diff --git a/src/bp-activity/bp-activity-filters.php b/src/bp-activity/bp-activity-filters.php index 82f992a..5dc0d4d 100644 --- a/src/bp-activity/bp-activity-filters.php +++ b/src/bp-activity/bp-activity-filters.php @@ -386,6 +386,8 @@ function bp_activity_make_nofollow_filter( $text ) { /** * Truncate long activity entries when viewed in activity streams. * + * This method can only be used inside the Activity loop. + * * @since BuddyPress (1.5.0) * * @uses bp_is_single_activity() @@ -402,9 +404,20 @@ function bp_activity_make_nofollow_filter( $text ) { function bp_activity_truncate_entry( $text ) { global $activities_template; + /** + * Provides a filter that lets you choose whether to skip this filter on a per-activity basis. + * + * @param bool $maybe_truncate_text If true, text should be checked to see if it needs truncating. + * @since BuddyPress (2.3.0) + */ + $maybe_truncate_text = apply_filters( 'bp_activity_maybe_truncate_entry', + ! in_array( $activities_template->activity->type, array( 'new_blog_post', ), true ) + ); + // The full text of the activity update should always show on the single activity screen - if ( bp_is_single_activity() ) + if ( ! $maybe_truncate_text || bp_is_single_activity() ) { return $text; + } /** * Filters the appended text for the activity excerpt. diff --git a/src/bp-activity/bp-activity-functions.php b/src/bp-activity/bp-activity-functions.php index 756dc03..67c13ec 100644 --- a/src/bp-activity/bp-activity-functions.php +++ b/src/bp-activity/bp-activity-functions.php @@ -1869,20 +1869,15 @@ function bp_activity_post_type_publish( $post_id = 0, $post = null, $user_id = 0 'recorded_time' => $post->post_date_gmt, ); - // Remove large images and replace them with just one image thumbnail. - if ( ! empty( $activity_args['content'] ) ) { - $activity_args['content'] = bp_activity_thumbnail_content_images( $activity_args['content'], $activity_args['primary_link'], $activity_args ); - } - if ( ! empty( $activity_args['content'] ) ) { // Create the excerpt. - $activity_excerpt = bp_create_excerpt( $activity_args['content'] ); + $activity_summary = bp_activity_create_summary( $activity_args['content'], $activity_args ); // Backward compatibility filter for blog posts. if ( 'blogs' == $activity_post_object->component_id ) { - $activity_args['content'] = apply_filters( 'bp_blogs_record_activity_content', $activity_excerpt, $activity_args['content'], $activity_args, $post->post_type ); + $activity_args['content'] = apply_filters( 'bp_blogs_record_activity_content', $activity_summary, $activity_args['content'], $activity_args, $post->post_type ); } else { - $activity_args['content'] = $activity_excerpt; + $activity_args['content'] = $activity_summary; } } @@ -1963,17 +1958,13 @@ function bp_activity_post_type_update( $post = null ) { $activity = new BP_Activity_Activity( $activity_id ); if ( ! empty( $post->post_content ) ) { - // Make sure to update the thumbnail image. - $post_content = bp_activity_thumbnail_content_images( $post->post_content, $activity->primary_link, (array) $activity ); - - // Generate an excerpt. - $activity_excerpt = bp_create_excerpt( $post_content ); + $activity_summary = bp_activity_create_summary( $post->post_content, (array) $activity ); // Backward compatibility filter for the blogs component. if ( 'blogs' == $activity_post_object->component_id ) { - $activity->content = apply_filters( 'bp_blogs_record_activity_content', $activity_excerpt, $post_content, (array) $activity, $post->post_type ); + $activity->content = apply_filters( 'bp_blogs_record_activity_content', $activity_summary, $post->post_content, (array) $activity, $post->post_type ); } else { - $activity->content = $activity_excerpt; + $activity->content = $activity_summary; } } @@ -2585,6 +2576,8 @@ function bp_activity_hide_user_activity( $user_id ) { * through the content, grabs the first image and converts it to a thumbnail, * and removes the rest of the images from the string. * + * As of BuddyPress 2.3, this function is no longer in use. + * * @since BuddyPress (1.2.0) * * @uses esc_attr() @@ -2656,6 +2649,161 @@ function bp_activity_thumbnail_content_images( $content, $link = false, $args = } /** + * Create a rich summary of an activity item for the activity stream. + * + * More than just a simple excerpt, the summary could contain oEmbeds and other types of media. + * Currently, it's only used for blog post items, but it will probably be used for all types of + * activity in the future. + * + * @param string $content The content of the activity item. + * @param array $activity_args The data passed to bp_activity_add() or the values from an Activity obj. + * @return string + * @since BuddyPress (2.3.0) + */ +function bp_activity_create_summary( $content, $activity ) { + $args = array( + 'width' => isset( $GLOBALS['content_width'] ) ? (int) $GLOBALS['content_width'] : 'medium', + ); + + // Get the WP_Post object if this activity type is a blog post. + if ( $activity['type'] === 'new_blog_post' ) { + $content = get_post( $activity['secondary_item_id'] ); + } + + + /** + * Filter the class name of the media extractor when creating an Activity summary. + * + * Use this filter to change the media extractor used to extract media info for the activity item. + * + * @param string $extractor Class name. + * @param string $content The content of the activity item. + * @param array $activity The data passed to bp_activity_add() or the values from an Activity obj. + * @since BuddyPress (2.3.0) + */ + $extractor = apply_filters( 'bp_activity_create_summary_extractor_class', 'BP_Media_Extractor', $content, $activity ); + $extractor = new $extractor; + + /** + * Filter the arguments passed to the media extractor when creating an Activity summary. + * + * @param array $args Array of bespoke data for the media extractor. + * @param string $content The content of the activity item. + * @param array $activity The data passed to bp_activity_add() or the values from an Activity obj. + * @param BP_Media_Extractor $extractor The media extractor object. + * @since BuddyPress (2.3.0) + */ + $args = apply_filters( 'bp_activity_create_summary_extractor_args', $args, $content, $activity, $extractor ); + + + // Extract media information from the $content. + $media = $extractor->extract( $content, BP_Media_Extractor::ALL, $args ); + + // If we converted $content to an object earlier, flip it back to a string. + if ( is_a( $content, 'WP_Post' ) ) { + $content = $content->post_content; + } + + $para_count = substr_count( strtolower( wpautop( $content ) ), '

' ); + $has_audio = ! empty( $media['has']['audio'] ) && $media['has']['audio']; + $has_videos = ! empty( $media['has']['videos'] ) && $media['has']['videos']; + $has_feat_image = ! empty( $media['has']['featured_images'] ) && $media['has']['featured_images']; + $has_galleries = ! empty( $media['has']['galleries'] ) && $media['has']['galleries']; + $has_images = ! empty( $media['has']['images'] ) && $media['has']['images']; + $has_embeds = false; + + // Embeds must be subtracted from the paragraph count. + if ( ! empty( $media['has']['embeds'] ) ) { + $has_embeds = $media['has']['embeds'] > 0; + $para_count -= count( $media['has']['embeds'] ); + } + + $extracted_media = array(); + $use_media_type = ''; + $image_source = ''; + + // If it's a short article and there's an embed/audio/video, use it. + if ( $para_count <= 3 ) { + if ( $has_embeds ) { + $use_media_type = 'embeds'; + } elseif ( $has_audio ) { + $use_media_type = 'audio'; + } elseif ( $has_videos ) { + $use_media_type = 'videos'; + } + } + + // If not, or in any other situation, try to use an image. + if ( ! $use_media_type && $has_images ) { + $use_media_type = 'images'; + $image_source = 'html'; + + // Featured Image > Galleries > inline . + if ( $has_feat_image ) { + $image_source = 'featured_images'; + + } elseif ( $has_galleries ) { + $image_source = 'galleries'; + } + } + + // Extract an item from the $media results. + if ( $use_media_type ) { + if ( $use_media_type === 'images' ) { + $extracted_media = wp_list_filter( $media[ $use_media_type ], array( 'source' => $image_source ) ); + $extracted_media = array_shift( $extracted_media ); + } else { + $extracted_media = array_shift( $media[ $use_media_type ] ); + } + + /** + * Filter the results of the media extractor when creating an Activity summary. + * + * @param array $extracted_media Extracted media item. See {@link BP_Media_Extractor::extract()} for format. + * @param string $content Content of the activity item. + * @param array $activity The data passed to bp_activity_add() or the values from an Activity obj. + * @param array $media All results from the media extraction. See {@link BP_Media_Extractor::extract()} for format. + * @param string $use_media_type The kind of media item that was preferentially extracted. + * @param string $image_source If $use_media_type was "images", the preferential source of the image. + * Otherwise empty. + * @since BuddyPress (2.3.0) + */ + $extracted_media = apply_filters( + 'bp_activity_create_summary_extractor_result', + $extracted_media, + $content, + $activity, + $media, + $use_media_type, + $image_source + ); + } + + // Generate a text excerpt for this activity item (and remove any oEmbeds URLs). + $summary = strip_shortcodes( html_entity_decode( strip_tags( $content ) ) ); + $summary = bp_create_excerpt( preg_replace( '#^\s*(https?://[^\s"]+)\s*$#im', '', $summary ) ); + + if ( $use_media_type === 'embeds' ) { + $summary .= PHP_EOL . PHP_EOL . $extracted_media['url']; + } elseif ( $use_media_type === 'images' ) { + $summary .= sprintf( ' ', esc_url( $extracted_media['url'] ) ); + } elseif ( in_array( $use_media_type, array( 'audio', 'videos' ), true ) ) { + $summary .= PHP_EOL . PHP_EOL . $extracted_media['original']; // Full shortcode. + } + + /** + * Filters the newly-generated summary for the activity item. + * + * @param string $summary Activity summary HTML. + * @param string $content $content Content of the activity item. + * @param array $activity The data passed to bp_activity_add() or the values from an Activity obj. + * @param array $extracted_media Media item extracted. See {@link BP_Media_Extractor::extract()} for format. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_activity_create_summary', $summary, $content, $activity, $extracted_media ); +} + +/** * Fetch whether the current user is allowed to mark items as spam. * * @since BuddyPress (1.6.0) diff --git a/src/bp-blogs/bp-blogs-activity.php b/src/bp-blogs/bp-blogs-activity.php index 422e149..c9b3115 100644 --- a/src/bp-blogs/bp-blogs-activity.php +++ b/src/bp-blogs/bp-blogs-activity.php @@ -352,11 +352,6 @@ function bp_blogs_record_activity( $args = '' ) { $r = wp_parse_args( $args, $defaults ); - // Remove large images and replace them with just one image thumbnail - if ( ! empty( $r['content'] ) ) { - $r['content'] = bp_activity_thumbnail_content_images( $r['content'], $r['primary_link'], $r ); - } - if ( ! empty( $r['action'] ) ) { /** @@ -376,11 +371,11 @@ function bp_blogs_record_activity( $args = '' ) { * * @since BuddyPress (1.2.0) * - * @param string $value Generated excerpt from content for the activity stream. + * @param string $value Generated summary from content for the activity stream. * @param string $value Content for the activity stream. * @param array $r Array of arguments used for the activity stream item. */ - $r['content'] = apply_filters( 'bp_blogs_record_activity_content', bp_create_excerpt( $r['content'] ), $r['content'], $r ); + $r['content'] = apply_filters( 'bp_blogs_record_activity_content', bp_activity_create_summary( $r['content'], $r ), $r['content'], $r ); } // Check for an existing entry and update if one exists. diff --git a/src/bp-core/bp-core-classes.php b/src/bp-core/bp-core-classes.php index b50325d..70d9084 100644 --- a/src/bp-core/bp-core-classes.php +++ b/src/bp-core/bp-core-classes.php @@ -20,3 +20,4 @@ require dirname( __FILE__ ) . '/classes/class-bp-walker-nav-menu-checklist.php'; require dirname( __FILE__ ) . '/classes/class-bp-suggestions.php'; require dirname( __FILE__ ) . '/classes/class-bp-members-suggestions.php'; require dirname( __FILE__ ) . '/classes/class-bp-recursive-query.php'; +require dirname( __FILE__ ) . '/classes/class-bp-media-extractor.php'; diff --git a/src/bp-core/classes/class-bp-media-extractor.php b/src/bp-core/classes/class-bp-media-extractor.php new file mode 100644 index 0000000..ab40585 --- /dev/null +++ b/src/bp-core/classes/class-bp-media-extractor.php @@ -0,0 +1,901 @@ + + * Mentions: @name + * If the Activity component is enabled, we use it to parse out any @names. A consequence + * to note is that the "name" mentioned must match a real user account. If it's a made-up + * @name, then it isn't extracted. + * If the Activity component is disabled, any @name is extracted (both those matching + * real accounts, and those made-up). + * Images: , [gallery], [gallery ids="2,3"], featured images (Post thumbnails). + * If an extracted image is in the Media Library, then its resolution will be included. + * Shortcodes: Extract information about any (registered) shortcodes. + * This includes any shortcodes indirectly covered by any of the other media extraction types. + * For example, [gallery]. + * Embeds: Extract any URL matching a registered oEmbed handler. + * Audio: , [audio] + * See wp_get_audio_extensions() for supported audio formats. + * Video: [video] + * See wp_get_video_extensions() for supported video formats. + * + * @see BP_Media_Extractor::extract() Use this to extract media. + * @since BuddyPress (2.3.0) + */ +class BP_Media_Extractor { + /** + * Media type. + * + * @since BuddyPress (2.3.0) + * @var int + */ + const ALL = 255; + const LINKS = 1; + const MENTIONS = 2; + const IMAGES = 4; + const SHORTCODES = 8; + const EMBEDS = 16; + const AUDIO = 32; + const VIDEOS = 64; + + + /** + * Extract media from text. + * + * @param string|WP_Post $richtext Content to parse. + * @param int $what_to_extract Media type to extract (optional). + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $audio + * @type int $embeds + * @type int $images + * @type int $links + * @type int $mentions + * @type int $shortcodes + * @type int $video + * } + * @type array $audio Extracted audio. { + * Array of extracted media. + * + * @type string $source Media source. Either "html" or "shortcodes". + * @type string $url Link to audio. + * } + * @type array $embeds Extracted oEmbeds. { + * Array of extracted media. + * + * @type string $url oEmbed link. + * } + * @type array $images Extracted images. { + * Array of extracted media. + * + * @type int $gallery_id Gallery ID. Optional, not always set. + * @type int $height Width of image. If unknown, set to 0. + * @type string $source Media source. Either "html" or "galleries". + * @type string $url Link to image. + * @type int $width Width of image. If unknown, set to 0. + * } + * @type array $links Extracted URLs. { + * Array of extracted media. + * + * @type string $url Link. + * } + * @type array $mentions Extracted mentions. { + * Array of extracted media. + * + * @type string $name @mention. + * @type string $user_id User ID. Optional, only set if Activity component enabled. + * } + * @type array $shortcodes Extracted shortcodes. { + * Array of extracted media. + * + * @type array $attributes Key/value pairs of the shortcodes attributes (if any). + * @type string $content Text wrapped by the shortcode. + * @type string $type Shortcode type. + * @type string $original The entire shortcode. + * } + * @type array $videos Extracted video. { + * Array of extracted media. + * + * @type string $source Media source. Currently only "shortcodes". + * @type string $url Link to audio. + * } + * } + * @since BuddyPress (2.3.0) + */ + public function extract( $richtext, $what_to_extract = self::ALL, $extra_args = array() ) { + $media = array(); + + // Support passing a WordPress Post for the $richtext parameter. + if ( is_a( $richtext, 'WP_Post' ) ) { + $extra_args['post'] = $richtext; + $richtext = $extra_args['post']->post_content; + } + + $plaintext = $this->strip_markup( $richtext ); + + + // Extract links. + if ( self::LINKS & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_links( $richtext, $plaintext, $extra_args ) ); + } + + // Extract mentions. + if ( self::MENTIONS & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_mentions( $richtext, $plaintext, $extra_args ) ); + } + + // Extract images. + if ( self::IMAGES & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_images( $richtext, $plaintext, $extra_args ) ); + } + + // Extract shortcodes. + if ( self::SHORTCODES & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_shortcodes( $richtext, $plaintext, $extra_args ) ); + } + + // Extract oEmbeds. + if ( self::EMBEDS & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_embeds( $richtext, $plaintext, $extra_args ) ); + } + + // Extract audio. + if ( self::AUDIO & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_audio( $richtext, $plaintext, $extra_args ) ); + } + + // Extract video. + if ( self::VIDEOS & $what_to_extract ) { + $media = array_merge_recursive( $media, $this->extract_video( $richtext, $plaintext, $extra_args ) ); + } + + /** + * Filters media extracted from text. + * + * @param array $media Extracted media. See {@link BP_Media_Extractor::extract()} for format. + * @param string $richtext Content to parse. + * @param int $what_to_extract Media type to extract. + * @param array $extra_args Bespoke data for a particular extractor. + * @param string $plaintext Copy of $richtext without any markup. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_extract', $media, $richtext, $what_to_extract, $extra_args, $plaintext ); + } + + + /** + * Content type specific extraction methods. + * + * You shouldn't need to use these directly; just use {@link BP_Media_Extractor::extract()}. + */ + + /** + * Extract `` tags from text. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $links + * } + * @type array $links Extracted URLs. { + * Array of extracted media. + * + * @type string $url Link. + * } + * } + * @since BuddyPress (2.3.0) + */ + protected function extract_links( $richtext, $plaintext, $extra_args = array() ) { + $data = array( 'has' => array( 'links' => 0 ), 'links' => array() ); + + // Matches: href="text" and href='text' + if ( stripos( $richtext, 'href=' ) !== false ) { + preg_match_all( '#href=(["\'])([^"\']+)\1#i', $richtext, $matches ); + + if ( ! empty( $matches[2] ) ) { + $matches[2] = array_unique( $matches[2] ); + + foreach ( $matches[2] as $link_src ) { + $link_src = esc_url_raw( $link_src ); + + if ( $link_src ) { + $data['links'][] = array( 'url' => $link_src ); + } + } + } + } + + $data['has']['links'] = count( $data['links'] ); + + /** + * Filters links extracted from text. + * + * @param array $data Extracted links. See {@link BP_Media_Extractor::extract_links()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_links', $data, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract @mentions tags from text. + * + * If the Activity component is enabled, it is used to parse @mentions. + * The mentioned "name" must match a user account, otherwise it is discarded. + * + * If the Activity component is disabled, any @mentions are extracted. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor. + * @return array { + * @type array $has Extracted media counts. { + * @type int $mentions + * } + * @type array $mentions Extracted mentions. { + * Array of extracted media. + * + * @type string $name @mention. + * @type string $user_id User ID. Optional, only set if Activity component enabled. + * } + * } + * @since BuddyPress (2.3.0) + */ + protected function extract_mentions( $richtext, $plaintext, $extra_args = array() ) { + $data = array( 'has' => array( 'mentions' => 0 ), 'mentions' => array() ); + $mentions = array(); + + // If the Activity component is active, use it to parse @mentions. + if ( bp_is_active( 'activity' ) ) { + $mentions = bp_activity_find_mentions( $plaintext ); + if ( ! $mentions ) { + $mentions = array(); + } + + // If the Activity component is disabled, instead do a basic parse. + } else { + if ( strpos( $plaintext, '@' ) !== false ) { + preg_match_all( '/[@]+([A-Za-z0-9-_\.@]+)\b/', $plaintext, $matches ); + + if ( ! empty( $matches[1] ) ) { + $mentions = array_unique( array_map( 'strtolower', $matches[1] ) ); + } + } + } + + // Build results + foreach ( $mentions as $user_id => $mention_name ) { + $mention = array( 'name' => strtolower( $mention_name ) ); + + // If the Activity component is active, store the User ID, too. + if ( bp_is_active( 'activity' ) ) { + $mention['user_id'] = (int) $user_id; + } + + $data['mentions'][] = $mention; + } + + $data['has']['mentions'] = count( $data['mentions'] ); + + /** + * Filters @mentions extracted from text. + * + * @param array $data Extracted @mentions. See {@link BP_Media_Extractor::extract_mentions()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_mentions', $data, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract images from `` tags, [galleries], and featured images from a Post. + * + * If an image is in the Media Library, then its resolution is included in the results. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $images + * } + * @type array $images Extracted images. { + * Array of extracted media. + * + * @type int $gallery_id Gallery ID. Optional, not always set. + * @type int $height Width of image. If unknown, set to 0. + * @type string $source Media source. Either "html" or "galleries". + * @type string $url Link to image. + * @type int $width Width of image. If unknown, set to 0. + * } + * } + * @since BuddyPress (2.3.0) + */ + protected function extract_images( $richtext, $plaintext, $extra_args = array() ) { + $media = array( 'has' => array( 'images' => 0 ), 'images' => array() ); + + $featured_image = $this->extract_images_from_featured_images( $richtext, $plaintext, $extra_args ); + $galleries = $this->extract_images_from_galleries( $richtext, $plaintext, $extra_args ); + + + // `` tags. + if ( stripos( $richtext, 'src=' ) !== false ) { + preg_match_all( '#src=(["\'])([^"\']+)\1#i', $richtext, $img_srcs ); // matches src="text" and src='text' + + // . + if ( ! empty( $img_srcs[2] ) ) { + $img_srcs[2] = array_unique( $img_srcs[2] ); + + foreach ( $img_srcs[2] as $image_src ) { + // Skip data URIs. + if ( strtolower( substr( $image_src, 0, 5 ) ) === 'data:' ) { + continue; + } + + $image_src = esc_url_raw( $image_src ); + if ( ! $image_src ) { + continue; + } + + $media['images'][] = array( + 'source' => 'html', + 'url' => $image_src, + + // The image resolution isn't available, but we need to set the keys anyway. + 'height' => 0, + 'width' => 0, + ); + } + } + } + + // Galleries. + if ( ! empty( $galleries ) ) { + foreach ( $galleries as $gallery ) { + foreach ( $gallery as $image ) { + $image_url = esc_url_raw( $image['url'] ); + if ( ! $image_url ) { + continue; + } + + $media['images'][] = array( + 'gallery_id' => $image['gallery_id'], + 'source' => 'galleries', + 'url' => $image_url, + 'width' => $image['width'], + 'height' => $image['height'], + ); + } + } + + $media['has']['galleries'] = count( $galleries ); + } + + // Featured images (aka thumbnails). + if ( ! empty( $featured_image ) ) { + $image_url = esc_url_raw( $featured_image[0] ); + + if ( $image_url ) { + $media['images'][] = array( + 'source' => 'featured_images', + 'url' => $image_url, + 'width' => $featured_image[1], + 'height' => $featured_image[2], + ); + + $media['has']['featured_images'] = 1; + } + } + + // Update image count. + $media['has']['images'] = count( $media['images'] ); + + + /** + * Filters images extracted from text. + * + * @param array $media Extracted images. See {@link BP_Media_Extractor::extract_images()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_images', $media, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract shortcodes from text. + * + * This includes any shortcodes indirectly used by other media extraction types. + * For example, [gallery] and [audio]. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $shortcodes + * } + * @type array $shortcodes Extracted shortcodes. { + * Array of extracted media. + * + * @type array $attributes Key/value pairs of the shortcodes attributes (if any). + * @type string $content Text wrapped by the shortcode. + * @type string $type Shortcode type. + * @type string $original The entire shortcode. + * } + * } + * @since BuddyPress (2.3.0) + */ + protected function extract_shortcodes( $richtext, $plaintext, $extra_args = array() ) { + $data = array( 'has' => array( 'shortcodes' => 0 ), 'shortcodes' => array() ); + + // Match any registered WordPress shortcodes. + if ( strpos( $richtext, '[' ) !== false ) { + preg_match_all( '/' . get_shortcode_regex() . '/s', $richtext, $matches ); + + if ( ! empty( $matches[2] ) ) { + foreach ( $matches[2] as $i => $shortcode_name ) { + $attrs = shortcode_parse_atts( $matches[3][ $i ] ); + $attrs = ( ! $attrs ) ? array() : $attrs; + + $shortcode = array(); + $shortcode['attributes'] = $attrs; // Attributes + $shortcode['content'] = $matches[5][ $i ]; // Content + $shortcode['type'] = $shortcode_name; // Shortcode + $shortcode['original'] = $matches[0][ $i ]; // Entire shortcode + + $data['shortcodes'][] = $shortcode; + } + } + } + + $data['has']['shortcodes'] = count( $data['shortcodes'] ); + + /** + * Filters shortcodes extracted from text. + * + * @param array $data Extracted shortcodes. See {@link BP_Media_Extractor::extract_shortcodes()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_shortcodes', $data, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract any URL, matching a registered oEmbed endpoint, from text. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $embeds + * } + * @type array $embeds Extracted oEmbeds. { + * Array of extracted media. + * + * @type string $url oEmbed link. + * } + * } + * @since BuddyPress (2.3.0) + */ + protected function extract_embeds( $richtext, $plaintext, $extra_args = array() ) { + $data = array( 'has' => array( 'embeds' => 0 ), 'embeds' => array() ); + $embeds = array(); + + if ( ! function_exists( '_wp_oembed_get_object' ) ) { + require( ABSPATH . WPINC . '/class-oembed.php' ); + } + + + // Matches any links on their own lines. They may be oEmbeds. + if ( stripos( $richtext, 'http' ) !== false ) { + preg_match_all( '#^\s*(https?://[^\s"]+)\s*$#im', $richtext, $matches ); + + if ( ! empty( $matches[1] ) ) { + $matches[1] = array_unique( $matches[1] ); + $oembed = _wp_oembed_get_object(); + + foreach ( $matches[1] as $link ) { + // Skip data URIs. + if ( strtolower( substr( $link, 0, 5 ) ) === 'data:' ) { + continue; + } + + foreach ( $oembed->providers as $matchmask => $oembed_data ) { + list( , $is_regex ) = $oembed_data; + + // Turn asterisk-type provider URLs into regexs. + if ( ! $is_regex ) { + $matchmask = '#' . str_replace( '___wildcard___', '(.+)', preg_quote( str_replace( '*', '___wildcard___', $matchmask ), '#' ) ) . '#i'; + $matchmask = preg_replace( '|^#http\\\://|', '#https?\://', $matchmask ); + } + + // Check whether this "link" is really an oEmbed. + if ( preg_match( $matchmask, $link ) ) { + $data['embeds'][] = array( 'url' => $link ); + + break; + } + } + } + } + } + + $data['has']['embeds'] = count( $data['embeds'] ); + + /** + * Filters embeds extracted from text. + * + * @param array $data Extracted embeds. See {@link BP_Media_Extractor::extract_embeds()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_embeds', $data, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract [audio] shortcodes and `` tags, from text. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $audio + * } + * @type array $audio Extracted audio. { + * Array of extracted media. + * + * @type string $original The entire shortcode. + * @type string $source Media source. Either "html" or "shortcodes". + * @type string $url Link to audio. + * } + * } + * @see wp_get_audio_extensions() for supported audio formats. + * @since BuddyPress (2.3.0) + */ + protected function extract_audio( $richtext, $plaintext, $extra_args = array() ) { + $data = array( 'has' => array( 'audio' => 0 ), 'audio' => array() ); + $audios = $this->extract_shortcodes( $richtext, $plaintext, $extra_args ); + $links = $this->extract_links( $richtext, $plaintext, $extra_args ); + + $audio_types = wp_get_audio_extensions(); + + + // [audio] + $audios = wp_list_filter( $audios['shortcodes'], array( 'type' => 'audio' ) ); + foreach ( $audios as $audio ) { + + // Media URL can appear as the first parameter inside the shortcode brackets. + if ( isset( $audio['attributes']['src'] ) ) { + $src_param = 'src'; + } elseif ( isset( $audio['attributes'][0] ) ) { + $src_param = 0; + } else { + continue; + } + + $path = untrailingslashit( parse_url( $audio['attributes'][ $src_param ], PHP_URL_PATH ) ); + + foreach ( $audio_types as $extension ) { + $extension = '.' . $extension; + + // Check this URL's file extension matches that of an accepted audio format. + if ( ! $path || substr( $path, -4 ) !== $extension ) { + continue; + } + + $data['audio'][] = array( + 'original' => '[audio src="' . esc_url_raw( $audio['attributes'][ $src_param ] ) . '"]', + 'source' => 'shortcodes', + 'url' => esc_url_raw( $audio['attributes'][ $src_param ] ), + ); + } + } + + // tags + foreach ( $audio_types as $extension ) { + $extension = '.' . $extension; + + foreach ( $links['links'] as $link ) { + $path = untrailingslashit( parse_url( $link['url'], PHP_URL_PATH ) ); + + // Check this URL's file extension matches that of an accepted audio format. + if ( ! $path || substr( $path, -4 ) !== $extension ) { + continue; + } + + $data['audio'][] = array( + 'original' => '[audio src="' . esc_url_raw( $link['url'] ) . '"]', // Build an audio shortcode. + 'source' => 'html', + 'url' => esc_url_raw( $link['url'] ), + ); + } + } + + $data['has']['audio'] = count( $data['audio'] ); + + /** + * Filters audio extracted from text. + * + * @param array $data Extracted audio. See {@link BP_Media_Extractor::extract_audio()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_audio', $data, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract [video] shortcodes from text. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array { + * @type array $has Extracted media counts. { + * @type int $video + * } + * @type array $videos Extracted video. { + * Array of extracted media. + * + * @type string $source Media source. Currently only "shortcodes". + * @type string $url Link to audio. + * } + * } + * @see wp_get_video_extensions() for supported video formats. + * @since BuddyPress (2.3.0) + */ + protected function extract_video( $richtext, $plaintext, $extra_args = array() ) { + $data = array( 'has' => array( 'videos' => 0 ), 'videos' => array() ); + $videos = $this->extract_shortcodes( $richtext, $plaintext, $extra_args ); + + $video_types = wp_get_video_extensions(); + + + // [video] + $videos = wp_list_filter( $videos['shortcodes'], array( 'type' => 'video' ) ); + foreach ( $videos as $video ) { + + // Media URL can appear as the first parameter inside the shortcode brackets. + if ( isset( $video['attributes']['src'] ) ) { + $src_param = 'src'; + } elseif ( isset( $video['attributes'][0] ) ) { + $src_param = 0; + } else { + continue; + } + + $path = untrailingslashit( parse_url( $video['attributes'][ $src_param ], PHP_URL_PATH ) ); + + foreach ( $video_types as $extension ) { + $extension = '.' . $extension; + + // Check this URL's file extension matches that of an accepted video format (-5 for webm). + if ( ! $path || ( substr( $path, -4 ) !== $extension && substr( $path, -5 ) !== $extension ) ) { + continue; + } + + $data['videos'][] = array( + 'original' => $video['original'], // Entire shortcode. + 'source' => 'shortcodes', + 'url' => esc_url_raw( $video['attributes'][ $src_param ] ), + ); + } + } + + $data['has']['videos'] = count( $data['videos'] ); + + /** + * Filters videos extracted from text. + * + * @param array $data Extracted videos. See {@link BP_Media_Extractor::extract_videos()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_videos', $data, $richtext, $plaintext, $extra_args ); + } + + + /** + * Helpers and utility methods. + */ + + /** + * Extract images in [galleries] shortcodes from text. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Bespoke data for a particular extractor (optional). + * @return array + * @since BuddyPress (2.3.0) + */ + protected function extract_images_from_galleries( $richtext, $plaintext, $extra_args = array() ) { + if ( ! isset( $extra_args['post'] ) || ! is_a( $extra_args['post'], 'WP_Post' ) ) { + $post = new WP_Post( (object) array( 'post_content' => $richtext ) ); + } else { + $post = $extra_args['post']; + } + + // We're not using get_post_galleries_images() because it returns thumbnails; we want the original image. + $galleries = get_post_galleries( $post, false ); + $galleries_data = array(); + + if ( ! empty( $galleries ) ) { + // Validate the size of the images requested. + if ( isset( $extra_args['width'] ) ) { + + // A width was specified but not a height, so calculate it assuming a 4:3 ratio. + if ( ! isset( $extra_args['height'] ) && ctype_digit( $extra_args['width'] ) ) { + $extra_args['height'] = round( ( $extra_args['width'] / 4 ) * 3 ); + } + + if ( ctype_digit( $extra_args['width'] ) ) { + $image_size = array( $extra_args['width'], $extra_args['height'] ); + } else { + $image_size = $extra_args['width']; // e.g. "thumb", "medium". + } + + } else { + $image_size = 'full'; + } + + /** + * There are two variants of gallery shortcode. + * + * One kind specifies the image (post) IDs via an `ids` parameter. + * The other gets the image IDs from post_type=attachment and post_parent=get_the_ID(). + */ + + foreach ( $galleries as $gallery_id => $gallery ) { + $data = array(); + $images = array(); + + // Gallery ids= variant. + if ( isset( $gallery['ids'] ) ) { + $images = wp_parse_id_list( $gallery['ids'] ); + + // Gallery post_parent variant. + } elseif ( isset( $extra_args['post'] ) ) { + $images = wp_parse_id_list( + get_children( array( + 'fields' => 'ids', + 'order' => 'ASC', + 'orderby' => 'menu_order ID', + 'post_mime_type' => 'image', + 'post_parent' => $extra_args['post']->ID, + 'post_status' => 'inherit', + 'post_type' => 'attachment', + ) ) + ); + } + + // Extract the data we need from each image in this gallery. + foreach ( $images as $image_id ) { + $image = wp_get_attachment_image_src( $image_id, $image_size ); + $data[] = array( + 'url' => $image[0], + 'width' => $image[1], + 'height' => $image[2], + + 'gallery_id' => 1 + $gallery_id, + ); + } + + $galleries_data[] = $data; + } + } + + /** + * Filters image galleries extracted from text. + * + * @param array $galleries_data Galleries. See {@link BP_Media_Extractor::extract_images_from_galleries()}. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_galleries', $galleries_data, $richtext, $plaintext, $extra_args ); + } + + /** + * Extract the featured image from a Post. + * + * @param string $richtext Content to parse. + * @param string $plaintext Sanitized version of the content. + * @param array $extra_args Contains data that an implementation might need beyond the defaults. + * @return array + * @since BuddyPress (2.3.0) + */ + protected function extract_images_from_featured_images( $richtext, $plaintext, $extra_args ) { + $image = array(); + $thumb = 0; + + if ( isset( $extra_args['post'] ) ) { + $thumb = (int) get_post_thumbnail_id( $extra_args['post']->ID ); + } + + if ( $thumb ) { + // Validate the size of the images requested. + if ( isset( $extra_args['width'] ) ) { + if ( ! isset( $extra_args['height'] ) && ctype_digit( $extra_args['width'] ) ) { + // A width was specified but not a height, so calculate it assuming a 4:3 ratio. + $extra_args['height'] = round( ( $extra_args['width'] / 4 ) * 3 ); + } + + if ( ctype_digit( $extra_args['width'] ) ) { + $image_size = array( $extra_args['width'], $extra_args['height'] ); + } else { + $image_size = $extra_args['width']; // e.g. "thumb", "medium". + } + } else { + $image_size = 'full'; + } + + $image = wp_get_attachment_image_src( $thumb, $image_size ); + } + + /** + * Filters featured images extracted from a WordPress Post. + * + * @param array $image Extracted images. See {@link BP_Media_Extractor_Post::extract_images()} for format. + * @param string $richtext Content to parse. + * @param string $plaintext Copy of $richtext without any markup. + * @param array $extra_args Bespoke data for a particular extractor. + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_featured_images', $image, $richtext, $plaintext, $extra_args ); + } + + /** + * Sanitize and format raw content to prepare for content extraction. + * + * HTML tags and shortcodes are removed, and HTML entities are decoded. + * + * @param string $richtext + * @return string + * @since BuddyPress (2.3.0) + */ + protected function strip_markup( $richtext ) { + $plaintext = strip_shortcodes( html_entity_decode( strip_tags( $richtext ) ) ); + + /** + * Filters the generated plain text version of the content passed to the extractor. + * + * @param array $plaintext Generated plain text. + * @param string $richtext Original content + * @since BuddyPress (2.3.0) + */ + return apply_filters( 'bp_media_extractor_strip_markup', $plaintext, $richtext ); + } +} \ No newline at end of file diff --git a/tests/phpunit/testcases/core/class-bp-media-extractor.php b/tests/phpunit/testcases/core/class-bp-media-extractor.php new file mode 100644 index 0000000..f791abf --- /dev/null +++ b/tests/phpunit/testcases/core/class-bp-media-extractor.php @@ -0,0 +1,506 @@ +Testing a regular link. + But we should throw in some markup and maybe even an . + . + It definitely does not like data URIs. @ + + The parser only extracts wp_allowed_protocols() protocols, not something like phone. + + [caption id='example']Here is a caption shortcode.[/caption] + + There are two types of [gallery] shortcodes; one like that, and another with IDs specified. + + Audio shortcodes: + [audio src='http://example.com/source.mp3'] + [audio src='http://example.com/source.wav' loop='on' autoplay='off' preload='metadata']. + + The following shortcode should be picked up by the shortcode extractor, but not the audio extractor, because + it has an unrecognised file extension (for an audio file). [audio src='http://example.com/not_audio.gif'] + This should be picked up, too. + + Video shortcodes: + [video src='http://example.com/source.ogv'] + [video src='http://example.com/source.webm' loop='on' autoplay='off' preload='metadata'] + + The following shortcode should be picked up by the shortcode extractor, but not the video extractor, because + it has an unrecognised file extension (for a video file). [video src='http://example.com/not_video.mp3'] + "; + } + + public function setUp() { + parent::setUp(); + + $this->factory->user->create( array( 'user_login' => 'paulgibbs' ) ); + } + + public function tearDown() { + parent::tearDown(); + + $this->remove_added_uploads(); + } + + + /** + * General. + */ + + public function test_check_media_extraction_return_types() { + $media = self::$media_extractor->extract( self::$richtext ); + + foreach ( array( 'has', 'embeds', 'images', 'links', 'mentions', 'shortcodes', 'audio' ) as $key ) { + $this->assertArrayHasKey( $key, $media ); + $this->assertInternalType( 'array', $media[ $key ] ); + } + + foreach ( $media['has'] as $item ) { + $this->assertInternalType( 'int', $item ); + } + + foreach ( $media['links'] as $item ) { + $this->assertArrayHasKey( 'url', $item ); + $this->assertInternalType( 'string', $item['url'] ); + $this->assertNotEmpty( $item['url'] ); + } + + foreach ( $media['mentions'] as $item ) { + $this->assertArrayHasKey( 'name', $item ); + $this->assertInternalType( 'string', $item['name'] ); + $this->assertNotEmpty( $item['name'] ); + } + + foreach ( $media['images'] as $item ) { + $this->assertArrayHasKey( 'height', $item ); + $this->assertInternalType( 'int', $item['height'] ); + + $this->assertArrayHasKey( 'width', $item ); + $this->assertInternalType( 'int', $item['width'] ); + + $this->assertArrayHasKey( 'source', $item ); + $this->assertInternalType( 'string', $item['source'] ); + $this->assertNotEmpty( $item['source'] ); + + $this->assertArrayHasKey( 'url', $item ); + $this->assertInternalType( 'string', $item['url'] ); + $this->assertNotEmpty( $item['url'] ); + } + + foreach ( $media['shortcodes'] as $shortcode_type => $item ) { + $this->assertArrayHasKey( 'attributes', $item ); + $this->assertInternalType( 'array', $item['attributes'] ); + + $this->assertArrayHasKey( 'content', $item ); + $this->assertInternalType( 'string', $item['content'] ); + + $this->assertArrayHasKey( 'type', $item ); + $this->assertInternalType( 'string', $item['type'] ); + + $this->assertArrayHasKey( 'original', $item ); + $this->assertInternalType( 'string', $item['original'] ); + } + + foreach ( $media['embeds'] as $item ) { + $this->assertArrayHasKey( 'url', $item ); + $this->assertInternalType( 'string', $item['url'] ); + $this->assertNotEmpty( $item['url'] ); + } + + foreach ( $media['audio'] as $item ) { + $this->assertArrayHasKey( 'url', $item ); + $this->assertInternalType( 'string', $item['url'] ); + $this->assertNotEmpty( $item['url'] ); + + $this->assertArrayHasKey( 'source', $item ); + $this->assertInternalType( 'string', $item['source'] ); + $this->assertNotEmpty( $item['source'] ); + } + } + + public function test_check_media_extraction_counts_are_correct() { + $media = self::$media_extractor->extract( self::$richtext ); + $types = array_keys( $media ); + + foreach ( $types as $type ) { + if ( $type === 'has' ) { + continue; + } + + $this->assertArrayHasKey( $type, $media['has'] ); + $this->assertSame( count( $media[ $type ] ), $media['has'][ $type ], "Difference with the 'has' count for {$type}." ); + } + } + + + public function test_extract_multiple_media_types_from_content() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::LINKS | BP_Media_Extractor::MENTIONS ); + + $this->assertNotEmpty( $media['links'] ); + $this->assertNotEmpty( $media['mentions'] ); + $this->assertArrayNotHasKey( 'shortcodes', $media ); + } + + public function test_extract_media_from_a_wp_post() { + $post_id = $this->factory->post->create( array( 'post_content' => self::$richtext ) ); + $media = self::$media_extractor->extract( get_post( $post_id ), BP_Media_Extractor::LINKS ); + + $this->assertArrayHasKey( 'links', $media ); + $this->assertSame( 'https://example.com', $media['links'][0]['url'] ); + $this->assertSame( 'http://example.com', $media['links'][1]['url'] ); + } + + + /** + * Link extraction. + */ + + public function test_extract_links_from_content() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::LINKS ); + + $this->assertArrayHasKey( 'links', $media ); + $this->assertSame( 'https://example.com', $media['links'][0]['url'] ); + $this->assertSame( 'http://example.com', $media['links'][1]['url'] ); + } + + public function test_extract_no_links_from_content_with_invalid_links() { + $richtext = "This is some sample text, with links, but not the kinds we want. + Empty links should be ignore and + weird protocols should be ignored, too. + "; + + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::LINKS ); + $this->assertSame( 0, $media['has']['links'] ); + } + + + /** + * at-mentions extraction. + */ + + public function test_extract_mentions_from_content_with_activity_enabled() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::MENTIONS ); + + $this->assertArrayHasKey( 'user_id', $media['mentions'][0] ); + $this->assertSame( 'paulgibbs', $media['mentions'][0]['name'] ); + } + + public function test_extract_mentions_from_content_with_activity_disabled() { + $was_activity_enabled = false; + + // Turn activity off. + if ( isset( buddypress()->active_components['activity'] ) ) { + unset( buddypress()->active_components['activity'] ); + $was_activity_enabled = true; + } + + + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::MENTIONS ); + + $this->assertArrayNotHasKey( 'user_id', $media['mentions'][0] ); + $this->assertSame( 'paulgibbs', $media['mentions'][0]['name'] ); + + + // Turn activity on. + if ( $was_activity_enabled ) { + buddypress()->active_components['activity'] = 1; + } + } + + + /** + * Shortcodes extraction. + */ + + public function test_extract_shortcodes_from_content() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::SHORTCODES ); + + $this->assertArrayHasKey( 'shortcodes', $media ); + + $this->assertSame( 'caption', $media['shortcodes'][0]['type'] ); + $this->assertSame( 'Here is a caption shortcode.', $media['shortcodes'][0]['content'] ); + $this->assertSame( 'example', $media['shortcodes'][0]['attributes']['id'] ); + + $this->assertSame( 'gallery', $media['shortcodes'][1]['type'] ); + $this->assertEmpty( $media['shortcodes'][1]['content'] ); + + $this->assertSame( 'audio', $media['shortcodes'][2]['type'] ); + $this->assertEmpty( $media['shortcodes'][2]['content'] ); + $this->assertSame( 'http://example.com/source.mp3', $media['shortcodes'][2]['attributes']['src'] ); + + $this->assertSame( 'audio', $media['shortcodes'][3]['type'] ); + $this->assertEmpty( $media['shortcodes'][3]['content'] ); + $this->assertSame( 'http://example.com/source.wav', $media['shortcodes'][3]['attributes']['src'] ); + $this->assertSame( 'on', $media['shortcodes'][3]['attributes']['loop'] ); + $this->assertSame( 'off', $media['shortcodes'][3]['attributes']['autoplay'] ); + $this->assertSame( 'metadata', $media['shortcodes'][3]['attributes']['preload'] ); + } + + public function test_extract_no_shortcodes_from_content_with_unregistered_shortcodes() { + $richtext = 'This sample text has some made-up [fake]shortcodes[/fake].'; + + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::SHORTCODES ); + $this->assertSame( 0, $media['has']['shortcodes'] ); + } + + + /** + * oEmbeds extraction. + */ + + public function test_extract_oembeds_from_content() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::EMBEDS ); + + $this->assertArrayHasKey( 'embeds', $media ); + $this->assertSame( 'https://www.youtube.com/watch?v=2mjvfnUAfyo', $media['embeds'][0]['url'] ); + $this->assertSame( 'http://www.youtube.com/watch?v=KaOC9danxNo', $media['embeds'][1]['url'] ); + } + + + /** + * Images extraction (src tags). + */ + + // both quote styles + public function test_extract_images_from_content_with_src_tags() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::IMAGES ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'html' ) ) ); + + $this->assertSame( 'http://example.com/image.gif', $media[0]['url'] ); + $this->assertSame( 'http://example.com/image-in-a-link.gif', $media[1]['url'] ); + } + + // empty src attributes, data: URIs + public function test_extract_no_images_from_content_with_invalid_src_tags() { + $richtext = 'This sample text will contain images with invalid src tags, like this: + or . + '; + + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::IMAGES ); + + $this->assertArrayHasKey( 'images', $media ); + $this->assertSame( 0, $media['has']['images'] ); + } + + + /** + * Images extraction (galleries). + */ + + public function test_extract_images_from_content_with_galleries_variant_no_ids() { + // To test the [gallery] shortcode, we need to create a post and an attachment. + $post_id = $this->factory->post->create( array( 'post_content' => self::$richtext ) ); + $attachment_id = $this->factory->attachment->create_object( 'image.jpg', $post_id, array( + 'post_mime_type' => 'image/jpeg', + 'post_type' => 'attachment' + ) ); + wp_update_attachment_metadata( $attachment_id, array( 'width' => 100, 'height' => 100 ) ); + + + // Extract the gallery images. + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::IMAGES, array( + 'post' => get_post( $post_id ), + ) ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'galleries' ) ) ); + $this->assertCount( 1, $media ); + + $this->assertSame( 'http://' . WP_TESTS_DOMAIN . '/wp-content/uploads/image.jpg', $media[0]['url'] ); + } + + public function test_extract_images_from_content_with_galleries_variant_ids() { + // To test the [gallery] shortcode, we need to create a post and attachments. + $attachment_ids = array(); + foreach ( range( 1, 3 ) as $i ) { + $attachment_id = $this->factory->attachment->create_object( "image{$i}.jpg", 0, array( + 'post_mime_type' => 'image/jpeg', + 'post_type' => 'attachment' + ) ); + + wp_update_attachment_metadata( $attachment_id, array( 'width' => 100, 'height' => 100 ) ); + $attachment_ids[] = $attachment_id; + } + + $attachment_ids = join( ',', $attachment_ids ); + $post_id = $this->factory->post->create( array( 'post_content' => "[gallery ids='{$attachment_ids}']" ) ); + + + // Extract the gallery images. + $media = self::$media_extractor->extract( '', BP_Media_Extractor::IMAGES, array( + 'post' => get_post( $post_id ), + ) ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'galleries' ) ) ); + $this->assertCount( 3, $media ); + + for ( $i = 1; $i <= 3; $i++ ) { + $this->assertSame( 'http://' . WP_TESTS_DOMAIN . "/wp-content/uploads/image{$i}.jpg", $media[ $i - 1 ]['url'] ); + } + } + + public function test_extract_no_images_from_content_with_invalid_galleries_variant_no_ids() { + $post_id = $this->factory->post->create( array( 'post_content' => self::$richtext ) ); + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::IMAGES, array( + 'post' => get_post( $post_id ), + ) ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'galleries' ) ) ); + $this->assertCount( 0, $media ); + } + + public function test_extract_no_images_from_content_with_invalid_galleries_variant_ids() { + $post_id = $this->factory->post->create( array( 'post_content' => '[gallery ids="117,4529"]' ) ); + $media = self::$media_extractor->extract( '', BP_Media_Extractor::IMAGES, array( + 'post' => get_post( $post_id ), + ) ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'galleries' ) ) ); + $this->assertCount( 0, $media ); + } + + + /** + * Images extraction (thumbnail). + */ + + public function test_extract_no_images_from_content_with_featured_image() { + $post_id = $this->factory->post->create( array( 'post_content' => self::$richtext ) ); + $thumbnail_id = $this->factory->attachment->create_object( 'image.jpg', $post_id, array( + 'post_mime_type' => 'image/jpeg', + 'post_type' => 'attachment' + ) ); + set_post_thumbnail( $post_id, $thumbnail_id ); + + + // Extract the gallery images. + $media = self::$media_extractor->extract( '', BP_Media_Extractor::IMAGES, array( + 'post' => get_post( $post_id ), + ) ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'featured_images' ) ) ); + $this->assertCount( 1, $media ); + + $this->assertSame( 'http://' . WP_TESTS_DOMAIN . '/wp-content/uploads/image.jpg', $media[0]['url'] ); + } + + public function test_extract_images_from_content_without_featured_image() { + $post_id = $this->factory->post->create( array( 'post_content' => self::$richtext ) ); + $media = self::$media_extractor->extract( '', BP_Media_Extractor::IMAGES, array( + 'post' => get_post( $post_id ), + ) ); + + $this->assertArrayHasKey( 'images', $media ); + $media = array_values( wp_list_filter( $media['images'], array( 'source' => 'featured_images' ) ) ); + $this->assertCount( 0, $media ); + } + + + /** + * Audio extraction. + */ + + public function test_extract_audio_from_content() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::AUDIO ); + + $this->assertArrayHasKey( 'audio', $media ); + $this->assertCount( 3, $media['audio'] ); + + $this->assertSame( 'shortcodes', $media['audio'][0]['source'] ); + $this->assertSame( 'shortcodes', $media['audio'][1]['source'] ); + $this->assertSame( 'html', $media['audio'][2]['source'] ); + + $this->assertSame( 'http://example.com/source.mp3', $media['audio'][0]['url'] ); + $this->assertSame( 'http://example.com/source.wav', $media['audio'][1]['url'] ); + $this->assertSame( 'http://example.com/more_audio.mp3', $media['audio'][2]['url'] ); + } + + public function test_extract_audio_shortcode_with_no_src_param() { + $richtext = '[audio http://example.com/a-song.mp3]'; + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::AUDIO ); + + $this->assertArrayHasKey( 'audio', $media ); + $this->assertCount( 1, $media['audio'] ); + $this->assertSame( 'http://example.com/a-song.mp3', $media['audio'][0]['url'] ); + } + + public function test_extract_no_audio_from_invalid_content() { + $richtext = '[audio src="http://example.com/not_audio.gif"] + Hello.'; + + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::AUDIO ); + $this->assertSame( 0, $media['has']['audio'] ); + } + + public function test_extract_no_audio_from_empty_audio_shortcode() { + $media = self::$media_extractor->extract( '[audio]', BP_Media_Extractor::AUDIO ); + $this->assertSame( 0, $media['has']['audio'] ); + } + + + /** + * Video extraction. + */ + + public function test_extract_video_from_content() { + $media = self::$media_extractor->extract( self::$richtext, BP_Media_Extractor::VIDEOS ); + + $this->assertArrayHasKey( 'videos', $media ); + $this->assertCount( 2, $media['videos'] ); + + $this->assertSame( 'shortcodes', $media['videos'][0]['source'] ); + $this->assertSame( 'shortcodes', $media['videos'][1]['source'] ); + + $this->assertSame( 'http://example.com/source.ogv', $media['videos'][0]['url'] ); + $this->assertSame( 'http://example.com/source.webm', $media['videos'][1]['url'] ); + } + + + public function test_extract_video_shortcode_with_no_src_param() { + $richtext = '[video http://example.com/source.ogv]'; + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::VIDEOS ); + + $this->assertArrayHasKey( 'videos', $media ); + $this->assertCount( 1, $media['videos'] ); + $this->assertSame( 'http://example.com/source.ogv', $media['videos'][0]['url'] ); + } + + public function test_extract_no_video_from_invalid_content() { + $richtext = '[video src="http://example.com/not_video.mp3"]'; + $media = self::$media_extractor->extract( $richtext, BP_Media_Extractor::VIDEOS ); + + $this->assertSame( 0, $media['has']['videos'] ); + } + + public function test_extract_no_videos_from_empty_video_shortcodes() { + $media = self::$media_extractor->extract( '[video]', BP_Media_Extractor::VIDEOS ); + $this->assertSame( 0, $media['has']['videos'] ); + } +}