/**
* Builds a Google Sitemap of all public pages known to the indexer
*
* The map is placed in the cache directory named sitemap.xml.gz - This
* file needs to be writable!
*
* @author Michael Hamann
* @author Andreas Gohr
* @link https://www.google.com/webmasters/sitemaps/docs/en/about.html
* @link http://www.sitemaps.org/
*/
public function generate()
{
global $conf;
if ($conf['sitemap'] < 1 || !is_numeric($conf['sitemap'])) {
return false;
}
$sitemap = Sitemapper::getFilePath();
if (@file_exists($sitemap)) {
if (!is_writable($sitemap)) {
return false;
}
} else {
if (!is_writable(dirname($sitemap))) {
return false;
}
}
if (@filesize($sitemap) && @filemtime($sitemap) > time() - $conf['sitemap'] * 86400) {
// 60*60*24=86400
dbglog('Sitemapper::generate(): Sitemap up to date');
// FIXME: only in debug mode
return false;
}
dbglog("Sitemapper::generate(): using {$sitemap}");
// FIXME: Only in debug mode
$pages = idx_getIndex('page', '');
dbglog('Sitemapper::generate(): creating sitemap using ' . count($pages) . ' pages');
$items = array();
// build the sitemap items
foreach ($pages as $id) {
//skip hidden, non existing and restricted files
if (isHiddenPage($id)) {
continue;
}
if (auth_aclcheck($id, '', '') < AUTH_READ) {
continue;
}
$item = SitemapItem::createFromID($id);
if ($item !== NULL) {
$items[] = $item;
}
}
$eventData = array('items' => &$items, 'sitemap' => &$sitemap);
$event = new Doku_Event('SITEMAP_GENERATE', $eventData);
if ($event->advise_before(true)) {
//save the new sitemap
$result = io_saveFile($sitemap, Sitemapper::getXML($items));
}
$event->advise_after();
return $result;
}
/**
* Get count of occurrences for a list of tags
*
* @param array $tags array of tags
* @param array $namespaces array of namespaces where to count the tags
* @param boolean $allTags boolean if all available tags should be counted
* @param boolean $recursive boolean if pages in subnamespaces are allowed
* @return array
*/
function tagOccurrences($tags, $namespaces = NULL, $allTags = false, $recursive = NULL)
{
// map with trim here in order to remove newlines from tags
if ($allTags) {
$tags = array_map('trim', idx_getIndex('subject', '_w'));
}
$tags = $this->_cleanTagList($tags);
$otags = array();
//occurrences
if (!$namespaces || $namespaces[0] == '' || !is_array($namespaces)) {
$namespaces = NULL;
}
// $namespaces not specified
$indexer = idx_get_indexer();
$indexer_pages = $indexer->lookupKey('subject', $tags, array($this, '_tagCompare'));
$root_allowed = $namespaces == NULL ? false : in_array('.', $namespaces);
if ($recursive === NULL) {
$recursive = $this->getConf('list_tags_of_subns');
}
foreach ($tags as $tag) {
if (!isset($indexer_pages[$tag])) {
continue;
}
// just to be sure remove duplicate pages from the list of pages
$pages = array_unique($indexer_pages[$tag]);
// don't count hidden pages or pages the user can't access
// for performance reasons this doesn't take drafts into account
$pages = array_filter($pages, array($this, '_isVisible'));
if (empty($pages)) {
continue;
}
if ($namespaces == NULL || $root_allowed && $recursive) {
// count all pages
$otags[$tag] = count($pages);
} else {
if (!$recursive) {
// filter by exact namespace
$otags[$tag] = 0;
foreach ($pages as $page) {
$ns = getNS($page);
if ($ns == false && $root_allowed || in_array($ns, $namespaces)) {
$otags[$tag]++;
}
}
} else {
// recursive, no root
$otags[$tag] = 0;
foreach ($pages as $page) {
foreach ($namespaces as $ns) {
if (strpos($page, $ns . ':') === 0) {
$otags[$tag]++;
break;
}
}
}
}
}
// don't return tags without pages
if ($otags[$tag] == 0) {
unset($otags[$tag]);
}
}
return $otags;
}
/**
* Lookup words in index
*
* Takes an array of word and will return a list of matching
* documents for each one.
*
* Important: No ACL checking is done here! All results are
* returned, regardless of permissions
*
* @author Andreas Gohr <*****@*****.**>
*/
function idx_lookup($words)
{
global $conf;
$result = array();
$wids = idx_getIndexWordsSorted($words, $result);
if (empty($wids)) {
return array();
}
// load known words and documents
$page_idx = idx_getIndex('page', '');
$docs = array();
// hold docs found
foreach (array_keys($wids) as $wlen) {
$wids[$wlen] = array_unique($wids[$wlen]);
$index = idx_getIndex('i', $wlen);
foreach ($wids[$wlen] as $ixid) {
if ($ixid < count($index)) {
$docs["{$wlen}*{$ixid}"] = idx_parseIndexLine($page_idx, $index[$ixid]);
}
}
}
// merge found pages into final result array
$final = array();
foreach ($result as $word => $res) {
$final[$word] = array();
foreach ($res as $wid) {
$hits =& $docs[$wid];
foreach ($hits as $hitkey => $hitcnt) {
if (!isset($final[$word][$hitkey])) {
$final[$word][$hitkey] = $hitcnt;
} else {
$final[$word][$hitkey] += $hitcnt;
}
}
}
}
return $final;
}
/**
* Returns the sorted word cloud array
*/
function _getWordCloud($num, &$min, &$max)
{
global $conf;
// load stopwords
$swfile = DOKU_INC . 'inc/lang/' . $conf['lang'] . '/stopwords.txt';
if (@file_exists($swfile)) {
$stopwords = file($swfile, FILE_IGNORE_NEW_LINES);
} else {
$stopwords = array();
}
// load extra local stopwords
$swfile = DOKU_CONF . 'stopwords.txt';
if (@file_exists($swfile)) {
$stopwords = array_merge($stopwords, file($swfile, FILE_IGNORE_NEW_LINES));
}
$cloud = array();
if (@file_exists($conf['indexdir'] . '/page.idx')) {
// new word-length based index
require_once DOKU_INC . 'inc/indexer.php';
$n = $this->getConf('minimum_word_length');
// minimum word length
$lengths = idx_indexLengths($n);
foreach ($lengths as $len) {
$idx = idx_getIndex('i', $len);
$word_idx = idx_getIndex('w', $len);
$this->_addWordsToCloud($cloud, $idx, $word_idx, $stopwords);
}
} else {
// old index
$idx = file($conf['cachedir'] . '/index.idx');
$word_idx = file($conf['cachedir'] . '/word.idx');
$this->_addWordsToCloud($cloud, $idx, $word_idx, $stopwords);
}
return $this->_sortCloud($cloud, $num, $min, $max);
}
/**
* Returns a list of matching documents for the given query
*
* @author Andreas Gohr <*****@*****.**>
* @author Kazutaka Miyasaka <*****@*****.**>
*/
function _ft_pageSearch(&$data)
{
// parse the given query
$q = ft_queryParser($data['query']);
$data['highlight'] = $q['highlight'];
if (empty($q['parsed_ary'])) {
return array();
}
// lookup all words found in the query
$lookup = idx_lookup($q['words']);
// get all pages in this dokuwiki site (!: includes nonexistent pages)
$pages_all = array();
foreach (idx_getIndex('page', '') as $id) {
$pages_all[trim($id)] = 0;
// base: 0 hit
}
// process the query
$stack = array();
foreach ($q['parsed_ary'] as $token) {
switch (substr($token, 0, 3)) {
case 'W+:':
case 'W-:':
case 'W_:':
// word
$word = substr($token, 3);
$stack[] = (array) $lookup[$word];
break;
case 'P+:':
case 'P-:':
// phrase
$phrase = substr($token, 3);
// since phrases are always parsed as ((W1)(W2)...(P)),
// the end($stack) always points the pages that contain
// all words in this phrase
$pages = end($stack);
$pages_matched = array();
foreach (array_keys($pages) as $id) {
$text = utf8_strtolower(rawWiki($id));
if (strpos($text, $phrase) !== false) {
$pages_matched[$id] = 0;
// phrase: always 0 hit
}
}
$stack[] = $pages_matched;
break;
case 'N+:':
case 'N-:':
// namespace
$ns = substr($token, 3);
$pages_matched = array();
foreach (array_keys($pages_all) as $id) {
if (strpos($id, $ns) === 0) {
$pages_matched[$id] = 0;
// namespace: always 0 hit
}
}
$stack[] = $pages_matched;
break;
case 'AND':
// and operation
list($pages1, $pages2) = array_splice($stack, -2);
$stack[] = ft_resultCombine(array($pages1, $pages2));
break;
case 'OR':
// or operation
list($pages1, $pages2) = array_splice($stack, -2);
$stack[] = ft_resultUnite(array($pages1, $pages2));
break;
case 'NOT':
// not operation (unary)
$pages = array_pop($stack);
$stack[] = ft_resultComplement(array($pages_all, $pages));
break;
}
}
$docs = array_pop($stack);
if (empty($docs)) {
return array();
}
// check: settings, acls, existence
foreach (array_keys($docs) as $id) {
if (isHiddenPage($id) || auth_quickaclcheck($id) < AUTH_READ || !page_exists($id, '', false)) {
unset($docs[$id]);
}
}
// sort docs by count
arsort($docs);
return $docs;
}
/**
* List all pages - we use the indexer list here
*/
function listPages()
{
$list = array();
$pages = array_filter(array_filter(idx_getIndex('page', ''), 'isVisiblePage'), 'page_exists');
foreach (array_keys($pages) as $idx) {
$perm = auth_quickaclcheck($pages[$idx]);
if ($perm < AUTH_READ) {
continue;
}
$page = array();
$page['id'] = trim($pages[$idx]);
$page['perms'] = $perm;
$page['size'] = @filesize(wikiFN($pages[$idx]));
$page['lastModified'] = new IXR_Date(@filemtime(wikiFN($pages[$idx])));
$list[] = $page;
}
return $list;
}
/**
* Gets the first heading from a file
*
* @param string $id dokuwiki page id
* @param bool $render rerender if first heading not known
* default: true -- must be set to false for calls from the metadata renderer to
* protects against loops and excessive resource usage when pages
* for which only a first heading is required will attempt to
* render metadata for all the pages for which they require first
* headings ... and so on.
*
* @author Andreas Gohr <*****@*****.**>
* @author Michael Hamann <*****@*****.**>
*/
function p_get_first_heading($id, $render = true)
{
// counter how many titles have been requested using p_get_metadata
static $count = 1;
// the index of all titles, only loaded when many titles are requested
static $title_index = null;
// cache for titles requested using p_get_metadata
static $title_cache = array();
$id = cleanID($id);
// check if this title has already been requested
if (isset($title_cache[$id])) {
return $title_cache[$id];
}
// check if already too many titles have been requested and probably
// using the title index is better
if ($count > P_GET_FIRST_HEADING_METADATA_LIMIT) {
if (is_null($title_index)) {
$pages = array_map('rtrim', idx_getIndex('page', ''));
$titles = array_map('rtrim', idx_getIndex('title', ''));
// check for corrupt title index #FS2076
if (count($pages) != count($titles)) {
$titles = array_fill(0, count($pages), '');
@unlink($conf['indexdir'] . '/title.idx');
// will be rebuilt in inc/init.php
}
$title_index = array_combine($pages, $titles);
}
return $title_index[$id];
}
++$count;
$title_cache[$id] = p_get_metadata($id, 'title', $render);
return $title_cache[$id];
}
/**
* Create a pagewords index from the existing index.
*
* @author Tom N Harris <*****@*****.**>
*/
function idx_upgradePageWords()
{
global $conf;
$page_idx = idx_getIndex('page', '');
if (empty($page_idx)) {
return;
}
$pagewords = array();
$len = count($page_idx);
for ($n = 0; $n < $len; $n++) {
$pagewords[] = array();
}
unset($page_idx);
$n = 0;
foreach (idx_indexLengths($n) as $wlen) {
$lines = idx_getIndex('i', $wlen);
$len = count($lines);
for ($wid = 0; $wid < $len; $wid++) {
$wkey = "{$wlen}*{$wid}";
foreach (explode(':', trim($lines[$wid])) as $part) {
if ($part == '') {
continue;
}
list($doc, $cnt) = explode('*', $part);
$pagewords[(int) $doc][] = $wkey;
}
}
}
$fn = $conf['indexdir'] . '/pageword';
$fh = @fopen($fn . '.tmp', 'w');
if (!$fh) {
trigger_error("Failed to write word index", E_USER_ERROR);
return false;
}
foreach ($pagewords as $line) {
fwrite($fh, join(':', $line) . "\n");
}
fclose($fh);
if ($conf['fperm']) {
chmod($fn . '.tmp', $conf['fperm']);
}
io_rename($fn . '.tmp', $fn . '.idx');
return true;
}
function _ft_pageLookup(&$data)
{
// split out original parameters
$id = $data['id'];
if (preg_match('/(?:^| )@(\\w+)/', $id, $matches)) {
$ns = cleanID($matches[1]) . ':';
$id = str_replace($matches[0], '', $id);
}
$in_ns = $data['in_ns'];
$in_title = $data['in_title'];
$pages = array_map('rtrim', idx_getIndex('page', ''));
$titles = array_map('rtrim', idx_getIndex('title', ''));
$pages = array_combine($pages, $titles);
if ($id !== '' && cleanID($id) !== '') {
$cleaned = cleanID($id);
$matched_pages = array();
foreach ($pages as $p_id => $p_title) {
if ((strpos($in_ns ? $p_id : noNSorNS($p_id), $cleaned) !== false || $in_title && stripos($p_title, $id) !== false) && (!isset($ns) || strpos($p_id, $ns) === 0)) {
$matched_pages[$p_id] = $p_title;
}
}
$pages = $matched_pages;
}
// discard hidden pages
// discard nonexistent pages
// check ACL permissions
foreach (array_keys($pages) as $idx) {
if (!isVisiblePage($idx) || !page_exists($idx) || auth_quickaclcheck($idx) < AUTH_READ) {
unset($pages[$idx]);
}
}
uasort($pages, 'ft_pagesorter');
return $pages;
}
/**
* Run a few sanity checks
*
* @author Andreas Gohr <*****@*****.**>
*/
function check()
{
global $conf;
global $INFO;
if ($INFO['isadmin'] || $INFO['ismanager']) {
msg('DokuWiki version: ' . getVersion(), 1);
}
if (version_compare(phpversion(), '5.2.0', '<')) {
msg('Your PHP version is too old (' . phpversion() . ' vs. 5.2.0+ needed)', -1);
} else {
msg('PHP version ' . phpversion(), 1);
}
$mem = (int) php_to_byte(ini_get('memory_limit'));
if ($mem) {
if ($mem < 16777216) {
msg('PHP is limited to less than 16MB RAM (' . $mem . ' bytes). Increase memory_limit in php.ini', -1);
} elseif ($mem < 20971520) {
msg('PHP is limited to less than 20MB RAM (' . $mem . ' bytes), you might encounter problems with bigger pages. Increase memory_limit in php.ini', -1);
} elseif ($mem < 33554432) {
msg('PHP is limited to less than 32MB RAM (' . $mem . ' bytes), but that should be enough in most cases. If not, increase memory_limit in php.ini', 0);
} else {
msg('More than 32MB RAM (' . $mem . ' bytes) available.', 1);
}
}
if (is_writable($conf['changelog'])) {
msg('Changelog is writable', 1);
} else {
if (@file_exists($conf['changelog'])) {
msg('Changelog is not writable', -1);
}
}
if (isset($conf['changelog_old']) && @file_exists($conf['changelog_old'])) {
msg('Old changelog exists', 0);
}
if (@file_exists($conf['changelog'] . '_failed')) {
msg('Importing old changelog failed', -1);
} else {
if (@file_exists($conf['changelog'] . '_importing')) {
msg('Importing old changelog now.', 0);
} else {
if (@file_exists($conf['changelog'] . '_import_ok')) {
msg('Old changelog imported', 1);
if (!plugin_isdisabled('importoldchangelog')) {
msg('Importoldchangelog plugin not disabled after import', -1);
}
}
}
}
if (is_writable(DOKU_CONF)) {
msg('conf directory is writable', 1);
} else {
msg('conf directory is not writable', -1);
}
if ($conf['authtype'] == 'plain') {
global $config_cascade;
if (is_writable($config_cascade['plainauth.users']['default'])) {
msg('conf/users.auth.php is writable', 1);
} else {
msg('conf/users.auth.php is not writable', 0);
}
}
if (function_exists('mb_strpos')) {
if (defined('UTF8_NOMBSTRING')) {
msg('mb_string extension is available but will not be used', 0);
} else {
msg('mb_string extension is available and will be used', 1);
if (ini_get('mbstring.func_overload') != 0) {
msg('mb_string function overloading is enabled, this will cause problems and should be disabled', -1);
}
}
} else {
msg('mb_string extension not available - PHP only replacements will be used', 0);
}
if (!UTF8_PREGSUPPORT) {
msg('PHP is missing UTF-8 support in Perl-Compatible Regular Expressions (PCRE)', -1);
}
if (!UTF8_PROPERTYSUPPORT) {
msg('PHP is missing Unicode properties support in Perl-Compatible Regular Expressions (PCRE)', -1);
}
$loc = setlocale(LC_ALL, 0);
if (!$loc) {
msg('No valid locale is set for your PHP setup. You should fix this', -1);
} elseif (stripos($loc, 'utf') === false) {
msg('Your locale <code>' . hsc($loc) . '</code> seems not to be a UTF-8 locale, you should fix this if you encounter problems.', 0);
} else {
msg('Valid locale ' . hsc($loc) . ' found.', 1);
}
if ($conf['allowdebug']) {
msg('Debugging support is enabled. If you don\'t need it you should set $conf[\'allowdebug\'] = 0', -1);
} else {
msg('Debugging support is disabled', 1);
}
if ($INFO['userinfo']['name']) {
msg('You are currently logged in as ' . $_SERVER['REMOTE_USER'] . ' (' . $INFO['userinfo']['name'] . ')', 0);
msg('You are part of the groups ' . join($INFO['userinfo']['grps'], ', '), 0);
} else {
msg('You are currently not logged in', 0);
}
msg('Your current permission for this page is ' . $INFO['perm'], 0);
if (is_writable($INFO['filepath'])) {
msg('The current page is writable by the webserver', 0);
} else {
msg('The current page is not writable by the webserver', 0);
}
if ($INFO['writable']) {
msg('The current page is writable by you', 0);
} else {
msg('The current page is not writable by you', 0);
}
// Check for corrupted search index
$lengths = idx_listIndexLengths();
$index_corrupted = false;
foreach ($lengths as $length) {
if (count(idx_getIndex('w', $length)) != count(idx_getIndex('i', $length))) {
$index_corrupted = true;
break;
}
}
foreach (idx_getIndex('metadata', '') as $index) {
if (count(idx_getIndex($index . '_w', '')) != count(idx_getIndex($index . '_i', ''))) {
$index_corrupted = true;
break;
}
}
if ($index_corrupted) {
msg('The search index is corrupted. It might produce wrong results and most
probably needs to be rebuilt. See
<a href="http://www.dokuwiki.org/faq:searchindex">faq:searchindex</a>
for ways to rebuild the search index.', -1);
} elseif (!empty($lengths)) {
msg('The search index seems to be working', 1);
} else {
msg('The search index is empty. See
<a href="http://www.dokuwiki.org/faq:searchindex">faq:searchindex</a>
for help on how to fix the search index. If the default indexer
isn\'t used or the wiki is actually empty this is normal.');
}
}
/**
* Run a few sanity checks
*
* @author Andreas Gohr <*****@*****.**>
*/
function check()
{
global $conf;
global $INFO;
if ($INFO['isadmin'] || $INFO['ismanager']) {
msg('DokuWiki version: ' . getVersion(), 1);
}
if (version_compare(phpversion(), '5.1.2', '<')) {
msg('Your PHP version is too old (' . phpversion() . ' vs. 5.1.2+ needed)', -1);
} else {
msg('PHP version ' . phpversion(), 1);
}
$mem = (int) php_to_byte(ini_get('memory_limit'));
if ($mem) {
if ($mem < 16777216) {
msg('PHP is limited to less than 16MB RAM (' . $mem . ' bytes). Increase memory_limit in php.ini', -1);
} elseif ($mem < 20971520) {
msg('PHP is limited to less than 20MB RAM (' . $mem . ' bytes), you might encounter problems with bigger pages. Increase memory_limit in php.ini', -1);
} elseif ($mem < 33554432) {
msg('PHP is limited to less than 32MB RAM (' . $mem . ' bytes), but that should be enough in most cases. If not, increase memory_limit in php.ini', 0);
} else {
msg('More than 32MB RAM (' . $mem . ' bytes) available.', 1);
}
}
if (is_writable($conf['changelog'])) {
msg('Changelog is writable', 1);
} else {
if (@file_exists($conf['changelog'])) {
msg('Changelog is not writable', -1);
}
}
if (isset($conf['changelog_old']) && @file_exists($conf['changelog_old'])) {
msg('Old changelog exists', 0);
}
if (@file_exists($conf['changelog'] . '_failed')) {
msg('Importing old changelog failed', -1);
} else {
if (@file_exists($conf['changelog'] . '_importing')) {
msg('Importing old changelog now.', 0);
} else {
if (@file_exists($conf['changelog'] . '_import_ok')) {
msg('Old changelog imported', 1);
if (!plugin_isdisabled('importoldchangelog')) {
msg('Importoldchangelog plugin not disabled after import', -1);
}
}
}
}
if (is_writable($conf['datadir'])) {
msg('Datadir is writable', 1);
} else {
msg('Datadir is not writable', -1);
}
if (is_writable($conf['olddir'])) {
msg('Attic is writable', 1);
} else {
msg('Attic is not writable', -1);
}
if (is_writable($conf['mediadir'])) {
msg('Mediadir is writable', 1);
} else {
msg('Mediadir is not writable', -1);
}
if (is_writable($conf['cachedir'])) {
msg('Cachedir is writable', 1);
} else {
msg('Cachedir is not writable', -1);
}
if (is_writable($conf['lockdir'])) {
msg('Lockdir is writable', 1);
} else {
msg('Lockdir is not writable', -1);
}
if (is_writable(DOKU_CONF)) {
msg('conf directory is writable', 1);
} else {
msg('conf directory is not writable', -1);
}
if ($conf['authtype'] == 'plain') {
global $config_cascade;
if (is_writable($config_cascade['plainauth.users']['default'])) {
msg('conf/users.auth.php is writable', 1);
} else {
msg('conf/users.auth.php is not writable', 0);
}
}
if (function_exists('mb_strpos')) {
if (defined('UTF8_NOMBSTRING')) {
msg('mb_string extension is available but will not be used', 0);
} else {
msg('mb_string extension is available and will be used', 1);
if (ini_get('mbstring.func_overload') != 0) {
msg('mb_string function overloading is enabled, this will cause problems and should be disabled', -1);
}
}
} else {
msg('mb_string extension not available - PHP only replacements will be used', 0);
}
if ($conf['allowdebug']) {
msg('Debugging support is enabled. If you don\'t need it you should set $conf[\'allowdebug\'] = 0', -1);
} else {
msg('Debugging support is disabled', 1);
}
if ($INFO['userinfo']['name']) {
msg('You are currently logged in as ' . $_SERVER['REMOTE_USER'] . ' (' . $INFO['userinfo']['name'] . ')', 0);
msg('You are part of the groups ' . join($INFO['userinfo']['grps'], ', '), 0);
} else {
msg('You are currently not logged in', 0);
}
msg('Your current permission for this page is ' . $INFO['perm'], 0);
if (is_writable($INFO['filepath'])) {
msg('The current page is writable by the webserver', 0);
} else {
msg('The current page is not writable by the webserver', 0);
}
if ($INFO['writable']) {
msg('The current page is writable by you', 0);
} else {
msg('The current page is not writable by you', 0);
}
$check = wl('', '', true) . 'data/_dummy';
$http = new DokuHTTPClient();
$http->timeout = 6;
$res = $http->get($check);
if (strpos($res, 'data directory') !== false) {
msg('It seems like the data directory is accessible from the web.
Make sure this directory is properly protected
(See <a href="http://www.dokuwiki.org/security">security</a>)', -1);
} elseif ($http->status == 404 || $http->status == 403) {
msg('The data directory seems to be properly protected', 1);
} else {
msg('Failed to check if the data directory is accessible from the web.
Make sure this directory is properly protected
(See <a href="http://www.dokuwiki.org/security">security</a>)', -1);
}
// Check for corrupted search index
$lengths = idx_listIndexLengths();
$index_corrupted = false;
foreach ($lengths as $length) {
if (count(idx_getIndex('w', $length)) != count(idx_getIndex('i', $length))) {
$index_corrupted = true;
break;
}
}
foreach (idx_getIndex('metadata', '') as $index) {
if (count(idx_getIndex($index . '_w', '')) != count(idx_getIndex($index . '_i', ''))) {
$index_corrupted = true;
break;
}
}
if ($index_corrupted) {
msg('The search index is corrupted. It might produce wrong results and most
probably needs to be rebuilt. See
<a href="http://www.dokuwiki.org/faq:searchindex">faq:searchindex</a>
for ways to rebuild the search index.', -1);
} elseif (!empty($lengths)) {
msg('The search index seems to be working', 1);
} else {
msg('The search index is empty. See
<a href="http://www.dokuwiki.org/faq:searchindex">faq:searchindex</a>
for help on how to fix the search index. If the default indexer
isn\'t used or the wiki is actually empty this is normal.');
}
}
/**
*
*/
function _loadPageIndex()
{
global $conf;
if (@file_exists($conf['indexdir'] . '/page.idx')) {
require_once DOKU_INC . 'inc/indexer.php';
$this->pageIndex = idx_getIndex('page', '');
if (count($this->pageIndex) == 0) {
throw new Exception('err_emptyidx');
}
} else {
throw new Exception('err_idxaccess');
}
}
/**
*
*/
private function loadPages()
{
global $conf;
if (file_exists($conf['indexdir'] . '/page.idx')) {
require_once DOKU_INC . 'inc/indexer.php';
$pageIndex = idx_getIndex('page', '');
$namespace = refnotes_configuration::getSetting('reference-db-namespace');
$namespacePattern = '/^' . trim($namespace, ':') . ':/';
$cache = new refnotes_reference_database_cache();
foreach ($pageIndex as $pageId) {
$pageId = trim($pageId);
if (preg_match($namespacePattern, $pageId) == 1 && file_exists(wikiFN($pageId))) {
$this->enabled = false;
$this->page[$pageId] = new refnotes_reference_database_page($this, $cache, $pageId);
$this->enabled = true;
}
}
$cache->save();
}
}
function _ft_pageLookup(&$data)
{
global $conf;
// split out original parameters
$id = $data['id'];
if (preg_match('/(?:^| )@(\\w+)/', $id, $matches)) {
$ns = cleanID($matches[1]) . ':';
$id = str_replace($matches[0], '', $id);
}
$in_ns = $data['in_ns'];
$in_title = $data['in_title'];
$pages = array_map('rtrim', idx_getIndex('page', ''));
$titles = array_map('rtrim', idx_getIndex('title', ''));
// check for corrupt title index #FS2076
if (count($pages) != count($titles)) {
$titles = array_fill(0, count($pages), '');
@unlink($conf['indexdir'] . '/title.idx');
// will be rebuilt in inc/init.php
}
$pages = array_combine($pages, $titles);
$cleaned = cleanID($id);
if ($id !== '' && $cleaned !== '') {
foreach ($pages as $p_id => $p_title) {
if (strpos($in_ns ? $p_id : noNSorNS($p_id), $cleaned) === false && (!$in_title || stripos($p_title, $id) === false)) {
unset($pages[$p_id]);
}
}
}
if (isset($ns)) {
foreach (array_keys($pages) as $p_id) {
if (strpos($p_id, $ns) !== 0) {
unset($pages[$p_id]);
}
}
}
// discard hidden pages
// discard nonexistent pages
// check ACL permissions
foreach (array_keys($pages) as $idx) {
if (!isVisiblePage($idx) || !page_exists($idx) || auth_quickaclcheck($idx) < AUTH_READ) {
unset($pages[$idx]);
}
}
uksort($pages, 'ft_pagesorter');
return $pages;
}
/**
* Builds a Google Sitemap of all public pages known to the indexer
*
* The map is placed in the root directory named sitemap.xml.gz - This
* file needs to be writable!
*
* @author Andreas Gohr
* @link https://www.google.com/webmasters/sitemaps/docs/en/about.html
*/
function runSitemapper()
{
global $conf;
print "runSitemapper(): started" . NL;
if (!$conf['sitemap']) {
return false;
}
if ($conf['compression'] == 'bz2' || $conf['compression'] == 'gz') {
$sitemap = 'sitemap.xml.gz';
} else {
$sitemap = 'sitemap.xml';
}
print "runSitemapper(): using {$sitemap}" . NL;
if (@file_exists(DOKU_INC . $sitemap)) {
if (!is_writable(DOKU_INC . $sitemap)) {
return false;
}
} else {
if (!is_writable(DOKU_INC)) {
return false;
}
}
if (@filesize(DOKU_INC . $sitemap) && @filemtime(DOKU_INC . $sitemap) > time() - $conf['sitemap'] * 60 * 60 * 24) {
print 'runSitemapper(): Sitemap up to date' . NL;
return false;
}
$pages = idx_getIndex('page', '');
print 'runSitemapper(): creating sitemap using ' . count($pages) . ' pages' . NL;
// build the sitemap
ob_start();
print '<?xml version="1.0" encoding="UTF-8"?>' . NL;
print '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' . NL;
foreach ($pages as $id) {
$id = trim($id);
$file = wikiFN($id);
//skip hidden, non existing and restricted files
if (isHiddenPage($id)) {
continue;
}
$date = @filemtime($file);
if (!$date) {
continue;
}
if (auth_aclcheck($id, '', '') < AUTH_READ) {
continue;
}
print ' <url>' . NL;
print ' <loc>' . wl($id, '', true) . '</loc>' . NL;
print ' <lastmod>' . date_iso8601($date) . '</lastmod>' . NL;
print ' </url>' . NL;
}
print '</urlset>' . NL;
$data = ob_get_contents();
ob_end_clean();
//save the new sitemap
io_saveFile(DOKU_INC . $sitemap, $data);
//ping search engines...
$http = new DokuHTTPClient();
$http->timeout = 8;
//ping google
print 'runSitemapper(): pinging google' . NL;
$url = 'http://www.google.com/webmasters/sitemaps/ping?sitemap=';
$url .= urlencode(DOKU_URL . $sitemap);
$resp = $http->get($url);
if ($http->error) {
print 'runSitemapper(): ' . $http->error . NL;
}
print 'runSitemapper(): ' . preg_replace('/[\\n\\r]/', ' ', strip_tags($resp)) . NL;
//ping yahoo
print 'runSitemapper(): pinging yahoo' . NL;
$url = 'http://search.yahooapis.com/SiteExplorerService/V1/updateNotification?appid=dokuwiki&url=';
$url .= urlencode(DOKU_URL . $sitemap);
$resp = $http->get($url);
if ($http->error) {
print 'runSitemapper(): ' . $http->error . NL;
}
print 'runSitemapper(): ' . preg_replace('/[\\n\\r]/', ' ', strip_tags($resp)) . NL;
//ping microsoft
print 'runSitemapper(): pinging microsoft' . NL;
$url = 'http://www.bing.com/webmaster/ping.aspx?siteMap=';
$url .= urlencode(DOKU_URL . $sitemap);
$resp = $http->get($url);
if ($http->error) {
print 'runSitemapper(): ' . $http->error . NL;
}
print 'runSitemapper(): ' . preg_replace('/[\\n\\r]/', ' ', strip_tags($resp)) . NL;
print 'runSitemapper(): finished' . NL;
return true;
}
