lucene入门篇

package test3;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.io.Reader;
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 LuceneIndexTest {
public static void main(String[] args) throws Exception {
// 声明一个对象
LuceneIndexTest indexer = new LuceneIndexTest();
// 建立索引
Date start = new Date();
indexer.writeToIndex();
Date end = new Date();

System.out.println("建立索引用时" + (end.getTime() - start.getTime()) + "毫秒");

indexer.close();
}

public LuceneIndexTest() {
try {
writer = new IndexWriter(Constants.INDEX_STORE_PATH,
new StandardAnalyzer(), true);
} catch (Exception e) {
e.printStackTrace();
}
}

// 索引器
private IndexWriter writer = null;

// 将要建立索引的文件构造成一个Document对象，并添加一个域"content"
private Document getDocument(File f) throws Exception {
Document doc = new Document();

FileInputStream is = new FileInputStream(f);
Reader reader = new BufferedReader(new InputStreamReader(is));
doc.add(Field.Text("contents", reader));

doc.add(Field.Keyword("path", f.getAbsolutePath()));
return doc;
}

public void writeToIndex() throws Exception {
File folder = new File(Constants.INDEX_FILE_PATH);
if (folder.isDirectory()) {
String[] files = folder.list();
for (int i = 0; i < files.length; i++) {
File file = new File(folder, files[i]);
Document doc = getDocument(file);
System.out.println("正在建立索引 : " + file + "");
writer.addDocument(doc);
}
}
}

public void close() throws Exception {
writer.close();
}

}

package test3;

import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;

public class LuceneSearchTest {

public static void main(String[] args) throws Exception {
LuceneSearchTest test = new LuceneSearchTest();
Hits h = null;
h = test.search("法院");
test.printResult(h);
h = test.search("学院");
test.printResult(h);
h = test.search("boy");
test.printResult(h);
}

public LuceneSearchTest() {
try {
searcher = new IndexSearcher(IndexReader
.open(Constants.INDEX_STORE_PATH));
} catch (Exception e) {
e.printStackTrace();
}
}

// 声明一个IndexSearcher对象
private IndexSearcher searcher = null;

// 声明一个Query对象
private Query query = null;

public final Hits search(String keyword) {
System.out.println("正在检索关键字 : " + keyword);
try {
// 将关键字包装成Query对象
query = QueryParser.parse(keyword, "contents",
new StandardAnalyzer());

Date start = new Date();
Hits hits = searcher.search(query);
Date end = new Date();
System.out.println("检索完成，用时" + (end.getTime() - start.getTime()) + "毫秒");
return hits;
} catch (Exception e) {
e.printStackTrace();
return null;
}
}

public void printResult(Hits h) {
if (h.length() == 0) {
System.out.println("对不起，没有找到您要的结果。");
}
else
{
for (int i = 0; i < h.length(); i++) {
try {
Document doc = h.doc(i);
System.out.print("这是第" + i + "个检索到的结果，文件名为：");
System.out.println(doc.get("path"));
} catch (Exception e) {
e.printStackTrace();
}
}
}
System.out.println("--------------------------");
}

}

package test1;

public class Constants {
public final static String INDEX_FILE_PATH = "d:\\Users\\file";
public final static String INDEX_STORE_PATH = "d:\\Users\\index";
}

索引数据源：doc(field1,field2...) doc(field1,field2...)
\  indexer /
_____________
| Lucene Index|
--------------
/ searcher \
结果输出：Hits(doc(field1,field2) doc(field1...))

索引数据源：record(field1,field2...) record(field1..)
\  SQL: insert/
_____________
| DB  Index   |
-------------
/ SQL: select \
结果输出：results(record(field1,field2..) record(field1...))