Issue #3239472 by stefanos.petrakis, danflanagan8, sjerdo, kporras07, alorenc,... (687473d5) · Commits · project / drupal

core/modules/filter/filter.module

+44 −36

Original line number	Diff line number	Diff line
		@@ -447,6 +447,9 @@ function template_preprocess_filter_tips(&$variables) {
		* expression that could possibly match all of the cases in one pass.
		*/
		function _filter_url($text, $filter) {
		// Store the current text in case any of the preg_* functions fail.
		$saved_text = $text;

		// Tags to skip and not recurse into.
		$ignore_tags = 'a\|script\|style\|code\|pre';

		@@ -523,10 +526,13 @@ function _filter_url($text, $filter) {
		// markup, especially a '>'. Therefore, remove all comment contents and add
		// them back later.
		_filter_url_escape_comments('', TRUE);
		$text = preg_replace_callback('`<!--(.*?)-->`s', '_filter_url_escape_comments', $text);
		$text = is_null($text) ? '' : preg_replace_callback('`<!--(.*?)-->`s', '_filter_url_escape_comments', $text);

		// Split at all tags; ensures that no tags or attributes are processed.
		$chunks = preg_split('/(<.+?>)/is', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
		$chunks = is_null($text) ? [''] : preg_split('/(<.+?>)/is', $text, -1, PREG_SPLIT_DELIM_CAPTURE);

		// Do not attempt to convert links into URLs if preg_split() fails.
		if ($chunks !== FALSE) {
		// PHP ensures that the array consists of alternating delimiters and
		// literals, and begins and ends with a literal (inserting NULL as
		// required). Therefore, the first chunk is always text:
		@@ -535,7 +541,6 @@ function _filter_url($text, $filter) {
		// removed when the closing tag is found. Until the closing tag is found,
		// no replacements are made.
		$open_tag = '';

		for ($i = 0; $i < count($chunks); $i++) {
		if ($chunk_type == 'text') {
		// Only process this text if there are no unclosed $ignore_tags.
		@@ -567,12 +572,15 @@ function _filter_url($text, $filter) {
		}

		$text = implode($chunks);
		}

		// Revert to the original comment contents
		_filter_url_escape_comments('', FALSE);
		$text = preg_replace_callback('`<!--(.*?)-->`', '_filter_url_escape_comments', $text);
		$text = $text ? preg_replace_callback('`<!--(.*?)-->`', '_filter_url_escape_comments', $text) : $text;
		}

		return $text;
		// If there is no text at this point revert to the previous text.
		return strlen((string) $text) > 0 ? $text : $saved_text;
		}

		/**

core/modules/filter/tests/src/Kernel/FilterKernelTest.php

+19 −0

Original line number	Diff line number	Diff line
		@@ -879,6 +879,7 @@ public function assertFilteredString(FilterInterface $filter, array $tests): voi
		* comments.
		* - Empty HTML tags (BR, IMG).
		* - Mix of absolute and partial URLs, and email addresses in one content.
		* - Input that exceeds PCRE backtracking limit.
		*/
		public function testUrlFilterContent() {
		// Get FilterUrl object.
		@@ -894,6 +895,24 @@ public function testUrlFilterContent() {
		$expected = file_get_contents($path . '/filter.url-output.txt');
		$result = _filter_url($input, $filter);
		$this->assertSame($expected, $result, 'Complex HTML document was correctly processed.');

		$pcre_backtrack_limit = ini_get('pcre.backtrack_limit');
		// Setting this limit to the smallest possible value should cause PCRE
		// errors and break the various preg_* functions used by _filter_url().
		ini_set('pcre.backtrack_limit', 1);

		// If PCRE errors occur, _filter_url() should return the exact same text.
		// Case of a small and simple HTML document.
		$input = $expected = '<p>www.test.com</p>';
		$result = _filter_url($input, $filter);
		$this->assertSame($expected, $result, 'Simple HTML document was left intact when PCRE errors occurred.');
		// Case of a complex HTML document.
		$input = $expected = file_get_contents($path . '/filter.url-input.txt');
		$result = _filter_url($input, $filter);
		$this->assertSame($expected, $result, 'Complex HTML document was left intact when PCRE errors occurred.');

		// Setting limit back to default.
		ini_set('pcre.backtrack_limit', $pcre_backtrack_limit);
		}

		/**