用java修改文件的编码

Posted 2020-09-29 zhangjinru123

1、将本地的文件转换成另外一种编码输出，主要逻辑代码如下：

 1  /**
 2      * 将本地文件以哪种编码输出
 3      * @param inputfile 输入文件的路径
 4      * @param outfile 输出文件的路径
 5      * @param code 输出文件的编码
 6      * @throws IOException
 7      */
 8     public  void convert(String inputfile,String outfile,String code) throws IOException {
 9         StringBuffer sb = new StringBuffer();
10         //得到当前文件的编码
11         String ch=getCharset(inputfile);
12         InputStreamReader isr=null;
13         OutputStreamWriter osw =null;
14         //根据当前文件编码进行解码
15         if(ch.equals("UTF8")){
16             isr= new InputStreamReader(new FileInputStream(inputfile), "UTF-8");    
17         }else if(ch.equals("Unicode")){
18             isr= new InputStreamReader(new FileInputStream(inputfile), "Unicode");    
19         }else {
20             isr= new InputStreamReader(new FileInputStream(inputfile), "GB2312");    
21         }
22         //将字符串存入StringBuffer中
23         BufferedReader br = new BufferedReader(isr);        
24         String line = null;
25         while ((line = br.readLine()) != null) {
26             sb.append(line + "\\n");
27         }        
28         br.close();
29         isr.close();
30 
31         //以哪种方式写入文件
32         if("UTF-8".equals(code)){
33             osw = new OutputStreamWriter(new FileOutputStream(outfile), "UTF-8");
34         }else if("GB2312".equals(code)){
35             osw = new OutputStreamWriter(new FileOutputStream(outfile), "GB2312");
36         }else if("Unicode".equals(code)){
37             osw = new OutputStreamWriter(new FileOutputStream(outfile), "Unicode");
38         }else{
39             osw = new OutputStreamWriter(new FileOutputStream(outfile), "UTF-8");
40         }
41         BufferedWriter bw = new BufferedWriter(osw);
42         bw.write(sb.toString());
43         bw.close();
44         osw.close();
45     }
46 
47 /**
48      * 根据文件路径判断编码
49      * @param str
50      * @return
51      * @throws IOException
52      */
53     private String getCharset(String str) throws IOException{ 
54         BytesEncodingDetect s = new BytesEncodingDetect();   
55         String code = BytesEncodingDetect.javaname[s.detectEncoding(new File(str))];  
56         return code;  
57     } 

View Code

2、将远程的文件转换成自己想要的编码，然后写入本地

 1 /**
 2      * 将远程文件以哪种编码输出到本地
 3      * @param fileurl 远程文件的URL
 4      * @param outfile 输出文件的路径
 5      * @param code 以哪种编码输出
 6      * @throws Exception
 7      */
 8     public void Remote(String fileurl,String outfile,String code) throws Exception{ 
 9         //        String str="http://172.18.1.103:8080/kms/text.txt";
10         URL url =new URL(fileurl);
11         HttpURLConnection urlCon = (HttpURLConnection)url.openConnection();
12         //设置连接超时和读取超时
13         urlCon.setConnectTimeout(5000);
14         urlCon.setReadTimeout(5000);
15         //得到远程文件的编码
16         String ch=getCharset_Remote(fileurl);
17         //文件写入流
18         OutputStreamWriter osw =null;
19         BufferedReader br=null;
20         //将字符串保存到临时的StringBuffer中
21         StringBuffer sb = new StringBuffer();
22         if(ch.equals("UTF8")){
23             br =new BufferedReader(new InputStreamReader( urlCon.getInputStream(),"UTF-8"));
24             String line = null;
25             while ((line = br.readLine()) != null) {
26                 sb.append(line + "\\n");
27             }
28         }
29         else if(ch.equals("Unicode")){
30             br =new BufferedReader(new InputStreamReader( urlCon.getInputStream(),"Unicode"));
31             String line = null;
32             while ((line = br.readLine()) != null) {
33                 sb.append(line + "\\n");
34             }
35         }
36         else{
37             br =new BufferedReader(new InputStreamReader( urlCon.getInputStream(),"GB2312"));
38             String line = null;
39             while ((line = br.readLine()) != null) {
40                 sb.append(line + "\\n");
41             }
42         }
43         br.close();    
44 
45         //以哪种方式写入文件
46         if("UTF-8".equals(code)){
47             osw = new OutputStreamWriter(new FileOutputStream(outfile), "UTF-8");
48         }else if("GB2312".equals(code)){
49             osw = new OutputStreamWriter(new FileOutputStream(outfile), "GB2312");
50         }else if("Unicode".equals(code)){
51             osw = new OutputStreamWriter(new FileOutputStream(outfile), "Unicode");
52         }else{
53             osw = new OutputStreamWriter(new FileOutputStream(outfile), "UTF-8");
54         }
55         BufferedWriter bw = new BufferedWriter(osw);
56         bw.write(sb.toString());
57         bw.close();
58         osw.close();
59     } 
60 
61 /**
62      * 根据文件路径判断远程文件编码
63      * @param str
64      * @return
65      * @throws IOException
66      */
67     private String getCharset_Remote(String str) throws IOException{  
68         URL url =new URL(str);
69         BytesEncodingDetect s = new BytesEncodingDetect();   
70         String fileCode = BytesEncodingDetect.javaname[s.detectEncoding(url)];  
71         return fileCode;
72     }

View Code

3、测试代码：

 1 package com.zhang.test;
 2 
 3 public class test {
 4     public static void main(String[] args) {
 5         String inputfile="D:/gbk.txt";
 6         String outfile="D:/utf8.txt";
 7         String outfileurl="D:/utf8url.txt";
 8         String fileurl="http://127.0.0.1:8080/jsp/gbk.txt";
 9 //        String file="D:/unicode.txt";
10         Convert_Code code=new Convert_Code();
11         try {
12             code.convert(inputfile,outfile,"UTF-8");
13             code.Remote(fileurl, outfileurl, "UTF-8");
14         } catch (Exception e) {
15             e.printStackTrace();
16         }
17     }
18 }

View Code

注意：这两个方法引用了BytesEncodingDetect.java文件

此案例的下载链接：http://download.csdn.net/detail/u013865056/9908100