luceneIKAnalyzer 中文分词及索引,简单实例_中文分词程序实验报告

luceneIKAnalyzer 中文分词及索引,简单实例由刀豆文库小编整理，希望给你工作、学习、生活带来方便，猜你可能喜欢“中文分词程序实验报告”。

http:///posts/list/344.page

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.document.DateTools;

import org.apache.lucene.index.IndexWriter;

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;

import org.mira.lucene.analysis.IK_CAnalyzer;

import java.io.File;

import java.io.FileNotFoundException;

import java.io.IOException;

import java.io.FileReader;

import java.util.Date;

public cla Searcher {

private static String INDEX_DIR = Searcher.cla.getResource(“/”).getPath()+“/data/index”;//“c:luceneindex”;

private static String DOC_DIR =Searcher.cla.getResource(“/”).getPath();//“c:lucenedoc”;public static void main(String[] args)throws Exception {String queryString;

queryString = “²âÊÔ”;

File indexDir = new File(INDEX_DIR);

File docDir = new File(DOC_DIR);

Date start = new Date();

//±ØÐëÏȽ¨Ë÷Òý

try {

IndexWriter writer = new IndexWriter(INDEX_DIR, new IK_CAnalyzer(), true);

System.out.println(“Indexing to directory '” + INDEX_DIR + “'...”);

indexDocs(writer, docDir);

System.out.println(“Optimizing...”);

writer.optimize();

writer.close();

Date end = new Date();

System.out.println(end.getTime()start)+ “milliseconds)that matched query” + q + “:”);

for(int i = 0;i

Document doc = hits.doc(i);// ¢Ü µÃµ½Æ¥ÅäµÄÎĵµSystem.out.println(“file: ” + doc.get(“path”));}

}

}