[java]Base64

Base64是网络上最常见的用于传输8Bit字节代码的编码方式之一，大家可以查看RFC2045～RFC2049，上面有MIME的详细规范。Base64编码可用于在HTTP环境下传递较长的标识信息。例如，在Java Persistence系统Hibernate中，就采用了Base64来将一个较长的唯一标识符（一般为128-bit的UUID）编码为一个字符串，用作HTTP表单和HTTP GET URL中的参数。在其他应用程序中，也常常需要把二进制数据编码为适合放在URL（包括隐藏表单域）中的形式。此时，采用Base64编码具有不可读性，即所编码的数据不会被人用肉眼所直接看到。

一、编码规则
Base64编码的思想是是采用64个基本的ASCII码字符对数据进行重新编码。它将需要编码的数据拆分成字节数组。以3个字节为一组。按顺序排列24 位数据，再把这24位数据分成4组，即每组6位。再在每组的的最高位前补两个0凑足一个字节。这样就把一个3字节为一组的数据重新编码成了4个字节。当所要编码的数据的字节数不是3的整倍数，也就是说在分组时最后一组不够3个字节。这时在最后一组填充1到2个0字节。并在最后编码完成后在结尾添加1到2个 “=”。

例：将对ABC进行BASE64编码：
1、首先取ABC对应的ASCII码值。A（65）B（66）C（67）；
2、再取二进制值A（01000001）B（01000010）C（01000011）；
3、然后把这三个字节的二进制码接起来（010000010100001001000011）；
4、 再以6位为单位分成4个数据块,并在最高位填充两个0后形成4个字节的编码后的值，（00010000）（00010100）（00001001）（00000011），其中蓝色部分为真实数据；
5、再把这四个字节数据转化成10进制数得（16）（20）（9）（3）；
6、最后根据BASE64给出的64个基本字符表，查出对应的ASCII码字符（Q）（U）（J）（D），这里的值实际就是数据在字符表中的索引。
注：BASE64字符表：ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/

二、解码规则
解码过程就是把4个字节再还原成3个字节再根据不同的数据形式把字节数组重新整理成数据。

三、java程序

import java.io.ByteArrayOutputStream;
import java.io.IOException;

public class Base64 {

	// Create arrays to hold the base64 characters and a
	// lookup for base64 chars
	private static byte[] base64Alphabet;

	/**
	 * The base length.
	 */
	static final int BASELENGTH = 255;

	/**
	 * Chunk separator per RFC 2045 section 2.1.
	 * 
	 * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 2.1</a>
	 */
	static final byte[] CHUNK_SEPARATOR = "\r\n".getBytes();

	/**
	 * Chunk size per RFC 2045 section 6.8.
	 * 
	 * <p>
	 * The {@value} character limit does not count the trailing CRLF, but counts
	 * all other characters, including any equal signs.
	 * </p>
	 * 
	 * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 6.8</a>
	 */
	static final int CHUNK_SIZE = 76;

	/**
	 * Used to calculate the number of bits in a byte.
	 */
	static final int EIGHTBIT = 8;

	/**
	 * Used to get the number of Quadruples.
	 */
	static final int FOURBYTE = 4;

	private static byte[] lookUpBase64Alphabet;

	/**
	 * Lookup length.
	 */
	static final int LOOKUPLENGTH = 64;

	/**
	 * Byte used to pad output.
	 */
	static final byte PAD = (byte) '=';

	/**
	 * Used to test the sign of a byte.
	 */
	static final int SIGN = -128;

	/**
	 * Used when encoding something which has fewer than 24 bits.
	 */
	static final int SIXTEENBIT = 16;

	/**
	 * Used to determine how many bits data contains.
	 */
	static final int TWENTYFOURBITGROUP = 24;

	// Populating the lookup and character arrays
	static {
		lookUpBase64Alphabet = new byte[LOOKUPLENGTH];
		base64Alphabet = new byte[BASELENGTH];
		for (int i = 0; i < BASELENGTH; i++) {
			base64Alphabet[i] = (byte) -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] = (byte) ('A' + i);
		}

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

		for (int i = 52, j = 0; i <= 61; i++, j++) {
			lookUpBase64Alphabet[i] = (byte) ('0' + j);
		}

		lookUpBase64Alphabet[62] = (byte) '+';
		lookUpBase64Alphabet[63] = (byte) '/';
	}

	/**
	 * Decodes Base64 data into octects
	 * 
	 * @param base64Data
	 *            Byte array containing Base64 data
	 * @return Array containing decoded data.
	 */
	public static byte[] decodeBase64(byte[] base64Data) {
		// RFC 2045 requires that we discard ALL non-Base64 characters
		base64Data = discardNonBase64(base64Data);

		// handle the edge case, so we don't have to worry about it
		// later
		if (base64Data.length == 0) {
			return new byte[0];
		}

		int numberQuadruple = base64Data.length / FOURBYTE;
		byte decodedData[] = null;
		byte b1 = 0, b2 = 0, b3 = 0, b4 = 0, marker0 = 0, marker1 = 0;

		// Throw away anything not in base64Data

		int encodedIndex = 0;
		int dataIndex = 0;
		{
			// this sizes the output array properly - rlw
			int lastData = base64Data.length;
			// ignore the '=' padding
			while (base64Data[lastData - 1] == PAD) {
				if (--lastData == 0) {
					return new byte[0];
				}
			}
			decodedData = new byte[lastData - numberQuadruple];
		}

		for (int i = 0; i < numberQuadruple; i++) {
			dataIndex = i * 4;
			marker0 = base64Data[dataIndex + 2];
			marker1 = base64Data[dataIndex + 3];

			b1 = base64Alphabet[base64Data[dataIndex]];
			b2 = base64Alphabet[base64Data[dataIndex + 1]];

			if (marker0 != PAD && marker1 != PAD) {
				// No PAD e.g 3cQl
				b3 = base64Alphabet[marker0];
				b4 = base64Alphabet[marker1];

				decodedData[encodedIndex] = (byte) (b1 << 2 | b2 >> 4);
				decodedData[encodedIndex + 1] = (byte) (((b2 & 0xf) << 4) | ((b3 >> 2) & 0xf));
				decodedData[encodedIndex + 2] = (byte) (b3 << 6 | b4);
			} else if (marker0 == PAD) {
				// Two PAD e.g. 3c[Pad][Pad]
				decodedData[encodedIndex] = (byte) (b1 << 2 | b2 >> 4);
			} else if (marker1 == PAD) {
				// One PAD e.g. 3cQ[Pad]
				b3 = base64Alphabet[marker0];

				decodedData[encodedIndex] = (byte) (b1 << 2 | b2 >> 4);
				decodedData[encodedIndex + 1] = (byte) (((b2 & 0xf) << 4) | ((b3 >> 2) & 0xf));
			}
			encodedIndex += 3;
		}
		return decodedData;
	}

	/**
	 * Discards any characters outside of the base64 alphabet, per the
	 * requirements on page 25 of RFC 2045 - "Any characters outside of the
	 * base64 alphabet are to be ignored in base64 encoded data."
	 * 
	 * @param data
	 *            The base-64 encoded data to groom
	 * @return The data, less non-base64 characters (see RFC 2045).
	 */
	static byte[] discardNonBase64(byte[] data) {
		byte groomedData[] = new byte[data.length];
		int bytesCopied = 0;

		for (int i = 0; i < data.length; i++) {
			if (isBase64(data[i])) {
				groomedData[bytesCopied++] = data[i];
			}
		}

		byte packedData[] = new byte[bytesCopied];

		System.arraycopy(groomedData, 0, packedData, 0, bytesCopied);

		return packedData;
	}

	/**
	 * Discards any whitespace from a base-64 encoded block.
	 * 
	 * @param data
	 *            The base-64 encoded data to discard the whitespace from.
	 * @return The data, less whitespace (see RFC 2045).
	 */
	static byte[] discardWhitespace(byte[] data) {
		byte groomedData[] = new byte[data.length];
		int bytesCopied = 0;

		for (int i = 0; i < data.length; i++) {
			switch (data[i]) {
			case (byte) ' ':
			case (byte) '\n':
			case (byte) '\r':
			case (byte) '\t':
				break;
			default:
				groomedData[bytesCopied++] = data[i];
			}
		}

		byte packedData[] = new byte[bytesCopied];

		System.arraycopy(groomedData, 0, packedData, 0, bytesCopied);

		return packedData;
	}

	/**
	 * Encodes binary data using the base64 algorithm but does not chunk the
	 * output.
	 * 
	 * @param binaryData
	 *            binary data to encode
	 * @return Base64 characters
	 */
	public static byte[] encodeBase64(byte[] binaryData) {
		return encodeBase64(binaryData, false);
	}

	/**
	 * Encodes binary data using the base64 algorithm, optionally chunking the
	 * output into 76 character blocks.
	 * 
	 * @param binaryData
	 *            Array containing binary data to encode.
	 * @param isChunked
	 *            if isChunked is true this encoder will chunk the base64 output
	 *            into 76 character blocks
	 * @return Base64-encoded data.
	 */
	public static byte[] encodeBase64(byte[] binaryData, boolean isChunked) {
		int lengthDataBits = binaryData.length * EIGHTBIT;
		int fewerThan24bits = lengthDataBits % TWENTYFOURBITGROUP;
		int numberTriplets = lengthDataBits / TWENTYFOURBITGROUP;
		byte encodedData[] = null;
		int encodedDataLength = 0;
		int nbrChunks = 0;

		if (fewerThan24bits != 0) {
			// data not divisible by 24 bit
			encodedDataLength = (numberTriplets + 1) * 4;
		} else {
			// 16 or 8 bit
			encodedDataLength = numberTriplets * 4;
		}

		// If the output is to be "chunked" into 76 character
		// sections,
		// for compliance with RFC 2045 MIME, then it is important to
		// allow for extra length to account for the separator(s)
		if (isChunked) {

			nbrChunks = (CHUNK_SEPARATOR.length == 0 ? 0 : (int) Math
					.ceil((float) encodedDataLength / CHUNK_SIZE));
			encodedDataLength += nbrChunks * CHUNK_SEPARATOR.length;
		}

		encodedData = new byte[encodedDataLength];

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

		int encodedIndex = 0;
		int dataIndex = 0;
		int i = 0;
		int nextSeparatorIndex = CHUNK_SIZE;
		int chunksSoFar = 0;

		// log.debug("number of triplets = " + numberTriplets);
		for (i = 0; i < numberTriplets; i++) {
			dataIndex = i * 3;
			b1 = binaryData[dataIndex];
			b2 = binaryData[dataIndex + 1];
			b3 = binaryData[dataIndex + 2];

			// log.debug("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);

			encodedData[encodedIndex] = lookUpBase64Alphabet[val1];
			// log.debug( "val2 = " + val2 );
			// log.debug( "k4 = " + (k<<4) );
			// log.debug( "vak = " + (val2 | (k<<4)) );
			encodedData[encodedIndex + 1] = lookUpBase64Alphabet[val2
					| (k << 4)];
			encodedData[encodedIndex + 2] = lookUpBase64Alphabet[(l << 2)
					| val3];
			encodedData[encodedIndex + 3] = lookUpBase64Alphabet[b3 & 0x3f];

			encodedIndex += 4;

			// If we are chunking, let's put a chunk separator down.
			if (isChunked) {
				// this assumes that CHUNK_SIZE % 4 == 0
				if (encodedIndex == nextSeparatorIndex) {
					System.arraycopy(CHUNK_SEPARATOR, 0, encodedData,
							encodedIndex, CHUNK_SEPARATOR.length);
					chunksSoFar++;
					nextSeparatorIndex = (CHUNK_SIZE * (chunksSoFar + 1))
							+ (chunksSoFar * CHUNK_SEPARATOR.length);
					encodedIndex += CHUNK_SEPARATOR.length;
				}
			}
		}

		// form integral number of 6-bit groups
		dataIndex = i * 3;

		if (fewerThan24bits == EIGHTBIT) {
			b1 = binaryData[dataIndex];
			k = (byte) (b1 & 0x03);
			// log.debug("b1=" + b1);
			// log.debug("b1<<2 = " + (b1>>2) );
			byte val1 = ((b1 & SIGN) == 0) ? (byte) (b1 >> 2)
					: (byte) ((b1) >> 2 ^ 0xc0);
			encodedData[encodedIndex] = lookUpBase64Alphabet[val1];
			encodedData[encodedIndex + 1] = lookUpBase64Alphabet[k << 4];
			encodedData[encodedIndex + 2] = PAD;
			encodedData[encodedIndex + 3] = 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 + 1] = lookUpBase64Alphabet[val2
					| (k << 4)];
			encodedData[encodedIndex + 2] = lookUpBase64Alphabet[l << 2];
			encodedData[encodedIndex + 3] = PAD;
		}

		if (isChunked) {
			// we also add a separator to the end of the final chunk.
			if (chunksSoFar < nbrChunks) {
				System.arraycopy(CHUNK_SEPARATOR, 0, encodedData,
						encodedDataLength - CHUNK_SEPARATOR.length,
						CHUNK_SEPARATOR.length);
			}
		}

		return encodedData;
	}

	/**
	 * Encodes binary data using the base64 algorithm and chunks the encoded
	 * output into 76 character blocks
	 * 
	 * @param binaryData
	 *            binary data to encode
	 * @return Base64 characters chunked in 76 character blocks
	 */
	public static byte[] encodeBase64Chunked(byte[] binaryData) {
		return encodeBase64(binaryData, true);
	}

	/**
	 * Tests a given byte array to see if it contains only valid characters
	 * within the Base64 alphabet.
	 * 
	 * @param arrayOctect
	 *            byte array to test
	 * @return true if all bytes are valid characters in the Base64 alphabet or
	 *         if the byte array is empty; false, otherwise
	 */
	public static boolean isArrayByteBase64(byte[] arrayOctect) {

		arrayOctect = discardWhitespace(arrayOctect);

		int length = arrayOctect.length;
		if (length == 0) {
			// shouldn't a 0 length array be valid base64 data?
			// return false;
			return true;
		}
		for (int i = 0; i < length; i++) {
			if (!isBase64(arrayOctect[i])) {
				return false;
			}
		}
		return true;
	}

	private static boolean isBase64(byte octect) {

		if (octect == PAD) {
			return true;
		} else if (base64Alphabet[0xff & octect] == -1) {
			return false;
		} else {
			return true;
		}
	}

	/**
	 * Decodes a byte[] containing containing characters in the Base64 alphabet.
	 * 
	 * @param pArray
	 *            A byte array containing Base64 character data
	 * @return a byte array containing binary data
	 */
	public byte[] decode(byte[] pArray) {
		return decodeBase64(pArray);
	}

	/**
	 * Encodes a byte[] containing binary data, into a byte[] containing
	 * characters in the Base64 alphabet.
	 * 
	 * @param pArray
	 *            a byte array containing binary data
	 * @return A byte array containing only Base64 character data
	 */
	public byte[] encode(byte[] pArray) {
		return encodeBase64(pArray, false);
	}

	public static byte[] encodeXml(byte src[]) {
		ByteArrayOutputStream baos = new ByteArrayOutputStream();
		ByteArrayOutputStream text_os = new ByteArrayOutputStream();
		byte tag_left = (byte) '<';
		byte tag_right = (byte) '>';
		boolean begin = false;
		boolean in_tag = false;
		for (int i = 0; i < src.length; i++) {
			byte b = src[i];
			if (begin == false && b == tag_left)
				begin = true;
			if (b == tag_left)
				in_tag = true;
			else if (b == tag_right)
				in_tag = false;
			if (!begin)
				continue;
			if (in_tag || b == tag_right) {
				if (b == tag_left) {
					byte[] text = text_os.toByteArray();
					try {
						baos.write(encodeBase64(text));
					} catch (IOException e) {
						e.printStackTrace();
					}
					text_os.reset();
				}
				baos.write(b);
			} else {
				text_os.write(b);
			}
		}
		return baos.toByteArray();
	}
}