pdflucenetest.java

一个搜索引擎,希望对大家有用

package ch7.pdfbox;

import java.io.File;

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.FuzzyQuery;
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.apache.lucene.search.WildcardQuery;
import org.pdfbox.searchengine.lucene.LucenePDFDocument;

public class PdfLuceneTest {
	public static void main(String[] args) {
		try {
			// IndexWriter存放索引到d:\index下
			IndexWriter writer = new IndexWriter("d:\\index",
					new StandardAnalyzer(), true);
			// LucenePDFDocument返回由PDF产生的Lucene Docuement
			Document d = LucenePDFDocument
					.getDocument(new File("C:\\index.pdf"));
			// 写入索引
			writer.addDocument(d);
			// 关闭索引文件流
			writer.close();
			// 读取d:\index下的索引文件建立IndexSearcher
			IndexSearcher searcher = new IndexSearcher("d:\\index");
			// 对索引的contents Field进行查找关键词poi
			Term t = new Term("contents", "poi");
			// 根据Term生成Query
			Query q = new TermQuery(t);
			// 搜索返回结果集
			Hits hits = searcher.search(q);
			// 打印结果集
			for (int i = 0; i < hits.length(); i++) {
				System.out.println(hits.doc(i));
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}