File size: 6,722 Bytes
9ebf6d4 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 | /// Attempt to find the sequence of `pattern` lines within `lines` beginning at or after `start`.
/// Returns the starting index of the match or `None` if not found. Matches are attempted with
/// decreasing strictness: exact match, then ignoring trailing whitespace, then ignoring leading
/// and trailing whitespace. When `eof` is true, we first try starting at the end-of-file (so that
/// patterns intended to match file endings are applied at the end), and fall back to searching
/// from `start` if needed.
///
/// Special cases handled defensively:
/// • Empty `pattern` → returns `Some(start)` (no-op match)
/// • `pattern.len() > lines.len()` → returns `None` (cannot match, avoids
/// out‑of‑bounds panic that occurred pre‑2025‑04‑12)
pub(crate) fn seek_sequence(
lines: &[String],
pattern: &[String],
start: usize,
eof: bool,
update_file_mode: crate::ApplyPatchFileUpdateMode,
) -> Option<usize> {
if pattern.is_empty() {
return Some(start);
}
// When the pattern is longer than the available input there is no possible
// match. Early‑return to avoid the out‑of‑bounds slice that would occur in
// the search loops below (previously caused a panic when
// `pattern.len() > lines.len()`).
if pattern.len() > lines.len() {
return None;
}
let search_start = if eof && lines.len() >= pattern.len() {
let eof_start = lines.len() - pattern.len();
match update_file_mode {
crate::ApplyPatchFileUpdateMode::NormalizeToLf => eof_start,
crate::ApplyPatchFileUpdateMode::PreserveLineEndings => eof_start.max(start),
}
} else {
start
};
// Exact match first.
for i in search_start..=lines.len().saturating_sub(pattern.len()) {
if lines[i..i + pattern.len()] == *pattern {
return Some(i);
}
}
// Then rstrip match.
for i in search_start..=lines.len().saturating_sub(pattern.len()) {
let mut ok = true;
for (p_idx, pat) in pattern.iter().enumerate() {
if lines[i + p_idx].trim_end() != pat.trim_end() {
ok = false;
break;
}
}
if ok {
return Some(i);
}
}
// Finally, trim both sides to allow more lenience.
for i in search_start..=lines.len().saturating_sub(pattern.len()) {
let mut ok = true;
for (p_idx, pat) in pattern.iter().enumerate() {
if lines[i + p_idx].trim() != pat.trim() {
ok = false;
break;
}
}
if ok {
return Some(i);
}
}
// ------------------------------------------------------------------
// Final, most permissive pass – attempt to match after *normalising*
// common Unicode punctuation to their ASCII equivalents so that diffs
// authored with plain ASCII characters can still be applied to source
// files that contain typographic dashes / quotes, etc. This mirrors the
// fuzzy behaviour of `git apply` which ignores minor byte-level
// differences when locating context lines.
// ------------------------------------------------------------------
fn normalise(s: &str) -> String {
s.trim()
.chars()
.map(|c| match c {
// Various dash / hyphen code-points → ASCII '-'
'\u{2010}' | '\u{2011}' | '\u{2012}' | '\u{2013}' | '\u{2014}' | '\u{2015}'
| '\u{2212}' => '-',
// Fancy single quotes → '\''
'\u{2018}' | '\u{2019}' | '\u{201A}' | '\u{201B}' => '\'',
// Fancy double quotes → '"'
'\u{201C}' | '\u{201D}' | '\u{201E}' | '\u{201F}' => '"',
// Non-breaking space and other odd spaces → normal space
'\u{00A0}' | '\u{2002}' | '\u{2003}' | '\u{2004}' | '\u{2005}' | '\u{2006}'
| '\u{2007}' | '\u{2008}' | '\u{2009}' | '\u{200A}' | '\u{202F}' | '\u{205F}'
| '\u{3000}' => ' ',
other => other,
})
.collect::<String>()
}
for i in search_start..=lines.len().saturating_sub(pattern.len()) {
let mut ok = true;
for (p_idx, pat) in pattern.iter().enumerate() {
if normalise(&lines[i + p_idx]) != normalise(pat) {
ok = false;
break;
}
}
if ok {
return Some(i);
}
}
None
}
#[cfg(test)]
mod tests {
use super::seek_sequence;
use crate::ApplyPatchFileUpdateMode;
use std::string::ToString;
fn to_vec(strings: &[&str]) -> Vec<String> {
strings.iter().map(ToString::to_string).collect()
}
#[test]
fn test_exact_match_finds_sequence() {
let lines = to_vec(&["foo", "bar", "baz"]);
let pattern = to_vec(&["bar", "baz"]);
assert_eq!(
seek_sequence(
&lines,
&pattern,
/*start*/ 0,
/*eof*/ false,
ApplyPatchFileUpdateMode::NormalizeToLf,
),
Some(1)
);
}
#[test]
fn test_rstrip_match_ignores_trailing_whitespace() {
let lines = to_vec(&["foo ", "bar\t\t"]);
// Pattern omits trailing whitespace.
let pattern = to_vec(&["foo", "bar"]);
assert_eq!(
seek_sequence(
&lines,
&pattern,
/*start*/ 0,
/*eof*/ false,
ApplyPatchFileUpdateMode::NormalizeToLf,
),
Some(0)
);
}
#[test]
fn test_trim_match_ignores_leading_and_trailing_whitespace() {
let lines = to_vec(&[" foo ", " bar\t"]);
// Pattern omits any additional whitespace.
let pattern = to_vec(&["foo", "bar"]);
assert_eq!(
seek_sequence(
&lines,
&pattern,
/*start*/ 0,
/*eof*/ false,
ApplyPatchFileUpdateMode::NormalizeToLf,
),
Some(0)
);
}
#[test]
fn test_pattern_longer_than_input_returns_none() {
let lines = to_vec(&["just one line"]);
let pattern = to_vec(&["too", "many", "lines"]);
// Should not panic – must return None when pattern cannot possibly fit.
assert_eq!(
seek_sequence(
&lines,
&pattern,
/*start*/ 0,
/*eof*/ false,
ApplyPatchFileUpdateMode::NormalizeToLf,
),
None
);
}
}
|