
建立索引:
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Date;
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;
public class Indexer
{
// 建立索引
/* *
* @param args
*/
public static void main(String[] args) throws Exception
{
// TODO Auto-generated method stub
if (args.length != 2 )
{
throw new Exception( " Usage: java " + Indexer. class .getName() + " <index dir> <data dir> " );
}
File indexDir = new File(args[ 0 ]); // 存放索引的路径
File dataDir = new File(args[ 1 ]); // 要建立索引的目录路径
long start = new Date().getTime();
int numIndexed = index(indexDir, dataDir); // 建立索引
long end = new Date().getTime();
System. out .println( " Indexing " + numIndexed + " files took " + (end - start) + " milliseconds " );
}
private static int index(File indexDir, File dataDir) throws IOException
{
if ( ! dataDir.exists() || ! dataDir.isDirectory())
{
throw new IOException(dataDir + " does not exist or is not a directory " );
}
IndexWriter writer = new IndexWriter(indexDir, new StandardAnalyzer(), true );
writer.setUseCompoundFile( false );
indexDirectory(writer, dataDir);
int numIndexed = writer.docCount();
writer.optimize();
writer.close();
return numIndexed;
}
private static void indexDirectory(IndexWriter writer, File dataDir) throws IOException
{
// TODO Auto-generated method stub
File[] files = dataDir.listFiles();
for ( int i = 0 ; i < files.length; i ++ )
{
File f = files[i];
if (f.isDirectory())
{
indexDirectory(writer, f);
}
else if (f.getName().endsWith( " .txt " ))
{
indexFile(writer, f);
}
}
}
private static void indexFile(IndexWriter writer, File f) throws IOException
{
if (f.isHidden() || ! f.exists() || ! f.canRead())
{
return ;
}
System. out .println( " Indexing " + f.getCanonicalPath());
Document doc = new Document();
doc.add( new Field( " contents " , new FileReader(f)));
doc.add( new Field( " filename " , f.getCanonicalPath(), Field.Store.YES, Field.Index.TOKENIZED));
writer.addDocument(doc);
}
}
import java.io.FileReader;
import java.io.IOException;
import java.util.Date;
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;
public class Indexer
{
// 建立索引
/* *
* @param args
*/
public static void main(String[] args) throws Exception
{
// TODO Auto-generated method stub
if (args.length != 2 )
{
throw new Exception( " Usage: java " + Indexer. class .getName() + " <index dir> <data dir> " );
}
File indexDir = new File(args[ 0 ]); // 存放索引的路径
File dataDir = new File(args[ 1 ]); // 要建立索引的目录路径
long start = new Date().getTime();
int numIndexed = index(indexDir, dataDir); // 建立索引
long end = new Date().getTime();
System. out .println( " Indexing " + numIndexed + " files took " + (end - start) + " milliseconds " );
}
private static int index(File indexDir, File dataDir) throws IOException
{
if ( ! dataDir.exists() || ! dataDir.isDirectory())
{
throw new IOException(dataDir + " does not exist or is not a directory " );
}
IndexWriter writer = new IndexWriter(indexDir, new StandardAnalyzer(), true );
writer.setUseCompoundFile( false );
indexDirectory(writer, dataDir);
int numIndexed = writer.docCount();
writer.optimize();
writer.close();
return numIndexed;
}
private static void indexDirectory(IndexWriter writer, File dataDir) throws IOException
{
// TODO Auto-generated method stub
File[] files = dataDir.listFiles();
for ( int i = 0 ; i < files.length; i ++ )
{
File f = files[i];
if (f.isDirectory())
{
indexDirectory(writer, f);
}
else if (f.getName().endsWith( " .txt " ))
{
indexFile(writer, f);
}
}
}
private static void indexFile(IndexWriter writer, File f) throws IOException
{
if (f.isHidden() || ! f.exists() || ! f.canRead())
{
return ;
}
System. out .println( " Indexing " + f.getCanonicalPath());
Document doc = new Document();
doc.add( new Field( " contents " , new FileReader(f)));
doc.add( new Field( " filename " , f.getCanonicalPath(), Field.Store.YES, Field.Index.TOKENIZED));
writer.addDocument(doc);
}
}
搜索:
import java.io.File;
import java.util.Date;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
public class Searcher
{
/* *
* @param args
*/
public static void main(String[] args) throws Exception
{
if (args.length != 2 )
{
throw new Exception( " Usage: java " + Searcher. class .getName() + " <index dir> <auery> " );
}
File indexDir = new File(args[ 0 ]); // 要搜索的索引所在目录
String q = args[ 1 ]; // 搜索关键字
if ( ! indexDir.exists() || ! indexDir.isDirectory())
{
throw new Exception(indexDir + " does not exist or is not a directory. " );
}
search(indexDir, q);
}
private static void search(File indexDir, String q) throws Exception
{
Directory fsDir = FSDirectory.getDirectory(indexDir, false );
IndexSearcher is = new IndexSearcher(fsDir); // 打开索引
QueryParser parser = new QueryParser( " contents " , new StandardAnalyzer());
Query query = parser.parse(q); // 对文本内容进行分析查询
long start = new Date().getTime();
Hits hits = is .search(query); // 搜索索引
long end = new Date().getTime();
System.err.println( " Found " + hits.length() + " document(s) (in " + (end - start) + " milliseconds) that matched query ' " + q + " ’: " );
for ( int i = 0 ; i < hits.length(); i ++ )
{
Document doc = hits.doc(i); // 得到匹配的文档
System. out .println(doc. get ( " filename " ));
}
}
}
import java.util.Date;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
public class Searcher
{
/* *
* @param args
*/
public static void main(String[] args) throws Exception
{
if (args.length != 2 )
{
throw new Exception( " Usage: java " + Searcher. class .getName() + " <index dir> <auery> " );
}
File indexDir = new File(args[ 0 ]); // 要搜索的索引所在目录
String q = args[ 1 ]; // 搜索关键字
if ( ! indexDir.exists() || ! indexDir.isDirectory())
{
throw new Exception(indexDir + " does not exist or is not a directory. " );
}
search(indexDir, q);
}
private static void search(File indexDir, String q) throws Exception
{
Directory fsDir = FSDirectory.getDirectory(indexDir, false );
IndexSearcher is = new IndexSearcher(fsDir); // 打开索引
QueryParser parser = new QueryParser( " contents " , new StandardAnalyzer());
Query query = parser.parse(q); // 对文本内容进行分析查询
long start = new Date().getTime();
Hits hits = is .search(query); // 搜索索引
long end = new Date().getTime();
System.err.println( " Found " + hits.length() + " document(s) (in " + (end - start) + " milliseconds) that matched query ' " + q + " ’: " );
for ( int i = 0 ; i < hits.length(); i ++ )
{
Document doc = hits.doc(i); // 得到匹配的文档
System. out .println(doc. get ( " filename " ));
}
}
}
重点学习的几个方面:
1, Lucene的索引结构,
2, 各种异构数据源的解析器(Parser)
3, 分词器(Analyzer)提取索引项(尤其是如何进行中文分词)
注:这里使用的是lucene2.2.0