more config options, unpack error handling, fuzzing

add --eof-in-length option
add parameter to print out margin for overlapped unpacking
2026-01-20 19:46:42 +01:00 · 2022-09-27 17:16:05 +02:00 · 2022-09-26 23:41:17 +02:00 · 2022-09-25 23:44:03 +02:00 · 2022-09-25 16:24:24 +02:00 · 2022-09-25 16:23:11 +02:00
13 changed files with 594 additions and 71 deletions
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -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]]
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "upkr"
-version = "0.2.0-pre1"
+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"
--- a/fuzz/.gitignore
+++ b/fuzz/.gitignore
@@ -0,0 +1,3 @@
+target
+corpus
+artifacts
--- a/fuzz/Cargo.lock
+++ b/fuzz/Cargo.lock
@@ -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"
--- a/fuzz/Cargo.toml
+++ b/fuzz/Cargo.toml
@@ -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
--- a/fuzz/fuzz_targets/all_configs.rs
+++ b/fuzz/fuzz_targets/all_configs.rs
@@ -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);
+});
--- a/fuzz/fuzz_targets/unpack.rs
+++ b/fuzz/fuzz_targets/unpack.rs
@@ -0,0 +1,6 @@
+#![no_main]
+use libfuzzer_sys::fuzz_target;
+
+fuzz_target!(|data: &[u8]| {
+    let _ = upkr::unpack(data, &upkr::Config::default(), 64 * 1024);
+});
--- a/src/greedy_packer.rs
+++ b/src/greedy_packer.rs
@@ -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,
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -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,
@@ -20,6 +21,12 @@ pub struct Config {

    pub bitstream_is_big_endian: bool,
    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 {
@@ -35,6 +42,22 @@ impl Default for Config {

            bitstream_is_big_endian: false,
            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
        }
    }
 }
@@ -42,13 +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)
    }
 }

--- a/src/lz.rs
+++ b/src/lz.rs
@@ -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);
-                if !state.prev_was_match {
+                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);
                }
-                if offset != state.last_offset {
+                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,
        );
    }
-    encode_length(coder, state, 256 * state.parity_contexts + 1, 1, config);
+    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(
@@ -124,41 +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 prev_was_match
+            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(
@@ -166,7 +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;
                }
@@ -176,24 +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;
            }
-            result.push(byte);
+            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)
 }
--- a/src/main.rs
+++ b/src/main.rs
@@ -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()? {
@@ -28,22 +30,32 @@ fn main() -> Result<()> {
                config.use_bitstream = true;
                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()),
@@ -75,7 +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 {
@@ -87,7 +99,7 @@ fn main() -> Result<()> {
        let mut packed_data = upkr::pack(
            &data,
            level,
-            config,
+            &config,
            Some(&mut |pos| {
                pb.set(pos as u64);
            }),
@@ -111,11 +123,16 @@ fn main() -> Result<()> {
        if reverse {
            data.reverse();
        }
-        let mut unpacked_data = upkr::unpack(&data, config);
-        if reverse {
-            unpacked_data.reverse();
+        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)?);
        }
-        File::create(outfile)?.write_all(&unpacked_data)?;
    }

    Ok(())
@@ -125,13 +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");
@@ -145,5 +167,9 @@ fn print_help(exit_code: i32) -> ! {
    eprintln!(" --invert-bit-encoding");
    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);
 }
--- a/src/parsing_packer.rs
+++ b/src/parsing_packer.rs
@@ -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 {
@@ -183,19 +187,21 @@ 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;
-                found_last_offset |= offset as u32 == arrival.state.last_offset();
-                add_match(
-                    &mut arrivals,
-                    cost_counter,
-                    pos,
-                    offset,
-                    m.length,
-                    &arrival,
-                    max_arrivals,
-                    encoding_config,
-                );
-                if m.length >= config.greedy_size {
-                    break 'arrival_loop;
+                if offset <= encoding_config.max_offset {
+                    found_last_offset |= offset as u32 == arrival.state.last_offset();
+                    add_match(
+                        &mut arrivals,
+                        cost_counter,
+                        pos,
+                        offset,
+                        m.length,
+                        &arrival,
+                        max_arrivals,
+                        encoding_config,
+                    );
+                    if m.length >= config.greedy_size {
+                        break 'arrival_loop;
+                    }
                }
            }

@@ -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(
--- a/src/rans.rs
+++ b/src/rans.rs
@@ -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)
    }
 }
Author	SHA1	Message	Date
Dennis Ranke	f6642f07c9	more config options, unpack error handling, fuzzing	2022-09-27 17:16:05 +02:00
Dennis Ranke	8715dede0e	add --eof-in-length option	2022-09-26 23:41:17 +02:00
Dennis Ranke	b12c8f8d93	add parameter to print out margin for overlapped unpacking	2022-09-25 23:44:03 +02:00
Dennis Ranke	af5fe898bf	add --no-repeated-offsets to help	2022-09-25 16:24:24 +02:00
Dennis Ranke	331857a711	add option to disable repeated offsets	2022-09-25 16:23:11 +02:00