apache lucene 一个最简单的实例
就像每个程序都有一个Hello World来让人体验它一样,lucene也可以很简单的提供一个实例。如下(来自lucene in action的例子)有两个类组成:
一个是建立索引
下篇文章将介绍一下lucene的核心类
一个是建立索引
package my;
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 {
public static void main(String[] args) throws Exception {
if (args.length != 2) {
throw new Exception("Usage: java " + Indexer.class.getName()
+ " <index dir> <data dir>");
}
File indexDir = new File(args[0]);
File dataDir = new File(args[1]);
long start = new Date().getTime();
int numIndexed = index(indexDir, dataDir);
long end = new Date().getTime();
System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
}
// open an index and start file directory traversal
public 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;
}
// recursive method that calls itself when it finds a directory
private static void indexDirectory(IndexWriter writer, File dir)
throws IOException {
File[] files = dir.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);
}
}
}
// method to actually index file using Lucene
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(Field.Text("contents", new FileReader(f)));
doc.add(Field.Keyword("filename", f.getCanonicalPath()));
writer.addDocument(doc);
}
}
另一个是搜索: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 {
public static void main(String[] args) throws Exception {
if (args.length != 2) {
throw new Exception("Usage: java " + Indexer.class.getName()
+ " <index dir> <data dir>");
}
File indexDir = new File(args[0]);
File dataDir = new File(args[1]);
long start = new Date().getTime();
int numIndexed = index(indexDir, dataDir);
long end = new Date().getTime();
System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
}
// open an index and start file directory traversal
public 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;
}
// recursive method that calls itself when it finds a directory
private static void indexDirectory(IndexWriter writer, File dir)
throws IOException {
File[] files = dir.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);
}
}
}
// method to actually index file using Lucene
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(Field.Text("contents", new FileReader(f)));
doc.add(Field.Keyword("filename", f.getCanonicalPath()));
writer.addDocument(doc);
}
}
package my;
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 {
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]);
String q = args[1];
if (!indexDir.exists() || !indexDir.isDirectory()) {
throw new Exception(indexDir
+ " does not exist or is not a directory.");
}
search(indexDir, q);
}
public static void search(File indexDir, String q) throws Exception {
Directory fsDir = FSDirectory.getDirectory(indexDir, false);
IndexSearcher is = new IndexSearcher(fsDir);
Query query = QueryParser.parse(q, "contents", new StandardAnalyzer());
long start = new Date().getTime();
Hits hits = is.search(query);
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);
System.out.println(doc.get("filename"));
}
}
}
ok,这样就简单实现了,在搜索目录下所有txt,找出包括某一个字符串的txt文件名的功能。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 {
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]);
String q = args[1];
if (!indexDir.exists() || !indexDir.isDirectory()) {
throw new Exception(indexDir
+ " does not exist or is not a directory.");
}
search(indexDir, q);
}
public static void search(File indexDir, String q) throws Exception {
Directory fsDir = FSDirectory.getDirectory(indexDir, false);
IndexSearcher is = new IndexSearcher(fsDir);
Query query = QueryParser.parse(q, "contents", new StandardAnalyzer());
long start = new Date().getTime();
Hits hits = is.search(query);
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);
System.out.println(doc.get("filename"));
}
}
}
下篇文章将介绍一下lucene的核心类