diff --git a/linkchecker.module b/linkchecker.module index 3c58e3b..c9d3558 100644 --- a/linkchecker.module +++ b/linkchecker.module @@ -568,43 +568,9 @@ function _linkchecker_add_node_links($node, $skip_missing_links_detection = FALS // Create array of node fields to scan. $text_items = array(); $text_items[] = _filter_url($node->title, $filter); - //$text_items[] = _linkchecker_check_markup($node->summary, $node->format, $node->language); - $text_items[] = _linkchecker_check_markup($node->body, $node->format, $node->language); - $text_items[] = _linkchecker_check_markup($node->teaser, $node->format, $node->language); - // Search for links in 'weblink' nodes from 'links' module package. - if (module_exists('links_weblink') && $node->type == 'weblink' && !empty($node->links_weblink_url)) { - $text_items[] = _filter_url(url($node->links_weblink_url, $url_options), $node->format); - } - - // Search for links in 'weblinks' nodes from 'weblinks' module. - if (module_exists('weblinks') && $node->type == 'weblinks' && !empty($node->url)) { - $text_items[] = _filter_url(url($node->url, $url_options), $node->format); - } - - // Search for CCK-fields of types 'link' and 'text'. - if (module_exists('content')) { - // FIXME: How to port to D7??? - $fields = content_fields(NULL, $node->type); - foreach ($fields as $field) { - if (!empty($node->{$field['field_name']})) { - if (module_exists('link') && $field['type'] == 'link') { - foreach ($node->$field['field_name'] as $delta => $item) { - if (!empty($item['url'])) { - // Make non-absolute urls absolute or they are not found by _filter_url(). - // FIXME D7: needs language parameter for check_markup. - $text_items[] = _filter_url(url($item['url'], $url_options), $node->format); - } - } - } - elseif (module_exists('text') && $field['type'] == 'text') { - foreach ($node->$field['field_name'] as $delta => $item) { - $text_items[] = _filter_url($item['value'], $filter); - } - } - } - } - } + // Parse the fields from node and get all urls(add they to $text_items array). + linkchecker_parse_fields($node, $node->type, $text_items); // Get the absolute node path for extraction of relative links. $path = url('node/'. $node->nid, $url_options); @@ -676,6 +642,62 @@ function _linkchecker_add_node_links($node, $skip_missing_links_detection = FALS } /** + * Parse the urls from entity. + * + * This function parse all fields from the entity(a node or comment) and + * add they to $text_items array. + * + * @param $entity + * The entity to parse, a node or a comment object. + * @param $type + * The type(blunde) to parse. As a example, when the $entity is a node + * object, pass $node->type as value for this parameter. + * @param $text_items + * This is an array with all URLs found. + */ +function linkchecker_parse_fields($entity, $type, &$text_items) { + $field_list = field_info_fields(); + + foreach($field_list as $name => $field) { + // Prevents a warning in the next if. + $field['bundles']['node'] = isset($field['bundles']['node']) ? $field['bundles']['node'] : array(); + $field['bundles']['comment'] = isset($field['bundles']['comment']) ? $field['bundles']['comment'] : array(); + if (in_array($type, $field['bundles']['node']) || in_array($type, $field['bundles']['comment'])) { + // This is because a php parse error. + $entityField = $entity->$name; + switch($field['type']) { + case 'text_with_summary': + foreach($entityField as $language) { + foreach($language as $item) { + $text_items[] = _linkchecker_check_markup($item['value'], $item['format'], $entity->language); + $text_items[] = _linkchecker_check_markup($item['summary'], $item['format'], $entity->language); + } + } + break; + + case 'text_long': + case 'text': + foreach($entityField as $language) { + foreach($language as $item) { + $text_items[] = _linkchecker_check_markup($item['value'], $item['format'], $entity->language); + } + } + break; + + case 'link_field': + foreach($entityField as $language) { + foreach($language as $item) { + $text_items[] = _linkchecker_check_markup($item['url'], NULL, $entity->language); + $text_items[] = _linkchecker_check_markup($item['title'], NULL, $entity->language); + } + } + break; + } + } + } +} + +/** * Add comment links to database. * * @param $comment @@ -1337,60 +1359,69 @@ function _linkchecker_link_replace(&$text, $old_link_fqdn = '', $new_link_fqdn = * * See http://api.drupal.org/api/function/check_markup/7 for API documentation. */ -function _linkchecker_check_markup($text, $format = FILTER_FORMAT_DEFAULT, $langcode = '', $cache = TRUE) { - if (isset($text)) { - $format = filter_resolve_format($format); +function _linkchecker_check_markup($text, $format_id = NULL, $langcode = '', $cache = FALSE) { + if (!isset($text)) { + return ''; + } + + if (!isset($format_id)) { + $format_id = filter_fallback_format(); + } + // If the requested text format does not exist, the text cannot be filtered. + if (!$format = filter_format_load($format_id)) { + watchdog('filter', 'Missing text format: %format.', array('%format' => $format_id), WATCHDOG_ALERT); + return ''; + } - // Check for a cached version of this piece of text. - $cache_id = 'linkchecker:' . $format . ':' . $langcode . ':' . md5($text); - if ($cache && $cached = cache_get($cache_id, 'cache_filter')) { + // Check for a cached version of this piece of text. + $cache = $cache && !empty($format->cache); + $cache_id = ''; + if ($cache) { + $cache_id = 'linkchecker:' . $format->format . ':' . $langcode . ':' . hash('sha256', $text); + if ($cached = cache_get($cache_id, 'cache_filter')) { return $cached->data; } + } - // Convert all Windows and Mac newlines to a single newline, - // so filters only need to deal with one possibility. - $text = str_replace(array("\r\n", "\r"), "\n", $text); - - // Get a complete list of filters, ordered properly. - $filters = filter_list_format($format); - - // Do not run placeholder or special tag filters used as references - // to nodes like 'weblink' or 'weblinks' node types. If the original - // link node is updated, all links are automatically up-to-date and - // there is no need to notify about the broken link on all nodes having - // a link reference in content. This would only confuse the authors as - // they may also not be able to fix the source node of the reference. - $filters_blacklist = array_keys(array_filter(variable_get('linkchecker_filter_blacklist', explode('|', LINKCHECKER_DEFAULT_FILTER_BLACKLIST)))); - - // Give filters the chance to escape HTML-like data such as code or formulas. - foreach ($filters as $filter) { - if (!in_array($filter->name, $filters_blacklist)) { - $filter_info = module_invoke($filter->module, 'filter_info'); - // TODO: http://drupal.org/node/562694 - if (isset($filter_info[$filter->name]['prepare callback']) && function_exists($filter_info[$filter->name]['prepare callback'])) { - $text = call_user_func($filter_info[$filter->name]['prepare callback'], $text, $format, $langcode, $cache_id); - } + // Convert all Windows and Mac newlines to a single newline, so filters only + // need to deal with one possibility. + $text = str_replace(array("\r\n", "\r"), "\n", $text); + + // Get a complete list of filters, ordered properly. + $filters = filter_list_format($format->format); + $filter_info = filter_get_filters(); + + // Do not run placeholder or special tag filters used as references + // to nodes like 'weblink' or 'weblinks' node types. If the original + // link node is updated, all links are automatically up-to-date and + // there is no need to notify about the broken link on all nodes having + // a link reference in content. This would only confuse the authors as + // they may also not be able to fix the source node of the reference. + $filters_blacklist = array_keys(array_filter(variable_get('linkchecker_filter_blacklist', explode('|', LINKCHECKER_DEFAULT_FILTER_BLACKLIST)))); + + // Give filters the chance to escape HTML-like data such as code or formulas. + foreach ($filters as $name => $filter) { + if (!in_array($name, $filters_blacklist)) { + if ($filter->status && isset($filter_info[$name]['prepare callback']) && function_exists($filter_info[$name]['prepare callback'])) { + $function = $filter_info[$name]['prepare callback']; + $text = $function($text, $filter, $format, $langcode, $cache, $cache_id); } } + } - // Perform filtering. - foreach ($filters as $filter) { - if (!in_array($filter->name, $filters_blacklist)) { - $filter_info = module_invoke($filter->module, 'filter_info'); - // TODO: http://drupal.org/node/562694 - if (isset($filter_info[$filter->name]['process callback']) && function_exists($filter_info[$filter->name]['process callback'])) { - $text = call_user_func($filter_info[$filter->name]['process callback'], $text, $format, $langcode, $cache_id); - } + // Perform filtering. + foreach ($filters as $name => $filter) { + if (!in_array($name, $filters_blacklist)) { + if ($filter->status && isset($filter_info[$name]['process callback']) && function_exists($filter_info[$name]['process callback'])) { + $function = $filter_info[$name]['process callback']; + $text = $function($text, $filter, $format, $langcode, $cache, $cache_id); } } - - // Store in cache with a minimum expiration time of 1 day. - if ($cache && filter_format_allowcache($format)) { - cache_set($cache_id, $text, 'cache_filter', REQUEST_TIME + (60 * 60 * 24)); - } } - else { - $text = t('n/a'); + + // Store in cache with a minimum expiration time of 1 day. + if ($cache) { + cache_set($cache_id, $text, 'cache_filter', REQUEST_TIME + (60 * 60 * 24)); } return $text;