lucenestandardanalyzertext.java

《lucene+nutch搜索引擎开发》源代码

package chapter8;

import java.io.IOException;
import java.io.StringReader;

import org.apache.lucene.document.Field;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.ParseException;
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.analysis.Analyzer;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Token;

import java.util.*;
import java.io.*;

public class LuceneStandardAnalyzerText {
	
	private static String Dest_Index_Path = "D:\\workshop\\TextIndex";
	static protected String textdetail = "The Lucene works very well,it is very useful.我们认为很好用。" ;
	static protected String chinesedetail = "中文文档中最基础的结构是句子、短语、词汇、单个的汉字。中文环境的句子通常可以利用标点符号来分隔。" ;
	 public static final String[] self_stop_words = {
		    "a", "an", "and", "are", "as", "at", "be", "but", "by",
		    "for", "if", "in", "into", "is", "it",
		    "no", "not", "of", "on", "or", "such",
		    "that", "the", "their", "then", "there", "these",
		    "they", "this", "to", "was", "will", "with",
		    "very"
		  };
	 
		public static void IndexBuilder() {
			try {
				Analyzer TextAnalyzer = new StandardAnalyzer();
				
				IndexWriter TextIndex = new IndexWriter(Dest_Index_Path,TextAnalyzer,true);
				Document document = new Document();
				Field field_content = new Field("content", chinesedetail, 
						Field.Store.YES,Field.Index.TOKENIZED);
				document.add(field_content);
				TextIndex.addDocument(document);
				
				ArrayList ItemList = new ArrayList();
				
				TokenStream stream = TextAnalyzer.tokenStream("content", new StringReader(chinesedetail));
				while(true)
				{
					Token item = stream.next();
					if(null == item ) break;
					System.out.print("{"+item.termText()+"} ");
				}
				TextIndex.optimize();
				TextIndex.close();
			} catch (IOException e) {
				e.printStackTrace();
			}
			System.out.println("");
			System.out.println("Index success");
			
		}
		/*================================================================
		 * 名 称：QueryStandardAnalyzerTest
		 * 功 能：构造检索查询器，使用指定的分析器对检索词进行分析，找到相应结果输出。
		 ===============================================================*/
		public static void QueryStandardAnalyzerTest(){
		
			try {
				Analyzer analyzer = new StandardAnalyzer();
				
				IndexSearcher searcher = new IndexSearcher(Dest_Index_Path);
			    String searchWords = "中文文档";
			    QueryParser parser = new QueryParser("content",analyzer); 
			    
			    try{
				    Query query = parser.parse(searchWords);
					System.out.println(query.toString());
					//System.out.println(query.getClass());
		
					Hits hits = searcher.search(query);
					
					System.out.println("Search result:");	
					
					for(int i=0; i < hits.length(); i++)
					{
						System.out.println(hits.doc(i).getField("content"));
					}

			    } catch(ParseException e1){
					e1.printStackTrace();
			    }
			}catch (IOException e) {
					e.printStackTrace();
			}
			System.out.println("Search success");		
		}
		
	public static void main(String[] args) {

		IndexBuilder();
		QueryStandardAnalyzerTest();
	}
}