LUCENE.COM.CN 中国
用PHP调用Lucene包来实现全文检索* public String createIndex(String indexDir_path,String dataDir_path)
* public String searchword(String ss,String index_path)
package TestLucene;
![]()
import java.io.File;
import java.io.FileReader;
import java.io.Reader;
import java.util.Date;
![]()
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.FSDirectory;
![]()
public class TxtFileIndexer ...{
![]()
public String test() ...{
return "test is ok hohoho";
}
![]()
/**//**
* @param args
*/
public String createIndex(String indexDir_path,String dataDir_path) throws Exception ...{
String result = "";
File indexDir = new File(indexDir_path);
File dataDir = new File(dataDir_path);
Analyzer luceneAnalyzer = new StandardAnalyzer();
File[] dataFiles = dataDir.listFiles();
IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);
long startTime = new Date().getTime();
for(int i=0; i < dataFiles.length; i++) ...{
if(dataFiles[i].isFile() && dataFiles[i].getName().endsWith(".html")) ...{
result += "Indexing file" + dataFiles[i].getCanonicalPath()+"<br />";
Document document = new Document();
Reader txtReader = new FileReader(dataFiles[i]);
document.add(Field.Text("path",dataFiles[i].getCanonicalPath()));
document.add(Field.Text("contents",txtReader));
indexWriter.addDocument(document);
}
}
![]()
indexWriter.optimize();
indexWriter.close();
long endTime = new Date().getTime();
![]()
result += "It takes"+(endTime-startTime)
+ " milliseconds to create index for the files in directory "
+ dataDir.getPath();
return result;
}
![]()
public String searchword(String ss,String index_path) throws Exception ...{
String queryStr = ss;
String result = "Result:<br />";
//This is the directory that hosts the Lucene index
File indexDir = new File(index_path);
FSDirectory directory = FSDirectory.getDirectory(indexDir,false);
IndexSearcher searcher = new IndexSearcher(directory);
if(!indexDir.exists())...{
result = "The Lucene index is not exist";
return result;
}
Term term = new Term("contents",queryStr.toLowerCase());
TermQuery luceneQuery = new TermQuery(term);
Hits hits = searcher.search(luceneQuery);
for(int i = 0; i < hits.length(); i++)...{
Document document = hits.doc(i);
result += "<br /><a href='getfile.php?w="+ss+"&f="+document.get("path")+"'>File: " + document.get("path")+"</a>\n";
}
return result;
}
![]()
}
$tf = new Java('TestLucene.TxtFileIndexer');
$data_path = "F:/test/php_lucene/htdocs/data/manual"; //定义被索引内容的目录
$index_path = "F:/test/php_lucene/htdocs/data/search"; //定义生成的索引文件存放目录
$s = $tf->createIndex($index_path,$data_path); //调用Java类的方法
print $s; //打印返回的结果
$index_path = "F:/test/php_lucene/htdocs/data/search"; //定义生成的索引文件存放目录
$s = $tf->searchword("here is keyword for search",$index_path);
print $s;
java_require("F:/test/php_lucene/htdocs/lib/"); //这是个例子,我的类和Lucene都放到这个目录下,这样就可以了,是不是很简单。
<?php
![]()
error_reporting(0);
![]()
java_require("F:/test/php_lucene/htdocs/lib/");
![]()
$tf = new Java('TestLucene.TxtFileIndexer');
$s = $tf->test();
print "TestLucene.TxtFileIndexer->test()<br />".$s;
echo "<hr />";
![]()
$data_path = "F:/test/php_lucene/htdocs/data/manual";
$index_path = "F:/test/php_lucene/htdocs/data/search";
![]()
if($_GET["action"] == "create") ...{
$s = $tf->createIndex($index_path,$data_path);
print $s;
}else ...{
echo "<form method=get> <input type=text name=w /><input type=submit value=search /><br />";
if($_GET["w"] != "") ...{
$s = $tf->searchword($_GET["w"],$index_path);
print $s;
}
}
?>
extension=php_java.dll
![]()
[Java]
java.class.path = "C:\php\ext\JavaBridge.jar;F:\test\php_lucene\htdocs"
java.java_home = "C:\j2sdk1.4.2_10"
java.library.path = "c:\php\ext;F:\test\php_lucene\htdocs"