Files
wuffs/std/lzma/decode_lzma.wuffs
T
2023-12-12 23:41:26 +11:00

325 lines
9.3 KiB
Plaintext

// Copyright 2023 The Wuffs Authors.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// https://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//
// SPDX-License-Identifier: Apache-2.0 OR MIT
pub status "#bad bitstream trailer"
pub status "#bad code"
pub status "#bad decoded length"
pub status "#bad distance"
pub status "#bad header"
pub status "#truncated input"
pub status "#unsupported decoded length"
pub status "#unsupported properties"
pub const DECODER_HISTORY_RETAIN_LENGTH_MAX_INCL_WORST_CASE : base.u64 = 0xFFFF_FFFF
pub const DECODER_WORKBUF_LEN_MAX_INCL_WORST_CASE : base.u64 = 0
pub struct decoder? implements base.io_transformer(
// In theory, lc ranges in [0 ..= 8]. In practice, to keep the
// worst-case size of the statically allocated probs_lit array
// managable, we only support configurations where ((lc + lp) <= 4) and
// otherwise return "#unsupported properties".
//
// This matches "LZMA2's limited property condition" described at:
// https://github.com/jljusten/LZMA-SDK/blob/781863cdf592da3e97420f50de5dac056ad352a5/DOC/lzma-specification.txt#L192
lc : base.u32[..= 4], // The number of Literal Context bits. Default: 3.
lp : base.u32[..= 4], // The number of Literal Position bits. Default: 0.
pb : base.u32[..= 4], // The number of Position Bits. Default: 2.
dict_size : base.u32,
decoded_length : base.u64,
util : base.utility,
) + (
// 12 is the number of states. 4 is the pb inclusive maximum.
//
// The AlgOveNN line numbers refer to the ./README.md file.
probs_ao00 : array[12 << 4] base.u16, // AlgOve00.
probs_ao20 : array[12] base.u16, // AlgOve20.
probs_ao40 : array[12] base.u16, // AlgOve40.
probs_ao41 : array[12 << 4] base.u16, // AlgOve41.
probs_ao60 : array[12] base.u16, // AlgOve60.
probs_ao63 : array[12] base.u16, // AlgOve63.
// AlgOve22 and what "decodeLen expands to".
probs_match_len_low : array[1 << 4] array[1 << 3] base.u16,
probs_match_len_mid : array[1 << 4] array[1 << 3] base.u16,
probs_match_len_high : array[1 << 0] array[1 << 8] base.u16,
// AlgOve80 and what "decodeLen expands to".
probs_longrep_len_low : array[1 << 4] array[1 << 3] base.u16,
probs_longrep_len_mid : array[1 << 4] array[1 << 3] base.u16,
probs_longrep_len_high : array[1 << 0] array[1 << 8] base.u16,
// AlgOve23. The first index is min(len-2, 3). There are then 64
// possible slots, so a 6-bit binary tree.
probs_slot : array[4] array[1 << 6] base.u16,
// This holds the "xxxx" binary trees, packed per below. The first
// element and last 13 elements are unused. The index_small_dist_base
// constant is set to (Low - 1) and index_small_dist_extra variable
// starts at 1. (index_small_dist_base + index_small_dist_extra) ranges
// in Low .. High during the "decode a binary tree" loop.
//
// Slot Low .. High H-L NumberOfXByms
// 4 1 .. 2 1 1
// 5 2 .. 3 1 1
// 6 3 .. 6 3 2
// 7 6 .. 9 3 2
// 8 9 .. 16 7 3
// 9 16 .. 23 7 3
// 10 23 .. 38 15 4
// 11 38 .. 53 15 4
// 12 53 .. 84 31 5
// 13 84 .. 115 31 5
probs_small_dist : array[128] base.u16,
// This holds the "zzzz" binary tree.
probs_large_dist : array[1 << 4] base.u16,
// 4 is the (lc + lp) inclusive maximum. The 0x300 holds three 8-bit
// binary trees. The first is for (state < 7), when the previous packet
// was a LITERAL. The other two trees are for (state >= 7), when it was
// an LZ-copy. Which tree gets used depends on the bits in the next
// historical byte after the LZ-copy-source, up until the point where
// those bits don't match the currently decoded literal byte, when it
// drops back to the first tree.
probs_lit : array[1 << 4] array[0x300] base.u16,
)
pub func decoder.get_quirk(key: base.u32) base.u64 {
return 0
}
pub func decoder.set_quirk!(key: base.u32, value: base.u64) base.status {
return base."#unsupported option"
}
pub func decoder.history_retain_length() base.optional_u63 {
if this.dict_size == 0 {
return this.util.make_optional_u63(has_value: false, value: 0)
}
return this.util.make_optional_u63(has_value: true, value: this.dict_size as base.u64)
}
pub func decoder.workbuf_len() base.range_ii_u64 {
return this.util.make_range_ii_u64(min_incl: 0, max_incl: 0)
}
pub func decoder.transform_io?(dst: base.io_writer, src: base.io_reader, workbuf: slice base.u8) {
var status : base.status
while true {
status =? this.do_transform_io?(dst: args.dst, src: args.src, workbuf: args.workbuf)
if (status == base."$short read") and args.src.is_closed() {
return "#truncated input"
}
yield? status
} endwhile
}
pri func decoder.do_transform_io?(dst: base.io_writer, src: base.io_reader, workbuf: slice base.u8) {
this.decode_properties?(src: args.src)
this.initialize_probs!()
this.decode_bitstream_slow?(dst: args.dst, src: args.src)
}
pri func decoder.decode_properties?(src: base.io_reader) {
var c8 : base.u8
var c32 : base.u32
var lc : base.u32[..= 8]
var lp : base.u32[..= 4]
var pb : base.u32[..= 4]
c8 = args.src.read_u8?()
if c8 >= 225 {
return "#bad header"
}
lc = (c8 % 9) as base.u32
c8 /= 9
lp = (c8 % 5) as base.u32
pb = (c8 / 5) as base.u32
if (lc + lp) > 4 {
return "#unsupported properties"
}
this.lc = lc.min(no_more_than: 4)
this.lp = lp
this.pb = pb
c32 = args.src.read_u32le?()
this.dict_size = c32.max(no_less_than: 4096)
this.decoded_length = args.src.read_u64le?()
if (this.decoded_length >= 0x8000_0000_0000_0000) and
(this.decoded_length <> 0xFFFF_FFFF_FFFF_FFFF) {
return "#unsupported decoded length"
}
}
// initialize_probs sets all of the probs_foo[i][j] values to 1024.
pri func decoder.initialize_probs!() {
var i : base.u32
var j : base.u32
i = 0
while i < (12 << 4) {
this.probs_ao00[i] = 1024
i += 1
} endwhile
i = 0
while i < 12 {
this.probs_ao20[i] = 1024
i += 1
} endwhile
i = 0
while i < 12 {
this.probs_ao40[i] = 1024
i += 1
} endwhile
i = 0
while i < (12 << 4) {
this.probs_ao41[i] = 1024
i += 1
} endwhile
i = 0
while i < 12 {
this.probs_ao60[i] = 1024
i += 1
} endwhile
i = 0
while i < 12 {
this.probs_ao63[i] = 1024
i += 1
} endwhile
i = 0
while i < 16 {
j = 0
while j < 8,
inv i < 16,
{
this.probs_match_len_low[i][j] = 1024
j += 1
} endwhile
i += 1
} endwhile
i = 0
while i < 16 {
j = 0
while j < 8,
inv i < 16,
{
this.probs_match_len_mid[i][j] = 1024
j += 1
} endwhile
i += 1
} endwhile
i = 0
while i < 256 {
this.probs_match_len_high[0][i] = 1024
i += 1
} endwhile
i = 0
while i < 16 {
j = 0
while j < 8,
inv i < 16,
{
this.probs_longrep_len_low[i][j] = 1024
j += 1
} endwhile
i += 1
} endwhile
i = 0
while i < 16 {
j = 0
while j < 8,
inv i < 16,
{
this.probs_longrep_len_mid[i][j] = 1024
j += 1
} endwhile
i += 1
} endwhile
i = 0
while i < 256 {
this.probs_longrep_len_high[0][i] = 1024
i += 1
} endwhile
i = 0
while i < 4 {
j = 0
while j < 64,
inv i < 4,
{
this.probs_slot[i][j] = 1024
j += 1
} endwhile
i += 1
} endwhile
i = 0
while i < 128 {
this.probs_small_dist[i] = 1024
i += 1
} endwhile
i = 0
while i < 16 {
this.probs_large_dist[i] = 1024
i += 1
} endwhile
i = 0
while i < 16 {
j = 0
while j < 0x300,
inv i < 16,
{
this.probs_lit[i][j] = 1024
j += 1
} endwhile
i += 1
} endwhile
}
pri const STATE_TRANSITION_LITERAL : roarray[12] base.u8[..= 11] = [
0x0, 0x0, 0x0, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x4, 0x5,
]
pri const STATE_TRANSITION_MATCH : roarray[12] base.u8[..= 11] = [
0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0xA, 0xA, 0xA, 0xA, 0xA,
]
pri const STATE_TRANSITION_LONGREP : roarray[12] base.u8[..= 11] = [
0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0xB, 0xB, 0xB, 0xB, 0xB,
]
pri const STATE_TRANSITION_SHORTREP : roarray[12] base.u8[..= 11] = [
0x9, 0x9, 0x9, 0x9, 0x9, 0x9, 0x9, 0xB, 0xB, 0xB, 0xB, 0xB,
]
pri const CLAMP_NO_MORE_THAN_3 : roarray[8] base.u8[..= 3] = [
0, 1, 2, 3, 3, 3, 3, 3,
]