Skip to content

expr: Fix parsing regex anchors '^' and '$' #7953

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.

Sign up for GitHub

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
RenjiSann merged 2 commits into from
May 23, 2025
Merged

expr: Fix parsing regex anchors '^' and '$' #7953

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f664578
expr: Handle special cases for `^` in regex
frendsick May 23, 2025
2933286
expr: Handle special cases for `$` in regex
frendsick May 23, 2025
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
40 changes: 33 additions & 7 deletions src/uu/expr/src/syntax_tree.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ impl StringOp {
re_string.push('^');

// Handle first character from the input pattern
let mut pattern_chars = right.chars();
let mut pattern_chars = right.chars().peekable();
let first = pattern_chars.next();
match first {
Some('^') => {} // Start of string anchor is already added
Expand All @@ -166,16 +166,42 @@ impl StringOp {
};

// Handle the rest of the input pattern.
// Escaped previous character should not affect the current.
let mut prev = first.unwrap_or_default();
let mut prev_is_escaped = false;
for curr in pattern_chars {
while let Some(curr) = pattern_chars.next() {
match curr {
// Carets are interpreted literally, unless used as character class negation "[^a]"
'^' if prev_is_escaped || !matches!(prev, '\\' | '[') => {
re_string.push_str(r"\^");
'^' => match (prev, prev_is_escaped) {
// Start of a capturing group
('(', true)
// Start of an alternative pattern
| ('|', true)
// Character class negation "[^a]"
| ('[', false)
// Explicitly escaped caret
| ('\\', false) => re_string.push(curr),
_ => re_string.push_str(r"\^"),
},
'$' => {
if let Some('\\') = pattern_chars.peek() {
// The next character was checked to be a backslash
let backslash = pattern_chars.next().unwrap_or_default();
match pattern_chars.peek() {
// End of a capturing group
Some(')') => re_string.push('$'),
// End of an alternative pattern
Some('|') => re_string.push('$'),
_ => re_string.push_str(r"\$"),
}
re_string.push(backslash);
} else if (prev_is_escaped || prev != '\\')
&& pattern_chars.peek().is_some()
{
re_string.push_str(r"\$");
} else {
re_string.push('$');
}
}
char => re_string.push(char),
_ => re_string.push(curr),
}

prev_is_escaped = prev == '\\' && !prev_is_escaped;
Expand Down
21 changes: 20 additions & 1 deletion tests/by-util/test_expr.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,10 +282,26 @@ fn test_regex() {
.args(&["a^b", ":", "a\\^b"])
.succeeds()
.stdout_only("3\n");
new_ucmd!()
.args(&["b", ":", "a\\|^b"])
.succeeds()
.stdout_only("1\n");
new_ucmd!()
.args(&["ab", ":", "\\(^a\\)b"])
.succeeds()
.stdout_only("a\n");
new_ucmd!()
.args(&["a$b", ":", "a\\$b"])
.succeeds()
.stdout_only("3\n");
new_ucmd!()
.args(&["a", ":", "a$\\|b"])
.succeeds()
.stdout_only("1\n");
new_ucmd!()
.args(&["ab", ":", "a\\(b$\\)"])
.succeeds()
.stdout_only("b\n");
new_ucmd!()
.args(&["abc", ":", "^abc"])
.succeeds()
Expand All @@ -298,6 +314,10 @@ fn test_regex() {
.args(&["b^$ic", ":", "b^\\$ic"])
.succeeds()
.stdout_only("5\n");
new_ucmd!()
.args(&["a$c", ":", "a$\\c"])
.succeeds()
.stdout_only("3\n");
new_ucmd!()
.args(&["^^^^^^^^^", ":", "^^^"])
.succeeds()
Expand Down Expand Up @@ -766,7 +786,6 @@ mod gnu_expr {
.stdout_only("3\n");
}

#[ignore]
#[test]
fn test_bre11() {
new_ucmd!()
Expand Down
Loading