1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
// This file is part of the uutils coreutils package.
//
// For the full copyright and license information, please view the LICENSE
// file that was distributed with this source code.
//! Parsing a glob Pattern from a string.
//!
//! Use the [`from_str`] function to parse a [`Pattern`] from a string.
// cSpell:words fnmatch
use glob::{Pattern, PatternError};
fn fix_negation(glob: &str) -> String {
let mut chars = glob.chars().collect::<Vec<_>>();
let mut i = 0;
// Add 3 to prevent out of bounds in loop
while i + 3 < chars.len() {
if chars[i] == '[' && chars[i + 1] == '^' {
match chars[i + 3..].iter().position(|x| *x == ']') {
None => {
// if closing square bracket not found, stop looking for it
// again
break;
}
Some(j) => {
chars[i + 1] = '!';
i += j + 4;
continue;
}
}
}
i += 1;
}
chars.into_iter().collect::<String>()
}
/// Parse a glob Pattern from a string.
///
/// This function amends the input string to replace any caret or circumflex
/// character (^) used to negate a set of characters with an exclamation mark
/// (!), which adapts rust's glob matching to function the way the GNU utils'
/// fnmatch does.
///
/// # Examples
///
/// ```rust
/// use std::time::Duration;
/// use uucore::parse_glob::from_str;
/// assert!(!from_str("[^abc]").unwrap().matches("a"));
/// assert!(from_str("[^abc]").unwrap().matches("x"));
/// ```
pub fn from_str(glob: &str) -> Result<Pattern, PatternError> {
Pattern::new(&fix_negation(glob))
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_from_str() {
assert_eq!(from_str("[^abc]").unwrap(), Pattern::new("[!abc]").unwrap());
}
#[test]
fn test_fix_negation() {
// Happy/Simple case
assert_eq!(fix_negation("[^abc]"), "[!abc]");
// Should fix negations in a long regex
assert_eq!(fix_negation("foo[abc] bar[^def]"), "foo[abc] bar[!def]");
// Should fix multiple negations in a regex
assert_eq!(fix_negation("foo[^abc]bar[^def]"), "foo[!abc]bar[!def]");
// Should fix negation of the single character ]
assert_eq!(fix_negation("[^]]"), "[!]]");
// Should fix negation of the single character ^
assert_eq!(fix_negation("[^^]"), "[!^]");
// Should fix negation of the space character
assert_eq!(fix_negation("[^ ]"), "[! ]");
// Complicated patterns
assert_eq!(fix_negation("[^][]"), "[!][]");
assert_eq!(fix_negation("[^[]]"), "[![]]");
// More complex patterns that should be replaced
assert_eq!(fix_negation("[[]] [^a]"), "[[]] [!a]");
assert_eq!(fix_negation("[[] [^a]"), "[[] [!a]");
assert_eq!(fix_negation("[]] [^a]"), "[]] [!a]");
// test that we don't look for closing square brackets unnecessarily
// Verifies issue #5584
let chars = "^[".repeat(174571);
assert_eq!(fix_negation(chars.as_str()), chars);
}
#[test]
fn test_fix_negation_should_not_amend() {
assert_eq!(fix_negation("abc"), "abc");
// Regex specifically matches either [ or ^
assert_eq!(fix_negation("[[^]"), "[[^]");
// Regex that specifically matches either space or ^
assert_eq!(fix_negation("[ ^]"), "[ ^]");
// Regex that specifically matches either [, space or ^
assert_eq!(fix_negation("[[ ^]"), "[[ ^]");
assert_eq!(fix_negation("[ [^]"), "[ [^]");
// Invalid globs (according to rust's glob implementation) will remain unamended
assert_eq!(fix_negation("[^]"), "[^]");
assert_eq!(fix_negation("[^"), "[^");
assert_eq!(fix_negation("[][^]"), "[][^]");
// Issue #4479
assert_eq!(fix_negation("ààà[^"), "ààà[^");
}
}