com.aeontronix.commons.BaseNCodec Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of aeon-commons-core Show documentation
Show all versions of aeon-commons-core Show documentation
Various utility classes. Except for very rare exceptions (annotation-based validation) this will not
require any dependencies beyond the JRE
The newest version!
/*
* Copyright (c) 2014 Kloudtek Ltd
*/
package com.aeontronix.commons;
/**
* Created by yannick on 07/12/13.
*/
import java.util.Arrays;
public abstract class BaseNCodec {
/**
* Holds thread context so classes can be thread-safe.
*
* This class is not itself thread-safe; each thread must allocate its own copy.
*
* @since 1.7
*/
static class Context {
/**
* Place holder for the bytes we're dealing with for our based logic.
* Bitwise operations store and extract the encoding or decoding from this variable.
*/
int ibitWorkArea;
/**
* Place holder for the bytes we're dealing with for our based logic.
* Bitwise operations store and extract the encoding or decoding from this variable.
*/
long lbitWorkArea;
/**
* Buffer for streaming.
*/
byte[] buffer;
/**
* Position where next character should be written in the buffer.
*/
int pos;
/**
* Position where next character should be read from the buffer.
*/
int readPos;
/**
* Boolean flag to indicate the EOF has been reached. Once EOF has been reached, this object becomes useless,
* and must be thrown away.
*/
boolean eof;
/**
* Variable tracks how many characters have been written to the current line. Only used when encoding. We use
* it to make sure each encoded line never goes beyond lineLength (if lineLength > 0).
*/
int currentLinePos;
/**
* Writes to the buffer only occur after every 3/5 reads when encoding, and every 4/8 reads when decoding. This
* variable helps track that.
*/
int modulus;
Context() {
}
/**
* Returns a String useful for debugging (especially within a debugger.)
*
* @return a String useful for debugging.
*/
@SuppressWarnings("boxing") // OK to ignore boxing here
@Override
public String toString() {
return String.format("%s[buffer=%s, currentLinePos=%s, eof=%s, ibitWorkArea=%s, lbitWorkArea=%s, " +
"modulus=%s, pos=%s, readPos=%s]", this.getClass().getSimpleName(), Arrays.toString(buffer),
currentLinePos, eof, ibitWorkArea, lbitWorkArea, modulus, pos, readPos
);
}
}
/**
* EOF
*
* @since 1.7
*/
static final int EOF = -1;
/**
*
* MIME chunk size per RFC 2045 section 6.8.
*
*
* The {@value} character limit does not count the trailing CRLF, but counts all other characters, including any
* equal signs.
*
*
* @see RFC 2045 section 6.8
*/
public static final int MIME_CHUNK_SIZE = 76;
/**
*
* PEM chunk size per RFC 1421 section 4.3.2.4.
*
*
* The {@value} character limit does not count the trailing CRLF, but counts all other characters, including any
* equal signs.
*
*
* @see RFC 1421 section 4.3.2.4
*/
public static final int PEM_CHUNK_SIZE = 64;
private static final int DEFAULT_BUFFER_RESIZE_FACTOR = 2;
/**
* Defines the default buffer size - currently {@value}
* - must be large enough for at least one encoded block+separator
*/
private static final int DEFAULT_BUFFER_SIZE = 8192;
/**
* Mask used to extract 8 bits, used in decoding bytes
*/
protected static final int MASK_8BITS = 0xff;
/**
* Byte used to pad output.
*/
protected static final byte PAD_DEFAULT = '='; // Allow static access to default
protected final byte PAD = PAD_DEFAULT; // instance variable just in case it needs to vary later
/**
* Number of bytes in each full block of unencoded data, e.g. 4 for Base64 and 5 for Base32
*/
private final int unencodedBlockSize;
/**
* Number of bytes in each full block of encoded data, e.g. 3 for Base64 and 8 for Base32
*/
private final int encodedBlockSize;
/**
* Chunksize for encoding. Not used when decoding.
* A value of zero or less implies no chunking of the encoded data.
* Rounded down to nearest multiple of encodedBlockSize.
*/
protected final int lineLength;
/**
* Size of chunk separator. Not used unless {@link #lineLength} > 0.
*/
private final int chunkSeparatorLength;
/**
* Note lineLength is rounded down to the nearest multiple of {@link #encodedBlockSize}
* If chunkSeparatorLength is zero, then chunking is disabled.
*
* @param unencodedBlockSize the size of an unencoded block (e.g. Base64 = 3)
* @param encodedBlockSize the size of an encoded block (e.g. Base64 = 4)
* @param lineLength if > 0, use chunking with a length lineLength
* @param chunkSeparatorLength the chunk separator length, if relevant
*/
protected BaseNCodec(final int unencodedBlockSize, final int encodedBlockSize,
final int lineLength, final int chunkSeparatorLength) {
this.unencodedBlockSize = unencodedBlockSize;
this.encodedBlockSize = encodedBlockSize;
final boolean useChunking = lineLength > 0 && chunkSeparatorLength > 0;
this.lineLength = useChunking ? (lineLength / encodedBlockSize) * encodedBlockSize : 0;
this.chunkSeparatorLength = chunkSeparatorLength;
}
/**
* Returns true if this object has buffered data for reading.
*
* @param context the context to be used
* @return true if there is data still available for reading.
*/
boolean hasData(final Context context) { // package protected for access from I/O streams
return context.buffer != null;
}
/**
* Returns the amount of buffered data available for reading.
*
* @param context the context to be used
* @return The amount of buffered data available for reading.
*/
int available(final Context context) { // package protected for access from I/O streams
return context.buffer != null ? context.pos - context.readPos : 0;
}
/**
* Get the default buffer size. Can be overridden.
*
* @return {@link #DEFAULT_BUFFER_SIZE}
*/
protected int getDefaultBufferSize() {
return DEFAULT_BUFFER_SIZE;
}
/**
* Increases our buffer by the {@link #DEFAULT_BUFFER_RESIZE_FACTOR}.
*
* @param context the context to be used
*/
private byte[] resizeBuffer(final Context context) {
if (context.buffer == null) {
context.buffer = new byte[getDefaultBufferSize()];
context.pos = 0;
context.readPos = 0;
} else {
final byte[] b = new byte[context.buffer.length * DEFAULT_BUFFER_RESIZE_FACTOR];
System.arraycopy(context.buffer, 0, b, 0, context.buffer.length);
context.buffer = b;
}
return context.buffer;
}
/**
* Ensure that the buffer has room for size bytes
*
* @param size minimum spare space required
* @param context the context to be used
* @return buffer data
*/
protected byte[] ensureBufferSize(final int size, final Context context) {
if ((context.buffer == null) || (context.buffer.length < context.pos + size)) {
return resizeBuffer(context);
}
return context.buffer;
}
/**
* Extracts buffered data into the provided byte[] array, starting at position bPos, up to a maximum of bAvail
* bytes. Returns how many bytes were actually extracted.
*
* Package protected for access from I/O streams.
*
* @param b byte[] array to extract the buffered data into.
* @param bPos position in byte[] array to start extraction at.
* @param bAvail amount of bytes we're allowed to extract. We may extract fewer (if fewer are available).
* @param context the context to be used
* @return The number of bytes successfully extracted into the provided byte[] array.
*/
int readResults(final byte[] b, final int bPos, final int bAvail, final Context context) {
if (context.buffer != null) {
final int len = Math.min(available(context), bAvail);
System.arraycopy(context.buffer, context.readPos, b, bPos, len);
context.readPos += len;
if (context.readPos >= context.pos) {
context.buffer = null; // so hasData() will return false, and this method can return -1
}
return len;
}
return context.eof ? EOF : 0;
}
/**
* Checks if a byte value is whitespace or not.
* Whitespace is taken to mean: space, tab, CR, LF
*
* @param byteToCheck the byte to check
* @return true if byte is whitespace, false otherwise
*/
protected static boolean isWhiteSpace(final byte byteToCheck) {
switch (byteToCheck) {
case ' ':
case '\n':
case '\r':
case '\t':
return true;
default:
return false;
}
}
/**
* Encodes an Object using the Base-N algorithm. This method is provided in order to satisfy the requirements of
* the Encoder interface, and will throw an EncoderException if the supplied object is not of type byte[].
*
* @param obj Object to encode
* @return An object (of type byte[]) containing the Base-N encoded data which corresponds to the byte[] supplied.
* @throws IllegalArgumentException if the parameter supplied is not of type byte[]
*/
public Object encode(final Object obj) throws IllegalArgumentException {
if (!(obj instanceof byte[])) {
throw new IllegalArgumentException("Parameter supplied to Base-N encode is not a byte[]");
}
return encode((byte[]) obj);
}
/**
* Encodes a byte[] containing binary data, into a String containing characters in the Base-N alphabet.
* Uses UTF8 encoding.
*
* @param pArray a byte array containing binary data
* @return A String containing only Base-N character data
*/
public String encodeToString(final byte[] pArray) {
return StringUtils.utf8(encode(pArray));
}
/**
* Encodes a byte[] containing binary data, into a String containing characters in the appropriate alphabet.
* Uses UTF8 encoding.
*
* @param pArray a byte array containing binary data
* @return String containing only character data in the appropriate alphabet.
*/
public String encodeAsString(final byte[] pArray) {
return StringUtils.utf8(encode(pArray));
}
/**
* Decodes an Object using the Base-N algorithm. This method is provided in order to satisfy the requirements of
* the Decoder interface, and will throw a DecoderException if the supplied object is not of type byte[] or String.
*
* @param obj Object to decode
* @return An object (of type byte[]) containing the binary data which corresponds to the byte[] or String
* supplied.
* @throws IllegalArgumentException if the parameter supplied is not of type byte[]
*/
public Object decode(final Object obj) throws IllegalArgumentException {
if (obj instanceof byte[]) {
return decode((byte[]) obj);
} else if (obj instanceof String) {
return decode((String) obj);
} else {
throw new IllegalArgumentException("Parameter supplied to Base-N decode is not a byte[] or a String");
}
}
/**
* Decodes a String containing characters in the Base-N alphabet.
*
* @param pArray A String containing Base-N character data
* @return a byte array containing binary data
*/
public byte[] decode(final String pArray) {
return decode(StringUtils.utf8(pArray));
}
/**
* Decodes a byte[] containing characters in the Base-N alphabet.
*
* @param pArray A byte array containing Base-N character data
* @return a byte array containing binary data
*/
public byte[] decode(final byte[] pArray) {
if (pArray == null || pArray.length == 0) {
return pArray;
}
final Context context = new Context();
decode(pArray, 0, pArray.length, context);
decode(pArray, 0, EOF, context); // Notify decoder of EOF.
final byte[] result = new byte[context.pos];
readResults(result, 0, result.length, context);
return result;
}
/**
* Encodes a byte[] containing binary data, into a byte[] containing characters in the alphabet.
*
* @param pArray a byte array containing binary data
* @return A byte array containing only the basen alphabetic character data
*/
public byte[] encode(final byte[] pArray) {
if (pArray == null || pArray.length == 0) {
return pArray;
}
final Context context = new Context();
encode(pArray, 0, pArray.length, context);
encode(pArray, 0, EOF, context); // Notify encoder of EOF.
final byte[] buf = new byte[context.pos - context.readPos];
readResults(buf, 0, buf.length, context);
return buf;
}
// package protected for access from I/O streams
abstract void encode(byte[] pArray, int i, int length, Context context);
// package protected for access from I/O streams
abstract void decode(byte[] pArray, int i, int length, Context context);
/**
* Returns whether or not the octet is in the current alphabet.
* Does not allow whitespace or pad.
*
* @param value The value to test
* @return {@code true} if the value is defined in the current alphabet, {@code false} otherwise.
*/
protected abstract boolean isInAlphabet(byte value);
/**
* Tests a given byte array to see if it contains only valid characters within the alphabet.
* The method optionally treats whitespace and pad as valid.
*
* @param arrayOctet byte array to test
* @param allowWSPad if {@code true}, then whitespace and PAD are also allowed
* @return {@code true} if all bytes are valid characters in the alphabet or if the byte array is empty;
* {@code false}, otherwise
*/
public boolean isInAlphabet(final byte[] arrayOctet, final boolean allowWSPad) {
for (int i = 0; i < arrayOctet.length; i++) {
if (!isInAlphabet(arrayOctet[i]) &&
(!allowWSPad || (arrayOctet[i] != PAD) && !isWhiteSpace(arrayOctet[i]))) {
return false;
}
}
return true;
}
/**
* Tests a given String to see if it contains only valid characters within the alphabet.
* The method treats whitespace and PAD as valid.
*
* @param basen String to test
* @return {@code true} if all characters in the String are valid characters in the alphabet or if
* the String is empty; {@code false}, otherwise
* @see #isInAlphabet(byte[], boolean)
*/
public boolean isInAlphabet(final String basen) {
return isInAlphabet(StringUtils.utf8(basen), true);
}
/**
* Tests a given byte array to see if it contains any characters within the alphabet or PAD.
* Intended for use in checking line-ending arrays
*
* @param arrayOctet byte array to test
* @return {@code true} if any byte is a valid character in the alphabet or PAD; {@code false} otherwise
*/
protected boolean containsAlphabetOrPad(final byte[] arrayOctet) {
if (arrayOctet == null) {
return false;
}
for (final byte element : arrayOctet) {
if (PAD == element || isInAlphabet(element)) {
return true;
}
}
return false;
}
/**
* Calculates the amount of space needed to encode the supplied array.
*
* @param pArray byte[] array which will later be encoded
* @return amount of space needed to encoded the supplied array.
* Returns a long since a max-len array will require > Integer.MAX_VALUE
*/
public long getEncodedLength(final byte[] pArray) {
// Calculate non-chunked size - rounded up to allow for padding
// cast to long is needed to avoid possibility of overflow
long len = ((pArray.length + unencodedBlockSize - 1) / unencodedBlockSize) * (long) encodedBlockSize;
if (lineLength > 0) { // We're using chunking
// Round up to nearest multiple
len += ((len + lineLength - 1) / lineLength) * chunkSeparatorLength;
}
return len;
}
}