if (isset($_SESSION['sniff_navigator']) && $_SESSION['sniff_navigator']!="checked") {
$_SESSION['sniff_navigator']=Security::remove_XSS($_POST['sniff_navigator']);
$_SESSION['sniff_screen_size_w']=Security::remove_XSS($_POST['sniff_navigator_screen_size_w']);
$_SESSION['sniff__screen_size_h']=Security::remove_XSS($_POST['sniff_navigator_screen_size_h']);
$_SESSION['sniff_type_mimetypes']=Security::remove_XSS($_POST['sniff_navigator_type_mimetypes']);
$_SESSION['sniff_suffixes_mimetypes']=Security::remove_XSS($_POST['sniff_navigator_suffixes_mimetypes']);
$_SESSION['sniff_list_plugins']=Security::remove_XSS($_POST['sniff_navigator_list_plugins']);
$_SESSION['sniff_check_some_activex']=Security::remove_XSS($_POST['sniff_navigator_check_some_activex']);
$_SESSION['sniff_check_some_plugins']=Security::remove_XSS($_POST['sniff_navigator_check_some_plugins']);
$_SESSION['sniff_java']=Security::remove_XSS($_POST['sniff_navigator_java']);
$_SESSION['sniff_java_sun_ver']=Security::remove_XSS($_POST['sniff_navigator_java_sun_ver']);
}
*/
/* MAIN CODE */
$controller = new IndexManager(get_lang('MyCourses'));
// Main courses and session list
$courses_and_sessions = $controller->return_courses_and_sessions($user_id);
//Show the chamilo mascot
if (empty($courses_and_sessions) && !isset($_GET['history'])) {
$controller->tpl->assign('welcome_to_course_block', $controller->return_welcome_to_course_block());
}
$controller->tpl->assign('content', $courses_and_sessions);
if (api_get_setting('allow_browser_sniffer') == 'true') {
if ($_SESSION['sniff_navigator']!="checked") {
$cidReset = true;
require_once 'main/inc/global.inc.php';
require_once 'main/chat/chat_functions.lib.php';
//require_once 'main/auth/external_login/facebook.inc.php';
// The section (for the tabs).
$this_section = SECTION_CAMPUS;
$header_title = null;
if (!api_is_anonymous()) {
$header_title = " ";
}
// Facebook connexion, if activated
/*if (api_is_facebook_auth_activated() && !api_get_user_id()) {
facebookConnect();
}
*/
$controller = new IndexManager($header_title);
//Actions
$loginFailed = isset($_GET['loginFailed']) ? true : isset($loginFailed);
if (!empty($_GET['logout'])) {
$redirect = !empty($_GET['no_redirect']) ? false : true;
$controller->logout($redirect);
}
/* Table definitions */
/* Constants and CONFIGURATION parameters */
/** @todo these configuration settings should move to the Chamilo config settings. */
/** Defines wether or not anonymous visitors can see a list of the courses on the Chamilo homepage that are open to the world. */
$_setting['display_courses_to_anonymous_users'] = 'true';
/* LOGIN */
/**
* Registers in the track_e_default table (view in important activities in admin
* interface) a possible attempted break in, sending auth data through get.
*/
function changeMyCoursesView(inView)
{
$.cookie("defaultMyCourseView"+userId, inView, { expires: 365 });
if (inView == ' . IndexManager::VIEW_BY_SESSION . ') {
$("#viewBySession").addClass("btn-primary");
$("#viewByDefault").removeClass("btn-primary");
} else {
$("#viewByDefault").addClass("btn-primary");
$("#viewBySession").removeClass("btn-primary");
}
}
</script>
';
}
$controller = new IndexManager(get_lang('MyCourses'));
// Main courses and session list
//$courseAndSessions = $controller->returnCoursesAndSessions($userId);
// Main courses and session list
if (isset($_COOKIE['defaultMyCourseView' . $userId]) && $_COOKIE['defaultMyCourseView' . $userId] == IndexManager::VIEW_BY_SESSION && $displayMyCourseViewBySessionLink) {
$courseAndSessions = $controller->returnCoursesAndSessionsViewBySession($userId);
IndexManager::setDefaultMyCourseView(IndexManager::VIEW_BY_SESSION, $userId);
} else {
$courseAndSessions = $controller->returnCoursesAndSessions($userId);
IndexManager::setDefaultMyCourseView(IndexManager::VIEW_BY_DEFAULT, $userId);
}
// if teacher, session coach or admin, display the button to change te course view
if ($displayMyCourseViewBySessionLink && (api_is_drh() || api_is_course_coach() || api_is_platform_admin() || api_is_session_admin() || api_is_teacher())) {
$courseAndSessions['html'] = "<div class='view-by-session-link'>\n\t\t<div class='btn-group pull-right'>\n\t\t<a class='btn btn-default' id='viewByDefault' href='user_portal.php' onclick='changeMyCoursesView(\"" . IndexManager::VIEW_BY_DEFAULT . "\")'>\n\t\t" . get_lang('MyCoursesDefaultView') . "\n\t\t</a>\n\t\t<a class='btn btn-default' id='viewBySession' href='user_portal.php' onclick='changeMyCoursesView(\"" . IndexManager::VIEW_BY_SESSION . "\")'>\n\t\t" . get_lang('MyCoursesSessionView') . "\n\t\t</a>\n\t\t</div>\n\t</div><br /><br />\n\t" . $courseAndSessions['html'];
}
// Check if a user is enrolled only in one course for going directly to the course after the login.
/**
* Ensure the indexes to the database
*
* @param boolean $delete (optional) true by default drop unknown and old indexes
*
* @return boolean
*
* @api
*/
public function ensureIndexes($delete = true)
{
$indexManager = new IndexManager($this);
return $indexManager->commit($delete);
}
/**
* Extracts all phrases (sequences of adjacent words) from $string. Does
* not extract terms within those phrase. Array key indicates position
* of phrase
*
* @param string $string subject to extract phrases from
* @param string $lang locale tag for stemming
* @param string $index_name name of index to be used as a reference
* when extracting phrases
* @param bool $exact_match whether the match has to be exact or not
* @param int $threshold roughly causes a stop to extracting more phrases
* if exceed $threshold (still might get more than $threshold back, only
* when detect have more stop)
* @return array of phrases
*/
static function extractPhrases($string, $lang = NULL, $index_name = NULL, $exact_match = false, $threshold = 10)
{
if (isset(self::$programming_language_map[$lang])) {
$control_word = self::$programming_language_map[$lang] . self::CONTROL_WORD_INDICATOR;
$string = trim(substr($string, strlen($control_word) + 1));
} else {
self::canonicalizePunctuatedTerms($string, $lang);
}
$terms = self::stemCharGramSegment($string, $lang);
$num = count($terms);
if ($index_name == NULL || $num <= 1) {
return $terms;
}
if (count($terms) > MAX_QUERY_TERMS) {
$first_terms = array_slice($terms, 0, MAX_QUERY_TERMS);
$whole_phrase = implode(" ", $first_terms);
} else {
$whole_phrase = implode(" ", $terms);
$first_terms =& $terms;
}
if ($exact_match) {
return $terms;
/* for exact phrase search do not use suffix tree
stuff for now
*/
}
$count_whole_phrase = IndexManager::numDocsTerm($whole_phrase, $index_name, $threshold);
if ($count_whole_phrase >= $threshold || $num > SUFFIX_TREE_THRESHOLD) {
$terms = array($whole_phrase, $terms[0]);
return $terms;
} else {
if ($count_whole_phrase > 0) {
foreach ($terms as $term) {
$count_term = IndexManager::numDocsTerm($term, $index_name, 5 * $threshold);
if ($count_term > 50 * $count_whole_phrase) {
$terms = array($whole_phrase, $terms[0]);
return $terms;
}
}
} else {
if ($num > 2) {
$start_terms = $first_terms;
$last_term = array_pop($start_terms);
$start_phrase = implode(" ", $start_terms);
$count_start = IndexManager::numDocsTerm($start_phrase, $index_name, $threshold);
if ($count_start >= $threshold) {
$terms = array($start_phrase, $last_term, $terms[0]);
return $terms;
}
$end_terms = $first_terms;
$first_term = array_shift($end_terms);
$end_phrase = implode(" ", $end_terms);
$count_end = IndexManager::numDocsTerm($end_phrase, $index_name, $threshold);
if ($count_end >= $threshold) {
$terms = array($first_term, $end_phrase);
return $terms;
}
}
}
}
if ($index_name != 'feed' && IndexManager::getVersion($index_name) == 0) {
return $terms;
//old style index before max phrase extraction
}
return $terms;
}
exit;
}
$userResetPasswordSetting = api_get_setting('user_reset_password');
if ($userResetPasswordSetting === 'true') {
$user = Database::getManager()->getRepository('ChamiloUserBundle:User')->find($user['uid']);
Login::sendResetEmail($user, true);
if (CustomPages::enabled() && CustomPages::exists(CustomPages::INDEX_UNLOGGED)) {
CustomPages::display(CustomPages::INDEX_UNLOGGED, ['info' => get_lang('CheckYourEmailAndFollowInstructions')]);
exit;
}
header('Location: ' . api_get_path(WEB_PATH));
exit;
}
$messageText = Login::handle_encrypted_password($user, true);
if (CustomPages::enabled() && CustomPages::exists(CustomPages::INDEX_UNLOGGED)) {
CustomPages::display(CustomPages::INDEX_UNLOGGED, ['info' => $messageText]);
exit;
}
Display::addFlash(Display::return_message($messageText));
header('Location: ' . api_get_path(WEB_PATH));
exit;
}
if (CustomPages::enabled() && CustomPages::exists(CustomPages::LOST_PASSWORD)) {
CustomPages::display(CustomPages::LOST_PASSWORD, ['form' => $form->returnForm()]);
exit;
}
$controller = new IndexManager($tool_name);
$controller->set_login_form();
$controller->tpl->assign('form', $form->returnForm());
$template = $controller->tpl->get_template('auth/lost_password.tpl');
$controller->tpl->display($template);
/**
* Returns the number of documents in an index that a phrase occurs in.
* If it occurs in more than threshold documents then cut off search.
*
* @param string $phrase to look up in index
* @param int $threshold once count in posting list for any word
* reaches to threshold then return the number
* @param string $index_name selected index for search engine
* @param string $lang locale tag for the query
* @return int number of documents phrase occurs in
*/
static function numDocsIndex($phrase, $threshold, $index_name, $lang)
{
PhraseParser::canonicalizePunctuatedTerms($phrase, $lang);
$terms = PhraseParser::stemCharGramSegment($phrase, $lang);
$num = count($terms);
if ($index_name == NULL) {
return 0;
}
if (count($terms) > MAX_QUERY_TERMS) {
$terms = array_slice($terms, 0, MAX_QUERY_TERMS);
}
$whole_phrase = implode(" ", $terms);
return IndexManager::numDocsTerm($whole_phrase, $index_name, $threshold);
}
/**
* Hook function used by currentDocsWithWord to return the current block
* of docs if it is not cached
*
* @return mixed doc ids and score if there are docs left, -1 otherwise
*/
function findDocsWithWord()
{
if ($this->current_generation >= $this->num_generations || $this->current_generation == $this->num_generations - 1 && $this->current_offset > $this->last_offset) {
return -1;
}
$pre_results = array();
$this->next_offset = $this->current_offset;
$index = IndexManager::getIndex($this->index_name);
$index->setCurrentShard($this->current_generation, true);
//the next call also updates next offset
$shard = $index->getCurrentShard();
$this->getShardInfo($this->current_generation);
$doc_key_len = IndexShard::DOC_KEY_LEN;
$num_docs_or_links = $shard->num_docs + $shard->num_link_docs;
$pre_results = array();
$num_docs_so_far = 0;
do {
if ($this->next_offset >= $this->last_offset) {
break;
}
$posting = packPosting($this->next_offset >> 4, array(1));
list($doc_id, $num_keys, $item) = $shard->makeItem($posting, $num_docs_or_links);
if ($num_keys % 2 == 0) {
$num_keys++;
}
$this->next_offset += ($num_keys + 1) * $doc_key_len;
$pre_results[$doc_id] = $item;
$num_docs_so_far++;
} while ($num_docs_so_far < $this->results_per_block);
$results = array();
$doc_key_len = IndexShard::DOC_KEY_LEN;
$filter = $this->filter == NULL ? array() : $this->filter;
foreach ($pre_results as $keys => $data) {
$host_key = substr($keys, self::HOST_KEY_POS, self::KEY_LEN);
if (in_array($host_key, $filter)) {
continue;
}
$data[self::KEY] = $keys;
// inlinks is the domain of the inlink
list($hash_url, $data[self::HASH], $data[self::INLINKS]) = str_split($keys, $doc_key_len);
$data[self::CRAWL_TIME] = $this->index_name;
$results[$keys] = $data;
}
$this->count_block = count($results);
if ($this->current_generation == $this->num_generations - 1 && $results == array()) {
$results = NULL;
}
$this->pages = $results;
return $results;
}
/**
* Using the supplied $word_structs, contructs an iterator for getting
* results to a query
*
* @param array $word_structs an array of word_structs. Here a word_struct
* is an associative array with at least the following fields
* KEYS -- an array of word keys
* QUOTE_POSITIONS -- an array of positions of words that appreared in
* quotes (so need to be matched exactly)
* DISALLOW_PHRASES -- an array of words the document must not contain
* WEIGHT -- a weight to multiple scores returned from this iterator by
* INDEX_NAME -- an index timestamp to get results from
* @param array& $filter an array of hashes of domains to filter from
* results
* and then potentially restored in cache
* @param int $raw ($raw == 0) normal grouping, ($raw == 1)
* no grouping done on data also no summaries returned (only lookup
* info), $raw > 1 return summaries but no grouping
* @param int $to_retrieve number of items to retrieve from location in
* in interator
* @param array $queue_servers a list of urls of yioop machines which might
* be used during lookup
* @param string $original_query if set, the orginal query that corresponds
* to $word_structs
* @param string $save_timestamp_name if this timestamp is non empty, then
* when making iterator get sub-iterators to advance to gen doc_offset
* stored with respect to save_timestamp if exists.
* @param bool $limit_news if true the number of media:news items to
* allow in search results is limited to WordIterator::LIMIT_NEWS_COUNT
*
* @return &object an iterator for iterating through results to the
* query
*/
function getQueryIterator($word_structs, &$filter, $raw, &$to_retrieve, $queue_servers = array(), $original_query = "", $save_timestamp_name = "", $limit_news = true)
{
$iterators = array();
$total_iterators = 0;
$network_flag = false;
$min_group_flag = false;
$min_group_override = false;
if ($queue_servers != array() && !$this->isSingleLocalhost($queue_servers)) {
$network_flag = true;
$total_iterators = 1;
if (!in_array(NAME_SERVER, $queue_servers)) {
$queue_servers[] = NAME_SERVER;
//name server might still have news
}
$num_servers = count($queue_servers);
if ((!isset($this->index_name) || !$this->index_name) && isset($word_structs[0]["INDEX_NAME"])) {
$index_name = $word_structs[0]["INDEX_NAME"];
} else {
$index_name = $this->index_name;
}
$iterators[0] = new NetworkIterator($original_query, $queue_servers, $index_name, $filter, $save_timestamp_name, $limit_news);
}
if (!$network_flag) {
$doc_iterate_hashes = array(substr(crawlHashWord("site:any"), 0, 9), substr(crawlHash("site:any"), 0, 9), substr(crawlHashWord("site:doc"), 0, 9), substr(crawlHash("site:doc"), 0, 9));
if ($save_timestamp_name != "") {
// used for archive crawls of crawl mixes
$save_file = CRAWL_DIR . '/schedules/' . self::save_point . $save_timestamp_name . ".txt";
if (file_exists($save_file)) {
$save_point = unserialize(file_get_contents($save_file));
}
$save_count = 0;
}
foreach ($word_structs as $word_struct) {
if (!is_array($word_struct)) {
continue;
}
$word_keys = $word_struct["KEYS"];
$distinct_word_keys = array();
$seen_keys = array();
foreach ($word_keys as $wkey) {
if (is_string($wkey) || is_string($wkey[0])) {
$tmp_key = is_string($wkey) ? $wkey : $wkey[0];
if (!isset($seen_keys[$tmp_key])) {
$seen_keys[$tmp_key] = true;
$distinct_word_keys[] = $wkey;
}
} else {
$distinct_word_keys[] = $wkey;
}
}
$quote_positions = $word_struct["QUOTE_POSITIONS"];
$disallow_keys = $word_struct["DISALLOW_KEYS"];
$index_name = $word_struct["INDEX_NAME"];
$weight = $word_struct["WEIGHT"];
$num_word_keys = count($word_keys);
$total_iterators = count($distinct_word_keys);
$word_iterators = array();
$word_iterator_map = array();
if ($num_word_keys < 1) {
continue;
}
$sum = 0;
for ($i = 0; $i < $total_iterators; $i++) {
$current_key = is_string($distinct_word_keys[$i]) ? $distinct_word_keys[$i] : (is_string($distinct_word_keys[$i][0]) ? $distinct_word_keys[$i][0] : $distinct_word_keys[$i][0][0]);
if (!is_string($current_key)) {
$current_key = $current_key[0];
}
if (in_array(substr($current_key, 0, 9), $doc_iterate_hashes)) {
$word_iterators[$i] = new DocIterator($index_name, $filter, $to_retrieve);
$min_group_override = true;
} else {
//can happen if exact phrase search suffix approach used
if (isset($distinct_word_keys[$i][0][0]) && is_array($distinct_word_keys[$i][0][0])) {
$distinct_keys = array($distinct_word_keys[$i][0][1]);
} else {
if (isset($distinct_word_keys[$i][0]) && is_array($distinct_word_keys[$i][0])) {
$distinct_keys = $distinct_word_keys[$i];
} else {
$distinct_keys = array($distinct_word_keys[$i]);
}
}
$out_keys = array();
$old_distinct_key_id = "";
foreach ($distinct_keys as $distinct_key) {
if (is_array($distinct_key)) {
if (!isset($distinct_key[2]) && isset($distinct_key[1])) {
$distinct_keys[] = $distinct_key[1];
}
$shift = isset($distinct_key[1]) ? $distinct_key[1] : 0;
$mask = isset($distinct_key[2]) ? $distinct_key[2] : "" . "";
if (isset($distinct_key[3])) {
$old_distinct_key_id = unbase64Hash($distinct_key[3]);
}
$distinct_key_id = unbase64Hash($distinct_key[0]);
} else {
$shift = 0;
$mask = "" . "";
$distinct_key_id = unbase64Hash($distinct_key);
}
$lookup_cutoff = max(MIN_RESULTS_TO_GROUP, $to_retrieve);
$info = IndexManager::getWordInfo($index_name, $distinct_key_id, $shift, $mask);
if ($old_distinct_key_id != "") {
$old_info = IndexManager::getWordInfo($index_name, $old_distinct_key_id, $shift, $mask);
if ($info !== false && $old_info !== false) {
$info = array_merge($info, $old_info);
} else {
if ($old_info !== false) {
$info = $old_info;
}
}
}
if ($info != array()) {
$tmp_keys = arrayColumnCount($info, 4, 3);
$sum += array_sum($tmp_keys);
$out_keys = array_merge($out_keys, $tmp_keys);
}
if ($sum > $lookup_cutoff) {
break;
}
}
arsort($out_keys);
$out_keys = array_keys(array_slice($out_keys, 0, 50));
$tmp_word_iterators = array();
$m = 0;
foreach ($out_keys as $distinct_key) {
$tmp_word_iterators[$m] = new WordIterator($distinct_key, $index_name, true, $filter, $to_retrieve, $limit_news);
if ($tmp_word_iterators[$m]->dictionary_info != array() || $tmp_word_iterators[$m]->feed_count > 0) {
$min_group_override = true;
$m++;
} else {
unset($tmp_word_iterators[$m]);
}
}
if ($m == 1) {
$word_iterators[$i] = $tmp_word_iterators[0];
} else {
$word_iterators[$i] = new DisjointIterator($tmp_word_iterators);
}
}
foreach ($word_keys as $index => $key) {
if (isset($distinct_word_keys[$i]) && $key == $distinct_word_keys[$i]) {
$word_iterator_map[$index] = $i;
}
}
}
$num_disallow_keys = count($disallow_keys);
if ($num_disallow_keys > 0) {
for ($i = 0; $i < $num_disallow_keys; $i++) {
$disallow_iterator = new WordIterator($disallow_keys[$i], $index_name, false, $filter);
$word_iterators[$num_word_keys + $i] = new NegationIterator($disallow_iterator);
}
}
$num_word_keys += $num_disallow_keys;
if ($num_word_keys == 1 && $weight == 1) {
$base_iterator = $word_iterators[0];
} else {
$base_iterator = new IntersectIterator($word_iterators, $word_iterator_map, $quote_positions, $weight);
$min_group_flag = true;
if ($save_timestamp_name == "") {
$base_iterator->sync_timer_on = true;
} else {
$base_iterator->sync_timer_on = false;
}
}
if ($save_timestamp_name != "") {
if (isset($save_point[$save_count]) && $save_point[$save_count] != -1) {
$base_iterator->advance($save_point[$save_count]);
}
$save_count++;
}
$iterators[] = $base_iterator;
}
}
$num_iterators = count($iterators);
//if network_flag should be 1
if ($num_iterators < 1) {
return NULL;
} else {
if ($num_iterators == 1) {
$union_iterator = $iterators[0];
} else {
$union_iterator = new UnionIterator($iterators);
}
}
$raw = intval($raw);
if ($raw > 0) {
$group_iterator = $union_iterator;
} else {
$group_iterator = new GroupIterator($union_iterator, $total_iterators, $this->current_machine, $network_flag);
}
if ($network_flag) {
$union_iterator->results_per_block = ceil(SERVER_ALPHA * $group_iterator->results_per_block / $num_servers);
} else {
if ($save_timestamp_name != "") {
$group_iterator->save_iterators = $iterators;
} else {
if ($min_group_flag && !$min_group_override) {
$group_iterator->results_per_block = max(MIN_RESULTS_TO_GROUP / 20, 1);
$to_retrieve = -1;
}
}
}
return $group_iterator;
}
/**
* Determines the offset into the summaries WebArchiveBundle and generation
* of the provided url (or hash_url) so that the info:url
* (info:base64_hash_url) summary can be retrieved. This assumes of course
* that the info:url meta word has been stored.
*
* @param string $url_or_key either info:base64_hash_url or just a url to
* lookup
* @param string $index_name index into which to do the lookup
* @param bool $is_key whether the string is info:base64_hash_url or just a
* url
* @return array (offset, generation) into the web archive bundle
*/
function lookupSummaryOffsetGeneration($url_or_key, $index_name = "", $is_key = false)
{
if ($index_name == "") {
$index_name = $this->index_name;
}
$index_archive = IndexManager::getIndex($index_name);
if (!$index_archive) {
return false;
}
$num_retrieved = 0;
$pages = array();
$summary_offset = NULL;
if (!isset($index_archive->generation_info['ACTIVE'])) {
return false;
}
$mask = "";
$num_generations = $index_archive->generation_info['ACTIVE'];
$hash_key = $is_key ? crawlHashWord($url_or_key, true, $mask) : crawlHashWord("info:{$url_or_key}", true, $mask);
$info = IndexManager::getWordInfo($index_name, $hash_key, 0, $mask, 1);
if (!isset($info[0][4])) {
return false;
}
$word_iterator = new WordIterator($info[0][4], $index_name, true);
if (is_array($next_docs = $word_iterator->nextDocsWithWord())) {
foreach ($next_docs as $doc_key => $doc_info) {
$summary_offset = $doc_info[CrawlConstants::SUMMARY_OFFSET];
$generation = $doc_info[CrawlConstants::GENERATION];
$index_archive->setCurrentShard($generation, true);
$page = @$index_archive->getPage($summary_offset);
$num_retrieved++;
if ($num_retrieved >= 1) {
break;
}
}
if ($num_retrieved == 0) {
return false;
}
} else {
return false;
}
return array($summary_offset, $generation);
}
/**
* Returns the number of document that a given term or phrase appears in
* in the given index
*
* @param string $term_or_phrase what to look up in the indexes dictionary
* no mask is used for this look up
* @param string $index_name index to look up term or phrase in
* @param int $threshold if set and positive then once threshold many
* documents are found the search for more documents to add to the
* total is stopped
* @return int number of documents
*/
static function numDocsTerm($term_or_phrase, $index_name, $threshold = -1)
{
$index = IndexManager::getIndex($index_name);
if (!$index->dictionary) {
return false;
}
$pos = -1;
$total_num_docs = 0;
$hashes = allCrawlHashPaths($term_or_phrase, array(), array(), true);
if (!is_array($hashes)) {
$hashes = array($hashes);
}
foreach ($hashes as $hash) {
if (is_array($hash)) {
$dictionary_info = IndexManager::getWordInfo($index_name, $hash[0], $hash[1], $hash[2], $threshold);
} else {
$dictionary_info = IndexManager::getWordInfo($index_name, $hash);
}
$num_generations = count($dictionary_info);
$start = isset($dictionary_info[-1]) ? -1 : 0;
$end = $start == -1 ? $num_generations - 1 : $num_generations;
for ($i = $start; $i < $end; $i++) {
list(, , , $num_docs) = $dictionary_info[$i];
$total_num_docs += $num_docs;
if ($threshold > 0 && $total_num_docs > $threshold) {
return $total_num_docs;
}
}
}
return $total_num_docs;
}
/**
* Prints information about $num many postings beginning at the
* provided $generation and $offset
*
* @param string $archive_path the path of a directory that holds
* an IndexArchiveBundle
* @param int $generation which index shard to use
* @param int $offset offset into posting lists for that shard
* @param int $num how many postings to print info for
*/
function outputPostingInfo($archive_path, $generation, $offset, $num = 1)
{
$bundle_name = $this->getArchiveName($archive_path);
echo "\nBundle Name: {$bundle_name}\n";
$archive_type = $this->getArchiveKind($archive_path);
echo "Bundle Type: {$archive_type}\n";
echo "Generation: {$generation}\n";
echo "Offset: {$offset}\n";
if (strcmp($archive_type, "IndexArchiveBundle") != 0) {
$this->badFormatMessageAndExit($archive_path, "index");
}
$index_timestamp = substr($archive_path, strpos($archive_path, self::index_data_base_name) + strlen(self::index_data_base_name));
$index = IndexManager::getIndex($index_timestamp);
$index->setCurrentShard($generation, true);
$shard = $index->getCurrentShard();
$next = $offset >> 2;
$raw_postings = array();
$doc_indexes = array();
$documents = array();
for ($i = 0; $i < $num; $i++) {
$dummy_offset = 0;
$posting_start = $next;
$posting_end = $next;
$old_offset = $next << 2;
$old_start = $next << 2;
$old_end = $next << 2;
$tmp = $shard->getPostingAtOffset($next, $posting_start, $posting_end);
$next = $posting_end + 1;
if (!$tmp) {
break;
}
$documents = array_merge($documents, $shard->getPostingsSlice($old_offset, $old_start, $old_end, 1));
$raw_postings[] = $tmp;
$post_array = unpackPosting($tmp, $dummy_offset);
$doc_indexes[] = $post_array[0];
}
$end_offset = $next << 2;
echo "Offset After Returned Results: {$end_offset}\n\n";
if (!$documents || ($count = count($documents)) < 1) {
echo "No documents correspond to generation and offset given\n\n";
exit;
}
$document_word = $count == 1 ? "Document" : "Documents";
echo "{$count} {$document_word} Found:\n";
echo str_pad("", $count + 1, "=") . "================\n";
$j = 0;
foreach ($documents as $key => $document) {
echo "\nDOC ID: " . toHexString($key);
echo "\nTYPE: " . ($document[self::IS_DOC] ? "Document" : "Link");
echo "\nDOC INDEX: " . $doc_indexes[$j];
$summary_offset = $document[self::SUMMARY_OFFSET];
echo "\nSUMMARY OFFSET: " . $summary_offset;
echo "\nSCORE: " . $document[self::SCORE];
echo "\nDOC RANK: " . $document[self::DOC_RANK];
echo "\nRELEVANCE: " . $document[self::RELEVANCE];
echo "\nPROXIMITY: " . $document[self::PROXIMITY];
echo "\nHEX POSTING:\n";
echo "------------\n";
echo wordwrap(toHexString($raw_postings[$j]), 80);
if (isset($document[self::POSITION_LIST])) {
echo "\nTERM OCCURRENCES IN DOCUMENT (Count starts at title):";
echo "\n-------------------------" . "----------------------------\n";
$i = 0;
foreach ($document[self::POSITION_LIST] as $position) {
printf("%09d ", $position);
$i++;
if ($i >= 5) {
echo "\n";
$i = 0;
}
}
if ($i != 0) {
echo "\n";
}
}
$page = @$index->getPage($summary_offset);
if (isset($page[self::TITLE])) {
echo "SUMMARY TITLE:\n";
echo "--------------\n";
echo wordwrap($page[self::TITLE], 80) . "\n";
}
if (isset($page[self::DESCRIPTION])) {
echo "SUMMARY DESCRIPTION:\n";
echo "--------------\n";
echo $page[self::DESCRIPTION] . "\n";
}
$j++;
}
}
/**
* Computes for each word in an array of words a count of the total number
* of times it occurs in this crawl model's default index.
*
* @param array $words words to find the counts for
* @param array $machine_urls machines to invoke this command on
* @return array associative array of word => counts
*/
function countWords($words, $machine_urls = NULL)
{
if ($machine_urls != NULL && !$this->isSingleLocalhost($machine_urls)) {
$count_strings = $this->execMachines("countWords", $machine_urls, serialize(array($words, $this->index_name)));
$word_counts = array();
foreach ($count_strings as $count_string) {
$a_word_counts = unserialize(webdecode($count_string[self::PAGE]));
if (is_array($a_word_counts)) {
foreach ($a_word_counts as $word => $count) {
$word_counts[$word] = isset($word_counts[$word]) ? $word_counts[$word] + $count : $count;
}
}
}
return $word_counts;
}
$index_archive = IndexManager::getIndex($this->index_name);
$hashes = array();
$lookup = array();
foreach ($words as $word) {
$tmp = crawlHash($word);
$hashes[] = $tmp;
$lookup[$tmp] = $word;
}
$word_key_counts = $index_archive->countWordKeys($hashes);
$phrases = array();
$word_counts = array();
if (is_array($word_key_counts) && count($word_key_counts) > 0) {
foreach ($word_key_counts as $word_key => $count) {
$word_counts[$lookup[$word_key]] = $count;
}
}
return $word_counts;
}