8000 [2.1][DomCrawler] Fix relative path handling in links by lazyhammer · Pull Request #7244 · symfony/symfony · GitHub
[go: up one dir, main page]
Skip to content

[2.1][DomCrawler] Fix relative path handling in links #7244

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
Mar 6, 2013
Merged

[2.1][DomCrawler] Fix relative path handling in links #7244

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
[DomCrawler] Fix relative path handling in links 
Added relative path canonicalization according to RFC 3986, section 5.2.4
  • Loading branch information
@lazyhammer
lazyhammer committed Mar 2, 2013
commit a4ec6772df9e0812be254b8455563ea5e3b5cf43
39 changes: 37 additions & 2 deletions src/Symfony/Component/DomCrawler/Link.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,13 +120,18 @@ public function getUri()
return $baseUri.$uri;
}

$baseUri = preg_replace('#^(.*?//[^/]+)(?:\/.*)?$#', '$1', $this->currentUri);

// absolute path
if ('/' === $uri[0]) {
return preg_replace('#^(.*?//[^/]+)(?:\/.*)?$#', '$1', $this->currentUri).$uri;
return $baseUri.$uri;
}

// relative path
return substr($this->currentUri, 0, strrpos($this->currentUri, '/') + 1).$uri;
$path = parse_url(substr($this->currentUri, strlen($baseUri)), PHP_URL_PATH);
$path = $this->canonicalizePath(substr($path, 0, strrpos($path, '/')).'/'.$uri);

return $baseUri.('' === $path || '/' !== $path[0] ? '/' : '').$path;
}

/**
Expand All @@ -139,6 +144,36 @@ protected function getRawUri()
return $this->node->getAttribute('href');
}

/**
* Returns the canonicalized URI path (see RFC 3986, section 5.2.4)
*
* @param string $path URI path
*
* @return string
*/
protected function canonicalizePath($path)
{
if ('' === $path || '/' === $path) {
return $path;
}

if ('.' === substr($path, -1)) {
$path = $path.'/';
}

$output = array();

foreach (explode('/', $path) as $segment) {
if ('..' === $segment) {
array_pop($output);
} elseif ('.' !== $segment) {
array_push($output, $segment);
}
}

return implode('/', $output);
}

/**
* Sets current \DOMNode instance
*
Expand Down
15 changes: 15 additions & 0 deletions src/Symfony/Component/DomCrawler/Tests/LinkTest.php
View file
854A Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,21 @@ public function getGetUriTests()
array('?foo=2', 'http://localhost/bar?foo=1', 'http://localhost/bar?foo=2'),
array('?foo=2', 'http://localhost/bar/?foo=1', 'http://localhost/bar/?foo=2'),
array('?bar=2', 'http://localhost?foo=1', 'http://localhost?bar=2'),

array('.', 'http://localhost/foo/bar/baz', 'http://localhost/foo/bar/'),
array('./', 'http://localhost/foo/bar/baz', 'http://localhost/foo/bar/'),
array('./foo', 'http://localhost/foo/bar/baz', 'http://localhost/foo/bar/foo'),
array('..', 'http://localhost/foo/bar/baz', 'http://localhost/foo/'),
array('../', 'http://localhost/foo/bar/baz', 'http://localhost/foo/'),
array('../foo', 'http://localhost/foo/bar/baz', 'http://localhost/foo/foo'),
array('../..', 'http://localhost/foo/bar/baz', 'http://localhost/'),
array('../../', 'http://localhost/foo/bar/baz', 'http://localhost/'),
array('../../foo', 'http://localhost/foo/bar/baz', 'http://localhost/foo'),
array('../../foo', 'http://localhost/bar/foo/', 'http://localhost/foo'),
array('../bar/../../foo', 'http://localhost/bar/foo/', 'http://localhost/foo'),
array('../bar/./../../foo', 'http://localhost/bar/foo/', 'http://localhost/foo'),
array('../../', 'http://localhost/', 'http://localhost/'),
array('../../', 'http://localhost', 'http://localhost/'),
);
}
}
0