diff options
| author | xue <> | 2006-05-12 12:38:32 +0000 |
|---|---|---|
| committer | xue <> | 2006-05-12 12:38:32 +0000 |
| commit | e2149e3d8b87b382563a9def6f376a5f289754d3 (patch) | |
| tree | fd24e9c28d023a483cc632683e6e998d2e11bfce /buildscripts/index/api_index.php | |
| parent | d84327e69e858d369ea0c78f6106cfaa54994032 (diff) | |
Merge from 3.0 branch till 1054.
Diffstat (limited to 'buildscripts/index/api_index.php')
| -rw-r--r-- | buildscripts/index/api_index.php | 120 |
1 files changed, 120 insertions, 0 deletions
diff --git a/buildscripts/index/api_index.php b/buildscripts/index/api_index.php new file mode 100644 index 00000000..ac2e37a7 --- /dev/null +++ b/buildscripts/index/api_index.php @@ -0,0 +1,120 @@ +<?php
+/*
+ * Created on 10/05/2006
+ */
+
+class api_index
+{
+ const API_URL = '';
+
+ private $_index;
+ private $_api;
+
+ public function __construct($index_file, $api)
+ {
+ $this->_api = $api;
+ $this->_index = new Zend_Search_Lucene($index_file, true);
+
+
+ }
+
+ function create_index()
+ {
+ echo "Building search index...\n";
+ $files = $this->get_file_list($this->_api);
+ $count = 0;
+ foreach($files as $file)
+ {
+ $content = $this->get_details($file, $this->_api);
+
+ $doc = new Zend_Search_Lucene_Document();
+
+ $title = $content['namespace'].'.'.$content['class'];
+
+ echo " Adding ".$title."\n";
+
+ //unsearchable text
+ $doc->addField(Zend_Search_Lucene_Field::UnIndexed('link', $content['link']));
+ $doc->addField(Zend_Search_Lucene_Field::UnIndexed('title', $title));
+ //$doc->addField(Zend_Search_Lucene_Field::UnIndexed('text', $content['content']));
+
+ //searchable
+ $body = strtolower($this->sanitize($content['content'])).' '.strtolower($title);
+ $doc->addField(Zend_Search_Lucene_Field::Keyword('page', strtolower(str_replace('.',' ',$title))));
+ $doc->addField(Zend_Search_Lucene_Field::Unstored('contents',$body));
+ $this->_index->addDocument($doc);
+ $count++;
+ }
+ $this->_index->commit();
+ echo "\n {$count} files indexed.\n";
+ }
+
+ function sanitize($input)
+ {
+ return htmlentities(strip_tags( $input ));
+ }
+
+
+ function get_file_list($path)
+ {
+
+ $d = dir($path);
+
+ $files = array();
+ while (false !== ($entry = $d->read()))
+ {
+ $filepath = $path.'/'.$entry;
+
+ if(is_dir($filepath) && is_int(strpos($entry, 'System')))
+ {
+ $files = array_merge($files, $this->get_files($filepath));
+ }
+ }
+
+ $d->close();
+ return $files;
+ }
+
+ function get_files($path)
+ {
+ $d = dir($path);
+
+ $files = array();
+ while (false !== ($entry = $d->read()))
+ {
+ $filepath = $path.'/'.$entry;
+ if(is_file($filepath) && $entry[0] !== '_')
+ $files[] = realpath($filepath);
+ }
+ return $files;
+ $d->close();
+ }
+
+ function get_doc_content($file)
+ {
+ $content = file_get_contents($file);
+ $html = preg_replace('/<h1>/','~~~', $content);
+ $html = preg_replace('/<![^~]+/m', '', $html);
+ $html = preg_replace('/<div class="credit">[\s\w\W\S]+/m', '', $html);
+ $html = preg_replace('/ |~+|\s{2,}/',' ',$html);
+ $html = preg_replace('/\s{2,}/',' ',$html);
+ $text = strip_tags($html);
+ $text = str_replace(' , ',', ',$text);
+ return $text;
+ }
+
+ function get_details($file, $base)
+ {
+ $result['content'] = $this->get_doc_content($file);
+ $find = array($base, '.html', '-');
+ $replace = array('', '', '.');
+ $path = preg_split('/\/|\\\/', str_replace($find, $replace, $file));
+ $result['namespace'] = $path[1];
+ $result['class'] = $path[2];
+ $result['link'] = self::API_URL.$path[1].'/'.$path[2].'.html';
+ return $result;
+ }
+}
+
+
+?>
\ No newline at end of file |