java 从zip包中抽取文件

项目需求

• 从多个文件夹中读取zip包
• 解压zip包
• 读取zip包中的数据
• 把读取的数据写入到txt文件中

Util.java

import java.io.*;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.List;
import java.util.zip.*;


public class Util {
    public List<String> getFileName(String path){//path为绝对路径
        List<String> zipFileName = new ArrayList<String>();
        File file = new File(path);
        File[] files = file.listFiles();
        if(files.length == 0){
            System.out.println("This package is empty");
        }else{
            for(File file2:files){
                if(file2.isDirectory()){
                    String name_1 = file2.getName();
                    File[] zipfile = file2.listFiles();
                    for(File zip:zipfile){
                        zipFileName.add(name_1+File.separator+zip.getName().replaceAll(".zip",""));
                    }
                }
            }
        }
        return zipFileName;
    }

    public List<String> getZipWithAnt(String path) throws Exception {
        List<String> innerJsonFile = new ArrayList<String>();
        String[] strings = new String[0];
        FileInputStream fis = null;
        try {
            fis = new FileInputStream(path);
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
        CheckedInputStream check = new CheckedInputStream(fis,new Adler32());
        Charset gbk = Charset.forName("gbk");
        ZipInputStream zis = new ZipInputStream(check,gbk);
        ZipEntry ze = zis.getNextEntry();
        BufferedReader br = new BufferedReader(new InputStreamReader(zis));
        char[] chars =  new char[1024*1024];
        while(ze != null){
            if(ze.toString().endsWith(".txt")){
                String line;
                while((line = br.readLine())!= null){
                    line = line.substring(1,line.length()-1);
                    strings = line.split(",\\{");
                    for(int i = 1;i < strings.length;i++){
                        strings[i] = "{" + strings[i];
                    }
                    break;
                }
            }
            ze = zis.getNextEntry();
        }
        br.close();
        zis.close();
        check.close();
        fis.close();
        for(String str:strings){
            innerJsonFile.add(str);
        }
        System.out.println(path);
        return innerJsonFile;
    }

    public List<String> getZipInnerFile(String path)  {//path格式为xxx.zip
        List<String> innerJsonFile = new ArrayList<String>();
        ZipFile zf = null;
        try {
            zf = new ZipFile(path);
        } catch (IOException e) {
            System.out.println(e);
            e.printStackTrace();
        }
        try {
            InputStream in = null;
            in = new BufferedInputStream(new FileInputStream(path));
            Charset gbk = Charset.forName("GBK");
            ZipInputStream zin = new ZipInputStream(in,gbk);
            ZipEntry ze = new ZipEntry(path);
            while((ze = zin.getNextEntry()) != null){
                if(ze.toString().endsWith("txt")){
                    BufferedReader br = new BufferedReader(
                            new InputStreamReader(zf.getInputStream(ze)));
                    String line;
                    while((line = br.readLine()) != null){
                        line = line.substring(1,line.length()-1);
                        String[] strings = line.split(",\\{");
                        for(int i = 1;i < strings.length;i++){
                            strings[i] = "{" + strings[i];
                        }
                        for(String str:strings){
                            innerJsonFile.add(str);
                        }
                        line = br.readLine();
                    }
                    br.close();
                }
                else if(ze.toString().startsWith("attach")){
                    break;
                }
            }
            zin.closeEntry();
            return innerJsonFile;
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            System.out.println(path);
        }
        return null;
    }
    public void writeToTxt(String json,String path) throws IOException {
        BufferedWriter out = new BufferedWriter(
                new OutputStreamWriter(new FileOutputStream(path,true)));
        out.write(json+"\r\n");
        out.close();
    }
}

Collect.java

import java.io.File;
import java.io.IOException;
import java.util.List;

public class Collect {
    public static void main(String[] args){
        String path = "/data/app/sh/notes";
        Util util = new Util();
        List<String> zipfilename = util.getFileName(path);
        String name = "part-r-0000";//存储json的文件名
        int count = 0,n = 0;
        //path+zipfilename+".zip"   即为绝对路径
        //读取zip包内文件
        for(String file:zipfilename){
            String fullFileName = path + File.separator+ file + ".zip";

             List<String> innerJsonFile = null;
            try {
                innerJsonFile = util.getZipWithAnt(fullFileName);//json条
            } catch (Exception ex) {
                continue;
            }
            for(String json:innerJsonFile){
                if(count < 10000 ){
                    try {
                        util.writeToTxt(file+"\t"+json,path+File.separator+"json"+File.separator+name+String.valueOf(n)+".txt");
                    } catch (IOException e) {
                        e.printStackTrace();
                    }finally {
                        count++;
                    }
                }
                else{
                    count = 0;
                    n++;
                    try {
                        util.writeToTxt(file+"\t"+json,path+File.separator+"json"+File.separator+name+String.valueOf(n)+".txt");
                    } catch (IOException e) {
                        e.printStackTrace();
                    }finally {
                        count++;
                    }
                }
            }
        }
    }
}

本次实验遇到的问题：不可在main函数上加异常，否则为系统级异常，抛出异常后程序自动停止。
注：中间遇到的其他问题在本人其他博客已写明。