代码片段，使用TIKA来解析PDF,WORD和EMAIL

?

/**

 * com.jiaoyiping.pdstest.TestTika.java

 * Copyright (c) 2009 Hewlett-Packard Development Company, L.P.

 * All rights reserved.

 */

package com.jiaoyiping.pdstest;

 

import java.io.BufferedInputStream;

import java.io.BufferedOutputStream;

import java.io.File;

import java.io.FileInputStream;

import java.io.FileOutputStream;

import java.io.InputStream;

import java.io.OutputStream;

 

import org.apache.tika.metadata.Metadata;

import org.apache.tika.parser.ParseContext;

import org.apache.tika.parser.Parser;

import org.apache.tika.parser.mail.RFC822Parser;

import org.apache.tika.parser.microsoft.OfficeParser;

import org.apache.tika.parser.pdf.PDFParser;

import org.apache.tika.sax.BodyContentHandler;

import org.junit.Test;

import org.xml.sax.ContentHandler;

 

/**

 * <pre>

 * Desc：

 * @author 焦一平

 * @refactor 焦一平

 * @date   2014年12月4日 下午1:31:09

 * @version 1.0

 * @see 

 * REVISIONS:

 * Version     Date             Author            Description

 * -------------------------------------------------------------------

 * 1.0        2014年12月4日                                  焦一平            1. Created this class.

 * </pre> 

 */

public class TestTika {

     

    //解析PDF

    @Test

    public void testPdf() throws Exception{

        Long start = System.currentTimeMillis();

        Parser parser = new PDFParser();

        InputStream is = new BufferedInputStream(new FileInputStream(new File("D:\\我的微盘\\文档\\参考文档\\Linux Shell脚本攻略.pdf")));

        OutputStream os = new BufferedOutputStream(new FileOutputStream(new File("C:\\Users\\Administrator\\Desktop\\result.txt")));

        Metadata meta = new Metadata(); 

        meta.add(Metadata.CONTENT_ENCODING, "utf-8"); 

        ContentHandler iHandler = new BodyContentHandler(os); 

        parser.parse(is, iHandler, meta, new ParseContext());

        Long end = System.currentTimeMillis();

        Long used = (end-start)/1000;

        System.out.println("耗时： "+used+"秒");

    }

    //解析Word

    @Test

    public void testWrod() throws Exception{

        Long start = System.currentTimeMillis();

        Parser parser = new OfficeParser();

        InputStream is = new BufferedInputStream(new FileInputStream(new File("D:\\我的微盘\\文档\\参考文档\\jBPM5_用户指南中文版.doc")));

        OutputStream os = new BufferedOutputStream(new FileOutputStream(new File("C:\\Users\\Administrator\\Desktop\\result.txt")));

        Metadata meta = new Metadata(); 

        meta.add(Metadata.CONTENT_ENCODING, "utf-8"); 

        ContentHandler iHandler = new BodyContentHandler(os); 

        parser.parse(is, iHandler, meta, new ParseContext());

         

        Long end = System.currentTimeMillis();

        Long used = (end-start)/1000;

        System.out.println("耗时："+used+"秒");

    }

    //解析EMAIL(只能解析标准的eml格式的,不能解析微软的msg格式)

    //使用commons-email来进行解析的可以得到收件人、发件人、主题、内容等元数据,TIkA是否支持未尝试

    @Test

    public void testEmail() throws Exception{

        Long start = System.currentTimeMillis();

        Parser parser = new RFC822Parser();

        InputStream is = new BufferedInputStream(new FileInputStream(new File("C:\\Users\\Administrator\\Downloads\\回复_ RE_ 数据导入工作 - 外部系统枚举与U-Cloud枚举映射.eml")));

        OutputStream os = new BufferedOutputStream(new FileOutputStream(new File("C:\\Users\\Administrator\\Desktop\\result.txt")));

        Metadata meta = new Metadata(); 

        meta.add(Metadata.CONTENT_ENCODING, "utf-8");

        ContentHandler iHandler = new BodyContentHandler(os); 

        parser.parse(is, iHandler, meta, new ParseContext());

         

        Long end = System.currentTimeMillis();

        Long used = (end-start)/1000;

        System.out.println("耗时："+used+"秒");

    }

}