Skip to content

expr: Escape anchor characters within pattern #7842

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
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
28 changes: 26 additions & 2 deletions src/uu/expr/src/syntax_tree.rs
Original file line number Diff line number Diff line change
Expand Up @@ -150,8 +150,32 @@ impl StringOp {
let left = left?.eval_as_string();
let right = right?.eval_as_string();
check_posix_regex_errors(&right)?;
let prefix = if right.starts_with('*') { r"^\" } else { "^" };
let re_string = format!("{prefix}{right}");

// All patterns are anchored so they begin with a caret (^)
let mut re_string = String::with_capacity(right.len() + 1);
re_string.push('^');

// Handle first character from the input pattern
let mut pattern_chars = right.chars();
let first = pattern_chars.next();
match first {
Some('^') => {} // Start of string anchor is already added
Some('*') => re_string.push_str(r"\*"),
Some(char) => re_string.push(char),
None => return Ok(0.into()),
};

// Handle the rest of the input pattern.
// Escape characters that should be handled literally within the pattern.
let mut prev = first.unwrap_or_default();
for curr in pattern_chars {
match curr {
'^' if prev != '\\' => re_string.push_str(r"\^"),
char => re_string.push(char),
}
prev = curr;
}

let re = Regex::with_options(
&re_string,
RegexOptions::REGEX_OPTION_NONE,
Expand Down
35 changes: 29 additions & 6 deletions tests/by-util/test_expr.rs
Original file line number Diff line number Diff line change
Expand Up @@ -274,11 +274,10 @@ fn test_length_mb() {

#[test]
fn test_regex() {
// FixME: [2022-12-19; rivy] test disabled as it currently fails due to 'oniguruma' bug (see GH:kkos/oniguruma/issues/279)
// new_ucmd!()
// .args(&["a^b", ":", "a^b"])
// .succeeds()
// .stdout_only("3\n");
new_ucmd!()
.args(&["a^b", ":", "a^b"])
.succeeds()
.stdout_only("3\n");
new_ucmd!()
.args(&["a^b", ":", "a\\^b"])
.succeeds()
Expand All @@ -287,14 +286,39 @@ fn test_regex() {
.args(&["a$b", ":", "a\\$b"])
.succeeds()
.stdout_only("3\n");
new_ucmd!()
.args(&["abc", ":", "^abc"])
.succeeds()
.stdout_only("3\n");
new_ucmd!()
.args(&["^abc", ":", "^^abc"])
.succeeds()
.stdout_only("4\n");
new_ucmd!()
.args(&["b^$ic", ":", "b^\\$ic"])
.succeeds()
.stdout_only("5\n");
new_ucmd!()
.args(&["^^^^^^^^^", ":", "^^^"])
.succeeds()
.stdout_only("2\n");
new_ucmd!()
.args(&["-5", ":", "-\\{0,1\\}[0-9]*$"])
.succeeds()
.stdout_only("2\n");
new_ucmd!().args(&["", ":", ""]).fails().stdout_only("0\n");
new_ucmd!()
.args(&["abc", ":", ""])
.fails()
.stdout_only("0\n");
new_ucmd!()
.args(&["abc", ":", "bc"])
.fails()
.stdout_only("0\n");
new_ucmd!()
.args(&["^abc", ":", "^abc"])
.fails()
.stdout_only("0\n");
}

#[test]
Expand Down Expand Up @@ -711,7 +735,6 @@ mod gnu_expr {
.stdout_only("\n");
}

#[ignore = "rust-onig bug, see https://github.com/rust-onig/rust-onig/issues/188"]
#[test]
fn test_bre10() {
new_ucmd!()
Expand Down
Loading