Skip to content

Bug 500 error when invalid url #825

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

Open
wants to merge 7 commits into
base: develop
Choose a base branch
from
Open

Bug 500 error when invalid url #825

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
2b435ab
Added a regex replace to remove multiple // in a URI
Oct 8, 2021
0f70789
Fixed lint messages
Oct 8, 2021
5000ded
Fix input string | null to just pass in url on null
Oct 8, 2021
bda4054
Attempt to match coding style
Oct 8, 2021
b834d4b
and again. - sorry
Oct 8, 2021
9fbe180
Cleaned up code
Oct 8, 2021
cc158ec
Fix array_map namespace callback issue
Oct 9, 2021
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
28 changes: 24 additions & 4 deletions src/SitemapParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,8 +173,13 @@ public function getQueue() {
* @throws WP2StaticException
*/
public function parse( $url, $url_content = null ) {
$check_url = $url;
$clean_url = preg_replace( '/(?<!:)\/\/+/', '/', $url );
$this->clean();
$this->current_url = $this->urlEncode( $url );
if ( $clean_url ) {
$check_url = $clean_url;
}
$this->current_url = $this->urlEncode( $check_url );
if ( ! $this->urlValidate( $this->current_url ) ) {
throw new WP2StaticException( 'Invalid URL' );
}
Expand Down Expand Up @@ -242,6 +247,16 @@ protected function getContent() {
}
}

/**
* callable trim function
*
* @param string $string
* @return string
*/
protected function trim( $string ) {
return trim( $string );
}

/**
* Search for sitemaps in the robots.txt content
*
Expand All @@ -252,7 +267,7 @@ protected function parseRobotstxt( $robotstxt ) {
// Split lines into array
$lines = array_filter(
array_map(
'trim',
[ $this, 'trim' ],
(array) preg_split( '/\r\n|\n|\r/', $robotstxt )
)
);
Expand All @@ -269,7 +284,7 @@ protected function parseRobotstxt( $robotstxt ) {
$line = $line[0];

// Split by directive and rule
$pair = array_map( 'trim', (array) preg_split( '/:/', $line, 2 ) );
$pair = array_map( [ $this, 'trim' ], (array) preg_split( '/:/', $line, 2 ) );
// Check if the line contains a sitemap
if (
strtolower( $pair[0] ) !== self::XML_TAG_SITEMAP ||
Expand Down Expand Up @@ -374,7 +389,12 @@ protected function parseString( $string ) {
// Strings are not part of any documented sitemap standard
return false;
}
$array = array_filter( array_map( 'trim', (array) preg_split( '/\r\n|\n|\r/', $string ) ) );
$array = array_filter(
array_map(
[ $this, 'trim' ],
(array) preg_split( '/\r\n|\n|\r/', $string )
)
);
foreach ( $array as $line ) {
if ( $this->isSitemapURL( $line ) ) {
$this->addArray( self::XML_TAG_SITEMAP, [ 'loc' => $line ] );
Expand Down