wordpress-activitypub/includes/class-mention.php

175 lines
4.7 KiB
PHP
Raw Normal View History

2022-12-09 11:59:24 +01:00
<?php
namespace Activitypub;
use WP_Error;
2023-10-12 13:25:50 +02:00
use Activitypub\Webfinger;
2022-12-09 11:59:24 +01:00
/**
* ActivityPub Mention Class
*
* @author Alex Kirk
*/
class Mention {
/**
* Initialize the class, registering WordPress hooks
*/
public static function init() {
Comment Federation (#550) * Comments 1 * Delete FUNDING.yml * Add basic BuddyPress support fix #122 thanks and props @skysarwer * change URL to `bp_core_get_user_domain` * fix "Follow" issue fix #133 * fix #135 * version bump * Create phpunit.yml * Update composer.json * Update composer.json * Update phpunit.yml * Update composer.json * Create phpcs.yml * Update phpcs.xml * Update composer.json * phpcs fixes * fix typo * Comments update * webfinger_extract remove extra param * coding standards * Replies Collection, settings, other fixes * Create stale.yml * move stale file * code standards cleanup * Migrate / Update script * bugfix * add settings link to plugin page * fix code standards * fix cs * fix PHPCS * PHPCS fixes * change background image for wp.org * fix docker * fix webfinger for email identifiers fix #152 * version bump * update composer file to fix unit testing * allow plugins * fix dependencies * Migrate tools * code cleanup * regression fix * Fix announce, clarified language * update included filename * code cleanup * Improve migration UX * Add comments view, warnings to migrate page * style fix * more style fixes * Fix send_delete_activity * replace ap_comment_id to reuse replytocom var * Comments class missing attributes * Post class fix attributes * move js file to assets/js * Separate file for Comment processing hooks * fix file path * associate comments to back compat post * Fix js assets enqueue * change regex matching potential hashtags Matches any string starting with '#' and consisting of any number and combination of [A-Za-z0-9_] that is directly followed by whitespace or punctuation. Groups everything after '#' for access in functions using this regex. This fixes #183 (incomplete links on hashtags containing special characters) by not matching these at all. * also detect hashtags at the start of a paragraph * restrict html tags after which to detect a hashtag Hashtags should not be detected after just any html tag - for example not after an opening a or div. To still allow detection at the start of a line, allow specifically p and br to directly precede a hashtag. * fix pagination * Add Custom Post Type support to outbox API * remove comment_type * fix comparison * remove trailing spaces * fix phpcs issues * fix phpcs issues * run phpcs also on pull_requests * fix phpcs issues * support threaded comments from ActivityPub * refactor support for threaded comments from ActivityPub * remove debugging log line * add first unit tests for class inbox * fix code smells * make filter function static * attempt to resolve backwards compatibility issues * update js to new file * delete old js * Remove migrate code * update post meta canonical * remove type and mention meta from comment filters * extract mentions from comment_content * phpcbf * remove extra curly bracket * Remove migrate code * remove version_check() * Update enqueue scripts * Remove remote comments from preprocessing * Reply to comments from Dashboard * rename function, inserts users into reply text * Update dispatch comments * update comment model * fix comment model replies property * fix preprocess_comment cap check * Add webfinger filter to comments * Add comment edit datetime * cleanup * fix var name * cleanup * phpcbf * better actual translation support * Separate comment reply script * migrate dispatch, migrate comment model to transform * ignore WP_Comment type for now * Adds new helpers for resolving inReplyTo url * Update activitypub_send_comment_activity to include type * remove redundant id check * reinclude user_id in saved ap_object meta * update post field meta * Fix comment updated datetime * front-end reply inserts @mentions * enqueue reply script on front end * use const instead of dirname * some simplifications * move some functions * fixes * some more fixes * fix namespace * fix unittests * fix testcase * fixed typo * fix tests * fix tests * fix PHPCS * move functions to transformer class * fix warnings * Link remote comments on frontend * Link to comment source as row action * Init Comments class * remove dead dispatch action * re-add extract mentions filter * Restore and tweak Comment transform * Schedule comments activities for non-admin users * lint * remove context property * rename get_id method to generate_id * fix locale * move functions * PHPDoc * this is never used * remove some edit methods * remove replies for now * remove JS calls * remove reply_recipients * never used * remove other query-vars * otherwise to_json would not work properly * small changes * use `c` for comment IDs * remove comments.php for now maybe re-add it later * wp_insert_post is an action * also parse comment_text * remove duplicate functions * add Base transformer * remove invalid test * update to new query var * update dispatcher to support comments and posts * fix transition * remove unused functions for now * schedule_comment_activity seems to ignore create and update * fix wrong use of functions! * not every platforms sends an URL * check source-id first * remove hashtags for now * fallback to ID * fix typo * move to_activity to Base class * remove unused function * add support for announce and like * also ping inboxes of other commenters in the thread * restructure WebFinger class * some small improvements * simplified to_object class props @Menrath for the feedback and the idea! * fix unit tests * make transformer filterable /cc @Menrath * use transformer factory, so that transformer can be overwritten * phpcs fixes * fix attachments * fix comment transformer * remove comments for now * update readme/changelog * simplify and unify json_encodes --------- Co-authored-by: Django Doucet <mediaformat.ux@gmail.com> Co-authored-by: Andreas <andreas@bocops.de> Co-authored-by: Eana Hufwe <eana@1a23.com> Co-authored-by: Matthew Exon <git.mexon@spamgourmet.com> Co-authored-by: Django Doucet <django.doucet@webdevstudios.com>
2023-12-22 10:12:26 +01:00
\add_filter( 'the_content', array( self::class, 'the_content' ), 99, 1 );
\add_filter( 'comment_text', array( self::class, 'the_content' ), 10, 1 );
2023-04-20 15:22:11 +02:00
\add_filter( 'activitypub_extract_mentions', array( self::class, 'extract_mentions' ), 99, 2 );
2022-12-09 11:59:24 +01:00
}
/**
2022-12-09 13:39:48 +01:00
* Filter to replace the mentions in the content with links
2022-12-09 11:59:24 +01:00
*
* @param string $the_content the post-content
*
* @return string the filtered post-content
*/
public static function the_content( $the_content ) {
// small protection against execution timeouts: limit to 1 MB
if ( mb_strlen( $the_content ) > MB_IN_BYTES ) {
return $the_content;
}
$tag_stack = array();
$protected_tags = array(
'pre',
'code',
'textarea',
'style',
'a',
2022-12-13 11:34:07 +01:00
);
$content_with_links = '';
$in_protected_tag = false;
foreach ( wp_html_split( $the_content ) as $chunk ) {
if ( preg_match( '#^<!--[\s\S]*-->$#i', $chunk, $m ) ) {
$content_with_links .= $chunk;
continue;
}
2022-12-13 11:34:07 +01:00
if ( preg_match( '#^<(/)?([a-z-]+)\b[^>]*>$#i', $chunk, $m ) ) {
$tag = strtolower( $m[2] );
if ( '/' === $m[1] ) {
// Closing tag.
$i = array_search( $tag, $tag_stack );
// We can only remove the tag from the stack if it is in the stack.
if ( false !== $i ) {
$tag_stack = array_slice( $tag_stack, 0, $i );
}
} else {
// Opening tag, add it to the stack.
$tag_stack[] = $tag;
}
// If we're in a protected tag, the tag_stack contains at least one protected tag string.
// The protected tag state can only change when we encounter a start or end tag.
$in_protected_tag = array_intersect( $tag_stack, $protected_tags );
// Never inspect tags.
$content_with_links .= $chunk;
continue;
}
if ( $in_protected_tag ) {
// Don't inspect a chunk inside an inspected tag.
$content_with_links .= $chunk;
continue;
}
// Only reachable when there is no protected tag in the stack.
$content_with_links .= \preg_replace_callback( '/@' . ACTIVITYPUB_USERNAME_REGEXP . '/', array( self::class, 'replace_with_links' ), $chunk );
}
2022-12-13 11:34:07 +01:00
return $content_with_links;
2022-12-09 11:59:24 +01:00
}
/**
2022-12-09 13:39:48 +01:00
* A callback for preg_replace to build the user links
2022-12-09 11:59:24 +01:00
*
* @param array $result the preg_match results
*
2022-12-09 11:59:24 +01:00
* @return string the final string
*/
public static function replace_with_links( $result ) {
2023-05-04 08:50:44 +02:00
$metadata = get_remote_metadata_by_actor( $result[0] );
2023-08-10 15:35:10 +02:00
2023-09-05 21:03:25 +02:00
if ( ! empty( $metadata ) && ! is_wp_error( $metadata ) && ! empty( $metadata['url'] ) ) {
2022-12-12 16:39:55 +01:00
$username = ltrim( $result[0], '@' );
if ( ! empty( $metadata['name'] ) ) {
$username = $metadata['name'];
}
2022-12-09 11:59:24 +01:00
if ( ! empty( $metadata['preferredUsername'] ) ) {
$username = $metadata['preferredUsername'];
}
2023-07-18 06:30:06 +02:00
return \sprintf( '<a rel="mention" class="u-url mention" href="%s">@<span>%s</span></a>', esc_url( $metadata['url'] ), esc_html( $username ) );
2022-12-09 11:59:24 +01:00
}
2022-12-09 12:02:55 +01:00
return $result[0];
2022-12-09 11:59:24 +01:00
}
/**
* Get the Inboxes for the mentioned Actors
*
* @param array $mentioned The list of Actors that were mentioned
*
* @return array The list of Inboxes
*/
public static function get_inboxes( $mentioned ) {
$inboxes = array();
foreach ( $mentioned as $actor ) {
$inbox = self::get_inbox_by_mentioned_actor( $actor );
if ( ! is_wp_error( $inbox ) && $inbox ) {
$inboxes[] = $inbox;
}
}
return $inboxes;
}
/**
* Get the inbox from the Remote-Profile of a mentioned Actor
*
* @param string $actor The Actor-URL
*
* @return string The Inbox-URL
*/
public static function get_inbox_by_mentioned_actor( $actor ) {
2023-05-31 14:03:46 +02:00
$metadata = get_remote_metadata_by_actor( $actor );
if ( \is_wp_error( $metadata ) ) {
return $metadata;
}
if ( isset( $metadata['endpoints'] ) && isset( $metadata['endpoints']['sharedInbox'] ) ) {
return $metadata['endpoints']['sharedInbox'];
}
if ( \array_key_exists( 'inbox', $metadata ) ) {
return $metadata['inbox'];
}
return new WP_Error( 'activitypub_no_inbox', \__( 'No "Inbox" found', 'activitypub' ), $metadata );
}
/**
* Extract the mentions from the post_content.
*
2023-01-27 16:50:04 +01:00
* @param array $mentions The already found mentions.
* @param string $post_content The post content.
*
* @return mixed The discovered mentions.
*/
public static function extract_mentions( $mentions, $post_content ) {
\preg_match_all( '/@' . ACTIVITYPUB_USERNAME_REGEXP . '/i', $post_content, $matches );
2022-12-09 11:59:24 +01:00
foreach ( $matches[0] as $match ) {
$link = Webfinger::resolve( $match );
2022-12-09 11:59:24 +01:00
if ( ! is_wp_error( $link ) ) {
$mentions[ $match ] = $link;
}
}
return $mentions;
}
}