lucene的普通搜索(二)

时间:2022-10-01 20:31:47

首先得到索引:

package com.wp.util;

import java.io.File;
import java.io.FileReader;
import java.nio.file.Paths; 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.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory; public class Indexer { private IndexWriter writer; // 写索引实例 /**
* 构造方法 实例化IndexWriter
*
* @param indexDir
* @throws Exception
*/
public Indexer(String indexDir) throws Exception {
Directory dir = FSDirectory.open(Paths.get(indexDir));// 根据路径获取存储索引的目录
Analyzer analyzer = new StandardAnalyzer(); // 这里用了多态,StandardAnalyzer是一个标准分词器,
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);//将分词器加入到索引中
writer = new IndexWriter(dir, iwc);
} /**
* 关闭写索引
*
* @throws Exception
*/
public void close() throws Exception {
writer.close();
} /**
* 索引指定目录的所有文件
*
* @param dataDir
* @throws Exception
*/
public int index(String dataDir) throws Exception {
File[] files = new File(dataDir).listFiles();//得到目录下的所有文件
for (File f : files) {
indexFile(f);
}
return writer.numDocs();
} /**
* 索引指定文件
*
* @param f
*/
private void indexFile(File f) throws Exception {
// 关于f.getCanonicalPath()查看http://www.blogjava.net/dreamstone/archive/2007/08/08/134968.html
System.out.println("索引文件:" + f.getCanonicalPath());//得到绝对路径
Document doc = getDocument(f);
writer.addDocument(doc);
} /**
* 获取文档,文档里再设置每个字段
*
* @param f
*/
private Document getDocument(File f) throws Exception {
Document doc = new Document();//创建文档
doc.add(new TextField("contents", new FileReader(f)));//以文件流的形式读取文件内容
doc.add(new TextField("fileName", f.getName(), Field.Store.YES));//Field.Store.YES表示将属性存入内存中
doc.add(new TextField("fullPath", f.getCanonicalPath(),Field.Store.YES));//存入内存中
return doc;
} public static void main(String[] args) {
String indexDir = "D:\\lucene\\luceneIndex";
String dataDir = "D:\\lucene\\data";
Indexer indexer = null;
int numIndexed = 0;
long start = System.currentTimeMillis();
try {
indexer = new Indexer(indexDir);//创建索引
numIndexed = indexer.index(dataDir);//索引指定目录的所有文件
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
indexer.close();
} catch (Exception e) {
e.printStackTrace();
}
}
long end = System.currentTimeMillis();
System.out.println("索引:" + numIndexed + " 个文件 花费了" + (end - start)
+ " 毫秒");
}
}

增加的知识:

getPath():

返回的是定义时的路径,可能是相对路径,也可能是绝对路径,这个取决于定义时用的是相对路径还是绝对路径。如果定义时用的是绝对路径,那么使用getPath()返回的结果跟用getAbsolutePath()返回的结果一样

getAbsolutePath():

返回的是定义时的路径对应的相对路径,但不会处理“.”和“..”的情况

getCanonicalPath():

返回的是规范化的绝对路径,相当于将getAbsolutePath()中的“.”和“..”解析成对应的正确的路径

搜索:

package com.wp.util;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
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.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.After;
import org.junit.Before;
import org.junit.Test; public class SearchTest { private Directory dir;
private IndexReader reader;
private IndexSearcher is; @Before
public void setUp() throws Exception {
dir = FSDirectory.open(Paths.get("D:\\lucene\\luceneIndex"));// 得到存储索引的目录
reader = DirectoryReader.open(dir);// 读取索引
is = new IndexSearcher(reader);// //创建索引搜索
} @After
public void tearDown() throws Exception {
reader.close();
} /**
* 对特定项搜索(只能是指定的字符串,而不是其中的字母)
*
* @throws Exception
*/
@Test
public void testTermQuery() throws Exception {
String searchField = "contents";
String q = "particular";
Term t = new Term(searchField, q);// 查询contents中的particular字符
Query query = new TermQuery(t);// 对特定字符查询
TopDocs hits = is.search(query, 10);// 得到查询的最前面10条数据
System.out.println("匹配 '" + q + "',总共查询到" + hits.totalHits + "个文档");
for (ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc);// 得到查询到的得分文档个数
System.out.println(doc.get("fullPath"));
}
} /**
* 解析查询表达式
*
* @throws Exception
*/
@Test
public void testQueryParser() throws Exception {
Analyzer analyzer = new StandardAnalyzer(); // 标准分词器
String searchField = "contents";
// String q = "particular AND SA";//表示查询都: 注意AND要大写
// String q = "particular or a";// 表示查询或者
String q = "particular~";// ~符号表示查询相近的
QueryParser parser = new QueryParser(searchField, analyzer);
Query query = parser.parse(q);// 进行解析
TopDocs hits = is.search(query, 100);
System.out.println("匹配 " + q + "查询到" + hits.totalHits + "个记录");
for (ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc);
System.out.println(doc.get("fullPath"));
}
}
}