add experimental support for simplepie rss parser

This commit is contained in:
Andrew Dolgov 2006-07-04 06:51:05 +01:00
parent 3d7d6cdd57
commit 7c5a308d91
3 changed files with 210 additions and 91 deletions

View File

@ -9,9 +9,15 @@
define('DB_PASS', "XXXXXX"); define('DB_PASS', "XXXXXX");
//define('DB_PORT', '5432'); // when neeeded, PG-only //define('DB_PORT', '5432'); // when neeeded, PG-only
define(RSS_BACKEND_TYPE, "magpie");
// magpie (stable) or simplepie (EXPERIMENTAL!)
define('MAGPIE_CACHE_DIR', '/var/tmp/magpie-ttrss-cache'); define('MAGPIE_CACHE_DIR', '/var/tmp/magpie-ttrss-cache');
// Local cache directory for RSS feeds // Local cache directory for RSS feeds
define('SIMPLEPIE_CACHE_DIR', '/var/tmp/simplepie-ttrss-cache');
// Local cache directory for RSS feeds (simplepie)
define('WEB_DEMO_MODE', false); define('WEB_DEMO_MODE', false);
// Demo mode with reduced functionality. // Demo mode with reduced functionality.
// Warning: this option is obsolete. Don't rely on it being // Warning: this option is obsolete. Don't rely on it being

View File

@ -12,7 +12,11 @@
require_once 'errors.php'; require_once 'errors.php';
require_once 'version.php'; require_once 'version.php';
require_once 'magpierss/rss_utils.inc'; if (RSS_BACKEND_TYPE == "magpie") {
require_once 'magpierss/rss_utils.inc';
} else if (RSS_BACKEND_TYPE == "simplepie") {
require_once 'simplepie/simplepie.inc';
}
define('MAGPIE_OUTPUT_ENCODING', 'UTF-8'); define('MAGPIE_OUTPUT_ENCODING', 'UTF-8');
@ -270,15 +274,33 @@
} }
} }
error_reporting(0);
$rss = fetch_rss($fetch_url);
error_reporting (DEFAULT_ERROR_LEVEL); if (RSS_BACKEND_TYPE == "magpie") {
error_reporting(0);
$rss = fetch_rss($fetch_url);
error_reporting (DEFAULT_ERROR_LEVEL);
} else if (RSS_BACKEND_TYPE == "simplepie") {
if (!file_exists(SIMPLEPIE_CACHE_DIR)) {
mkdir(SIMPLEPIE_CACHE_DIR);
}
$rss = new SimplePie();
$rss->feed_url($fetch_url);
$rss->cache_location(SIMPLEPIE_CACHE_DIR);
$rss->init();
}
$feed = db_escape_string($feed); $feed = db_escape_string($feed);
if ($rss) { $rss_check = $rss;
if (RSS_BACKEND_TYPE == "simplepie") {
$rss_check = $rss->data;
}
if ($rss_check) {
// db_query($link, "BEGIN"); // db_query($link, "BEGIN");
$result = db_query($link, "SELECT title,icon_url,site_url,owner_uid $result = db_query($link, "SELECT title,icon_url,site_url,owner_uid
@ -295,14 +317,24 @@
} }
if (!$registered_title || $registered_title == "[Unknown]") { if (!$registered_title || $registered_title == "[Unknown]") {
$feed_title = db_escape_string($rss->channel["title"]);
if (RSS_BACKEND_TYPE == "magpie") {
$feed_title = db_escape_string($rss->channel["title"]);
} else {
$feed_title = $rss->get_feed_title();
}
db_query($link, "UPDATE ttrss_feeds SET db_query($link, "UPDATE ttrss_feeds SET
title = '$feed_title' WHERE id = '$feed'"); title = '$feed_title' WHERE id = '$feed'");
} }
$site_url = $rss->channel["link"]; if (RSS_BACKEND_TYPE == "magpie") {
// weird, weird Magpie $site_url = $rss->channel["link"];
if (!$site_url) $site_url = db_escape_string($rss->channel["link_"]); // weird, weird Magpie
if (!$site_url) $site_url = db_escape_string($rss->channel["link_"]);
} else {
$site_url = $rss->get_feed_link();
}
if ($site_url && $orig_site_url != db_escape_string($site_url)) { if ($site_url && $orig_site_url != db_escape_string($site_url)) {
db_query($link, "UPDATE ttrss_feeds SET db_query($link, "UPDATE ttrss_feeds SET
@ -311,7 +343,11 @@
// print "I: " . $rss->channel["image"]["url"]; // print "I: " . $rss->channel["image"]["url"];
$icon_url = $rss->image["url"]; if (RSS_BACKEND_TYPE == "magpie") {
$icon_url = $rss->image["url"];
} else {
$icon_url = $rss->get_image_url(); # FIXME
}
if ($icon_url && !$orig_icon_url != db_escape_string($icon_url)) { if ($icon_url && !$orig_icon_url != db_escape_string($icon_url)) {
$icon_url = db_escape_string($icon_url); $icon_url = db_escape_string($icon_url);
@ -339,10 +375,15 @@
array_push($filters[$line["name"]], $filter); array_push($filters[$line["name"]], $filter);
} }
$iterator = $rss->items; if (RSS_BACKEND_TYPE == "magpie") {
$iterator = $rss->items;
if (!$iterator || !is_array($iterator)) $iterator = $rss->entries; if (!$iterator || !is_array($iterator)) $iterator = $rss->entries;
if (!$iterator || !is_array($iterator)) $iterator = $rss; if (!$iterator || !is_array($iterator)) $iterator = $rss;
} else {
$iterator = $rss->get_items();
}
if (!is_array($iterator)) { if (!is_array($iterator)) {
/* db_query($link, "UPDATE ttrss_feeds /* db_query($link, "UPDATE ttrss_feeds
@ -352,83 +393,142 @@
} }
foreach ($iterator as $item) { foreach ($iterator as $item) {
$entry_guid = $item["id"];
if (!$entry_guid) $entry_guid = $item["guid"];
if (!$entry_guid) $entry_guid = $item["link"];
if (!$entry_guid) continue; if (RSS_BACKEND_TYPE == "magpie") {
$entry_timestamp = "";
$rss_2_date = $item['pubdate'];
$rss_1_date = $item['dc']['date'];
$atom_date = $item['issued'];
if (!$atom_date) $atom_date = $item['updated'];
if ($atom_date != "") $entry_timestamp = parse_w3cdtf($atom_date);
if ($rss_1_date != "") $entry_timestamp = parse_w3cdtf($rss_1_date);
if ($rss_2_date != "") $entry_timestamp = strtotime($rss_2_date);
if ($entry_timestamp == "") { $entry_guid = $item["id"];
$entry_timestamp = time();
$no_orig_date = 'true'; if (!$entry_guid) $entry_guid = $item["guid"];
} else { if (!$entry_guid) $entry_guid = $item["link"];
$no_orig_date = 'false';
if (!$entry_guid) continue;
$entry_timestamp = "";
$rss_2_date = $item['pubdate'];
$rss_1_date = $item['dc']['date'];
$atom_date = $item['issued'];
if (!$atom_date) $atom_date = $item['updated'];
if ($atom_date != "") $entry_timestamp = parse_w3cdtf($atom_date);
if ($rss_1_date != "") $entry_timestamp = parse_w3cdtf($rss_1_date);
if ($rss_2_date != "") $entry_timestamp = strtotime($rss_2_date);
if ($entry_timestamp == "") {
$entry_timestamp = time();
$no_orig_date = 'true';
} else {
$no_orig_date = 'false';
}
$entry_timestamp_fmt = strftime("%Y/%m/%d %H:%M:%S", $entry_timestamp);
$entry_title = $item["title"];
// strange Magpie workaround
$entry_link = $item["link_"];
if (!$entry_link) $entry_link = $item["link"];
if (!$entry_title) continue;
if (!$entry_link) continue;
$entry_content = $item["content:escaped"];
if (!$entry_content) $entry_content = $item["content:encoded"];
if (!$entry_content) $entry_content = $item["content"];
if (!$entry_content) $entry_content = $item["summary"];
if (!$entry_content) $entry_content = $item["description"];
// if (!$entry_content) continue;
// WTF
if (is_array($entry_content)) {
$entry_content = $entry_content["encoded"];
if (!$entry_content) $entry_content = $entry_content["escaped"];
}
// print_r($item);
// print_r(htmlspecialchars($entry_content));
// print "<br>";
$entry_content_unescaped = $entry_content;
$content_hash = "SHA1:" . sha1(strip_tags($entry_content));
$entry_comments = $item["comments"];
$entry_author = db_escape_string($item['dc']['creator']);
$entry_guid = db_escape_string($entry_guid);
$result = db_query($link, "SELECT id FROM ttrss_entries
WHERE guid = '$entry_guid'");
$entry_content = db_escape_string($entry_content);
$entry_title = db_escape_string($entry_title);
$entry_link = db_escape_string($entry_link);
$entry_comments = db_escape_string($entry_comments);
$num_comments = db_escape_string($item["slash"]["comments"]);
if (!$num_comments) $num_comments = 0;
} else if (RSS_BACKEND_TYPE == "simplepie") {
$entry_guid = $item->get_id();
if (!$entry_guid) {
$entry_guid = $item->get_permalink();
}
if (!$entry_guid) continue;
$entry_timestamp = $item->get_date("U");
if ($entry_timestamp == "") {
$entry_timestamp = time();
$no_orig_date = 'true';
} else {
$no_orig_date = 'false';
}
$entry_timestamp_fmt = strftime("%Y/%m/%d %H:%M:%S", $entry_timestamp);
$entry_title = $item->get_title();
$entry_link = $item->get_permalink();
if (!$entry_title) continue;
if (!$entry_link) continue;
$entry_content = $item->get_description();
// print_r(htmlspecialchars($entry_content));
// print "<br>";
$entry_content_unescaped = $entry_content;
$content_hash = "SHA1:" . sha1(strip_tags($entry_content));
$entry_comments = ""; # FIXME
$entry_author = $item->get_author(0);
$entry_author = db_escape_string($entry_author->name);
$entry_guid = db_escape_string($entry_guid);
$result = db_query($link, "SELECT id FROM ttrss_entries
WHERE guid = '$entry_guid'");
$entry_content = db_escape_string($entry_content);
$entry_title = db_escape_string($entry_title);
$entry_link = db_escape_string($entry_link);
$entry_comments = db_escape_string($entry_comments);
$num_comments = 0; # FIXME
if (!$num_comments) $num_comments = 0;
} }
$entry_timestamp_fmt = strftime("%Y/%m/%d %H:%M:%S", $entry_timestamp);
$entry_title = $item["title"];
// strange Magpie workaround
$entry_link = $item["link_"];
if (!$entry_link) $entry_link = $item["link"];
if (!$entry_title) continue;
if (!$entry_link) continue;
$entry_content = $item["content:escaped"];
if (!$entry_content) $entry_content = $item["content:encoded"];
if (!$entry_content) $entry_content = $item["content"];
if (!$entry_content) $entry_content = $item["summary"];
if (!$entry_content) $entry_content = $item["description"];
// if (!$entry_content) continue;
// WTF
if (is_array($entry_content)) {
$entry_content = $entry_content["encoded"];
if (!$entry_content) $entry_content = $entry_content["escaped"];
}
// print_r($item);
// print_r(htmlspecialchars($entry_content));
// print "<br>";
$entry_content_unescaped = $entry_content;
$content_hash = "SHA1:" . sha1(strip_tags($entry_content));
$entry_comments = $item["comments"];
$entry_author = db_escape_string($item['dc']['creator']);
$entry_guid = db_escape_string($entry_guid);
$result = db_query($link, "SELECT id FROM ttrss_entries
WHERE guid = '$entry_guid'");
$entry_content = db_escape_string($entry_content);
$entry_title = db_escape_string($entry_title);
$entry_link = db_escape_string($entry_link);
$entry_comments = db_escape_string($entry_comments);
$num_comments = db_escape_string($item["slash"]["comments"]);
if (!$num_comments) $num_comments = 0;
db_query($link, "BEGIN"); db_query($link, "BEGIN");
if (db_num_rows($result) == 0) { if (db_num_rows($result) == 0) {

View File

@ -16,7 +16,7 @@
exit; exit;
} }
if (!file_exists("magpierss/rss_fetch.inc")) { if (RSS_BACKEND_TYPE == "magpie" && !file_exists("magpierss/rss_fetch.inc")) {
print "<b>Fatal Error</b>: You forgot to place print "<b>Fatal Error</b>: You forgot to place
<a href=\"http://magpierss.sourceforge.net\">MagpieRSS</a> <a href=\"http://magpierss.sourceforge.net\">MagpieRSS</a>
distribution in <b>magpierss/</b> distribution in <b>magpierss/</b>
@ -24,9 +24,22 @@
exit; exit;
} }
if (CONFIG_VERSION != EXPECTED_CONFIG_VERSION) { if (RSS_BACKEND_TYPE == "simplepie" && !file_exists("simplepie/simplepie.inc")) {
return "config: your config file version is incorrect. See config.php-dist."; print "<b>Fatal Error</b>: You forgot to place
} <a href=\"http://simplepie.org\">SimplePie</a>
distribution in <b>simplepie/</b>
subdirectory of TT-RSS tree.";
exit;
}
if (RSS_BACKEND_TYPE != "simplepie" && RSS_BACKEND_TYPE != "magpie") {
print "<b>Fatal Error</b>: Invalid RSS_BACKEND_TYPE";
exit;
}
if (CONFIG_VERSION != EXPECTED_CONFIG_VERSION) {
return "config: your config file version is incorrect. See config.php-dist.";
}
if (file_exists("xml-export.php") || file_exists("xml-import.php")) { if (file_exists("xml-export.php") || file_exists("xml-import.php")) {
print "<b>Fatal Error</b>: XML Import/Export tools (<b>xml-export.php</b> print "<b>Fatal Error</b>: XML Import/Export tools (<b>xml-export.php</b>