Skip to content

Fix/Rewrite .gitignore regex builder #40763

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
merged 1 commit into from
May 9, 2021
Merged

Fix/Rewrite .gitignore regex builder #40763

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
132 changes: 43 additions & 89 deletions src/Symfony/Component/Finder/Gitignore.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,120 +14,74 @@
/**
* Gitignore matches against text.
*
* @author Michael Voříšek <vorismi3@fel.cvut.cz>
* @author Ahmed Abdou <mail@ahmd.io>
*/
class Gitignore
{
/**
* Returns a regexp which is the equivalent of the gitignore pattern.
*
* @return string The regexp
* Format specification: https://git-scm.com/docs/gitignore#_pattern_format
*/
public static function toRegex(string $gitignoreFileContent): string
{
$gitignoreFileContent = preg_replace('/^[^\\\r\n]*#.*/m', '', $gitignoreFileContent);
$gitignoreLines = preg_split('/\r\n|\r|\n/', $gitignoreFileContent);
$gitignoreFileContent = preg_replace('~(?<!\\\\)#[^\n\r]*~', '', $gitignoreFileContent);
$gitignoreLines = preg_split('~\r\n?|\n~', $gitignoreFileContent);

$positives = [];
$negatives = [];
$res = self::lineToRegex('');
foreach ($gitignoreLines as $i => $line) {
$line = trim($line);
if ('' === $line) {
continue;
}

if (1 === preg_match('/^!/', $line)) {
$positives[$i] = null;
$negatives[$i] = self::getRegexFromGitignore(preg_replace('/^!(.*)/', '${1}', $line), true);

continue;
}
$negatives[$i] = null;
$positives[$i] = self::getRegexFromGitignore($line);
}
$line = preg_replace('~(?<!\\\\)[ \t]+$~', '', $line);

$index = 0;
$patterns = [];
foreach ($positives as $pattern) {
if (null === $pattern) {
continue;
if ('!' === substr($line, 0, 1)) {
$line = substr($line, 1);
$isNegative = true;
} else {
$isNegative = false;
}

$negativesAfter = array_filter(\array_slice($negatives, ++$index));
if ([] !== $negativesAfter) {
$pattern .= sprintf('(?<!%s)', implode('|', $negativesAfter));
if ('' !== $line) {
if ($isNegative) {
$res = '(?!'.self::lineToRegex($line).'$)'.$res;
} else {
$res = '(?:'.$res.'|'.self::lineToRegex($line).')';
}
}

$patterns[] = $pattern;
}

return sprintf('/^((%s))$/', implode(')|(', $patterns));
return '~^(?:'.$res.')~s';
}

private static function getRegexFromGitignore(string $gitignorePattern, bool $negative = false): string
private static function lineToRegex(string $gitignoreLine): string
{
$regex = '';
$isRelativePath = false;
// If there is a separator at the beginning or middle (or both) of the pattern, then the pattern is relative to the directory level of the particular .gitignore file itself
$slashPosition = strpos($gitignorePattern, '/');
if (false !== $slashPosition && \strlen($gitignorePattern) - 1 !== $slashPosition) {
if (0 === $slashPosition) {
$gitignorePattern = substr($gitignorePattern, 1);
}

$isRelativePath = true;
$regex .= '^';
if ('' === $gitignoreLine) {
return '$f'; // always false
}

if ('/' === $gitignorePattern[\strlen($gitignorePattern) - 1]) {
$gitignorePattern = substr($gitignorePattern, 0, -1);
}

$iMax = \strlen($gitignorePattern);
for ($i = 0; $i < $iMax; ++$i) {
$tripleChars = substr($gitignorePattern, $i, 3);
if ('**/' === $tripleChars || '/**' === $tripleChars) {
$regex .= '.*';
$i += 2;
continue;
}

$doubleChars = substr($gitignorePattern, $i, 2);
if ('**' === $doubleChars) {
$regex .= '.*';
++$i;
continue;
}
if ('*/' === $doubleChars) {
$regex .= '[^\/]*\/?[^\/]*';
++$i;
continue;
$slashPos = strpos($gitignoreLine, '/');
if (false !== $slashPos && \strlen($gitignoreLine) - 1 !== $slashPos) {
if (0 === $slashPos) {
$gitignoreLine = substr($gitignoreLine, 1);
}

$c = $gitignorePattern[$i];
switch ($c) {
case '*':
$regex .= $isRelativePath ? '[^\/]*' : '[^\/]*\/?[^\/]*';
break;
case '/':
case '.':
case ':':
case '(':
case ')':
case '{':
case '}':
$regex .= '\\'.$c;
break;
default:
$regex .= $c;
}
}

if ($negative) {
// a lookbehind assertion has to be a fixed width (it can not have nested '|' statements)
return sprintf('%s$|%s\/$', $regex, $regex);
$isAbsolute = true;
} else {
$isAbsolute = false;
}

return '(?>'.$regex.'($|\/.*))';
$parts = array_map(function (string $v): string {
$v = preg_quote(str_replace('\\', '', $v), '~');
$v = preg_replace_callback('~\\\\\[([^\[\]]*)\\\\\]~', function (array $matches): string {
return '['.str_replace('\\-', '-', $matches[1]).']';
}, $v);
$v = preg_replace('~\\\\\*\\\\\*~', '[^/]+(?:/[^/]+)*', $v);
$v = preg_replace('~\\\\\*~', '[^/]*', $v);
$v = preg_replace('~\\\\\?~', '[^/]', $v);

return $v;
}, explode('/', $gitignoreLine));

return ($isAbsolute ? '' : '(?:[^/]+/)*')
.implode('/', $parts)
.('' !== end($parts) ? '(?:$|/)' : '');
}
}
Loading