summaryrefslogtreecommitdiff
path: root/modules/aggregator/aggregator.parser.inc
diff options
context:
space:
mode:
Diffstat (limited to 'modules/aggregator/aggregator.parser.inc')
-rw-r--r--modules/aggregator/aggregator.parser.inc327
1 files changed, 327 insertions, 0 deletions
diff --git a/modules/aggregator/aggregator.parser.inc b/modules/aggregator/aggregator.parser.inc
new file mode 100644
index 000000000..7512b44a5
--- /dev/null
+++ b/modules/aggregator/aggregator.parser.inc
@@ -0,0 +1,327 @@
+<?php
+// $Id$
+
+/**
+ * @file
+ * Parser functions for the aggregator module.
+ */
+
+/**
+ * Implementation of hook_aggregator_parse_info().
+ */
+function aggregator_aggregator_parse_info() {
+ return array(
+ 'title' => t('Default parser'),
+ 'description' => t('Parses RSS, Atom and RDF feeds.'),
+ );
+}
+
+/**
+ * Implementation of hook_aggregator_parse().
+ */
+function aggregator_aggregator_parse($feed) {
+ global $channel, $image;
+
+ // Filter the input data.
+ if (aggregator_parse_feed($feed->source_string, $feed)) {
+ $modified = empty($feed->http_headers['Last-Modified']) ? 0 : strtotime($feed->http_headers['Last-Modified']);
+
+ // Prepare the channel data.
+ foreach ($channel as $key => $value) {
+ $channel[$key] = trim($value);
+ }
+
+ // Prepare the image data (if any).
+ foreach ($image as $key => $value) {
+ $image[$key] = trim($value);
+ }
+
+ if (!empty($image['LINK']) && !empty($image['URL']) && !empty($image['TITLE'])) {
+ $image = l(theme('image', $image['URL'], $image['TITLE']), $image['LINK'], array('html' => TRUE));
+ }
+ else {
+ $image = '';
+ }
+
+ $etag = empty($feed->http_headers['ETag']) ? '' : $feed->http_headers['ETag'];
+ // Update the feed data.
+ db_merge('aggregator_feed')
+ ->key(array('fid' => $feed->fid))
+ ->fields(array(
+ 'url' => $feed->url,
+ 'checked' => REQUEST_TIME,
+ 'link' => !empty($channel['LINK']) ? $channel['LINK'] : '',
+ 'description' => !empty($channel['DESCRIPTION']) ? $channel['DESCRIPTION'] : '',
+ 'image' => $image,
+ 'hash' => md5($feed->source_string),
+ 'etag' => $etag,
+ 'modified' => $modified,
+ ))
+ ->execute();
+
+ // Clear the cache.
+ cache_clear_all();
+
+ if (isset($feed->redirected)) {
+ watchdog('aggregator', 'Updated URL for feed %title to %url.', array('%title' => $feed->title, '%url' => $feed->url));
+ }
+
+ watchdog('aggregator', 'There is new syndicated content from %site.', array('%site' => $feed->title));
+ drupal_set_message(t('There is new syndicated content from %site.', array('%site' => $feed->title)));
+
+ }
+}
+
+/**
+ * Parse a feed and store its items.
+ *
+ * @param $data
+ * The feed data.
+ * @param $feed
+ * An object describing the feed to be parsed.
+ * @return
+ * FALSE on error, TRUE otherwise.
+ */
+function aggregator_parse_feed(&$data, $feed) {
+ global $items, $image, $channel;
+
+ // Unset the global variables before we use them.
+ unset($GLOBALS['element'], $GLOBALS['item'], $GLOBALS['tag']);
+ $items = array();
+ $image = array();
+ $channel = array();
+
+ // Parse the data.
+ $xml_parser = drupal_xml_parser_create($data);
+ xml_set_element_handler($xml_parser, 'aggregator_element_start', 'aggregator_element_end');
+ xml_set_character_data_handler($xml_parser, 'aggregator_element_data');
+
+ if (!xml_parse($xml_parser, $data, 1)) {
+ watchdog('aggregator', 'The feed from %site seems to be broken, due to an error "%error" on line %line.', array('%site' => $feed->title, '%error' => xml_error_string(xml_get_error_code($xml_parser)), '%line' => xml_get_current_line_number($xml_parser)), WATCHDOG_WARNING);
+ drupal_set_message(t('The feed from %site seems to be broken, because of error "%error" on line %line.', array('%site' => $feed->title, '%error' => xml_error_string(xml_get_error_code($xml_parser)), '%line' => xml_get_current_line_number($xml_parser))), 'error');
+ return FALSE;
+ }
+ xml_parser_free($xml_parser);
+
+ // We reverse the array such that we store the first item last, and the last
+ // item first. In the database, the newest item should be at the top.
+ $items = array_reverse($items);
+
+ // Initialize items array.
+ $feed->items = array();
+ foreach ($items as $item) {
+
+ // Prepare the item:
+ foreach ($item as $key => $value) {
+ $item[$key] = trim($value);
+ }
+
+ // Resolve the item's title. If no title is found, we use up to 40
+ // characters of the description ending at a word boundary, but not
+ // splitting potential entities.
+ if (!empty($item['TITLE'])) {
+ $item['TITLE'] = $item['TITLE'];
+ }
+ elseif (!empty($item['DESCRIPTION'])) {
+ $item['TITLE'] = preg_replace('/^(.*)[^\w;&].*?$/', "\\1", truncate_utf8($item['DESCRIPTION'], 40));
+ }
+ else {
+ $item['TITLE'] = '';
+ }
+
+ // Resolve the items link.
+ if (!empty($item['LINK'])) {
+ $item['LINK'] = $item['LINK'];
+ }
+ else {
+ $item['LINK'] = $feed->link;
+ }
+ $item['GUID'] = isset($item['GUID']) ? $item['GUID'] : '';
+
+ // Atom feeds have a CONTENT and/or SUMMARY tag instead of a DESCRIPTION tag.
+ if (!empty($item['CONTENT:ENCODED'])) {
+ $item['DESCRIPTION'] = $item['CONTENT:ENCODED'];
+ }
+ elseif (!empty($item['SUMMARY'])) {
+ $item['DESCRIPTION'] = $item['SUMMARY'];
+ }
+ elseif (!empty($item['CONTENT'])) {
+ $item['DESCRIPTION'] = $item['CONTENT'];
+ }
+
+ // Try to resolve and parse the item's publication date.
+ $date = '';
+ foreach (array('PUBDATE', 'DC:DATE', 'DCTERMS:ISSUED', 'DCTERMS:CREATED', 'DCTERMS:MODIFIED', 'ISSUED', 'CREATED', 'MODIFIED', 'PUBLISHED', 'UPDATED') as $key) {
+ if (!empty($item[$key])) {
+ $date = $item[$key];
+ break;
+ }
+ }
+
+ $item['TIMESTAMP'] = strtotime($date);
+
+ if ($item['TIMESTAMP'] === FALSE) {
+ $item['TIMESTAMP'] = aggregator_parse_w3cdtf($date); // Aggregator_parse_w3cdtf() returns FALSE on failure.
+ }
+
+ $item += array('AUTHOR' => '', 'DESCRIPTION' => '');
+
+ // Store on $feed object. This is where processors will look for parsed items.
+ $feed->items[] = $item;
+ }
+
+ return TRUE;
+}
+
+/**
+ * Callback function used by the XML parser.
+ */
+function aggregator_element_start($parser, $name, $attributes) {
+ global $item, $element, $tag, $items, $channel;
+
+ switch ($name) {
+ case 'IMAGE':
+ case 'TEXTINPUT':
+ case 'CONTENT':
+ case 'SUMMARY':
+ case 'TAGLINE':
+ case 'SUBTITLE':
+ case 'LOGO':
+ case 'INFO':
+ $element = $name;
+ break;
+ case 'ID':
+ if ($element != 'ITEM') {
+ $element = $name;
+ }
+ case 'LINK':
+ if (!empty($attributes['REL']) && $attributes['REL'] == 'alternate') {
+ if ($element == 'ITEM') {
+ $items[$item]['LINK'] = $attributes['HREF'];
+ }
+ else {
+ $channel['LINK'] = $attributes['HREF'];
+ }
+ }
+ break;
+ case 'ITEM':
+ $element = $name;
+ $item += 1;
+ break;
+ case 'ENTRY':
+ $element = 'ITEM';
+ $item += 1;
+ break;
+ }
+
+ $tag = $name;
+}
+
+/**
+ * Call-back function used by the XML parser.
+ */
+function aggregator_element_end($parser, $name) {
+ global $element;
+
+ switch ($name) {
+ case 'IMAGE':
+ case 'TEXTINPUT':
+ case 'ITEM':
+ case 'ENTRY':
+ case 'CONTENT':
+ case 'INFO':
+ $element = '';
+ break;
+ case 'ID':
+ if ($element == 'ID') {
+ $element = '';
+ }
+ }
+}
+
+/**
+ * Callback function used by the XML parser.
+ */
+function aggregator_element_data($parser, $data) {
+ global $channel, $element, $items, $item, $image, $tag;
+ $items += array($item => array());
+ switch ($element) {
+ case 'ITEM':
+ $items[$item] += array($tag => '');
+ $items[$item][$tag] .= $data;
+ break;
+ case 'IMAGE':
+ case 'LOGO':
+ $image += array($tag => '');
+ $image[$tag] .= $data;
+ break;
+ case 'LINK':
+ if ($data) {
+ $items[$item] += array($tag => '');
+ $items[$item][$tag] .= $data;
+ }
+ break;
+ case 'CONTENT':
+ $items[$item] += array('CONTENT' => '');
+ $items[$item]['CONTENT'] .= $data;
+ break;
+ case 'SUMMARY':
+ $items[$item] += array('SUMMARY' => '');
+ $items[$item]['SUMMARY'] .= $data;
+ break;
+ case 'TAGLINE':
+ case 'SUBTITLE':
+ $channel += array('DESCRIPTION' => '');
+ $channel['DESCRIPTION'] .= $data;
+ break;
+ case 'INFO':
+ case 'ID':
+ case 'TEXTINPUT':
+ // The sub-element is not supported. However, we must recognize
+ // it or its contents will end up in the item array.
+ break;
+ default:
+ $channel += array($tag => '');
+ $channel[$tag] .= $data;
+ }
+}
+
+/**
+ * Parse the W3C date/time format, a subset of ISO 8601.
+ *
+ * PHP date parsing functions do not handle this format.
+ * See http://www.w3.org/TR/NOTE-datetime for more information.
+ * Originally from MagpieRSS (http://magpierss.sourceforge.net/).
+ *
+ * @param $date_str
+ * A string with a potentially W3C DTF date.
+ * @return
+ * A timestamp if parsed successfully or FALSE if not.
+ */
+function aggregator_parse_w3cdtf($date_str) {
+ if (preg_match('/(\d{4})-(\d{2})-(\d{2})T(\d{2}):(\d{2})(:(\d{2}))?(?:([-+])(\d{2}):?(\d{2})|(Z))?/', $date_str, $match)) {
+ list($year, $month, $day, $hours, $minutes, $seconds) = array($match[1], $match[2], $match[3], $match[4], $match[5], $match[6]);
+ // Calculate the epoch for current date assuming GMT.
+ $epoch = gmmktime($hours, $minutes, $seconds, $month, $day, $year);
+ if ($match[10] != 'Z') { // Z is zulu time, aka GMT
+ list($tz_mod, $tz_hour, $tz_min) = array($match[8], $match[9], $match[10]);
+ // Zero out the variables.
+ if (!$tz_hour) {
+ $tz_hour = 0;
+ }
+ if (!$tz_min) {
+ $tz_min = 0;
+ }
+ $offset_secs = (($tz_hour * 60) + $tz_min) * 60;
+ // Is timezone ahead of GMT? If yes, subtract offset.
+ if ($tz_mod == '+') {
+ $offset_secs *= -1;
+ }
+ $epoch += $offset_secs;
+ }
+ return $epoch;
+ }
+ else {
+ return FALSE;
+ }
+}
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-21 10:01:22 +0000