RubyGems - zrip - Versions diffs - 0.1.0 - Mend

zrip 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (16) hide show

checksums.yaml ADDED Viewed

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: cec06279fae44f8a9e27237f7eda38cddd28f192a05612cb48d8ce97195ccd96
+  data.tar.gz: 5829099982f42ef6adca1ada816eb49d1ad61c5b87fc81a5567a28d96d37e381
+SHA512:
+  metadata.gz: 59a7636a293430724a1bbca39f4bab97ed5e160162383b8ff48e44dc754518e5b58172041adaf3841026881523bab6937ce20c72a876852d9f1df7b236e243c4
+  data.tar.gz: 4f52bc2bbb0c9e65b46be617963639ebb6deb3fca57ae630387aa59116b5403000e08fb798bf95fb48b00f9ffcbec93e85da737897ff514cd2304126f4aa0751

data/CHANGELOG.md ADDED Viewed

@@ -0,0 +1,12 @@
+# Changelog
+## [Unreleased]
+## [0.1.0] - 2026-06-20
+- Initial release.
+- `Zrip::FrameCodec`: frame-format Zstandard codec (Ractor-shareable).
+- `Zrip::BlockCodec`: frame-format Zstandard codec, per-Ractor (no lock overhead).
+- `Zrip::Dictionary`: immutable value type for Zstandard dictionaries.
+- `Zrip::DictTrainer`: FastCOVER-based dictionary trainer.
+- `Zrip::FrameCodec.get_frame_content_size`: reads FCS from frame header.

data/Cargo.lock ADDED Viewed

@@ -0,0 +1,318 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+[[package]]
+name = "bindgen"
+version = "0.72.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "993776b509cfb49c750f11b8f07a46fa23e0a1386ffc01fb1e7d343efc387895"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+[[package]]
+name = "bitflags"
+version = "2.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4388bee8683e3d04af747c73422af53102d2bd24d9eadb6cbc100baef4b43f8"
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom",
+]
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+[[package]]
+name = "clang-sys"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+[[package]]
+name = "either"
+version = "1.16.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91622ff5e7162018101f2fea40d6ebf4a78bbe5a49736a2020649edf9693679e"
+[[package]]
+name = "glob"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
+[[package]]
+name = "itertools"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
+dependencies = [
+ "either",
+]
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+[[package]]
+name = "libc"
+version = "0.2.186"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
+[[package]]
+name = "libloading"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7c4b02199fee7c5d21a5ae7d8cfa79a6ef5bb2fc834d6e9058e89c825efdc55"
+dependencies = [
+ "cfg-if",
+ "windows-link",
+]
+[[package]]
+name = "magnus"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b36a5b126bbe97eb0d02d07acfeb327036c6319fd816139a49824a83b7f9012"
+dependencies = [
+ "magnus-macros",
+ "rb-sys",
+ "rb-sys-env",
+ "seq-macro",
+]
+[[package]]
+name = "magnus-macros"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "47607461fd8e1513cb4f2076c197d8092d921a1ea75bd08af97398f593751892"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+[[package]]
+name = "memchr"
+version = "2.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "88904434abc2901f197fe8cc55f0445e7ded921dba5911dad2e2b39b48e663c4"
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+[[package]]
+name = "quote"
+version = "1.0.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+dependencies = [
+ "proc-macro2",
+]
+[[package]]
+name = "rb-sys"
+version = "0.9.128"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "45ca28513560e56cfb79a62b1fce363c73af170a182024ce880c77ee9429920a"
+dependencies = [
+ "rb-sys-build",
+]
+[[package]]
+name = "rb-sys-build"
+version = "0.9.128"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ce04b2c55eff3a21aaa623fcc655d94373238e72cac6b3e1a3641ff31649f99a"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+[[package]]
+name = "rb-sys-env"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cca7ad6a7e21e72151d56fe2495a259b5670e204c3adac41ee7ef676ea08117a"
+[[package]]
+name = "regex"
+version = "1.12.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f1292b7759ae1cb9ec195452d1390a074f0cd8541ab7a5a8c31cd6db45d4a6ba"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+[[package]]
+name = "regex-automata"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+[[package]]
+name = "regex-syntax"
+version = "0.8.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d6f6ff9a378485b298a5286656da665ba74413d36db0979633275d2e708145d4"
+[[package]]
+name = "rustc-hash"
+version = "2.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
+[[package]]
+name = "seq-macro"
+version = "0.3.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
+[[package]]
+name = "shell-words"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc6fe69c597f9c37bfeeeeeb33da3530379845f10be461a66d16d03eca2ded77"
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+[[package]]
+name = "syn"
+version = "2.0.118"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b9ae57f904213ebb649ce6895b8a66c66f0203b9319718f69a5612a065b1422"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+[[package]]
+name = "zrip"
+version = "0.1.0"
+dependencies = [
+ "magnus",
+ "rb-sys",
+ "zrip 0.3.4",
+]
+[[package]]
+name = "zrip"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86ea9c671343ec4c85c7e64e1e81ba37653c5ba190fa4861fc094fa21fe8a7ce"
+dependencies = [
+ "zrip-core",
+ "zrip-decode",
+ "zrip-encode",
+]
+[[package]]
+name = "zrip-core"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d085b7cbd7698827ed6ce19331819146e70e6612ed2e2dc26b0b14a1c2dab2d0"
+[[package]]
+name = "zrip-decode"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc4ad88afeb185aaf5209a86efafae5ce320d3e9a6e80d76b45a27773dab5ece"
+dependencies = [
+ "zrip-core",
+]
+[[package]]
+name = "zrip-encode"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9bbf6a9da066f17b5e76d189c7e028dc61dcd806ab394b3999b6ee3c2da7bf79"
+dependencies = [
+ "zrip-core",
+]

data/Cargo.toml ADDED Viewed

@@ -0,0 +1,9 @@
+[workspace]
+members  = ["ext/zrip"]
+resolver = "2"
+[profile.release]
+opt-level     = 3
+lto           = true
+codegen-units = 1
+panic         = "abort"

data/LICENSE ADDED Viewed

@@ -0,0 +1,21 @@
+MIT License
+Copyright (c) 2026 Patrik Wenger
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md ADDED Viewed

@@ -0,0 +1,150 @@
+# zrip — Ractor-safe Zstandard for Ruby
+[![CI](https://github.com/paddor/zrip-rb/actions/workflows/ci.yml/badge.svg)](https://github.com/paddor/zrip-rb/actions/workflows/ci.yml)
+[![Gem Version](https://img.shields.io/gem/v/zrip?color=e9573f)](https://rubygems.org/gems/zrip)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+[![Ruby](https://img.shields.io/badge/Ruby-%3E%3D%204.0-CC342D?logo=ruby&logoColor=white)](https://www.ruby-lang.org)
+Ruby bindings for [zrip](https://crates.io/crates/zrip), a pure-Rust Zstandard
+implementation. Built with [magnus](https://github.com/matsadler/magnus) and
+declared Ractor-safe so you can compress from any Ractor without a global lock.
+## Features
+- **Frame codec** for standard Zstd frames (Ractor-shareable)
+- **Block codec** with per-Ractor context (no lock overhead)
+- **Dictionary support** for both frame and block codecs
+- **FastCOVER-based dictionary trainer** (`DictTrainer`)
+- **Configurable compression levels** (default: 1)
+- **Bounded decompression** with `max_output_size:` and frame content size checks
+- **Ractor-safe**: `FrameCodec` is shareable across Ractors, `BlockCodec` is
+  per-Ractor (mutable context state)
+## Install
+Requires Ruby >= 4.0 and a Rust toolchain (for building the native extension):
+```sh
+gem install zrip
+```
+Or in your Gemfile:
+```ruby
+gem "zrip"
+```
+## Usage
+### Frame codec (standard Zstd frames)
+```ruby
+require "zrip"
+codec = Zrip::FrameCodec.new
+compressed = codec.compress("hello world " * 1000)
+original   = codec.decompress(compressed)
+```
+### Block codec
+```ruby
+codec = Zrip::BlockCodec.new
+compressed = codec.compress("hello world " * 1000)
+original   = codec.decompress(compressed)
+```
+### Compression levels
+```ruby
+fast   = Zrip::FrameCodec.new(level: -3)   # negative = faster
+strong = Zrip::FrameCodec.new(level: 19)    # higher = smaller output
+```
+### Bounded decompression
+```ruby
+codec = Zrip::FrameCodec.new
+# Limit output size to 1 MiB
+codec.decompress(compressed, max_output_size: 1_048_576)
+# Read frame content size from header (without decompressing)
+Zrip::FrameCodec.get_frame_content_size(compressed)  #=> 12000
+```
+### Dictionary compression
+```ruby
+dict = Zrip::Dictionary.new(bytes: trained_dict_bytes)
+codec = Zrip::FrameCodec.new(dict: dict)
+compressed = codec.compress("common log prefix: event=login user=alice")
+original   = codec.decompress(compressed)
+```
+### Dictionary training
+```ruby
+trainer = Zrip::DictTrainer.new(8192)
+messages.each { |msg| trainer.add_sample(msg) }
+dict_bytes = trainer.train
+dict  = Zrip::Dictionary.new(bytes: dict_bytes)
+codec = Zrip::FrameCodec.new(dict: dict)
+```
+### Ractor safety
+```ruby
+codec = Zrip::FrameCodec.new
+ractors = 4.times.map do |i|
+  Ractor.new(codec) do |c|
+    data = "ractor #{Ractor.current} payload " * 100
+    ct   = c.compress(data)
+    raise "mismatch" unless c.decompress(ct) == data
+    :ok
+  end
+end
+ractors.each { |r| p r.value }  # => :ok, :ok, :ok, :ok
+```
+## API
+| Class / Module | Method | Description |
+|---|---|---|
+| `Zrip::FrameCodec` | `.new(dict: nil, level: 1)` | Create a frame codec, optionally with a `Dictionary`, raw `String` dict, or compression level |
+| | `.get_frame_content_size(string)` | Read Frame_Content_Size from a Zstd frame header |
+| | `#compress(string)` | Compress to Zstd frame |
+| | `#decompress(string, max_output_size: nil)` | Decompress a Zstd frame, optionally bounded |
+| | `#has_dict?` | Whether a dictionary is loaded |
+| | `#id` | Dictionary ID (nil without dict) |
+| | `#size` | Dictionary size in bytes (0 without dict) |
+| | `#level` | Compression level |
+| `Zrip::BlockCodec` | `.new(dict: nil, level: 1)` | Create a block codec, optionally with a dict |
+| | `#compress(string)` | Compress to Zstd block |
+| | `#decompress(string, max_output_size: nil)` | Decompress a Zstd block, optionally bounded |
+| | `#has_dict?` | Whether a dictionary is loaded |
+| | `#size` | Dictionary size in bytes (0 without dict) |
+| | `#level` | Compression level |
+| `Zrip::Dictionary` | `.new(bytes:, id: nil)` | Immutable dictionary value object (`Data.define`) |
+| | `#bytes` | Frozen binary dict bytes |
+| | `#id` | 32-bit dictionary ID (auto-detected from ZDICT header or SHA-256) |
+| | `#size` | Dictionary size in bytes |
+| `Zrip::DictTrainer` | `.new(max_dict_size)` | Create a trainer |
+| | `#add_sample(string)` | Feed a training sample (skips < 4 bytes) |
+| | `#train` | Consume the trainer, return dict bytes |
+| | `#sample_count` | Number of accepted samples |
+| | `#total_bytes` | Total bytes of accepted samples |
+| | `#trained?` | Whether `#train` has been called |
+| | `#max_dict_size` | Configured max dict size |
+| `Zrip::DecompressError` | | Raised on decompression failure |
+| `Zrip::CompressError` | | Raised on compression failure |
+| `Zrip::MissingContentSizeError` | | Raised when Frame_Content_Size is absent (subclass of `DecompressError`) |
+| `Zrip::OutputSizeLimitError` | | Raised when declared content size exceeds limit (subclass of `DecompressError`) |
+## License
+[MIT](LICENSE)

data/ext/zrip/Cargo.toml ADDED Viewed

@@ -0,0 +1,16 @@
+[package]
+name    = "zrip"
+version = "0.1.0"
+edition = "2021"
+[lib]
+name       = "zrip"
+crate-type = ["cdylib", "rlib"]
+[dependencies]
+zstd   = { version = "0.3", package = "zrip", features = ["frame", "dict_builder"] }
+magnus = "0.8"
+rb-sys = "0.9"
+[build-dependencies]
+rb-sys = "0.9"

data/ext/zrip/extconf.rb ADDED Viewed

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+require "mkmf"
+require "rb_sys/mkmf"
+create_rust_makefile("zrip/zrip") do |r|
+  r.profile = ENV.fetch("RB_SYS_CARGO_PROFILE", :release).to_sym
+end

data/ext/zrip/src/lib.rs ADDED Viewed

@@ -0,0 +1,576 @@
+use magnus::{
+    exception::ExceptionClass, function, method, prelude::*, r_string::RString, value::Opaque,
+    Error, Ruby,
+};
+use std::cell::RefCell;
+use std::sync::{Mutex, OnceLock};
+use zstd::dict::fastcover::FastCoverParams;
+use zstd::{CompressContext, DecompressContext, Dictionary};
+static DECOMPRESS_ERROR: OnceLock<Opaque<ExceptionClass>> = OnceLock::new();
+static COMPRESS_ERROR: OnceLock<Opaque<ExceptionClass>> = OnceLock::new();
+static MISSING_CONTENT_SIZE_ERROR: OnceLock<Opaque<ExceptionClass>> = OnceLock::new();
+static OUTPUT_SIZE_LIMIT_ERROR: OnceLock<Opaque<ExceptionClass>> = OnceLock::new();
+fn decompress_error(ruby: &Ruby) -> ExceptionClass {
+    ruby.get_inner(
+        *DECOMPRESS_ERROR
+            .get()
+            .expect("DecompressError not initialized"),
+    )
+}
+fn compress_error(ruby: &Ruby) -> ExceptionClass {
+    ruby.get_inner(*COMPRESS_ERROR.get().expect("CompressError not initialized"))
+}
+fn missing_content_size_error(ruby: &Ruby) -> ExceptionClass {
+    ruby.get_inner(
+        *MISSING_CONTENT_SIZE_ERROR
+            .get()
+            .expect("MissingContentSizeError not initialized"),
+    )
+}
+fn output_size_limit_error(ruby: &Ruby) -> ExceptionClass {
+    ruby.get_inner(
+        *OUTPUT_SIZE_LIMIT_ERROR
+            .get()
+            .expect("OutputSizeLimitError not initialized"),
+    )
+}
+// ---------- frame header parsing ----------
+const ZSTD_FRAME_MAGIC: [u8; 4] = [0x28, 0xB5, 0x2F, 0xFD];
+#[derive(Debug)]
+enum BoundedError {
+    BadMagic,
+    MissingContentSize,
+    OutputSizeLimit { declared: u64, limit: u64 },
+    DecoderFailed(String),
+}
+fn parse_frame_content_size(input: &[u8]) -> Result<Option<u64>, BoundedError> {
+    if input.len() < 5 {
+        return Err(BoundedError::BadMagic);
+    }
+    if input[..4] != ZSTD_FRAME_MAGIC {
+        return Err(BoundedError::BadMagic);
+    }
+    let fhd = input[4];
+    let fcs_flag = (fhd >> 6) & 3;
+    let single_segment = (fhd >> 5) & 1;
+    let dict_id_flag = fhd & 3;
+    let window_desc_size = if single_segment == 0 { 1usize } else { 0 };
+    let dict_id_size = [0usize, 1, 2, 4][dict_id_flag as usize];
+    let fcs_field_size = match fcs_flag {
+        0 => {
+            if single_segment == 1 {
+                1usize
+            } else {
+                return Ok(None);
+            }
+        }
+        1 => 2,
+        2 => 4,
+        3 => 8,
+        _ => unreachable!(),
+    };
+    let fcs_offset = 5 + window_desc_size + dict_id_size;
+    if input.len() < fcs_offset + fcs_field_size {
+        return Err(BoundedError::BadMagic);
+    }
+    let fcs_bytes = &input[fcs_offset..fcs_offset + fcs_field_size];
+    let value = match fcs_field_size {
+        1 => fcs_bytes[0] as u64,
+        2 => u16::from_le_bytes([fcs_bytes[0], fcs_bytes[1]]) as u64 + 256,
+        4 => u32::from_le_bytes([fcs_bytes[0], fcs_bytes[1], fcs_bytes[2], fcs_bytes[3]]) as u64,
+        8 => u64::from_le_bytes(fcs_bytes.try_into().unwrap()),
+        _ => unreachable!(),
+    };
+    Ok(Some(value))
+}
+fn decompress_bounded(
+    compressed: &[u8],
+    max_output: usize,
+    dctx: &mut DecompressContext,
+) -> Result<Vec<u8>, BoundedError> {
+    if compressed.len() < ZSTD_FRAME_MAGIC.len() || compressed[..4] != ZSTD_FRAME_MAGIC {
+        return Err(BoundedError::BadMagic);
+    }
+    let upper = match parse_frame_content_size(compressed)? {
+        Some(n) => {
+            if max_output != 0 && n > max_output as u64 {
+                return Err(BoundedError::OutputSizeLimit {
+                    declared: n,
+                    limit: max_output as u64,
+                });
+            }
+            if n > u64::from(u32::MAX) {
+                return Err(BoundedError::OutputSizeLimit {
+                    declared: n,
+                    limit: u64::from(u32::MAX),
+                });
+            }
+            n as usize
+        }
+        None => {
+            if max_output != 0 {
+                return Err(BoundedError::MissingContentSize);
+            }
+            1024 * 1024
+        }
+    };
+    let result = dctx
+        .decompress_with_limit(compressed, upper)
+        .map_err(|e| BoundedError::DecoderFailed(format!("{e}")))?;
+    Ok(result.into_owned())
+}
+fn raise_bounded(ruby: &Ruby, err: BoundedError, prefix: &str) -> Error {
+    match err {
+        BoundedError::BadMagic => Error::new(
+            decompress_error(ruby),
+            format!("{prefix}: bad magic (input is not a Zstd frame)"),
+        ),
+        BoundedError::MissingContentSize => Error::new(
+            missing_content_size_error(ruby),
+            format!("{prefix}: Frame_Content_Size absent from frame header"),
+        ),
+        BoundedError::OutputSizeLimit { declared, limit } => Error::new(
+            output_size_limit_error(ruby),
+            format!("{prefix}: declared content size {declared} exceeds limit {limit}"),
+        ),
+        BoundedError::DecoderFailed(msg) => {
+            Error::new(decompress_error(ruby), format!("{prefix}: {msg}"))
+        }
+    }
+}
+// ---------- dict helper ----------
+fn load_dict(ruby: &Ruby, bytes: &[u8]) -> Result<Dictionary, Error> {
+    Dictionary::from_bytes(bytes).map_err(|_| {
+        Error::new(
+            ruby.exception_runtime_error(),
+            "dictionary must be in ZDICT format (use DictTrainer to train one)",
+        )
+    })
+}
+// ---------- FrameCodec ----------
+#[magnus::wrap(class = "Zrip::FrameCodec", free_immediately, size)]
+struct FrameCodec {
+    dict_len: usize,
+    dict_id: Option<u32>,
+    level: i32,
+    cctx: Mutex<CompressContext>,
+    dctx: Mutex<DecompressContext>,
+}
+unsafe impl Send for FrameCodec {}
+unsafe impl Sync for FrameCodec {}
+fn frame_codec_new(
+    ruby: &Ruby,
+    rb_dict: Option<RString>,
+    id: u32,
+    level: i32,
+) -> Result<FrameCodec, Error> {
+    let (dict_len, dict_id, cctx, dctx) = match rb_dict {
+        None => {
+            let cctx = CompressContext::new(level).map_err(|e| {
+                Error::new(
+                    compress_error(ruby),
+                    format!("CompressContext::new failed: {e}"),
+                )
+            })?;
+            (0, None, cctx, DecompressContext::new())
+        }
+        Some(s) => {
+            let bytes: Vec<u8> = unsafe { s.as_slice().to_vec() };
+            s.freeze();
+            let dict = load_dict(ruby, &bytes)?;
+            let dl = bytes.len();
+            let cctx = CompressContext::with_dict(level, dict.clone()).map_err(|e| {
+                Error::new(
+                    compress_error(ruby),
+                    format!("CompressContext::with_dict failed: {e}"),
+                )
+            })?;
+            let dctx = DecompressContext::with_dict(dict);
+            (dl, Some(id), cctx, dctx)
+        }
+    };
+    Ok(FrameCodec {
+        dict_len,
+        dict_id,
+        level,
+        cctx: Mutex::new(cctx),
+        dctx: Mutex::new(dctx),
+    })
+}
+fn frame_codec_compress(
+    ruby: &Ruby,
+    rb_self: &FrameCodec,
+    rb_input: RString,
+) -> Result<RString, Error> {
+    let input: &[u8] = unsafe { rb_input.as_slice() };
+    let mut cctx = rb_self.cctx.lock().expect("FrameCodec CCtx mutex poisoned");
+    let out = cctx
+        .compress(input)
+        .map_err(|e| Error::new(compress_error(ruby), format!("zstd compress failed: {e}")))?;
+    Ok(ruby.str_from_slice(&out))
+}
+fn frame_codec_decompress(
+    ruby: &Ruby,
+    rb_self: &FrameCodec,
+    rb_input: RString,
+    max_output: usize,
+) -> Result<RString, Error> {
+    let compressed: &[u8] = unsafe { rb_input.as_slice() };
+    let mut dctx = rb_self.dctx.lock().expect("FrameCodec DCtx mutex poisoned");
+    let out = decompress_bounded(compressed, max_output, &mut dctx)
+        .map_err(|e| raise_bounded(ruby, e, "zstd frame decode failed"))?;
+    Ok(ruby.str_from_slice(&out))
+}
+fn frame_codec_size(rb_self: &FrameCodec) -> usize {
+    rb_self.dict_len
+}
+fn frame_codec_has_dict(rb_self: &FrameCodec) -> bool {
+    rb_self.dict_id.is_some()
+}
+fn frame_codec_id(rb_self: &FrameCodec) -> Option<u32> {
+    rb_self.dict_id
+}
+fn frame_codec_level(rb_self: &FrameCodec) -> i32 {
+    rb_self.level
+}
+fn frame_codec_get_frame_content_size(
+    ruby: &Ruby,
+    rb_input: RString,
+) -> Result<Option<u64>, Error> {
+    let bytes: &[u8] = unsafe { rb_input.as_slice() };
+    match parse_frame_content_size(bytes) {
+        Ok(v) => Ok(v),
+        Err(BoundedError::BadMagic) => Err(Error::new(
+            decompress_error(ruby),
+            "zstd frame header parse failed: bad magic (input is not a Zstd frame)",
+        )),
+        Err(e) => Err(raise_bounded(ruby, e, "zstd frame header parse failed")),
+    }
+}
+// ---------- BlockCodec ----------
+#[magnus::wrap(class = "Zrip::BlockCodec", free_immediately, size)]
+struct BlockCodec {
+    dict_len: usize,
+    dict_id: Option<u32>,
+    level: i32,
+    cctx: RefCell<CompressContext>,
+    dctx: RefCell<DecompressContext>,
+}
+fn block_codec_new(
+    ruby: &Ruby,
+    rb_dict: Option<RString>,
+    id: u32,
+    level: i32,
+) -> Result<BlockCodec, Error> {
+    let (dict_len, dict_id, cctx, dctx) = match rb_dict {
+        None => {
+            let cctx = CompressContext::new(level).map_err(|e| {
+                Error::new(
+                    compress_error(ruby),
+                    format!("CompressContext::new failed: {e}"),
+                )
+            })?;
+            (0, None, cctx, DecompressContext::new())
+        }
+        Some(s) => {
+            let bytes: Vec<u8> = unsafe { s.as_slice().to_vec() };
+            let dict = load_dict(ruby, &bytes)?;
+            let dl = bytes.len();
+            let cctx = CompressContext::with_dict(level, dict.clone()).map_err(|e| {
+                Error::new(
+                    compress_error(ruby),
+                    format!("CompressContext::with_dict failed: {e}"),
+                )
+            })?;
+            let dctx = DecompressContext::with_dict(dict);
+            (dl, Some(id), cctx, dctx)
+        }
+    };
+    Ok(BlockCodec {
+        dict_len,
+        dict_id,
+        level,
+        cctx: RefCell::new(cctx),
+        dctx: RefCell::new(dctx),
+    })
+}
+fn block_codec_compress(
+    ruby: &Ruby,
+    rb_self: &BlockCodec,
+    rb_input: RString,
+) -> Result<RString, Error> {
+    let input: &[u8] = unsafe { rb_input.as_slice() };
+    let mut cctx = rb_self.cctx.borrow_mut();
+    let out = cctx
+        .compress(input)
+        .map_err(|e| Error::new(compress_error(ruby), format!("zstd compress failed: {e}")))?;
+    Ok(ruby.str_from_slice(&out))
+}
+fn block_codec_decompress(
+    ruby: &Ruby,
+    rb_self: &BlockCodec,
+    rb_input: RString,
+    max_output: usize,
+) -> Result<RString, Error> {
+    let compressed: &[u8] = unsafe { rb_input.as_slice() };
+    let mut dctx = rb_self.dctx.borrow_mut();
+    let out = decompress_bounded(compressed, max_output, &mut dctx)
+        .map_err(|e| raise_bounded(ruby, e, "zstd block decode failed"))?;
+    Ok(ruby.str_from_slice(&out))
+}
+fn block_codec_size(rb_self: &BlockCodec) -> usize {
+    rb_self.dict_len
+}
+fn block_codec_has_dict(rb_self: &BlockCodec) -> bool {
+    rb_self.dict_id.is_some()
+}
+fn block_codec_level(rb_self: &BlockCodec) -> i32 {
+    rb_self.level
+}
+// ---------- DictTrainer ----------
+#[magnus::wrap(class = "Zrip::DictTrainer", free_immediately, size)]
+struct RbDictTrainer {
+    inner: RefCell<Option<TrainerState>>,
+    max_dict_size: usize,
+}
+struct TrainerState {
+    samples: Vec<Vec<u8>>,
+    total_bytes: usize,
+}
+fn dict_trainer_new(_ruby: &Ruby, max_dict_size: usize) -> RbDictTrainer {
+    RbDictTrainer {
+        max_dict_size,
+        inner: RefCell::new(Some(TrainerState {
+            samples: Vec::new(),
+            total_bytes: 0,
+        })),
+    }
+}
+fn dict_trainer_add_sample(
+    ruby: &Ruby,
+    rb_self: &RbDictTrainer,
+    rb_data: RString,
+) -> Result<(), Error> {
+    let mut borrow = rb_self.inner.borrow_mut();
+    let state = borrow.as_mut().ok_or_else(|| {
+        Error::new(
+            ruby.exception_runtime_error(),
+            "DictTrainer already consumed by #train",
+        )
+    })?;
+    let data: Vec<u8> = unsafe { rb_data.as_slice().to_vec() };
+    if data.len() < 4 {
+        return Ok(());
+    }
+    state.total_bytes += data.len();
+    state.samples.push(data);
+    Ok(())
+}
+fn dict_trainer_sample_count(ruby: &Ruby, rb_self: &RbDictTrainer) -> Result<usize, Error> {
+    let borrow = rb_self.inner.borrow();
+    borrow.as_ref().map(|s| s.samples.len()).ok_or_else(|| {
+        Error::new(
+            ruby.exception_runtime_error(),
+            "DictTrainer already consumed by #train",
+        )
+    })
+}
+fn dict_trainer_total_bytes(ruby: &Ruby, rb_self: &RbDictTrainer) -> Result<usize, Error> {
+    let borrow = rb_self.inner.borrow();
+    borrow.as_ref().map(|s| s.total_bytes).ok_or_else(|| {
+        Error::new(
+            ruby.exception_runtime_error(),
+            "DictTrainer already consumed by #train",
+        )
+    })
+}
+fn dict_trainer_train(ruby: &Ruby, rb_self: &RbDictTrainer) -> Result<RString, Error> {
+    let state = rb_self.inner.borrow_mut().take().ok_or_else(|| {
+        Error::new(
+            ruby.exception_runtime_error(),
+            "DictTrainer already consumed by #train",
+        )
+    })?;
+    if state.samples.len() < 2 {
+        return Ok(ruby.str_from_slice(b""));
+    }
+    let refs: Vec<&[u8]> = state.samples.iter().map(|s| s.as_slice()).collect();
+    let content = zstd::dict::fastcover::select_segments(
+        &refs,
+        rb_self.max_dict_size,
+        &FastCoverParams::default(),
+    );
+    let dict_bytes =
+        zstd::dict::finalize::finalize_dictionary(&content, &refs, rb_self.max_dict_size);
+    Ok(ruby.str_from_slice(&dict_bytes))
+}
+fn dict_trainer_max_dict_size(rb_self: &RbDictTrainer) -> usize {
+    rb_self.max_dict_size
+}
+fn dict_trainer_trained(rb_self: &RbDictTrainer) -> bool {
+    rb_self.inner.borrow().is_none()
+}
+// ---------- module init ----------
+#[magnus::init]
+fn init(ruby: &Ruby) -> Result<(), Error> {
+    unsafe { rb_sys::rb_ext_ractor_safe(true) };
+    let module = ruby.define_module("Zrip")?;
+    let decompress_error_class =
+        module.define_error("DecompressError", ruby.exception_standard_error())?;
+    DECOMPRESS_ERROR
+        .set(Opaque::from(decompress_error_class))
+        .unwrap_or_else(|_| panic!("init called more than once"));
+    let compress_error_class =
+        module.define_error("CompressError", ruby.exception_standard_error())?;
+    COMPRESS_ERROR
+        .set(Opaque::from(compress_error_class))
+        .unwrap_or_else(|_| panic!("init called more than once"));
+    let missing_content_size_error_class =
+        module.define_error("MissingContentSizeError", decompress_error_class)?;
+    MISSING_CONTENT_SIZE_ERROR
+        .set(Opaque::from(missing_content_size_error_class))
+        .unwrap_or_else(|_| panic!("init called more than once"));
+    let output_size_limit_error_class =
+        module.define_error("OutputSizeLimitError", decompress_error_class)?;
+    OUTPUT_SIZE_LIMIT_ERROR
+        .set(Opaque::from(output_size_limit_error_class))
+        .unwrap_or_else(|_| panic!("init called more than once"));
+    // FrameCodec
+    let frame_codec_class = module.define_class("FrameCodec", ruby.class_object())?;
+    frame_codec_class.define_singleton_method("_native_new", function!(frame_codec_new, 3))?;
+    frame_codec_class.define_singleton_method(
+        "get_frame_content_size",
+        function!(frame_codec_get_frame_content_size, 1),
+    )?;
+    frame_codec_class.define_method("compress", method!(frame_codec_compress, 1))?;
+    frame_codec_class.define_method("_native_decompress", method!(frame_codec_decompress, 2))?;
+    frame_codec_class.define_method("size", method!(frame_codec_size, 0))?;
+    frame_codec_class.define_method("has_dict?", method!(frame_codec_has_dict, 0))?;
+    frame_codec_class.define_method("id", method!(frame_codec_id, 0))?;
+    frame_codec_class.define_method("level", method!(frame_codec_level, 0))?;
+    // BlockCodec
+    let block_codec_class = module.define_class("BlockCodec", ruby.class_object())?;
+    block_codec_class.define_singleton_method("_native_new", function!(block_codec_new, 3))?;
+    block_codec_class.define_method("compress", method!(block_codec_compress, 1))?;
+    block_codec_class.define_method("_native_decompress", method!(block_codec_decompress, 2))?;
+    block_codec_class.define_method("size", method!(block_codec_size, 0))?;
+    block_codec_class.define_method("has_dict?", method!(block_codec_has_dict, 0))?;
+    block_codec_class.define_method("level", method!(block_codec_level, 0))?;
+    // DictTrainer
+    let trainer_class = module.define_class("DictTrainer", ruby.class_object())?;
+    trainer_class.define_singleton_method("_native_new", function!(dict_trainer_new, 1))?;
+    trainer_class.define_method("add_sample", method!(dict_trainer_add_sample, 1))?;
+    trainer_class.define_method("sample_count", method!(dict_trainer_sample_count, 0))?;
+    trainer_class.define_method("total_bytes", method!(dict_trainer_total_bytes, 0))?;
+    trainer_class.define_method("train", method!(dict_trainer_train, 0))?;
+    trainer_class.define_method("max_dict_size", method!(dict_trainer_max_dict_size, 0))?;
+    trainer_class.define_method("trained?", method!(dict_trainer_trained, 0))?;
+    Ok(())
+}
+#[cfg(test)]
+mod tests {
+    use super::*;
+    #[test]
+    fn round_trip() {
+        let data = b"the quick brown fox jumps over the lazy dog ".repeat(100);
+        let compressed = zstd::compress(&data, 1).unwrap();
+        assert!(compressed.len() < data.len());
+        assert_eq!(&compressed[..4], &ZSTD_FRAME_MAGIC);
+        let decompressed = zstd::decompress(&compressed).unwrap();
+        assert_eq!(decompressed, data);
+    }
+    #[test]
+    fn empty_round_trip() {
+        let compressed = zstd::compress(b"", 1).unwrap();
+        let decompressed = zstd::decompress(&compressed).unwrap();
+        assert!(decompressed.is_empty());
+    }
+    #[test]
+    fn context_round_trip() {
+        let mut cctx = CompressContext::new(1).unwrap();
+        let mut dctx = DecompressContext::new();
+        let data = b"hello world hello world hello world";
+        let ct = cctx.compress(data).unwrap();
+        let pt = dctx.decompress(&ct).unwrap();
+        assert_eq!(&*pt, data);
+    }
+    #[test]
+    fn parse_fcs() {
+        let data = b"test data for fcs parsing".repeat(10);
+        let compressed = zstd::compress(&data, 1).unwrap();
+        let fcs = parse_frame_content_size(&compressed).unwrap();
+        assert_eq!(fcs, Some(data.len() as u64));
+    }
+}

data/lib/zrip/block_codec.rb ADDED Viewed

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+require_relative "dictionary"
+module Zrip
+  class BlockCodec
+    def self.new(dict: nil, level: DEFAULT_LEVEL)
+      case dict
+      when nil
+        _native_new(nil, 0, Integer(level))
+      when Dictionary
+        _native_new(dict.bytes, dict.id, Integer(level))
+      when String
+        d = Dictionary.new(bytes: dict)
+        _native_new(d.bytes, d.id, Integer(level))
+      else
+        raise TypeError, "expected Zrip::Dictionary, String, or nil; got #{dict.class}"
+      end
+    end
+    def decompress(bytes, max_output_size: nil)
+      _native_decompress(bytes, Integer(max_output_size || 0))
+    end
+  end
+end

data/lib/zrip/dict_trainer.rb ADDED Viewed

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+module Zrip
+  class DictTrainer
+    def self.new(max_dict_size)
+      _native_new(max_dict_size)
+    end
+  end
+end

data/lib/zrip/dictionary.rb ADDED Viewed

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+require "digest"
+module Zrip
+  Dictionary = Data.define(:bytes, :id)
+  class Dictionary
+    ZDICT_MAGIC       = "\x37\xA4\x30\xEC".b.freeze
+    USER_DICT_ID_MIN  = 32_768
+    USER_DICT_ID_MAX  = (2**31) - 1
+    USER_DICT_ID_SIZE = USER_DICT_ID_MAX - USER_DICT_ID_MIN + 1
+    def initialize(bytes:, id: nil)
+      b = bytes.b
+      id ||= if b.byteslice(0, 4) == ZDICT_MAGIC
+               b.byteslice(4, 4).unpack1("V")
+             else
+               raw = Digest::SHA256.digest(b).byteslice(0, 4).unpack1("V")
+               USER_DICT_ID_MIN + (raw % USER_DICT_ID_SIZE)
+             end
+      super(bytes: b.freeze, id: id)
+    end
+    def size
+      bytes.bytesize
+    end
+  end
+end

data/lib/zrip/frame_codec.rb ADDED Viewed

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+require_relative "dictionary"
+module Zrip
+  class FrameCodec
+    def self.new(dict: nil, level: DEFAULT_LEVEL)
+      case dict
+      when nil
+        _native_new(nil, 0, Integer(level))
+      when Dictionary
+        _native_new(dict.bytes, dict.id, Integer(level))
+      when String
+        d = Dictionary.new(bytes: dict)
+        _native_new(d.bytes, d.id, Integer(level))
+      else
+        raise TypeError, "expected Zrip::Dictionary, String, or nil; got #{dict.class}"
+      end
+    end
+    def decompress(bytes, max_output_size: nil)
+      _native_decompress(bytes, Integer(max_output_size || 0))
+    end
+  end
+end

data/lib/zrip/version.rb ADDED Viewed

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+module Zrip
+  VERSION = "0.1.0"
+end

data/lib/zrip.rb ADDED Viewed

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+require_relative "zrip/zrip"        # Rust extension
+require_relative "zrip/version"
+module Zrip
+  DEFAULT_LEVEL = 1
+end
+require_relative "zrip/dictionary"
+require_relative "zrip/block_codec"
+require_relative "zrip/frame_codec"
+require_relative "zrip/dict_trainer"

metadata ADDED Viewed

@@ -0,0 +1,75 @@
+--- !ruby/object:Gem::Specification
+name: zrip
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Patrik Wenger
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rb_sys
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+description: Ruby bindings (via Rust/magnus) for zrip, a pure-Rust Zstandard implementation.
+  Frame-format and block-format compress/decompress with optional dictionary support,
+  configurable compression levels, and FastCOVER-based dictionary training. Ractor-safe.
+email:
+- paddor@gmail.com
+executables: []
+extensions:
+- ext/zrip/extconf.rb
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- Cargo.lock
+- Cargo.toml
+- LICENSE
+- README.md
+- ext/zrip/Cargo.toml
+- ext/zrip/extconf.rb
+- ext/zrip/src/lib.rs
+- lib/zrip.rb
+- lib/zrip/block_codec.rb
+- lib/zrip/dict_trainer.rb
+- lib/zrip/dictionary.rb
+- lib/zrip/frame_codec.rb
+- lib/zrip/version.rb
+homepage: https://github.com/paddor/zrip-rb
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/paddor/zrip-rb
+  source_code_uri: https://github.com/paddor/zrip-rb
+  changelog_uri: https://github.com/paddor/zrip-rb/blob/main/CHANGELOG.md
+  rubygems_mfa_required: 'true'
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 4.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 4.0.10
+specification_version: 4
+summary: Ractor-safe Zstandard bindings for Ruby (pure-Rust zrip backend)
+test_files: []