private void Reset()
{
_state = _hasFormatReader ?
Inflater64State.ReadingHeader : // start by reading Header info
Inflater64State.ReadingBFinal; // start by reading BFinal bit
}
// Format of the dynamic block header:
// 5 Bits: HLIT, # of Literal/Length codes - 257 (257 - 286)
// 5 Bits: HDIST, # of Distance codes - 1 (1 - 32)
// 4 Bits: HCLEN, # of Code Length codes - 4 (4 - 19)
//
// (HCLEN + 4) x 3 bits: code lengths for the code length
// alphabet given just above, in the order: 16, 17, 18,
// 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15
//
// These code lengths are interpreted as 3-bit integers
// (0-7); as above, a code length of 0 means the
// corresponding symbol (literal/length or distance code
// length) is not used.
//
// HLIT + 257 code lengths for the literal/length alphabet,
// encoded using the code length Huffman code
//
// HDIST + 1 code lengths for the distance alphabet,
// encoded using the code length Huffman code
//
// The code length repeat codes can cross from HLIT + 257 to the
// HDIST + 1 code lengths. In other words, all code lengths form
// a single sequence of HLIT + HDIST + 258 values.
private bool DecodeDynamicBlockHeader()
{
switch (_state)
{
case Inflater64State.ReadingNumLitCodes:
_literalLengthCodeCount = _input.GetBits(5);
if (_literalLengthCodeCount < 0)
{
return(false);
}
_literalLengthCodeCount += 257;
_state = Inflater64State.ReadingNumDistCodes;
goto case Inflater64State.ReadingNumDistCodes;
case Inflater64State.ReadingNumDistCodes:
_distanceCodeCount = _input.GetBits(5);
if (_distanceCodeCount < 0)
{
return(false);
}
_distanceCodeCount += 1;
_state = Inflater64State.ReadingNumCodeLengthCodes;
goto case Inflater64State.ReadingNumCodeLengthCodes;
case Inflater64State.ReadingNumCodeLengthCodes:
_codeLengthCodeCount = _input.GetBits(4);
if (_codeLengthCodeCount < 0)
{
return(false);
}
_codeLengthCodeCount += 4;
_loopCounter = 0;
_state = Inflater64State.ReadingCodeLengthCodes;
goto case Inflater64State.ReadingCodeLengthCodes;
case Inflater64State.ReadingCodeLengthCodes:
while (_loopCounter < _codeLengthCodeCount)
{
int bits = _input.GetBits(3);
if (bits < 0)
{
return(false);
}
_codeLengthTreeCodeLength[s_codeOrder[_loopCounter]] = (byte)bits;
++_loopCounter;
}
for (int i = _codeLengthCodeCount; i < s_codeOrder.Length; i++)
{
_codeLengthTreeCodeLength[s_codeOrder[i]] = 0;
}
// create huffman tree for code length
_codeLengthTree = new HuffmanTree(_codeLengthTreeCodeLength);
_codeArraySize = _literalLengthCodeCount + _distanceCodeCount;
_loopCounter = 0; // reset loop count
_state = Inflater64State.ReadingTreeCodesBefore;
goto case Inflater64State.ReadingTreeCodesBefore;
case Inflater64State.ReadingTreeCodesBefore:
case Inflater64State.ReadingTreeCodesAfter:
while (_loopCounter < _codeArraySize)
{
if (_state == Inflater64State.ReadingTreeCodesBefore)
{
if ((_lengthCode = _codeLengthTree.GetNextSymbol(_input)) < 0)
{
return(false);
}
}
// The alphabet for code lengths is as follows:
// 0 - 15: Represent code lengths of 0 - 15
// 16: Copy the previous code length 3 - 6 times.
// The next 2 bits indicate repeat length
// (0 = 3, ... , 3 = 6)
// Example: Codes 8, 16 (+2 bits 11),
// 16 (+2 bits 10) will expand to
// 12 code lengths of 8 (1 + 6 + 5)
// 17: Repeat a code length of 0 for 3 - 10 times.
// (3 bits of length)
// 18: Repeat a code length of 0 for 11 - 138 times
// (7 bits of length)
if (_lengthCode <= 15)
{
_codeList[_loopCounter++] = (byte)_lengthCode;
}
else
{
int repeatCount;
if (_lengthCode == 16)
{
if (!_input.EnsureBitsAvailable(2))
{
_state = Inflater64State.ReadingTreeCodesAfter;
return(false);
}
if (_loopCounter == 0)
{
// can't have "prev code" on first code
throw new InvalidDataException();
}
byte previousCode = _codeList[_loopCounter - 1];
repeatCount = _input.GetBits(2) + 3;
if (_loopCounter + repeatCount > _codeArraySize)
{
throw new InvalidDataException();
}
for (int j = 0; j < repeatCount; j++)
{
_codeList[_loopCounter++] = previousCode;
}
}
else if (_lengthCode == 17)
{
if (!_input.EnsureBitsAvailable(3))
{
_state = Inflater64State.ReadingTreeCodesAfter;
return(false);
}
repeatCount = _input.GetBits(3) + 3;
if (_loopCounter + repeatCount > _codeArraySize)
{
throw new InvalidDataException();
}
for (int j = 0; j < repeatCount; j++)
{
_codeList[_loopCounter++] = 0;
}
}
else
{
// code == 18
if (!_input.EnsureBitsAvailable(7))
{
_state = Inflater64State.ReadingTreeCodesAfter;
return(false);
}
repeatCount = _input.GetBits(7) + 11;
if (_loopCounter + repeatCount > _codeArraySize)
{
throw new InvalidDataException();
}
for (int j = 0; j < repeatCount; j++)
{
_codeList[_loopCounter++] = 0;
}
}
}
_state = Inflater64State.ReadingTreeCodesBefore; // we want to read the next code.
}
break;
default:
Debug.Fail("check why we are here!");
throw new InvalidDataException(SR.UnknownState);
}
byte[] literalTreeCodeLength = new byte[HuffmanTree.MaxLiteralTreeElements];
byte[] distanceTreeCodeLength = new byte[HuffmanTree.MaxDistTreeElements];
// Create literal and distance tables
Array.Copy(_codeList, 0, literalTreeCodeLength, 0, _literalLengthCodeCount);
Array.Copy(_codeList, _literalLengthCodeCount, distanceTreeCodeLength, 0, _distanceCodeCount);
// Make sure there is an end-of-block code, otherwise how could we ever end?
if (literalTreeCodeLength[HuffmanTree.EndOfBlockCode] == 0)
{
throw new InvalidDataException();
}
_literalLengthTree = new HuffmanTree(literalTreeCodeLength);
_distanceTree = new HuffmanTree(distanceTreeCodeLength);
_state = Inflater64State.DecodeTop;
return(true);
}
// Format of Non-compressed blocks (BTYPE=00):
//
// Any bits of input up to the next byte boundary are ignored.
// The rest of the block consists of the following information:
//
// 0 1 2 3 4...
// +---+---+---+---+================================+
// | LEN | NLEN |... LEN bytes of literal data...|
// +---+---+---+---+================================+
//
// LEN is the number of data bytes in the block. NLEN is the
// one's complement of LEN.
private bool DecodeUncompressedBlock(out bool end_of_block)
{
end_of_block = false;
while (true)
{
switch (_state)
{
case Inflater64State.UncompressedAligning: // initial state when calling this function
// we must skip to a byte boundary
_input.SkipToByteBoundary();
_state = Inflater64State.UncompressedByte1;
goto case Inflater64State.UncompressedByte1;
case Inflater64State.UncompressedByte1: // decoding block length
case Inflater64State.UncompressedByte2:
case Inflater64State.UncompressedByte3:
case Inflater64State.UncompressedByte4:
int bits = _input.GetBits(8);
if (bits < 0)
{
return(false);
}
_blockLengthBuffer[_state - Inflater64State.UncompressedByte1] = (byte)bits;
if (_state == Inflater64State.UncompressedByte4)
{
_blockLength = _blockLengthBuffer[0] + _blockLengthBuffer[1] * 256;
int blockLengthComplement = _blockLengthBuffer[2] + _blockLengthBuffer[3] * 256;
// make sure complement matches
if ((ushort)_blockLength != (ushort)(~blockLengthComplement))
{
throw new InvalidDataException(SR.InvalidBlockLength);
}
}
_state += 1;
break;
case Inflater64State.DecodingUncompressed: // copying block data
// Directly copy bytes from input to output.
int bytesCopied = _output.CopyFrom(_input, _blockLength);
_blockLength -= bytesCopied;
if (_blockLength == 0)
{
// Done with this block, need to re-init bit buffer for next block
_state = Inflater64State.ReadingBFinal;
end_of_block = true;
return(true);
}
// We can fail to copy all bytes for two reasons:
// Running out of Input
// running out of free space in output window
if (_output.FreeBytes == 0)
{
return(true);
}
return(false);
default:
Debug.Fail("check why we are here!");
throw new InvalidDataException(SR.UnknownState);
}
}
}
private bool DecodeBlock(out bool end_of_block_code_seen)
{
end_of_block_code_seen = false;
int freeBytes = _output.FreeBytes; // it is a little bit faster than frequently accessing the property
while (freeBytes > 65536)
{
// With Deflate64 we can have up to a 64kb length, so we ensure at least that much space is available
// in the OutputWindow to avoid overwriting previous unflushed output data.
int symbol;
switch (_state)
{
case Inflater64State.DecodeTop:
// decode an element from the literal tree
// TODO: optimize this!!!
symbol = _literalLengthTree.GetNextSymbol(_input);
if (symbol < 0)
{
// running out of input
return(false);
}
if (symbol < 256)
{
// literal
_output.Write((byte)symbol);
--freeBytes;
}
else if (symbol == 256)
{
// end of block
end_of_block_code_seen = true;
// Reset state
_state = Inflater64State.ReadingBFinal;
return(true);
}
else
{
// length/distance pair
symbol -= 257; // length code started at 257
if (symbol < 8)
{
symbol += 3; // match length = 3,4,5,6,7,8,9,10
_extraBits = 0;
}
else
{
if (symbol < 0 || symbol >= s_extraLengthBits.Length)
{
throw new InvalidDataException(SR.GenericInvalidData);
}
_extraBits = s_extraLengthBits[symbol];
Debug.Assert(_extraBits != 0, "We handle other cases separately!");
}
_length = symbol;
goto case Inflater64State.HaveInitialLength;
}
break;
case Inflater64State.HaveInitialLength:
if (_extraBits > 0)
{
_state = Inflater64State.HaveInitialLength;
int bits = _input.GetBits(_extraBits);
if (bits < 0)
{
return(false);
}
if (_length < 0 || _length >= s_lengthBase.Length)
{
throw new InvalidDataException(SR.GenericInvalidData);
}
_length = s_lengthBase[_length] + bits;
}
_state = Inflater64State.HaveFullLength;
goto case Inflater64State.HaveFullLength;
case Inflater64State.HaveFullLength:
if (_blockType == BlockType.Dynamic)
{
_distanceCode = _distanceTree.GetNextSymbol(_input);
}
else
{
// get distance code directly for static block
_distanceCode = _input.GetBits(5);
if (_distanceCode >= 0)
{
_distanceCode = s_staticDistanceTreeTable[_distanceCode];
}
}
if (_distanceCode < 0)
{
// running out input
return(false);
}
_state = Inflater64State.HaveDistCode;
goto case Inflater64State.HaveDistCode;
case Inflater64State.HaveDistCode:
// To avoid a table lookup we note that for distanceCode > 3,
// extra_bits = (distanceCode-2) >> 1
int offset;
if (_distanceCode > 3)
{
_extraBits = (_distanceCode - 2) >> 1;
int bits = _input.GetBits(_extraBits);
if (bits < 0)
{
return(false);
}
offset = s_distanceBasePosition[_distanceCode] + bits;
}
else
{
offset = _distanceCode + 1;
}
_output.WriteLengthDistance(_length, offset);
freeBytes -= _length;
_state = Inflater64State.DecodeTop;
break;
default:
Debug.Fail("check why we are here!");
throw new InvalidDataException(SR.UnknownState);
}
}
return(true);
}
//Each block of compressed data begins with 3 header bits
// containing the following data:
// first bit BFINAL
// next 2 bits BTYPE
// Note that the header bits do not necessarily begin on a byte
// boundary, since a block does not necessarily occupy an integral
// number of bytes.
// BFINAL is set if and only if this is the last block of the data
// set.
// BTYPE specifies how the data are compressed, as follows:
// 00 - no compression
// 01 - compressed with fixed Huffman codes
// 10 - compressed with dynamic Huffman codes
// 11 - reserved (error)
// The only difference between the two compressed cases is how the
// Huffman codes for the literal/length and distance alphabets are
// defined.
//
// This function returns true for success (end of block or output window is full,)
// false if we are short of input
//
private bool Decode()
{
bool eob = false;
bool result;
if (Finished())
{
return(true);
}
if (_hasFormatReader)
{
if (_state == Inflater64State.ReadingHeader)
{
if (!_formatReader.ReadHeader(_input))
{
return(false);
}
_state = Inflater64State.ReadingBFinal;
}
else if (_state == Inflater64State.StartReadingFooter || _state == Inflater64State.ReadingFooter)
{
if (!_formatReader.ReadFooter(_input))
{
return(false);
}
_state = Inflater64State.VerifyingFooter;
return(true);
}
}
if (_state == Inflater64State.ReadingBFinal)
{
// reading bfinal bit
// Need 1 bit
if (!_input.EnsureBitsAvailable(1))
{
return(false);
}
_bfinal = _input.GetBits(1);
_state = Inflater64State.ReadingBType;
}
if (_state == Inflater64State.ReadingBType)
{
// Need 2 bits
if (!_input.EnsureBitsAvailable(2))
{
_state = Inflater64State.ReadingBType;
return(false);
}
_blockType = (BlockType)_input.GetBits(2);
if (_blockType == BlockType.Dynamic)
{
_state = Inflater64State.ReadingNumLitCodes;
}
else if (_blockType == BlockType.Static)
{
_literalLengthTree = HuffmanTree.StaticLiteralLengthTree;
_distanceTree = HuffmanTree.StaticDistanceTree;
_state = Inflater64State.DecodeTop;
}
else if (_blockType == BlockType.Uncompressed)
{
_state = Inflater64State.UncompressedAligning;
}
else
{
throw new InvalidDataException(SR.UnknownBlockType);
}
}
if (_blockType == BlockType.Dynamic)
{
if (_state < Inflater64State.DecodeTop)
{
// we are reading the header
result = DecodeDynamicBlockHeader();
}
else
{
result = DecodeBlock(out eob); // this can returns true when output is full
}
}
else if (_blockType == BlockType.Static)
{
result = DecodeBlock(out eob);
}
else if (_blockType == BlockType.Uncompressed)
{
result = DecodeUncompressedBlock(out eob);
}
else
{
throw new InvalidDataException(SR.UnknownBlockType);
}
//
// If we reached the end of the block and the block we were decoding had
// bfinal=1 (final block)
//
if (eob && (_bfinal != 0))
{
if (_hasFormatReader)
{
_state = Inflater64State.StartReadingFooter;
}
else
{
_state = Inflater64State.Done;
}
}
return(result);
}
