mirror of
https://github.com/exoticorn/upkr.git
synced 2026-06-28 13:59:42 +02:00
Compare commits
41 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 dranke
|
31fb91c629 | ||
|
dranke
|
e429f252a5 | ||
|
dranke
|
f6642f07c9 | ||
|
dranke
|
8715dede0e | ||
|
dranke
|
b12c8f8d93 | ||
 Peter Helcmanovsky (Ped)
|
8a32e1384c | ||
|
Peter Helcmanovsky (Ped)
|
9913dcf4bb | ||
|
Peter Helcmanovsky (Ped)
|
a8fd3dc573 | ||
|
Peter Helcmanovsky (Ped)
|
e1f9fa143a | ||
|
Peter Helcmanovsky (Ped)
|
db1c7d2d14 | ||
|
Peter Helcmanovsky (Ped)
|
c1ffd0e7ed | ||
|
Peter Helcmanovsky (Ped)
|
00d084105a | ||
|
Peter Helcmanovsky (Ped)
|
8e5298caee | ||
|
Peter Helcmanovsky (Ped)
|
1fb29f3a1b | ||
|
dranke
|
c8924456aa | ||
|
dranke
|
7b0e22f459 | ||
|
Peter Helcmanovsky (Ped)
|
165f593a11 | ||
|
Peter Helcmanovsky (Ped)
|
d4bce4bf7c | ||
|
Peter Helcmanovsky (Ped)
|
b13fa05413 | ||
|
Peter Helcmanovsky (Ped)
|
3c773aca8d | ||
|
dranke
|
a5406deb30 | ||
|
Peter Helcmanovsky (Ped)
|
9211544cb9 | ||
|
Peter Helcmanovsky (Ped)
|
3fa9e0fa12 | ||
|
Peter Helcmanovsky (Ped)
|
aa3fad4d80 | ||
|
Peter Helcmanovsky (Ped)
|
6624940ed9 | ||
|
Peter Helcmanovsky (Ped)
|
c3a9773e5c | ||
|
Peter Helcmanovsky (Ped)
|
a75a35efb2 | ||
|
dranke
|
540a91d1ba | ||
|
dranke
|
e7aaf1491a | ||
|
dranke
|
a1dabaf7f9 | ||
|
dranke
|
75e375fb1f | ||
|
Peter Helcmanovsky (Ped)
|
c7ea11bce3 | ||
|
Peter Helcmanovsky (Ped)
|
02d20867ee | ||
|
Peter Helcmanovsky (Ped)
|
511ddefc08 | ||
|
Peter Helcmanovsky (Ped)
|
d30baaa91f | ||
|
Peter Helcmanovsky (Ped)
|
919a892ef0 | ||
|
Peter Helcmanovsky (Ped)
|
ea5c0b1b15 | ||
|
Peter Helcmanovsky (Ped)
|
a19ec2abb7 | ||
|
Peter Helcmanovsky (Ped)
|
7b051113e1 | ||
|
dranke
|
f1f1c64a76 | ||
|
dranke
|
36cb6d77b5 |
Generated
+57
-1
@@ -95,6 +95,24 @@ dependencies = [
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "proc-macro2"
|
||||
version = "1.0.44"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7bd7356a8122b6c4a24a82b278680c73357984ca2fc79a0f9fa6dea7dced7c58"
|
||||
dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "quote"
|
||||
version = "1.0.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bbe448f377a7d6961e30f5955f9b8d106c3f5e449d493ee1b125c1d43c2b5179"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "sacabase"
|
||||
version = "2.0.0"
|
||||
@@ -104,6 +122,37 @@ dependencies = [
|
||||
"num-traits",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "syn"
|
||||
version = "1.0.101"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e90cde112c4b9690b8cbe810cba9ddd8bc1d7472e2cae317b69e9438c1cba7d2"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "thiserror"
|
||||
version = "1.0.36"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0a99cb8c4b9a8ef0e7907cd3b617cc8dc04d571c4e73c8ae403d80ac160bb122"
|
||||
dependencies = [
|
||||
"thiserror-impl",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "thiserror-impl"
|
||||
version = "1.0.36"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3a891860d3c8d66fec8e73ddb3765f90082374dbaaa833407b904a94f1a7eb43"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "time"
|
||||
version = "0.1.44"
|
||||
@@ -115,14 +164,21 @@ dependencies = [
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "unicode-ident"
|
||||
version = "1.0.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dcc811dc4066ac62f84f11307873c4850cb653bfa9b1719cee2bd2204a4bc5dd"
|
||||
|
||||
[[package]]
|
||||
name = "upkr"
|
||||
version = "0.2.0-pre1"
|
||||
version = "0.2.0-pre3"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"cdivsufsort",
|
||||
"lexopt",
|
||||
"pbr",
|
||||
"thiserror",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
+2
-1
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "upkr"
|
||||
version = "0.2.0-pre2"
|
||||
version = "0.2.0-pre3"
|
||||
edition = "2021"
|
||||
|
||||
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
|
||||
@@ -9,4 +9,5 @@ edition = "2021"
|
||||
cdivsufsort = "2"
|
||||
lexopt = "0.2.1"
|
||||
anyhow = "1"
|
||||
thiserror = "1.0.36"
|
||||
pbr = "1"
|
||||
@@ -0,0 +1,3 @@
|
||||
target
|
||||
corpus
|
||||
artifacts
|
||||
Generated
+247
@@ -0,0 +1,247 @@
|
||||
# This file is automatically @generated by Cargo.
|
||||
# It is not intended for manual editing.
|
||||
version = 3
|
||||
|
||||
[[package]]
|
||||
name = "anyhow"
|
||||
version = "1.0.65"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "98161a4e3e2184da77bb14f02184cdd111e83bbbcc9979dfee3c44b9a85f5602"
|
||||
|
||||
[[package]]
|
||||
name = "arbitrary"
|
||||
version = "1.1.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f44124848854b941eafdb34f05b3bcf59472f643c7e151eba7c2b69daa469ed5"
|
||||
|
||||
[[package]]
|
||||
name = "autocfg"
|
||||
version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.0.73"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2fff2a6927b3bb87f9595d67196a70493f627687a71d87a0d692242c33f58c11"
|
||||
dependencies = [
|
||||
"jobserver",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cdivsufsort"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "edefce019197609da416762da75bb000bbd2224b2d89a7e722c2296cbff79b8c"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"sacabase",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cfg-if"
|
||||
version = "1.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-channel"
|
||||
version = "0.5.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c2dd04ddaf88237dc3b8d8f9a3c1004b506b54b3313403944054d23c0870c521"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"crossbeam-utils",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-utils"
|
||||
version = "0.8.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "51887d4adc7b564537b15adcfb307936f8075dfcd5f00dde9a9f1d29383682bc"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"once_cell",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "jobserver"
|
||||
version = "0.1.25"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "068b1ee6743e4d11fb9c6a1e6064b3693a1b600e7f5f5988047d98b3dc9fb90b"
|
||||
dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lexopt"
|
||||
version = "0.2.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "478ee9e62aaeaf5b140bd4138753d1f109765488581444218d3ddda43234f3e8"
|
||||
|
||||
[[package]]
|
||||
name = "libc"
|
||||
version = "0.2.133"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c0f80d65747a3e43d1596c7c5492d95d5edddaabd45a7fcdb02b95f644164966"
|
||||
|
||||
[[package]]
|
||||
name = "libfuzzer-sys"
|
||||
version = "0.4.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ae185684fe19814afd066da15a7cc41e126886c21282934225d9fc847582da58"
|
||||
dependencies = [
|
||||
"arbitrary",
|
||||
"cc",
|
||||
"once_cell",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "num-traits"
|
||||
version = "0.2.15"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "578ede34cf02f8924ab9447f50c28075b4d3e5b269972345e7e0372b38c6cdcd"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "once_cell"
|
||||
version = "1.15.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e82dad04139b71a90c080c8463fe0dc7902db5192d939bd0950f074d014339e1"
|
||||
|
||||
[[package]]
|
||||
name = "pbr"
|
||||
version = "1.0.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ff5751d87f7c00ae6403eb1fcbba229b9c76c9a30de8c1cf87182177b168cea2"
|
||||
dependencies = [
|
||||
"crossbeam-channel",
|
||||
"libc",
|
||||
"time",
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "proc-macro2"
|
||||
version = "1.0.44"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7bd7356a8122b6c4a24a82b278680c73357984ca2fc79a0f9fa6dea7dced7c58"
|
||||
dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "quote"
|
||||
version = "1.0.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bbe448f377a7d6961e30f5955f9b8d106c3f5e449d493ee1b125c1d43c2b5179"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "sacabase"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9883fc3d6ce3d78bb54d908602f8bc1f7b5f983afe601dabe083009d86267a84"
|
||||
dependencies = [
|
||||
"num-traits",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "syn"
|
||||
version = "1.0.101"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e90cde112c4b9690b8cbe810cba9ddd8bc1d7472e2cae317b69e9438c1cba7d2"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "thiserror"
|
||||
version = "1.0.36"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0a99cb8c4b9a8ef0e7907cd3b617cc8dc04d571c4e73c8ae403d80ac160bb122"
|
||||
dependencies = [
|
||||
"thiserror-impl",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "thiserror-impl"
|
||||
version = "1.0.36"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3a891860d3c8d66fec8e73ddb3765f90082374dbaaa833407b904a94f1a7eb43"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "time"
|
||||
version = "0.1.44"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6db9e6914ab8b1ae1c260a4ae7a49b6c5611b40328a735b21862567685e73255"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"wasi",
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "unicode-ident"
|
||||
version = "1.0.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dcc811dc4066ac62f84f11307873c4850cb653bfa9b1719cee2bd2204a4bc5dd"
|
||||
|
||||
[[package]]
|
||||
name = "upkr"
|
||||
version = "0.2.0-pre3"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"cdivsufsort",
|
||||
"lexopt",
|
||||
"pbr",
|
||||
"thiserror",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "upkr-fuzz"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"libfuzzer-sys",
|
||||
"upkr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasi"
|
||||
version = "0.10.0+wasi-snapshot-preview1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1a143597ca7c7793eff794def352d41792a93c481eb1042423ff7ff72ba2c31f"
|
||||
|
||||
[[package]]
|
||||
name = "winapi"
|
||||
version = "0.3.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
|
||||
dependencies = [
|
||||
"winapi-i686-pc-windows-gnu",
|
||||
"winapi-x86_64-pc-windows-gnu",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "winapi-i686-pc-windows-gnu"
|
||||
version = "0.4.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
|
||||
|
||||
[[package]]
|
||||
name = "winapi-x86_64-pc-windows-gnu"
|
||||
version = "0.4.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
|
||||
@@ -0,0 +1,31 @@
|
||||
[package]
|
||||
name = "upkr-fuzz"
|
||||
version = "0.0.0"
|
||||
authors = ["Automatically generated"]
|
||||
publish = false
|
||||
edition = "2018"
|
||||
|
||||
[package.metadata]
|
||||
cargo-fuzz = true
|
||||
|
||||
[dependencies]
|
||||
libfuzzer-sys = "0.4"
|
||||
|
||||
[dependencies.upkr]
|
||||
path = ".."
|
||||
|
||||
# Prevent this from interfering with workspaces
|
||||
[workspace]
|
||||
members = ["."]
|
||||
|
||||
[[bin]]
|
||||
name = "all_configs"
|
||||
path = "fuzz_targets/all_configs.rs"
|
||||
test = false
|
||||
doc = false
|
||||
|
||||
[[bin]]
|
||||
name = "unpack"
|
||||
path = "fuzz_targets/unpack.rs"
|
||||
test = false
|
||||
doc = false
|
||||
@@ -0,0 +1,29 @@
|
||||
#![no_main]
|
||||
use libfuzzer_sys::fuzz_target;
|
||||
|
||||
fuzz_target!(|data: &[u8]| {
|
||||
let mut config = upkr::Config::default();
|
||||
let mut level = 1;
|
||||
let mut data = data;
|
||||
if data.len() > 2 {
|
||||
let flags1 = data[0];
|
||||
let flags2 = data[1];
|
||||
data = &data[2..];
|
||||
config.use_bitstream = (flags1 & 1) != 0;
|
||||
config.parity_contexts = if (flags1 & 2) == 0 { 1 } else { 2 };
|
||||
config.invert_bit_encoding = (flags1 & 4) != 0;
|
||||
config.is_match_bit = (flags1 & 8) != 0;
|
||||
config.new_offset_bit = (flags1 & 16) != 0;
|
||||
config.continue_value_bit = (flags1 & 32) != 0;
|
||||
config.bitstream_is_big_endian = (flags1 & 64) != 0;
|
||||
config.simplified_prob_update = (flags1 & 128) != 0;
|
||||
config.no_repeated_offsets = (flags2 & 32) != 0;
|
||||
config.eof_in_length = (flags2 & 1) != 0;
|
||||
config.max_offset = if (flags2 & 2) == 0 { usize::MAX } else { 32 };
|
||||
config.max_length = if (flags2 & 4) == 0 { usize::MAX } else { 5 };
|
||||
level = (flags2 >> 3) & 3;
|
||||
}
|
||||
let packed = upkr::pack(data, level, &config, None);
|
||||
let unpacked = upkr::unpack(&packed, &config, 1024 * 1024).unwrap();
|
||||
assert!(unpacked == data);
|
||||
});
|
||||
@@ -0,0 +1,6 @@
|
||||
#![no_main]
|
||||
use libfuzzer_sys::fuzz_target;
|
||||
|
||||
fuzz_target!(|data: &[u8]| {
|
||||
let _ = upkr::unpack(data, &upkr::Config::default(), 64 * 1024);
|
||||
});
|
||||
@@ -19,15 +19,16 @@ pub fn pack(
|
||||
}
|
||||
let mut encoded_match = false;
|
||||
if let Some(m) = match_finder.matches(pos).next() {
|
||||
let max_offset = 1 << (m.length * 3 - 1).min(31);
|
||||
let max_offset = config.max_offset.min(1 << (m.length * 3 - 1).min(31));
|
||||
let offset = pos - m.pos;
|
||||
if offset < max_offset {
|
||||
if offset < max_offset && m.length >= config.min_length() {
|
||||
let length = m.length.min(config.max_length);
|
||||
lz::Op::Match {
|
||||
offset: offset as u32,
|
||||
len: m.length as u32,
|
||||
len: length as u32,
|
||||
}
|
||||
.encode(&mut rans_coder, &mut state, config);
|
||||
pos += m.length;
|
||||
pos += length;
|
||||
encoded_match = true;
|
||||
}
|
||||
}
|
||||
@@ -39,8 +40,9 @@ pub fn pack(
|
||||
.iter()
|
||||
.zip(data[(pos - offset)..].iter())
|
||||
.take_while(|(a, b)| a == b)
|
||||
.count();
|
||||
if length > 0 {
|
||||
.count()
|
||||
.min(config.max_length);
|
||||
if length >= config.min_length() {
|
||||
lz::Op::Match {
|
||||
offset: offset as u32,
|
||||
len: length as u32,
|
||||
|
||||
+23
-4
@@ -5,10 +5,11 @@ mod match_finder;
|
||||
mod parsing_packer;
|
||||
mod rans;
|
||||
|
||||
pub use lz::unpack;
|
||||
pub use lz::{calculate_margin, unpack, UnpackError};
|
||||
|
||||
pub type ProgressCallback<'a> = &'a mut dyn FnMut(usize);
|
||||
|
||||
#[derive(Debug)]
|
||||
pub struct Config {
|
||||
pub use_bitstream: bool,
|
||||
pub parity_contexts: usize,
|
||||
@@ -22,6 +23,10 @@ pub struct Config {
|
||||
pub simplified_prob_update: bool,
|
||||
|
||||
pub no_repeated_offsets: bool,
|
||||
pub eof_in_length: bool,
|
||||
|
||||
pub max_offset: usize,
|
||||
pub max_length: usize,
|
||||
}
|
||||
|
||||
impl Default for Config {
|
||||
@@ -39,6 +44,20 @@ impl Default for Config {
|
||||
simplified_prob_update: false,
|
||||
|
||||
no_repeated_offsets: false,
|
||||
eof_in_length: false,
|
||||
|
||||
max_offset: usize::MAX,
|
||||
max_length: usize::MAX,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl Config {
|
||||
pub fn min_length(&self) -> usize {
|
||||
if self.eof_in_length {
|
||||
2
|
||||
} else {
|
||||
1
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -46,13 +65,13 @@ impl Default for Config {
|
||||
pub fn pack(
|
||||
data: &[u8],
|
||||
level: u8,
|
||||
config: Config,
|
||||
config: &Config,
|
||||
progress_callback: Option<ProgressCallback>,
|
||||
) -> Vec<u8> {
|
||||
if level == 0 {
|
||||
greedy_packer::pack(data, &config, progress_callback)
|
||||
greedy_packer::pack(data, config, progress_callback)
|
||||
} else {
|
||||
parsing_packer::pack(data, level, &config, progress_callback)
|
||||
parsing_packer::pack(data, level, config, progress_callback)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
use crate::context_state::ContextState;
|
||||
use crate::rans::{EntropyCoder, RansDecoder};
|
||||
use crate::Config;
|
||||
use thiserror::Error;
|
||||
|
||||
#[derive(Copy, Clone, Debug)]
|
||||
pub enum Op {
|
||||
@@ -25,26 +26,28 @@ impl Op {
|
||||
}
|
||||
&Op::Match { offset, len } => {
|
||||
encode_bit(coder, state, literal_base, config.is_match_bit);
|
||||
let mut new_offset = true;
|
||||
if !state.prev_was_match && !config.no_repeated_offsets {
|
||||
new_offset = offset != state.last_offset;
|
||||
encode_bit(
|
||||
coder,
|
||||
state,
|
||||
256 * state.parity_contexts,
|
||||
(offset != state.last_offset) == config.new_offset_bit,
|
||||
new_offset == config.new_offset_bit,
|
||||
);
|
||||
} else {
|
||||
assert!(offset != state.last_offset || config.no_repeated_offsets);
|
||||
}
|
||||
if offset != state.last_offset || config.no_repeated_offsets {
|
||||
assert!(offset as usize <= config.max_offset);
|
||||
if new_offset {
|
||||
encode_length(
|
||||
coder,
|
||||
state,
|
||||
256 * state.parity_contexts + 1,
|
||||
offset + 1,
|
||||
offset + if config.eof_in_length { 0 } else { 1 },
|
||||
config,
|
||||
);
|
||||
state.last_offset = offset;
|
||||
}
|
||||
assert!(len as usize >= config.min_length() && len as usize <= config.max_length);
|
||||
encode_length(coder, state, 256 * state.parity_contexts + 65, len, config);
|
||||
state.prev_was_match = true;
|
||||
state.pos += len as usize;
|
||||
@@ -60,15 +63,20 @@ pub fn encode_eof(coder: &mut dyn EntropyCoder, state: &mut CoderState, config:
|
||||
state.pos % state.parity_contexts * 256,
|
||||
config.is_match_bit,
|
||||
);
|
||||
if !state.prev_was_match {
|
||||
if !state.prev_was_match && !config.no_repeated_offsets {
|
||||
encode_bit(
|
||||
coder,
|
||||
state,
|
||||
256 * state.parity_contexts,
|
||||
config.new_offset_bit,
|
||||
config.new_offset_bit ^ config.eof_in_length,
|
||||
);
|
||||
}
|
||||
if !config.eof_in_length || state.prev_was_match || config.no_repeated_offsets {
|
||||
encode_length(coder, state, 256 * state.parity_contexts + 1, 1, config);
|
||||
}
|
||||
if config.eof_in_length {
|
||||
encode_length(coder, state, 256 * state.parity_contexts + 65, 1, config);
|
||||
}
|
||||
}
|
||||
|
||||
fn encode_bit(
|
||||
@@ -124,42 +132,81 @@ impl CoderState {
|
||||
}
|
||||
}
|
||||
|
||||
pub fn unpack(packed_data: &[u8], config: Config) -> Vec<u8> {
|
||||
#[derive(Error, Debug)]
|
||||
pub enum UnpackError {
|
||||
#[error("match offset out of range: {offset} > {position}")]
|
||||
OffsetOutOfRange { offset: usize, position: usize },
|
||||
#[error("Unpacked data over size limit: {size} > {limit}")]
|
||||
OverSize { size: usize, limit: usize },
|
||||
#[error("Unexpected end of input data")]
|
||||
UnexpectedEOF {
|
||||
#[from]
|
||||
source: crate::rans::UnexpectedEOF,
|
||||
},
|
||||
#[error("Overflow while reading value")]
|
||||
ValueOverflow,
|
||||
}
|
||||
|
||||
pub fn unpack(
|
||||
packed_data: &[u8],
|
||||
config: &Config,
|
||||
max_size: usize,
|
||||
) -> Result<Vec<u8>, UnpackError> {
|
||||
let mut result = vec![];
|
||||
let _ = unpack_internal(Some(&mut result), packed_data, config, max_size)?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub fn calculate_margin(packed_data: &[u8], config: &Config) -> Result<isize, UnpackError> {
|
||||
unpack_internal(None, packed_data, config, usize::MAX)
|
||||
}
|
||||
|
||||
pub fn unpack_internal(
|
||||
mut result: Option<&mut Vec<u8>>,
|
||||
packed_data: &[u8],
|
||||
config: &Config,
|
||||
max_size: usize,
|
||||
) -> Result<isize, UnpackError> {
|
||||
let mut decoder = RansDecoder::new(packed_data, &config);
|
||||
let mut contexts = ContextState::new((1 + 255) * config.parity_contexts + 1 + 64 + 64, &config);
|
||||
let mut result = vec![];
|
||||
let mut offset = 0;
|
||||
let mut offset = usize::MAX;
|
||||
let mut position = 0usize;
|
||||
let mut prev_was_match = false;
|
||||
let mut margin = 0isize;
|
||||
|
||||
fn decode_length(
|
||||
decoder: &mut RansDecoder,
|
||||
contexts: &mut ContextState,
|
||||
mut context_index: usize,
|
||||
config: &Config,
|
||||
) -> usize {
|
||||
) -> Result<usize, UnpackError> {
|
||||
let mut length = 0;
|
||||
let mut bit_pos = 0;
|
||||
while decoder.decode_with_context(&mut contexts.context_mut(context_index))
|
||||
while decoder.decode_with_context(&mut contexts.context_mut(context_index))?
|
||||
== config.continue_value_bit
|
||||
{
|
||||
length |= (decoder.decode_with_context(&mut contexts.context_mut(context_index + 1))
|
||||
length |= (decoder.decode_with_context(&mut contexts.context_mut(context_index + 1))?
|
||||
as usize)
|
||||
<< bit_pos;
|
||||
bit_pos += 1;
|
||||
if bit_pos >= 32 {
|
||||
return Err(UnpackError::ValueOverflow);
|
||||
}
|
||||
context_index += 2;
|
||||
}
|
||||
length | (1 << bit_pos)
|
||||
Ok(length | (1 << bit_pos))
|
||||
}
|
||||
|
||||
loop {
|
||||
let literal_base = result.len() % config.parity_contexts * 256;
|
||||
if decoder.decode_with_context(&mut contexts.context_mut(literal_base))
|
||||
margin = margin.max(position as isize - decoder.pos() as isize);
|
||||
let literal_base = position % config.parity_contexts * 256;
|
||||
if decoder.decode_with_context(&mut contexts.context_mut(literal_base))?
|
||||
== config.is_match_bit
|
||||
{
|
||||
if config.no_repeated_offsets
|
||||
|| prev_was_match
|
||||
|| decoder
|
||||
.decode_with_context(&mut contexts.context_mut(256 * config.parity_contexts))
|
||||
.decode_with_context(&mut contexts.context_mut(256 * config.parity_contexts))?
|
||||
== config.new_offset_bit
|
||||
{
|
||||
offset = decode_length(
|
||||
@@ -167,7 +214,7 @@ pub fn unpack(packed_data: &[u8], config: Config) -> Vec<u8> {
|
||||
&mut contexts,
|
||||
256 * config.parity_contexts + 1,
|
||||
&config,
|
||||
) - 1;
|
||||
)? - if config.eof_in_length { 0 } else { 1 };
|
||||
if offset == 0 {
|
||||
break;
|
||||
}
|
||||
@@ -177,24 +224,49 @@ pub fn unpack(packed_data: &[u8], config: Config) -> Vec<u8> {
|
||||
&mut contexts,
|
||||
256 * config.parity_contexts + 65,
|
||||
&config,
|
||||
);
|
||||
for _ in 0..length {
|
||||
result.push(result[result.len() - offset]);
|
||||
)?;
|
||||
if config.eof_in_length && length == 1 {
|
||||
break;
|
||||
}
|
||||
if offset > position {
|
||||
return Err(UnpackError::OffsetOutOfRange { offset, position });
|
||||
}
|
||||
if let Some(ref mut result) = result {
|
||||
for _ in 0..length {
|
||||
if result.len() < max_size {
|
||||
result.push(result[result.len() - offset]);
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
position += length;
|
||||
prev_was_match = true;
|
||||
} else {
|
||||
let mut context_index = 1;
|
||||
let mut byte = 0;
|
||||
for i in (0..8).rev() {
|
||||
let bit = decoder
|
||||
.decode_with_context(&mut contexts.context_mut(literal_base + context_index));
|
||||
.decode_with_context(&mut contexts.context_mut(literal_base + context_index))?;
|
||||
context_index = (context_index << 1) | bit as usize;
|
||||
byte |= (bit as u8) << i;
|
||||
}
|
||||
if let Some(ref mut result) = result {
|
||||
if result.len() < max_size {
|
||||
result.push(byte);
|
||||
}
|
||||
}
|
||||
position += 1;
|
||||
prev_was_match = false;
|
||||
}
|
||||
}
|
||||
|
||||
result
|
||||
if position > max_size {
|
||||
return Err(UnpackError::OverSize {
|
||||
size: position,
|
||||
limit: max_size,
|
||||
});
|
||||
}
|
||||
|
||||
Ok(margin + decoder.pos() as isize - position as isize)
|
||||
}
|
||||
|
||||
+29
-5
@@ -8,9 +8,11 @@ fn main() -> Result<()> {
|
||||
let mut config = upkr::Config::default();
|
||||
let mut reverse = false;
|
||||
let mut unpack = false;
|
||||
let mut calculate_margin = false;
|
||||
let mut level = 2;
|
||||
let mut infile: Option<PathBuf> = None;
|
||||
let mut outfile: Option<PathBuf> = None;
|
||||
let mut max_unpacked_size = 512 * 1024 * 1024;
|
||||
|
||||
let mut parser = lexopt::Parser::from_env();
|
||||
while let Some(arg) = parser.next()? {
|
||||
@@ -29,22 +31,31 @@ fn main() -> Result<()> {
|
||||
config.bitstream_is_big_endian = true;
|
||||
}
|
||||
Long("no-repeated-offsets") => config.no_repeated_offsets = true,
|
||||
Long("eof-in-length") => config.eof_in_length = true,
|
||||
|
||||
Long("max-offset") => config.max_offset = parser.value()?.parse()?,
|
||||
Long("max-length") => config.max_length = parser.value()?.parse()?,
|
||||
|
||||
Long("z80") => {
|
||||
config.use_bitstream = true;
|
||||
config.bitstream_is_big_endian = true;
|
||||
config.invert_bit_encoding = true;
|
||||
config.simplified_prob_update = true;
|
||||
level = 9;
|
||||
}
|
||||
Long("x86") => {
|
||||
config.use_bitstream = true;
|
||||
config.continue_value_bit = false;
|
||||
config.is_match_bit = false;
|
||||
config.new_offset_bit = false;
|
||||
}
|
||||
|
||||
Short('u') | Long("unpack") => unpack = true,
|
||||
Long("margin") => calculate_margin = true,
|
||||
Short('l') | Long("level") => level = parser.value()?.parse()?,
|
||||
Short(n) if n.is_ascii_digit() => level = n as u8 - b'0',
|
||||
Short('h') | Long("help") => print_help(0),
|
||||
Long("max-unpacked-size") => max_unpacked_size = parser.value()?.parse()?,
|
||||
Value(val) if infile.is_none() => infile = Some(val.try_into()?),
|
||||
Value(val) if outfile.is_none() => outfile = Some(val.try_into()?),
|
||||
_ => return Err(arg.unexpected().into()),
|
||||
@@ -76,7 +87,7 @@ fn main() -> Result<()> {
|
||||
process::exit(1);
|
||||
}
|
||||
|
||||
if !unpack {
|
||||
if !unpack && !calculate_margin {
|
||||
let mut data = vec![];
|
||||
File::open(infile)?.read_to_end(&mut data)?;
|
||||
if reverse {
|
||||
@@ -88,7 +99,7 @@ fn main() -> Result<()> {
|
||||
let mut packed_data = upkr::pack(
|
||||
&data,
|
||||
level,
|
||||
config,
|
||||
&config,
|
||||
Some(&mut |pos| {
|
||||
pb.set(pos as u64);
|
||||
}),
|
||||
@@ -112,12 +123,17 @@ fn main() -> Result<()> {
|
||||
if reverse {
|
||||
data.reverse();
|
||||
}
|
||||
let mut unpacked_data = upkr::unpack(&data, config);
|
||||
if unpack {
|
||||
let mut unpacked_data = upkr::unpack(&data, &config, max_unpacked_size)?;
|
||||
if reverse {
|
||||
unpacked_data.reverse();
|
||||
}
|
||||
File::create(outfile)?.write_all(&unpacked_data)?;
|
||||
}
|
||||
if calculate_margin {
|
||||
println!("{}", upkr::calculate_margin(&data, &config)?);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
@@ -126,13 +142,18 @@ fn print_help(exit_code: i32) -> ! {
|
||||
eprintln!("Usage:");
|
||||
eprintln!(" upkr [-l level(0-9)] [config options] <infile> [<outfile>]");
|
||||
eprintln!(" upkr -u [config options] <infile> [<outfile>]");
|
||||
eprintln!(" upkr --margin [config options] <infile>");
|
||||
eprintln!();
|
||||
eprintln!(" -l, --level N compression level 0-9");
|
||||
eprintln!(" -0, ..., -9 short form for setting compression level");
|
||||
eprintln!(" -u, --unpack unpack infile");
|
||||
eprintln!(" --margin calculate margin for overlapped unpacking of a packed file");
|
||||
eprintln!();
|
||||
eprintln!("Config presets for specific unpackers:");
|
||||
eprintln!(" --z80 --big-endian-bitstream --invert-bit-encoding --simplified-prob-update");
|
||||
eprintln!(" --x86 --bitstream --invert-is-match-bit --invert-continue-value-bit");
|
||||
eprintln!(" --z80 --big-endian-bitstream --invert-bit-encoding --simplified-prob-update -9");
|
||||
eprintln!(
|
||||
" --x86 --bitstream --invert-is-match-bit --invert-continue-value-bit --invert-new-offset-bit"
|
||||
);
|
||||
eprintln!();
|
||||
eprintln!("Config options (need to match when packing/unpacking):");
|
||||
eprintln!(" -b, --bitstream bitstream mode");
|
||||
@@ -147,5 +168,8 @@ fn print_help(exit_code: i32) -> ! {
|
||||
eprintln!(" --simplified-prob-update");
|
||||
eprintln!(" --big-endian-bitstream (implies --bitstream)");
|
||||
eprintln!(" --no-repeated-offsets");
|
||||
eprintln!(" --eof-in-length");
|
||||
eprintln!(" --max-offset N");
|
||||
eprintln!(" --max-length N");
|
||||
process::exit(exit_code);
|
||||
}
|
||||
|
||||
+10
-1
@@ -105,11 +105,15 @@ fn parse(
|
||||
cost_counter: &mut CostCounter,
|
||||
pos: usize,
|
||||
offset: usize,
|
||||
length: usize,
|
||||
mut length: usize,
|
||||
arrival: &Arrival,
|
||||
max_arrivals: usize,
|
||||
config: &crate::Config,
|
||||
) {
|
||||
if length < config.min_length() {
|
||||
return;
|
||||
}
|
||||
length = length.min(config.max_length);
|
||||
cost_counter.reset();
|
||||
let mut state = arrival.state.clone();
|
||||
let op = lz::Op::Match {
|
||||
@@ -183,6 +187,7 @@ fn parse(
|
||||
for m in match_finder.matches(pos) {
|
||||
closest_match = Some(closest_match.unwrap_or(0).max(m.pos));
|
||||
let offset = pos - m.pos;
|
||||
if offset <= encoding_config.max_offset {
|
||||
found_last_offset |= offset as u32 == arrival.state.last_offset();
|
||||
add_match(
|
||||
&mut arrivals,
|
||||
@@ -198,6 +203,7 @@ fn parse(
|
||||
break 'arrival_loop;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let mut near_matches_left = config.num_near_matches;
|
||||
let mut match_pos = last_seen[data[pos] as usize];
|
||||
@@ -206,6 +212,9 @@ fn parse(
|
||||
&& closest_match.iter().all(|p| *p < match_pos)
|
||||
{
|
||||
let offset = pos - match_pos;
|
||||
if offset > encoding_config.max_offset {
|
||||
break;
|
||||
}
|
||||
let length = match_length(offset);
|
||||
assert!(length > 0);
|
||||
add_match(
|
||||
|
||||
+27
-10
@@ -1,4 +1,5 @@
|
||||
use crate::{context_state::Context, Config};
|
||||
use thiserror::Error;
|
||||
|
||||
pub const PROB_BITS: u32 = 8;
|
||||
pub const ONE_PROB: u32 = 1 << PROB_BITS;
|
||||
@@ -149,6 +150,7 @@ impl EntropyCoder for CostCounter {
|
||||
|
||||
pub struct RansDecoder<'a> {
|
||||
data: &'a [u8],
|
||||
pos: usize,
|
||||
state: u32,
|
||||
use_bitstream: bool,
|
||||
byte: u8,
|
||||
@@ -159,10 +161,15 @@ pub struct RansDecoder<'a> {
|
||||
|
||||
const PROB_MASK: u32 = ONE_PROB - 1;
|
||||
|
||||
#[derive(Debug, Error)]
|
||||
#[error("Unexpected end of input")]
|
||||
pub struct UnexpectedEOF;
|
||||
|
||||
impl<'a> RansDecoder<'a> {
|
||||
pub fn new(data: &'a [u8], config: &Config) -> RansDecoder<'a> {
|
||||
RansDecoder {
|
||||
data,
|
||||
pos: 0,
|
||||
state: 0,
|
||||
use_bitstream: config.use_bitstream,
|
||||
byte: 0,
|
||||
@@ -172,19 +179,26 @@ impl<'a> RansDecoder<'a> {
|
||||
}
|
||||
}
|
||||
|
||||
pub fn decode_with_context(&mut self, context: &mut Context) -> bool {
|
||||
let bit = self.decode_bit(context.prob());
|
||||
context.update(bit);
|
||||
bit
|
||||
pub fn pos(&self) -> usize {
|
||||
self.pos
|
||||
}
|
||||
|
||||
pub fn decode_bit(&mut self, prob: u16) -> bool {
|
||||
pub fn decode_with_context(&mut self, context: &mut Context) -> Result<bool, UnexpectedEOF> {
|
||||
let bit = self.decode_bit(context.prob())?;
|
||||
context.update(bit);
|
||||
Ok(bit)
|
||||
}
|
||||
|
||||
pub fn decode_bit(&mut self, prob: u16) -> Result<bool, UnexpectedEOF> {
|
||||
let prob = prob as u32;
|
||||
if self.use_bitstream {
|
||||
while self.state < 32768 {
|
||||
if self.bits_left == 0 {
|
||||
self.byte = self.data[0];
|
||||
self.data = &self.data[1..];
|
||||
if self.pos >= self.data.len() {
|
||||
return Err(UnexpectedEOF);
|
||||
}
|
||||
self.byte = self.data[self.pos];
|
||||
self.pos += 1;
|
||||
self.bits_left = 8;
|
||||
}
|
||||
if self.bitstream_is_big_endian {
|
||||
@@ -198,8 +212,11 @@ impl<'a> RansDecoder<'a> {
|
||||
}
|
||||
} else {
|
||||
while self.state < 4096 {
|
||||
self.state = (self.state << 8) | self.data[0] as u32;
|
||||
self.data = &self.data[1..];
|
||||
if self.pos >= self.data.len() {
|
||||
return Err(UnexpectedEOF);
|
||||
}
|
||||
self.state = (self.state << 8) | self.data[self.pos] as u32;
|
||||
self.pos += 1;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -212,6 +229,6 @@ impl<'a> RansDecoder<'a> {
|
||||
};
|
||||
self.state = prob * (self.state >> PROB_BITS) + (self.state & PROB_MASK) - start;
|
||||
|
||||
bit ^ self.invert_bit_encoding
|
||||
Ok(bit ^ self.invert_bit_encoding)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
*.bin
|
||||
*.tap
|
||||
*.lst
|
||||
@@ -0,0 +1,11 @@
|
||||
all: unpack.bin example/example.sna
|
||||
|
||||
# binary is positioned from ORG 0, not usable, just assembling to verify the syntax
|
||||
unpack.bin: unpack.asm
|
||||
sjasmplus --msg=war --lst --lstlab=sort --raw=unpack.bin unpack.asm
|
||||
|
||||
example/example.sna: unpack.asm example/example.asm
|
||||
cd example && sjasmplus --msg=war --lst --lstlab=sort example.asm
|
||||
|
||||
clean:
|
||||
$(RM) unpack.bin unpack.lst example/example.sna example/example.lst
|
||||
@@ -0,0 +1,100 @@
|
||||
;; Example using upkr depacker for screens slideshow
|
||||
OPT --syntax=abf
|
||||
DEVICE ZXSPECTRUM48,$8FFF
|
||||
|
||||
ORG $9000
|
||||
;; forward example data
|
||||
compressed_scr_files.fwd: ; border color byte + upkr-packed .scr file
|
||||
DB 1
|
||||
INCBIN "screens/Grongy - ZX Spectrum (2022).scr.upk"
|
||||
DB 7
|
||||
INCBIN "screens/Schafft - Poison (2017).scr.upk"
|
||||
DB 0
|
||||
INCBIN "screens/diver - Mercenary 4. The Heaven's Devil (2014) (Forever 2014 Olympic Edition, 1).scr.upk"
|
||||
DB 6
|
||||
INCBIN "screens/diver - Back to Bjork (2015).scr.upk"
|
||||
.e:
|
||||
;; backward example data (unpacker goes from the end of the data!)
|
||||
compressed_scr_files.rwd.e: EQU $-1 ; the final IX will point one byte ahead of "$" here
|
||||
INCBIN "screens.reversed/diver - Back to Bjork (2015).scr.upk"
|
||||
DB 6
|
||||
INCBIN "screens.reversed/diver - Mercenary 4. The Heaven's Devil (2014) (Forever 2014 Olympic Edition, 1).scr.upk"
|
||||
DB 0
|
||||
INCBIN "screens.reversed/Schafft - Poison (2017).scr.upk"
|
||||
DB 7
|
||||
INCBIN "screens.reversed/Grongy - ZX Spectrum (2022).scr.upk"
|
||||
compressed_scr_files.rwd: ; border color byte + upkr-packed .scr file (backward)
|
||||
DB 1
|
||||
|
||||
start:
|
||||
di
|
||||
; OPT --zxnext
|
||||
; nextreg 7,3 ; ZX Next: switch to 28Mhz
|
||||
|
||||
;;; FORWARD packed/unpacked data demo
|
||||
ld ix,compressed_scr_files.fwd
|
||||
.slideshow_loop.fwd:
|
||||
; set BORDER for next image
|
||||
ld a,(ix)
|
||||
inc ix
|
||||
out (254),a
|
||||
; call unpack of next image directly into VRAM
|
||||
ld de,$4000 ; target VRAM
|
||||
exx
|
||||
; IX = packed data, DE' = destination ($4000)
|
||||
; returned IX will point right after the packed data
|
||||
call fwd.upkr.unpack
|
||||
; do some busy loop with CPU to delay between images
|
||||
call delay
|
||||
; check if all images were displayed, loop around from first one then
|
||||
ld a,ixl
|
||||
cp low compressed_scr_files.fwd.e
|
||||
jr nz,.slideshow_loop.fwd
|
||||
|
||||
;;; BACKWARD packed/unpacked data demo
|
||||
ld ix,compressed_scr_files.rwd
|
||||
.slideshow_loop.rwd:
|
||||
; set BORDER for next image
|
||||
ld a,(ix)
|
||||
dec ix
|
||||
out (254),a
|
||||
; call unpack of next image directly into VRAM
|
||||
ld de,$5AFF ; target VRAM
|
||||
exx
|
||||
; IX = packed data, DE' = destination
|
||||
; returned IX will point right ahead of the packed data
|
||||
call rwd.upkr.unpack
|
||||
; do some busy loop with CPU to delay between images
|
||||
call delay
|
||||
; check if all images were displayed, loop around from first one then
|
||||
ld a,ixl
|
||||
cp low compressed_scr_files.rwd.e
|
||||
jr nz,.slideshow_loop.rwd
|
||||
|
||||
jr start
|
||||
|
||||
delay:
|
||||
ld bc,$AA00
|
||||
.delay:
|
||||
.8 ex (sp),ix
|
||||
dec c
|
||||
jr nz,.delay
|
||||
djnz .delay
|
||||
ret
|
||||
|
||||
; include the depacker library, optionally putting probs array buffer near end of RAM
|
||||
DEFINE UPKR_PROBS_ORIGIN $FA00 ; if not defined, array will be put after unpack code
|
||||
|
||||
MODULE fwd
|
||||
INCLUDE "../unpack.asm"
|
||||
ENDMODULE
|
||||
|
||||
MODULE rwd
|
||||
DEFINE BACKWARDS_UNPACK ; defined to build backwards unpack
|
||||
; initial IX points at last byte of compressed data
|
||||
; initial DE' points at last byte of unpacked data
|
||||
|
||||
INCLUDE "../unpack.asm"
|
||||
ENDMODULE
|
||||
|
||||
SAVESNA "example.sna",start
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
BIN
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
@@ -0,0 +1,32 @@
|
||||
Z80 asm implementation of C unpacker, code-size focused (not performance).
|
||||
|
||||
**ONLY BITSTREAM** variant is currently supported, make sure to use "-b" in packer.
|
||||
|
||||
The project is expected to further evolve, including possible changes to binary format, this is
|
||||
initial version of Z80 unpacker to explore if/how it works and how it can be improved further.
|
||||
|
||||
(copy full packer+depacker source to your project if you plan to use it, as future revisions
|
||||
may be incompatible with files you will produce with current version)
|
||||
|
||||
Asm syntax is z00m's sjasmplus: https://github.com/z00m128/sjasmplus
|
||||
|
||||
Backward direction unpacker added as compile-time option, see example for both forward/backward
|
||||
depacker in action.
|
||||
|
||||
The packed/unpacked data-overlap has to be tested per-case, in worst case the packed data
|
||||
may need even more than 7 bytes to unpack final byte, but usually 1-4 bytes may suffice.
|
||||
|
||||
TODO:
|
||||
- build bigger corpus of test data to benchmark future changes in algorithm/format (example and zx48.rom was used to do initial tests)
|
||||
- maybe try to beat double-loop `decode_number` with different encoding format
|
||||
- (@ped7g) Z80N version of unpacker for ZX Next devs
|
||||
- (@exoticorn) add Z80 specific packer (to avoid confusion with original MicroW8 variant), and land it all to master branch, maybe in "z80" directory or something? (and overall decide how to organise+merge this upstream into main repo)
|
||||
- (@exoticorn) add to packer output with possible packed/unpacked region overlap
|
||||
|
||||
DONE:
|
||||
* review non-bitstream variant, if it's feasible to try to implement it with Z80
|
||||
- Ped7g: IMHO nope, the 12b x 8b MUL code would probably quickly cancel any gains from the simpler state update
|
||||
* review first implementation to identify weak spots where the implementation can be shorter+faster
|
||||
with acceptable small changes to the format
|
||||
- Ped7g: the decode_bit settled down and now doesn't feel so confused and redundant, the code seems pretty on point to me, no obvious simplification from format change
|
||||
- Ped7g: the decode_number double-loop is surprisingly resilient, especially in terms of code size I failed to beat it, speed wise only negligible gains
|
||||
@@ -0,0 +1,381 @@
|
||||
;; https://github.com/exoticorn/upkr/blob/z80/c_unpacker/unpack.c - original C implementation
|
||||
;; C source in comments ahead of asm - the C macros are removed to keep only bitstream variant
|
||||
;;
|
||||
;; initial version by Peter "Ped" Helcmanovsky (C) 2022, licensed same as upkr project ("unlicensed")
|
||||
;; to assemble use z00m's sjasmplus: https://github.com/z00m128/sjasmplus
|
||||
;;
|
||||
;; you can define UPKR_PROBS_ORIGIN to specific 256 byte aligned address for probs array (320 bytes),
|
||||
;; otherwise it will be positioned after the unpacker code (256 aligned)
|
||||
;;
|
||||
;; public API:
|
||||
;;
|
||||
;; upkr.unpack
|
||||
;; IN: IX = packed data, DE' (shadow DE) = destination
|
||||
;; OUT: IX = after packed data
|
||||
;; modifies: all registers except IY, requires 10 bytes of stack space
|
||||
;;
|
||||
|
||||
; DEFINE BACKWARDS_UNPACK ; uncomment to build backwards depacker (write_ptr--, upkr_data_ptr--)
|
||||
; initial IX points at last byte of compressed data
|
||||
; initial DE' points at last byte of unpacked data
|
||||
|
||||
; DEFINE UPKR_UNPACK_SPEED ; uncomment to get larger but faster unpack routine
|
||||
|
||||
; code size hint: if you put probs array just ahead of BASIC entry point, you will get BC
|
||||
; initialised to probs.e by BASIC `USR` command and you can remove it from unpack init (-3B)
|
||||
|
||||
OPT push reset --syntax=abf
|
||||
MODULE upkr
|
||||
|
||||
NUMBER_BITS EQU 16+15 ; context-bits per offset/length (16+15 for 16bit offsets/pointers)
|
||||
; numbers (offsets/lengths) are encoded like: 1a1b1c1d1e0 = 0000'0000'001e'dbca
|
||||
|
||||
/*
|
||||
u8* upkr_data_ptr;
|
||||
u8 upkr_probs[1 + 255 + 1 + 2*32 + 2*32];
|
||||
u16 upkr_state;
|
||||
u8 upkr_current_byte;
|
||||
int upkr_bits_left;
|
||||
|
||||
int upkr_unpack(void* destination, void* compressed_data) {
|
||||
upkr_data_ptr = (u8*)compressed_data;
|
||||
upkr_state = 0;
|
||||
upkr_bits_left = 0;
|
||||
for(int i = 0; i < sizeof(upkr_probs); ++i)
|
||||
upkr_probs[i] = 128;
|
||||
|
||||
u8* write_ptr = (u8*)destination;
|
||||
|
||||
int prev_was_match = 0;
|
||||
int offset = 0;
|
||||
for(;;) {
|
||||
if(upkr_decode_bit(0)) {
|
||||
if(prev_was_match || upkr_decode_bit(256)) {
|
||||
offset = upkr_decode_length(257) - 1;
|
||||
if(offset == 0) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
int length = upkr_decode_length(257 + 64);
|
||||
while(length--) {
|
||||
*write_ptr = write_ptr[-offset];
|
||||
++write_ptr;
|
||||
}
|
||||
prev_was_match = 1;
|
||||
} else {
|
||||
int byte = 1;
|
||||
while(byte < 256) {
|
||||
int bit = upkr_decode_bit(byte);
|
||||
byte = (byte << 1) + bit;
|
||||
}
|
||||
*write_ptr++ = byte;
|
||||
prev_was_match = 0;
|
||||
}
|
||||
}
|
||||
|
||||
return write_ptr - (u8*)destination;
|
||||
}
|
||||
*/
|
||||
; IN: IX = compressed_data, DE' = destination
|
||||
unpack:
|
||||
; ** reset probs to 0x80, also reset HL (state) to zero, and set BC to probs+context 0
|
||||
ld hl,probs.c>>1
|
||||
ld bc,probs.e
|
||||
ld a,$80
|
||||
.reset_probs:
|
||||
dec bc
|
||||
ld (bc),a ; will overwrite one extra byte after the array because of odd length
|
||||
dec bc
|
||||
ld (bc),a
|
||||
dec l
|
||||
jr nz,.reset_probs
|
||||
exa
|
||||
; BC = probs (context_index 0), state HL = 0, A' = 0x80 (no source bits left in upkr_current_byte)
|
||||
|
||||
; ** main loop to decompress data
|
||||
; D = prev_was_match = uninitialised, literal is expected first => will reset D to "false"
|
||||
; values for false/true of prev_was_match are: false = high(probs), true = 1 + high(probs)
|
||||
.decompress_data:
|
||||
ld c,0
|
||||
call decode_bit ; if(upkr_decode_bit(0))
|
||||
jr c,.copy_chunk
|
||||
|
||||
; * extract byte from compressed data (literal)
|
||||
inc c ; C = byte = 1 (and also context_index)
|
||||
.decode_byte:
|
||||
call decode_bit ; bit = upkr_decode_bit(byte);
|
||||
rl c ; byte = (byte << 1) + bit;
|
||||
jr nc,.decode_byte ; while(byte < 256)
|
||||
ld a,c
|
||||
exx
|
||||
ld (de),a ; *write_ptr++ = byte;
|
||||
IFNDEF BACKWARDS_UNPACK : inc de : ELSE : dec de : ENDIF
|
||||
exx
|
||||
ld d,b ; prev_was_match = false
|
||||
jr .decompress_data
|
||||
|
||||
; * copy chunk of already decompressed data (match)
|
||||
.copy_chunk:
|
||||
ld a,b
|
||||
inc b ; context_index = 256
|
||||
; if(prev_was_match || upkr_decode_bit(256)) {
|
||||
; offset = upkr_decode_length(257) - 1;
|
||||
; if (0 == offset) break;
|
||||
; }
|
||||
cp d ; CF = prev_was_match
|
||||
call nc,decode_bit ; if not prev_was_match, then upkr_decode_bit(256)
|
||||
jr nc,.keep_offset ; if neither, keep old offset
|
||||
call decode_number ; context_index is already 257-1 as needed by decode_number
|
||||
dec de ; offset = upkr_decode_length(257) - 1;
|
||||
ld a,d
|
||||
or e
|
||||
ret z ; if(offset == 0) break
|
||||
ld (.offset),de
|
||||
.keep_offset:
|
||||
; int length = upkr_decode_length(257 + 64);
|
||||
; while(length--) {
|
||||
; *write_ptr = write_ptr[-offset];
|
||||
; ++write_ptr;
|
||||
; }
|
||||
; prev_was_match = 1;
|
||||
ld c,low(257 + NUMBER_BITS - 1) ; context_index to second "number" set for lengths decoding
|
||||
call decode_number ; length = upkr_decode_length(257 + 64);
|
||||
push de
|
||||
exx
|
||||
IFNDEF BACKWARDS_UNPACK
|
||||
; forward unpack (write_ptr++, upkr_data_ptr++)
|
||||
ld h,d ; DE = write_ptr
|
||||
ld l,e
|
||||
.offset+*: ld bc,0
|
||||
sbc hl,bc ; CF=0 from decode_number ; HL = write_ptr - offset
|
||||
pop bc ; BC = length
|
||||
ldir
|
||||
ELSE
|
||||
; backward unpack (write_ptr--, upkr_data_ptr--)
|
||||
.offset+*: ld hl,0
|
||||
add hl,de ; HL = write_ptr + offset
|
||||
pop bc ; BC = length
|
||||
lddr
|
||||
ENDIF
|
||||
exx
|
||||
ld d,b ; prev_was_match = true
|
||||
djnz .decompress_data ; adjust context_index back to 0..255 range, go to main loop
|
||||
|
||||
/*
|
||||
int upkr_decode_bit(int context_index) {
|
||||
while(upkr_state < 32768) {
|
||||
if(upkr_bits_left == 0) {
|
||||
upkr_current_byte = *upkr_data_ptr++;
|
||||
upkr_bits_left = 8;
|
||||
}
|
||||
upkr_state = (upkr_state << 1) + (upkr_current_byte >> 7);
|
||||
upkr_current_byte <<= 1;
|
||||
--upkr_bits_left;
|
||||
}
|
||||
|
||||
int prob = upkr_probs[context_index];
|
||||
int bit = (upkr_state & 255) >= prob ? 1 : 0;
|
||||
|
||||
int prob_offset = 16;
|
||||
int state_offset = 0;
|
||||
int state_scale = prob;
|
||||
if(bit) {
|
||||
state_offset = -prob;
|
||||
state_scale = 256 - prob;
|
||||
prob_offset = 0;
|
||||
}
|
||||
upkr_state = state_offset + state_scale * (upkr_state >> 8) + (upkr_state & 255);
|
||||
upkr_probs[context_index] = prob_offset + prob - ((prob + 8) >> 4);
|
||||
|
||||
return bit;
|
||||
}
|
||||
*/
|
||||
inc_c_decode_bit:
|
||||
; ++low(context_index) before decode_bit (to get -1B by two calls in decode_number)
|
||||
inc c
|
||||
decode_bit:
|
||||
; HL = upkr_state
|
||||
; IX = upkr_data_ptr
|
||||
; BC = probs+context_index
|
||||
; A' = upkr_current_byte (!!! init to 0x80 at start, not 0x00)
|
||||
; preserves DE
|
||||
; ** while (state < 32768) - initial check
|
||||
push de
|
||||
bit 7,h
|
||||
jr nz,.state_b15_set
|
||||
exa
|
||||
; ** while body
|
||||
.state_b15_zero:
|
||||
; HL = upkr_state
|
||||
; IX = upkr_data_ptr
|
||||
; A = upkr_current_byte (init to 0x80 at start, not 0x00)
|
||||
add a,a ; upkr_current_byte <<= 1; // and testing if(upkr_bits_left == 0)
|
||||
jr nz,.has_bit ; CF=data, ZF=0 -> some bits + stop bit still available
|
||||
; CF=1 (by stop bit)
|
||||
ld a,(ix)
|
||||
IFNDEF BACKWARDS_UNPACK : inc ix : ELSE : dec ix : ENDIF ; upkr_current_byte = *upkr_data_ptr++;
|
||||
adc a,a ; CF=data, b0=1 as new stop bit
|
||||
.has_bit:
|
||||
adc hl,hl ; upkr_state = (upkr_state << 1) + (upkr_current_byte >> 7);
|
||||
jp p,.state_b15_zero ; while (state < 32768)
|
||||
exa
|
||||
; ** set "bit"
|
||||
.state_b15_set:
|
||||
ld a,(bc) ; A = upkr_probs[context_index]
|
||||
dec a ; prob is in ~7..249 range, never zero, safe to -1
|
||||
cp l ; CF = bit = prob-1 < (upkr_state & 255) <=> prob <= (upkr_state & 255)
|
||||
inc a
|
||||
; ** adjust state
|
||||
push bc
|
||||
ld c,l ; C = (upkr_state & 255); (preserving the value)
|
||||
push af
|
||||
jr nc,.bit_is_0
|
||||
neg ; A = -prob == (256-prob), CF=1 preserved
|
||||
.bit_is_0:
|
||||
ld d,0
|
||||
ld e,a ; DE = state_scale ; prob || (256-prob)
|
||||
ld l,d ; H:L = (upkr_state>>8) : 0
|
||||
|
||||
IFNDEF UPKR_UNPACK_SPEED
|
||||
|
||||
;; looped MUL for minimum unpack size
|
||||
ld b,8 ; counter
|
||||
.mulLoop:
|
||||
add hl,hl
|
||||
jr nc,.mul0
|
||||
add hl,de
|
||||
.mul0:
|
||||
djnz .mulLoop ; until HL = state_scale * (upkr_state>>8), also BC becomes (upkr_state & 255)
|
||||
|
||||
ELSE
|
||||
|
||||
;;; unrolled MUL for better performance, +25 bytes unpack size
|
||||
ld b,d
|
||||
DUP 8
|
||||
add hl,hl
|
||||
jr nc,0_f
|
||||
add hl,de
|
||||
0:
|
||||
EDUP
|
||||
|
||||
ENDIF
|
||||
|
||||
add hl,bc ; HL = state_scale * (upkr_state >> 8) + (upkr_state & 255)
|
||||
pop af ; restore prob and CF=bit
|
||||
jr nc,.bit_is_0_2
|
||||
dec d ; DE = -prob (also D = bit ? $FF : $00)
|
||||
add hl,de ; HL += -prob
|
||||
; ^ this always preserves CF=1, because (state>>8) >= 128, state_scale: 7..250, prob: 7..250,
|
||||
; so 7*128 > 250 and thus edge case `ADD hl=(7*128+0),de=(-250)` => CF=1
|
||||
.bit_is_0_2:
|
||||
; *** adjust probs[context_index]
|
||||
rra ; + (bit<<4) ; part of -prob_offset, needs another -16
|
||||
and $FC ; clear/keep correct bits to get desired (prob>>4) + extras, CF=0
|
||||
rra
|
||||
rra
|
||||
rra ; A = (bit<<4) + (prob>>4), CF=(prob & 8)
|
||||
adc a,-16 ; A = (bit<<4) - 16 + ((prob + 8)>>4) ; -prob_offset = (bit<<4) - 16
|
||||
ld e,a
|
||||
pop bc
|
||||
ld a,(bc) ; A = prob (cheaper + shorter to re-read again from memory)
|
||||
sub e ; A = 16 - (bit<<4) + prob - ((prob + 8)>>4) ; = prob_offset + prob - ((prob + 8)>>4)
|
||||
ld (bc),a ; probs[context_index] = prob_offset + prob - ((prob + 8) >> 4);
|
||||
add a,d ; restore CF = bit (D = bit ? $FF : $00 && A > 0)
|
||||
pop de
|
||||
ret
|
||||
|
||||
/*
|
||||
int upkr_decode_length(int context_index) {
|
||||
int length = 0;
|
||||
int bit_pos = 0;
|
||||
while(upkr_decode_bit(context_index)) {
|
||||
length |= upkr_decode_bit(context_index + 1) << bit_pos++;
|
||||
context_index += 2;
|
||||
}
|
||||
return length | (1 << bit_pos);
|
||||
}
|
||||
*/
|
||||
decode_number:
|
||||
; HL = upkr_state
|
||||
; IX = upkr_data_ptr
|
||||
; BC = probs+context_index-1
|
||||
; A' = upkr_current_byte (!!! init to 0x80 at start, not 0x00)
|
||||
; return length in DE, CF=0
|
||||
ld de,$FFFF ; length = 0 with positional-stop-bit
|
||||
or a ; CF=0 to skip getting data bit and use only `rr d : rr e` to fix init DE
|
||||
.loop:
|
||||
call c,inc_c_decode_bit ; get data bit, context_index + 1 / if CF=0 just add stop bit into DE init
|
||||
rr d
|
||||
rr e ; DE = length = (length >> 1) | (bit << 15);
|
||||
call inc_c_decode_bit ; context_index += 2
|
||||
jr c,.loop
|
||||
.fix_bit_pos:
|
||||
ccf ; NC will become this final `| (1 << bit_pos)` bit
|
||||
rr d
|
||||
rr e
|
||||
jr c,.fix_bit_pos ; until stop bit is reached (all bits did land to correct position)
|
||||
ret ; return with CF=0 (important for unpack routine)
|
||||
|
||||
DISPLAY "upkr.unpack total size: ",/D,$-unpack
|
||||
|
||||
; reserve space for probs array without emitting any machine code (using only EQU)
|
||||
|
||||
IFDEF UPKR_PROBS_ORIGIN ; if specific address is defined by user, move probs array there
|
||||
probs: EQU ((UPKR_PROBS_ORIGIN) + 255) & -$100 ; probs array aligned to 256
|
||||
ELSE
|
||||
probs: EQU ($ + 255) & -$100 ; probs array aligned to 256
|
||||
ENDIF
|
||||
.real_c: EQU 1 + 255 + 1 + 2*NUMBER_BITS ; real size of probs array
|
||||
.c: EQU (.real_c + 1) & -2 ; padding to even size (required by init code)
|
||||
.e: EQU probs + .c
|
||||
|
||||
DISPLAY "upkr.unpack probs array placed at: ",/A,probs,",\tsize: ",/A,probs.c
|
||||
|
||||
/*
|
||||
archived: negligibly faster but +6B longer decode_number variant using HL' and BC' to
|
||||
do `number|=(1<<bit_pos);` type of logic in single loop.
|
||||
*/
|
||||
; decode_number:
|
||||
; exx
|
||||
; ld bc,1
|
||||
; ld l,b
|
||||
; ld h,b ; HL = 0
|
||||
; .loop
|
||||
; exx
|
||||
; inc c
|
||||
; call decode_bit
|
||||
; jr nc,.done
|
||||
; inc c
|
||||
; call decode_bit
|
||||
; exx
|
||||
; jr nc,.b0
|
||||
; add hl,bc
|
||||
; .b0:
|
||||
; sla c
|
||||
; rl b
|
||||
; jr .loop
|
||||
; .done:
|
||||
; exx
|
||||
; add hl,bc
|
||||
; push hl
|
||||
; exx
|
||||
; pop de
|
||||
; ret
|
||||
|
||||
/*
|
||||
archived: possible LUT variant of updating probs value, requires 512-aligned 512B table (not tested)
|
||||
*/
|
||||
; code is replacing decode_bit from "; *** adjust probs[context_index]", followed by `ld (bc),a : add a,d ...`
|
||||
; ld c,a
|
||||
; ld a,high(probs_update_table)/2 ; must be 512 aligned
|
||||
; rla
|
||||
; ld b,a
|
||||
; ld a,(bc)
|
||||
; pop bc
|
||||
; -------------------------------------------
|
||||
; probs_update_table: EQU probs-512
|
||||
; -------------------------------------------
|
||||
; table generator is not obvious and probably not short either, 20+ bytes almost for sure, maybe even 30-40
|
||||
|
||||
ENDMODULE
|
||||
OPT pop
|
||||
Reference in New Issue
Block a user