pdfboxpathindex.java

《lucene+nutch搜索引擎开发》源代码

package chapter9;

import java.io.FileInputStream;
import java.io.IOException;
import java.io.File;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.pdfbox.searchengine.lucene.LucenePDFDocument;
import org.pdfbox.searchengine.lucene.IndexFiles;

public class PDFBoxPathIndex {
	private static String Dst_Index_Path = "D:\\workshop\\pdfindex\\";
	private static String Src_Index_Path = "D:\\workshop\\docs\\";
	
	/*================================================================
	 * 名 称：PDFQueryIndex
	 * 功 能：构造PDF文档检索查询器，对指定的索引进行查询。
	 ===============================================================*/
	public static void PDFQueryIndex(){
		
		try {
			IndexSearcher searcher = new IndexSearcher(Dst_Index_Path); // 生成检索器对象
			Term term = new Term("contents","pdfbox");                  // 检索关键字
			Query query = new TermQuery(term);                          // 生成检索对象
			System.out.println("----------检索内容："+query.toString()+"----------");	

			Hits hits = searcher.search(query);                          // 提交检索
			
			System.out.println("----------检索结果: 共检索到 "+hits.length()+" 条 ----------");		
			
//			for(int i=0; i < hits.length(); i++)                         // 获得结果
//			{
//				System.out.println(hits.doc(i));
//				System.out.println(hits.doc(i).getField("id"));			
//			}
			
		}catch (IOException e) {
				e.printStackTrace();
		}

		System.out.println("----------索引检索：PDF索引查询成功----------");		
		
	}
	
	/*================================================================
	 * 名 称：PDFIndexBuilder
	 * 功 能：针对指定的目录，构造PDF磁盘索引。
	 ===============================================================*/
	public static void PDFIndexBuilder(){
		
		try {
			

	        IndexFiles indexpdf = new IndexFiles();
	        indexpdf.index(new File(Src_Index_Path),true,Dst_Index_Path);
		
		}catch ( Exception e) {
				e.printStackTrace();
		}

		System.out.println("----------创建索引：PDF 文件成功. ----------");		
	}
	/*================================================================
	 * 名 称：main
	 * 功 能：测试Lucene中PDF文件的索引建立和检索查询功能。
	 ===============================================================*/
	public static void main(String[] args) {
		
		PDFIndexBuilder();    // 创建索引
		PDFQueryIndex();      // 检索关键字 
		
		System.out.println("----------PDF Lucene 检索测试 ----------");
	}
}