字符编码工具类
字符编码工具类
package charTools;
import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import java.net.URLDecoder;
import java.security.*;
import java.text.*;
import java.util.*;
/**
* Title:字符编码工具类
* Description:
* Copyright: flashman.com.cn Copyright (c) 2005
* Company: flashman.com.cn
* @author: jeffzhu
* @version 1.0
*/
/*
*===================功能说明====================================
*
*================================字符操作=======================
*String chopAtWord(String string, int length) 从字符串第一位开始取n位字符
*
*
*
*=================================编码转换======================
*String ISO2GB(String text) 转换编码 ISO-8859-1到GB2312
*String GB2ISO(String text) 转换编码 GB2312到ISO-8859-1
*String Utf8URLencode(String text) Utf8URL编码
*String Utf8URLdecode(String text) Utf8URL解码
*String CodeToWord(String text） utf8URL编码转字符
*boolean Utf8codeCheck(String text) 编码是否有效
*boolean isUtf8Url(String text) 是否Utf8Url编码
*
*
*==================================加密解密======================
*synchronized static final String hash(String data) MessageDigest加密
*String encodeBase64(String data) base64加密
*public static String decodeBase64(String data) base64解密
*
*
*/
public class charTools1 {
/**
* 转换编码 ISO-8859-1到GB2312
* @param text
* @return
*/
public String ISO2GB(String text) {
String result = "";
try {
result = new String(text.getBytes("ISO-8859-1"), "GB2312");
}
catch (UnsupportedEncodingException ex) {
result = ex.toString();
}
return result;
}
/**
* 转换编码 GB2312到ISO-8859-1
* @param text
* @return
*/
public String GB2ISO(String text) {
String result = "";
try {
result = new String(text.getBytes("GB2312"), "ISO-8859-1");
}
catch (UnsupportedEncodingException ex) {
ex.printStackTrace();
}
return result;
}
/**
* Utf8URL编码
* @param s
* @return
*/
public String Utf8URLencode(String text) {
StringBuffer result = new StringBuffer();
for (int i = 0; i < text.length(); i++) {
char c = text.charAt(i);
if (c >= 0 && c <= 255) {
result.append(c);
}else {
byte[] b = new byte[0];
try {
b = Character.toString(c).getBytes("UTF-8");
}catch (Exception ex) {
}
for (int j = 0; j < b.length; j++) {
int k = b[j];
if (k < 0) k += 256;
result.append("%" + Integer.toHexString(k).toUpperCase());
}
}
}
return result.toString();
}
/**
* Utf8URL解码
* @param text
* @return
*/
public String Utf8URLdecode(String text) {
String result = "";
int p = 0;
if (text!=null && text.length()>0){
text = text.toLowerCase();
p = text.indexOf("%e");
if (p == -1) return text;
while (p != -1) {
result += text.substring(0, p);
text = text.substring(p, text.length());
if (text == "" || text.length() < 9) return result;
result += CodeToWord(text.substring(0, 9));
text = text.substring(9, text.length());
p = text.indexOf("%e");
}
}
return result + text;
}
/**
* utf8URL编码转字符
* @param text
* @return
*/
private String CodeToWord(String text) {
String result;
if (Utf8codeCheck(text)) {
byte[] code = new byte[3];
code[0] = (byte) (Integer.parseInt(text.substring(1, 3), 16) - 256);
code[1] = (byte) (Integer.parseInt(text.substring(4, 6), 16) - 256);
code[2] = (byte) (Integer.parseInt(text.substring(7, 9), 16) - 256);
try {
result = new String(code, "UTF-8");
}catch (UnsupportedEncodingException ex) {
result = null;
}
}
else {
result = text;
}
return result;
}
public static boolean isValidUtf8(byte[] b, int aMaxCount) {
int lLen = b.length, lCharCount = 0;
for (int i = 0; i < lLen && lCharCount < aMaxCount; ++lCharCount) {
byte lByte = b[i++]; //to fast operation, ++ now, ready for the following for(;;)
if (lByte >= 0) continue; //>=0 is normal ascii
if (lByte < (byte) 0xc0 || lByte > (byte) 0xfd)
return false;
int lCount = lByte > (byte) 0xfc ? 5 : lByte > (byte) 0xf8 ? 4 : lByte > (byte) 0xf0 ? 3 : lByte > (byte) 0xe0 ? 2 : 1;
if (i + lCount > lLen) return false;
for (int j = 0; j < lCount; ++j, ++i)
if (b[i] >= (byte) 0xc0)return false;
}
return true;
}
/**
* 编码是否有效
* @param text
* @return
*/
private boolean Utf8codeCheck(String text){
String sign = "";
if (text.startsWith("%e"))
for (int i = 0, p = 0; p != -1; i++) {
p = text.indexOf("%", p);
if (p != -1)
p++;
sign += p;
}
return sign.equals("147-1");
}
/**
* 是否Utf8Url编码
* @param text
* @return
*/
public boolean isUtf8Url(String text) {
text = text.toLowerCase();
int p = text.indexOf("%");
if (p != -1 && text.length() - p > 9) {
text = text.substring(p, p + 9);
}
return Utf8codeCheck(text);
}
/*
* ======================================加密解密=================================================
*/
/**
* Used by the hash method.
*/
private static MessageDigest digest = null;
/**
* 将传入的参数转化为它所对应的hash码
* @param data the String to compute the hash of.
* @return a hashed version of the passed-in String
*/
public synchronized static final String hash(String data) {
if (digest == null) {
try {
digest = MessageDigest.getInstance("MD5");
}
catch (NoSuchAlgorithmException nsae) {
System.err.println("Failed to load the MD5 MessageDigest. " +
"Jive will be unable to function normally.");
nsae.printStackTrace();
}
}
// Now, compute hash.
digest.update(data.getBytes());
return encodeHex(digest.digest());
}
/**
* 将传入的byte型数组转化为对应的十六进制，并组合成字符串输出
* Turns an array of bytes into a String representing each byte as an
* unsigned hex number.
* <p>
* Method by Santeri Paavolainen, Helsinki Finland 1996<br>
* (c) Santeri Paavolainen, Helsinki Finland 1996<br>
* Distributed under LGPL.
*
* @param bytes an array of bytes to convert to a hex-string
* @return generated hex string
*/
public static final String encodeHex(byte[] bytes) {
StringBuffer buf = new StringBuffer(bytes.length * 2);
int i;
for (i = 0; i < bytes.length; i++) {
if (((int) bytes[i] & 0xff) < 0x10) {
buf.append("0");
}
buf.append(Long.toString((int) bytes[i] & 0xff, 16));
}
return buf.toString();
}
/**
* 将十六进制数字型的字符串转化为byte型的数组，将字符串按两位两位分开
* Turns a hex encoded string into a byte array. It is specifically meant
* to "reverse" the toHex(byte[]) method.
* @param hex a hex encoded String to transform into a byte array.
* @return a byte array representing the hex String[
*/
public static final byte[] decodeHex(String hex) {
char [] chars = hex.toCharArray();
byte[] bytes = new byte[chars.length/2];
int byteCount = 0;
for (int i=0; i<chars.length; i+=2) {
byte newByte = 0x00;
newByte |= hexCharToByte(chars[i]);
newByte <<= 4;
newByte |= hexCharToByte(chars[i+1]);
bytes[byteCount] = newByte;
byteCount++;
}
return bytes;
}
/**
* Returns the the byte value of a hexadecmical char (0-f). It's assumed
* that the hexidecimal chars are lower case as appropriate.
*
* @param ch a hexedicmal character (0-f)
* @return the byte value of the character (0x00-0x0F)
*/
private static final byte hexCharToByte(char ch) {
switch(ch) {
case '0': return 0x00;
case '1': return 0x01;
case '2': return 0x02;
case '3': return 0x03;
case '4': return 0x04;
case '5': return 0x05;
case '6': return 0x06;
case '7': return 0x07;
case '8': return 0x08;
case '9': return 0x09;
case 'a': return 0x0A;
case 'b': return 0x0B;
case 'c': return 0x0C;
case 'd': return 0x0D;
case 'e': return 0x0E;
case 'f': return 0x0F;
}
return 0x00;
}
//*********************************************************************
//* Base64 - a simple base64 encoder and decoder.
//*
//* Copyright (c) 1999, Bob Withers - [email protected]
//*
//* This code may be freely used for any purpose, either personal
//* or commercial, provided the authors copyright notice remains
//* intact.
//*********************************************************************
/**base64加密
* Encodes a String as a base64 String.
*
* @param data a String to encode.
* @return a base64 encoded String.
*/
public static String encodeBase64(String data) {
return encodeBase64(data.getBytes());
}
/**
* Encodes a byte array into a base64 String.
*
* @param data a byte array to encode.
* @return a base64 encode String.
*/
public static String encodeBase64(byte[] data) {
int c;
int len = data.length;
StringBuffer ret = new StringBuffer(((len / 3) + 1) * 4);
for (int i = 0; i < len; ++i) {
c = (data[i] >> 2) & 0x3f;
ret.append(cvt.charAt(c));
c = (data[i] << 4) & 0x3f;
if (++i < len)
c |= (data[i] >> 4) & 0x0f;
ret.append(cvt.charAt(c));
if (i < len) {
c = (data[i] << 2) & 0x3f;
if (++i < len)
c |= (data[i] >> 6) & 0x03;
ret.append(cvt.charAt(c));
}
else {
++i;
ret.append((char) fillchar);
}
if (i < len) {
c = data[i] & 0x3f;
ret.append(cvt.charAt(c));
}
else {
ret.append((char) fillchar);
}
}
return ret.toString();
}
/**base64解密
* Decodes a base64 String.
*
* @param data a base64 encoded String to decode.
* @return the decoded String.
*/
public static String decodeBase64(String data) {
return decodeBase64(data.getBytes());
}
/**
* Decodes a base64 aray of bytes.
*
* @param data a base64 encode byte array to decode.
* @return the decoded String.
*/
public static String decodeBase64(byte[] data) {
int c, c1;
int len = data.length;
StringBuffer ret = new StringBuffer((len * 3) / 4);
for (int i = 0; i < len; ++i) {
c = cvt.indexOf(data[i]);
++i;
c1 = cvt.indexOf(data[i]);
c = ((c << 2) | ((c1 >> 4) & 0x3));
ret.append((char) c);
if (++i < len) {
c = data[i];
if (fillchar == c)
break;
c = cvt.indexOf((char) c);
c1 = ((c1 << 4) & 0xf0) | ((c >> 2) & 0xf);
ret.append((char) c1);
}
if (++i < len) {
c1 = data[i];
if (fillchar == c1)
break;
c1 = cvt.indexOf((char) c1);
c = ((c << 6) & 0xc0) | c1;
ret.append((char) c);
}
}
return ret.toString();
}
private static final int fillchar = '=';
private static final String cvt = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+ "abcdefghijklmnopqrstuvwxyz"
+ "0123456789+/";
/**
* 从字符串中取n位字符
*
* @param string the String to chop.
* @param length the index in <code>string</code> to start looking for a
* whitespace boundary at.
* @return a substring of <code>string</code> whose length is less than or
* equal to <code>length</code>, and that is chopped at whitespace.
*/
public static final String chopAtWord(String string, int length) {
if (string == null) {
return string;
}
char [] charArray = string.toCharArray();
int sLength = string.length();
if (length < sLength) {
sLength = length;
}
// First check if there is a newline character before length; if so,
// chop word there.
for (int i=0; i<sLength-1; i++) {
// Windows
if (charArray[i] == '\r' && charArray[i+1] == '\n') {
return string.substring(0, i+1);
}
// Unix
else if (charArray[i] == '\n') {
return string.substring(0, i);
}
}
// Also check boundary case of Unix newline
if (charArray[sLength-1] == '\n') {
return string.substring(0, sLength-1);
}
// Done checking for newline, now see if the total string is less than
// the specified chop point.
if (string.length() < length) {
return string;
}
// No newline, so chop at the first whitespace.
for (int i = length-1; i > 0; i--) {
if (charArray[i] == ' ') {
return string.substring(0, i).trim();
}
}
// Did not find word boundary so return original String chopped at
// specified length.
return string.substring(0, length);
}
/**
* 测试
* @param args
*/
public static void main(String[] args) {
//实例化工具类
charTools1 charTools = new charTools1();
String url;
//定义一个URL字符串
url="http://www.baidu.com/s?bs=indexof+%D3%C3%B7%A8&f=8&wd=java+%D7%D6%B7%FB%B4%A6%C0%ED%B9%A4%BE%DF%C0%E0";
// url = "http://www.google.com/search?hl=zh-CN&newwindow=1&q=%E4%B8%AD%E5%9B%BD%E5%A4%A7%E7%99%BE%E7%A7%91%E5%9C%A8%E7%BA%BF%E5%85%A8%E6%96%87%E6%A3%80%E7%B4%A2&btnG=%E6%90%9C%E7%B4%A2&lr=";
//调用方法isUtf8Url，进行判断是否Utf8Url编码
if(charTools.isUtf8Url(url)){
//如果是Utf8Url编码则调用Utf8URLdecode进行解码
System.out.println(charTools.Utf8URLdecode(url));
}else{
System.out.println(URLDecoder.decode(url));
}
url = "http://www.baidu.com/baidu?word=%D6%D0%B9%FA%B4%F3%B0%D9%BF%C6%D4%DA%CF%DF%C8%AB%CE%C4%BC%EC%CB%F7&tn=myie2dg";
if(charTools.isUtf8Url(url)){
System.out.println(charTools.Utf8URLdecode(url));
}else{
System.out.println(URLDecoder.decode(url));
}
String charT="刘奇庭是不错的人";
String ct=charTools1.chopAtWord(charT, 5);
System.out.println(ct);
}
}