Mercurial > hg > extraction-interface
diff interface/review_index_xml.php @ 0:b12c99b7c3f0
commit for previous development
author | Zoe Hong <zhong@mpiwg-berlin.mpg.de> |
---|---|
date | Mon, 19 Jan 2015 17:13:49 +0100 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/interface/review_index_xml.php Mon Jan 19 17:13:49 2015 +0100 @@ -0,0 +1,131 @@ +<?php +header("Content-Type: text/html;charset=utf-8"); + +if (isset($_GET['books_id'])) { + $books_id = $_GET['books_id']; +} + +include_once('./Lib_mb_utf8.php'); + +set_time_limit(0); +ini_set('memory_limit', '-1'); + +$link_mysql = mysql_connect($mysql_server, $mysql_user, $mysql_password); +mysql_query("SET NAMES utf8"); + +if (!$link_mysql) { + die('Could not connect: ' . mysql_error()); +} + +$db_selected = mysql_select_db($mysql_database, $link_mysql); +if (!$db_selected) { + die ('Can\'t use foo : ' . mysql_error()); +} + +if (!function_exists("GetSQLValueString")) { +function GetSQLValueString($theValue, $theType, $theDefinedValue = "", $theNotDefinedValue = "") +{ + $theValue = get_magic_quotes_gpc() ? stripslashes($theValue) : $theValue; + + $theValue = function_exists("mysql_real_escape_string") ? mysql_real_escape_string($theValue) : mysql_escape_string($theValue); + + switch ($theType) { + case "text": + $theValue = ($theValue != "") ? "'" . $theValue . "'" : "NULL"; + break; + case "long": + case "int": + $theValue = ($theValue != "") ? intval($theValue) : "NULL"; + break; + case "double": + $theValue = ($theValue != "") ? "'" . doubleval($theValue) . "'" : "NULL"; + break; + case "date": + $theValue = ($theValue != "") ? "'" . $theValue . "'" : "NULL"; + break; + case "defined": + $theValue = ($theValue != "") ? $theDefinedValue : $theNotDefinedValue; + break; + } + return $theValue; +} +} + +$pbCount = 1; +$imgCount = 1; + +function rep_pb_count($matches) { + global $pbCount; + return "</page>\n<page n=\"".++$pbCount."\">\n"; +} +function rep_img_count($matches) { + global $imgCount; + return "<img n=\"".$imgCount++."\"/>\n"; +} + +$counter=0; +$counterError=0; +$counterIndex1=0; +$counterIndex2=0; +$counterMultiIndex=0; +$counterSingleIndex=0; +$counterNullIndex=0; + +$hasWordInIndex=array(); +$hasWordInContent=array(); + +echo "<table width=\"100%\" border=\"1\">"; +$query = sprintf("SELECT * FROM books WHERE `id`=%s ORDER BY `id` ASC", $books_id); +$result = mysql_query($query); +while ($row = mysql_fetch_assoc($result)) { + $startPage = -1; + $endPage = -1; + $fileID = $row['id']; + $indexFilename = "../bookindexxml/".$fileID.".xml"; + + $index = file_get_contents($indexFilename); + if ( !preg_match("/<Index>(.*?)<\/Index>/sm", $index, $matches) ) { + //echo "ERROR!".$fileID."\n"; + } else { + $matchString = preg_replace("/\r\n/u", "", $matches[0]); + + $counter++; + if ( ! ($doc = simplexml_load_string( $matchString )) ) { + echo "ERROR!"; + exit; + } else { + + } + + foreach ( $doc->children() as $child ) { + $tempArray = $child->attributes(); + if ( $tempArray['Type'] == "UNKNOWN" ) { + echo "<tr bgcolor=\"#FFE4E1\"><font color=\"#FF0000\">"; + } else if ( $tempArray['Type'] == "FROMFULLTEXT" ) { + echo "<tr bgcolor=\"#FFFACD\"><font color=\"#000000\">"; + } else { + echo "<tr bgcolor=\"#FFFFFF\"><font color=\"#000000\">"; + } + echo "<td>".$tempArray['Entry']."</td>"; + echo "<td>".$tempArray['StartPage']."(".$tempArray['StartRange'].")</td>"; + echo "<td>".$tempArray['EndPage']."</td>"; + echo "</font></tr>"; + foreach ( $child->children() as $child2 ) { + $tempArray = $child2->attributes(); + if ( $tempArray['Type'] == "UNKNOWN" ) { + echo "<tr bgcolor=\"#FFE4E1\"><font color=\"#FF0000\">"; + } else if ( $tempArray['Type'] == "FROMFULLTEXT" ) { + echo "<tr bgcolor=\"#FFFACD\"><font color=\"#000000\">"; + } else { + echo "<tr bgcolor=\"#FFFFFF\"><font color=\"#000000\">"; + } + echo "<td><span style=\"padding: 0 40px\"> </span>".$tempArray['Entry']."</td>"; + echo "<td>".$tempArray['StartPage']."(".$tempArray['StartRange'].")</td>"; + echo "<td>".$tempArray['EndPage']."</td>"; + echo "</font></tr>"; + } + } + } +} + +?>