Skip to content

Use native batch URL rewrites for text nodes #284

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

Draft
adamziel wants to merge 1 commit into
base: codex-native-structured-rewrite
Choose a base branch
from
Draft

Use native batch URL rewrites for text nodes #284

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
34 changes: 34 additions & 0 deletions components/DataLiberation/BlockMarkup/class-blockmarkupurlprocessor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,40 @@ public function next_url_in_current_token() {
}
}

/**
* Rewrites all supported URLs in the current text node through the native
* batch URL base rewriter.
*
* This only handles ASCII text nodes. Non-ASCII text still falls through to
* the structured PHP path to preserve the broader URL parsing behavior.
*/
public function rewrite_current_text_node_url_bases( $compact_mapping ) {
if (
'#text' !== $this->get_token_type() ||
! function_exists( 'wp_native_apis_rewrite_text_url_bases' ) ||
( defined( 'WP_NATIVE_APIS_DISABLE_DEFAULTS' ) && WP_NATIVE_APIS_DISABLE_DEFAULTS )
) {
return false;
}

$text = $this->get_modifiable_text();
if ( preg_match( '/[^\x00-\x7F]/', $text ) ) {
return false;
}

$updated_text = wp_native_apis_rewrite_text_url_bases(
$text,
$this->base_url_string,
$compact_mapping
);

if ( $updated_text === $text ) {
return false;
}

return $this->set_modifiable_text( $updated_text );
}

private function next_url_in_text_node() {
if ( '#text' !== $this->get_token_type() ) {
return false;
Expand Down
83 changes: 47 additions & 36 deletions components/DataLiberation/URL/functions.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,50 +66,61 @@ function wp_rewrite_urls( $options ) {
}
$mapping_cache_key = sha1( implode( "\0", $mapping_key_parts ) );

$compact_mapping = '';
foreach ( $options['url-mapping'] as $from_url_string => $to_url_string ) {
$compact_mapping .= $from_url_string . "\x1f" . $to_url_string . "\x1e";
}

$p = new BlockMarkupUrlProcessor( $options['block_markup'], $options['base_url'] );
while ( $p->next_url() ) {
$token_type = $p->get_token_type();
$raw_url = $p->get_raw_url();
$cache_key = $mapping_cache_key . "\0" . $token_type . "\0" . $raw_url;

$cached = $rewrite_cache->get( $cache_key );
if ( null !== $cached ) {
if ( false !== $cached ) {
$p->set_url( $cached['raw_url'], $cached['parsed_url'] );
}
while ( $p->next_token() ) {
if ( $p->rewrite_current_text_node_url_bases( $compact_mapping ) ) {
continue;
}

$parsed_url = $p->get_parsed_url();
$converted = false;
foreach ( $url_mapping as $mapping ) {
if ( is_child_url_of( $parsed_url, $mapping['from_url'] ) ) {
$converted = WPURL::replace_base_url(
$parsed_url,
array(
'old_base_url' => $base_url_object,
'new_base_url' => $mapping['to_url'],
'raw_url' => $raw_url,
'is_relative' => (
'#text' !== $token_type &&
! WPURL::can_parse( $raw_url )
),
)
while ( $p->next_url_in_current_token() ) {
$token_type = $p->get_token_type();
$raw_url = $p->get_raw_url();
$cache_key = $mapping_cache_key . "\0" . $token_type . "\0" . $raw_url;

$cached = $rewrite_cache->get( $cache_key );
if ( null !== $cached ) {
if ( false !== $cached ) {
$p->set_url( $cached['raw_url'], $cached['parsed_url'] );
}
continue;
}

$parsed_url = $p->get_parsed_url();
$converted = false;
foreach ( $url_mapping as $mapping ) {
if ( is_child_url_of( $parsed_url, $mapping['from_url'] ) ) {
$converted = WPURL::replace_base_url(
$parsed_url,
array(
'old_base_url' => $base_url_object,
'new_base_url' => $mapping['to_url'],
'raw_url' => $raw_url,
'is_relative' => (
'#text' !== $token_type &&
! WPURL::can_parse( $raw_url )
),
)
);
break;
}
}

$cache_value = false;
if ( false !== $converted ) {
$cache_value = array(
'raw_url' => (string) $converted,
'parsed_url' => $converted->new_url,
);
break;
$p->set_url( $cache_value['raw_url'], $cache_value['parsed_url'] );
}
}

$cache_value = false;
if ( false !== $converted ) {
$cache_value = array(
'raw_url' => (string) $converted,
'parsed_url' => $converted->new_url,
);
$p->set_url( $cache_value['raw_url'], $cache_value['parsed_url'] );
$rewrite_cache->set( $cache_key, $cache_value );
}

$rewrite_cache->set( $cache_key, $cache_value );
}

return $p->get_updated_html();
Expand Down
Loading