lucene教程
现实流程
lucene 相关jar包
第一个:Lucene-core-4.0.0.jar, 其中包括了常用的文档，索引，搜索，存储等相关核心代码。 第二个:Lucene-analyzers-common-4.0.0.jar， 这里面包含了各种语言的词法分析器，用于对文件内容进行关键字切分，提取。 第三个:Lucene-highlighter-4.0.0.jar， 这个jar包主要用于搜索出的内容高亮显示。 第四个和第五个: lucene-queries-4.0.0.jar 和 Lucene-queryparser-4.0.0.jar， 提供了搜索相关的代码，用于各种搜索， 比如模糊搜索，范围搜索，等等。
lucene IndexManager.java基本类
package lucene;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class IndexManager{
private static IndexManager indexManager;
private static String content="";
public static String INDEX_DIR = "D:\\luceneIndex";
public static String DATA_DIR = "D:\\luceneData";
private static Analyzer analyzer = null;
private static Directory directory = null;
private static IndexWriter indexWriter = null;
/**
* 创建索引管理器
* @return 返回索引管理器对象
*/
public IndexManager getManager(){
if(indexManager == null){
indexManager = new IndexManager();
}
return indexManager;
}
/**
* 创建当前文件目录的索引
* @param path 当前文件目录
* @return 是否成功
*/
public static boolean createIndex(String path){
Date date1 = new Date();
List<File> fileList = getFileList(path);
analyzer = new StandardAnalyzer(Version.LUCENE_40);
try {
directory = FSDirectory.open(new File(INDEX_DIR));
} catch (IOException e1) {
e1.printStackTrace();
}
for (File file : fileList) {
content = "";
//获取文件后缀
String type = file.getName().substring(file.getName().lastIndexOf(".")+1);
if("txt".equalsIgnoreCase(type)){
content += txt2String(file);
}
System.out.println("name :"+file.getName());
System.out.println("path :"+file.getPath());
System.out.println("content :"+content);
System.out.println();
try{
File indexFile = new File(INDEX_DIR);
if (!indexFile.exists()) {
indexFile.mkdirs();
}
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
indexWriter = new IndexWriter(directory, config);
Document document = new Document();
document.add(new TextField("filename", file.getName(), Store.YES));
document.add(new TextField("content", content, Store.YES));
document.add(new TextField("path", file.getPath(), Store.YES));
indexWriter.addDocument(document);
indexWriter.commit();
closeWriter();
}catch(Exception e){
e.printStackTrace();
}
content = "";
}
Date date2 = new Date();
System.out.println("创建索引-----耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
return true;
}
/**
* 从数据库中创建索引<br/>
* @param list 代表从数据库中提取的一整张表,其中的Map为<String,Object>格式,一个Map代表一行数据 <br/>
* 单个Map中存放形式 <br/>
* key -- value <br/>
* -------------- <br/>
* ID -- 23 <br/>
* NAME -- bobo <br/>
* AGE -- 29 <br/>
* -------------- <br/>
* 所以多个Map形成的List就成了一整张表 <br/>
* @return
*/
public static boolean createIndexFromDB(List<Map> list) {
if (null == list)
return false;
try {
analyzer = new StandardAnalyzer(Version.LUCENE_40);
directory = FSDirectory.open(new File(INDEX_DIR));
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
indexWriter = new IndexWriter(directory, config);
for (Map map : list) {
Document document = new Document();
Iterator iterator = map.keySet().iterator();
while (iterator.hasNext()) {
String name = (String) iterator.next();//name为列名
document.add(new TextField(name, (String) map.get(name),Store.YES));
}
indexWriter.addDocument(document);
}
indexWriter.commit();
closeWriter();
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
return true;
}
/**
* 根据field字段（值为 keyword）删除指定的document.
* @param field 指定的某个字段,目前建议只用ID唯一主键进行删除
* @param keywords keywords 中不能有""空串. <br/>
* 而且删的是 keywords中并集,而不是keywords的交集.<br/>
* <br/>
* 因为并集关系,目前该field字段必需是唯一的,不然删除时可能会引出其它多余删除问题<br/>
*/
public static void deleteIndexes(String field, String[] keywords) {
Directory dir;
IndexWriterConfig config;
try {
dir = FSDirectory.open(new File(INDEX_DIR));
analyzer = new StandardAnalyzer(Version.LUCENE_40);
config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
indexWriter = new IndexWriter(dir, config);
QueryParser parser = new QueryParser(Version.LUCENE_40, field, analyzer);
Query query;
for(String keyword : keywords){
query = parser.parse(keyword);
indexWriter.deleteDocuments(query);
}
indexWriter.commit();
indexWriter.close();
} catch (IOException e1) {
e1.printStackTrace();
} catch (ParseException e) {
e.printStackTrace();
}
}
/**
* 读取txt文件的内容
* @param file 想要读取的文件对象
* @return 返回文件内容
*/
public static String txt2String(File file){
String result = "";
try{
BufferedReader br = new BufferedReader(new FileReader(file));//构造一个BufferedReader类来读取文件
String s = null;
while((s = br.readLine())!=null){//使用readLine方法，一次读一行
result = result + "\n" +s;
}
br.close();
}catch(Exception e){
e.printStackTrace();
}
return result;
}
/**
* 查找索引，返回符合条件的文件
* @param text 查找的字符串
* @return 符合条件的文件List
*/
public static void searchIndex(String text){
Date date1 = new Date();
try{
directory = FSDirectory.open(new File(INDEX_DIR));
DirectoryReader ireader = DirectoryReader.open(directory);
IndexSearcher isearcher = new IndexSearcher(ireader);
analyzer = new StandardAnalyzer(Version.LUCENE_40);
QueryParser parser = new QueryParser(Version.LUCENE_40, "content", analyzer);
parser.setDefaultOperator(QueryParser.AND_OPERATOR);//查询条件用and
Query query = parser.parse(text);
ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs;
for (int i = 0; i < hits.length; i++) {
Document hitDoc = isearcher.doc(hits[i].doc);
System.out.println("↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓结果↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓结果↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓");
// System.out.println(hitDoc.get("filename"));
System.out.println(hitDoc.get("content"));
// System.out.println(hitDoc.get("path"));
System.out.println("↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑结果↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑结果↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑\n");
}
ireader.close();
directory.close();
}catch(Exception e){
e.printStackTrace();
}
Date date2 = new Date();
System.out.println("查看索引-----耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
}
/**
* 过滤目录下的文件
* @param dirPath 想要获取文件的目录
* @return 返回文件list
*/
public static List<File> getFileList(String dirPath) {
File[] files = new File(dirPath).listFiles();
List<File> fileList = new ArrayList<File>();
for (File file : files) {
if (isTxtFile(file.getName())) {
fileList.add(file);
}
}
return fileList;
}
/**
* 判断是否为目标文件，目前支持txt xls doc格式
* @param fileName 文件名称
* @return 如果是文件类型满足过滤条件，返回true；否则返回false
*/
public static boolean isTxtFile(String fileName) {
if (fileName.lastIndexOf(".txt") > 0) {
return true;
}
return false;
}
public static void closeWriter() throws Exception {
if (indexWriter != null) {
indexWriter.close();
}
}
/**
* 删除文件目录下的所有文件<br/>
* 测试的时候每次都delete一下被创建的索引目录,不然相同索引会一直往里添加
* @param file 要删除的文件目录
* @return 如果成功，返回true.
*/
public static boolean deleteDir(File file){
if(file.isDirectory()){
File[] files = file.listFiles();
for(int i=0; i<files.length; i++){
deleteDir(files[i]);
}
}
file.delete();
return true;
}
}
扩展:多个字段组合查询
import java.io.File;
import java.io.IOException;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
/**
* lucene利用BooleanQuery进行多个Query组合查询
*
*/
public class LuceneWildCardSearcher {
public static void main(String[] args) {
String dir = "D:\\index";
try {
Directory directory = FSDirectory.getDirectory(new File(dir));
@SuppressWarnings("deprecation")
IndexReader reader = IndexReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(reader);
Term term1 = new Term("filename", "<<傲慢与偏见>>");
WildcardQuery wildcardQuery = new WildcardQuery(term1);
Term term2 = new Term("content", "傲慢让别人无法来爱我，偏见让我无法去爱别人");
TermQuery termQuery = new TermQuery(term2);
//创建booleanQuery,然后把其它query串起来
BooleanQuery booleanQuery = new BooleanQuery();
booleanQuery.add(wildcardQuery, Occur.MUST);
booleanQuery.add(termQuery, Occur.MUST);
TopDocs topDocs = indexSearcher.search(booleanQuery,null, 10);
ScoreDoc scoreDocs[] = topDocs.scoreDocs;
for (int i = 0; i < scoreDocs.length; i++) {
Document document = indexSearcher.doc(scoreDocs[i].doc);
System.out.println(document.get("id"));
System.out.println(document.get("name"));
System.out.println(document.get("text"));
System.out.println(document.get("datetime"));
}
directory.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
用文件创建索引main入口
package entrance;
import java.io.File;
import lucene.IndexManager;
/**
* 用文件创建索引main入口
* @author King
*
*/
public class FileEntrance {
public static void main(String[] args){
IndexManager.deleteDir(new File(IndexManager.INDEX_DIR));
IndexManager.createIndex(IndexManager.DATA_DIR);
IndexManager.searchIndex("杭州");
}
}
从数据库创建索引入口
package entrance;
import java.io.File;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import lucene.IndexManager;
/**
* 从数据库创建索引入口
* @author King
*
*/
public class DbEntrance {
@SuppressWarnings("unchecked")
public static void main(String[] args){
List<Map> list = new ArrayList<Map>();
Map map = new HashMap();
map.put("ID", "23");
map.put("NAME", "bobo");
map.put("AGE", "29");
map.put("content", "23 bobo 29");
list.add(map);
IndexManager.deleteDir(new File(IndexManager.INDEX_DIR));
IndexManager.createIndexFromDB(list);
IndexManager.searchIndex("23");
}
}
删除索引main入口
package entrance;
import java.io.File;
import lucene.IndexManager;
/**
* 删除索引main入口
* @author King
*
*/
public class delIndexEntrance {
public static void main(String[] args){
String[] delArray={"杭州","Hi"};//删的是并集,而非交集,特别注意
//先清空索引
IndexManager.deleteDir(new File(IndexManager.INDEX_DIR));
//再创建索引
IndexManager.createIndex(IndexManager.DATA_DIR);
//再删除和杭州相关的某个索引
IndexManager.deleteIndexes("content", delArray);
//最后搜索"杭州",看结果是否查到
IndexManager.searchIndex("杭州");
//找不到结果了,证明确实删除了
}
}
AnalyzerTool分词工具.非常实用!
可以查看某串字符最终被分割成什么样子,这样便于查询时深刻明白为什么有的查不到有的却能查到.
package com.isoftstone.www.tool;
import java.io.IOException;
import java.io.StringReader;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.Version;
/**
*展示分词后的效果
*/
public class AnalyzerTool {
/**
* 打印分词后的信息
* @param str 待分词的字符串
* @param analyzer 分词器
*/
public static void displayToken(String str,Analyzer analyzer){
try {
//将一个字符串创建成Token流
TokenStream stream = analyzer.tokenStream("content", new StringReader(str));
CharTermAttribute cta = stream.addAttribute(CharTermAttribute.class);
stream.reset();//一定要重置,不然老报错
while(stream.incrementToken()){
System.out.print("【" + cta + "】");
}
System.out.println();
} catch (IOException e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
Analyzer aly1 = new StandardAnalyzer(Version.LUCENE_40);
Analyzer aly2 = new StopAnalyzer(Version.LUCENE_40);
Analyzer aly3 = new SimpleAnalyzer(Version.LUCENE_40);
Analyzer aly4 = new WhitespaceAnalyzer(Version.LUCENE_40);
String str = "Hello ,I am King,我是 中国人,my email is [email protected]";
AnalyzerTool.displayToken(str, aly1);
AnalyzerTool.displayToken(str, aly2);
AnalyzerTool.displayToken(str, aly3);
AnalyzerTool.displayToken(str, aly4);
}
}
参考: 【手把手教你全文检索】Apache Lucene初探 要特别注意的是: FSDirectory.open(new File(INDEX_DIR)); 这条语句使用得越少越好,不停的打开非常极超级耗时. 所以 该网页中的open()位置是有点问题的,要改成本页面中的IndexManager.java类才优雅.
下载: 百度云盘分享 (附源码,jar包,ppt)