<?php

/**

 * @file

 * Enables site-wide keyword searching.

 */

/**

 * 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 CJK (Chinese, Japanese, Korean) letter-like characters.

 *

 * This list is derived from the "East Asian Scripts" section of

 * http://www.unicode.org/charts/index.html, as well as a comment on

 * http://unicode.org/reports/tr11/tr11-11.html listing some character

 * ranges that are reserved for additional CJK ideographs.

 *

 * The character ranges do not include numbers, punctuation, or symbols, since

 * these are handled separately in search. Note that radicals and strokes are

 * considered symbols. (See

 * http://www.unicode.org/Public/UNIDATA/extracted/DerivedGeneralCategory.txt)

 *

 * @see search_expand_cjk()

 */

define('PREG_CLASS_CJK', '\x{1100}-\x{11FF}\x{3040}-\x{309F}\x{30A1}-\x{318E}' .

  '\x{31A0}-\x{31B7}\x{31F0}-\x{31FF}\x{3400}-\x{4DBF}\x{4E00}-\x{9FCF}' .

  '\x{A000}-\x{A48F}\x{A4D0}-\x{A4FD}\x{A960}-\x{A97F}\x{AC00}-\x{D7FF}' .

  '\x{F900}-\x{FAFF}\x{FF21}-\x{FF3A}\x{FF41}-\x{FF5A}\x{FF66}-\x{FFDC}' .

  '\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}');

/**

 * Implements hook_help().

 */

function search_help($path, $arg) {

  switch ($path) {

    case 'admin/help#search':

      $output = '';

      $output .= '<h3>' . t('About') . '</h3>';

      $output .= '<p>' . t('The Search module provides the ability to index and search for content by exact keywords, and for users by username or e-mail. For more information, see the online handbook entry for <a href="@search-module">Search module</a>.', array('@search-module' => 'http://drupal.org/documentation/modules/search/', '@search' => url('search'))) . '</p>';

      $output .= '<h3>' . t('Uses') . '</h3>';

      $output .= '<dl>';

      $output .= '<dt>' . t('Searching content and users') . '</dt>';

      $output .= '<dd>' . t('Users with <em>Use search</em> permission can use the search block and <a href="@search">Search page</a>. Users with the <em>View published content</em> permission can search for content containing exact keywords. Users with the <em>View user profiles</em> permission can search for users containing the keyword anywhere in the user name, and users with the <em>Administer users</em> permission can search for users by email address. Additionally, users with <em>Use advanced search</em> permission can find content using more complex search methods and filtering by choosing the <em>Advanced search</em> option on the <a href="@search">Search page</a>.', array('@search' => url('search'))) . '</dd>';

      $output .= '<dt>' . t('Indexing content with cron') . '</dt>';

      $output .= '<dd>' . t('To provide keyword searching, the search engine maintains an index of words found in the content and its fields, along with text added to your content by other modules (such as comments from the core Comment module, and taxonomy terms from the core Taxonomy module). To build and maintain this index, a correctly configured <a href="@cron">cron maintenance task</a> is required. Users with <em>Administer search</em> permission can further configure the cron settings on the <a href="@searchsettings">Search settings page</a>.', array('@cron' => 'http://drupal.org/cron', '@searchsettings' => url('admin/config/search/settings'))) . '</dd>';

      $output .= '<dt>' . t('Content reindexing') . '</dt>';

      $output .= '<dd>' . t('Content-related actions on your site (creating, editing, or deleting content and comments) automatically cause affected content items to be marked for indexing or reindexing at the next cron run. When content is marked for reindexing, the previous content remains in the index until cron runs, at which time it is replaced by the new content. Unlike content-related actions, actions related to the structure of your site do not cause affected content to be marked for reindexing. Examples of structure-related actions that affect content include deleting or editing taxonomy terms, enabling or disabling modules that add text to content (such as Taxonomy, Comment, and field-providing modules), and modifying the fields or display parameters of your content types. If you take one of these actions and you want to ensure that the search index is updated to reflect your changed site structure, you can mark all content for reindexing by clicking the "Re-index site" button on the <a href="@searchsettings">Search settings page</a>. If you have a lot of content on your site, it may take several cron runs for the content to be reindexed.', array('@searchsettings' => url('admin/config/search/settings'))) . '</dd>';

      $output .= '<dt>' . t('Configuring search settings') . '</dt>';

      $output .= '<dd>' . t('Indexing behavior can be adjusted using the <a href="@searchsettings">Search settings page</a>. Users with <em>Administer search</em> permission can control settings such as the <em>Number of items to index per cron run</em>, <em>Indexing settings</em> (word length), <em>Active search modules</em>, and <em>Content ranking</em>, which lets you adjust the priority in which indexed content is returned in results.', array('@searchsettings' => url('admin/config/search/settings'))) . '</dd>';

      $output .= '<dt>' . t('Search block') . '</dt>';

      $output .= '<dd>' . t('The Search module includes a default <em>Search form</em> block, which can be enabled and configured on the <a href="@blocks">Blocks administration page</a>. The block is available to users with the <em>Search content</em> permission.', array('@blocks' => url('admin/structure/block'))) . '</dd>';

      $output .= '<dt>' . t('Extending Search module') . '</dt>';

      $output .= '<dd>' . t('By default, the Search module only supports exact keyword matching in content searches. You can modify this behavior by installing a language-specific stemming module for your language (such as <a href="http://drupal.org/project/porterstemmer">Porter Stemmer</a> for American English), which allows words such as walk, walking, and walked to be matched in the Search module. Another approach is to use a third-party search technology with stemming or partial word matching features built in, such as <a href="http://drupal.org/project/apachesolr">Apache Solr</a> or <a href="http://drupal.org/project/sphinx">Sphinx</a>. These and other <a href="@contrib-search">search-related contributed modules</a> can be downloaded by visiting Drupal.org.', array('@contrib-search' => 'http://drupal.org/project/modules?filters=tid%3A105')) . '</dd>';

      $output .= '</dl>';

      return $output;

    case 'admin/config/search/settings':

      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 search for each word individually. <em>bike shed</em> will often show more results than <em>&quot;bike shed&quot;</em>.</li>

<li>Consider loosening your query with <em>OR</em>. <em>bike OR shed</em> will often show more results than <em>bike shed</em>.</li>

</ul>');

  }

}

/**

 * Implements hook_theme().

 */

function search_theme() {

  return array(

    'search_block_form' => array(

      'render element' => 'form',

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

    ),

    'search_result' => array(

      'variables' => array('result' => NULL, 'module' => NULL),

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

      'template' => 'search-result',

    ),

    'search_results' => array(

      'variables' => array('results' => NULL, 'module' => NULL),

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

      'template' => 'search-results',

    ),

  );

}

/**

 * Implements hook_permission().

 */

function search_permission() {

  return array(

    'administer search' => array(

      'title' => t('Administer search'),

    ),

    'search content' => array(

      'title' => t('Use search'),

    ),

    'use advanced search' => array(

      'title' => t('Use advanced search'),

    ),

  );

}

/**

 * Implements hook_block_info().

 */

function search_block_info() {

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

  // Not worth caching.

  $blocks['form']['cache'] = DRUPAL_NO_CACHE;

  $blocks['form']['properties']['administrative'] = TRUE;

  return $blocks;

}

/**

 * Implements hook_block_view().

 */

function search_block_view($delta = '') {

  if (user_access('search content')) {

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

    return $block;

  }

}

/**

 * Implements hook_menu().

 */

function search_menu() {

  $items['search'] = array(

    'title' => 'Search',

    'page callback' => 'search_view',

    'access callback' => 'search_is_active',

    'type' => MENU_SUGGESTED_ITEM,

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

  );

  $items['admin/config/search/settings'] = 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'),

    'weight' => -10,

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

  );

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

    'title' => 'Clear index',

    'page callback' => 'drupal_get_form',

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

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

    'type' => MENU_VISIBLE_IN_BREADCRUMB,

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

  );

  // Add paths for searching. We add each module search path twice: once without

  // and once with %menu_tail appended. The reason for this is that we want to

  // preserve keywords when switching tabs, and also to have search tabs

  // highlighted properly. The only way to do that within the Drupal menu

  // system appears to be having two sets of tabs. See discussion on issue

  // http://drupal.org/node/245103 for details.

  drupal_static_reset('search_get_info');

  $default_info = search_get_default_module_info();

  if ($default_info) {

    foreach (search_get_info() as $module => $search_info) {

      $path = 'search/' . $search_info['path'];

      $items[$path] = array(

        'title' => $search_info['title'],

        'page callback' => 'search_view',

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

        'access callback' => '_search_menu_access',

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

        'type' => MENU_LOCAL_TASK,

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

        'weight' => $module == $default_info['module'] ? -10 : 0,

      );

      $items["$path/%menu_tail"] = array(

        'title' => $search_info['title'],

        'load arguments' => array('%map', '%index'),

        'page callback' => 'search_view',

        'page arguments' => array($module, 2),

        'access callback' => '_search_menu_access',

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

        // The default local task points to its parent, but this item points to

        // where it should so it should not be changed.

        'type' => MENU_LOCAL_TASK,

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

        'weight' => 0,

        // These tabs are not subtabs.

        'tab_root' => 'search/' . $default_info['path'] . '/%',

        // These tabs need to display at the same level.

        'tab_parent' => 'search/' . $default_info['path'],

      );

    }

  }

  return $items;

}

/**

 * Determines access for the ?q=search path.

 */

function search_is_active() {

  // This path cannot be accessed if there are no active modules.

  return user_access('search content') && search_get_info();

}

/**

 * Returns information about available search modules.

 *

 * @param $all

 *   If TRUE, information about all enabled modules implementing

 *   hook_search_info() will be returned. If FALSE (default), only modules that

 *   have been set to active on the search settings page will be returned.

 *

 * @return

 *   Array of hook_search_info() return values, keyed by module name. The

 *   'title' and 'path' array elements will be set to defaults for each module

 *   if not supplied by hook_search_info(), and an additional array element of

 *   'module' will be added (set to the module name).

 */

function search_get_info($all = FALSE) {

  $search_hooks = &drupal_static(__FUNCTION__);

  if (!isset($search_hooks)) {

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

      $search_hooks[$module] = call_user_func($module . '_search_info');

      // Use module name as the default value.

      $search_hooks[$module] += array('title' => $module, 'path' => $module);

      // Include the module name itself in the array.

      $search_hooks[$module]['module'] = $module;

    }

  }

  if ($all) {

    return $search_hooks;

  }

  $active = variable_get('search_active_modules', array('node', 'user'));

  return array_intersect_key($search_hooks, array_flip($active));

}

/**

 * Returns information about the default search module.

 *

 * @return

 *    The search_get_info() array element for the default search module, if any.

 */

function search_get_default_module_info() {

  $info = search_get_info();

  $default = variable_get('search_default_module', 'node');

  if (isset($info[$default])) {

    return $info[$default];

  }

  // The variable setting does not match any active module, so just return

  // the info for the first active module (if any).

  return reset($info);

}

/**

 * Access callback for search tabs.

 */

function _search_menu_access($name) {

  return user_access('search content') && (!function_exists($name . '_search_access') || module_invoke($name, 'search_access'));

}

/**

 * Clears a part of or the entire search index.

 *

 * @param $sid

 *   (optional) The ID of the item to remove from the search index. If

 *   specified, $module must also be given. Omit both $sid and $module to clear

 *   the entire search index.

 * @param $module

 *   (optional) The machine-readable name of the module for the item to remove

 *   from the search index.

 */

function search_reindex($sid = NULL, $module = NULL, $reindex = FALSE) {

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

    module_invoke_all('search_reset');

  }

  else {

    db_delete('search_dataset')

      ->condition('sid', $sid)

      ->condition('type', $module)

      ->execute();

    db_delete('search_index')

      ->condition('sid', $sid)

      ->condition('type', $module)

      ->execute();

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

    if (!$reindex) {

      db_delete('search_node_links')

        ->condition('sid', $sid)

        ->condition('type', $module)

        ->execute();

    }

  }

}

/**

 * Marks a word as "dirty" (changed), or retrieves the list of dirty words.

 *

 * This is used during indexing (cron). Words that are dirty have outdated

 * total counts in the search_total table, and need to be recounted.

 */

function search_dirty($word = NULL) {

  $dirty = &drupal_static(__FUNCTION__, array());

  if ($word !== NULL) {

    $dirty[$word] = TRUE;

  }

  else {

    return $dirty;

  }

}

/**

 * Implements 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.

  drupal_register_shutdown_function('search_update_totals');

  foreach (variable_get('search_active_modules', array('node', 'user')) as $module) {

    // Update word index

    module_invoke($module, 'update_index');

  }

}

/**

 * Updates the {search_total} database table.

 *

 * 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_query("SELECT SUM(score) FROM {search_index} WHERE word = :word", array(':word' => $word), array('target' => 'slave'))->fetchField();

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

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

    db_merge('search_total')

      ->key(array('word' => $word))

      ->fields(array('count' => $total))

      ->execute();

  }

  // 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", array(), array('target' => 'slave'));

  $or = db_or();

  foreach ($result as $word) {

    $or->condition('word', $word->realword);

  }

  if (count($or) > 0) {

    db_delete('search_total')

      ->condition($or)

      ->execute();

  }

}

/**

 * Simplifies a string according to indexing rules.

 *

 * @param $text

 *   Text to simplify.

 *

 * @return

 *   Simplified text.

 *

 * @see hook_search_preprocess()

 */

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);

  // Multiple dot and dash groups are word boundaries and replaced with space.

  // No need to use the unicode modifer here because 0-127 ASCII characters

  // can't match higher UTF-8 characters as the leftmost bit of those are 1.

  $text = preg_replace('/[.-]{2,}/', ' ', $text);

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

  // search behavior with acronyms and URLs. See unicode note directly above.

  $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_UNICODE_WORD_BOUNDARY . ']+/u', ' ', $text);

  // Truncate everything to 50 characters.

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

  array_walk($words, '_search_index_truncate');

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

  return $text;

}

/**

 * Splits CJK (Chinese, Japanese, Korean) text into tokens.

 *

 * The Search module matches exact words, where a word is defined to be a

 * sequence of characters delimited by spaces or punctuation. CJK languages are

 * written in long strings of characters, though, not split up into words. So

 * in order to allow search matching, we split up CJK text into tokens

 * consisting of consecutive, overlapping sequences of characters whose length

 * is equal to the 'minimum_word_size' variable. This tokenizing is only done if

 * the 'overlap_cjk' variable is TRUE.

 *

 * @param $matches

 *   This function is a callback for preg_replace_callback(), which is called

 *   from search_simplify(). So, $matches is an array of regular expression

 *   matches, which means that $matches[0] contains the matched text -- a string

 *   of CJK characters to tokenize.

 *

 * @return

 *   Tokenized text, starting and ending with a space character.

 */

function search_expand_cjk($matches) {

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

  $str = $matches[0];

  $length = drupal_strlen($str);

  // If the text is shorter than the minimum word size, don't tokenize it.

  if ($length <= $min) {

    return ' ' . $str . ' ';

  }

  $tokens = ' ';

  // Build a FIFO queue of characters.

  $chars = array();

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

    // Add the next character off the beginning of the string to the queue.

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

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

    $chars[] = $current;

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

      // Make a token of $min characters, and add it to the token string.

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

      // Shift out the first character in the queue.

      array_shift($chars);

    }

  }

  return $tokens;

}

/**

 * Simplifies and splits a string into tokens for indexing.

 */

function search_index_split($text) {

  $last = &drupal_static(__FUNCTION__);

  $lastsplit = &drupal_static(__FUNCTION__ . ':lastsplit');

  if ($last == $text) {

    return $lastsplit;

  }

  // Process words

  $text = search_simplify($text);

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

  // Save last keyword result

  $last = $text;

  $lastsplit = $words;

  return $words;

}

/**

 * Helper function for array_walk in search_index_split.

 */

function _search_index_truncate(&$text) {

  if (is_numeric($text)) {

    $text = ltrim($text, '0');

  }

  $text = truncate_utf8($text, 50);