function _filter_url
Same name in other branches
- 7.x modules/filter/filter.module \_filter_url()
- 9 core/modules/filter/filter.module \_filter_url()
- 8.9.x core/modules/filter/filter.module \_filter_url()
- 10 core/modules/filter/filter.module \_filter_url()
Converts text into hyperlinks automatically.
This filter identifies and makes clickable three types of "links".
- URLs like http://example.com.
- Email addresses like name@example.com.
- Web addresses without the "http://" protocol defined, like www.example.com.
Each type must be processed separately, as there is no one regular expression that could possibly match all of the cases in one pass.
Related topics
2 calls to _filter_url()
- FilterKernelTest::testUrlFilterContent in core/
modules/ filter/ tests/ src/ Kernel/ FilterKernelTest.php - Tests URL filter on longer content.
- FilterUrl::process in core/
modules/ filter/ src/ Plugin/ Filter/ FilterUrl.php - Performs the filter processing.
File
-
core/
modules/ filter/ filter.module, line 456
Code
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';
// Pass length to regexp callback.
_filter_url_trim(NULL, $filter->settings['filter_url_length']);
// Create an array which contains the regexps for each type of link.
// The key to the regexp is the name of a function that is used as
// callback function to process matches of the regexp. The callback function
// is to return the replacement for the match. The array is used and
// matching/replacement done below inside some loops.
$tasks = [];
// Prepare protocols pattern for absolute URLs.
// \Drupal\Component\Utility\UrlHelper::stripDangerousProtocols() will replace
// any bad protocols with HTTP, so we need to support the identical list.
// While '//' is technically optional for MAILTO only, we cannot cleanly
// differ between protocols here without hard-coding MAILTO, so '//' is
// optional for all protocols.
// @see \Drupal\Component\Utility\UrlHelper::stripDangerousProtocols()
$protocols = \Drupal::getContainer()->getParameter('filter_protocols');
$protocols = implode(':(?://)?|', $protocols) . ':(?://)?';
$valid_url_path_characters = "[\\p{L}\\p{M}\\p{N}!\\*\\';:=\\+,\\.\$\\/%#\\[\\]\\-_~@&]";
// Allow URL paths to contain balanced parens
// 1. Used in Wikipedia URLs like /Primer_(film)
// 2. Used in IIS sessions like /S(dfd346)/
$valid_url_balanced_parens = '\\(' . $valid_url_path_characters . '+\\)';
// Valid end-of-path characters (so /foo. does not gobble the period).
// 1. Allow =&# for empty URL parameters and other URL-join artifacts
$valid_url_ending_characters = '[\\p{L}\\p{M}\\p{N}:_+~#=/]|(?:' . $valid_url_balanced_parens . ')';
$valid_url_query_chars = '[a-zA-Z0-9!?\\*\'@\\(\\);:&=\\+\\$\\/%#\\[\\]\\-_\\.,~|]';
$valid_url_query_ending_chars = '[a-zA-Z0-9_&=#\\/]';
// Full path
// and allow @ in a URL, but only in the middle. Catch things like http://example.com/@user/
$valid_url_path = '(?:(?:' . $valid_url_path_characters . '*(?:' . $valid_url_balanced_parens . $valid_url_path_characters . '*)*' . $valid_url_ending_characters . ')|(?:@' . $valid_url_path_characters . '+\\/))';
// Prepare domain name pattern.
// The ICANN seems to be on track towards accepting more diverse top level
// domains (TLDs), so this pattern has been "future-proofed" to allow for
// TLDs of length 2-64.
$domain = '(?:[\\p{L}\\p{M}\\p{N}._+-]+\\.)?[\\p{L}\\p{M}]{2,64}\\b';
// Mail domains differ from the generic domain pattern, specifically:
// A . character must be present in the string that follows the @ character.
$email_domain = '(?:[\\p{L}\\p{M}\\p{N}._+-]+\\.)+[\\p{L}\\p{M}]{2,64}\\b';
$ip = '(?:[0-9]{1,3}\\.){3}[0-9]{1,3}';
$auth = '[\\p{L}\\p{M}\\p{N}:%_+*~#?&=.,/;-]+@';
$trail = '(' . $valid_url_path . '*)?(\\?' . $valid_url_query_chars . '*' . $valid_url_query_ending_chars . ')?';
// Match absolute URLs.
$url_pattern = "(?:{$auth})?(?:{$domain}|{$ip})/?(?:{$trail})?";
$pattern = "`((?:{$protocols})(?:{$url_pattern}))`u";
$tasks['_filter_url_parse_full_links'] = $pattern;
// Match email addresses.
$url_pattern = "[\\p{L}\\p{M}\\p{N}._+-]{1,254}@(?:{$email_domain})";
$pattern = "`({$url_pattern})`u";
$tasks['_filter_url_parse_email_links'] = $pattern;
// Match www domains.
$url_pattern = "www\\.(?:{$domain})/?(?:{$trail})?";
$pattern = "`({$url_pattern})`u";
$tasks['_filter_url_parse_partial_links'] = $pattern;
// Each type of URL needs to be processed separately. The text is joined and
// re-split after each task, since all injected HTML tags must be correctly
// protected before the next task.
foreach ($tasks as $task => $pattern) {
// HTML comments need to be handled separately, as they may contain HTML
// markup, especially a '>'. Therefore, remove all comment contents and add
// them back later.
_filter_url_escape_comments('', TRUE);
$text = is_null($text) ? '' : preg_replace_callback('`<!--(.*?)-->`s', '_filter_url_escape_comments', $text);
// Split at all tags; ensures that no tags or attributes are processed.
$chunks = is_null($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:
$chunk_type = 'text';
// If a tag of $ignore_tags is found, it is stored in $open_tag and only
// 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 $ignore_tags.
if ($open_tag == '') {
// If there is a match, inject a link into this chunk via the callback
// function contained in $task.
$chunks[$i] = preg_replace_callback($pattern, $task, $chunks[$i]);
}
// Text chunk is done, so next chunk must be a tag.
$chunk_type = 'tag';
}
else {
// Only process this tag if there are no unclosed $ignore_tags.
if ($open_tag == '') {
// Check whether this tag is contained in $ignore_tags.
if (preg_match("`<({$ignore_tags})(?:\\s|>)`i", $chunks[$i], $matches)) {
$open_tag = $matches[1];
}
}
else {
if (preg_match("`<\\/{$open_tag}>`i", $chunks[$i], $matches)) {
$open_tag = '';
}
}
// Tag chunk is done, so next chunk must be text.
$chunk_type = 'text';
}
}
$text = implode($chunks);
}
// Revert to the original comment contents
_filter_url_escape_comments('', FALSE);
$text = $text ? preg_replace_callback('`<!--(.*?)-->`', '_filter_url_escape_comments', $text) : $text;
}
// If there is no text at this point revert to the previous text.
return strlen((string) $text) > 0 ? $text : $saved_text;
}
Buggy or inaccurate documentation? Please file an issue. Need support? Need help programming? Connect with the Drupal community.