diff options
author | ctrlaltca <> | 2012-07-12 11:21:01 +0000 |
---|---|---|
committer | ctrlaltca <> | 2012-07-12 11:21:01 +0000 |
commit | 903ae8a581fac1e6917fc3e31d2ad8fb91df80c3 (patch) | |
tree | e08bf04f0823650a231227ac3499121270172a23 /buildscripts/index/api_index.php | |
parent | 3e4e6e66aeb3f8fea4e1eb4237498ef9d2358f63 (diff) |
standardize the use of unix eol; use svn properties to enforce native eol
Diffstat (limited to 'buildscripts/index/api_index.php')
-rw-r--r-- | buildscripts/index/api_index.php | 240 |
1 files changed, 120 insertions, 120 deletions
diff --git a/buildscripts/index/api_index.php b/buildscripts/index/api_index.php index c85fa267..339cb042 100644 --- a/buildscripts/index/api_index.php +++ b/buildscripts/index/api_index.php @@ -1,121 +1,121 @@ -<?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)
- {
- echo " processing $file...\n";
- $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);
- }
- $d->close();
- return $files;
- }
-
- function get_doc_content($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;
- }
-}
-
-
+<?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) + { + echo " processing $file...\n"; + $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); + } + $d->close(); + return $files; + } + + function get_doc_content($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 |