java字符转码:三种方法
转码成功的前提:解码后无乱码
转码流程:文件(gbk)-->解码-->编码--->文件(utf-8)
注:如有问题请留言
下面具体的实例
方法一:Java.lang.String
|
1
2
3
4
5
6
7
8
|
//用于解码的构造器:
String(byte[] bytes, int offset, int length, String charsetName)
String(byte[] bytes, String charsetName)
用于编码的方法:
byte[] getBytes(String charsetName) //使用指定字符集进行编码
byte[] getBytes() //使用系统默认字符集进行编码
<br>
|
|
1
2
3
4
5
6
7
8
9
10
|
public void convertionString() throws UnsupportedEncodingException{
String s = "清山";
byte[] b = s.getBytes("gbk");//编码
String sa = new String(b, "gbk");//解码:用什么字符集编码就用什么字符集解码
System.out.println(sa);
b = sa.getBytes("utf-8");//编码
sa = new String(b, "utf-8");//解码
System.err.println(sa);
}
|
方法二:java.io.InputStreamReader/OutputStreamWriter:桥转换
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
|
package com.qingshan.io;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.UnsupportedEncodingException;
/**
* <pre>
* 使用java.io桥转换:对文件进行转码
* </pre>
* <hr Color="green" ></hr>
* 2012 Qingshan Group 版权所有
* <hr Color="green" ></hr>
* @author thetopofqingshan
* @version 1.0.0
* @since JDK 1.5
* @date 2012-4-28
*/
public class CharsetConvertion {
private FileInputStream fis;// 文件输入流:读取文件中内容
private InputStream is;
private InputStreamReader isr;
private OutputStream os;
private OutputStreamWriter osw;//写入
private char[] ch = new char[1024];
public void convertionFile() throws IOException{
is = new FileInputStream("C:/项目进度跟踪.txt");//文件读取
isr = new InputStreamReader(is, "gbk");//解码
os = new FileOutputStream("C:/项目进度跟踪_utf-8.txt");//文件输出
osw = new OutputStreamWriter(os, "utf-8");//开始编码
char[] c = new char[1024];//缓冲
int length = 0;
while(true){
length = isr.read(c);
if(length == -1){
break;
}
System.out.println(new String(c, 0, length));
osw.write(c, 0, length);
osw.flush();
}
}
public void convertionString() throws UnsupportedEncodingException{
String s = "清山集团";
byte[] b = s.getBytes("gbk");//编码
String sa = new String(b, "gbk");//解码:用什么字符集编码就用什么字符集解码
System.out.println(sa);
b = sa.getBytes("utf-8");//编码
sa = new String(b, "utf-8");//解码
System.err.println(sa);
}
/**
* <pre>
* 关闭所有流
* </pre>
*
*/
public void close(){
if(isr != null){
try {
isr.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(is != null){
try {
is.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
if(osw != null){
try {
osw.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
if(os != null){
try {
os.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
/**
* <pre>
* 用io读取文件内容
* </pre>
*
* @throws IOException
* 读取过程中发生错误
*
*/
/**
* <pre>
*
* </pre>
* @param path
* @param charset
* @throws IOException
*
*/
public void read(String path, String charset) throws IOException {
fis = new FileInputStream(path);
isr = new InputStreamReader(fis, charset);
while (fis.available() > 0) {
int length = isr.read(ch);
System.out.println(new String(ch));
}
}
public static void main(String[] args) {
try {
CharsetConvertion cc = new CharsetConvertion();
cc.convertionFile();
cc.convertionString();
cc.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
|
方法三:java.nio.Charset
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
|
package com.qingshan.nio;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.channels.FileChannel;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
/**
* <pre>
* 使用nio中的Charset转换字符:整个流程是文件读取-->byte-->解码(正确)-->编码--->byte-->写入文件
* </pre>
* <hr Color="green" >
* </hr>
* 2012 Qingshan Group 版权所有
* <hr Color="green" >
* </hr>
*
* @author thetopofqingshan
* @version 1.0.0
* @since JDK 1.5
* @date 2012-4-27
*/
public class CharsetConvertion {
private FileInputStream fis;// 文件输入流:读取文件中内容
private FileChannel in;// 文件通道:双向,流从中而过
private FileChannel out;// 文件通道:双向,流从中而过
private FileOutputStream fos;// 文件输出流:向文件中写入内容
private ByteBuffer b = ByteBuffer.allocate(1024 * 3);// 设置缓存区的大小
private Charset inSet;// 解码字符集
private Charset outSet;// 编码字符集
private CharsetDecoder de;// 解码器
private CharsetEncoder en;// 编码器
private CharBuffer convertion;// 中间的字符数据
private ByteBuffer temp = ByteBuffer.allocate(1024 * 3);// 设置缓存区的大小:临时
private byte[] by = new byte[1024];
private InputStreamReader isr;
private char[] ch = new char[1024];
/**
* <pre>
*
* </pre>
*
* @param src
* @param dest
* @throws IOException
*
*/
public void convertionFile_nio(String src, String dest) throws IOException {
fis = new FileInputStream(src);
in = fis.getChannel();
fos = new FileOutputStream(dest);
out = fos.getChannel();
inSet = Charset.forName("gbk");
outSet = Charset.forName("utf-8");
de = inSet.newDecoder();
en = outSet.newEncoder();
while (fis.available() > 0) {
b.clear();// 清除标记
in.read(b); // 将文件内容读入到缓冲区内:将标记位置从0-b.capacity(),
// 读取完毕标记在0-b.capacity()之间
b.flip();// 调节标记,下次读取从该位置读起
convertion = de.decode(b);// 开始编码
temp.clear();// 清除标记
temp = en.encode(convertion);
b.flip(); // 将标记移到缓冲区的开始,并保存其中所有的数据:将标记移到开始0
out.write(temp); // 将缓冲区内的内容写入文件中:从标记处开始取出数据
}
}
/**
* <pre>
* 测试转码是否成功, 指定字符集读取文件
* </pre>
*
* @param src
* 被复制文件全路径
* @param charset 解码字符集
*
* @throws IOException 读取过程中的发生的异常
*
*/
public void read(String path, String charset) throws IOException {
fis = new FileInputStream(path);
isr = new InputStreamReader(fis, charset);
while (fis.available() > 0) {
int length = isr.read(ch);
System.out.println(new String(ch));
}
}
/**
* <pre>
* 关闭所有流或通道
* </pre>
*
*/
public void close() {
try {
if (in != null) {
in.close();
}
} catch (IOException e) {
e.printStackTrace();
}
try {
if (out != null) {
out.close();
}
} catch (IOException e) {
e.printStackTrace();
}
try {
if (fis != null) {
fis.close();
}
} catch (IOException e) {
e.printStackTrace();
}
try {
if (fos != null) {
fos.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
CharsetConvertion n = new CharsetConvertion();
try {
n.convertionFile_nio("C:/项目进度跟踪.txt", "C:/nio_write.txt");
// n.read("C:/nio_write.txt", "utf-8");// 正确
// n.read("C:/nio_write.txt", "gbk");//乱码
} catch (IOException e) {
e.printStackTrace();
} finally {
n.close();
}
}
}
|
感谢阅读，希望能帮助到大家，谢谢大家对本站的支持！
原文链接：http://blog.csdn.net/zhengqiqiqinqin/article/details/12621201