 @@ mod tests {
#[test] #[test]
fn patterns_match() { fn patterns_match() {
// Word matching // Word matching without glob
assert!("foo bar".matches_pattern("foo", true)); assert!("foo bar".matches_pattern("foo", true));
assert!("Foo bar".matches_pattern("foo", true)); assert!("Foo bar".matches_pattern("foo", true));
assert!(!"foobar".matches_pattern("foo", true)); assert!(!"foobar".matches_pattern("foo", true));
assert!("foo bar".matches_pattern("foo*", true));
assert!("".matches_pattern("", true)); assert!("".matches_pattern("", true));
assert!(!"foo".matches_pattern("", true)); assert!(!"foo".matches_pattern("", true));
assert!("foo bar".matches_pattern("foo bar", true));
assert!(" foo bar ".matches_pattern("foo bar", true));
assert!("baz foo bar baz".matches_pattern("foo bar", true));
assert!("foo baré".matches_pattern("foo bar", true));
assert!(!"bar foo".matches_pattern("foo bar", true));
assert!("foo bar".matches_pattern("foo ", true));
assert!("foo ".matches_pattern("foo ", true));
assert!("foo ".matches_pattern("foo ", true));
assert!(" foo ".matches_pattern("foo ", true));
// Word matching with glob
assert!("foo bar".matches_pattern("foo*", true));
assert!("foo bar".matches_pattern("foo b?r", true));
assert!(" foo bar ".matches_pattern("foo b?r", true));
assert!("baz foo bar baz".matches_pattern("foo b?r", true));
assert!("foo baré".matches_pattern("foo b?r", true));
assert!(!"bar foo".matches_pattern("foo b?r", true));
assert!("foo bar".matches_pattern("f*o ", true));
assert!("foo ".matches_pattern("f*o ", true));
assert!("foo ".matches_pattern("f*o ", true));
assert!(" foo ".matches_pattern("f*o ", true));
// Glob matching // Glob matching
assert!(!"foo bar".matches_pattern("foo", false)); assert!(!"foo bar".matches_pattern("foo", false));