Move LZX models to IO

This commit is contained in:
Matt Nadareski
2025-09-22 10:33:33 -04:00
parent c6062f71eb
commit 973a94b340
10 changed files with 0 additions and 385 deletions

View File

@@ -1,58 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// An aligned offset block is identical to the verbatim block except for the presence of the aligned offset
/// tree preceding the other trees.
/// </summary>
/// <see href="https://interoperability.blob.core.windows.net/files/MS-PATCH/%5bMS-PATCH%5d.pdf"/>
public class AlignedOffsetBlockData : BlockData
{
/// <summary>
/// Aligned offset tree
/// </summary>
/// <remarks>8 elements, 3 bits each</remarks>
public byte[]? AlignedOffsetTree { get; set; }
/// <summary>
/// Pretree for first 256 elements of main tree
/// </summary>
/// <remarks>20 elements, 4 bits each</remarks>
public byte[]? PretreeFirst256 { get; set; }
/// <summary>
/// Path lengths of first 256 elements of main tree
/// </summary>
/// <remarks>Encoded using pretree</remarks>
public int[]? PathLengthsFirst256 { get; set; }
/// <summary>
/// Pretree for remainder of main tree
/// </summary>
/// <remarks>20 elements, 4 bits each</remarks>
public byte[]? PretreeRemainder { get; set; }
/// <summary>
/// Path lengths of remaining elements of main tree
/// </summary>
/// <remarks>Encoded using pretree</remarks>
public int[]? PathLengthsRemainder { get; set; }
/// <summary>
/// Pretree for length tree
/// </summary>
/// <remarks>20 elements, 4 bits each</remarks>
public byte[]? PretreeLengthTree { get; set; }
/// <summary>
/// Path lengths of elements in length tree
/// </summary>
/// <remarks>Encoded using pretree</remarks>
public int[]? PathLengthsLengthTree { get; set; }
/// <summary>
/// Token sequence (matches and literals)
/// </summary>
/// <remarks>Variable</remarks>
public byte[]? TokenSequence { get; set; }
}
}

View File

@@ -1,24 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// An LZXD block represents a sequence of compressed data that is encoded with the same set of
/// Huffman trees, or a sequence of uncompressed data. There can be one or more LZXD blocks in a
/// compressed stream, each with its own set of Huffman trees. Blocks do not have to start or end on a
/// chunk boundary; blocks can span multiple chunks, or a single chunk can contain multiple blocks. The
/// number of chunks is related to the size of the data being compressed, while the number of blocks is
/// related to how well the data is compressed.
/// </summary>
/// <see href="https://interoperability.blob.core.windows.net/files/MS-PATCH/%5bMS-PATCH%5d.pdf"/>
public class Block
{
/// <summary>
/// Block header
/// </summary>
public BlockHeader? Header { get; set; }
/// <summary>
/// Block data
/// </summary>
public BlockData? BlockData { get; set; }
}
}

View File

@@ -1,8 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <see href="https://interoperability.blob.core.windows.net/files/MS-PATCH/%5bMS-PATCH%5d.pdf"/>
public abstract class BlockData
{
// No common fields between all block data
}
}

View File

@@ -1,33 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// The Block Type field, as specified in section 2.3.1.1, indicates which type of block follows,
/// and the Block Size field, as specified in section 2.3.1.2, indicates the number of
/// uncompressed bytes represented by the block. Following the generic block
/// header is a type-specific header that describes the remainder of the block.
/// </summary>
/// <see href="https://interoperability.blob.core.windows.net/files/MS-PATCH/%5bMS-PATCH%5d.pdf"/>
public class BlockHeader
{
/// <remarks>3 bits</remarks>
public BlockType BlockType { get; set; }
/// <summary>
/// Block size is the high 8 bits of 24
/// </summary>
/// <remarks>8 bits</remarks>
public byte BlockSizeMSB { get; set; }
/// <summary>
/// Block size is the middle 8 bits of 24
/// </summary>
/// <remarks>8 bits</remarks>
public byte BlockSizeByte2 { get; set; }
/// <summary>
/// Block size is the low 8 bits of 24
/// </summary>
/// <remarks>8 bits</remarks>
public byte BlocksizeLSB { get; set; }
}
}

View File

@@ -1,25 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// The LZXD compressor emits chunks of compressed data. A chunk represents exactly 32 KB of
/// uncompressed data until the last chunk in the stream, which can represent less than 32 KB. To
/// ensure that an exact number of input bytes represent an exact number of output bytes for each
/// chunk, after each 32 KB of uncompressed data is represented in the output compressed bitstream, the
/// output bitstream is padded with up to 15 bits of zeros to realign the bitstream on a 16-bit boundary
/// (even byte boundary) for the next 32 KB of data. This results in a compressed chunk of a byte-aligned
/// size. The compressed chunk could be smaller than 32 KB or larger than 32 KB if the data is
/// incompressible when the chunk is not the last one.
/// </summary>
public class Chunk
{
/// <summary>
/// Chunk header
/// </summary>
public ChunkHeader? Header { get; set; }
/// <summary>
/// Block headers and data
/// </summary>
public Block[]? Blocks { get; set; }
}
}

View File

@@ -1,46 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// The LZXD compressor emits chunks of compressed data. A chunk represents exactly 32 KB of
/// uncompressed data until the last chunk in the stream, which can represent less than 32 KB. To
/// ensure that an exact number of input bytes represent an exact number of output bytes for each
/// chunk, after each 32 KB of uncompressed data is represented in the output compressed bitstream, the
/// output bitstream is padded with up to 15 bits of zeros to realign the bitstream on a 16-bit boundary
/// (even byte boundary) for the next 32 KB of data. This results in a compressed chunk of a byte-aligned
/// size. The compressed chunk could be smaller than 32 KB or larger than 32 KB if the data is
/// incompressible when the chunk is not the last one.
/// </summary>
public class ChunkHeader
{
/// <summary>
/// The LZXD engine encodes a compressed, chunk-size prefix field preceding each compressed chunk in
/// the compressed byte stream. The compressed, chunk-size prefix field is a byte aligned, little-endian,
/// 16-bit field. The chunk prefix chain could be followed in the compressed stream without
/// decompressing any data. The next chunk prefix is at a location computed by the absolute byte offset
/// location of this chunk prefix plus 2 (for the size of the chunk-size prefix field) plus the current chunk
/// size.
/// </summary>
public ushort ChunkSize { get; set; }
/// <summary>
/// The first bit in the first chunk in the LZXD bitstream (following the 2-byte, chunk-size prefix described
/// in section 2.2.1) indicates the presence or absence of two 16-bit fields immediately following the
/// single bit. If the bit is set, E8 translation is enabled for all the following chunks in the stream using the
/// 32-bit value derived from the two 16-bit fields as the E8_file_size provided to the compressor when E8
/// translation was enabled. Note that E8_file_size is completely independent of the length of the
/// uncompressed data. E8 call translation is disabled after the 32,768th chunk (after 1 gigabyte (GB) of
/// uncompressed data).
/// </summary>
public byte E8Translation { get; set; }
/// <summary>
/// E8 translation size, high WORD
/// </summary>
public ushort? TranslationSizeHighWord { get; set; }
/// <summary>
/// E8 translation size, low WORD
/// </summary>
public ushort? TranslationSizeLowWord { get; set; }
}
}

View File

@@ -1,38 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
public static class Constants
{
/* some constants defined by the LZX specification */
public const int LZX_MIN_MATCH = 2;
public const int LZX_MAX_MATCH = 257;
public const int LZX_NUM_CHARS = 256;
public const int LZX_PRETREE_NUM_ELEMENTS = 20;
/// <summary>
/// aligned offset tree #elements
/// </summary>
public const int LZX_ALIGNED_NUM_ELEMENTS = 8;
/// <summary>
/// this one missing from spec!
/// </summary>
public const int LZX_NUM_PRIMARY_LENGTHS = 7;
/// <summary>
/// length tree #elements
/// </summary>
public const int LZX_NUM_SECONDARY_LENGTHS = 249;
/* LZX huffman defines: tweak tablebits as desired */
public const int LZX_PRETREE_MAXSYMBOLS = LZX_PRETREE_NUM_ELEMENTS;
public const int LZX_PRETREE_TABLEBITS = 6;
public const int LZX_MAINTREE_MAXSYMBOLS = LZX_NUM_CHARS + 50 * 8;
public const int LZX_MAINTREE_TABLEBITS = 12;
public const int LZX_LENGTH_MAXSYMBOLS = LZX_NUM_SECONDARY_LENGTHS + 1;
public const int LZX_LENGTH_TABLEBITS = 12;
public const int LZX_ALIGNED_MAXSYMBOLS = LZX_ALIGNED_NUM_ELEMENTS;
public const int LZX_ALIGNED_TABLEBITS = 7;
public const int LZX_LENTABLE_SAFETY = 64; /* we allow length table decoding overruns */
}
}

View File

@@ -1,48 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// 3-bit block type
/// </summary>
public enum BlockType : byte
{
/// <summary>
/// Not valid
/// </summary>
INVALID_0 = 0b000,
/// <summary>
/// Verbatim block
/// </summary>
Verbatim = 0b001,
/// <summary>
/// Aligned offset block
/// </summary>
AlignedOffset = 0b010,
/// <summary>
/// Uncompressed block
/// </summary>
Uncompressed = 0b011,
/// <summary>
/// Not valid
/// </summary>
INVALID_4 = 0b100,
/// <summary>
/// Not valid
/// </summary>
INVALID_5 = 0b101,
/// <summary>
/// Not valid
/// </summary>
INVALID_6 = 0b110,
/// <summary>
/// Not valid
/// </summary>
INVALID_7 = 0b111,
}
}

View File

@@ -1,54 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// Following the generic block header, an uncompressed block begins with 1 to 16 bits of zero padding
/// to align the bit buffer on a 16-bit boundary. At this point, the bitstream ends and a byte stream
/// begins. Following the zero padding, new 32-bit values for R0, R1, and R2 are output in little-endian
/// form, followed by the uncompressed data bytes themselves. Finally, if the uncompressed data length
/// is odd, one extra byte of zero padding is encoded to realign the following bitstream.
///
/// Then the bitstream of byte-swapped 16-bit integers resumes for the next Block Type field (if there
/// are subsequent blocks).
///
/// The decoded R0, R1, and R2 values are used as initial repeated offset values to decode the
/// subsequent compressed block if present.
/// </summary>
/// <see href="https://interoperability.blob.core.windows.net/files/MS-PATCH/%5bMS-PATCH%5d.pdf"/>
public class UncompressedBlockData : BlockData
{
/// <summary>
/// Padding to align following field on 16-bit boundary
/// </summary>
/// <remarks>Bits have a value of zero</remarks>
public ushort PaddingBits { get; set; }
/// <summary>
/// Least significant to most significant byte (little-endian DWORD ([MS-DTYP]))
/// </summary>
/// <remarks>Encoded directly in the byte stream, not in the bitstream of byte-swapped 16-bit words</remarks>
public uint R0 { get; set; }
/// <summary>
/// Least significant to most significant byte (little-endian DWORD)
/// </summary>
/// <remarks>Encoded directly in the byte stream, not in the bitstream of byte-swapped 16-bit words</remarks>
public uint R1 { get; set; }
/// <summary>
/// Least significant to most significant byte (little-endian DWORD)
/// </summary>
/// <remarks>Encoded directly in the byte stream, not in the bitstream of byte-swapped 16-bit words</remarks>
public uint R2 { get; set; }
/// <summary>
/// Can use the direct memcpy function, as specified in [IEEE1003.1]
/// </summary>
/// <remarks>Encoded directly in the byte stream, not in the bitstream of byte-swapped 16-bit words</remarks>
public byte[]? RawDataBytes { get; set; }
/// <summary>
/// Only if uncompressed size is odd
/// </summary>
public byte AlignmentByte { get; set; }
}
}

View File

@@ -1,51 +0,0 @@
namespace SabreTools.Models.Compression.LZX
{
/// <summary>
/// The fields of a verbatim block that follow the generic block header
/// </summary>
/// <see href="https://interoperability.blob.core.windows.net/files/MS-PATCH/%5bMS-PATCH%5d.pdf"/>
public class VerbatimBlockData : BlockData
{
/// <summary>
/// Pretree for first 256 elements of main tree
/// </summary>
/// <remarks>20 elements, 4 bits each</remarks>
public byte[]? PretreeFirst256 { get; set; }
/// <summary>
/// Path lengths of first 256 elements of main tree
/// </summary>
/// <remarks>Encoded using pretree</remarks>
public int[]? PathLengthsFirst256 { get; set; }
/// <summary>
/// Pretree for remainder of main tree
/// </summary>
/// <remarks>20 elements, 4 bits each</remarks>
public byte[]? PretreeRemainder { get; set; }
/// <summary>
/// Path lengths of remaining elements of main tree
/// </summary>
/// <remarks>Encoded using pretree</remarks>
public int[]? PathLengthsRemainder { get; set; }
/// <summary>
/// Pretree for length tree
/// </summary>
/// <remarks>20 elements, 4 bits each</remarks>
public byte[]? PretreeLengthTree { get; set; }
/// <summary>
/// Path lengths of elements in length tree
/// </summary>
/// <remarks>Encoded using pretree</remarks>
public int[]? PathLengthsLengthTree { get; set; }
/// <summary>
/// Token sequence (matches and literals)
/// </summary>
/// <remarks>Variable</remarks>
public byte[]? TokenSequence { get; set; }
}
}