function dw_get_pages($dir)
{
static $trunclen = null;
if (!$trunclen) {
global $conf;
$trunclen = strlen($conf['datadir'] . ':');
}
if (!is_dir($dir)) {
fwrite(STDERR, "Unable to read directory {$dir}\n");
exit(1);
}
$pages = array();
$dh = opendir($dir);
while (false !== ($entry = readdir($dh))) {
$status = dw_dir_filter($entry, $dir);
if ($status == DW_DIR_CONTINUE) {
continue;
} else {
if ($status == DW_DIR_NS) {
$pages = array_merge($pages, dw_get_pages($dir . '/' . $entry));
} else {
$page = array('id' => pathID(substr($dir . '/' . $entry, $trunclen)), 'file' => $dir . '/' . $entry);
$pages[] = $page;
}
}
}
closedir($dh);
return $pages;
}
/**
* Search for internal wiki links in page $file
*/
function orph_Check_InternalLinks(&$data, $base, $file, $type, $lvl, $opts)
{
global $conf;
define('LINK_PATTERN', '%\\[\\[([^\\]|#]*)(#[^\\]|]*)?\\|?([^\\]]*)]]%');
if (!preg_match("/.*\\.txt\$/", $file)) {
return;
}
$currentID = pathID($file);
$currentNS = getNS($currentID);
if ($conf['allowdebug']) {
echo sprintf("<p><b>%s</b>: %s</p>\n", $file, $currentID);
}
// echo " <!-- checking file: $file -->\n";
$body = @file_get_contents($conf['datadir'] . $file);
// ignores entries in <nowiki>, %%, <code> and emails with @
foreach (array('/<nowiki>.*?<\\/nowiki>/', '/%%.*?%%/', '@<code[^>]*?>.*?<\\/code>@siu', '@<file[^>]*?>.*?<\\/file>@siu') as $ignored) {
$body = preg_replace($ignored, '', $body);
}
$links = array();
preg_match_all(LINK_PATTERN, $body, $links);
foreach ($links[1] as $link) {
if ($conf['allowdebug']) {
echo sprintf("--- Checking %s<br />\n", $link);
}
if (0 < strlen(ltrim($link)) and !preg_match('/^[a-zA-Z0-9\\.]+>{1}.*$/u', $link) and !preg_match('/^\\\\\\\\[\\w.:?\\-;,]+?\\\\/u', $link) and !preg_match('#^([a-z0-9\\-\\.+]+?)://#i', $link) and !preg_match('<' . PREG_PATTERN_VALID_EMAIL . '>', $link) and !preg_match('!^#.+!', $link)) {
$pageExists = false;
resolve_pageid($currentNS, $link, $pageExists);
if ($conf['allowdebug']) {
echo sprintf("---- link='%s' %s ", $link, $pageExists ? 'EXISTS' : 'MISS');
}
if (strlen(ltrim($link)) > 0 and !auth_quickaclcheck($link) < AUTH_READ) {
// should be visible to user
//echo " <!-- adding $link -->\n";
if ($conf['allowdebug']) {
echo ' A_LINK';
}
$link = utf8_strtolower($link);
$this->orph_handle_link($data, $link);
} else {
if ($conf['allowdebug']) {
echo ' EMPTY_OR_FORBIDDEN';
}
}
} else {
if ($conf['allowdebug']) {
echo ' NOT_INTERNAL';
}
}
if ($conf['allowdebug']) {
echo "<br />\n";
}
}
// end of foreach link
}
function indexmenu_search_index(&$data, $base, $file, $type, $lvl, $opts)
{
global $conf;
$ret = true;
$item = array();
if ($type == 'f' && !preg_match('#\\.txt$#', $file)) {
// don't add
return false;
}
// get page id by filename
$id = pathID($file);
// check hiddens
if ($type == 'f' && isHiddenPage($id)) {
return false;
}
// bugfix for the
// /ns/
// /<ns>.txt
// case, need to force the 'directory' type
if ($type == 'f' && file_exists(dirname(wikiFN($id . ":" . noNS($id))))) {
$type = 'd';
}
// page target id = global id
$target = $id;
if ($type == 'd') {
// this will check 3 kinds of headpage:
// 1. /<ns>/<ns>.txt
// 2. /<ns>/
// /<ns>.txt
// 3. /<ns>/
// /<ns>/<start_page>
$nsa = array($id . ":" . noNS($id), $id, $id . ":" . $conf['start']);
$nspage = false;
foreach ($nsa as $nsp) {
if (@file_exists(wikiFN($nsp)) && auth_quickaclcheck($nsp) >= AUTH_READ) {
$nspage = $nsp;
break;
}
}
//headpage exists
if ($nspage) {
$target = $nspage;
} else {
// open namespace index, if headpage does not exists
$target = $target . ':';
}
}
$data[] = array('id' => $id, 'date' => @filectime(wikiFN($target)), 'type' => $type, 'target' => $target, 'title' => $conf['useheading'] && ($title = p_get_first_heading($target)) ? $title : $id, 'level' => $lvl);
if (substr_count($id, ":") > 2) {
$ret = 0;
}
return $ret;
}
/**
* function for the search callback
*/
function search_discussionpages(&$data, $base, $file, $type, $lvl, $opts)
{
global $conf;
if ($type == 'd') {
return true;
}
// recurse into directories
if (!preg_match('#' . preg_quote('/' . DISCUSSION_NS . '/', '#') . '#u', $file)) {
return false;
}
if (!preg_match('#\\.txt$#', $file)) {
return false;
}
$id = pathID(str_replace(DISCUSSION_NS . '/', '', $file));
$data[] = array('id' => $id, 'old' => $conf['datadir'] . $file, 'new' => metaFN($id, '.comments'));
return true;
}
/**
* This is a very universal callback for the search() function, replacing
* many of the former individual functions at the cost of a more complex
* setup.
*
* How the function behaves, depends on the options passed in the $opts
* array, where the following settings can be used.
*
* depth int recursion depth. 0 for unlimited
* keeptxt bool keep .txt extension for IDs
* listfiles bool include files in listing
* listdirs bool include namespaces in listing
* pagesonly bool restrict files to pages
* skipacl bool do not check for READ permission
* sneakyacl bool don't recurse into nonreadable dirs
* hash bool create MD5 hash for files
* meta bool return file metadata
* filematch string match files against this regexp
* idmatch string match full ID against this regexp
* dirmatch string match directory against this regexp when adding
* nsmatch string match namespace against this regexp when adding
* recmatch string match directory against this regexp when recursing
* showmsg bool warn about non-ID files
* showhidden bool show hidden files too
* firsthead bool return first heading for pages
*
* @author Andreas Gohr <*****@*****.**>
*/
function search_universal(&$data, $base, $file, $type, $lvl, $opts)
{
$item = array();
$return = true;
// get ID and check if it is a valid one
$item['id'] = pathID($file);
if ($item['id'] != cleanID($item['id'])) {
if ($opts['showmsg']) {
msg(hsc($item['id']) . ' is not a valid file name for DokuWiki - skipped', -1);
}
return false;
// skip non-valid files
}
$item['ns'] = getNS($item['id']);
if ($type == 'd') {
// decide if to recursion into this directory is wanted
if (!$opts['depth']) {
$return = true;
// recurse forever
} else {
$depth = substr_count($file, '/');
if ($depth >= $opts['depth']) {
$return = false;
// depth reached
} else {
$return = true;
}
}
if ($return && !preg_match('/' . $opts['recmatch'] . '/', $file)) {
$return = false;
// doesn't match
}
}
// check ACL
if (!$opts['skipacl']) {
if ($type == 'd') {
$item['perm'] = auth_quickaclcheck($item['id'] . ':*');
} else {
$item['perm'] = auth_quickaclcheck($item['id']);
//FIXME check namespace for media files
}
} else {
$item['perm'] = AUTH_DELETE;
}
// are we done here maybe?
if ($type == 'd') {
if (!$opts['listdirs']) {
return $return;
}
if (!$opts['skipacl'] && $opts['sneakyacl'] && $item['perm'] < AUTH_READ) {
return false;
}
//neither list nor recurse
if ($opts['dirmatch'] && !preg_match('/' . $opts['dirmatch'] . '/', $file)) {
return $return;
}
if ($opts['nsmatch'] && !preg_match('/' . $opts['nsmatch'] . '/', $item['ns'])) {
return $return;
}
} else {
if (!$opts['listfiles']) {
return $return;
}
if (!$opts['skipacl'] && $item['perm'] < AUTH_READ) {
return $return;
}
if ($opts['pagesonly'] && substr($file, -4) != '.txt') {
return $return;
}
if (!$conf['showhidden'] && isHiddenPage($id)) {
return $return;
}
if ($opts['filematch'] && !preg_match('/' . $opts['filematch'] . '/', $file)) {
return $return;
}
if ($opts['idmatch'] && !preg_match('/' . $opts['idmatch'] . '/', $item['id'])) {
return $return;
}
}
// still here? prepare the item
$item['type'] = $type;
$item['level'] = $lvl;
$item['open'] = $return;
if ($opts['meta']) {
$item['file'] = basename($file);
$item['size'] = filesize($base . '/' . $file);
$item['mtime'] = filemtime($base . '/' . $file);
$item['rev'] = $item['mtime'];
$item['writable'] = is_writable($base . '/' . $file);
$item['executable'] = is_executable($base . '/' . $file);
}
if ($type == 'f') {
if ($opts['hash']) {
$item['hash'] = md5(io_readFile($base . '/' . $file, false));
}
if ($opts['firsthead']) {
$item['title'] = p_get_first_heading($item['id'], false);
}
}
// finally add the item
$data[] = $item;
return $return;
}
function orph_search_wanted(&$data, $base, $file, $type, $lvl, $opts)
{
if ($type == 'd') {
return true;
// recurse all directories, but we don't store namespaces
}
if (!preg_match("/.*\\.txt\$/", $file)) {
// Ignore everything but TXT
return true;
}
// search the body of the file for links
// dae mod
// orph_Check_InternalLinks(&$data,$base,$file,$type,$lvl,$opts);
orph_Check_InternalLinks($data, $base, $file, $type, $lvl, $opts);
// get id of this file
$id = pathID($file);
//check ACL
if (auth_quickaclcheck($id) < AUTH_READ) {
return false;
}
// try to avoid making duplicate entries for forms and pages
$item =& $data["{$id}"];
if (isset($item)) {
// This item already has a member in the array
// Note that the file search found it
$item['exists'] = true;
} else {
// Create a new entry
$data["{$id}"] = array('exists' => true, 'links' => 0);
}
return true;
}
/**
* fulltext search helper
* searches a text file with a given regular expression
* no ACL checks are performed. This have to be done by
* the caller if necessary.
*
* @param array $data reference to array for results
* @param string $base base directory
* @param string $file file name to search in
* @param string $reg regular expression to search for
* @param array $words words that should be marked in the results
*
* @author Andreas Gohr <*****@*****.**>
* @author Matthias Grimm <*****@*****.**>
*
* @deprecated - fulltext indexer is used instead
*/
function search_regex(&$data, $base, $file, $reg, $words)
{
//get text
$text = io_readfile($base . '/' . $file);
//lowercase text (u modifier does not help with case)
$lctext = utf8_strtolower($text);
//do the fulltext search
$matches = array();
if ($cnt = preg_match_all('#' . $reg . '#usi', $lctext, $matches)) {
//this is not the best way for snippet generation but the fastest I could find
$q = $words[0];
//use first word for snippet creation
$p = utf8_strpos($lctext, $q);
$f = $p - 100;
$l = utf8_strlen($q) + 200;
if ($f < 0) {
$f = 0;
}
$snippet = '<span class="search_sep"> ... </span>' . htmlspecialchars(utf8_substr($text, $f, $l)) . '<span class="search_sep"> ... </span>';
$mark = '(' . join('|', $words) . ')';
$snippet = preg_replace('#' . $mark . '#si', '<strong class="search_hit">\\1</strong>', $snippet);
$data[] = array('id' => pathID($file), 'count' => preg_match_all('#' . $mark . '#usi', $lctext, $matches), 'poswords' => join(' ', $words), 'snippet' => $snippet);
}
return true;
}
/**
* Expire the renderer cache of archive pages whenever a page is updated or a comment or linkback is added
*
* @author Michael Hamann <*****@*****.**>
*/
function handle_cache(Doku_Event $event, $params)
{
global $conf;
/** @var cache_parser $cache */
$cache = $event->data;
if (!in_array($cache->mode, array('xhtml', 'metadata'))) {
return;
}
$page = $cache->page;
// try to extract the page id from the file if possible
if (empty($page)) {
if (strpos($cache->file, $conf['datadir']) === 0) {
$page = pathID(substr($cache->file, strlen($conf['datadir']) + 1));
} else {
return;
}
}
$meta = p_get_metadata($page, 'plugin_blog');
if ($meta === null) {
return;
}
if (isset($meta['purgefile_cache'])) {
$cache->depends['files'][] = $conf['cachedir'] . '/purgefile';
$cache->depends['files'][] = $conf['metadir'] . '/_comments.changes';
$cache->depends['files'][] = $conf['metadir'] . '/_linkbacks.changes';
}
// purge the cache when a page is listed that the current user can't access
if (isset($meta['archive_pages'])) {
foreach ($meta['archive_pages'] as $page) {
if (auth_quickaclcheck($page) < AUTH_READ) {
$cache->depends['purge'] = true;
return;
}
}
}
}
/**
* Build the browsable index of pages
*
* $opts['ns'] is the current namespace
*
* @author Andreas Gohr <*****@*****.**>
* modified by Samuele Tognini <*****@*****.**>
*/
function _search_index(&$data, $base, $file, $type, $lvl, $opts)
{
global $conf;
$hns = false;
$return = false;
$isopen = false;
$skip_index = $opts['skip_index'];
$skip_file = $opts['skip_file'];
$headpage = $opts['headpage'];
$id = pathID($file);
if ($type == 'd') {
// Skip folders in plugin conf
if (!empty($skip_index) && preg_match($skip_index, $id)) {
return false;
}
//check ACL (for sneaky_index namespaces too).
if ($this->getConf('sneaky_index') && auth_quickaclcheck($id . ':') < AUTH_READ) {
return false;
}
//Open requested level
if ($opts['level'] > $lvl || $opts['level'] == -1) {
$isopen = true;
}
//Search optional namespaces
if (!empty($opts['nss'])) {
$nss = $opts['nss'];
for ($a = 0; $a < count($nss); $a++) {
if (preg_match("/^" . $id . "(\$|:.+)/i", $nss[$a][0], $match)) {
//It contains an optional namespace
$isopen = true;
} elseif (preg_match("/^" . $nss[$a][0] . "(:.*)/i", $id, $match)) {
//It's inside an optional namespace
if ($nss[$a][1] == -1 || substr_count($match[1], ":") < $nss[$a][1]) {
$isopen = true;
} else {
$isopen = false;
}
}
}
}
if ($opts['nons']) {
return $isopen;
} elseif ($opts['max'] > 0 && !$isopen && $lvl >= $opts['max']) {
$isopen = false;
//Stop recursive searching
$return = false;
//change type
$type = "l";
} elseif ($opts['js']) {
$return = true;
} else {
$return = $isopen;
}
//Set title and headpage
$title = $this->_getTitle($id, $headpage, $hns);
if (!$hns && $opts['nopg']) {
$hns = $id . ":" . $conf['start'];
}
} else {
//Nopg.Dont show pages
if ($opts['nopg']) {
return false;
}
$return = true;
//Nons.Set all pages at first level
if ($opts['nons']) {
$lvl = 1;
}
//don't add
if (substr($file, -4) != '.txt') {
return false;
}
//check hiddens and acl
if (isHiddenPage($id) || auth_quickaclcheck($id) < AUTH_READ) {
return false;
}
//Skip files in plugin conf
if (!empty($skip_file) && preg_match($skip_file, $id)) {
return false;
}
//Skip headpages to hide
if (!$opts['nons'] && !empty($headpage) && $opts['hide_headpage']) {
if ($id == $conf['start']) {
return false;
}
$ahp = explode(",", $headpage);
foreach ($ahp as $hp) {
switch ($hp) {
case ":inside:":
if (noNS($id) == noNS(getNS($id))) {
return false;
}
break;
case ":same:":
if (@is_dir(dirname(wikiFN($id)) . "/" . utf8_encodeFN(noNS($id)))) {
return false;
}
break;
//it' s an inside start
//it' s an inside start
case ":start:":
if (noNS($id) == $conf['start']) {
return false;
}
break;
default:
if (noNS($id) == cleanID($hp)) {
return false;
}
}
}
}
//Set title
if (!$conf['useheading'] || !($title = p_get_first_heading($id, FALSE))) {
$title = noNS($id);
}
$title = htmlspecialchars($title, ENT_QUOTES);
}
$item = array('id' => $id, 'type' => $type, 'level' => $lvl, 'open' => $isopen, 'title' => $title, 'hns' => $hns, 'file' => $file, 'return' => $return);
$item['sort'] = $this->_setorder($item);
$data[] = $item;
return $return;
}
/**
* Handle the cache events, it looks if a page needs to be rewritten so it can expire the cache of the page
*
* @param Doku_Event $event The even object
* @param mixed $param Optional parameters (not used)
*/
function handle_cache(Doku_Event $event, $param)
{
global $conf;
/** @var $cache cache_parser */
$cache = $event->data;
$id = $cache->page;
if (!$id) {
// try to reconstruct the id from the filename
$path = $cache->file;
if (strpos($path, $conf['datadir']) === 0) {
$path = substr($path, strlen($conf['datadir']) + 1);
$id = pathID($path);
}
}
if ($id) {
/** @var helper_plugin_move_rewrite $helper */
$helper = $this->loadHelper('move_rewrite');
if (!is_null($helper)) {
$meta = $helper->getMoveMeta($id);
if ($meta && ($meta['pages'] || $meta['media'])) {
$file = wikiFN($id, '', false);
if (is_writable($file)) {
$cache->depends['purge'] = true;
} else {
// FIXME: print error here or fail silently?
msg('Error: Page ' . hsc($id) . ' needs to be rewritten because of page renames but is not writable.', -1);
}
}
}
}
}
protected function get_pages($dir)
{
static $trunclen = null;
if (!$trunclen) {
global $conf;
$trunclen = strlen($conf['datadir'] . ':');
}
if (!is_dir($dir)) {
throw new DokuCLI_Exception("Unable to read directory {$dir}");
}
$pages = array();
$dh = opendir($dir);
while (false !== ($entry = readdir($dh))) {
$status = $this->dir_filter($entry, $dir);
if ($status == WantedPagesCLI::DIR_CONTINUE) {
continue;
} else {
if ($status == WantedPagesCLI::DIR_NS) {
$pages = array_merge($pages, $this->get_pages($dir . '/' . $entry));
} else {
$page = array('id' => pathID(substr($dir . '/' . $entry, $trunclen)), 'file' => $dir . '/' . $entry);
$pages[] = $page;
}
}
}
closedir($dh);
return $pages;
}
/**
* Handle the cache events, it looks if a page needs to be rewritten so it can expire the cache of the page
*
* @param Doku_Event $event The even object
* @param mixed $param Optional parameters (not used)
*/
function handle_cache(Doku_Event $event, $param) {
global $conf;
/** @var $cache cache_parser */
$cache = $event->data;
$id = $cache->page;
if (!$id) {
// try to reconstruct the id from the filename
$path = $cache->file;
if (strpos($path, $conf['datadir']) === 0) {
$path = substr($path, strlen($conf['datadir'])+1);
$id = pathID($path);
}
}
if ($id) {
$meta = p_get_metadata($id, 'plugin_move', METADATA_DONT_RENDER);
if ($meta && (isset($meta['moves']) || isset($meta['media_moves']))) {
$file = wikiFN($id, '', false);
if (is_writable($file))
$cache->depends['purge'] = true;
else // FIXME: print error here or fail silently?
msg('Error: Page '.hsc($id).' needs to be rewritten because of page renames but is not writable.', -1);
}
}
}
/**
* search callback function
*
* filter out pages which can't be approved by the current user
* then check if they need approving
*/
function _search_helper(&$data, $base, $file, $type, $lvl, $opts)
{
$ns = $opts[0];
$valid_ns = $opts[1];
$invalid_ns = $opts[2];
if ($type == 'd') {
return $this->hlp->in_sub_namespace($valid_ns, $ns . ':' . str_replace('/', ':', $file));
}
if (!preg_match('#\\.txt$#', $file)) {
return false;
}
$id = pathID($ns . $file);
if (!$this->hlp->in_namespace($valid_ns, $id)) {
return false;
}
if ($this->hlp->in_namespace($invalid_ns, $id)) {
return false;
}
if (auth_quickaclcheck($id) < AUTH_DELETE) {
return false;
}
$meta = $this->hlp->getMeta($id);
if ($this->hlp->isCurrentRevisionApproved($id)) {
// Already approved
return false;
}
$data[] = array($id, $meta['approval'], $meta['last_change']['date']);
return false;
}
/**
* Just lists all documents
*
* $opts['depth'] recursion level, 0 for all
* $opts['hash'] do md5 sum of content?
* $opts['skipacl'] list everything regardless of ACL
*
* @param $data
* @param $base
* @param $file
* @param $type
* @param $lvl
* @param $opts
* @return bool
*/
public static function save_search_allpages(&$data, $base, $file, $type, $lvl, $opts)
{
if (!empty($opts['depth'])) {
$parts = explode('/', ltrim($file, '/'));
if ($type == 'd' && count($parts) >= $opts['depth'] || $type != 'd' && count($parts) > $opts['depth']) {
return false;
// depth reached
}
}
//we do nothing with directories
if ($type == 'd') {
return true;
}
//only search txt files
if (substr($file, -4) != '.txt') {
return true;
}
$pathId = pathID($file);
if (!$opts['skipacl'] && auth_quickaclcheck($pathId) < AUTH_READ) {
return false;
}
file_put_contents(self::$tempFileName, "{$pathId}\n", FILE_APPEND);
self::$totalPagesToIndex++;
return true;
}
