一、概述
1.Base64是什麼：
Base64是網絡上最常見的用於傳輸8Bit字節代碼的編碼方式之一，大家可以查看RFC2045～RFC2049，上面有MIME的詳細規范。Base64編碼可用於在HTTP環境下傳遞較長的標識信息。例如，在Java Persistence系統Hibernate中，就采用了Base64來將一個較長的唯一標識符（一般為128-bit的UUID）編碼為一個字符串，用作HTTP表單和HTTP GET URL中的參數。在其他應用程序中，也常常需要把二進制數據編碼為適合放在URL（包括隱藏表單域）中的形式。此時，采用Base64編碼不僅比較簡短，同時也具有不可讀性，即所編碼的數據不會被人用肉眼所直接看到
2.簡介：
標准的Base64並不適合直接放在URL裡傳輸，因為URL編碼器會把標准Base64中的“/”和“+”字符變為形如“%XX”的形式，而這些“%”號在存入數據庫時還需要再進行轉換，因為ANSI SQL中已將“%”號用作通配符。
為解決此問題，可采用一種用於URL的改進Base64編碼，它不在末尾填充'='號，並將標准Base64中的“+”和“/”分別改成了“*”和“-”，這樣就免去了在URL編解碼和數據庫存儲時所要作的轉換，避免了編碼信息長度在此過程中的增加，並統一了數據庫、表單等處對象標識符的格式。
另有一種用於正則表達式的改進Base64變種，它將“+”和“/”改成了“!”和“-”，因為“+”,“*”以及前面在IRCu中用到的“[”和“]”在正則表達式中都可能具有特殊含義。
此外還有一些變種，它們將“+/”改為“_-”或“._”（用作編程語言中的標識符名稱）或“.-”（用於XML中的Nmtoken）甚至“_:”（用於XML中的Name）。
Base64要求把每三個8Bit的字節轉換為四個6Bit的字節（3*8 = 4*6 = 24），然後把6Bit再添兩位高位0，組成四個8Bit的字節，也就是說，轉換後的字符串理論上將要比原來的長1/3。
3.規則：
關於這個編碼的規則：
①.把3個字符變成4個字符..
②.每76個字符加一個換行符..
③.最後的結束符也要處理..
這樣說會不會太抽象了？不用著急，我們來看一個例子：
轉換前： aaaaaabb ccccdddd eeffffff
轉換後： 00aaaaaa 00bbcccc 00ddddee 00ffffff
應該很清楚了吧？上面的三個字節是原文，下面的四個字節是轉換後的Base64編碼，其前兩位均為0。
轉換後，我們用一個碼表來得到我們想要的字符串（也就是最終的Base64編碼）
二、java實現代碼示例：
public final class Base64 {
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("中華人民共和國".getBytes()));
}
}
