cuqmbr/rss-bridge
1
0
Fork 0
mirror of https://github.com/RSS-Bridge/rss-bridge.git synced 2025-04-13 18:38:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

[html] parseSrcset: Add type hints, check preg_match_all

Browse Source
This commit is contained in:
ORelio 2025-03-31 19:09:08 +02:00 committed by GitHub
parent 96acb66fc4
commit 059514ea54
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/html.php
View File

@ -245,7 +245,7 @@ function defaultLinkTo($dom, $url)
* @param bool $return_largest_url Instead of returning an array, return URL for the largest entry * @param bool $return_largest_url Instead of returning an array, return URL for the largest entry
* @return array|string Content of srcset attribute as { size => url } array, or largest entry URL if requested * @return array|string Content of srcset attribute as { size => url } array, or largest entry URL if requested
*/ */
function parseSrcset($srcset, $return_largest_url = false) function parseSrcset(string $srcset, bool $return_largest_url = false)
{ {
// The srcset format is more tricky to parse that it seems: // The srcset format is more tricky to parse that it seems:
// URLs may contain commas, and space after comma is not mandatory, so the following is valid: // URLs may contain commas, and space after comma is not mandatory, so the following is valid:
@ -257,14 +257,16 @@ function parseSrcset($srcset, $return_largest_url = false)
// 2. Any amount of characters up to the next whitespace (space, tab, newline...): This is the URL // 2. Any amount of characters up to the next whitespace (space, tab, newline...): This is the URL
// 3. A nonnegative number followed by lowercase w, x or h: This is the image size // 3. A nonnegative number followed by lowercase w, x or h: This is the image size
// We parse the srcset entries using a regex to mimick the above parser/tokenizer behavior. // We parse the srcset entries using a regex to mimick the above parser/tokenizer behavior.
preg_match_all('/[\s]*,?[\s]*([^\s]+)\s+([0-9]+[wxh])/', $srcset, $matches); $preg_status = preg_match_all('/[\s]*,?[\s]*([^\s]+)\s+([0-9]+[wxh])/', $srcset, $matches);
$entries = []; $entries = [];
if ($preg_status !== false && $preg_status > 0) {
foreach ($matches[1] as $index => $url) { foreach ($matches[1] as $index => $url) {
if (array_key_exists($index, $matches[2])) { if (array_key_exists($index, $matches[2])) {
$size = $matches[2][$index]; $size = $matches[2][$index];
$entries[$size] = html_entity_decode($url); $entries[$size] = html_entity_decode($url);
} }
} }
}
if ($return_largest_url) { if ($return_largest_url) {
$largest_image_url = null; $largest_image_url = null;
$largest_image_size = -1; $largest_image_size = -1;