Last active
December 16, 2015 12:09
-
-
Save DrDub/5432860 to your computer and use it in GitHub Desktop.
The one-file-wonder behind http://tikiqa.duboue.net.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?php | |
| // this file assumes the augmented and interesting files are in ~/augmented, ~/interesting, respectively and a cloe of Elastica is available in ~/Elastica where ~ is /home/tikiqa | |
| function __autoload ($class) { | |
| $path = str_replace('\\', '/', $class); | |
| if (file_exists('/home/tikiqa/Elastica/lib/' . $path . '.php')) { | |
| require_once('/home/tikiqa/Elastica/lib/' . $path . '.php'); | |
| } | |
| } | |
| $has_query = array_key_exists('query',$_GET); | |
| $has_thread = array_key_exists('thread',$_GET); | |
| $raw = 0; | |
| if(array_key_exists('raw',$_GET)){ | |
| if(!$has_query) { | |
| die("must specify a query."); | |
| } | |
| $raw = 1; | |
| } | |
| if($has_query){ | |
| $elasticaClient = new \Elastica\Client(); | |
| $elasticaQueryString = new Elastica\Query\QueryString(); | |
| $elasticaQueryString->setQuery($_GET['query']); | |
| $elasticaQuery = new Elastica\Query(); | |
| $elasticaQuery->setQuery($elasticaQueryString); | |
| $elasticaIndex = $elasticaClient->getIndex('tiki'); | |
| $elasticaResultSet = $elasticaIndex->search($elasticaQuery); | |
| } | |
| ?> | |
| <?php | |
| if($raw) { | |
| print json_encode($elasticaResultSet->getResponse()->getData()); | |
| }else{ | |
| ?> | |
| <html> | |
| <head> | |
| <title>Tiki IRC QA Mining Demo</title> | |
| </head> | |
| <body> | |
| <h1>Mining Question/Answer pairs from #tikiwiki history</h1> | |
| See <a href="https://dev.tiki.org/IRC+QA+Mining">https://dev.tiki.org/IRC+QA+Mining</a> for details. | |
| <hr> | |
| <form method="GET"> | |
| Query for questions mined from <a href="http://irc.tiki.org/irclogger_logs/tikiwiki">#tikiwiki IRC logs</a>: <br/> | |
| <textarea name="query" rows=10 cols=80> | |
| <?php | |
| if($has_query) { | |
| echo $_GET['query']; | |
| } | |
| ?> | |
| </textarea> | |
| <br/> | |
| <input type="submit"> | |
| </form> | |
| <?php | |
| if($has_thread){ | |
| echo'<hr>'; | |
| // sanitize | |
| preg_match('/([0-9]+)/', $_GET['thread'], $matches); | |
| $unknown = 1; | |
| if($matches[0]){ | |
| $thread = $matches[0]; | |
| $file = "/home/tikiqa/augmented/$thread.txt"; | |
| if(file_exists($file)) { | |
| $unknown = 0; | |
| $lines = file($file); | |
| foreach($lines as $line) { | |
| echo $line . '<br/>'; | |
| } | |
| } | |
| } | |
| if($unknown) { | |
| die("Unknown thread."); | |
| } | |
| } elseif($has_query) { | |
| echo '<hr>'; | |
| echo '<ol>'; | |
| foreach ($elasticaResultSet as $elasticaResult) { | |
| echo '<li>'; | |
| $data = $elasticaResult->getData(); | |
| $date = date('Y-m-d,D', $data['postDateEpoch']); | |
| echo '<a href="http://irc.tiki.org/irclogger_log/tikiwiki?date='.$date.'" style="text-decoration: none"><b>'.$date.'</b></a> '; | |
| echo '<a href="/?thread=' . $data['thread'] . '" style="text-decoration: none">'; | |
| foreach(file("/home/tikiqa/augmented/" . $data['thread'] . ".txt") as $line) { | |
| $match = preg_match("/^([0-9]+) [^:]+\: (.*)$/", $line, $matches); | |
| if($match && $matches[1] == $data['postDateEpoch']) { | |
| echo $matches[2] . '<br/>'; | |
| } | |
| } | |
| echo '</a><br/>'; | |
| echo '<small>'.$data['question'].'</small>'; | |
| echo '</li>'; | |
| echo '<br/>'; | |
| } | |
| ?> | |
| </ol> | |
| <?php | |
| } | |
| ?> | |
| </form> | |
| </body> | |
| </html> | |
| <?php | |
| } | |
| ?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment