' . 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.') . '';
$output = '' . t('It is important to note that by default, the search module only supports exact keyword matching. You can modify this behavior by installing a language-specific stemming module for your language, which allows words such as walk, walking, and walked all to match each other. Another approach is to install an n-gram module, which breaks words down into small, overlapping chunks and finds words with a high degree of overlap, so that words like earthquake and quake can match each other. A third approach is to use a third-party search technology with features like this built in; there are modules available for several of these, such as Apache Solr and Sphinx.') . '
';
$output .= '' . 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 cron maintenance task is required. Indexing behavior can be adjusted using the search settings page; for example, the Number of items to index per cron run sets the maximum number of items indexed in each pass of a cron maintenance task. If necessary, reduce this number to prevent timeouts and memory errors when indexing.', array('@cron' => url('admin/reports/status'), '@searchsettings' => url('admin/config/search/settings'))) . '
';
$output .= '' . t('For more information, see the online handbook entry for Search module.', array('@search' => 'http://drupal.org/handbook/modules/search/')) . '
';
return $output;
case 'admin/config/search/settings':
return '' . t('The search engine maintains an index of words found in your site\'s content. To build and maintain this index, a correctly configured cron maintenance task is required. Indexing behavior can be adjusted using the settings below.', array('@cron' => url('admin/reports/status'))) . '
';
case 'search#noresults':
return t('
- Check if your spelling is correct.
- Remove quotes around phrases to search for each word individually. bike shed will often show more results than "bike shed".
- Consider loosening your query with OR. bike OR shed will often show more results than bike shed.
');
}
}
/**
* Implement 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',
),
'search_results_listing' => array(
'arguments' => array('title' => NULL, 'content' => NULL),
),
);
}
/**
* Implement hook_permission().
*/
function search_permission() {
return array(
'administer search' => array(
'title' => t('Administer search'),
'description' => t('Configure search administration settings.'),
),
'search content' => array(
'title' => t('Search content'),
'description' => t('Search website content.'),
),
'use advanced search' => array(
'title' => t('Use advanced search'),
'description' => t('Limit search results with additional criteria, such as specific content types. Could have performance implications.'),
),
);
}
/**
* Implement hook_block_info().
*/
function search_block_info() {
$blocks['form']['info'] = t('Search form');
// Not worth caching.
$blocks['form']['cache'] = DRUPAL_NO_CACHE;
return $blocks;
}
/**
* Implement hook_block_view().
*/
function search_block_view($delta = '') {
if (user_access('search content')) {
$block['content'] = drupal_get_form('search_block_form');
$block['subject'] = t('Search');
return $block;
}
}
/**
* Implement 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/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'),
'type' => MENU_NORMAL_ITEM,
'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_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 path' => drupal_get_path('module', 'dblog'),
'file' => 'dblog.admin.inc',
);
drupal_static_reset('search_get_info');
$search_hooks = search_get_info();
foreach(variable_get('search_active_modules', array('node', 'user')) as $module) {
if (isset($search_hooks[$module])) {
$items['search/' . $search_hooks[$module]['path'] . '/%menu_tail'] = array(
'title' => $search_hooks[$module]['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',
);
}
}
return $items;
}
/**
* Get information about all available search hooks.
*/
function search_get_info() {
$search_hooks = &drupal_static(__FUNCTION__);
if (!isset($search_hooks)) {
foreach (module_implements('search_info') as $module) {
$search_hooks[$module] = call_user_func($module . '_search_info');
// Use module name as the default.
$search_hooks[$module] += array('title' => $module, 'path' => $module);
}
}
return $search_hooks;
}
/**
* Access callback for search tabs.
*/
function _search_menu_access($name) {
return user_access('search content') && (!function_exists($name . '_search_access') || module_invoke($name, 'search_access'));
}
/**
* 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 $type
* (optional) The type of item to wipe.
*/
function search_reindex($sid = NULL, $type = NULL, $reindex = FALSE) {
if ($type == NULL && $sid == NULL) {
module_invoke_all('search_reset');
}
else {
db_delete('search_dataset')
->condition('sid', $sid)
->condition('type', $type)
->execute();
db_delete('search_index')
->condition('sid', $sid)
->condition('type', $type)
->execute();
// Don't remove links if re-indexing.
if (!$reindex) {
db_delete('search_node_links')
->condition('sid', $sid)
->condition('type', $type)
->execute();
}
}
}
/**
* Marks a word as dirty (or retrieves the list of dirty words). This is used
* during indexing (cron). Words which are dirty have outdated total counts in
* the search_total table, and need to be recounted.
*/
function search_dirty($word = NULL) {
static $dirty = array();
if ($word !== NULL) {
$dirty[$word] = TRUE;
}
else {
return $dirty;
}
}
/**
* Implement 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');
foreach(variable_get('search_active_modules', array('node', 'user')) as $module) {
// Update word index
module_invoke($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_query("SELECT SUM(score) FROM {search_index} WHERE word = :word", array(':word' => $word))->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");
$or = db_or();
foreach ($result as $word) {
$or->condition('word', $word->realword);
}
if (count($or) > 0) {
db_delete('search_total')
->condition($or)
->execute();
}
}
/**
* Simplifies a string according to indexing rules.
*/
function search_simplify($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. The weights are stored
// in a variable so that modules can overwrite the default weights.
// Note: 'a' must be included for link ranking to work.
$tags = variable_get('search_tag_weights', 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 analyzer
$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 uncacheable nodes to avoid redirect bugs.
$node = db_query('SELECT title, nid, vid FROM {node} WHERE nid = :nid', array(':nid' => $linknid))->fetchObject();
$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);
// Check wordlength
if ($num || drupal_strlen($word) >= $minimum_word_size) {
// Normalize numbers
if ($num) {
$word = (int)ltrim($word, '-0');
}
// Links score mainly for the target.
if ($link) {
if (!isset($results[$linknid])) {
$results[$linknid] = array();
}
$results[$linknid][] = $word;
// Reduce score of the link caption in the source.
$focus *= 0.2;
}
// Fall-through
if (!isset($results[0][$word])) {
$results[0][$word] = 0;
}
$results[0][$word] += $score * $focus;
// Focus is a decaying value in terms of the amount of unique words up to this point.
// From 100 words and more, it decays, to e.g. 0.5 at 500 words and 0.3 at 1000 words.
$focus = min(1, .01 + 3.5 / (2 + count($results[0]) * .015));
}
$tagwords++;
// Too many words inside a single tag probably mean a tag was accidentally left open.
if (count($tagstack) && $tagwords >= 15) {
$tagstack = array();
$score = 1;
}
}
}
}
$tag = !$tag;
}
search_reindex($sid, $type, TRUE);
// Insert cleaned up data into dataset
db_insert('search_dataset')
->fields(array(
'sid' => $sid,
'type' => $type,
'data' => $accum,
'reindex' => 0,
))
->execute();
// Insert results into search index
foreach ($results[0] as $word => $score) {
// If a word already exists in the database, its score gets increased
// appropriately. If not, we create a new record with the appropriate
// starting score.
db_merge('search_index')
->key(array(
'word' => $word,
'sid' => $sid,
'type' => $type,
))
->fields(array('score' => $score))
->expression('score', 'score + :score', array(':score' => $score))
->execute();
search_dirty($word);
}
unset($results[0]);
// Get all previous links from this item.
$result = db_query("SELECT nid, caption FROM {search_node_links} WHERE sid = :sid AND type = :type", array(
':sid' => $sid,
':type' => $type
));
$links = array();
foreach ($result as $link) {
$links[$link->nid] = $link->caption;
}
// Now store links to nodes.
foreach ($results as $nid => $words) {
$caption = implode(' ', $words);
if (isset($links[$nid])) {
if ($links[$nid] != $caption) {
// Update the existing link and mark the node for reindexing.
db_update('search_node_links')
->fields(array('caption' => $caption))
->condition('sid', $sid)
->condition('type', $type)
->condition('nid', $nid)
->execute();
search_touch_node($nid);
}
// Unset the link to mark it as processed.
unset($links[$nid]);
}
else {
// Insert the existing link and mark the node for reindexing.
db_insert('search_node_links')
->fields(array(
'caption' => $caption,
'sid' => $sid,
'type' => $type,
'nid' => $nid,
))
->execute();
search_touch_node($nid);
}
}
// Any left-over links in $links no longer exist. Delete them and mark the nodes for reindexing.
foreach ($links as $nid => $caption) {
db_delete('search_node_links')
->condition('sid', $sid)
->condition('type', $type)
->condition('nid', $nid)
->execute();
search_touch_node($nid);
}
}
/**
* Change a node's changed timestamp to 'now' to force reindexing.
*
* @param $nid
* The nid of the node that needs reindexing.
*/
function search_touch_node($nid) {
db_update('search_dataset')
->fields(array('reindex' => REQUEST_TIME))
->condition('type', 'node')
->condition('sid', $nid)
->execute();
}
function search_touch_data($type, $sid) {
db_query("UPDATE {search_dataset} SET reindex = :time WHERE sid = :sid AND type = :type", array(':time' => REQUEST_TIME, ':sid' => $sid, ':type' => $type));
}
/**
* Implement hook_node_update_index().
*/
function search_node_update_index($node) {
// Transplant links to a node into the target node.
$result = db_query("SELECT caption FROM {search_node_links} WHERE nid = :nid", array(':nid' => $node->nid));
$output = array();
foreach ($result as $link) {
$output[] = $link->caption;
}
if (count($output)) {
return '(' . implode(', ', $output) . ')';
}
}
/**
* Implement hook_node_update().
*/
function search_node_update($node) {
// Reindex the node when it is updated. The node is automatically indexed
// when it is added, simply by being added to the node table.
search_touch_node($node->nid);
}
/**
* Implement hook_comment_insert().
*/
function search_comment_insert($comment) {
// Reindex the node when comments are added.
search_touch_node($comment->nid);
}
/**
* Implement hook_comment_update().
*/
function search_comment_update($comment) {
// Reindex the node when comments are changed.
search_touch_node($comment->nid);
}
/**
* Implement hook_comment_delete().
*/
function search_comment_delete($comment) {
// Reindex the node when comments are deleted.
search_touch_node($comment->nid);
}
/**
* Implement hook_comment_publish().
*/
function search_comment_publish($comment) {
// Reindex the node when comments are published.
search_touch_node($comment->nid);
}
/**
* Implement hook_comment_unpublish().
*/
function search_comment_unpublish($comment) {
// Reindex the node when comments are unpublished.
search_touch_node($comment->nid);
}
/**
* Extract a module-specific search option from a search query. e.g. 'type:book'
*/
function search_expression_extract($keys, $option) {
if (preg_match('/(^| )' . $option . ':([^ ]*)( |$)/i', $keys, $matches)) {
return $matches[2];
}
}
/**
* Return a query with the given module-specific search option inserted in.
* e.g. 'type:book'.
*/
function search_expression_insert($keys, $option, $value = '') {
if (search_expression_extract($keys, $option)) {
$keys = trim(preg_replace('/(^| )' . $option . ':[^ ]*/i', '', $keys));
}
if ($value != '') {
$keys .= ' ' . $option . ':' . $value;
}
return $keys;
}
/**
* Helper function for grabbing search keys.
*/
function search_get_keys() {
static $return;
if (!isset($return)) {
// Extract keys as remainder of path
// Note: support old GET format of searches for existing links.
$path = explode('/', $_GET['q'], 3);
$keys = empty($_REQUEST['keys']) ? '' : $_REQUEST['keys'];
$return = count($path) == 3 ? $path[2] : $keys;
}
return $return;
}
/**
* @defgroup search Search interface
* @{
* The Drupal search interface manages a global search mechanism.
*
* Modules may plug into this system to provide searches of different types of
* data. Most of the system is handled by search.module, so this must be enabled
* for all of the search features to work.
*
* There are three ways to interact with the search system:
* - Specifically for searching nodes, you can implement hook_node_update_index()
* and hook_node_search_result(). However, note that the search system already
* indexes all visible output of a node, i.e. everything displayed normally
* by hook_view() and hook_node_view(). This is usually sufficient. You should
* only use this mechanism if you want additional, non-visible data to be
* indexed.
* - Implement hook_search(). This will create a search tab for your module on
* the /search page with a simple keyword search form.
* - Implement hook_update_index(). This allows your module to use Drupal's
* HTML indexing mechanism for searching full text efficiently.
*
* If your module needs to provide a more complicated search form, then you need
* to implement it yourself without hook_search(). In that case, you should
* define it as a local task (tab) under the /search page (e.g. /search/mymodule)
* so that users can easily find it.
*/
/**
* Render a search form.
*
* @param $action
* Form action. Defaults to "search".
* @param $keys
* The search string entered by the user, containing keywords for the search.
* @param $type
* The type of search to render the node for. Must be the name of module
* which implements hook_search(). Defaults to 'node'.
* @param $prompt
* A piece of text to put before the form (e.g. "Enter your keywords")
* @return
* An HTML string containing the search form.
*/
function search_form(&$form_state, $action = '', $keys = '', $type = NULL, $prompt = NULL) {
// Add CSS
drupal_add_css(drupal_get_path('module', 'search') . '/search.css', array('preprocess' => FALSE));
if (!$action) {
$action = url('search/' . $type);
}
if (is_null($prompt)) {
$prompt = t('Enter your keywords');
}
$form = array(
'#action' => $action,
'#attributes' => array('class' => array('search-form')),
);
$form['module'] = array('#type' => 'value', '#value' => $type);
$form['basic'] = array('#type' => 'item', '#title' => $prompt, '#id' => 'edit-keys');
$form['basic']['inline'] = array('#prefix' => '', '#suffix' => '
');
$form['basic']['inline']['keys'] = array(
'#type' => 'textfield',
'#title' => '',
'#default_value' => $keys,
'#size' => $prompt ? 40 : 20,
'#maxlength' => 255,
);
// processed_keys is used to coordinate keyword passing between other forms
// that hook into the basic search form.
$form['basic']['inline']['processed_keys'] = array('#type' => 'value', '#value' => array());
$form['basic']['inline']['submit'] = array('#type' => 'submit', '#value' => t('Search'));
return $form;
}
/**
* Form builder; Output a search form for the search block and the theme's search box.
*
* @ingroup forms
* @see search_box_form_submit()
* @see search-theme-form.tpl.php
* @see search-block-form.tpl.php
*/
function search_box(&$form_state, $form_id) {
$form[$form_id] = array(
'#title' => t('Search this site'),
'#type' => 'textfield',
'#size' => 15,
'#default_value' => '',
'#attributes' => array('title' => t('Enter the terms you wish to search for.')),
);
$form['submit'] = array('#type' => 'submit', '#value' => t('Search'));
$form['#submit'][] = 'search_box_form_submit';
return $form;
}
/**
* Process a block search form submission.
*/
function search_box_form_submit($form, &$form_state) {
// The search form relies on control of the redirect destination for its
// functionality, so we override any static destination set in the request,
// for example by drupal_access_denied() or drupal_not_found()
// (see http://drupal.org/node/292565).
if (isset($_REQUEST['destination'])) {
unset($_REQUEST['destination']);
}
$form_id = $form['form_id']['#value'];
$form_state['redirect'] = 'search/node/' . trim($form_state['values'][$form_id]);
}
/**
* Process variables for search-theme-form.tpl.php.
*
* The $variables array contains the following arguments:
* - $form
*
* @see search-theme-form.tpl.php
*/
function template_preprocess_search_theme_form(&$variables) {
$variables['search'] = array();
$hidden = array();
// Provide variables named after form keys so themers can print each element independently.
foreach (element_children($variables['form']) as $key) {
$type = $variables['form'][$key]['#type'];
if ($type == 'hidden' || $type == 'token') {
$hidden[] = drupal_render($variables['form'][$key]);
}
else {
$variables['search'][$key] = drupal_render($variables['form'][$key]);
}
}
// Hidden form elements have no value to themers. No need for separation.
$variables['search']['hidden'] = implode($hidden);
// Collect all form elements to make it easier to print the whole form.
$variables['search_form'] = implode($variables['search']);
}
/**
* Process variables for search-block-form.tpl.php.
*
* The $variables array contains the following arguments:
* - $form
*
* @see search-block-form.tpl.php
*/
function template_preprocess_search_block_form(&$variables) {
$variables['search'] = array();
$hidden = array();
// Provide variables named after form keys so themers can print each element independently.
foreach (element_children($variables['form']) as $key) {
$type = $variables['form'][$key]['#type'];
if ($type == 'hidden' || $type == 'token') {
$hidden[] = drupal_render($variables['form'][$key]);
}
else {
$variables['search'][$key] = drupal_render($variables['form'][$key]);
}
}
// Hidden form elements have no value to themers. No need for separation.
$variables['search']['hidden'] = implode($hidden);
// Collect all form elements to make it easier to print the whole form.
$variables['search_form'] = implode($variables['search']);
}
/**
* Perform a standard search on the given keys, and return the formatted results.
*/
function search_data($keys = NULL, $type = 'node') {
if (isset($keys)) {
if (module_hook($type, 'search_execute')) {
$results = module_invoke($type, 'search_execute', $keys);
if (isset($results) && is_array($results) && count($results)) {
if (module_hook($type, 'search_page')) {
return module_invoke($type, 'search_page', $results);
}
else {
return theme('search_results', $results, $type);
}
}
}
}
}
/**
* Returns snippets from a piece of text, with certain keywords highlighted.
* Used for formatting search results.
*
* @param $keys
* A string containing a search query.
*
* @param $text
* The text to extract fragments from.
*
* @return
* A string containing HTML for the excerpt.
*/
function search_excerpt($keys, $text) {
// We highlight around non-indexable or CJK characters.
$boundary = '(?:(?<=[' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . '])|(?=[' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . ']))';
// Extract positive keywords and phrases
preg_match_all('/ ("([^"]+)"|(?!OR)([^" ]+))/', ' ' . $keys, $matches);
$keys = array_merge($matches[2], $matches[3]);
// Prepare text
$text = ' ' . strip_tags(str_replace(array('<', '>'), array(' <', '> '), $text)) . ' ';
array_walk($keys, '_search_excerpt_replace');
$workkeys = $keys;
// Extract a fragment per keyword for at most 4 keywords.
// First we collect ranges of text around each keyword, starting/ending
// at spaces.
// If the sum of all fragments is too short, we look for second occurrences.
$ranges = array();
$included = array();
$length = 0;
while ($length < 256 && count($workkeys)) {
foreach ($workkeys as $k => $key) {
if (strlen($key) == 0) {
unset($workkeys[$k]);
unset($keys[$k]);
continue;
}
if ($length >= 256) {
break;
}
// Remember occurrence of key so we can skip over it if more occurrences
// are desired.
if (!isset($included[$key])) {
$included[$key] = 0;
}
// Locate a keyword (position $p), then locate a space in front (position
// $q) and behind it (position $s)
if (preg_match('/' . $boundary . $key . $boundary . '/iu', $text, $match, PREG_OFFSET_CAPTURE, $included[$key])) {
$p = $match[0][1];
if (($q = strpos($text, ' ', max(0, $p - 60))) !== FALSE) {
$end = substr($text, $p, 80);
if (($s = strrpos($end, ' ')) !== FALSE) {
$ranges[$q] = $p + $s;
$length += $p + $s - $q;
$included[$key] = $p + 1;
}
else {
unset($workkeys[$k]);
}
}
else {
unset($workkeys[$k]);
}
}
else {
unset($workkeys[$k]);
}
}
}
// If we didn't find anything, return the beginning.
if (count($ranges) == 0) {
return truncate_utf8($text, 256) . ' ...';
}
// Sort the text ranges by starting position.
ksort($ranges);
// Now we collapse overlapping text ranges into one. The sorting makes it O(n).
$newranges = array();
foreach ($ranges as $from2 => $to2) {
if (!isset($from1)) {
$from1 = $from2;
$to1 = $to2;
continue;
}
if ($from2 <= $to1) {
$to1 = max($to1, $to2);
}
else {
$newranges[$from1] = $to1;
$from1 = $from2;
$to1 = $to2;
}
}
$newranges[$from1] = $to1;
// Fetch text
$out = array();
foreach ($newranges as $from => $to) {
$out[] = substr($text, $from, $to - $from);
}
$text = (isset($newranges[0]) ? '' : '... ') . implode(' ... ', $out) . ' ...';
// Highlight keywords. Must be done at once to prevent conflicts ('strong' and '').
$text = preg_replace('/' . $boundary . '(' . implode('|', $keys) . ')' . $boundary . '/iu', '\0', $text);
return $text;
}
/**
* @} End of "defgroup search".
*/
/**
* Helper function for array_walk in search_except.
*/
function _search_excerpt_replace(&$text) {
$text = preg_quote($text, '/');
}
function search_forms() {
$forms['search_theme_form']= array(
'callback' => 'search_box',
'callback arguments' => array('search_theme_form'),
);
$forms['search_block_form']= array(
'callback' => 'search_box',
'callback arguments' => array('search_block_form'),
);
return $forms;
}