General updates, see README.txt.

search/README.txt

@@ -1,7 +1,23 @@
+2006/07/25
+----------
+Query logic moved into the SearchQuery class in querylib.php. Should be able
+to include this file in any page and run a query against the index (PHP 5
+checks must be added to those pages then, though).
+
+Index info can be retrieved using IndexInfo class in indexlib.php.
+
+Abstracted some stuff away, to reduce rendundancy and decrease the
+likelihood of errors. Improved the stats.php page to include some
+diagnostics for adminstrators.
+
+delete.php skeleton created for removing deleted documents from the
+index. cron.php will contain the logic for running delete.php,
+update.php and eventually add.php.
+
 2006/07/11
 ----------
 (Warning: It took me 1900 seconds to index the forum, go make coffee
-whilst you wait.)
+whilst you wait.) [Moodle.org forum data]
 
 Forum search functions changed to use 'get_recordset' instead of
 'get_records', for speed reasons. This provides a significant improvement,

search/Zend/Search/Lucene/Index/SegmentInfo.php

@@ -430,7 +430,7 @@ class Zend_Search_Lucene_Index_SegmentInfo
         $freqPointer = $prevTermInfo->freqPointer;
         $proxPointer = $prevTermInfo->proxPointer;
         for ($count = $prevPosition*$indexInterval + 1;
-             $count < $termCount &&
+             $count <= $termCount &&
              ( $this->_getFieldPosition($termFieldNum) < $searchDicField ||
               ($this->_getFieldPosition($termFieldNum) == $searchDicField &&
                strcmp($termValue, $term->text) < 0) );

search/Zend/Search/Lucene/Search/QueryTokenizer.php

@@ -64,7 +64,16 @@ class Zend_Search_Lucene_Search_QueryTokenizer implements Iterator
 
         $currentToken = '';
         for ($count = 0; $count < strlen($inputString); $count++) {
-            if (ctype_alnum( $inputString{$count} )) {
+            if (ctype_alnum( $inputString{$count} ) ||
+                $inputString{$count} == '_') {
+                $currentToken .= $inputString{$count};
+            } else if ($inputString{$count} == '\\') { // Escaped character
+                $count++;
+
+                if ($count == strlen($inputString)) {
+                    throw new Zend_Search_Lucene_Exception('Non finished escape sequence.');
+                }
+
                 $currentToken .= $inputString{$count};
             } else {
                 // Previous token is finished

search/documents/document.php

@@ -3,7 +3,7 @@
    * extend.
    * */
   
-  class SearchDocument extends Zend_Search_Lucene_Document {  
+  abstract class SearchDocument extends Zend_Search_Lucene_Document {  
     public function __construct(&$doc, &$data, $document_type, $course_id, $group_id) {      
       $this->addField(Zend_Search_Lucene_Field::Keyword('id', $doc->id));
       $this->addField(Zend_Search_Lucene_Field::Text('title', $doc->title));

search/documents/forum_document.php

@@ -8,11 +8,6 @@
   class ForumSearchDocument extends SearchDocument {  
     public function __construct(&$post, $forum_id, $course_id, $group_id) {
       // generic information     
-      /*$doc->id        = $post->id;
-      $doc->title     = $post->subject;
-      $doc->author    = $post->firstname." ".$post->lastname;
-      $doc->contents  = $post->message;*/
-      
       $doc->id        = $post['id'];
       $doc->title     = $post['subject'];
       $doc->author    = $post['firstname']." ".$post['lastname'];
@@ -24,7 +19,7 @@
       $data->forum      = $forum_id;
       $data->discussion = $post['discussion'];
       
-      parent::__construct($doc, $data, SEARCH_FORUM_TYPE, $course_id, $group_id);
+      parent::__construct($doc, $data, SEARCH_TYPE_FORUM, $course_id, $group_id);
     } //constructor    
   } //ForumSearchDocument
   
@@ -34,7 +29,7 @@
   } //forum_make_link
   
   function forum_iterator() {
-      //no @ = Undefined index:  82 in /home/michael/public_html/moodle/lib/datalib.php on line 2671    
+      //no @ = Undefined index:  82 in moodle/lib/datalib.php on line 2671    
       return @get_all_instances_in_courses("forum", get_courses());
   } //forum_iterator
   
@@ -72,33 +67,6 @@
       return $documents;
   } //forum_get_content_for_index
   
-  //old slower version
-  function forum_get_content_for_index_old(&$forum) {
-    $documents = array();  
-    if (!$forum) return $documents;
-  
-    $posts = forum_get_discussions($forum->id);      
-    if (!$posts) return $documents;
-                
-    foreach($posts as $post) {
-      if (is_object($post)) {
-        if (strlen($post->message) > 0 && ($post->deleted != 1)) {
-          $documents[] = new ForumSearchDocument($post, $forum->id, $forum->course, $post->groupid);
-        } //if
-          
-        if ($children = forum_get_child_posts($post->id, $forum->id)) {
-          foreach ($children as $child) {
-            if (strlen($child->message) > 0 && ($child->deleted != 1)) {
-              $documents[] = new ForumSearchDocument($child, $forum->id, $forum->course, $post->groupid);
-            } //if
-          } //foreach
-        } //if
-      } //if                
-    } //foreach      
-    
-    return $documents;
-  } //forum_get_content_for_index_old
-  
   //reworked faster version from /mod/forum/lib.php
   function forum_get_discussions_fast($forum) {
     global $CFG, $USER;

search/documents/wiki_document.php

@@ -32,7 +32,7 @@
       $data->wiki     = $wiki_id;
       
       // construct the parent class
-      parent::__construct($doc, $data, SEARCH_WIKI_TYPE, $course_id, $group_id);
+      parent::__construct($doc, $data, SEARCH_TYPE_WIKI, $course_id, $group_id);
     } //constructor    
   } //WikiSearchDocument
   

search/indexer.php

@@ -49,15 +49,18 @@
   //php5 found, continue including php5-only files
   require_once("$CFG->dirroot/search/Zend/Search/Lucene.php");
     
-  if (get_config("search_indexer_busy") == 1) {
+  mtrace('<pre>Server Time: '.date('r',time())."\n");
+
+  if ($CFG->search_indexer_busy == '1') {
+    //means indexing was not finished previously
+    mtrace("Warning: Indexing was not successfully completed last time, restarting.\n");
   } //if
 
   //turn on busy flag
-  set_config("search_indexer_busy", 1);
-  mtrace('<pre>Server Time: '.date('r',time())."\n");
+  set_config('search_indexer_busy', '1');
   
   //paths
-  $index_path = $CFG->dataroot.'/search';
+  $index_path = SEARCH_INDEX_PATH;
   $index_db_file = "$CFG->dirroot/search/db/$CFG->dbtype.sql";  
   
   //setup directory in data root
@@ -103,6 +106,7 @@
   
   if ($mods = get_records_select('modules' /*'index this module?' where statement*/)) {
     foreach ($mods as $mod) {
+      if ($mod->name == 'forum') continue;
       $class_file = $CFG->dirroot.'/search/documents/'.$mod->name.'_document.php';              
       
       if (file_exists($class_file)) {
@@ -174,6 +178,9 @@
   mtrace('</pre>');
   
   //finished, turn busy flag off
-  set_config("search_indexer_busy", 0);
+  set_config("search_indexer_busy", "0");
+  
+  //mark the time we last updated
+  set_config("search_indexer_run_date", time());
 
 ?>

search/indexersplash.php

@@ -20,28 +20,16 @@
     exit(0);
   } //if
   
-  $index_path = "$CFG->dataroot/search";  
-  $index_dir  = get_directory_list($index_path, '', false, false);
-  $index_filecount = count($index_dir);
+  require_once("$CFG->dirroot/search/indexlib.php");    
+  $indexinfo = new IndexInfo();
     
-  //check if the table exists in the db
-  $tables = $db->MetaTables();
-  
-  if (in_array($CFG->prefix.'search_documents', $tables)) {  
-    $db_count = count_records('search_documents');
-  } else {
-    $db_count = 0;
-  } //else    
-  
-  //TODO: elaborate on error messages, when db!=0 and index=0 -> corrupt, etc.
-  if ($index_filecount != 0 or $db_count != 0) {    
-    mtrace("<pre>The data directory ($index_path) contains $index_filecount files, and\n"
-          ."there are $db_count records in the <em>search_documents</em> table.\n"
+  if ($indexinfo->valid()) {    
+    mtrace("<pre>The data directory ($indexinfo->path) contains $indexinfo->filecount files, and\n"
+          ."there are ".$indexinfo->dbcount." records in the <em>search_documents</em> table.\n"
           ."\n"
-          ."This indicates that you have already succesfully indexed this site, or at least\n"
-          ."started and cancelled an indexing session. Follow the link if you are sure that\n"
-          ."you want to continue indexing - this will replace any existing index data (no\n"
-          ."Moodle data is affected).\n"
+          ."This indicates that you have already succesfully indexed this site. Follow the link\n"
+          ."if you are sure that you want to continue indexing - this will replace any existing\n"
+          ."index data (no Moodle data is affected).\n"
           ."\n"
           ."You are encouraged to use the 'Test indexing' script before continuing onto\n"
           ."indexing - this will check if the modules are set up correctly. Please correct\n"

search/lib.php

@@ -1,17 +1,30 @@
 <?php
 
-  //Move this stuff to lib/searchlib.php?
-  // Author: Michael Champanis
+  /* Move this stuff to lib/searchlib.php?
+   * Author: Michael Champanis
+   *
+   * This file must not contain any PHP 5, because it is used to test for PHP 5
+   * itself, and needs to be able to be executed on PHP 4 installations.
+   * */
+  
+  define('SEARCH_INDEX_PATH', "$CFG->dataroot/search");
   
   //document types that can be searched  
-  define('SEARCH_NO_TYPE', 'none');
-  define('SEARCH_WIKI_TYPE', 'wiki');
-  define('SEARCH_FORUM_TYPE', 'forum');
+  define('SEARCH_TYPE_NONE', 'none');
+  define('SEARCH_TYPE_WIKI', 'wiki');
+  define('SEARCH_TYPE_FORUM', 'forum');  
   
   //returns all the document type constants
-  function search_get_document_types() {
-    $r = Array(SEARCH_WIKI_TYPE, SEARCH_NO_TYPE, SEARCH_FORUM_TYPE);
-    return $r;
+  function search_get_document_types($prefix='SEARCH_TYPE') {
+    $ret = array();
+    
+    foreach (get_defined_constants() as $key=>$value) {
+      if (substr($key, 0, strlen($prefix)) == $prefix) {
+        $ret[$key] = $value;
+      } //if
+    } //foreach
+    
+    return $ret;
   } //search_get_document_types
     
   //shortens a url so it can fit on the results page

search/query.php

@@ -25,9 +25,9 @@
   require_once('../config.php');
   require_once("$CFG->dirroot/search/lib.php"); 
     
-  //check for php5, but don't die yet (see line 27)
+  //check for php5, but don't die yet (see line 52)
   if ($check = search_check_php5()) {      
-    require_once("$CFG->dirroot/search/Zend/Search/Lucene.php");
+    require_once("$CFG->dirroot/search/querylib.php");    
     
     $query_string = optional_param('query_string', '', PARAM_CLEAN);
     $page_number  = optional_param('page', 1, PARAM_INT);
@@ -36,102 +36,9 @@
       $page_number = 1;
     } //if
     
-    $index_path = "$CFG->dataroot/search";
-    $no_index = false; //optimism!
-    $results_per_page = 10;
-    
-    try {
-      $index = new Zend_Search_Lucene($index_path, false);
-    } catch(Exception $e) {
-      //print $e;
-      $no_index = true;
-    } //catch
+    $sq = new SearchQuery($query_string, $page_number, 10, true);  
   } //if
   
-  
-  //Result document class that contains all the display information we need
-  class ResultDocument {
-    public  $url,
-            $title,
-            $score,
-            $doctype,
-            $author;
-  } //ResultDocument  
-
-  //generates an HTML string of links to result pages
-  function page_numbers($query, $hits, $page=1, $results_per_page=20) {
-    //total result pages
-    $pages = ceil($hits/$results_per_page);
-    
-    $ret = "<div align='center'>";    
-    
-    //Back is disabled if we're on page 1
-    if ($page > 1) {
-      $ret .= "<a href='query.php?query_string=$query&page=".($page-1)."'>< Back</a>&nbsp;";
-    } else {
-      $ret .= "< Back&nbsp;";
-    } //else
-    
-    //don't <a href> the current page
-    for ($i = 1; $i <= $pages; $i++) {
-      if ($page == $i) {
-        $ret .= "[$i]&nbsp;";
-      } else {
-        $ret .= "<a href='query.php?query_string=$query&page=$i'>$i</a>&nbsp;";
-      } //else
-    } //for
-    
-    //Next disabled if we're on the last page
-    if ($page < $pages) {      
-      $ret .= "<a href='query.php?query_string=$query&page=".($page+1)."'>Next ></a>&nbsp;";
-    } else {
-      $ret .= "Next >&nbsp;";
-    } //else
-    
-    $ret .= "</div>";    
-    
-    //shorten really long page lists, to stop table distorting width-ways
-    if (strlen($ret) > 70) {
-      $start = 4;
-      $end = $page - 5;     
-      $ret = preg_replace("/<a\D+\d+\D+>$start<\/a>.*?<a\D+\d+\D+>$end<\/a>/", '...', $ret);
-
-      $start = $page + 5;
-      $end = $pages - 3;      
-      $ret = preg_replace("/<a\D+\d+\D+>$start<\/a>.*?<a\D+\d+\D+>$end<\/a>/", '...', $ret);
-    } //if
-    
-    return $ret;
-  } //page_numbers
-  
-  //calculates whether a user is allowed to see this result
-  function can_display(&$user, $course_id, $group_id) {
-    return true;
-  } //can_display
-  
-  //caches the results of the last query, deletes the previous one also
-  function cache($id=false, &$object=false) {
-    //see if there was a previous query
-    $last_term = (isset($_SESSION['search_last_term'])) ? $_SESSION['search_last_term'] : false;
-    
-    //if this query is different from the last, clear out the last one
-    if ($id != false and $last_term != $id) {
-      unset($_SESSION[$last_term]);
-      session_unregister($last_term);
-    } //if
-    
-    //store the new query if id and object are passed in
-    if ($object and $id) {
-      $_SESSION['search_last_term'] = $id;
-      $_SESSION[$id] = $object;
-      return true;
-    //otherwise return the stored results
-    } else if ($id and isset($_SESSION[$id])) {
-      return $_SESSION[$id];
-    } //else
-  } //cache
-  
-  
   if (!$site = get_site()) {
     redirect("index.php");
   } //if
@@ -166,17 +73,17 @@
 
 <div align="center">
 <?php
-  echo 'Searching: ';
+  print 'Searching: ';
   
-  if ($no_index) {
-    print "0";
+  if ($sq->is_valid_index()) {
+    print $sq->index_count();    
   } else {
-    print $index->count();
+    print "0";
   } //else
   
   print ' documents.';
   
-  if ($no_index and isadmin()) {
+  if (!$sq->is_valid_index() and isadmin()) {
     print "<br><br>Admin: There appears to be no index, click <a href='indexersplash.php'>here</a> to create one.";
   } //if
 ?>
@@ -185,43 +92,11 @@
 <?php  
   print_simple_box_end();
   
-  if (!empty($query_string) and !$no_index) {
+  if ($sq->is_valid()) {
     print_simple_box_start('center', '50%', 'white', 10);
     
     search_stopwatch();              
-    
-    //if the cache is empty
-    if (!($hits = cache($query_string))) {
-      $resultdocs = array();
-      $resultdoc  = new ResultDocument;
-      
-      //generate a new result-set      
-      $hits = $index->find(strtolower($query_string));
-      
-      foreach ($hits as $hit) {
-        //check permissions on each result
-        if (can_display($USER, $hit->course_id, $hit->group_id)) {
-          $resultdoc->url     = $hit->url;
-          $resultdoc->title   = $hit->title;
-          $resultdoc->score   = $hit->score;
-          $resultdoc->doctype = $hit->doctype;
-          $resultdoc->author  = $hit->author;
-          
-          //and store it if it passes the test
-          $resultdocs[] = clone($resultdoc);
-        } //if
-      } //foreach
-      
-      //cache the results so we don't have to compute this on every page-load
-      cache($query_string, $resultdocs);
-      
-      //print "Using new results.";
-    } else {
-      //There was something in the cache, so we're using that to save time
-      //print "Using cached results.";
-    } //else
-            
-    $hit_count = count($hits);    
+    $hit_count = $sq->count();    
     
     print "<br>";
 
@@ -229,27 +104,13 @@
     print "<br>";
       
     if ($hit_count > 0) {
-      if ($hit_count < $results_per_page) {
-        $page_number = 1;
-      } else if ($page_number > ceil($hit_count/$results_per_page)) {
-        $page_number = $hit_count/$results_per_page;
-      } //if
-    
-      $start = ($page_number - 1)*$results_per_page;
-      $end = $start + $results_per_page;
-
-      $page_links = page_numbers($query_string, $hit_count, $page_number, $results_per_page);
+      $page_links = $sq->page_numbers();
+      $hits       = $sq->results();
         
       print "<ol>";
         
-      for ($i = $start; $i < $end; $i++) {
-        if ($i >= $hit_count) {
-          break;
-        } //if
-      
-        $listing = $hits[$i];
-            
-        print "<li value='".($i+1)."'><a href='".$listing->url."'>$listing->title</a><br>\n"
+      foreach ($hits as $listing) {
+        print "<li value='".($listing->number+1)."'><a href='".$listing->url."'>$listing->title</a><br>\n"
              ."<em>".search_shorten_url($listing->url, 70)."</em><br>\n"        
              ."Type: ".$listing->doctype.", score: ".round($listing->score, 3).", author: ".$listing->author."<br>\n"            
              ."<br></li>\n";
@@ -260,9 +121,6 @@
     } //if        
     
     print_simple_box_end();
-  } //if
-  
-  if (!empty($query_string) and !$no_index) {
 ?>
 
 <div align="center">
@@ -270,7 +128,7 @@
 </div>
 
 <?php
-  } //if
+  } //if (sq is valid)
   
   print_simple_box_end();
   print_footer();

search/stats.php

@@ -1,6 +1,7 @@
 <?php
   /* Prints some basic statistics about the current index.
-   * Allows the administrator to create an index if none exists.
+   *
+   * Does some diagnostics if you are logged in as an administrator.   
    * */
   
   require_once('../config.php');  
@@ -8,31 +9,9 @@
 
   //check for php5, but don't die yet
   if ($check = search_check_php5()) {
-    //filesystem stats
-    $index_path = "$CFG->dataroot/search";
-    $index_size = display_size(get_directory_size($index_path));
-    $index_dir  = get_directory_list($index_path, '', false, false);
-    $index_filecount = count($index_dir);
+    require_once("$CFG->dirroot/search/indexlib.php");    
     
-    //indexed documents stats (via db)
-    $db_exists = false;
-    $admin_tables = $db->MetaTables();
-    
-    if (in_array($CFG->prefix.'search_documents', $admin_tables)) {
-      $db_exists = true;
-      $types = search_get_document_types();
-      sort($types);
-    
-      //total documents
-      $type_counts['Total'] = count_records('search_documents');
-
-      foreach($types as $type) {
-        $c = count_records('search_documents', 'doctype', $type);
-        $type_counts[$type] = (int)$c;
-      } //foreach
-    } else {
-      $type_counts['Total'] = 0;
-    } //else      
+    $indexinfo = new IndexInfo();
   } //if
   
   if (!$site = get_site()) {
@@ -66,12 +45,35 @@
     $admin_table->cellspacing = 0;
     $admin_table->width = '500';
   
-    $admin_table->data[] = array('<strong>Data directory</strong>', '<em><strong>'.$index_path.'</strong></em>');
-    $admin_table->data[] = array('Files in index directory', $index_filecount);
-    $admin_table->data[] = array('Total size', $index_size);
+    $admin_table->data[] = array('<strong>Data directory</strong>', '<em><strong>'.$indexinfo->path.'</strong></em>');
+    $admin_table->data[] = array('Files in index directory', $indexinfo->filecount);
+    $admin_table->data[] = array('Total size', $indexinfo->size);
     
-    if ($index_filecount == 0 or !$db_exists) {
-      $admin_table->data[] = array('Click to create index', "<a href='indexersplash.php'>Indexer</a>");
+    if ($indexinfo->time > 0) {
+      $admin_table->data[] = array('Created on', date('r', $indexinfo->time));
+    } else {
+      $admin_table->data[] = array('Created on', '-');
+    } //else
+          
+    if (!$indexinfo->valid($errors)) {
+      $admin_table->data[] = array('<strong>Errors</strong>', '&nbsp;');
+    
+      foreach ($errors as $key=>$value) {
+        $admin_table->data[] = array($key.' ... ', $value);
+      } //foreach
+
+      $admin_table->data[] = array('<strong>Solutions</strong>', '&nbsp;');
+
+      if (isset($errors['dir'])) {
+        $admin_table->data[] = array('Check dir', 'Ensure the data directory exists and is writable.');
+      } //if
+
+      if (isset($errors['db'])) {
+        $admin_table->data[] = array('Check DB', 'Check your database for any problems.');
+      } //if
+
+      $admin_table->data[] = array('Run indexer test', '<a href=\'tests/index.php\'>tests/index.php</a>');      
+      $admin_table->data[] = array('Run indexer', '<a href=\'indexersplash.php\'>indexersplash.php</a>');      
     } //if
   } //if
   
@@ -84,8 +86,17 @@
   $table->width = '500';
   
   $table->data[] = array('<strong>Database</strong>', '<em><strong>search_documents<strong></em>');
-  foreach($type_counts as $key => $value) {
-    $table->data[] = array($key, $value);
+  
+  //add an extra field if we're admin
+  if (isadmin()) {
+    //don't want to confuse users if the two totals don't match (hint: they should)
+    $table->data[] = array('Documents in index', $indexinfo->indexcount);
+  } //if
+  
+  $table->data[] = array('Documents in database', $indexinfo->dbcount);
+  
+  foreach($indexinfo->types as $key => $value) {
+    $table->data[] = array("'$key' documents", $value);
   } //foreach    
 
   if (isadmin()) {

search/tests/index.php

@@ -49,8 +49,8 @@
       if (file_exists($class_file)) {
         include_once($class_file);
         
-        if (!defined('SEARCH_'.strtoupper($mod->name).'_TYPE')) {
-          mtrace("ERROR: Constant 'SEARCH_".strtoupper($mod->name)."_TYPE' is not defined in /search/lib.php");
+        if (!defined('SEARCH_TYPE_'.strtoupper($mod->name))) {
+          mtrace("ERROR: Constant 'SEARCH_TYPE_".strtoupper($mod->name)."' is not defined in /search/lib.php");
           continue;
         } //if