<?php

// $Id: search.module,v 1.250.2.6 2009/03/10 17:20:01 goba Exp $

/**

 * @file

 * Enables site-wide keyword searching.

 */

/**

 * Matches Unicode character classes to exclude from the search index.

 *

 * See: http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values

 *

 * The index only contains the following character classes:

 * Lu     Letter, Uppercase

 * Ll     Letter, Lowercase

 * Lt     Letter, Titlecase

 * Lo     Letter, Other

 * Nd     Number, Decimal Digit

 * No     Number, Other

 */

define('PREG_CLASS_SEARCH_EXCLUDE',

'\x{0}-\x{2f}\x{3a}-\x{40}\x{5b}-\x{60}\x{7b}-\x{bf}\x{d7}\x{f7}\x{2b0}-'.

'\x{385}\x{387}\x{3f6}\x{482}-\x{489}\x{559}-\x{55f}\x{589}-\x{5c7}\x{5f3}-'.

'\x{61f}\x{640}\x{64b}-\x{65e}\x{66a}-\x{66d}\x{670}\x{6d4}\x{6d6}-\x{6ed}'.

'\x{6fd}\x{6fe}\x{700}-\x{70f}\x{711}\x{730}-\x{74a}\x{7a6}-\x{7b0}\x{901}-'.

'\x{903}\x{93c}\x{93e}-\x{94d}\x{951}-\x{954}\x{962}-\x{965}\x{970}\x{981}-'.

'\x{983}\x{9bc}\x{9be}-\x{9cd}\x{9d7}\x{9e2}\x{9e3}\x{9f2}-\x{a03}\x{a3c}-'.

'\x{a4d}\x{a70}\x{a71}\x{a81}-\x{a83}\x{abc}\x{abe}-\x{acd}\x{ae2}\x{ae3}'.

'\x{af1}-\x{b03}\x{b3c}\x{b3e}-\x{b57}\x{b70}\x{b82}\x{bbe}-\x{bd7}\x{bf0}-'.

'\x{c03}\x{c3e}-\x{c56}\x{c82}\x{c83}\x{cbc}\x{cbe}-\x{cd6}\x{d02}\x{d03}'.

'\x{d3e}-\x{d57}\x{d82}\x{d83}\x{dca}-\x{df4}\x{e31}\x{e34}-\x{e3f}\x{e46}-'.

'\x{e4f}\x{e5a}\x{e5b}\x{eb1}\x{eb4}-\x{ebc}\x{ec6}-\x{ecd}\x{f01}-\x{f1f}'.

'\x{f2a}-\x{f3f}\x{f71}-\x{f87}\x{f90}-\x{fd1}\x{102c}-\x{1039}\x{104a}-'.

'\x{104f}\x{1056}-\x{1059}\x{10fb}\x{10fc}\x{135f}-\x{137c}\x{1390}-\x{1399}'.

'\x{166d}\x{166e}\x{1680}\x{169b}\x{169c}\x{16eb}-\x{16f0}\x{1712}-\x{1714}'.

'\x{1732}-\x{1736}\x{1752}\x{1753}\x{1772}\x{1773}\x{17b4}-\x{17db}\x{17dd}'.

'\x{17f0}-\x{180e}\x{1843}\x{18a9}\x{1920}-\x{1945}\x{19b0}-\x{19c0}\x{19c8}'.

'\x{19c9}\x{19de}-\x{19ff}\x{1a17}-\x{1a1f}\x{1d2c}-\x{1d61}\x{1d78}\x{1d9b}-'.

'\x{1dc3}\x{1fbd}\x{1fbf}-\x{1fc1}\x{1fcd}-\x{1fcf}\x{1fdd}-\x{1fdf}\x{1fed}-'.

'\x{1fef}\x{1ffd}-\x{2070}\x{2074}-\x{207e}\x{2080}-\x{2101}\x{2103}-\x{2106}'.

'\x{2108}\x{2109}\x{2114}\x{2116}-\x{2118}\x{211e}-\x{2123}\x{2125}\x{2127}'.

'\x{2129}\x{212e}\x{2132}\x{213a}\x{213b}\x{2140}-\x{2144}\x{214a}-\x{2b13}'.

'\x{2ce5}-\x{2cff}\x{2d6f}\x{2e00}-\x{3005}\x{3007}-\x{303b}\x{303d}-\x{303f}'.

'\x{3099}-\x{309e}\x{30a0}\x{30fb}-\x{30fe}\x{3190}-\x{319f}\x{31c0}-\x{31cf}'.

'\x{3200}-\x{33ff}\x{4dc0}-\x{4dff}\x{a015}\x{a490}-\x{a716}\x{a802}\x{a806}'.

'\x{a80b}\x{a823}-\x{a82b}\x{d800}-\x{f8ff}\x{fb1e}\x{fb29}\x{fd3e}\x{fd3f}'.

'\x{fdfc}-\x{fe6b}\x{feff}-\x{ff0f}\x{ff1a}-\x{ff20}\x{ff3b}-\x{ff40}\x{ff5b}-'.

'\x{ff65}\x{ff70}\x{ff9e}\x{ff9f}\x{ffe0}-\x{fffd}');

/**

 * Matches all 'N' Unicode character classes (numbers)

 */

define('PREG_CLASS_NUMBERS',

'\x{30}-\x{39}\x{b2}\x{b3}\x{b9}\x{bc}-\x{be}\x{660}-\x{669}\x{6f0}-\x{6f9}'.

'\x{966}-\x{96f}\x{9e6}-\x{9ef}\x{9f4}-\x{9f9}\x{a66}-\x{a6f}\x{ae6}-\x{aef}'.

'\x{b66}-\x{b6f}\x{be7}-\x{bf2}\x{c66}-\x{c6f}\x{ce6}-\x{cef}\x{d66}-\x{d6f}'.

'\x{e50}-\x{e59}\x{ed0}-\x{ed9}\x{f20}-\x{f33}\x{1040}-\x{1049}\x{1369}-'.

'\x{137c}\x{16ee}-\x{16f0}\x{17e0}-\x{17e9}\x{17f0}-\x{17f9}\x{1810}-\x{1819}'.

'\x{1946}-\x{194f}\x{2070}\x{2074}-\x{2079}\x{2080}-\x{2089}\x{2153}-\x{2183}'.

'\x{2460}-\x{249b}\x{24ea}-\x{24ff}\x{2776}-\x{2793}\x{3007}\x{3021}-\x{3029}'.

'\x{3038}-\x{303a}\x{3192}-\x{3195}\x{3220}-\x{3229}\x{3251}-\x{325f}\x{3280}-'.

'\x{3289}\x{32b1}-\x{32bf}\x{ff10}-\x{ff19}');

/**

 * Matches all 'P' Unicode character classes (punctuation)

 */

define('PREG_CLASS_PUNCTUATION',

'\x{21}-\x{23}\x{25}-\x{2a}\x{2c}-\x{2f}\x{3a}\x{3b}\x{3f}\x{40}\x{5b}-\x{5d}'.

'\x{5f}\x{7b}\x{7d}\x{a1}\x{ab}\x{b7}\x{bb}\x{bf}\x{37e}\x{387}\x{55a}-\x{55f}'.

'\x{589}\x{58a}\x{5be}\x{5c0}\x{5c3}\x{5f3}\x{5f4}\x{60c}\x{60d}\x{61b}\x{61f}'.

'\x{66a}-\x{66d}\x{6d4}\x{700}-\x{70d}\x{964}\x{965}\x{970}\x{df4}\x{e4f}'.

'\x{e5a}\x{e5b}\x{f04}-\x{f12}\x{f3a}-\x{f3d}\x{f85}\x{104a}-\x{104f}\x{10fb}'.

'\x{1361}-\x{1368}\x{166d}\x{166e}\x{169b}\x{169c}\x{16eb}-\x{16ed}\x{1735}'.

'\x{1736}\x{17d4}-\x{17d6}\x{17d8}-\x{17da}\x{1800}-\x{180a}\x{1944}\x{1945}'.

'\x{2010}-\x{2027}\x{2030}-\x{2043}\x{2045}-\x{2051}\x{2053}\x{2054}\x{2057}'.

'\x{207d}\x{207e}\x{208d}\x{208e}\x{2329}\x{232a}\x{23b4}-\x{23b6}\x{2768}-'.

'\x{2775}\x{27e6}-\x{27eb}\x{2983}-\x{2998}\x{29d8}-\x{29db}\x{29fc}\x{29fd}'.

'\x{3001}-\x{3003}\x{3008}-\x{3011}\x{3014}-\x{301f}\x{3030}\x{303d}\x{30a0}'.

'\x{30fb}\x{fd3e}\x{fd3f}\x{fe30}-\x{fe52}\x{fe54}-\x{fe61}\x{fe63}\x{fe68}'.

'\x{fe6a}\x{fe6b}\x{ff01}-\x{ff03}\x{ff05}-\x{ff0a}\x{ff0c}-\x{ff0f}\x{ff1a}'.

'\x{ff1b}\x{ff1f}\x{ff20}\x{ff3b}-\x{ff3d}\x{ff3f}\x{ff5b}\x{ff5d}\x{ff5f}-'.

'\x{ff65}');

/**

 * Matches all CJK characters that are candidates for auto-splitting

 * (Chinese, Japanese, Korean).

 * Contains kana and BMP ideographs.

 */

define('PREG_CLASS_CJK', '\x{3041}-\x{30ff}\x{31f0}-\x{31ff}\x{3400}-\x{4db5}'.

'\x{4e00}-\x{9fbb}\x{f900}-\x{fad9}');

/**

 * Implementation of hook_help().

 */

function search_help($path, $arg) {

  switch ($path) {

    case 'admin/help#search':

      $output = '<p>'. t('The search module adds the ability to search for content by keywords. Search is often the only practical way to find content on a large site, and is useful for finding both users and posts.') .'</p>';

      $output .= '<p>'. t('To provide keyword searching, the search engine maintains an index of words found in your site\'s content. To build and maintain this index, a correctly configured <a href="@cron">cron maintenance task</a> is required. Indexing behavior can be adjusted using the <a href="@searchsettings">search settings page</a>; for example, the <em>Number of items to index per cron run</em> sets the maximum number of items indexed in each pass of a <a href="@cron">cron maintenance task</a>. If necessary, reduce this number to prevent timeouts and memory errors when indexing.', array('@cron' => url('admin/reports/status'), '@searchsettings' => url('admin/settings/search'))) .'</p>';

      $output .= '<p>'. t('For more information, see the online handbook entry for <a href="@search">Search module</a>.', array('@search' => 'http://drupal.org/handbook/modules/search/')) .'</p>';

      return $output;

    case 'admin/settings/search':

      return '<p>'. t('The search engine maintains an index of words found in your site\'s content. To build and maintain this index, a correctly configured <a href="@cron">cron maintenance task</a> is required. Indexing behavior can be adjusted using the settings below.', array('@cron' => url('admin/reports/status'))) .'</p>';

    case 'search#noresults':

      return t('<ul>

<li>Check if your spelling is correct.</li>

<li>Remove quotes around phrases to match each word individually: <em>"blue smurf"</em> will match less than <em>blue smurf</em>.</li>

<li>Consider loosening your query with <em>OR</em>: <em>blue smurf</em> will match less than <em>blue OR smurf</em>.</li>

</ul>');

  }

}

/**

 * Implementation of hook_theme()

 */

function search_theme() {

  return array(

    'search_theme_form' => array(

      'arguments' => array('form' => NULL),

      'template' => 'search-theme-form',

    ),

    'search_block_form' => array(

      'arguments' => array('form' => NULL),

      'template' => 'search-block-form',

    ),

    'search_result' => array(

      'arguments' => array('result' => NULL, 'type' => NULL),

      'file' => 'search.pages.inc',

      'template' => 'search-result',

    ),

    'search_results' => array(

      'arguments' => array('results' => NULL, 'type' => NULL),

      'file' => 'search.pages.inc',

      'template' => 'search-results',

    ),

  );

}

/**

 * Implementation of hook_perm().

 */

function search_perm() {

  return array('search content', 'use advanced search', 'administer search');

}

/**

 * Implementation of hook_block().

 */

function search_block($op = 'list', $delta = 0) {

  if ($op == 'list') {

    $blocks[0]['info'] = t('Search form');

    // Not worth caching.

    $blocks[0]['cache'] = BLOCK_NO_CACHE;

    return $blocks;

  }

  else if ($op == 'view' && user_access('search content')) {

    $block['content'] = drupal_get_form('search_block_form');

    $block['subject'] = t('Search');

    return $block;

  }

}

/**

 * Implementation of hook_menu().

 */

function search_menu() {

  $items['search'] = array(

    'title' => 'Search',

    'page callback' => 'search_view',

    'access arguments' => array('search content'),

    'type' => MENU_SUGGESTED_ITEM,

    'file' => 'search.pages.inc',

  );

  $items['admin/settings/search'] = array(

    'title' => 'Search settings',

    'description' => 'Configure relevance settings for search and other indexing options',

    'page callback' => 'drupal_get_form',

    'page arguments' => array('search_admin_settings'),

    'access arguments' => array('administer search'),

    'type' => MENU_NORMAL_ITEM,

    'file' => 'search.admin.inc',

  );

  $items['admin/settings/search/wipe'] = array(

    'title' => 'Clear index',

    'page callback' => 'drupal_get_form',

    'page arguments' => array('search_wipe_confirm'),

    'access arguments' => array('administer search'),

    'type' => MENU_CALLBACK,

    'file' => 'search.admin.inc',

  );

  $items['admin/reports/search'] = array(

    'title' => 'Top search phrases',

    'description' => 'View most popular search phrases.',

    'page callback' => 'dblog_top',

    'page arguments' => array('search'),

    'access arguments' => array('access site reports'),

    'file' => 'dblog.admin.inc',

    'file path' => drupal_get_path('module', 'dblog'),

  );

  foreach (module_implements('search') as $name) {

    $items['search/'. $name .'/%menu_tail'] = array(

      'title callback' => 'module_invoke',

      'title arguments' => array($name, 'search', 'name', TRUE),

      'page callback' => 'search_view',

      'page arguments' => array($name),

      'access callback' => '_search_menu',

      'access arguments' => array($name),

      'type' => MENU_LOCAL_TASK,

      'parent' => 'search',

      'file' => 'search.pages.inc',

    );

  }

  return $items;

}

function _search_menu($name) {

  return user_access('search content') && module_invoke($name, 'search', 'name');

}

/**

 * Wipes a part of or the entire search index.

 *

 * @param $sid

 *  (optional) The SID of the item to wipe. If specified, $type must be passed

 *  too.

 * @param $type

 *  (optional) The type of item to wipe.

 */

function search_wipe($sid = NULL, $type = NULL, $reindex = FALSE) {

  if ($type == NULL && $sid == NULL) {

    module_invoke_all('search', 'reset');

  }

  else {

    db_query("DELETE FROM {search_dataset} WHERE sid = %d AND type = '%s'", $sid, $type);

    db_query("DELETE FROM {search_index} WHERE sid = %d AND type = '%s'", $sid, $type);

    // Don't remove links if re-indexing.

    if (!$reindex) {

      db_query("DELETE FROM {search_node_links} WHERE sid = %d AND type = '%s'", $sid, $type);

    }

  }

}

/**

 * Marks a word as dirty (or retrieves the list of dirty words). This is used

 * during indexing (cron). Words which are dirty have outdated total counts in

 * the search_total table, and need to be recounted.

 */

function search_dirty($word = NULL) {

  static $dirty = array();

  if ($word !== NULL) {

    $dirty[$word] = TRUE;

  }

  else {

    return $dirty;

  }

}

/**

 * Implementation of hook_cron().

 *

 * Fires hook_update_index() in all modules and cleans up dirty words (see

 * search_dirty).

 */

function search_cron() {

  // We register a shutdown function to ensure that search_total is always up

  // to date.

  register_shutdown_function('search_update_totals');

  // Update word index

  foreach (module_list() as $module) {

    module_invoke($module, 'update_index');

  }

}

/**

 * This function is called on shutdown to ensure that search_total is always

 * up to date (even if cron times out or otherwise fails).

 */

function search_update_totals() {

  // Update word IDF (Inverse Document Frequency) counts for new/changed words

  foreach (search_dirty() as $word => $dummy) {

    // Get total count

    $total = db_result(db_query("SELECT SUM(score) FROM {search_index} WHERE word = '%s'", $word));

    // Apply Zipf's law to equalize the probability distribution

    $total = log10(1 + 1/(max(1, $total)));

    db_query("UPDATE {search_total} SET count = %f WHERE word = '%s'", $total, $word);

    if (!db_affected_rows()) {

      db_query("INSERT INTO {search_total} (word, count) VALUES ('%s', %f)", $word, $total);

    }

  }

  // Find words that were deleted from search_index, but are still in

  // search_total. We use a LEFT JOIN between the two tables and keep only the

  // rows which fail to join.

  $result = db_query("SELECT t.word AS realword, i.word FROM {search_total} t LEFT JOIN {search_index} i ON t.word = i.word WHERE i.word IS NULL");

  while ($word = db_fetch_object($result)) {

    db_query("DELETE FROM {search_total} WHERE word = '%s'", $word->realword);

  }

}

/**

 * Simplifies a string according to indexing rules.

 */

function search_simplify($text) {

  // Decode entities to UTF-8

  $text = decode_entities($text);

  // Lowercase

  $text = drupal_strtolower($text);

  // Call an external processor for word handling.

  search_invoke_preprocess($text);

  // Simple CJK handling

  if (variable_get('overlap_cjk', TRUE)) {

    $text = preg_replace_callback('/['. PREG_CLASS_CJK .']+/u', 'search_expand_cjk', $text);

  }

  // To improve searching for numerical data such as dates, IP addresses

  // or version numbers, we consider a group of numerical characters

  // separated only by punctuation characters to be one piece.

  // This also means that searching for e.g. '20/03/1984' also returns

  // results with '20-03-1984' in them.

  // Readable regexp: ([number]+)[punctuation]+(?=[number])

  $text = preg_replace('/(['. PREG_CLASS_NUMBERS .']+)['. PREG_CLASS_PUNCTUATION .']+(?=['. PREG_CLASS_NUMBERS .'])/u', '\1', $text);

  // The dot, underscore and dash are simply removed. This allows meaningful

  // search behavior with acronyms and URLs.

  $text = preg_replace('/[._-]+/', '', $text);

  // With the exception of the rules above, we consider all punctuation,

  // marks, spacers, etc, to be a word boundary.

  $text = preg_replace('/['. PREG_CLASS_SEARCH_EXCLUDE .']+/u', ' ', $text);

  return $text;

}

/**

 * Basic CJK tokenizer. Simply splits a string into consecutive, overlapping

 * sequences of characters ('minimum_word_size' long).

 */

function search_expand_cjk($matches) {

  $min = variable_get('minimum_word_size', 3);

  $str = $matches[0];

  $l = drupal_strlen($str);

  // Passthrough short words

  if ($l <= $min) {

    return ' '. $str .' ';

  }

  $tokens = ' ';

  // FIFO queue of characters

  $chars = array();

  // Begin loop

  for ($i = 0; $i < $l; ++$i) {

    // Grab next character

    $current = drupal_substr($str, 0, 1);

    $str = substr($str, strlen($current));

    $chars[] = $current;

    if ($i >= $min - 1) {

      $tokens .= implode('', $chars) .' ';

      array_shift($chars);

    }

  }

  return $tokens;

}

/**

 * Splits a string into tokens for indexing.

 */

function search_index_split($text) {

  static $last = NULL;

  static $lastsplit = NULL;

  if ($last == $text) {

    return $lastsplit;

  }

  // Process words

  $text = search_simplify($text);

  $words = explode(' ', $text);

  array_walk($words, '_search_index_truncate');

  // Save last keyword result

  $last = $text;

  $lastsplit = $words;

  return $words;

}

/**

 * Helper function for array_walk in search_index_split.

 */

function _search_index_truncate(&$text) {

  $text = truncate_utf8($text, 50);

}

/**

 * Invokes hook_search_preprocess() in modules.

 */

function search_invoke_preprocess(&$text) {

  foreach (module_implements('search_preprocess') as $module) {

    $text = module_invoke($module, 'search_preprocess', $text);

  }

}

/**

 * Update the full-text search index for a particular item.

 *

 * @param $sid

 *   A number identifying this particular item (e.g. node id).

 *

 * @param $type

 *   A string defining this type of item (e.g. 'node')

 *

 * @param $text

 *   The content of this item. Must be a piece of HTML text.

 *

 * @ingroup search

 */

function search_index($sid, $type, $text) {

  $minimum_word_size = variable_get('minimum_word_size', 3);

  // Link matching

  global $base_url;

  $node_regexp = '@href=[\'"]?(?:'. preg_quote($base_url, '@') .'/|'. preg_quote(base_path(), '@') .')(?:\?q=)?/?((?![a-z]+:)[^\'">]+)[\'">]@i';

  // Multipliers for scores of words inside certain HTML tags.

  // Note: 'a' must be included for link ranking to work.

  $tags = array('h1' => 25,

                'h2' => 18,

                'h3' => 15,

                'h4' => 12,

                'h5' => 9,

                'h6' => 6,

                'u' => 3,

                'b' => 3,

                'i' => 3,

                'strong' => 3,

                'em' => 3,

                'a' => 10);

  // Strip off all ignored tags to speed up processing, but insert space before/after

  // them to keep word boundaries.

  $text = str_replace(array('<', '>'), array(' <', '> '), $text);

  $text = strip_tags($text, '<'. implode('><', array_keys($tags)) .'>');

  // Split HTML tags from plain text.

  $split = preg_split('/\s*<([^>]+?)>\s*/', $text, -1, PREG_SPLIT_DELIM_CAPTURE);

  // Note: PHP ensures the array consists of alternating delimiters and literals

  // and begins and ends with a literal (inserting $null as required).

  $tag = FALSE; // Odd/even counter. Tag or no tag.

  $link = FALSE; // State variable for link analyser

  $score = 1; // Starting score per word

  $accum = ' '; // Accumulator for cleaned up data

  $tagstack = array(); // Stack with open tags

  $tagwords = 0; // Counter for consecutive words

  $focus = 1; // Focus state

  $results = array(0 => array()); // Accumulator for words for index

  foreach ($split as $value) {

    if ($tag) {

      // Increase or decrease score per word based on tag

      list($tagname) = explode(' ', $value, 2);

      $tagname = drupal_strtolower($tagname);

      // Closing or opening tag?

      if ($tagname[0] == '/') {

        $tagname = substr($tagname, 1);

        // If we encounter unexpected tags, reset score to avoid incorrect boosting.

        if (!count($tagstack) || $tagstack[0] != $tagname) {

          $tagstack = array();

          $score = 1;

        }

        else {

          // Remove from tag stack and decrement score

          $score = max(1, $score - $tags[array_shift($tagstack)]);

        }

        if ($tagname == 'a') {

          $link = FALSE;

        }

      }

      else {

        if (isset($tagstack[0]) && $tagstack[0] == $tagname) {

          // None of the tags we look for make sense when nested identically.

          // If they are, it's probably broken HTML.

          $tagstack = array();

          $score = 1;

        }

        else {

          // Add to open tag stack and increment score

          array_unshift($tagstack, $tagname);

          $score += $tags[$tagname];

        }

        if ($tagname == 'a') {

          // Check if link points to a node on this site

          if (preg_match($node_regexp, $value, $match)) {

            $path = drupal_get_normal_path($match[1]);

            if (preg_match('!(?:node|book)/(?:view/)?([0-9]+)!i', $path, $match)) {

              $linknid = $match[1];

              if ($linknid > 0) {

                // Note: ignore links to uncachable nodes to avoid redirect bugs.

                $node = db_fetch_object(db_query('SELECT n.title, n.nid, n.vid, r.format FROM {node} n INNER JOIN {node_revisions} r ON n.vid = r.vid WHERE n.nid = %d', $linknid));

                if (filter_format_allowcache($node->format)) {

                  $link = TRUE;

                  $linktitle = $node->title;

                }

              }

            }

          }

        }

      }

      // A tag change occurred, reset counter.

      $tagwords = 0;

    }

    else {

      // Note: use of PREG_SPLIT_DELIM_CAPTURE above will introduce empty values

      if ($value != '') {

        if ($link) {

          // Check to see if the node link text is its URL. If so, we use the target node title instead.

          if (preg_match('!^https?://!i', $value)) {

            $value = $linktitle;

          }

        }

        $words = search_index_split($value);

        foreach ($words as $word) {

          // Add word to accumulator

          $accum .= $word .' ';

          $num = is_numeric($word);