/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.jboss.as.process.stdin;
/**
* Variant of the <a href="http://commons.apache.org/proper/commons-codec">Commons Codec</a> project's class
* of the same name. This varies from the original in the implementation of the
* {@link #decode(byte[], int, int, org.jboss.as.process.stdin.BaseNCodec.Context)} method, which does not treat
* the presence of the {@code =} character in the stream as indicating an end of stream. This makes
* {@link org.jboss.as.process.stdin.Base64InputStream} useful for continuous reading of multiple sets
* of data, with the {@code =} character in the stream indicating the end of a set, while the commons-codec
* variant is limited to a single read. It also varies from the original by removing constructor options not needed
* by the intended use cases for this WildFly package.
* <p>
* Provides Base64 encoding and decoding as defined by <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a>.
* </p>
* <p>
* This class implements section <cite>6.8. Base64 Content-Transfer-Encoding</cite> from RFC 2045 <cite>Multipurpose
* Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</cite> by Freed and Borenstein.
* </p>
* <p>
* <p>
* Since this class operates directly on byte streams, and not character streams, it is hard-coded to only
* encode/decode character encodings which are compatible with the lower 127 ASCII chart (ISO-8859-1, Windows-1252,
* UTF-8, etc).
* </p>
* <p>
* This class is thread-safe.
* </p>
*
* @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a>
*/
class Base64 extends BaseNCodec {
/**
* BASE32 characters are 6 bits in length.
* They are formed by taking a block of 3 octets to form a 24-bit string,
* which is converted into 4 BASE64 characters.
*/
private static final int BITS_PER_ENCODED_BYTE = 6;
private static final int BYTES_PER_UNENCODED_BLOCK = 3;
private static final int BYTES_PER_ENCODED_BLOCK = 4;
/**
* Chunk separator per RFC 2045 section 2.1.
*
* <p>
* N.B. The next major release may break compatibility and make this field private.
* </p>
*
* @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 2.1</a>
*/
static final byte[] CHUNK_SEPARATOR = {'\r', '\n'};
/**
* This array is a lookup table that translates 6-bit positive integer index values into their "Base64 Alphabet"
* equivalents as specified in Table 1 of RFC 2045.
*
* Thanks to "commons" project in ws.apache.org for this code.
* http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/
*/
private static final byte[] STANDARD_ENCODE_TABLE = {
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '+', '/'
};
/**
* This is a copy of the STANDARD_ENCODE_TABLE above, but with + and /
* changed to - and _ to make the encoded Base64 results more URL-SAFE.
* This table is only used when the Base64's mode is set to URL-SAFE.
*/
private static final byte[] URL_SAFE_ENCODE_TABLE = {
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '-', '_'
};
/**
* This array is a lookup table that translates Unicode characters drawn from the "Base64 Alphabet" (as specified
* in Table 1 of RFC 2045) into their 6-bit positive integer equivalents. Characters that are not in the Base64
* alphabet but fall within the bounds of the array are translated to -1.
*
* Note: '+' and '-' both decode to 62. '/' and '_' both decode to 63. This means decoder seamlessly handles both
* URL_SAFE and STANDARD base64. (The encoder, on the other hand, needs to know ahead of time what to emit).
*
* Thanks to "commons" project in ws.apache.org for this code.
* http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/
*/
private static final byte[] DECODE_TABLE = {
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, 62, -1, 63, 52, 53, 54,
55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, -1, 0, 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, -1, -1, -1, -1, 63, -1, 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
};
/**
* Base64 uses 6-bit fields.
*/
/** Mask used to extract 6 bits, used when encoding */
private static final int MASK_6BITS = 0x3f;
// The static final fields above are used for the original static byte[] methods on Base64.
// The private member fields below are used with the new streaming approach, which requires
// some state be preserved between calls of encode() and decode().
/**
* Encode table to use: either STANDARD or URL_SAFE. Note: the DECODE_TABLE above remains static because it is able
* to decode both STANDARD and URL_SAFE streams, but the encodeTable must be a member variable so we can switch
* between the two modes.
*/
private final byte[] encodeTable;
// Only one decode table currently; keep for consistency with Base32 code
private final byte[] decodeTable = DECODE_TABLE;
/**
* Line separator for encoding. Not used when decoding. Only used if lineLength > 0.
*/
private final byte[] lineSeparator;
/**
* Convenience variable to help us determine when our buffer is going to run out of room and needs resizing.
* <code>decodeSize = 3 + lineSeparator.length;</code>
*/
private final int decodeSize;
/**
* Convenience variable to help us determine when our buffer is going to run out of room and needs resizing.
* <code>encodeSize = 4 + lineSeparator.length;</code>
*/
private final int encodeSize;
/**
* Creates a Base64 codec used for decoding (all modes) and encoding in URL-unsafe mode.
* <p>
* When encoding the line length and line separator are given in the constructor, and the encoding table is
* STANDARD_ENCODE_TABLE.
* </p>
* <p>
* Line lengths that aren't multiples of 4 will still essentially end up being multiples of 4 in the encoded data.
* </p>
* <p>
* When decoding all variants are supported.
* </p>
*
* @throws IllegalArgumentException
* Thrown when the provided lineSeparator included some base64 characters.
* @since 1.4
*/
Base64() {
super(BYTES_PER_ENCODED_BLOCK,-1, 0);
this.encodeSize = BYTES_PER_ENCODED_BLOCK;
this.lineSeparator = null;
this.decodeSize = this.encodeSize - 1;
this.encodeTable = STANDARD_ENCODE_TABLE;
}
/**
* Returns our current encode mode. True if we're URL-SAFE, false otherwise.
*
* @return true if we're in URL-SAFE mode, false otherwise.
* @since 1.4
*/
public boolean isUrlSafe() {
return this.encodeTable == URL_SAFE_ENCODE_TABLE;
}
/**
* <p>
* Encodes all of the provided data, starting at inPos, for inAvail bytes. Must be called at least twice: once with
* the data to encode, and once with inAvail set to "-1" to alert encoder that EOF has been reached, to flush last
* remaining bytes (if not multiple of 3).
* </p>
* <p><b>Note: no padding is added when encoding using the URL-safe alphabet.</b></p>
* <p>
* Thanks to "commons" project in ws.apache.org for the bitwise operations, and general approach.
* http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/
* </p>
*
* @param in
* byte[] array of binary data to base64 encode.
* @param inPos
* Position to start reading data from.
* @param inAvail
* Amount of bytes available from input for encoding.
* @param context
* the context to be used
*/
@Override
void encode(final byte[] in, int inPos, final int inAvail, final Context context) {
if (context.eof) {
return;
}
// inAvail < 0 is how we're informed of EOF in the underlying data we're
// encoding.
if (inAvail < 0) {
context.eof = true;
if (0 == context.modulus && lineLength == 0) {
return; // no leftovers to process and not using chunking
}
final byte[] buffer = ensureBufferSize(encodeSize, context);
final int savedPos = context.pos;
switch (context.modulus) { // 0-2
case 0 : // nothing to do here
break;
case 1 : // 8 bits = 6 + 2
// top 6 bits:
buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 2) & MASK_6BITS];
// remaining 2:
buffer[context.pos++] = encodeTable[(context.ibitWorkArea << 4) & MASK_6BITS];
// URL-SAFE skips the padding to further reduce size.
if (encodeTable == STANDARD_ENCODE_TABLE) {
buffer[context.pos++] = PAD;
buffer[context.pos++] = PAD;
}
break;
case 2 : // 16 bits = 6 + 6 + 4
buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 10) & MASK_6BITS];
buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 4) & MASK_6BITS];
buffer[context.pos++] = encodeTable[(context.ibitWorkArea << 2) & MASK_6BITS];
// URL-SAFE skips the padding to further reduce size.
if (encodeTable == STANDARD_ENCODE_TABLE) {
buffer[context.pos++] = PAD;
}
break;
default:
throw new IllegalStateException("Impossible modulus "+context.modulus);
}
context.currentLinePos += context.pos - savedPos; // keep track of current line position
// if currentPos == 0 we are at the start of a line, so don't add CRLF
if (lineLength > 0 && context.currentLinePos > 0) {
System.arraycopy(lineSeparator, 0, buffer, context.pos, lineSeparator.length);
context.pos += lineSeparator.length;
}
} else {
for (int i = 0; i < inAvail; i++) {
final byte[] buffer = ensureBufferSize(encodeSize, context);
context.modulus = (context.modulus+1) % BYTES_PER_UNENCODED_BLOCK;
int b = in[inPos++];
if (b < 0) {
b += 256;
}
context.ibitWorkArea = (context.ibitWorkArea << 8) + b; // BITS_PER_BYTE
if (0 == context.modulus) { // 3 bytes = 24 bits = 4 * 6 bits to extract
buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 18) & MASK_6BITS];
buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 12) & MASK_6BITS];
buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 6) & MASK_6BITS];
buffer[context.pos++] = encodeTable[context.ibitWorkArea & MASK_6BITS];
context.currentLinePos += BYTES_PER_ENCODED_BLOCK;
if (lineLength > 0 && lineLength <= context.currentLinePos) {
System.arraycopy(lineSeparator, 0, buffer, context.pos, lineSeparator.length);
context.pos += lineSeparator.length;
context.currentLinePos = 0;
}
}
}
}
}
/**
* <p>
* Decodes all of the provided data, starting at inPos, for inAvail bytes. Should be called at least twice: once
* with the data to decode, and once with inAvail set to "-1" to alert decoder that EOF has been reached. The "-1"
* call is not necessary when decoding, but it doesn't hurt, either.
* </p>
* <p>
* Ignores all non-base64 characters. This is how chunked (e.g. 76 character) data is handled, since CR and LF are
* silently ignored, but has implications for other bytes, too. This method subscribes to the garbage-in,
* garbage-out philosophy: it will not check the provided data for validity.
* </p>
* <p>
* Thanks to "commons" project in ws.apache.org for the bitwise operations, and general approach.
* http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/
* </p>
*
* @param in
* byte[] array of ascii data to base64 decode.
* @param inPos
* Position to start reading data from.
* @param inAvail
* Amount of bytes available from input for encoding.
* @param context
* the context to be used
*/
@Override
void decode(final byte[] in, int inPos, final int inAvail, final Context context) {
if (context.eof) {
return;
}
if (inAvail < 0) {
context.eof = true;
}
for (int i = 0; i < inAvail; i++) {
final byte[] buffer = ensureBufferSize(decodeSize, context);
final byte b = in[inPos++];
if (b == PAD) {
// A chunk of data is done.
// NOTE: BES 2014/01/04 -- THIS BLOCK IS WHERE ALL THIS STUFF DIFFERS FROM commons-codec
// We don't set context.eof=true -- we output the data we have and continue on
// We have some spare bits remaining
// Output all whole multiples of 8 bits and ignore the rest
switch (context.modulus) {
case 0 : // 2nd PAD case - ignore
break;
case 1 : // 6 bits - ignore entirely
// TODO not currently tested; perhaps it is impossible?
break;
case 2 : // 12 bits = 8 + 4
context.ibitWorkArea = context.ibitWorkArea >> 4; // dump the extra 4 bits
buffer[context.pos++] = (byte) ((context.ibitWorkArea) & MASK_8BITS);
break;
case 3 : // 18 bits = 8 + 8 + 2
context.ibitWorkArea = context.ibitWorkArea >> 2; // dump 2 bits
buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.ibitWorkArea) & MASK_8BITS);
break;
default:
throw new IllegalStateException("Impossible modulus "+context.modulus);
}
// Set the modulus to zero so further PAD (e.g. aB==) are ignored until we get a non-PAD
context.modulus = 0;
} else {
if (b >= 0 && b < DECODE_TABLE.length) {
final int result = DECODE_TABLE[b];
if (result >= 0) {
context.modulus = (context.modulus+1) % BYTES_PER_ENCODED_BLOCK;
context.ibitWorkArea = (context.ibitWorkArea << BITS_PER_ENCODED_BYTE) + result;
if (context.modulus == 0) {
buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 16) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) (context.ibitWorkArea & MASK_8BITS);
}
}
}
}
}
// Two forms of EOF as far as base64 decoder is concerned: actual
// EOF (-1) and first time '=' character is encountered in stream.
// This approach makes the '=' padding characters completely optional.
if (context.eof && context.modulus != 0) {
final byte[] buffer = ensureBufferSize(decodeSize, context);
// We have some spare bits remaining
// Output all whole multiples of 8 bits and ignore the rest
switch (context.modulus) {
// case 0 : // impossible, as excluded above
case 1 : // 6 bits - ignore entirely
// TODO not currently tested; perhaps it is impossible?
break;
case 2 : // 12 bits = 8 + 4
context.ibitWorkArea = context.ibitWorkArea >> 4; // dump the extra 4 bits
buffer[context.pos++] = (byte) ((context.ibitWorkArea) & MASK_8BITS);
break;
case 3 : // 18 bits = 8 + 8 + 2
context.ibitWorkArea = context.ibitWorkArea >> 2; // dump 2 bits
buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.ibitWorkArea) & MASK_8BITS);
break;
default:
throw new IllegalStateException("Impossible modulus "+context.modulus);
}
}
}
/**
* Tests a given byte array to see if it contains only valid characters within the Base64 alphabet. Currently the
* method treats whitespace as valid.
*
* @param arrayOctet
* byte array to test
* @return {@code true} if all bytes are valid characters in the Base64 alphabet or if the byte array is empty;
* {@code false}, otherwise
* @deprecated 1.5 Use {@link #isBase64(byte[])}, will be removed in 2.0.
*/
@Deprecated
public static boolean isArrayByteBase64(final byte[] arrayOctet) {
return isBase64(arrayOctet);
}
/**
* Returns whether or not the <code>octet</code> is in the base 64 alphabet.
*
* @param octet
* The value to test
* @return {@code true} if the value is defined in the the base 64 alphabet, {@code false} otherwise.
* @since 1.4
*/
public static boolean isBase64(final byte octet) {
return octet == PAD_DEFAULT || (octet >= 0 && octet < DECODE_TABLE.length && DECODE_TABLE[octet] != -1);
}
/**
* Tests a given byte array to see if it contains only valid characters within the Base64 alphabet. Currently the
* method treats whitespace as valid.
*
* @param arrayOctet
* byte array to test
* @return {@code true} if all bytes are valid characters in the Base64 alphabet or if the byte array is empty;
* {@code false}, otherwise
* @since 1.5
*/
public static boolean isBase64(final byte[] arrayOctet) {
for (int i = 0; i < arrayOctet.length; i++) {
if (!isBase64(arrayOctet[i]) && !isWhiteSpace(arrayOctet[i])) {
return false;
}
}
return true;
}
/**
* Returns whether or not the <code>octet</code> is in the Base64 alphabet.
*
* @param octet
* The value to test
* @return {@code true} if the value is defined in the the Base64 alphabet {@code false} otherwise.
*/
@Override
protected boolean isInAlphabet(final byte octet) {
return octet >= 0 && octet < decodeTable.length && decodeTable[octet] != -1;
}
}