邮件编码Content-Transfer-Encoding的各种形式？

转自：http://bbs.chinaunix.net/thread-1150250-1-1.html

转自：http://blog.csdn.net/songylwq/article/details/7578905

邮件编码Content-Transfer-Encoding的各种形式？  
为什么有这么多，只用一种不行吗？比如有的是：base64，有的是：8bit，有的是：quoted-printable  
什么时候用什么编码呀？ 

由於歷史原因，Internet 上有些郵件系統只支援 7Bit 的字元傳輸， 而漢字的內碼是 8Bit 的，當在電子郵件中發送中文時， 如果經過這些只支援 7Bit 字元的郵件系統， 便會將漢字內碼的第八位元的 1 全部變成 0。 
以 "中文" 兩字為例，HEX 為 A4A4A4E5， 當最高位元被清掉時就會變成 24242465，也就是 "$$$e"。 telnet 也存在這樣子的問題。 
除了中文郵件外，使用電子郵件傳送圖片、程式、 壓縮文件等也會發生這個問題。 所以在電子郵件中一般採用各種郵件編碼方式來解決這個問題， 將 8Bit 按照一定的規則進行編碼， 便可以完好地通過只支持 7Bit 字元的郵件系統。 
常見的郵件編碼有 UU 與 MIME，而 MIME (Multipurpose Internet Mail Extentions) 一般翻譯成「多媒體傳送模式」， 顧名思義，它標榜的就是可以傳送多媒體型式的檔案， 可以在一封mail中附加各種型式檔案一起送出。 
MIME 定義兩種編碼方法：Base64 與QP(Quote-Printable)， 兩者使用時機不同，QP 的規則是對於資料中的7bits無須重複encode， 僅8bits資料轉成7bits。QP編碼適用於非US-ASCII的文字內容， 例如我們的中文檔案，而Base64的編碼規則，是將整個檔案重新編碼，
編成7bits，它是用於傳送binary檔案時使用。 由於編碼的方式不同，會影響編碼之後的檔案大小。 有些較懶惰的軟體便都一律採用Base64編碼了。

一个例子：
Return-Path: 
Delivered-To: 
test2@2008.com
X-WM-Delivered: 
test2@2008.com
Received: from server ([9.9.9.10])
(envelope-sender )
by 9.9.9.10 with ESMTP
for ; Tue, 08 Apr 2008 14:03:35 +0800
Message-ID: 
From: "test" 
To: 
Subject: sssee
Date: Tue, 8 Apr 2008 14:03:34 +0800
MIME-Version: 1.0
Content-Type: multipart/mixed;
boundary="----=_NextPart_000_0825_01C89981.55C7FDA0"
X-Priority: 3
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 6.00.3790.3959
X-MimeOLE: Produced By Microsoft MimeOLE V6.00.3790.4133
X-P3Scan: Version 2.3.2 by /

This is a multi-part message in MIME format.

------=_NextPart_000_0825_01C89981.55C7FDA0
Content-Type: text/plain;
charset="gb2312"
Content-Transfer-Encoding: base64

c3Nlc2VzZQ==

------=_NextPart_000_0825_01C89981.55C7FDA0
Content-Type: text/plain;
name="ccc.txt"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
filename="ccc.txt"

eeeeeeeeeeeeer
------=_NextPart_000_0825_01C89981.55C7FDA0--

.

(“.”是邮件结束的标志)

Base64加密解密类：

package com.fitweber.util;

public class Base64Protector {

static private final int BASELENGTH = 255;
static private final int LOOKUPLENGTH = 64;
static private final int TWENTYFOURBITGROUP = 24;
static private final int EIGHTBIT = 8;
static private final int SIXTEENBIT = 16;
static private final int SIXBIT = 6;
static private final int FOURBYTE = 4;
static private final int SIGN = -128;
static private final char PAD = '=';
static private final boolean fDebug = false;
static final private byte[] base64Alphabet = new byte[BASELENGTH];
static final private char[] lookUpBase64Alphabet = new char[LOOKUPLENGTH];

static {

for (int i = 0; i < BASELENGTH; i++) {
base64Alphabet[i] = -1;
}
for (int i = 'Z'; i >= 'A'; i--) {
base64Alphabet[i] = (byte) (i - 'A');
}
for (int i = 'z'; i >= 'a'; i--) {
base64Alphabet[i] = (byte) (i - 'a' + 26);
}

for (int i = '9'; i >= '0'; i--) {
base64Alphabet[i] = (byte) (i - '0' + 52);
}

base64Alphabet['+'] = 62;
base64Alphabet['/'] = 63;

for (int i = 0; i <= 25; i++)
lookUpBase64Alphabet[i] = (char) ('A' + i);

for (int i = 26, j = 0; i <= 51; i++, j++)
lookUpBase64Alphabet[i] = (char) ('a' + j);

for (int i = 52, j = 0; i <= 61; i++, j++)
lookUpBase64Alphabet[i] = (char) ('0' + j);
lookUpBase64Alphabet[62] = (char) '+';
lookUpBase64Alphabet[63] = (char) '/';

}

protected static boolean isWhiteSpace(char octect) {
return (octect == 0x20 || octect == 0xd || octect == 0xa || octect == 0x9);
}

protected static boolean isPad(char octect) {
return (octect == PAD);
}

protected static boolean isData(char octect) {
return (base64Alphabet[octect] != -1);
}

protected static boolean isBase64(char octect) {
return (isWhiteSpace(octect) || isPad(octect) || isData(octect));
}

/**
* Encodes hex octects into Base64
*
* @param binaryData
* Array containing binaryData
* @return Encoded Base64 array
*/
public static String encode(byte[] binaryData) {

if (binaryData == null)
return null;

int lengthDataBits = binaryData.length * EIGHTBIT;
if (lengthDataBits == 0) {
return "";
}

int fewerThan24bits = lengthDataBits % TWENTYFOURBITGROUP;
int numberTriplets = lengthDataBits / TWENTYFOURBITGROUP;
int numberQuartet = fewerThan24bits != 0 ? numberTriplets + 1
: numberTriplets;
int numberLines = (numberQuartet - 1) / 19 + 1;
char encodedData[] = null;

encodedData = new char[numberQuartet * 4 + numberLines];

byte k = 0, l = 0, b1 = 0, b2 = 0, b3 = 0;

int encodedIndex = 0;
int dataIndex = 0;
int i = 0;
if (fDebug) {
System.out.println("number of triplets = " + numberTriplets);
}

for (int line = 0; line < numberLines - 1; line++) {
for (int quartet = 0; quartet < 19; quartet++) {
b1 = binaryData[dataIndex++];
b2 = binaryData[dataIndex++];
b3 = binaryData[dataIndex++];

if (fDebug) {
System.out.println("b1= " + b1 + ", b2= " + b2 + ", b3= "
+ b3);
}

l = (byte) (b2 & 0x0f);
k = (byte) (b1 & 0x03);

byte val1 = ((b1 & SIGN) == 0) ? (byte) (b1 >> 2)
: (byte) ((b1) >> 2 ^ 0xc0);

byte val2 = ((b2 & SIGN) == 0) ? (byte) (b2 >> 4)
: (byte) ((b2) >> 4 ^ 0xf0);
byte val3 = ((b3 & SIGN) == 0) ? (byte) (b3 >> 6)
: (byte) ((b3) >> 6 ^ 0xfc);

if (fDebug) {
System.out.println("val2 = " + val2);
System.out.println("k4 = " + (k << 4));
System.out.println("vak = " + (val2 | (k << 4)));
}

encodedData[encodedIndex++] = lookUpBase64Alphabet[val1];
encodedData[encodedIndex++] = lookUpBase64Alphabet[val2
| (k << 4)];
encodedData[encodedIndex++] = lookUpBase64Alphabet[(l << 2)
| val3];
encodedData[encodedIndex++] = lookUpBase64Alphabet[b3 & 0x3f];

i++;
}
encodedData[encodedIndex++] = 0xa;
}

for (; i < numberTriplets; i++) {
b1 = binaryData[dataIndex++];
b2 = binaryData[dataIndex++];
b3 = binaryData[dataIndex++];

if (fDebug) {
System.out.println("b1= " + b1 + ", b2= " + b2 + ", b3= " + b3);
}

l = (byte) (b2 & 0x0f);
k = (byte) (b1 & 0x03);

byte val1 = ((b1 & SIGN) == 0) ? (byte) (b1 >> 2)
: (byte) ((b1) >> 2 ^ 0xc0);

byte val2 = ((b2 & SIGN) == 0) ? (byte) (b2 >> 4)
: (byte) ((b2) >> 4 ^ 0xf0);
byte val3 = ((b3 & SIGN) == 0) ? (byte) (b3 >> 6)
: (byte) ((b3) >> 6 ^ 0xfc);

if (fDebug) {
System.out.println("val2 = " + val2);
System.out.println("k4 = " + (k << 4));
System.out.println("vak = " + (val2 | (k << 4)));
}

encodedData[encodedIndex++] = lookUpBase64Alphabet[val1];
encodedData[encodedIndex++] = lookUpBase64Alphabet[val2 | (k << 4)];
encodedData[encodedIndex++] = lookUpBase64Alphabet[(l << 2) | val3];
encodedData[encodedIndex++] = lookUpBase64Alphabet[b3 & 0x3f];
}

// form integral number of 6-bit groups
if (fewerThan24bits == EIGHTBIT) {
b1 = binaryData[dataIndex];
k = (byte) (b1 & 0x03);
if (fDebug) {
System.out.println("b1=" + b1);
System.out.println("b1<<2 = " + (b1 >> 2));
}
byte val1 = ((b1 & SIGN) == 0) ? (byte) (b1 >> 2)
: (byte) ((b1) >> 2 ^ 0xc0);
encodedData[encodedIndex++] = lookUpBase64Alphabet[val1];
encodedData[encodedIndex++] = lookUpBase64Alphabet[k << 4];
encodedData[encodedIndex++] = PAD;
encodedData[encodedIndex++] = PAD;
} else if (fewerThan24bits == SIXTEENBIT) {
b1 = binaryData[dataIndex];
b2 = binaryData[dataIndex + 1];
l = (byte) (b2 & 0x0f);
k = (byte) (b1 & 0x03);

byte val1 = ((b1 & SIGN) == 0) ? (byte) (b1 >> 2)
: (byte) ((b1) >> 2 ^ 0xc0);
byte val2 = ((b2 & SIGN) == 0) ? (byte) (b2 >> 4)
: (byte) ((b2) >> 4 ^ 0xf0);

encodedData[encodedIndex++] = lookUpBase64Alphabet[val1];
encodedData[encodedIndex++] = lookUpBase64Alphabet[val2 | (k << 4)];
encodedData[encodedIndex++] = lookUpBase64Alphabet[l << 2];
encodedData[encodedIndex++] = PAD;
}

encodedData[encodedIndex] = 0xa;

return new String(encodedData);
}

/**
* Decodes Base64 data into octects
*
* @param binaryData
* Byte array containing Base64 data
* @return Array containind decoded data.
*/
public static byte[] decode(String encoded) {

if (encoded == null)
return null;

char[] base64Data = encoded.toCharArray();
// remove white spaces
int len = removeWhiteSpace(base64Data);

if (len % FOURBYTE != 0) {
return null;// should be divisible by four
}

int numberQuadruple = (len / FOURBYTE);

if (numberQuadruple == 0)
return new byte[0];

byte decodedData[] = null;
byte b1 = 0, b2 = 0, b3 = 0, b4 = 0, marker0 = 0, marker1 = 0;
char d1 = 0, d2 = 0, d3 = 0, d4 = 0;

int i = 0;
int encodedIndex = 0;
int dataIndex = 0;
decodedData = new byte[(numberQuadruple) * 3];

for (; i < numberQuadruple - 1; i++) {

if (!isData((d1 = base64Data[dataIndex++]))
|| !isData((d2 = base64Data[dataIndex++]))
|| !isData((d3 = base64Data[dataIndex++]))
|| !isData((d4 = base64Data[dataIndex++])))
return null;// if found "no data" just return null

b1 = base64Alphabet[d1];
b2 = base64Alphabet[d2];
b3 = base64Alphabet[d3];
b4 = base64Alphabet[d4];

decodedData[encodedIndex++] = (byte) (b1 << 2 | b2 >> 4);
decodedData[encodedIndex++] = (byte) (((b2 & 0xf) << 4) | ((b3 >> 2) & 0xf));
decodedData[encodedIndex++] = (byte) (b3 << 6 | b4);
}

if (!isData((d1 = base64Data[dataIndex++]))
|| !isData((d2 = base64Data[dataIndex++]))) {
return null;// if found "no data" just return null
}

b1 = base64Alphabet[d1];
b2 = base64Alphabet[d2];

d3 = base64Data[dataIndex++];
d4 = base64Data[dataIndex++];
if (!isData((d3)) || !isData((d4))) {// Check if they are PAD characters
if (isPad(d3) && isPad(d4)) { // Two PAD e.g. 3c[Pad][Pad]
if ((b2 & 0xf) != 0)// last 4 bits should be zero
return null;
byte[] tmp = new byte[i * 3 + 1];
System.arraycopy(decodedData, 0, tmp, 0, i * 3);
tmp[encodedIndex] = (byte) (b1 << 2 | b2 >> 4);
return tmp;
} else if (!isPad(d3) && isPad(d4)) { // One PAD e.g. 3cQ[Pad]
b3 = base64Alphabet[d3];
if ((b3 & 0x3) != 0)// last 2 bits should be zero
return null;
byte[] tmp = new byte[i * 3 + 2];
System.arraycopy(decodedData, 0, tmp, 0, i * 3);
tmp[encodedIndex++] = (byte) (b1 << 2 | b2 >> 4);
tmp[encodedIndex] = (byte) (((b2 & 0xf) << 4) | ((b3 >> 2) & 0xf));
return tmp;
} else {
return null;// an error like "3c[Pad]r", "3cdX", "3cXd", "3cXX"
// where X is non data
}
} else { // No PAD e.g 3cQl
b3 = base64Alphabet[d3];
b4 = base64Alphabet[d4];
decodedData[encodedIndex++] = (byte) (b1 << 2 | b2 >> 4);
decodedData[encodedIndex++] = (byte) (((b2 & 0xf) << 4) | ((b3 >> 2) & 0xf));
decodedData[encodedIndex++] = (byte) (b3 << 6 | b4);

}

return decodedData;
}

/**
* remove WhiteSpace from MIME containing encoded Base64 data.
*
* @param data
* the byte array of base64 data (with WS)
* @return the new length
*/
protected static int removeWhiteSpace(char[] data) {
if (data == null)
return 0;

// count characters that's not whitespace
int newSize = 0;
int len = data.length;
for (int i = 0; i < len; i++) {
if (!isWhiteSpace(data[i]))
data[newSize++] = data[i];
}
return newSize;
}
public static void main(String[] args) {
System.out.println(encode("中华人民共和国".getBytes()));
}
}