Compare commits

..

2 Commits

Author SHA1 Message Date
copilot-swe-agent[bot]
dd242cb1c5 Fix ExtractToDirectory to properly truncate existing files
Changed File.OpenWrite to File.Create to ensure files are truncated when extracting over existing files. File.OpenWrite does not truncate, leaving old data at the end if the new file is shorter.

Added test Zip_Deflate_ArchiveExtractToDirectory_Overwrite to verify the fix.

Co-authored-by: adamhathcock <527620+adamhathcock@users.noreply.github.com>
2025-11-14 08:54:45 +00:00
copilot-swe-agent[bot]
0ecbe02ede Initial plan 2025-11-14 08:35:27 +00:00
363 changed files with 1364 additions and 74885 deletions

View File

@@ -3,11 +3,11 @@
"isRoot": true,
"tools": {
"csharpier": {
"version": "1.2.4",
"version": "1.1.2",
"commands": [
"csharpier"
],
"rollForward": false
}
}
}
}

15
.github/COPILOT_AGENT_README.md vendored Normal file
View File

@@ -0,0 +1,15 @@
# Copilot Coding Agent Configuration
This repository includes a minimal opt-in configuration and CI workflow to allow the GitHub Copilot coding agent to open and validate PRs.
- .copilot-agent.yml: opt-in config for automated agents
- .github/agents/copilot-agent.yml: detailed agent policy configuration
- .github/workflows/dotnetcore.yml: CI runs on PRs touching the solution, source, or tests to validate changes
- AGENTS.md: general instructions for Copilot coding agent with project-specific guidelines
Maintainers can adjust the allowed paths or disable the agent by editing or removing .copilot-agent.yml.
Notes:
- The agent can create, modify, and delete files within the allowed paths (src, tests, README.md, AGENTS.md)
- All changes require review before merge
- If build/test paths are different, update the workflow accordingly; this workflow targets SharpCompress.sln and the SharpCompress.Test test project.

View File

@@ -1,25 +0,0 @@
# Plan: Implement Missing Async Functionality in SharpCompress
SharpCompress has async support for low-level stream operations and Reader/Writer APIs, but critical entry points (Archive.Open, factory methods, initialization) remain synchronous. This plan adds async overloads for all user-facing I/O operations and fixes existing async bugs, enabling full end-to-end async workflows.
## Steps
1. **Add async factory methods** to [ArchiveFactory.cs](src/SharpCompress/Factories/ArchiveFactory.cs), [ReaderFactory.cs](src/SharpCompress/Factories/ReaderFactory.cs), and [WriterFactory.cs](src/SharpCompress/Factories/WriterFactory.cs) with `OpenAsync` and `CreateAsync` overloads accepting `CancellationToken`
2. **Implement async Open methods** on concrete archive types ([ZipArchive.cs](src/SharpCompress/Archives/Zip/ZipArchive.cs), [TarArchive.cs](src/SharpCompress/Archives/Tar/TarArchive.cs), [RarArchive.cs](src/SharpCompress/Archives/Rar/RarArchive.cs), [GZipArchive.cs](src/SharpCompress/Archives/GZip/GZipArchive.cs), [SevenZipArchive.cs](src/SharpCompress/Archives/SevenZip/SevenZipArchive.cs)) and reader types ([ZipReader.cs](src/SharpCompress/Readers/Zip/ZipReader.cs), [TarReader.cs](src/SharpCompress/Readers/Tar/TarReader.cs), etc.)
3. **Convert archive initialization logic to async** including header reading, volume loading, and format signature detection across archive constructors and internal initialization methods
4. **Fix LZMA decoder async bugs** in [LzmaStream.cs](src/SharpCompress/Compressors/LZMA/LzmaStream.cs), [Decoder.cs](src/SharpCompress/Compressors/LZMA/Decoder.cs), and [OutWindow.cs](src/SharpCompress/Compressors/LZMA/OutWindow.cs) to enable true async 7Zip support and remove `NonDisposingStream` workaround
5. **Complete Rar async implementation** by converting `UnpackV2017` methods to async in [UnpackV2017.cs](src/SharpCompress/Compressors/Rar/UnpackV2017.cs) and updating Rar20 decompression
6. **Add comprehensive async tests** covering all new async entry points, cancellation scenarios, and concurrent operations across all archive formats in test files
## Further Considerations
1. **Breaking changes** - Should new async methods be added alongside existing sync methods (non-breaking), or should sync methods eventually be deprecated? Recommend additive approach for backward compatibility.
2. **Performance impact** - Header parsing for formats like Zip/Tar is often small; consider whether truly async parsing adds value vs sync parsing wrapped in Task, or make it conditional based on stream type (network vs file).
3. **7Zip complexity** - The LZMA async bug fix (Step 4) may be challenging due to state management in the decoder; consider whether to scope it separately or implement a simpler workaround that maintains correctness.

View File

@@ -1,123 +0,0 @@
# Plan: Modernize SharpCompress Public API
Based on comprehensive analysis, the API has several inconsistencies around factory patterns, async support, format capabilities, and options classes. Most improvements can be done incrementally without breaking changes.
## Steps
1. **Standardize factory patterns** by deprecating format-specific static `Open` methods in [Archives/Zip/ZipArchive.cs](src/SharpCompress/Archives/Zip/ZipArchive.cs), [Archives/Tar/TarArchive.cs](src/SharpCompress/Archives/Tar/TarArchive.cs), etc. in favor of centralized [Factories/ArchiveFactory.cs](src/SharpCompress/Factories/ArchiveFactory.cs)
2. **Complete async implementation** in [Writers/Zip/ZipWriter.cs](src/SharpCompress/Writers/Zip/ZipWriter.cs) and other writers that currently use sync-over-async, implementing true async I/O throughout the writer hierarchy
3. **Unify options classes** by making [Common/ExtractionOptions.cs](src/SharpCompress/Common/ExtractionOptions.cs) inherit from `OptionsBase` and adding progress reporting to extraction methods consistently
4. **Clarify GZip semantics** in [Archives/GZip/GZipArchive.cs](src/SharpCompress/Archives/GZip/GZipArchive.cs) by adding XML documentation explaining single-entry limitation and relationship to GZip compression used in Tar.gz
## Further Considerations
1. **Breaking changes roadmap** - Should we plan a major version (2.0) to remove deprecated factory methods, clean up `ArchiveType` enum (remove Arc/Arj or add full support), and consolidate naming patterns?
2. **Progress reporting consistency** - Should `IProgress<ArchiveExtractionProgress<IEntry>>` be added to all extraction extension methods or consolidated into options classes?
## Detailed Analysis
### Factory Pattern Issues
Three different factory patterns exist with overlapping functionality:
1. **Static Factories**: ArchiveFactory, ReaderFactory, WriterFactory
2. **Instance Factories**: IArchiveFactory, IReaderFactory, IWriterFactory
3. **Format-specific static methods**: Each archive class has static `Open` methods
**Example confusion:**
```csharp
// Three ways to open a Zip archive - which is recommended?
var archive1 = ArchiveFactory.Open("file.zip");
var archive2 = ZipArchive.Open("file.zip");
var archive3 = ArchiveFactory.AutoFactory.Open(fileInfo, options);
```
### Async Support Gaps
Base `IWriter` interface has async methods, but writer implementations provide minimal async support. Most writers just call synchronous methods:
```csharp
public virtual async Task WriteAsync(...)
{
// Default implementation calls synchronous version
Write(filename, source, modificationTime);
await Task.CompletedTask.ConfigureAwait(false);
}
```
Real async implementations only in:
- `TarWriter` - Proper async implementation
- Most other writers use sync-over-async
### GZip Archive Special Case
GZip is treated as both a compression format and an archive format, but only supports single-entry archives:
```csharp
protected override GZipArchiveEntry CreateEntryInternal(...)
{
if (Entries.Any())
{
throw new InvalidFormatException("Only one entry is allowed in a GZip Archive");
}
// ...
}
```
### Options Class Hierarchy
```
OptionsBase (LeaveStreamOpen, ArchiveEncoding)
├─ ReaderOptions (LookForHeader, Password, DisableCheckIncomplete, BufferSize, ExtensionHint, Progress)
├─ WriterOptions (CompressionType, CompressionLevel, Progress)
│ ├─ ZipWriterOptions (ArchiveComment, UseZip64)
│ ├─ TarWriterOptions (FinalizeArchiveOnClose, HeaderFormat)
│ └─ GZipWriterOptions (no additional properties)
└─ ExtractionOptions (standalone - Overwrite, ExtractFullPath, PreserveFileTime, PreserveAttributes)
```
**Issues:**
- `ExtractionOptions` doesn't inherit from `OptionsBase` - no encoding support during extraction
- Progress reporting inconsistency between readers and extraction
- Obsolete properties (`ChecksumIsValid`, `Version`) with unclear migration path
### Implementation Priorities
**High Priority (Non-Breaking):**
1. Add API usage guide (Archive vs Reader, factory recommendations, async best practices)
2. Fix progress reporting consistency
3. Complete async implementation in writers
**Medium Priority (Next Major Version):**
1. Unify factory pattern - deprecate format-specific static `Open` methods
2. Clean up options classes - make `ExtractionOptions` inherit from `OptionsBase`
3. Clarify archive types - remove Arc/Arj from `ArchiveType` enum or add full support
4. Standardize naming across archive types
**Low Priority:**
1. Add BZip2 archive support similar to GZipArchive
2. Complete obsolete property cleanup with migration guide
### Backward Compatibility Strategy
**Safe (Non-Breaking) Changes:**
- Add new methods to interfaces (use default implementations)
- Add new options properties (with defaults)
- Add new factory methods
- Improve async implementations
- Add progress reporting support
**Breaking Changes to Avoid:**
- ❌ Removing format-specific `Open` methods (deprecate instead)
- ❌ Changing `LeaveStreamOpen` default (currently `true`)
- ❌ Removing obsolete properties before major version bump
- ❌ Changing return types or signatures of existing methods
**Deprecation Pattern:**
- Use `[Obsolete]` for one major version
- Use `[EditorBrowsable(EditorBrowsableState.Never)]` in next major version
- Remove in following major version

View File

@@ -1,155 +0,0 @@
# NuGet Release Workflow
This document describes the automated NuGet release workflow for SharpCompress.
## Overview
The `nuget-release.yml` workflow automatically builds, tests, and publishes SharpCompress packages to NuGet.org when:
- Changes are pushed to the `master` or `release` branch
- A version tag (format: `MAJOR.MINOR.PATCH`) is pushed
The workflow runs on both Windows and Ubuntu, but only the Windows build publishes to NuGet.
## How It Works
### Version Determination
The workflow automatically determines the version based on whether the commit is tagged using C# code in the build project:
1. **Tagged Release (Stable)**:
- If the current commit has a version tag (e.g., `0.42.1`)
- Uses the tag as the version number
- Published as a stable release
2. **Untagged Release (Prerelease)**:
- If the current commit is NOT tagged
- Creates a prerelease version based on the next minor version
- Format: `{NEXT_MINOR_VERSION}-beta.{COMMIT_COUNT}`
- Example: `0.43.0-beta.123` (if last tag is 0.42.x)
- Published as a prerelease to NuGet.org (Windows build only)
### Workflow Steps
The workflow runs on a matrix of operating systems (Windows and Ubuntu):
1. **Checkout**: Fetches the repository with full history for version detection
2. **Setup .NET**: Installs .NET 10.0
3. **Determine Version**: Runs `determine-version` build target to check for tags and determine version
4. **Update Version**: Runs `update-version` build target to update the version in the project file
5. **Build and Test**: Runs the full build and test suite on both platforms
6. **Upload Artifacts**: Uploads the generated `.nupkg` files as workflow artifacts (separate for each OS)
7. **Push to NuGet**: (Windows only) Runs `push-to-nuget` build target to publish the package to NuGet.org using the API key
All version detection, file updates, and publishing logic is implemented in C# in the `build/Program.cs` file using build targets.
## Setup Requirements
### 1. NuGet API Key Secret
The workflow requires a `NUGET_API_KEY` secret to be configured in the repository settings:
1. Go to https://www.nuget.org/account/apikeys
2. Create a new API key with "Push" permission for the SharpCompress package
3. In GitHub, go to: **Settings****Secrets and variables****Actions**
4. Create a new secret named `NUGET_API_KEY` with the API key value
### 2. Branch Protection (Recommended)
Consider enabling branch protection rules for the `release` branch to ensure:
- Code reviews are required before merging
- Status checks pass before merging
- Only authorized users can push to the branch
## Usage
### Creating a Stable Release
There are two ways to trigger a stable release:
**Method 1: Push tag to trigger workflow**
1. Ensure all changes are committed on the `master` or `release` branch
2. Create and push a version tag:
```bash
git checkout master # or release
git tag 0.43.0
git push origin 0.43.0
```
3. The workflow will automatically trigger, build, test, and publish `SharpCompress 0.43.0` to NuGet.org (Windows build)
**Method 2: Tag after pushing to branch**
1. Ensure all changes are merged and pushed to the `master` or `release` branch
2. Create and push a version tag on the already-pushed commit:
```bash
git checkout master # or release
git tag 0.43.0
git push origin 0.43.0
```
3. The workflow will automatically trigger, build, test, and publish `SharpCompress 0.43.0` to NuGet.org (Windows build)
### Creating a Prerelease
1. Push changes to the `master` or `release` branch without tagging:
```bash
git checkout master # or release
git push origin master # or release
```
2. The workflow will automatically:
- Build and test the project on both Windows and Ubuntu
- Publish a prerelease version like `0.43.0-beta.456` to NuGet.org (Windows build)
## Troubleshooting
### Workflow Fails to Push to NuGet
- **Check the API Key**: Ensure `NUGET_API_KEY` is set correctly in repository secrets
- **Check API Key Permissions**: Verify the API key has "Push" permission for SharpCompress
- **Check API Key Expiration**: NuGet API keys may expire; create a new one if needed
### Version Conflict
If you see "Package already exists" errors:
- The workflow uses `--skip-duplicate` flag to handle this gracefully
- If you need to republish the same version, delete it from NuGet.org first (if allowed)
### Build or Test Failures
- The workflow will not push to NuGet if build or tests fail
- Check the workflow logs in GitHub Actions for details
- Fix the issues and push again
## Manual Package Creation
If you need to create a package manually without publishing:
```bash
dotnet run --project build/build.csproj -- publish
```
The package will be created in the `artifacts/` directory.
## Build Targets
The workflow uses the following C# build targets defined in `build/Program.cs`:
- **determine-version**: Detects version from git tags and outputs VERSION and PRERELEASE variables
- **update-version**: Updates VersionPrefix, AssemblyVersion, and FileVersion in the project file
- **push-to-nuget**: Pushes the generated NuGet packages to NuGet.org (requires NUGET_API_KEY)
These targets can be run manually for testing:
```bash
# Determine the version
dotnet run --project build/build.csproj -- determine-version
# Update version in project file
VERSION=0.43.0 dotnet run --project build/build.csproj -- update-version
# Push to NuGet (requires NUGET_API_KEY environment variable)
NUGET_API_KEY=your-key dotnet run --project build/build.csproj -- push-to-nuget
```
## Related Files
- `.github/workflows/nuget-release.yml` - The workflow definition
- `build/Program.cs` - Build script with version detection and publishing logic
- `src/SharpCompress/SharpCompress.csproj` - Project file with version information

View File

@@ -1,120 +0,0 @@
# Testing Guide for NuGet Release Workflow
This document describes how to test the NuGet release workflow.
## Testing Strategy
Since this workflow publishes to NuGet.org and requires repository secrets, testing should be done carefully. The workflow runs on both Windows and Ubuntu, but only the Windows build publishes to NuGet.
## Pre-Testing Checklist
- [x] Workflow YAML syntax validated
- [x] Version determination logic tested locally
- [x] Version update logic tested locally
- [x] Build script works (`dotnet run --project build/build.csproj`)
## Manual Testing Steps
### 1. Test Prerelease Publishing (Recommended First Test)
This tests the workflow on untagged commits to the master or release branch.
**Steps:**
1. Ensure `NUGET_API_KEY` secret is configured in repository settings
2. Create a test commit on the `master` or `release` branch (e.g., update a comment or README)
3. Push to the `master` or `release` branch
4. Monitor the GitHub Actions workflow at: https://github.com/adamhathcock/sharpcompress/actions
5. Verify:
- Workflow triggers and runs successfully on both Windows and Ubuntu
- Version is determined correctly (e.g., `0.43.0-beta.XXX` if last tag is 0.42.x)
- Build and tests pass on both platforms
- Package artifacts are uploaded for both platforms
- Package is pushed to NuGet.org as prerelease (Windows build only)
**Expected Outcome:**
- A new prerelease package appears on NuGet.org: https://www.nuget.org/packages/SharpCompress/
- Package version follows pattern: `{NEXT_MINOR_VERSION}-beta.{COMMIT_COUNT}`
### 2. Test Tagged Release Publishing
This tests the workflow when a version tag is pushed.
**Steps:**
1. Prepare the `master` or `release` branch with all desired changes
2. Create a version tag (must be a pure semantic version like `MAJOR.MINOR.PATCH`):
```bash
git checkout master # or release
git tag 0.42.2
git push origin 0.42.2
```
3. Monitor the GitHub Actions workflow
4. Verify:
- Workflow triggers and runs successfully on both Windows and Ubuntu
- Version is determined as the tag (e.g., `0.42.2`)
- Build and tests pass on both platforms
- Package artifacts are uploaded for both platforms
- Package is pushed to NuGet.org as stable release (Windows build only)
**Expected Outcome:**
- A new stable release package appears on NuGet.org
- Package version matches the tag
### 3. Test Duplicate Package Handling
This tests the `--skip-duplicate` flag behavior.
**Steps:**
1. Push to the `release` branch without making changes
2. Monitor the workflow
3. Verify:
- Workflow runs but NuGet push is skipped with "duplicate" message
- No errors occur
### 4. Test Build Failure Handling
This tests that failed builds don't publish packages.
**Steps:**
1. Introduce a breaking change in a test or code
2. Push to the `release` branch
3. Verify:
- Workflow runs and detects the failure
- Build or test step fails
- NuGet push step is skipped
- No package is published
## Verification
After each test, verify:
1. **GitHub Actions Logs**: Check the workflow logs for any errors or warnings
2. **NuGet.org**: Verify the package appears with correct version and metadata
3. **Artifacts**: Download and inspect the uploaded artifacts
## Rollback/Cleanup
If testing produces unwanted packages:
1. **Prerelease packages**: Can be unlisted on NuGet.org (Settings → Unlist)
2. **Stable packages**: Cannot be deleted, only unlisted (use test versions)
3. **Tags**: Can be deleted with:
```bash
git tag -d 0.42.2
git push origin :refs/tags/0.42.2
```
## Known Limitations
- NuGet.org does not allow re-uploading the same version
- Deleted packages on NuGet.org reserve the version number
- The workflow requires the `NUGET_API_KEY` secret to be set
## Success Criteria
The workflow is considered successful if:
- ✅ Prerelease versions are published correctly with beta suffix
- ✅ Tagged versions are published as stable releases
- ✅ Build and test failures prevent publishing
- ✅ Duplicate packages are handled gracefully
- ✅ Workflow logs are clear and informative

View File

@@ -14,12 +14,12 @@ jobs:
os: [windows-latest, ubuntu-latest]
steps:
- uses: actions/checkout@v6
- uses: actions/checkout@v5
- uses: actions/setup-dotnet@v5
with:
dotnet-version: 10.0.x
dotnet-version: 8.0.x
- run: dotnet run --project build/build.csproj
- uses: actions/upload-artifact@v6
- uses: actions/upload-artifact@v5
with:
name: ${{ matrix.os }}-sharpcompress.nupkg
path: artifacts/*

View File

@@ -1,57 +0,0 @@
name: NuGet Release
on:
push:
branches:
- 'master'
- 'release'
tags:
- '[0-9]+.[0-9]+.[0-9]+'
permissions:
contents: read
jobs:
build-and-publish:
runs-on: ${{ matrix.os }}
strategy:
matrix:
os: [windows-latest, ubuntu-latest]
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0 # Fetch all history for versioning
- uses: actions/setup-dotnet@v5
with:
dotnet-version: 10.0.x
# Determine version using C# build target
- name: Determine Version
id: version
run: dotnet run --project build/build.csproj -- determine-version
# Update version in project file using C# build target
- name: Update Version in Project
run: dotnet run --project build/build.csproj -- update-version
env:
VERSION: ${{ steps.version.outputs.version }}
# Build and test
- name: Build and Test
run: dotnet run --project build/build.csproj
# Upload artifacts for verification
- name: Upload NuGet Package
uses: actions/upload-artifact@v6
with:
name: ${{ matrix.os }}-nuget-package
path: artifacts/*.nupkg
# Push to NuGet.org using C# build target (Windows only)
- name: Push to NuGet
if: success() && matrix.os == 'windows-latest'
run: dotnet run --project build/build.csproj -- push-to-nuget
env:
NUGET_API_KEY: ${{ secrets.NUGET_API_KEY }}

5
.gitignore vendored
View File

@@ -11,12 +11,11 @@ TestResults/
packages/*/
project.lock.json
tests/TestArchives/Scratch
tests/TestArchives/*/Scratch
tests/TestArchives/*/Scratch2
.vs
tools
.vscode
.idea/
artifacts/
.DS_Store
*.snupkg
/tests/TestArchives/6d23a38c-f064-4ef1-ad89-b942396f53b9/Scratch

View File

@@ -1,9 +0,0 @@
{
"recommendations": [
"ms-dotnettools.csdevkit",
"ms-dotnettools.csharp",
"ms-dotnettools.vscode-dotnet-runtime",
"csharpier.csharpier-vscode",
"formulahendry.dotnet-test-explorer"
]
}

97
.vscode/launch.json vendored
View File

@@ -1,97 +0,0 @@
{
"version": "0.2.0",
"configurations": [
{
"name": "Debug Tests (net10.0)",
"type": "coreclr",
"request": "launch",
"preLaunchTask": "build",
"program": "dotnet",
"args": [
"test",
"${workspaceFolder}/tests/SharpCompress.Test/SharpCompress.Test.csproj",
"-f",
"net10.0",
"--no-build",
"--verbosity=normal"
],
"cwd": "${workspaceFolder}",
"console": "internalConsole",
"stopAtEntry": false
},
{
"name": "Debug Specific Test (net10.0)",
"type": "coreclr",
"request": "launch",
"preLaunchTask": "build",
"program": "dotnet",
"args": [
"test",
"${workspaceFolder}/tests/SharpCompress.Test/SharpCompress.Test.csproj",
"-f",
"net10.0",
"--no-build",
"--filter",
"FullyQualifiedName~${input:testName}"
],
"cwd": "${workspaceFolder}",
"console": "internalConsole",
"stopAtEntry": false
},
{
"name": "Debug Performance Tests",
"type": "coreclr",
"request": "launch",
"preLaunchTask": "build",
"program": "dotnet",
"args": [
"run",
"--project",
"${workspaceFolder}/tests/SharpCompress.Performance/SharpCompress.Performance.csproj",
"--no-build"
],
"cwd": "${workspaceFolder}",
"console": "internalConsole",
"stopAtEntry": false
},
{
"name": "Debug Build Script",
"type": "coreclr",
"request": "launch",
"program": "dotnet",
"args": [
"run",
"--project",
"${workspaceFolder}/build/build.csproj",
"--",
"${input:buildTarget}"
],
"cwd": "${workspaceFolder}",
"console": "internalConsole",
"stopAtEntry": false
}
],
"inputs": [
{
"id": "testName",
"type": "promptString",
"description": "Enter test name or pattern (e.g., TestMethodName or ClassName)",
"default": ""
},
{
"id": "buildTarget",
"type": "pickString",
"description": "Select build target",
"options": [
"clean",
"restore",
"build",
"test",
"format",
"publish",
"default"
],
"default": "build"
}
]
}

29
.vscode/settings.json vendored
View File

@@ -1,29 +0,0 @@
{
"dotnet.defaultSolution": "SharpCompress.sln",
"files.exclude": {
"**/bin": true,
"**/obj": true
},
"files.watcherExclude": {
"**/bin/**": true,
"**/obj/**": true,
"**/artifacts/**": true
},
"search.exclude": {
"**/bin": true,
"**/obj": true,
"**/artifacts": true
},
"editor.formatOnSave": false,
"[csharp]": {
"editor.defaultFormatter": "csharpier.csharpier-vscode",
"editor.formatOnSave": true,
"editor.codeActionsOnSave": {
"source.fixAll": "explicit"
}
},
"csharpier.enableDebugLogs": false,
"omnisharp.enableRoslynAnalyzers": true,
"omnisharp.enableEditorConfigSupport": true,
"dotnet-test-explorer.testProjectPath": "tests/**/*.csproj"
}

178
.vscode/tasks.json vendored
View File

@@ -1,178 +0,0 @@
{
"version": "2.0.0",
"tasks": [
{
"label": "build",
"command": "dotnet",
"type": "process",
"args": [
"build",
"${workspaceFolder}/SharpCompress.sln",
"/property:GenerateFullPaths=true",
"/consoleloggerparameters:NoSummary;ForceNoAlign"
],
"problemMatcher": "$msCompile",
"group": {
"kind": "build",
"isDefault": true
}
},
{
"label": "build-release",
"command": "dotnet",
"type": "process",
"args": [
"build",
"${workspaceFolder}/SharpCompress.sln",
"-c",
"Release",
"/property:GenerateFullPaths=true",
"/consoleloggerparameters:NoSummary;ForceNoAlign"
],
"problemMatcher": "$msCompile",
"group": "build"
},
{
"label": "build-library",
"command": "dotnet",
"type": "process",
"args": [
"build",
"${workspaceFolder}/src/SharpCompress/SharpCompress.csproj",
"/property:GenerateFullPaths=true",
"/consoleloggerparameters:NoSummary;ForceNoAlign"
],
"problemMatcher": "$msCompile",
"group": "build"
},
{
"label": "restore",
"command": "dotnet",
"type": "process",
"args": [
"restore",
"${workspaceFolder}/SharpCompress.sln"
],
"problemMatcher": "$msCompile"
},
{
"label": "clean",
"command": "dotnet",
"type": "process",
"args": [
"clean",
"${workspaceFolder}/SharpCompress.sln"
],
"problemMatcher": "$msCompile"
},
{
"label": "test",
"command": "dotnet",
"type": "process",
"args": [
"test",
"${workspaceFolder}/tests/SharpCompress.Test/SharpCompress.Test.csproj",
"--no-build",
"--verbosity=normal"
],
"problemMatcher": "$msCompile",
"group": {
"kind": "test",
"isDefault": true
},
"dependsOn": "build"
},
{
"label": "test-net10",
"command": "dotnet",
"type": "process",
"args": [
"test",
"${workspaceFolder}/tests/SharpCompress.Test/SharpCompress.Test.csproj",
"-f",
"net10.0",
"--no-build",
"--verbosity=normal"
],
"problemMatcher": "$msCompile",
"group": "test",
"dependsOn": "build"
},
{
"label": "test-net48",
"command": "dotnet",
"type": "process",
"args": [
"test",
"${workspaceFolder}/tests/SharpCompress.Test/SharpCompress.Test.csproj",
"-f",
"net48",
"--no-build",
"--verbosity=normal"
],
"problemMatcher": "$msCompile",
"group": "test",
"dependsOn": "build"
},
{
"label": "format",
"command": "dotnet",
"type": "process",
"args": [
"csharpier",
"."
],
"problemMatcher": []
},
{
"label": "format-check",
"command": "dotnet",
"type": "process",
"args": [
"csharpier",
"check",
"."
],
"problemMatcher": []
},
{
"label": "run-build-script",
"command": "dotnet",
"type": "process",
"args": [
"run",
"--project",
"${workspaceFolder}/build/build.csproj"
],
"problemMatcher": "$msCompile"
},
{
"label": "pack",
"command": "dotnet",
"type": "process",
"args": [
"pack",
"${workspaceFolder}/src/SharpCompress/SharpCompress.csproj",
"-c",
"Release",
"-o",
"${workspaceFolder}/artifacts/"
],
"problemMatcher": "$msCompile",
"dependsOn": "build-release"
},
{
"label": "performance-tests",
"command": "dotnet",
"type": "process",
"args": [
"run",
"--project",
"${workspaceFolder}/tests/SharpCompress.Performance/SharpCompress.Performance.csproj",
"-c",
"Release"
],
"problemMatcher": "$msCompile"
}
]
}

View File

@@ -28,38 +28,14 @@ SharpCompress is a pure C# compression library supporting multiple archive forma
## Code Formatting
**Copilot agents: You MUST run the `format` task after making code changes to ensure consistency.**
- Use CSharpier for code formatting to ensure consistent style across the project
- CSharpier is configured as a local tool in `.config/dotnet-tools.json`
### Commands
1. **Restore tools** (first time only):
```bash
dotnet tool restore
```
2. **Check if files are formatted correctly** (doesn't modify files):
```bash
dotnet csharpier check .
```
- Exit code 0: All files are properly formatted
- Exit code 1: Some files need formatting (will show which files and differences)
3. **Format files** (modifies files):
```bash
dotnet csharpier format .
```
- Formats all files in the project to match CSharpier style
- Run from project root directory
4. **Configure your IDE** to format on save using CSharpier for the best experience
### Additional Notes
- Restore tools with: `dotnet tool restore`
- Format files from the project root with: `dotnet csharpier .`
- **Run `dotnet csharpier .` from the project root after making code changes before committing**
- Configure your IDE to format on save using CSharpier for the best experience
- The project also uses `.editorconfig` for editor settings (indentation, encoding, etc.)
- Let CSharpier handle code style while `.editorconfig` handles editor behavior
- Always run `dotnet csharpier check .` before committing to verify formatting
## Project Setup and Structure
@@ -73,30 +49,6 @@ SharpCompress is a pure C# compression library supporting multiple archive forma
- Use `dotnet test` to run tests
- Solution file: `SharpCompress.sln`
### Directory Structure
```
src/SharpCompress/
├── Archives/ # IArchive implementations (Zip, Tar, Rar, 7Zip, GZip)
├── Readers/ # IReader implementations (forward-only)
├── Writers/ # IWriter implementations (forward-only)
├── Compressors/ # Low-level compression streams (BZip2, Deflate, LZMA, etc.)
├── Factories/ # Format detection and factory pattern
├── Common/ # Shared types (ArchiveType, Entry, Options)
├── Crypto/ # Encryption implementations
└── IO/ # Stream utilities and wrappers
tests/SharpCompress.Test/
├── Zip/, Tar/, Rar/, SevenZip/, GZip/, BZip2/ # Format-specific tests
├── TestBase.cs # Base test class with helper methods
└── TestArchives/ # Test data (not checked into main test project)
```
### Factory Pattern
All format types implement factory interfaces (`IArchiveFactory`, `IReaderFactory`, `IWriterFactory`) for auto-detection:
- `ReaderFactory.Open()` - Auto-detects format by probing stream
- `WriterFactory.Open()` - Creates writer for specified `ArchiveType`
- Factories located in: `src/SharpCompress/Factories/`
## Nullable Reference Types
- Declare variables non-nullable, and check for `null` at entry points.
@@ -164,18 +116,3 @@ SharpCompress supports multiple archive and compression formats:
- Use test archives from `tests/TestArchives` directory for consistency.
- Test stream disposal and `LeaveStreamOpen` behavior.
- Test edge cases: empty archives, large files, corrupted archives, encrypted archives.
### Test Organization
- Base class: `TestBase` - Provides `TEST_ARCHIVES_PATH`, `SCRATCH_FILES_PATH`, temp directory management
- Framework: xUnit with AwesomeAssertions
- Test archives: `tests/TestArchives/` - Use existing archives, don't create new ones unnecessarily
- Match naming style of nearby test files
## Common Pitfalls
1. **Don't mix Archive and Reader APIs** - Archive needs seekable stream, Reader doesn't
2. **Solid archives (Rar, 7Zip)** - Use `ExtractAllEntries()` for best performance, not individual entry extraction
3. **Stream disposal** - Always set `LeaveStreamOpen` explicitly when needed (default is to close)
4. **Tar + non-seekable stream** - Must provide file size or it will throw
5. **Multi-framework differences** - Some features differ between .NET Framework and modern .NET (e.g., Mono.Posix)
6. **Format detection** - Use `ReaderFactory.Open()` for auto-detection, test with actual archive files

View File

@@ -1,19 +1,20 @@
<Project>
<ItemGroup>
<PackageVersion Include="Bullseye" Version="6.1.0" />
<PackageVersion Include="AwesomeAssertions" Version="9.3.0" />
<PackageVersion Include="Bullseye" Version="6.0.0" />
<PackageVersion Include="AwesomeAssertions" Version="9.2.1" />
<PackageVersion Include="Glob" Version="1.1.9" />
<PackageVersion Include="JetBrains.Profiler.SelfApi" Version="2.5.15" />
<PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.0" />
<PackageVersion Include="Microsoft.NET.Test.Sdk" Version="18.0.1" />
<PackageVersion Include="JetBrains.Profiler.SelfApi" Version="2.5.14" />
<PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="8.0.0" />
<PackageVersion Include="Microsoft.NET.Test.Sdk" Version="18.0.0" />
<PackageVersion Include="Mono.Posix.NETStandard" Version="1.0.0" />
<PackageVersion Include="SimpleExec" Version="12.1.0" />
<PackageVersion Include="System.Text.Encoding.CodePages" Version="10.0.0" />
<PackageVersion Include="SimpleExec" Version="12.0.0" />
<PackageVersion Include="System.Buffers" Version="4.6.1" />
<PackageVersion Include="System.Memory" Version="4.6.3" />
<PackageVersion Include="System.Text.Encoding.CodePages" Version="8.0.0" />
<PackageVersion Include="xunit" Version="2.9.3" />
<PackageVersion Include="xunit.runner.visualstudio" Version="3.1.5" />
<PackageVersion Include="Microsoft.NET.ILLink.Tasks" Version="10.0.0" />
<PackageVersion Include="ZstdSharp.Port" Version="0.8.6" />
<PackageVersion Include="Microsoft.NET.ILLink.Tasks" Version="8.0.21" />
<PackageVersion Include="Microsoft.SourceLink.GitHub" Version="8.0.0" />
<PackageVersion Include="Microsoft.NETFramework.ReferenceAssemblies" Version="1.0.3" />
</ItemGroup>

View File

@@ -22,28 +22,11 @@
| 7Zip (4) | LZMA, LZMA2, BZip2, PPMd, BCJ, BCJ2, Deflate | Decompress | SevenZipArchive | N/A | N/A |
1. SOLID Rars are only supported in the RarReader API.
2. Zip format supports pkware and WinzipAES encryption. However, encrypted LZMA is not supported. Zip64 reading/writing is supported but only with seekable streams as the Zip spec doesn't support Zip64 data in post data descriptors. Deflate64 is only supported for reading. See [Zip Format Notes](#zip-format-notes) for details on multi-volume archives and streaming behavior.
2. Zip format supports pkware and WinzipAES encryption. However, encrypted LZMA is not supported. Zip64 reading/writing is supported but only with seekable streams as the Zip spec doesn't support Zip64 data in post data descriptors. Deflate64 is only supported for reading.
3. The Tar format requires a file size in the header. If no size is specified to the TarWriter and the stream is not seekable, then an exception will be thrown.
4. The 7Zip format doesn't allow for reading as a forward-only stream so 7Zip is only supported through the Archive API. See [7Zip Format Notes](#7zip-format-notes) for details on async extraction behavior.
4. The 7Zip format doesn't allow for reading as a forward-only stream so 7Zip is only supported through the Archive API
5. LZip has no support for extra data like the file name or timestamp. There is a default filename used when looking at the entry Key on the archive.
### Zip Format Notes
- Multi-volume/split ZIP archives require ZipArchive (seekable streams) as ZipReader cannot seek across volume files.
- ZipReader processes entries from LocalEntry headers (which include directory entries ending with `/`) and intentionally skips DirectoryEntry headers from the central directory, as they are redundant in streaming mode - all entry data comes from LocalEntry headers which ZipReader has already processed.
### 7Zip Format Notes
- **Async Extraction Performance**: When using async extraction methods (e.g., `ExtractAllEntries()` with `MoveToNextEntryAsync()`), each file creates its own decompression stream to avoid state corruption in the LZMA decoder. This is less efficient than synchronous extraction, which can reuse a single decompression stream for multiple files in the same folder.
**Performance Impact**: For archives with many small files in the same compression folder, async extraction will be slower than synchronous extraction because it must:
1. Create a new LZMA decoder for each file
2. Skip through the decompressed data to reach each file's starting position
**Recommendation**: For best performance with 7Zip archives, use synchronous extraction methods (`MoveToNextEntry()` and `WriteEntryToDirectory()`) when possible. Use async methods only when you need to avoid blocking the thread (e.g., in UI applications or async-only contexts).
**Technical Details**: 7Zip archives group files into "folders" (compression units), where all files in a folder share one continuous LZMA-compressed stream. The LZMA decoder maintains internal state (dictionary window, decoder positions) that assumes sequential, non-interruptible processing. Async operations can yield control during awaits, which would corrupt this shared state. To avoid this, async extraction creates a fresh decoder stream for each file.
## Compression Streams
For those who want to directly compress/decompress bits. The single file formats are represented here as well. However, BZip2, LZip and XZ have no metadata (GZip has a little) so using them without something like a Tar file makes little sense.

View File

@@ -1,6 +1,6 @@
# SharpCompress
SharpCompress is a compression library in pure C# for .NET Framework 4.8, .NET 8.0 and .NET 10.0 that can unrar, un7zip, unzip, untar unbzip2, ungzip, unlzip, unzstd, unarc and unarj with forward-only reading and file random access APIs. Write support for zip/tar/bzip2/gzip/lzip are implemented.
SharpCompress is a compression library in pure C# for .NET Framework 4.62, .NET Standard 2.1, .NET 6.0 and NET 8.0 that can unrar, un7zip, unzip, untar unbzip2, ungzip, unlzip, unzstd with forward-only reading and file random access APIs. Write support for zip/tar/bzip2/gzip/lzip are implemented.
The major feature is support for non-seekable streams so large files can be processed on the fly (i.e. download stream).

View File

@@ -87,17 +87,20 @@ memoryStream.Position = 0;
### Extract all files from a rar file to a directory using RarArchive
Note: Extracting a solid rar or 7z file needs to be done in sequential order to get acceptable decompression speed.
`ExtractAllEntries` is primarily intended for solid archives (like solid Rar) or 7Zip archives, where sequential extraction provides the best performance. For general/simple extraction with any supported archive type, use `archive.WriteToDirectory()` instead.
It is explicitly recommended to use `ExtractAllEntries` when extracting an entire `IArchive` instead of iterating over all its `Entries`.
Alternatively, use `IArchive.WriteToDirectory`.
```C#
using (var archive = RarArchive.Open("Test.rar"))
{
// Simple extraction with RarArchive; this WriteToDirectory pattern works for all archive types
archive.WriteToDirectory(@"D:\temp", new ExtractionOptions()
using (var reader = archive.ExtractAllEntries())
{
ExtractFullPath = true,
Overwrite = true
});
reader.WriteAllToDirectory(@"D:\temp", new ExtractionOptions()
{
ExtractFullPath = true,
Overwrite = true
});
}
}
```
@@ -113,41 +116,6 @@ using (var archive = RarArchive.Open("Test.rar"))
}
```
### Extract solid Rar or 7Zip archives with manual progress reporting
`ExtractAllEntries` only works for solid archives (Rar) or 7Zip archives. For optimal performance with these archive types, use this method:
```C#
using (var archive = RarArchive.Open("archive.rar")) // Must be solid Rar or 7Zip
{
if (archive.IsSolid || archive.Type == ArchiveType.SevenZip)
{
// Calculate total size for progress reporting
double totalSize = archive.Entries.Where(e => !e.IsDirectory).Sum(e => e.Size);
long completed = 0;
using (var reader = archive.ExtractAllEntries())
{
while (reader.MoveToNextEntry())
{
if (!reader.Entry.IsDirectory)
{
reader.WriteEntryToDirectory(@"D:\output", new ExtractionOptions()
{
ExtractFullPath = true,
Overwrite = true
});
completed += reader.Entry.Size;
double progress = completed / totalSize;
Console.WriteLine($"Progress: {progress:P}");
}
}
}
}
}
```
### Use ReaderFactory to autodetect archive type and Open the entry stream
```C#
@@ -330,12 +298,14 @@ using (var writer = WriterFactory.Open(stream, ArchiveType.Zip, CompressionType.
```C#
using (var archive = ZipArchive.Open("archive.zip"))
{
// Simple async extraction - works for all archive types
await archive.WriteToDirectoryAsync(
@"C:\output",
new ExtractionOptions() { ExtractFullPath = true, Overwrite = true },
cancellationToken
);
using (var reader = archive.ExtractAllEntries())
{
await reader.WriteAllToDirectoryAsync(
@"C:\output",
new ExtractionOptions() { ExtractFullPath = true, Overwrite = true },
cancellationToken
);
}
}
```

View File

@@ -1,10 +1,7 @@
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Runtime.InteropServices;
using System.Text.RegularExpressions;
using System.Threading.Tasks;
using GlobExpressions;
using static Bullseye.Targets;
using static SimpleExec.Command;
@@ -14,11 +11,7 @@ const string Restore = "restore";
const string Build = "build";
const string Test = "test";
const string Format = "format";
const string CheckFormat = "check-format";
const string Publish = "publish";
const string DetermineVersion = "determine-version";
const string UpdateVersion = "update-version";
const string PushToNuGet = "push-to-nuget";
Target(
Clean,
@@ -49,20 +42,12 @@ Target(
Target(
Format,
() =>
{
Run("dotnet", "tool restore");
Run("dotnet", "csharpier format .");
}
);
Target(
CheckFormat,
() =>
{
Run("dotnet", "tool restore");
Run("dotnet", "csharpier check .");
}
);
Target(Restore, [CheckFormat], () => Run("dotnet", "restore"));
Target(Restore, [Format], () => Run("dotnet", "restore"));
Target(
Build,
@@ -76,7 +61,7 @@ Target(
Target(
Test,
[Build],
["net10.0", "net48"],
["net8.0", "net48"],
framework =>
{
IEnumerable<string> GetFiles(string d)
@@ -105,164 +90,6 @@ Target(
}
);
Target(
DetermineVersion,
async () =>
{
var (version, isPrerelease) = await GetVersion();
Console.WriteLine($"VERSION={version}");
Console.WriteLine($"PRERELEASE={isPrerelease.ToString().ToLower()}");
// Write to environment file for GitHub Actions
var githubOutput = Environment.GetEnvironmentVariable("GITHUB_OUTPUT");
if (!string.IsNullOrEmpty(githubOutput))
{
File.AppendAllText(githubOutput, $"version={version}\n");
File.AppendAllText(githubOutput, $"prerelease={isPrerelease.ToString().ToLower()}\n");
}
}
);
Target(
UpdateVersion,
async () =>
{
var version = Environment.GetEnvironmentVariable("VERSION");
if (string.IsNullOrEmpty(version))
{
var (detectedVersion, _) = await GetVersion();
version = detectedVersion;
}
Console.WriteLine($"Updating project file with version: {version}");
var projectPath = "src/SharpCompress/SharpCompress.csproj";
var content = File.ReadAllText(projectPath);
// Get base version (without prerelease suffix)
var baseVersion = version.Split('-')[0];
// Update VersionPrefix
content = Regex.Replace(
content,
@"<VersionPrefix>[^<]*</VersionPrefix>",
$"<VersionPrefix>{version}</VersionPrefix>"
);
// Update AssemblyVersion
content = Regex.Replace(
content,
@"<AssemblyVersion>[^<]*</AssemblyVersion>",
$"<AssemblyVersion>{baseVersion}</AssemblyVersion>"
);
// Update FileVersion
content = Regex.Replace(
content,
@"<FileVersion>[^<]*</FileVersion>",
$"<FileVersion>{baseVersion}</FileVersion>"
);
File.WriteAllText(projectPath, content);
Console.WriteLine($"Updated VersionPrefix to: {version}");
Console.WriteLine($"Updated AssemblyVersion and FileVersion to: {baseVersion}");
}
);
Target(
PushToNuGet,
() =>
{
var apiKey = Environment.GetEnvironmentVariable("NUGET_API_KEY");
if (string.IsNullOrEmpty(apiKey))
{
Console.WriteLine(
"NUGET_API_KEY environment variable is not set. Skipping NuGet push."
);
return;
}
var packages = Directory.GetFiles("artifacts", "*.nupkg");
if (packages.Length == 0)
{
Console.WriteLine("No packages found in artifacts directory.");
return;
}
foreach (var package in packages)
{
Console.WriteLine($"Pushing {package} to NuGet.org");
try
{
// Note: API key is passed via command line argument which is standard practice for dotnet nuget push
// The key is already in an environment variable and not displayed in normal output
Run(
"dotnet",
$"nuget push \"{package}\" --api-key {apiKey} --source https://api.nuget.org/v3/index.json --skip-duplicate"
);
}
catch (Exception ex)
{
Console.WriteLine($"Failed to push {package}: {ex.Message}");
throw;
}
}
}
);
Target("default", [Publish], () => Console.WriteLine("Done!"));
await RunTargetsAndExitAsync(args);
static async Task<(string version, bool isPrerelease)> GetVersion()
{
// Check if current commit has a version tag
var currentTag = (await GetGitOutput("tag", "--points-at HEAD"))
.Split('\n', StringSplitOptions.RemoveEmptyEntries)
.FirstOrDefault(tag => Regex.IsMatch(tag.Trim(), @"^\d+\.\d+\.\d+$"));
if (!string.IsNullOrEmpty(currentTag))
{
// Tagged release - use the tag as version
var version = currentTag.Trim();
Console.WriteLine($"Building tagged release version: {version}");
return (version, false);
}
else
{
// Not tagged - create prerelease version based on next minor version
var allTags = (await GetGitOutput("tag", "--list"))
.Split('\n', StringSplitOptions.RemoveEmptyEntries)
.Where(tag => Regex.IsMatch(tag.Trim(), @"^\d+\.\d+\.\d+$"))
.Select(tag => tag.Trim())
.ToList();
var lastTag = allTags.OrderBy(tag => Version.Parse(tag)).LastOrDefault() ?? "0.0.0";
var lastVersion = Version.Parse(lastTag);
// Increment minor version for next release
var nextVersion = new Version(lastVersion.Major, lastVersion.Minor + 1, 0);
// Use commit count since the last version tag if available; otherwise, fall back to total count
var revListArgs = allTags.Any() ? $"--count {lastTag}..HEAD" : "--count HEAD";
var commitCount = (await GetGitOutput("rev-list", revListArgs)).Trim();
var version = $"{nextVersion}-beta.{commitCount}";
Console.WriteLine($"Building prerelease version: {version}");
return (version, true);
}
}
static async Task<string> GetGitOutput(string command, string args)
{
try
{
// Use SimpleExec's Read to execute git commands in a cross-platform way
var (output, _) = await ReadAsync("git", $"{command} {args}");
return output;
}
catch (Exception ex)
{
throw new Exception($"Git command failed: git {command} {args}\n{ex.Message}", ex);
}
}

View File

@@ -1,7 +1,7 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net10.0</TargetFramework>
<TargetFramework>net8.0</TargetFramework>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Bullseye" />

View File

@@ -1,12 +1,12 @@
{
"version": 2,
"dependencies": {
"net10.0": {
"net8.0": {
"Bullseye": {
"type": "Direct",
"requested": "[6.1.0, )",
"resolved": "6.1.0",
"contentHash": "fltnAJDe0BEX5eymXGUq+il2rSUA0pHqUonNDRH2TrvRu8SkU17mYG0IVpdmG2ibtfhdjNrv4CuTCxHOwcozCA=="
"requested": "[6.0.0, )",
"resolved": "6.0.0",
"contentHash": "vgwwXfzs7jJrskWH7saHRMgPzziq/e86QZNWY1MnMxd7e+De7E7EX4K3C7yrvaK9y02SJoLxNxcLG/q5qUAghw=="
},
"Glob": {
"type": "Direct",
@@ -16,9 +16,9 @@
},
"SimpleExec": {
"type": "Direct",
"requested": "[12.1.0, )",
"resolved": "12.1.0",
"contentHash": "PcCSAlMcKr5yTd571MgEMoGmoSr+omwziq2crB47lKP740lrmjuBocAUXHj+Q6LR6aUDFyhszot2wbtFJTClkA=="
"requested": "[12.0.0, )",
"resolved": "12.0.0",
"contentHash": "ptxlWtxC8vM6Y6e3h9ZTxBBkOWnWrm/Sa1HT+2i1xcXY3Hx2hmKDZP5RShPf8Xr9D+ivlrXNy57ktzyH8kyt+Q=="
}
}
}

View File

@@ -1,6 +1,6 @@
{
"sdk": {
"version": "10.0.100",
"version": "8.0.100",
"rollForward": "latestFeature"
}
}

View File

@@ -8,7 +8,7 @@ using SharpCompress.Readers;
namespace SharpCompress.Archives;
public abstract class AbstractArchive<TEntry, TVolume> : IArchive
public abstract class AbstractArchive<TEntry, TVolume> : IArchive, IArchiveExtractionListener
where TEntry : IArchiveEntry
where TVolume : IVolume
{
@@ -17,6 +17,11 @@ public abstract class AbstractArchive<TEntry, TVolume> : IArchive
private bool _disposed;
private readonly SourceStream? _sourceStream;
public event EventHandler<ArchiveExtractionEventArgs<IArchiveEntry>>? EntryExtractionBegin;
public event EventHandler<ArchiveExtractionEventArgs<IArchiveEntry>>? EntryExtractionEnd;
public event EventHandler<CompressedBytesReadEventArgs>? CompressedBytesRead;
public event EventHandler<FilePartExtractionBeginEventArgs>? FilePartExtractionBegin;
protected ReaderOptions ReaderOptions { get; }
internal AbstractArchive(ArchiveType type, SourceStream sourceStream)
@@ -38,6 +43,12 @@ public abstract class AbstractArchive<TEntry, TVolume> : IArchive
public ArchiveType Type { get; }
void IArchiveExtractionListener.FireEntryExtractionBegin(IArchiveEntry entry) =>
EntryExtractionBegin?.Invoke(this, new ArchiveExtractionEventArgs<IArchiveEntry>(entry));
void IArchiveExtractionListener.FireEntryExtractionEnd(IArchiveEntry entry) =>
EntryExtractionEnd?.Invoke(this, new ArchiveExtractionEventArgs<IArchiveEntry>(entry));
private static Stream CheckStreams(Stream stream)
{
if (!stream.CanSeek || !stream.CanRead)
@@ -88,12 +99,38 @@ public abstract class AbstractArchive<TEntry, TVolume> : IArchive
}
}
private void EnsureEntriesLoaded()
void IArchiveExtractionListener.EnsureEntriesLoaded()
{
_lazyEntries.EnsureFullyLoaded();
_lazyVolumes.EnsureFullyLoaded();
}
void IExtractionListener.FireCompressedBytesRead(
long currentPartCompressedBytes,
long compressedReadBytes
) =>
CompressedBytesRead?.Invoke(
this,
new CompressedBytesReadEventArgs(
currentFilePartCompressedBytesRead: currentPartCompressedBytes,
compressedBytesRead: compressedReadBytes
)
);
void IExtractionListener.FireFilePartExtractionBegin(
string name,
long size,
long compressedSize
) =>
FilePartExtractionBegin?.Invoke(
this,
new FilePartExtractionBeginEventArgs(
compressedSize: compressedSize,
size: size,
name: name
)
);
/// <summary>
/// Use this method to extract all entries in an archive in order.
/// This is primarily for SOLID Rar Archives or 7Zip Archives as they need to be
@@ -109,11 +146,11 @@ public abstract class AbstractArchive<TEntry, TVolume> : IArchive
{
if (!IsSolid && Type != ArchiveType.SevenZip)
{
throw new SharpCompressException(
throw new InvalidOperationException(
"ExtractAllEntries can only be used on solid archives or 7Zip archives (which require random access)."
);
}
EnsureEntriesLoaded();
((IArchiveExtractionListener)this).EnsureEntriesLoaded();
return CreateReaderForSolidExtraction();
}
@@ -124,11 +161,6 @@ public abstract class AbstractArchive<TEntry, TVolume> : IArchive
/// </summary>
public virtual bool IsSolid => false;
/// <summary>
/// Archive is ENCRYPTED (this means the Archive has password-protected files).
/// </summary>
public virtual bool IsEncrypted => false;
/// <summary>
/// The archive can find all the parts of the archive needed to fully extract the archive. This forces the parsing of the entire archive.
/// </summary>
@@ -136,7 +168,7 @@ public abstract class AbstractArchive<TEntry, TVolume> : IArchive
{
get
{
EnsureEntriesLoaded();
((IArchiveExtractionListener)this).EnsureEntriesLoaded();
return Entries.All(x => x.IsComplete);
}
}

View File

@@ -7,6 +7,12 @@ namespace SharpCompress.Archives;
public interface IArchive : IDisposable
{
event EventHandler<ArchiveExtractionEventArgs<IArchiveEntry>> EntryExtractionBegin;
event EventHandler<ArchiveExtractionEventArgs<IArchiveEntry>> EntryExtractionEnd;
event EventHandler<CompressedBytesReadEventArgs> CompressedBytesRead;
event EventHandler<FilePartExtractionBeginEventArgs> FilePartExtractionBegin;
IEnumerable<IArchiveEntry> Entries { get; }
IEnumerable<IVolume> Volumes { get; }

View File

@@ -1,4 +1,3 @@
using System;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
@@ -9,153 +8,126 @@ namespace SharpCompress.Archives;
public static class IArchiveEntryExtensions
{
private const int BufferSize = 81920;
/// <param name="archiveEntry">The archive entry to extract.</param>
extension(IArchiveEntry archiveEntry)
public static void WriteTo(this IArchiveEntry archiveEntry, Stream streamToWriteTo)
{
/// <summary>
/// Extract entry to the specified stream.
/// </summary>
/// <param name="streamToWriteTo">The stream to write the entry content to.</param>
/// <param name="progress">Optional progress reporter for tracking extraction progress.</param>
public void WriteTo(Stream streamToWriteTo, IProgress<ProgressReport>? progress = null)
if (archiveEntry.IsDirectory)
{
if (archiveEntry.IsDirectory)
{
throw new ExtractionException("Entry is a file directory and cannot be extracted.");
}
using var entryStream = archiveEntry.OpenEntryStream();
var sourceStream = WrapWithProgress(entryStream, archiveEntry, progress);
sourceStream.CopyTo(streamToWriteTo, BufferSize);
throw new ExtractionException("Entry is a file directory and cannot be extracted.");
}
/// <summary>
/// Extract entry to the specified stream asynchronously.
/// </summary>
/// <param name="streamToWriteTo">The stream to write the entry content to.</param>
/// <param name="cancellationToken">Cancellation token.</param>
/// <param name="progress">Optional progress reporter for tracking extraction progress.</param>
public async Task WriteToAsync(
Stream streamToWriteTo,
IProgress<ProgressReport>? progress = null,
CancellationToken cancellationToken = default
)
var streamListener = (IArchiveExtractionListener)archiveEntry.Archive;
streamListener.EnsureEntriesLoaded();
streamListener.FireEntryExtractionBegin(archiveEntry);
streamListener.FireFilePartExtractionBegin(
archiveEntry.Key ?? "Key",
archiveEntry.Size,
archiveEntry.CompressedSize
);
var entryStream = archiveEntry.OpenEntryStream();
using (entryStream)
{
if (archiveEntry.IsDirectory)
{
throw new ExtractionException("Entry is a file directory and cannot be extracted.");
}
using var entryStream = await archiveEntry.OpenEntryStreamAsync(cancellationToken);
var sourceStream = WrapWithProgress(entryStream, archiveEntry, progress);
await sourceStream
.CopyToAsync(streamToWriteTo, BufferSize, cancellationToken)
.ConfigureAwait(false);
using Stream s = new ListeningStream(streamListener, entryStream);
s.CopyTo(streamToWriteTo);
}
streamListener.FireEntryExtractionEnd(archiveEntry);
}
private static Stream WrapWithProgress(
Stream source,
IArchiveEntry entry,
IProgress<ProgressReport>? progress
public static async Task WriteToAsync(
this IArchiveEntry archiveEntry,
Stream streamToWriteTo,
CancellationToken cancellationToken = default
)
{
if (progress is null)
if (archiveEntry.IsDirectory)
{
return source;
throw new ExtractionException("Entry is a file directory and cannot be extracted.");
}
var entryPath = entry.Key ?? string.Empty;
var totalBytes = GetEntrySizeSafe(entry);
return new ProgressReportingStream(
source,
progress,
entryPath,
totalBytes,
leaveOpen: true
var streamListener = (IArchiveExtractionListener)archiveEntry.Archive;
streamListener.EnsureEntriesLoaded();
streamListener.FireEntryExtractionBegin(archiveEntry);
streamListener.FireFilePartExtractionBegin(
archiveEntry.Key ?? "Key",
archiveEntry.Size,
archiveEntry.CompressedSize
);
}
private static long? GetEntrySizeSafe(IArchiveEntry entry)
{
try
var entryStream = archiveEntry.OpenEntryStream();
using (entryStream)
{
var size = entry.Size;
return size >= 0 ? size : null;
}
catch (NotImplementedException)
{
return null;
using Stream s = new ListeningStream(streamListener, entryStream);
await s.CopyToAsync(streamToWriteTo, 81920, cancellationToken).ConfigureAwait(false);
}
streamListener.FireEntryExtractionEnd(archiveEntry);
}
extension(IArchiveEntry entry)
{
/// <summary>
/// Extract to specific directory, retaining filename
/// </summary>
public void WriteToDirectory(
string destinationDirectory,
ExtractionOptions? options = null
) =>
ExtractionMethods.WriteEntryToDirectory(
entry,
destinationDirectory,
options,
entry.WriteToFile
);
/// <summary>
/// Extract to specific directory, retaining filename
/// </summary>
public static void WriteToDirectory(
this IArchiveEntry entry,
string destinationDirectory,
ExtractionOptions? options = null
) =>
ExtractionMethods.WriteEntryToDirectory(
entry,
destinationDirectory,
options,
entry.WriteToFile
);
/// <summary>
/// Extract to specific directory asynchronously, retaining filename
/// </summary>
public Task WriteToDirectoryAsync(
string destinationDirectory,
ExtractionOptions? options = null,
CancellationToken cancellationToken = default
) =>
ExtractionMethods.WriteEntryToDirectoryAsync(
entry,
destinationDirectory,
options,
entry.WriteToFileAsync,
cancellationToken
);
/// <summary>
/// Extract to specific directory asynchronously, retaining filename
/// </summary>
public static Task WriteToDirectoryAsync(
this IArchiveEntry entry,
string destinationDirectory,
ExtractionOptions? options = null,
CancellationToken cancellationToken = default
) =>
ExtractionMethods.WriteEntryToDirectoryAsync(
entry,
destinationDirectory,
options,
(x, opt) => entry.WriteToFileAsync(x, opt, cancellationToken),
cancellationToken
);
/// <summary>
/// Extract to specific file
/// </summary>
public void WriteToFile(string destinationFileName, ExtractionOptions? options = null) =>
ExtractionMethods.WriteEntryToFile(
entry,
destinationFileName,
options,
(x, fm) =>
{
using var fs = File.Open(destinationFileName, fm);
entry.WriteTo(fs);
}
);
/// <summary>
/// Extract to specific file
/// </summary>
public static void WriteToFile(
this IArchiveEntry entry,
string destinationFileName,
ExtractionOptions? options = null
) =>
ExtractionMethods.WriteEntryToFile(
entry,
destinationFileName,
options,
(x, fm) =>
{
using var fs = File.Open(destinationFileName, fm);
entry.WriteTo(fs);
}
);
/// <summary>
/// Extract to specific file asynchronously
/// </summary>
public Task WriteToFileAsync(
string destinationFileName,
ExtractionOptions? options = null,
CancellationToken cancellationToken = default
) =>
ExtractionMethods.WriteEntryToFileAsync(
entry,
destinationFileName,
options,
async (x, fm, ct) =>
{
using var fs = File.Open(destinationFileName, fm);
await entry.WriteToAsync(fs, null, ct).ConfigureAwait(false);
},
cancellationToken
);
}
/// <summary>
/// Extract to specific file asynchronously
/// </summary>
public static Task WriteToFileAsync(
this IArchiveEntry entry,
string destinationFileName,
ExtractionOptions? options = null,
CancellationToken cancellationToken = default
) =>
ExtractionMethods.WriteEntryToFileAsync(
entry,
destinationFileName,
options,
async (x, fm) =>
{
using var fs = File.Open(destinationFileName, fm);
await entry.WriteToAsync(fs, cancellationToken).ConfigureAwait(false);
}
);
}

View File

@@ -1,8 +1,8 @@
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.Readers;
@@ -10,159 +10,76 @@ namespace SharpCompress.Archives;
public static class IArchiveExtensions
{
/// <param name="archive">The archive to extract.</param>
extension(IArchive archive)
/// <summary>
/// Extract to specific directory, retaining filename
/// </summary>
public static void WriteToDirectory(
this IArchive archive,
string destinationDirectory,
ExtractionOptions? options = null
)
{
/// <summary>
/// Extract to specific directory with progress reporting
/// </summary>
/// <param name="destinationDirectory">The folder to extract into.</param>
/// <param name="options">Extraction options.</param>
/// <param name="progress">Optional progress reporter for tracking extraction progress.</param>
public void WriteToDirectory(
string destinationDirectory,
ExtractionOptions? options = null,
IProgress<ProgressReport>? progress = null
)
using var reader = archive.ExtractAllEntries();
reader.WriteAllToDirectory(destinationDirectory, options);
}
/// <summary>
/// Extracts the archive to the destination directory. Directories will be created as needed.
/// </summary>
/// <param name="archive">The archive to extract.</param>
/// <param name="destination">The folder to extract into.</param>
/// <param name="progressReport">Optional progress report callback.</param>
/// <param name="cancellationToken">Optional cancellation token.</param>
public static void ExtractToDirectory(
this IArchive archive,
string destination,
Action<double>? progressReport = null,
CancellationToken cancellationToken = default
)
{
// Prepare for progress reporting
var totalBytes = archive.TotalUncompressSize;
var bytesRead = 0L;
// Tracking for created directories.
var seenDirectories = new HashSet<string>();
// Extract
foreach (var entry in archive.Entries)
{
// For solid archives (Rar, 7Zip), use the optimized reader-based approach
if (archive.IsSolid || archive.Type == ArchiveType.SevenZip)
{
using var reader = archive.ExtractAllEntries();
reader.WriteAllToDirectory(destinationDirectory, options);
}
else
{
// For non-solid archives, extract entries directly
archive.WriteToDirectoryInternal(destinationDirectory, options, progress);
}
}
cancellationToken.ThrowIfCancellationRequested();
private void WriteToDirectoryInternal(
string destinationDirectory,
ExtractionOptions? options,
IProgress<ProgressReport>? progress
)
{
// Prepare for progress reporting
var totalBytes = archive.TotalUncompressSize;
var bytesRead = 0L;
// Tracking for created directories.
var seenDirectories = new HashSet<string>();
// Extract
foreach (var entry in archive.Entries)
if (entry.IsDirectory)
{
if (entry.IsDirectory)
var dirPath = Path.Combine(destination, entry.Key.NotNull("Entry Key is null"));
if (
Path.GetDirectoryName(dirPath + "/") is { } emptyDirectory
&& seenDirectories.Add(dirPath)
)
{
var dirPath = Path.Combine(
destinationDirectory,
entry.Key.NotNull("Entry Key is null")
);
if (
Path.GetDirectoryName(dirPath + "/") is { } parentDirectory
&& seenDirectories.Add(dirPath)
)
{
Directory.CreateDirectory(parentDirectory);
}
continue;
Directory.CreateDirectory(emptyDirectory);
}
// Use the entry's WriteToDirectory method which respects ExtractionOptions
entry.WriteToDirectory(destinationDirectory, options);
// Update progress
bytesRead += entry.Size;
progress?.Report(
new ProgressReport(entry.Key ?? string.Empty, bytesRead, totalBytes)
);
continue;
}
}
/// <summary>
/// Extract to specific directory asynchronously with progress reporting and cancellation support
/// </summary>
/// <param name="destinationDirectory">The folder to extract into.</param>
/// <param name="options">Extraction options.</param>
/// <param name="progress">Optional progress reporter for tracking extraction progress.</param>
/// <param name="cancellationToken">Optional cancellation token.</param>
public async Task WriteToDirectoryAsync(
string destinationDirectory,
ExtractionOptions? options = null,
IProgress<ProgressReport>? progress = null,
CancellationToken cancellationToken = default
)
{
// For solid archives (Rar, 7Zip), use the optimized reader-based approach
if (archive.IsSolid || archive.Type == ArchiveType.SevenZip)
// Create each directory if not already created
var path = Path.Combine(destination, entry.Key.NotNull("Entry Key is null"));
if (Path.GetDirectoryName(path) is { } directory)
{
using var reader = archive.ExtractAllEntries();
await reader.WriteAllToDirectoryAsync(
destinationDirectory,
options,
cancellationToken
);
}
else
{
// For non-solid archives, extract entries directly
await archive.WriteToDirectoryAsyncInternal(
destinationDirectory,
options,
progress,
cancellationToken
);
}
}
private async Task WriteToDirectoryAsyncInternal(
string destinationDirectory,
ExtractionOptions? options,
IProgress<ProgressReport>? progress,
CancellationToken cancellationToken
)
{
// Prepare for progress reporting
var totalBytes = archive.TotalUncompressSize;
var bytesRead = 0L;
// Tracking for created directories.
var seenDirectories = new HashSet<string>();
// Extract
foreach (var entry in archive.Entries)
{
cancellationToken.ThrowIfCancellationRequested();
if (entry.IsDirectory)
if (!Directory.Exists(directory) && !seenDirectories.Contains(directory))
{
var dirPath = Path.Combine(
destinationDirectory,
entry.Key.NotNull("Entry Key is null")
);
if (
Path.GetDirectoryName(dirPath + "/") is { } parentDirectory
&& seenDirectories.Add(dirPath)
)
{
Directory.CreateDirectory(parentDirectory);
}
continue;
Directory.CreateDirectory(directory);
seenDirectories.Add(directory);
}
// Use the entry's WriteToDirectoryAsync method which respects ExtractionOptions
await entry
.WriteToDirectoryAsync(destinationDirectory, options, cancellationToken)
.ConfigureAwait(false);
// Update progress
bytesRead += entry.Size;
progress?.Report(
new ProgressReport(entry.Key ?? string.Empty, bytesRead, totalBytes)
);
}
// Write file
using var fs = File.Create(path);
entry.WriteTo(fs);
// Update progress
bytesRead += entry.Size;
progressReport?.Invoke(bytesRead / (double)totalBytes);
}
}
}

View File

@@ -0,0 +1,10 @@
using SharpCompress.Common;
namespace SharpCompress.Archives;
internal interface IArchiveExtractionListener : IExtractionListener
{
void EnsureEntriesLoaded();
void FireEntryExtractionBegin(IArchiveEntry entry);
void FireEntryExtractionEnd(IArchiveEntry entry);
}

View File

@@ -84,8 +84,6 @@ public class RarArchive : AbstractArchive<RarArchiveEntry, RarVolume>
public override bool IsSolid => Volumes.First().IsSolidArchive;
public override bool IsEncrypted => Entries.First(x => !x.IsDirectory).IsEncrypted;
public virtual int MinVersion => Volumes.First().MinVersion;
public virtual int MaxVersion => Volumes.First().MaxVersion;

View File

@@ -76,7 +76,7 @@ public class RarArchiveEntry : RarEntry, IArchiveEntry
stream = new RarStream(
archive.UnpackV1.Value,
FileHeader,
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>())
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>(), archive)
);
}
else
@@ -84,7 +84,7 @@ public class RarArchiveEntry : RarEntry, IArchiveEntry
stream = new RarStream(
archive.UnpackV2017.Value,
FileHeader,
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>())
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>(), archive)
);
}
@@ -100,7 +100,7 @@ public class RarArchiveEntry : RarEntry, IArchiveEntry
stream = new RarStream(
archive.UnpackV1.Value,
FileHeader,
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>())
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>(), archive)
);
}
else
@@ -108,7 +108,7 @@ public class RarArchiveEntry : RarEntry, IArchiveEntry
stream = new RarStream(
archive.UnpackV2017.Value,
FileHeader,
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>())
new MultiVolumeReadOnlyStream(Parts.Cast<RarFilePart>(), archive)
);
}

View File

@@ -2,8 +2,6 @@ using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.Common.SevenZip;
using SharpCompress.Compressors.LZMA.Utilites;
@@ -207,15 +205,15 @@ public class SevenZipArchive : AbstractArchive<SevenZipArchiveEntry, SevenZipVol
.GroupBy(x => x.FilePart.Folder)
.Any(folder => folder.Count() > 1);
public override bool IsEncrypted => Entries.First(x => !x.IsDirectory).IsEncrypted;
public override long TotalSize =>
_database?._packSizes.Aggregate(0L, (total, packSize) => total + packSize) ?? 0;
private sealed class SevenZipReader : AbstractReader<SevenZipEntry, SevenZipVolume>
{
private readonly SevenZipArchive _archive;
private SevenZipEntry? _currentEntry;
private CFolder? _currentFolder;
private Stream? _currentStream;
private CFileItem? _currentItem;
internal SevenZipReader(ReaderOptions readerOptions, SevenZipArchive archive)
: base(readerOptions, ArchiveType.SevenZip) => this._archive = archive;
@@ -228,135 +226,40 @@ public class SevenZipArchive : AbstractArchive<SevenZipArchiveEntry, SevenZipVol
stream.Position = 0;
foreach (var dir in entries.Where(x => x.IsDirectory))
{
_currentEntry = dir;
yield return dir;
}
// For non-directory entries, yield them without creating shared streams
// Each call to GetEntryStream() will create a fresh decompression stream
// to avoid state corruption issues with async operations
foreach (var entry in entries.Where(x => !x.IsDirectory))
foreach (
var group in entries.Where(x => !x.IsDirectory).GroupBy(x => x.FilePart.Folder)
)
{
_currentEntry = entry;
yield return entry;
_currentFolder = group.Key;
if (group.Key is null)
{
_currentStream = Stream.Null;
}
else
{
_currentStream = _archive._database?.GetFolderStream(
stream,
_currentFolder,
new PasswordProvider(Options.Password)
);
}
foreach (var entry in group)
{
_currentItem = entry.FilePart.Header;
yield return entry;
}
}
}
protected override EntryStream GetEntryStream()
{
// Create a fresh decompression stream for each file (no state sharing).
// However, the LZMA decoder has bugs in its async implementation that cause
// state corruption even on fresh streams. The SyncOnlyStream wrapper
// works around these bugs by forcing async operations to use sync equivalents.
//
// TODO: Fix the LZMA decoder async bugs (in LzmaStream, Decoder, OutWindow)
// so this wrapper is no longer necessary.
var entry = _currentEntry.NotNull("currentEntry is not null");
if (entry.IsDirectory)
{
return CreateEntryStream(Stream.Null);
}
return CreateEntryStream(new SyncOnlyStream(entry.FilePart.GetCompressedStream()));
}
}
/// <summary>
/// WORKAROUND: Forces async operations to use synchronous equivalents.
/// This is necessary because the LZMA decoder has bugs in its async implementation
/// that cause state corruption (IndexOutOfRangeException, DataErrorException).
///
/// The proper fix would be to repair the LZMA decoder's async methods
/// (LzmaStream.ReadAsync, Decoder.CodeAsync, OutWindow async operations),
/// but that requires deep changes to the decoder state machine.
/// </summary>
private sealed class SyncOnlyStream : Stream
{
private readonly Stream _baseStream;
public SyncOnlyStream(Stream baseStream) => _baseStream = baseStream;
public override bool CanRead => _baseStream.CanRead;
public override bool CanSeek => _baseStream.CanSeek;
public override bool CanWrite => _baseStream.CanWrite;
public override long Length => _baseStream.Length;
public override long Position
{
get => _baseStream.Position;
set => _baseStream.Position = value;
}
public override void Flush() => _baseStream.Flush();
public override int Read(byte[] buffer, int offset, int count) =>
_baseStream.Read(buffer, offset, count);
public override long Seek(long offset, SeekOrigin origin) =>
_baseStream.Seek(offset, origin);
public override void SetLength(long value) => _baseStream.SetLength(value);
public override void Write(byte[] buffer, int offset, int count) =>
_baseStream.Write(buffer, offset, count);
// Force async operations to use sync equivalents to avoid LZMA decoder bugs
public override Task<int> ReadAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken
)
{
cancellationToken.ThrowIfCancellationRequested();
return Task.FromResult(_baseStream.Read(buffer, offset, count));
}
public override Task WriteAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken
)
{
cancellationToken.ThrowIfCancellationRequested();
_baseStream.Write(buffer, offset, count);
return Task.CompletedTask;
}
public override Task FlushAsync(CancellationToken cancellationToken)
{
cancellationToken.ThrowIfCancellationRequested();
_baseStream.Flush();
return Task.CompletedTask;
}
#if !NETFRAMEWORK && !NETSTANDARD2_0
public override ValueTask<int> ReadAsync(
Memory<byte> buffer,
CancellationToken cancellationToken = default
)
{
cancellationToken.ThrowIfCancellationRequested();
return new ValueTask<int>(_baseStream.Read(buffer.Span));
}
public override ValueTask WriteAsync(
ReadOnlyMemory<byte> buffer,
CancellationToken cancellationToken = default
)
{
cancellationToken.ThrowIfCancellationRequested();
_baseStream.Write(buffer.Span);
return ValueTask.CompletedTask;
}
#endif
protected override void Dispose(bool disposing)
{
if (disposing)
{
_baseStream.Dispose();
}
base.Dispose(disposing);
}
protected override EntryStream GetEntryStream() =>
CreateEntryStream(
new ReadOnlySubStream(
_currentStream.NotNull("currentStream is not null"),
_currentItem?.Size ?? 0
)
);
}
private class PasswordProvider : IPasswordProvider

View File

@@ -1,8 +1,7 @@
using System;
using System.Runtime.CompilerServices;
// CLSCompliant(false) is required because ZStandard integration uses unsafe code
[assembly: CLSCompliant(false)]
[assembly: CLSCompliant(true)]
[assembly: InternalsVisibleTo(
"SharpCompress.Test,PublicKey=0024000004800000940000000602000000240000525341310004000001000100158bebf1433f76dffc356733c138babea7a47536c65ed8009b16372c6f4edbb20554db74a62687f56b97c20a6ce8c4b123280279e33c894e7b3aa93ab3c573656fde4db576cfe07dba09619ead26375b25d2c4a8e43f7be257d712b0dd2eb546f67adb09281338618a58ac834fc038dd7e2740a7ab3591826252e4f4516306dc"
)]

View File

@@ -57,7 +57,7 @@ namespace SharpCompress.Common.Arc
return value switch
{
1 or 2 => CompressionType.None,
3 => CompressionType.Packed,
3 => CompressionType.RLE90,
4 => CompressionType.Squeezed,
5 or 6 or 7 or 8 => CompressionType.Crunched,
9 => CompressionType.Squashed,

View File

@@ -44,7 +44,7 @@ namespace SharpCompress.Common.Arc
Header.CompressedSize
);
break;
case CompressionType.Packed:
case CompressionType.RLE90:
compressedStream = new RunLength90Stream(
_stream,
(int)Header.CompressedSize
@@ -54,14 +54,6 @@ namespace SharpCompress.Common.Arc
compressedStream = new SqueezeStream(_stream, (int)Header.CompressedSize);
break;
case CompressionType.Crunched:
if (Header.OriginalSize > 128 * 1024)
{
throw new NotSupportedException(
"CompressionMethod: "
+ Header.CompressionMethod
+ " with size > 128KB"
);
}
compressedStream = new ArcLzwStream(
_stream,
(int)Header.CompressedSize,

View File

@@ -0,0 +1,10 @@
using System;
namespace SharpCompress.Common;
public class ArchiveExtractionEventArgs<T> : EventArgs
{
internal ArchiveExtractionEventArgs(T entry) => Item = entry;
public T Item { get; }
}

View File

@@ -38,22 +38,6 @@ namespace SharpCompress.Common.Arj
Header.CompressedSize
);
break;
case CompressionMethod.CompressedMost:
case CompressionMethod.Compressed:
case CompressionMethod.CompressedFaster:
if (Header.OriginalSize > 128 * 1024)
{
throw new NotSupportedException(
"CompressionMethod: "
+ Header.CompressionMethod
+ " with size > 128KB"
);
}
compressedStream = new LhaStream<Lh7DecoderCfg>(
_stream,
(int)Header.OriginalSize
);
break;
case CompressionMethod.CompressedFastest:
compressedStream = new LHDecoderStream(_stream, (int)Header.OriginalSize);
break;

View File

@@ -0,0 +1,25 @@
using System;
namespace SharpCompress.Common;
public sealed class CompressedBytesReadEventArgs : EventArgs
{
public CompressedBytesReadEventArgs(
long compressedBytesRead,
long currentFilePartCompressedBytesRead
)
{
CompressedBytesRead = compressedBytesRead;
CurrentFilePartCompressedBytesRead = currentFilePartCompressedBytesRead;
}
/// <summary>
/// Compressed bytes read for the current entry
/// </summary>
public long CompressedBytesRead { get; }
/// <summary>
/// Current file part read for Multipart files (e.g. Rar)
/// </summary>
public long CurrentFilePartCompressedBytesRead { get; }
}

View File

@@ -23,7 +23,7 @@ public enum CompressionType
Reduce4,
Explode,
Squeezed,
Packed,
RLE90,
Crunched,
Squashed,
Crushed,

View File

@@ -128,7 +128,7 @@ internal static class ExtractionMethods
IEntry entry,
string destinationDirectory,
ExtractionOptions? options,
Func<string, ExtractionOptions?, CancellationToken, Task> writeAsync,
Func<string, ExtractionOptions?, Task> writeAsync,
CancellationToken cancellationToken = default
)
{
@@ -189,7 +189,7 @@ internal static class ExtractionMethods
"Entry is trying to write a file outside of the destination directory."
);
}
await writeAsync(destinationFileName, options, cancellationToken).ConfigureAwait(false);
await writeAsync(destinationFileName, options).ConfigureAwait(false);
}
else if (options.ExtractFullPath && !Directory.Exists(destinationFileName))
{
@@ -201,7 +201,7 @@ internal static class ExtractionMethods
IEntry entry,
string destinationFileName,
ExtractionOptions? options,
Func<string, FileMode, CancellationToken, Task> openAndWriteAsync,
Func<string, FileMode, Task> openAndWriteAsync,
CancellationToken cancellationToken = default
)
{
@@ -225,8 +225,7 @@ internal static class ExtractionMethods
fm = FileMode.CreateNew;
}
await openAndWriteAsync(destinationFileName, fm, cancellationToken)
.ConfigureAwait(false);
await openAndWriteAsync(destinationFileName, fm).ConfigureAwait(false);
entry.PreserveExtractionOptions(destinationFileName, options);
}
}

View File

@@ -0,0 +1,28 @@
using System;
namespace SharpCompress.Common;
public sealed class FilePartExtractionBeginEventArgs : EventArgs
{
public FilePartExtractionBeginEventArgs(string name, long size, long compressedSize)
{
Name = name;
Size = size;
CompressedSize = compressedSize;
}
/// <summary>
/// File name for the part for the current entry
/// </summary>
public string Name { get; }
/// <summary>
/// Uncompressed size of the current entry in the part
/// </summary>
public long Size { get; }
/// <summary>
/// Compressed size of the current entry in the part
/// </summary>
public long CompressedSize { get; }
}

View File

@@ -0,0 +1,7 @@
namespace SharpCompress.Common;
public interface IExtractionListener
{
void FireFilePartExtractionBegin(string name, long size, long compressedSize);
void FireCompressedBytesRead(long currentPartCompressedBytes, long compressedReadBytes);
}

View File

@@ -1,43 +0,0 @@
namespace SharpCompress.Common;
/// <summary>
/// Represents progress information for compression or extraction operations.
/// </summary>
public sealed class ProgressReport
{
/// <summary>
/// Initializes a new instance of the <see cref="ProgressReport"/> class.
/// </summary>
/// <param name="entryPath">The path of the entry being processed.</param>
/// <param name="bytesTransferred">Number of bytes transferred so far.</param>
/// <param name="totalBytes">Total bytes to be transferred, or null if unknown.</param>
public ProgressReport(string entryPath, long bytesTransferred, long? totalBytes)
{
EntryPath = entryPath;
BytesTransferred = bytesTransferred;
TotalBytes = totalBytes;
}
/// <summary>
/// Gets the path of the entry being processed.
/// </summary>
public string EntryPath { get; }
/// <summary>
/// Gets the number of bytes transferred so far.
/// </summary>
public long BytesTransferred { get; }
/// <summary>
/// Gets the total number of bytes to be transferred, or null if unknown.
/// </summary>
public long? TotalBytes { get; }
/// <summary>
/// Gets the progress percentage (0-100), or null if total bytes is unknown.
/// </summary>
public double? PercentComplete =>
TotalBytes.HasValue && TotalBytes.Value > 0
? (double)BytesTransferred / TotalBytes.Value * 100
: null;
}

View File

@@ -0,0 +1,17 @@
using System;
using SharpCompress.Readers;
namespace SharpCompress.Common;
public sealed class ReaderExtractionEventArgs<T> : EventArgs
{
internal ReaderExtractionEventArgs(T entry, ReaderProgress? readerProgress = null)
{
Item = entry;
ReaderProgress = readerProgress;
}
public T Item { get; }
public ReaderProgress? ReaderProgress { get; }
}

View File

@@ -1,6 +1,5 @@
using System;
using System.Buffers.Binary;
using System.Collections.Generic;
using System.IO;
using System.Text;
@@ -10,16 +9,8 @@ internal sealed class TarHeader
{
internal static readonly DateTime EPOCH = new(1970, 1, 1, 0, 0, 0, DateTimeKind.Utc);
public TarHeader(
ArchiveEncoding archiveEncoding,
TarHeaderWriteFormat writeFormat = TarHeaderWriteFormat.GNU_TAR_LONG_LINK
)
{
ArchiveEncoding = archiveEncoding;
WriteFormat = writeFormat;
}
public TarHeader(ArchiveEncoding archiveEncoding) => ArchiveEncoding = archiveEncoding;
internal TarHeaderWriteFormat WriteFormat { get; set; }
internal string? Name { get; set; }
internal string? LinkName { get; set; }
@@ -34,119 +25,7 @@ internal sealed class TarHeader
internal const int BLOCK_SIZE = 512;
// Maximum size for long name/link headers to prevent memory exhaustion attacks
// This is generous enough for most real-world scenarios (32KB)
private const int MAX_LONG_NAME_SIZE = 32768;
internal void Write(Stream output)
{
switch (WriteFormat)
{
case TarHeaderWriteFormat.GNU_TAR_LONG_LINK:
WriteGnuTarLongLink(output);
break;
case TarHeaderWriteFormat.USTAR:
WriteUstar(output);
break;
default:
throw new Exception("This should be impossible...");
}
}
internal void WriteUstar(Stream output)
{
var buffer = new byte[BLOCK_SIZE];
WriteOctalBytes(511, buffer, 100, 8); // file mode
WriteOctalBytes(0, buffer, 108, 8); // owner ID
WriteOctalBytes(0, buffer, 116, 8); // group ID
//ArchiveEncoding.UTF8.GetBytes("magic").CopyTo(buffer, 257);
var nameByteCount = ArchiveEncoding
.GetEncoding()
.GetByteCount(Name.NotNull("Name is null"));
if (nameByteCount > 100)
{
// if name is longer, try to split it into name and namePrefix
string fullName = Name.NotNull("Name is null");
// find all directory separators
List<int> dirSeps = new List<int>();
for (int i = 0; i < fullName.Length; i++)
{
if (fullName[i] == Path.DirectorySeparatorChar)
{
dirSeps.Add(i);
}
}
// find the right place to split the name
int splitIndex = -1;
for (int i = 0; i < dirSeps.Count; i++)
{
int count = ArchiveEncoding
.GetEncoding()
.GetByteCount(fullName.Substring(0, dirSeps[i]));
if (count < 155)
{
splitIndex = dirSeps[i];
}
else
{
break;
}
}
if (splitIndex == -1)
{
throw new Exception(
$"Tar header USTAR format can not fit file name \"{fullName}\" of length {nameByteCount}! Directory separator not found! Try using GNU Tar format instead!"
);
}
string namePrefix = fullName.Substring(0, splitIndex);
string name = fullName.Substring(splitIndex + 1);
if (this.ArchiveEncoding.GetEncoding().GetByteCount(namePrefix) >= 155)
throw new Exception(
$"Tar header USTAR format can not fit file name \"{fullName}\" of length {nameByteCount}! Try using GNU Tar format instead!"
);
if (this.ArchiveEncoding.GetEncoding().GetByteCount(name) >= 100)
throw new Exception(
$"Tar header USTAR format can not fit file name \"{fullName}\" of length {nameByteCount}! Try using GNU Tar format instead!"
);
// write name prefix
WriteStringBytes(ArchiveEncoding.Encode(namePrefix), buffer, 345, 100);
// write partial name
WriteStringBytes(ArchiveEncoding.Encode(name), buffer, 100);
}
else
{
WriteStringBytes(ArchiveEncoding.Encode(Name.NotNull("Name is null")), buffer, 100);
}
WriteOctalBytes(Size, buffer, 124, 12);
var time = (long)(LastModifiedTime.ToUniversalTime() - EPOCH).TotalSeconds;
WriteOctalBytes(time, buffer, 136, 12);
buffer[156] = (byte)EntryType;
// write ustar magic field
WriteStringBytes(Encoding.ASCII.GetBytes("ustar"), buffer, 257, 6);
// write ustar version "00"
buffer[263] = 0x30;
buffer[264] = 0x30;
var crc = RecalculateChecksum(buffer);
WriteOctalBytes(crc, buffer, 148, 8);
output.Write(buffer, 0, buffer.Length);
}
internal void WriteGnuTarLongLink(Stream output)
{
var buffer = new byte[BLOCK_SIZE];
@@ -202,7 +81,7 @@ internal sealed class TarHeader
0,
100 - ArchiveEncoding.GetEncoding().GetMaxByteCount(1)
);
WriteGnuTarLongLink(output);
Write(output);
}
}
@@ -307,15 +186,6 @@ internal sealed class TarHeader
private string ReadLongName(BinaryReader reader, byte[] buffer)
{
var size = ReadSize(buffer);
// Validate size to prevent memory exhaustion from malformed headers
if (size < 0 || size > MAX_LONG_NAME_SIZE)
{
throw new InvalidFormatException(
$"Long name size {size} is invalid or exceeds maximum allowed size of {MAX_LONG_NAME_SIZE} bytes"
);
}
var nameLength = (int)size;
var nameBytes = reader.ReadBytes(nameLength);
var remainingBytesToRead = BLOCK_SIZE - (nameLength % BLOCK_SIZE);
@@ -358,18 +228,6 @@ internal sealed class TarHeader
buffer.Slice(i, length - i).Clear();
}
private static void WriteStringBytes(
ReadOnlySpan<byte> name,
Span<byte> buffer,
int offset,
int length
)
{
name.CopyTo(buffer.Slice(offset));
var i = Math.Min(length, name.Length);
buffer.Slice(offset + i, length - i).Clear();
}
private static void WriteStringBytes(string name, byte[] buffer, int offset, int length)
{
int i;

View File

@@ -1,7 +0,0 @@
namespace SharpCompress.Common.Tar.Headers;
public enum TarHeaderWriteFormat
{
GNU_TAR_LONG_LINK,
USTAR,
}

View File

@@ -1,7 +1,6 @@
using System;
using System.Buffers.Binary;
using System.Security.Cryptography;
using System.Text;
namespace SharpCompress.Common.Zip;
@@ -20,24 +19,8 @@ internal class WinzipAesEncryptionData
{
_keySize = keySize;
#if NETFRAMEWORK
#if NETFRAMEWORK || NETSTANDARD2_0
var rfc2898 = new Rfc2898DeriveBytes(password, salt, RFC2898_ITERATIONS);
KeyBytes = rfc2898.GetBytes(KeySizeInBytes);
IvBytes = rfc2898.GetBytes(KeySizeInBytes);
var generatedVerifyValue = rfc2898.GetBytes(2);
#elif NET10_0_OR_GREATER
var derivedKeySize = (KeySizeInBytes * 2) + 2;
var passwordBytes = Encoding.UTF8.GetBytes(password);
var derivedKey = Rfc2898DeriveBytes.Pbkdf2(
passwordBytes,
salt,
RFC2898_ITERATIONS,
HashAlgorithmName.SHA1,
derivedKeySize
);
KeyBytes = derivedKey.AsSpan(0, KeySizeInBytes).ToArray();
IvBytes = derivedKey.AsSpan(KeySizeInBytes, KeySizeInBytes).ToArray();
var generatedVerifyValue = derivedKey.AsSpan((KeySizeInBytes * 2), 2).ToArray();
#else
var rfc2898 = new Rfc2898DeriveBytes(
password,
@@ -45,10 +28,11 @@ internal class WinzipAesEncryptionData
RFC2898_ITERATIONS,
HashAlgorithmName.SHA1
);
KeyBytes = rfc2898.GetBytes(KeySizeInBytes);
#endif
KeyBytes = rfc2898.GetBytes(KeySizeInBytes); // 16 or 24 or 32 ???
IvBytes = rfc2898.GetBytes(KeySizeInBytes);
var generatedVerifyValue = rfc2898.GetBytes(2);
#endif
var verify = BinaryPrimitives.ReadInt16LittleEndian(passwordVerifyValue);
var generated = BinaryPrimitives.ReadInt16LittleEndian(generatedVerifyValue);

View File

@@ -13,8 +13,8 @@ using SharpCompress.Compressors.PPMd;
using SharpCompress.Compressors.Reduce;
using SharpCompress.Compressors.Shrink;
using SharpCompress.Compressors.Xz;
using SharpCompress.Compressors.ZStandard;
using SharpCompress.IO;
using ZstdSharp;
namespace SharpCompress.Common.Zip;

View File

@@ -4,68 +4,56 @@ using System.IO;
namespace SharpCompress.Compressors.Arj
{
[CLSCompliant(true)]
public class BitReader
public sealed class BitReader
{
private readonly Stream _input;
private int _bitBuffer; // currently buffered bits
private int _bitCount; // number of bits in buffer
private readonly Stream _stream;
private int _bitBuffer;
private int _bitsRemaining;
private bool _disposed;
public BitReader(Stream input)
{
_input = input ?? throw new ArgumentNullException(nameof(input));
_bitBuffer = 0;
_bitCount = 0;
_stream = input ?? throw new ArgumentNullException(nameof(input));
if (!input.CanRead)
throw new ArgumentException("Stream must be readable.", nameof(input));
}
/// <summary>
/// Reads a single bit from the stream. Returns 0 or 1.
/// </summary>
public int ReadBit()
{
if (_bitCount == 0)
{
int nextByte = _input.ReadByte();
if (nextByte < 0)
{
throw new EndOfStreamException("No more data available in BitReader.");
}
_bitBuffer = nextByte;
_bitCount = 8;
}
int bit = (_bitBuffer >> (_bitCount - 1)) & 1;
_bitCount--;
return bit;
}
/// <summary>
/// Reads n bits (up to 32) from the stream.
/// </summary>
public int ReadBits(int count)
{
if (count < 0 || count > 32)
{
if (_disposed)
throw new ObjectDisposedException(nameof(BitReader));
if (count <= 0 || count > 32)
throw new ArgumentOutOfRangeException(
nameof(count),
"Count must be between 0 and 32."
"Bit count must be between 1 and 32."
);
}
int result = 0;
for (int i = 0; i < count; i++)
{
result = (result << 1) | ReadBit();
if (_bitsRemaining == 0)
{
int nextByte = _stream.ReadByte();
if (nextByte == -1)
throw new EndOfStreamException();
_bitBuffer = nextByte;
_bitsRemaining = 8;
}
// hoogste bit eerst
result = (result << 1) | ((_bitBuffer >> 7) & 1);
_bitBuffer <<= 1;
_bitsRemaining--;
}
return result;
}
/// <summary>
/// Resets any buffered bits.
/// </summary>
public void AlignToByte()
{
_bitCount = 0;
_bitsRemaining = 0;
_bitBuffer = 0;
}
}

View File

@@ -1,43 +0,0 @@
using System;
using System.Collections;
using System.Collections.Generic;
namespace SharpCompress.Compressors.Arj
{
/// <summary>
/// Iterator that reads & pushes values back into the ring buffer.
/// </summary>
public class HistoryIterator : IEnumerator<byte>
{
private int _index;
private readonly IRingBuffer _ring;
public HistoryIterator(IRingBuffer ring, int startIndex)
{
_ring = ring;
_index = startIndex;
}
public bool MoveNext()
{
Current = _ring[_index];
_index = unchecked(_index + 1);
// Push value back into the ring buffer
_ring.Push(Current);
return true; // iterator is infinite
}
public void Reset()
{
throw new NotSupportedException();
}
public byte Current { get; private set; }
object IEnumerator.Current => Current;
public void Dispose() { }
}
}

View File

@@ -1,218 +0,0 @@
using System;
using System.Collections.Generic;
using System.IO;
using System.Text;
namespace SharpCompress.Compressors.Arj
{
[CLSCompliant(true)]
public enum NodeType
{
Leaf,
Branch,
}
[CLSCompliant(true)]
public sealed class TreeEntry
{
public readonly NodeType Type;
public readonly int LeafValue;
public readonly int BranchIndex;
public const int MAX_INDEX = 4096;
private TreeEntry(NodeType type, int leafValue, int branchIndex)
{
Type = type;
LeafValue = leafValue;
BranchIndex = branchIndex;
}
public static TreeEntry Leaf(int value)
{
return new TreeEntry(NodeType.Leaf, value, -1);
}
public static TreeEntry Branch(int index)
{
if (index >= MAX_INDEX)
{
throw new ArgumentOutOfRangeException(
nameof(index),
"Branch index exceeds MAX_INDEX"
);
}
return new TreeEntry(NodeType.Branch, 0, index);
}
}
[CLSCompliant(true)]
public sealed class HuffTree
{
private readonly List<TreeEntry> _tree;
public HuffTree(int capacity = 0)
{
_tree = new List<TreeEntry>(capacity);
}
public void SetSingle(int value)
{
_tree.Clear();
_tree.Add(TreeEntry.Leaf(value));
}
public void BuildTree(byte[] lengths, int count)
{
if (lengths == null)
{
throw new ArgumentNullException(nameof(lengths));
}
if (count < 0 || count > lengths.Length)
{
throw new ArgumentOutOfRangeException(nameof(count));
}
if (count > TreeEntry.MAX_INDEX / 2)
{
throw new ArgumentException(
$"Count exceeds maximum allowed: {TreeEntry.MAX_INDEX / 2}"
);
}
byte[] slice = new byte[count];
Array.Copy(lengths, slice, count);
BuildTree(slice);
}
public void BuildTree(byte[] valueLengths)
{
if (valueLengths == null)
{
throw new ArgumentNullException(nameof(valueLengths));
}
if (valueLengths.Length > TreeEntry.MAX_INDEX / 2)
{
throw new InvalidOperationException("Too many code lengths");
}
_tree.Clear();
int maxAllocated = 1; // start with a single (root) node
for (byte currentLen = 1; ; currentLen++)
{
// add missing branches up to current limit
int maxLimit = maxAllocated;
for (int i = _tree.Count; i < maxLimit; i++)
{
// TreeEntry.Branch may throw if index too large
try
{
_tree.Add(TreeEntry.Branch(maxAllocated));
}
catch (ArgumentOutOfRangeException e)
{
_tree.Clear();
throw new InvalidOperationException("Branch index exceeds limit", e);
}
// each branch node allocates two children
maxAllocated += 2;
}
// fill tree with leaves found in the lengths table at the current length
bool moreLeaves = false;
for (int value = 0; value < valueLengths.Length; value++)
{
byte len = valueLengths[value];
if (len == currentLen)
{
_tree.Add(TreeEntry.Leaf(value));
}
else if (len > currentLen)
{
moreLeaves = true; // there are more leaves to process
}
}
// sanity check (too many leaves)
if (_tree.Count > maxAllocated)
{
throw new InvalidOperationException("Too many leaves");
}
// stop when no longer finding longer codes
if (!moreLeaves)
{
break;
}
}
// ensure tree is complete
if (_tree.Count != maxAllocated)
{
throw new InvalidOperationException(
$"Missing some leaves: tree count = {_tree.Count}, expected = {maxAllocated}"
);
}
}
public int ReadEntry(BitReader reader)
{
if (_tree.Count == 0)
{
throw new InvalidOperationException("Tree not initialized");
}
TreeEntry node = _tree[0];
while (true)
{
if (node.Type == NodeType.Leaf)
{
return node.LeafValue;
}
int bit = reader.ReadBit();
int index = node.BranchIndex + bit;
if (index >= _tree.Count)
{
throw new InvalidOperationException("Invalid branch index during read");
}
node = _tree[index];
}
}
public override string ToString()
{
var result = new StringBuilder();
void FormatStep(int index, string prefix)
{
var node = _tree[index];
if (node.Type == NodeType.Leaf)
{
result.AppendLine($"{prefix} -> {node.LeafValue}");
}
else
{
FormatStep(node.BranchIndex, prefix + "0");
FormatStep(node.BranchIndex + 1, prefix + "1");
}
}
if (_tree.Count > 0)
{
FormatStep(0, "");
}
return result.ToString();
}
}
}

View File

@@ -1,9 +0,0 @@
namespace SharpCompress.Compressors.Arj
{
public interface ILhaDecoderConfig
{
int HistoryBits { get; }
int OffsetBits { get; }
RingBuffer RingBuffer { get; }
}
}

View File

@@ -1,17 +0,0 @@
namespace SharpCompress.Compressors.Arj
{
public interface IRingBuffer
{
int BufferSize { get; }
int Cursor { get; }
void SetCursor(int pos);
void Push(byte value);
HistoryIterator IterFromOffset(int offset);
HistoryIterator IterFromPos(int pos);
byte this[int index] { get; }
}
}

View File

@@ -1,9 +0,0 @@
namespace SharpCompress.Compressors.Arj
{
public class Lh5DecoderCfg : ILhaDecoderConfig
{
public int HistoryBits => 14;
public int OffsetBits => 4;
public RingBuffer RingBuffer { get; } = new RingBuffer(1 << 14);
}
}

View File

@@ -1,9 +0,0 @@
namespace SharpCompress.Compressors.Arj
{
public class Lh7DecoderCfg : ILhaDecoderConfig
{
public int HistoryBits => 17;
public int OffsetBits => 5;
public RingBuffer RingBuffer { get; } = new RingBuffer(1 << 17);
}
}

View File

@@ -1,363 +0,0 @@
using System;
using System.Data;
using System.IO;
using System.Linq;
using SharpCompress.IO;
namespace SharpCompress.Compressors.Arj
{
[CLSCompliant(true)]
public sealed class LhaStream<C> : Stream, IStreamStack
where C : ILhaDecoderConfig, new()
{
private readonly BitReader _bitReader;
private readonly Stream _stream;
private readonly HuffTree _commandTree;
private readonly HuffTree _offsetTree;
private int _remainingCommands;
private (int offset, int count)? _copyProgress;
private readonly RingBuffer _ringBuffer;
private readonly C _config = new C();
private const int NUM_COMMANDS = 510;
private const int NUM_TEMP_CODELEN = 20;
private readonly int _originalSize;
private int _producedBytes = 0;
#if DEBUG_STREAMS
long IStreamStack.InstanceId { get; set; }
#endif
int IStreamStack.DefaultBufferSize { get; set; }
Stream IStreamStack.BaseStream() => _stream;
int IStreamStack.BufferSize
{
get => 0;
set { }
}
int IStreamStack.BufferPosition
{
get => 0;
set { }
}
void IStreamStack.SetPosition(long position) { }
public LhaStream(Stream compressedStream, int originalSize)
{
_stream = compressedStream ?? throw new ArgumentNullException(nameof(compressedStream));
_bitReader = new BitReader(compressedStream);
_ringBuffer = _config.RingBuffer;
_commandTree = new HuffTree(NUM_COMMANDS * 2);
_offsetTree = new HuffTree(NUM_TEMP_CODELEN * 2);
_remainingCommands = 0;
_copyProgress = null;
_originalSize = originalSize;
}
public override bool CanRead => true;
public override bool CanSeek => false;
public override bool CanWrite => false;
public override long Length => throw new NotSupportedException();
public override long Position
{
get => throw new NotSupportedException();
set => throw new NotSupportedException();
}
public override void Flush() { }
public override long Seek(long offset, SeekOrigin origin) =>
throw new NotSupportedException();
public override void SetLength(long value) => throw new NotSupportedException();
public override void Write(byte[] buffer, int offset, int count) =>
throw new NotSupportedException();
public override int Read(byte[] buffer, int offset, int count)
{
if (buffer == null)
{
throw new ArgumentNullException(nameof(buffer));
}
if (offset < 0 || count < 0 || (offset + count) > buffer.Length)
{
throw new ArgumentOutOfRangeException();
}
if (_producedBytes >= _originalSize)
{
return 0; // EOF
}
if (count == 0)
{
return 0;
}
int bytesRead = FillBuffer(buffer);
return bytesRead;
}
private byte ReadCodeLength()
{
byte len = (byte)_bitReader.ReadBits(3);
if (len == 7)
{
while (_bitReader.ReadBit() != 0)
{
len++;
if (len > 255)
{
throw new InvalidOperationException("Code length overflow");
}
}
}
return len;
}
private int ReadCodeSkip(int skipRange)
{
int bits;
int increment;
switch (skipRange)
{
case 0:
return 1;
case 1:
bits = 4;
increment = 3; // 3..=18
break;
default:
bits = 9;
increment = 20; // 20..=531
break;
}
int skip = _bitReader.ReadBits(bits);
return skip + increment;
}
private void ReadTempTree()
{
byte[] codeLengths = new byte[NUM_TEMP_CODELEN];
// number of codes to read (5 bits)
int numCodes = _bitReader.ReadBits(5);
// single code only
if (numCodes == 0)
{
int code = _bitReader.ReadBits(5);
_offsetTree.SetSingle((byte)code);
return;
}
if (numCodes > NUM_TEMP_CODELEN)
{
throw new Exception("temporary codelen table has invalid size");
}
// read actual lengths
int count = Math.Min(3, numCodes);
for (int i = 0; i < count; i++)
{
codeLengths[i] = (byte)ReadCodeLength();
}
// 2-bit skip value follows
int skip = _bitReader.ReadBits(2);
if (3 + skip > numCodes)
{
throw new Exception("temporary codelen table has invalid size");
}
for (int i = 3 + skip; i < numCodes; i++)
{
codeLengths[i] = (byte)ReadCodeLength();
}
_offsetTree.BuildTree(codeLengths, numCodes);
}
private void ReadCommandTree()
{
byte[] codeLengths = new byte[NUM_COMMANDS];
// number of codes to read (9 bits)
int numCodes = _bitReader.ReadBits(9);
// single code only
if (numCodes == 0)
{
int code = _bitReader.ReadBits(9);
_commandTree.SetSingle((ushort)code);
return;
}
if (numCodes > NUM_COMMANDS)
{
throw new Exception("commands codelen table has invalid size");
}
int index = 0;
while (index < numCodes)
{
for (int n = 0; n < numCodes - index; n++)
{
int code = _offsetTree.ReadEntry(_bitReader);
if (code >= 0 && code <= 2) // skip range
{
int skipCount = ReadCodeSkip(code);
index += n + skipCount;
goto outerLoop;
}
else
{
codeLengths[index + n] = (byte)(code - 2);
}
}
break;
outerLoop:
;
}
_commandTree.BuildTree(codeLengths, numCodes);
}
private void ReadOffsetTree()
{
int numCodes = _bitReader.ReadBits(_config.OffsetBits);
if (numCodes == 0)
{
int code = _bitReader.ReadBits(_config.OffsetBits);
_offsetTree.SetSingle(code);
return;
}
if (numCodes > _config.HistoryBits)
{
throw new InvalidDataException("Offset code table too large");
}
byte[] codeLengths = new byte[NUM_TEMP_CODELEN];
for (int i = 0; i < numCodes; i++)
{
codeLengths[i] = (byte)ReadCodeLength();
}
_offsetTree.BuildTree(codeLengths, numCodes);
}
private void BeginNewBlock()
{
ReadTempTree();
ReadCommandTree();
ReadOffsetTree();
}
private int ReadCommand() => _commandTree.ReadEntry(_bitReader);
private int ReadOffset()
{
int bits = _offsetTree.ReadEntry(_bitReader);
if (bits <= 1)
{
return bits;
}
int res = _bitReader.ReadBits(bits - 1);
return res | (1 << (bits - 1));
}
private int CopyFromHistory(byte[] target, int targetIndex, int offset, int count)
{
var historyIter = _ringBuffer.IterFromOffset(offset);
int copied = 0;
while (
copied < count && historyIter.MoveNext() && (targetIndex + copied) < target.Length
)
{
target[targetIndex + copied] = historyIter.Current;
copied++;
}
if (copied < count)
{
_copyProgress = (offset, count - copied);
}
return copied;
}
public int FillBuffer(byte[] buffer)
{
int bufLen = buffer.Length;
int bufIndex = 0;
// stop when we reached original size
if (_producedBytes >= _originalSize)
{
return 0;
}
// calculate limit, so that we don't go over the original size
int remaining = (int)Math.Min(bufLen, _originalSize - _producedBytes);
while (bufIndex < remaining)
{
if (_copyProgress.HasValue)
{
var (offset, count) = _copyProgress.Value;
int copied = CopyFromHistory(
buffer,
bufIndex,
offset,
(int)Math.Min(count, remaining - bufIndex)
);
bufIndex += copied;
_copyProgress = null;
}
if (_remainingCommands == 0)
{
_remainingCommands = _bitReader.ReadBits(16);
if (bufIndex + _remainingCommands > remaining)
{
break;
}
BeginNewBlock();
}
_remainingCommands--;
int command = ReadCommand();
if (command >= 0 && command <= 0xFF)
{
byte value = (byte)command;
buffer[bufIndex++] = value;
_ringBuffer.Push(value);
}
else
{
int count = command - 0x100 + 3;
int offset = ReadOffset();
int copyCount = (int)Math.Min(count, remaining - bufIndex);
bufIndex += CopyFromHistory(buffer, bufIndex, offset, copyCount);
}
}
_producedBytes += bufIndex;
return bufIndex;
}
}
}

View File

@@ -1,67 +0,0 @@
using System;
using System.Collections;
using System.Collections.Generic;
namespace SharpCompress.Compressors.Arj
{
/// <summary>
/// A fixed-size ring buffer where N must be a power of two.
/// </summary>
public class RingBuffer : IRingBuffer
{
private readonly byte[] _buffer;
private int _cursor;
public int BufferSize { get; }
public int Cursor => _cursor;
private readonly int _mask;
public RingBuffer(int size)
{
if ((size & (size - 1)) != 0)
{
throw new ArgumentException("RingArrayBuffer size must be a power of two");
}
BufferSize = size;
_buffer = new byte[size];
_cursor = 0;
_mask = size - 1;
// Fill with spaces
for (int i = 0; i < size; i++)
{
_buffer[i] = (byte)' ';
}
}
public void SetCursor(int pos)
{
_cursor = pos & _mask;
}
public void Push(byte value)
{
int index = _cursor;
_buffer[index & _mask] = value;
_cursor = (index + 1) & _mask;
}
public byte this[int index] => _buffer[index & _mask];
public HistoryIterator IterFromOffset(int offset)
{
int masked = (offset & _mask) + 1;
int startIndex = _cursor + BufferSize - masked;
return new HistoryIterator(this, startIndex);
}
public HistoryIterator IterFromPos(int pos)
{
int startIndex = pos & _mask;
return new HistoryIterator(this, startIndex);
}
}
}

View File

@@ -544,12 +544,6 @@ internal sealed class CBZip2OutputStream : Stream, IStreamStack
private void EndBlock()
{
// Skip block processing for empty input (no data written)
if (last < 0)
{
return;
}
blockCRC = mCrc.GetFinalCRC();
combinedCRC = (combinedCRC << 1) | (int)(((uint)combinedCRC) >> 31);
combinedCRC ^= blockCRC;

View File

@@ -428,9 +428,7 @@ public class LzmaStream : Stream, IStreamStack
private async Task DecodeChunkHeaderAsync(CancellationToken cancellationToken = default)
{
var controlBuffer = new byte[1];
await _inputStream
.ReadExactlyAsync(controlBuffer, 0, 1, cancellationToken)
.ConfigureAwait(false);
await _inputStream.ReadAsync(controlBuffer, 0, 1, cancellationToken).ConfigureAwait(false);
var control = controlBuffer[0];
_inputPosition++;
@@ -457,15 +455,11 @@ public class LzmaStream : Stream, IStreamStack
_availableBytes = (control & 0x1F) << 16;
var buffer = new byte[2];
await _inputStream
.ReadExactlyAsync(buffer, 0, 2, cancellationToken)
.ConfigureAwait(false);
await _inputStream.ReadAsync(buffer, 0, 2, cancellationToken).ConfigureAwait(false);
_availableBytes += (buffer[0] << 8) + buffer[1] + 1;
_inputPosition += 2;
await _inputStream
.ReadExactlyAsync(buffer, 0, 2, cancellationToken)
.ConfigureAwait(false);
await _inputStream.ReadAsync(buffer, 0, 2, cancellationToken).ConfigureAwait(false);
_rangeDecoderLimit = (buffer[0] << 8) + buffer[1] + 1;
_inputPosition += 2;
@@ -473,7 +467,7 @@ public class LzmaStream : Stream, IStreamStack
{
_needProps = false;
await _inputStream
.ReadExactlyAsync(controlBuffer, 0, 1, cancellationToken)
.ReadAsync(controlBuffer, 0, 1, cancellationToken)
.ConfigureAwait(false);
Properties[0] = controlBuffer[0];
_inputPosition++;
@@ -501,9 +495,7 @@ public class LzmaStream : Stream, IStreamStack
{
_uncompressedChunk = true;
var buffer = new byte[2];
await _inputStream
.ReadExactlyAsync(buffer, 0, 2, cancellationToken)
.ConfigureAwait(false);
await _inputStream.ReadAsync(buffer, 0, 2, cancellationToken).ConfigureAwait(false);
_availableBytes = (buffer[0] << 8) + buffer[1] + 1;
_inputPosition += 2;
}

View File

@@ -7,7 +7,7 @@ using SharpCompress.Compressors.Deflate;
using SharpCompress.Compressors.Filters;
using SharpCompress.Compressors.LZMA.Utilites;
using SharpCompress.Compressors.PPMd;
using SharpCompress.Compressors.ZStandard;
using ZstdSharp;
namespace SharpCompress.Compressors.LZMA;

View File

@@ -37,8 +37,18 @@ internal sealed class MultiVolumeReadOnlyStream : Stream, IStreamStack
private IEnumerator<RarFilePart> filePartEnumerator;
private Stream currentStream;
internal MultiVolumeReadOnlyStream(IEnumerable<RarFilePart> parts)
private readonly IExtractionListener streamListener;
private long currentPartTotalReadBytes;
private long currentEntryTotalReadBytes;
internal MultiVolumeReadOnlyStream(
IEnumerable<RarFilePart> parts,
IExtractionListener streamListener
)
{
this.streamListener = streamListener;
filePartEnumerator = parts.GetEnumerator();
filePartEnumerator.MoveNext();
InitializeNextFilePart();
@@ -71,7 +81,15 @@ internal sealed class MultiVolumeReadOnlyStream : Stream, IStreamStack
currentPosition = 0;
currentStream = filePartEnumerator.Current.GetCompressedStream();
currentPartTotalReadBytes = 0;
CurrentCrc = filePartEnumerator.Current.FileHeader.FileCrc;
streamListener.FireFilePartExtractionBegin(
filePartEnumerator.Current.FilePartName,
filePartEnumerator.Current.FileHeader.CompressedSize,
filePartEnumerator.Current.FileHeader.UncompressedSize
);
}
public override int Read(byte[] buffer, int offset, int count)
@@ -123,6 +141,12 @@ internal sealed class MultiVolumeReadOnlyStream : Stream, IStreamStack
break;
}
}
currentPartTotalReadBytes += totalRead;
currentEntryTotalReadBytes += totalRead;
streamListener.FireCompressedBytesRead(
currentPartTotalReadBytes,
currentEntryTotalReadBytes
);
return totalRead;
}
@@ -182,6 +206,12 @@ internal sealed class MultiVolumeReadOnlyStream : Stream, IStreamStack
break;
}
}
currentPartTotalReadBytes += totalRead;
currentEntryTotalReadBytes += totalRead;
streamListener.FireCompressedBytesRead(
currentPartTotalReadBytes,
currentEntryTotalReadBytes
);
return totalRead;
}
@@ -240,6 +270,12 @@ internal sealed class MultiVolumeReadOnlyStream : Stream, IStreamStack
break;
}
}
currentPartTotalReadBytes += totalRead;
currentEntryTotalReadBytes += totalRead;
streamListener.FireCompressedBytesRead(
currentPartTotalReadBytes,
currentEntryTotalReadBytes
);
return totalRead;
}
#endif

View File

@@ -27,7 +27,7 @@ internal sealed partial class Unpack : BitInput, IRarUnpack
if (!disposed)
{
base.Dispose();
if (!externalWindow && window is not null)
if (!externalWindow)
{
ArrayPool<byte>.Shared.Return(window);
window = null;

View File

@@ -1,8 +1,6 @@
using System;
using System.Buffers.Binary;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
namespace SharpCompress.Compressors.Xz;
@@ -32,28 +30,6 @@ public static class BinaryUtils
internal static uint ReadLittleEndianUInt32(this Stream stream) =>
unchecked((uint)ReadLittleEndianInt32(stream));
public static async Task<int> ReadLittleEndianInt32Async(
this Stream stream,
CancellationToken cancellationToken = default
)
{
var bytes = new byte[4];
var read = await stream.ReadFullyAsync(bytes, cancellationToken).ConfigureAwait(false);
if (!read)
{
throw new EndOfStreamException();
}
return BinaryPrimitives.ReadInt32LittleEndian(bytes);
}
internal static async Task<uint> ReadLittleEndianUInt32Async(
this Stream stream,
CancellationToken cancellationToken = default
) =>
unchecked(
(uint)await ReadLittleEndianInt32Async(stream, cancellationToken).ConfigureAwait(false)
);
internal static byte[] ToBigEndianBytes(this uint uint32)
{
var result = BitConverter.GetBytes(uint32);

View File

@@ -1,7 +1,5 @@
using System;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
namespace SharpCompress.Compressors.Xz;
@@ -41,75 +39,4 @@ internal static class MultiByteIntegers
}
return Output;
}
public static async Task<ulong> ReadXZIntegerAsync(
this BinaryReader reader,
CancellationToken cancellationToken = default,
int MaxBytes = 9
)
{
if (MaxBytes <= 0)
{
throw new ArgumentOutOfRangeException(nameof(MaxBytes));
}
if (MaxBytes > 9)
{
MaxBytes = 9;
}
var LastByte = await ReadByteAsync(reader, cancellationToken).ConfigureAwait(false);
var Output = (ulong)LastByte & 0x7F;
var i = 0;
while ((LastByte & 0x80) != 0)
{
if (++i >= MaxBytes)
{
throw new InvalidFormatException();
}
LastByte = await ReadByteAsync(reader, cancellationToken).ConfigureAwait(false);
if (LastByte == 0)
{
throw new InvalidFormatException();
}
Output |= ((ulong)(LastByte & 0x7F)) << (i * 7);
}
return Output;
}
public static async Task<byte> ReadByteAsync(
this BinaryReader reader,
CancellationToken cancellationToken = default
)
{
var buffer = new byte[1];
var bytesRead = await reader
.BaseStream.ReadAsync(buffer, 0, 1, cancellationToken)
.ConfigureAwait(false);
if (bytesRead != 1)
{
throw new EndOfStreamException();
}
return buffer[0];
}
public static async Task<byte[]> ReadBytesAsync(
this BinaryReader reader,
int count,
CancellationToken cancellationToken = default
)
{
var buffer = new byte[count];
var bytesRead = await reader
.BaseStream.ReadAsync(buffer, 0, count, cancellationToken)
.ConfigureAwait(false);
if (bytesRead != count)
{
throw new EndOfStreamException();
}
return buffer;
}
}

View File

@@ -4,8 +4,6 @@ using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.Compressors.Xz.Filters;
@@ -74,49 +72,6 @@ public sealed class XZBlock : XZReadOnlyStream
return bytesRead;
}
public override async Task<int> ReadAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken = default
)
{
var bytesRead = 0;
if (!HeaderIsLoaded)
{
await LoadHeaderAsync(cancellationToken).ConfigureAwait(false);
}
if (!_streamConnected)
{
ConnectStream();
}
if (!_endOfStream)
{
bytesRead = await _decomStream
.ReadAsync(buffer, offset, count, cancellationToken)
.ConfigureAwait(false);
}
if (bytesRead != count)
{
_endOfStream = true;
}
if (_endOfStream && !_paddingSkipped)
{
await SkipPaddingAsync(cancellationToken).ConfigureAwait(false);
}
if (_endOfStream && !_crcChecked)
{
await CheckCrcAsync(cancellationToken).ConfigureAwait(false);
}
return bytesRead;
}
private void SkipPadding()
{
var bytes = (BaseStream.Position - _startPosition) % 4;
@@ -132,23 +87,6 @@ public sealed class XZBlock : XZReadOnlyStream
_paddingSkipped = true;
}
private async Task SkipPaddingAsync(CancellationToken cancellationToken = default)
{
var bytes = (BaseStream.Position - _startPosition) % 4;
if (bytes > 0)
{
var paddingBytes = new byte[4 - bytes];
await BaseStream
.ReadAsync(paddingBytes, 0, paddingBytes.Length, cancellationToken)
.ConfigureAwait(false);
if (paddingBytes.Any(b => b != 0))
{
throw new InvalidFormatException("Padding bytes were non-null");
}
}
_paddingSkipped = true;
}
private void CheckCrc()
{
var crc = new byte[_checkSize];
@@ -158,15 +96,6 @@ public sealed class XZBlock : XZReadOnlyStream
_crcChecked = true;
}
private async Task CheckCrcAsync(CancellationToken cancellationToken = default)
{
var crc = new byte[_checkSize];
await BaseStream.ReadAsync(crc, 0, _checkSize, cancellationToken).ConfigureAwait(false);
// Actually do a check (and read in the bytes
// into the function throughout the stream read).
_crcChecked = true;
}
private void ConnectStream()
{
_decomStream = BaseStream;
@@ -194,21 +123,6 @@ public sealed class XZBlock : XZReadOnlyStream
HeaderIsLoaded = true;
}
private async Task LoadHeaderAsync(CancellationToken cancellationToken = default)
{
await ReadHeaderSizeAsync(cancellationToken).ConfigureAwait(false);
var headerCache = await CacheHeaderAsync(cancellationToken).ConfigureAwait(false);
using (var cache = new MemoryStream(headerCache))
using (var cachedReader = new BinaryReader(cache))
{
cachedReader.BaseStream.Position = 1; // skip the header size byte
ReadBlockFlags(cachedReader);
ReadFilters(cachedReader);
}
HeaderIsLoaded = true;
}
private void ReadHeaderSize()
{
_blockHeaderSizeByte = (byte)BaseStream.ReadByte();
@@ -218,17 +132,6 @@ public sealed class XZBlock : XZReadOnlyStream
}
}
private async Task ReadHeaderSizeAsync(CancellationToken cancellationToken = default)
{
var buffer = new byte[1];
await BaseStream.ReadAsync(buffer, 0, 1, cancellationToken).ConfigureAwait(false);
_blockHeaderSizeByte = buffer[0];
if (_blockHeaderSizeByte == 0)
{
throw new XZIndexMarkerReachedException();
}
}
private byte[] CacheHeader()
{
var blockHeaderWithoutCrc = new byte[BlockHeaderSize - 4];
@@ -236,7 +139,7 @@ public sealed class XZBlock : XZReadOnlyStream
var read = BaseStream.Read(blockHeaderWithoutCrc, 1, BlockHeaderSize - 5);
if (read != BlockHeaderSize - 5)
{
throw new EndOfStreamException("Reached end of stream unexpectedly");
throw new EndOfStreamException("Reached end of stream unexectedly");
}
var crc = BaseStream.ReadLittleEndianUInt32();
@@ -249,30 +152,6 @@ public sealed class XZBlock : XZReadOnlyStream
return blockHeaderWithoutCrc;
}
private async Task<byte[]> CacheHeaderAsync(CancellationToken cancellationToken = default)
{
var blockHeaderWithoutCrc = new byte[BlockHeaderSize - 4];
blockHeaderWithoutCrc[0] = _blockHeaderSizeByte;
var read = await BaseStream
.ReadAsync(blockHeaderWithoutCrc, 1, BlockHeaderSize - 5, cancellationToken)
.ConfigureAwait(false);
if (read != BlockHeaderSize - 5)
{
throw new EndOfStreamException("Reached end of stream unexpectedly");
}
var crc = await BaseStream
.ReadLittleEndianUInt32Async(cancellationToken)
.ConfigureAwait(false);
var calcCrc = Crc32.Compute(blockHeaderWithoutCrc);
if (crc != calcCrc)
{
throw new InvalidFormatException("Block header corrupt");
}
return blockHeaderWithoutCrc;
}
private void ReadBlockFlags(BinaryReader reader)
{
var blockFlags = reader.ReadByte();

View File

@@ -1,8 +1,6 @@
using System;
using System.IO;
using System.Text;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.IO;
@@ -29,16 +27,6 @@ public class XZFooter
return footer;
}
public static async Task<XZFooter> FromStreamAsync(
Stream stream,
CancellationToken cancellationToken = default
)
{
var footer = new XZFooter(new BinaryReader(stream, Encoding.UTF8, true));
await footer.ProcessAsync(cancellationToken).ConfigureAwait(false);
return footer;
}
public void Process()
{
var crc = _reader.ReadLittleEndianUInt32();
@@ -61,29 +49,4 @@ public class XZFooter
throw new InvalidFormatException("Magic footer missing");
}
}
public async Task ProcessAsync(CancellationToken cancellationToken = default)
{
var crc = await _reader
.BaseStream.ReadLittleEndianUInt32Async(cancellationToken)
.ConfigureAwait(false);
var footerBytes = await _reader.ReadBytesAsync(6, cancellationToken).ConfigureAwait(false);
var myCrc = Crc32.Compute(footerBytes);
if (crc != myCrc)
{
throw new InvalidFormatException("Footer corrupt");
}
using (var stream = new MemoryStream(footerBytes))
using (var reader = new BinaryReader(stream))
{
BackwardSize = (reader.ReadLittleEndianUInt32() + 1) * 4;
StreamFlags = reader.ReadBytes(2);
}
var magBy = await _reader.ReadBytesAsync(2, cancellationToken).ConfigureAwait(false);
if (!magBy.AsSpan().SequenceEqual(_magicBytes))
{
throw new InvalidFormatException("Magic footer missing");
}
}
}

View File

@@ -1,8 +1,6 @@
using System.IO;
using System.Linq;
using System.Text;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.IO;
@@ -25,28 +23,12 @@ public class XZHeader
return header;
}
public static async Task<XZHeader> FromStreamAsync(
Stream stream,
CancellationToken cancellationToken = default
)
{
var header = new XZHeader(new BinaryReader(stream, Encoding.UTF8, true));
await header.ProcessAsync(cancellationToken).ConfigureAwait(false);
return header;
}
public void Process()
{
CheckMagicBytes(_reader.ReadBytes(6));
ProcessStreamFlags();
}
public async Task ProcessAsync(CancellationToken cancellationToken = default)
{
CheckMagicBytes(await _reader.ReadBytesAsync(6, cancellationToken).ConfigureAwait(false));
await ProcessStreamFlagsAsync(cancellationToken).ConfigureAwait(false);
}
private void ProcessStreamFlags()
{
var streamFlags = _reader.ReadBytes(2);
@@ -65,26 +47,6 @@ public class XZHeader
}
}
private async Task ProcessStreamFlagsAsync(CancellationToken cancellationToken = default)
{
var streamFlags = await _reader.ReadBytesAsync(2, cancellationToken).ConfigureAwait(false);
var crc = await _reader
.BaseStream.ReadLittleEndianUInt32Async(cancellationToken)
.ConfigureAwait(false);
var calcCrc = Crc32.Compute(streamFlags);
if (crc != calcCrc)
{
throw new InvalidFormatException("Stream header corrupt");
}
BlockCheckType = (CheckType)(streamFlags[1] & 0x0F);
var futureUse = (byte)(streamFlags[1] & 0xF0);
if (futureUse != 0 || streamFlags[0] != 0)
{
throw new InvalidFormatException("Unknown XZ Stream Version");
}
}
private void CheckMagicBytes(byte[] header)
{
if (!header.SequenceEqual(MagicHeader))

View File

@@ -3,8 +3,6 @@ using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Text;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.IO;
@@ -41,20 +39,6 @@ public class XZIndex
return index;
}
public static async Task<XZIndex> FromStreamAsync(
Stream stream,
bool indexMarkerAlreadyVerified,
CancellationToken cancellationToken = default
)
{
var index = new XZIndex(
new BinaryReader(stream, Encoding.UTF8, true),
indexMarkerAlreadyVerified
);
await index.ProcessAsync(cancellationToken).ConfigureAwait(false);
return index;
}
public void Process()
{
if (!_indexMarkerAlreadyVerified)
@@ -71,26 +55,6 @@ public class XZIndex
VerifyCrc32();
}
public async Task ProcessAsync(CancellationToken cancellationToken = default)
{
if (!_indexMarkerAlreadyVerified)
{
await VerifyIndexMarkerAsync(cancellationToken).ConfigureAwait(false);
}
NumberOfRecords = await _reader.ReadXZIntegerAsync(cancellationToken).ConfigureAwait(false);
for (ulong i = 0; i < NumberOfRecords; i++)
{
Records.Add(
await XZIndexRecord
.FromBinaryReaderAsync(_reader, cancellationToken)
.ConfigureAwait(false)
);
}
await SkipPaddingAsync(cancellationToken).ConfigureAwait(false);
await VerifyCrc32Async(cancellationToken).ConfigureAwait(false);
}
private void VerifyIndexMarker()
{
var marker = _reader.ReadByte();
@@ -100,15 +64,6 @@ public class XZIndex
}
}
private async Task VerifyIndexMarkerAsync(CancellationToken cancellationToken = default)
{
var marker = await _reader.ReadByteAsync(cancellationToken).ConfigureAwait(false);
if (marker != 0)
{
throw new InvalidFormatException("Not an index block");
}
}
private void SkipPadding()
{
var bytes = (int)(_reader.BaseStream.Position - StreamStartPosition) % 4;
@@ -122,32 +77,9 @@ public class XZIndex
}
}
private async Task SkipPaddingAsync(CancellationToken cancellationToken = default)
{
var bytes = (int)(_reader.BaseStream.Position - StreamStartPosition) % 4;
if (bytes > 0)
{
var paddingBytes = await _reader
.ReadBytesAsync(4 - bytes, cancellationToken)
.ConfigureAwait(false);
if (paddingBytes.Any(b => b != 0))
{
throw new InvalidFormatException("Padding bytes were non-null");
}
}
}
private void VerifyCrc32()
{
var crc = _reader.ReadLittleEndianUInt32();
// TODO verify this matches
}
private async Task VerifyCrc32Async(CancellationToken cancellationToken = default)
{
var crc = await _reader
.BaseStream.ReadLittleEndianUInt32Async(cancellationToken)
.ConfigureAwait(false);
// TODO verify this matches
}
}

View File

@@ -1,7 +1,5 @@
using System;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
namespace SharpCompress.Compressors.Xz;
@@ -20,16 +18,4 @@ public class XZIndexRecord
record.UncompressedSize = br.ReadXZInteger();
return record;
}
public static async Task<XZIndexRecord> FromBinaryReaderAsync(
BinaryReader br,
CancellationToken cancellationToken = default
)
{
var record = new XZIndexRecord();
record.UnpaddedSize = await br.ReadXZIntegerAsync(cancellationToken).ConfigureAwait(false);
record.UncompressedSize = await br.ReadXZIntegerAsync(cancellationToken)
.ConfigureAwait(false);
return record;
}
}

View File

@@ -2,8 +2,6 @@
using System;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Common;
using SharpCompress.IO;
@@ -106,35 +104,6 @@ public sealed class XZStream : XZReadOnlyStream, IStreamStack
return bytesRead;
}
public override async Task<int> ReadAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken = default
)
{
var bytesRead = 0;
if (_endOfStream)
{
return bytesRead;
}
if (!HeaderIsRead)
{
await ReadHeaderAsync(cancellationToken).ConfigureAwait(false);
}
bytesRead = await ReadBlocksAsync(buffer, offset, count, cancellationToken)
.ConfigureAwait(false);
if (bytesRead < count)
{
_endOfStream = true;
await ReadIndexAsync(cancellationToken).ConfigureAwait(false);
await ReadFooterAsync(cancellationToken).ConfigureAwait(false);
}
return bytesRead;
}
private void ReadHeader()
{
Header = XZHeader.FromStream(BaseStream);
@@ -142,31 +111,12 @@ public sealed class XZStream : XZReadOnlyStream, IStreamStack
HeaderIsRead = true;
}
private async Task ReadHeaderAsync(CancellationToken cancellationToken = default)
{
Header = await XZHeader
.FromStreamAsync(BaseStream, cancellationToken)
.ConfigureAwait(false);
AssertBlockCheckTypeIsSupported();
HeaderIsRead = true;
}
private void ReadIndex() => Index = XZIndex.FromStream(BaseStream, true);
private async Task ReadIndexAsync(CancellationToken cancellationToken = default) =>
Index = await XZIndex
.FromStreamAsync(BaseStream, true, cancellationToken)
.ConfigureAwait(false);
// TODO verify Index
// TODO veryfy Index
private void ReadFooter() => Footer = XZFooter.FromStream(BaseStream);
// TODO verify footer
private async Task ReadFooterAsync(CancellationToken cancellationToken = default) =>
Footer = await XZFooter
.FromStreamAsync(BaseStream, cancellationToken)
.ConfigureAwait(false);
private int ReadBlocks(byte[] buffer, int offset, int count)
{
var bytesRead = 0;
@@ -202,48 +152,6 @@ public sealed class XZStream : XZReadOnlyStream, IStreamStack
return bytesRead;
}
private async Task<int> ReadBlocksAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken = default
)
{
var bytesRead = 0;
if (_currentBlock is null)
{
NextBlock();
}
for (; ; )
{
try
{
if (bytesRead >= count)
{
break;
}
var remaining = count - bytesRead;
var newOffset = offset + bytesRead;
var justRead = await _currentBlock
.ReadAsync(buffer, newOffset, remaining, cancellationToken)
.ConfigureAwait(false);
if (justRead < remaining)
{
NextBlock();
}
bytesRead += justRead;
}
catch (XZIndexMarkerReachedException)
{
break;
}
}
return bytesRead;
}
private void NextBlock() =>
_currentBlock = new XZBlock(BaseStream, Header.BlockCheckType, Header.BlockCheckSize);
}

View File

@@ -1,311 +0,0 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
#if !NETCOREAPP3_0_OR_GREATER
using System.Runtime.CompilerServices;
using static SharpCompress.Compressors.ZStandard.UnsafeHelper;
// Some routines inspired by the Stanford Bit Twiddling Hacks by Sean Eron Anderson:
// http://graphics.stanford.edu/~seander/bithacks.html
namespace System.Numerics
{
/// <summary>
/// Utility methods for intrinsic bit-twiddling operations.
/// The methods use hardware intrinsics when available on the underlying platform,
/// otherwise they use optimized software fallbacks.
/// </summary>
public static unsafe class BitOperations
{
// hack: should be public because of inline
public static readonly byte* TrailingZeroCountDeBruijn = GetArrayPointer(
new byte[]
{
00,
01,
28,
02,
29,
14,
24,
03,
30,
22,
20,
15,
25,
17,
04,
08,
31,
27,
13,
23,
21,
19,
16,
07,
26,
12,
18,
06,
11,
05,
10,
09,
}
);
// hack: should be public because of inline
public static readonly byte* Log2DeBruijn = GetArrayPointer(
new byte[]
{
00,
09,
01,
10,
13,
21,
02,
29,
11,
14,
16,
18,
22,
25,
03,
30,
08,
12,
20,
28,
15,
17,
24,
07,
19,
27,
23,
06,
26,
05,
04,
31,
}
);
/// <summary>
/// Returns the integer (floor) log of the specified value, base 2.
/// Note that by convention, input value 0 returns 0 since log(0) is undefined.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int Log2(uint value)
{
// The 0->0 contract is fulfilled by setting the LSB to 1.
// Log(1) is 0, and setting the LSB for values > 1 does not change the log2 result.
value |= 1;
// value lzcnt actual expected
// ..0001 31 31-31 0
// ..0010 30 31-30 1
// 0010.. 2 31-2 29
// 0100.. 1 31-1 30
// 1000.. 0 31-0 31
// Fallback contract is 0->0
// No AggressiveInlining due to large method size
// Has conventional contract 0->0 (Log(0) is undefined)
// Fill trailing zeros with ones, eg 00010010 becomes 00011111
value |= value >> 01;
value |= value >> 02;
value |= value >> 04;
value |= value >> 08;
value |= value >> 16;
// uint.MaxValue >> 27 is always in range [0 - 31] so we use Unsafe.AddByteOffset to avoid bounds check
return Log2DeBruijn[
// Using deBruijn sequence, k=2, n=5 (2^5=32) : 0b_0000_0111_1100_0100_1010_1100_1101_1101u
(int)((value * 0x07C4ACDDu) >> 27)
];
}
/// <summary>
/// Returns the integer (floor) log of the specified value, base 2.
/// Note that by convention, input value 0 returns 0 since log(0) is undefined.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int Log2(ulong value)
{
value |= 1;
uint hi = (uint)(value >> 32);
if (hi == 0)
{
return Log2((uint)value);
}
return 32 + Log2(hi);
}
/// <summary>
/// Count the number of trailing zero bits in an integer value.
/// Similar in behavior to the x86 instruction TZCNT.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int TrailingZeroCount(int value) => TrailingZeroCount((uint)value);
/// <summary>
/// Count the number of trailing zero bits in an integer value.
/// Similar in behavior to the x86 instruction TZCNT.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int TrailingZeroCount(uint value)
{
// Unguarded fallback contract is 0->0, BSF contract is 0->undefined
if (value == 0)
{
return 32;
}
// uint.MaxValue >> 27 is always in range [0 - 31] so we use Unsafe.AddByteOffset to avoid bounds check
return TrailingZeroCountDeBruijn[
// Using deBruijn sequence, k=2, n=5 (2^5=32) : 0b_0000_0111_0111_1100_1011_0101_0011_0001u
(int)(((value & (uint)-(int)value) * 0x077CB531u) >> 27)
]; // Multi-cast mitigates redundant conv.u8
}
/// <summary>
/// Count the number of trailing zero bits in a mask.
/// Similar in behavior to the x86 instruction TZCNT.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int TrailingZeroCount(long value) => TrailingZeroCount((ulong)value);
/// <summary>
/// Count the number of trailing zero bits in a mask.
/// Similar in behavior to the x86 instruction TZCNT.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int TrailingZeroCount(ulong value)
{
uint lo = (uint)value;
if (lo == 0)
{
return 32 + TrailingZeroCount((uint)(value >> 32));
}
return TrailingZeroCount(lo);
}
/// <summary>
/// Rotates the specified value left by the specified number of bits.
/// Similar in behavior to the x86 instruction ROL.
/// </summary>
/// <param name="value">The value to rotate.</param>
/// <param name="offset">The number of bits to rotate by.
/// Any value outside the range [0..31] is treated as congruent mod 32.</param>
/// <returns>The rotated value.</returns>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static uint RotateLeft(uint value, int offset) =>
(value << offset) | (value >> (32 - offset));
/// <summary>
/// Rotates the specified value left by the specified number of bits.
/// Similar in behavior to the x86 instruction ROL.
/// </summary>
/// <param name="value">The value to rotate.</param>
/// <param name="offset">The number of bits to rotate by.
/// Any value outside the range [0..63] is treated as congruent mod 64.</param>
/// <returns>The rotated value.</returns>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static ulong RotateLeft(ulong value, int offset) =>
(value << offset) | (value >> (64 - offset));
/// <summary>
/// Rotates the specified value right by the specified number of bits.
/// Similar in behavior to the x86 instruction ROR.
/// </summary>
/// <param name="value">The value to rotate.</param>
/// <param name="offset">The number of bits to rotate by.
/// Any value outside the range [0..31] is treated as congruent mod 32.</param>
/// <returns>The rotated value.</returns>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static uint RotateRight(uint value, int offset) =>
(value >> offset) | (value << (32 - offset));
/// <summary>
/// Rotates the specified value right by the specified number of bits.
/// Similar in behavior to the x86 instruction ROR.
/// </summary>
/// <param name="value">The value to rotate.</param>
/// <param name="offset">The number of bits to rotate by.
/// Any value outside the range [0..63] is treated as congruent mod 64.</param>
/// <returns>The rotated value.</returns>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static ulong RotateRight(ulong value, int offset) =>
(value >> offset) | (value << (64 - offset));
/// <summary>
/// Count the number of leading zero bits in a mask.
/// Similar in behavior to the x86 instruction LZCNT.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int LeadingZeroCount(uint value)
{
// Unguarded fallback contract is 0->31, BSR contract is 0->undefined
if (value == 0)
{
return 32;
}
// No AggressiveInlining due to large method size
// Has conventional contract 0->0 (Log(0) is undefined)
// Fill trailing zeros with ones, eg 00010010 becomes 00011111
value |= value >> 01;
value |= value >> 02;
value |= value >> 04;
value |= value >> 08;
value |= value >> 16;
// uint.MaxValue >> 27 is always in range [0 - 31] so we use Unsafe.AddByteOffset to avoid bounds check
return 31
^ Log2DeBruijn[
// uint|long -> IntPtr cast on 32-bit platforms does expensive overflow checks not needed here
(int)((value * 0x07C4ACDDu) >> 27)
];
}
/// <summary>
/// Count the number of leading zero bits in a mask.
/// Similar in behavior to the x86 instruction LZCNT.
/// </summary>
/// <param name="value">The value.</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static int LeadingZeroCount(ulong value)
{
uint hi = (uint)(value >> 32);
if (hi == 0)
{
return 32 + LeadingZeroCount((uint)value);
}
return LeadingZeroCount(hi);
}
}
}
#endif

View File

@@ -1,301 +0,0 @@
using System;
using System.Buffers;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Compressors.ZStandard.Unsafe;
namespace SharpCompress.Compressors.ZStandard;
public class CompressionStream : Stream
{
private readonly Stream innerStream;
private readonly byte[] outputBuffer;
private readonly bool preserveCompressor;
private readonly bool leaveOpen;
private Compressor? compressor;
private ZSTD_outBuffer_s output;
public CompressionStream(
Stream stream,
int level = Compressor.DefaultCompressionLevel,
int bufferSize = 0,
bool leaveOpen = true
)
: this(stream, new Compressor(level), bufferSize, false, leaveOpen) { }
public CompressionStream(
Stream stream,
Compressor compressor,
int bufferSize = 0,
bool preserveCompressor = true,
bool leaveOpen = true
)
{
if (stream == null)
throw new ArgumentNullException(nameof(stream));
if (!stream.CanWrite)
throw new ArgumentException("Stream is not writable", nameof(stream));
if (bufferSize < 0)
throw new ArgumentOutOfRangeException(nameof(bufferSize));
innerStream = stream;
this.compressor = compressor;
this.preserveCompressor = preserveCompressor;
this.leaveOpen = leaveOpen;
var outputBufferSize =
bufferSize > 0
? bufferSize
: (int)Unsafe.Methods.ZSTD_CStreamOutSize().EnsureZstdSuccess();
outputBuffer = ArrayPool<byte>.Shared.Rent(outputBufferSize);
output = new ZSTD_outBuffer_s { pos = 0, size = (nuint)outputBufferSize };
}
public void SetParameter(ZSTD_cParameter parameter, int value)
{
EnsureNotDisposed();
compressor.NotNull().SetParameter(parameter, value);
}
public int GetParameter(ZSTD_cParameter parameter)
{
EnsureNotDisposed();
return compressor.NotNull().GetParameter(parameter);
}
public void LoadDictionary(byte[] dict)
{
EnsureNotDisposed();
compressor.NotNull().LoadDictionary(dict);
}
~CompressionStream() => Dispose(false);
#if !NETSTANDARD2_0 && !NETFRAMEWORK
public override async ValueTask DisposeAsync()
#else
public async Task DisposeAsync()
#endif
{
if (compressor == null)
return;
try
{
await FlushInternalAsync(ZSTD_EndDirective.ZSTD_e_end).ConfigureAwait(false);
}
finally
{
ReleaseUnmanagedResources();
GC.SuppressFinalize(this);
}
}
protected override void Dispose(bool disposing)
{
if (compressor == null)
return;
try
{
if (disposing)
FlushInternal(ZSTD_EndDirective.ZSTD_e_end);
}
finally
{
ReleaseUnmanagedResources();
}
}
private void ReleaseUnmanagedResources()
{
if (!preserveCompressor)
{
compressor.NotNull().Dispose();
}
compressor = null;
if (outputBuffer != null)
{
ArrayPool<byte>.Shared.Return(outputBuffer);
}
if (!leaveOpen)
{
innerStream.Dispose();
}
}
public override void Flush() => FlushInternal(ZSTD_EndDirective.ZSTD_e_flush);
public override async Task FlushAsync(CancellationToken cancellationToken) =>
await FlushInternalAsync(ZSTD_EndDirective.ZSTD_e_flush, cancellationToken)
.ConfigureAwait(false);
private void FlushInternal(ZSTD_EndDirective directive) => WriteInternal(null, directive);
private async Task FlushInternalAsync(
ZSTD_EndDirective directive,
CancellationToken cancellationToken = default
) => await WriteInternalAsync(null, directive, cancellationToken).ConfigureAwait(false);
public override void Write(byte[] buffer, int offset, int count) =>
Write(new ReadOnlySpan<byte>(buffer, offset, count));
#if !NETSTANDARD2_0 && !NETFRAMEWORK
public override void Write(ReadOnlySpan<byte> buffer) =>
WriteInternal(buffer, ZSTD_EndDirective.ZSTD_e_continue);
#else
public void Write(ReadOnlySpan<byte> buffer) =>
WriteInternal(buffer, ZSTD_EndDirective.ZSTD_e_continue);
#endif
private void WriteInternal(ReadOnlySpan<byte> buffer, ZSTD_EndDirective directive)
{
EnsureNotDisposed();
var input = new ZSTD_inBuffer_s
{
pos = 0,
size = buffer != null ? (nuint)buffer.Length : 0,
};
nuint remaining;
do
{
output.pos = 0;
remaining = CompressStream(ref input, buffer, directive);
var written = (int)output.pos;
if (written > 0)
innerStream.Write(outputBuffer, 0, written);
} while (
directive == ZSTD_EndDirective.ZSTD_e_continue ? input.pos < input.size : remaining > 0
);
}
#if !NETSTANDARD2_0 && !NETFRAMEWORK
private async ValueTask WriteInternalAsync(
ReadOnlyMemory<byte>? buffer,
ZSTD_EndDirective directive,
CancellationToken cancellationToken = default
)
#else
private async Task WriteInternalAsync(
ReadOnlyMemory<byte>? buffer,
ZSTD_EndDirective directive,
CancellationToken cancellationToken = default
)
#endif
{
EnsureNotDisposed();
var input = new ZSTD_inBuffer_s
{
pos = 0,
size = buffer.HasValue ? (nuint)buffer.Value.Length : 0,
};
nuint remaining;
do
{
output.pos = 0;
remaining = CompressStream(
ref input,
buffer.HasValue ? buffer.Value.Span : null,
directive
);
var written = (int)output.pos;
if (written > 0)
await innerStream
.WriteAsync(outputBuffer, 0, written, cancellationToken)
.ConfigureAwait(false);
} while (
directive == ZSTD_EndDirective.ZSTD_e_continue ? input.pos < input.size : remaining > 0
);
}
#if !NETSTANDARD2_0 && !NETFRAMEWORK
public override Task WriteAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken
) => WriteAsync(new ReadOnlyMemory<byte>(buffer, offset, count), cancellationToken).AsTask();
public override async ValueTask WriteAsync(
ReadOnlyMemory<byte> buffer,
CancellationToken cancellationToken = default
) =>
await WriteInternalAsync(buffer, ZSTD_EndDirective.ZSTD_e_continue, cancellationToken)
.ConfigureAwait(false);
#else
public override Task WriteAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken
) => WriteAsync(new ReadOnlyMemory<byte>(buffer, offset, count), cancellationToken);
public async Task WriteAsync(
ReadOnlyMemory<byte> buffer,
CancellationToken cancellationToken = default
) =>
await WriteInternalAsync(buffer, ZSTD_EndDirective.ZSTD_e_continue, cancellationToken)
.ConfigureAwait(false);
#endif
internal unsafe nuint CompressStream(
ref ZSTD_inBuffer_s input,
ReadOnlySpan<byte> inputBuffer,
ZSTD_EndDirective directive
)
{
fixed (byte* inputBufferPtr = inputBuffer)
fixed (byte* outputBufferPtr = outputBuffer)
{
input.src = inputBufferPtr;
output.dst = outputBufferPtr;
return compressor
.NotNull()
.CompressStream(ref input, ref output, directive)
.EnsureZstdSuccess();
}
}
public override bool CanRead => false;
public override bool CanSeek => false;
public override bool CanWrite => true;
public override long Length => throw new NotSupportedException();
public override long Position
{
get => throw new NotSupportedException();
set => throw new NotSupportedException();
}
public override long Seek(long offset, SeekOrigin origin) => throw new NotSupportedException();
public override void SetLength(long value) => throw new NotSupportedException();
public override int Read(byte[] buffer, int offset, int count) =>
throw new NotSupportedException();
private void EnsureNotDisposed()
{
if (compressor == null)
throw new ObjectDisposedException(nameof(CompressionStream));
}
public void SetPledgedSrcSize(ulong pledgedSrcSize)
{
EnsureNotDisposed();
compressor.NotNull().SetPledgedSrcSize(pledgedSrcSize);
}
}

View File

@@ -1,204 +0,0 @@
using System;
using SharpCompress.Compressors.ZStandard.Unsafe;
namespace SharpCompress.Compressors.ZStandard;
public unsafe class Compressor : IDisposable
{
/// <summary>
/// Minimum negative compression level allowed
/// </summary>
public static int MinCompressionLevel => Unsafe.Methods.ZSTD_minCLevel();
/// <summary>
/// Maximum compression level available
/// </summary>
public static int MaxCompressionLevel => Unsafe.Methods.ZSTD_maxCLevel();
/// <summary>
/// Default compression level
/// </summary>
/// <see cref="Unsafe.Methods.ZSTD_defaultCLevel"/>
public const int DefaultCompressionLevel = 3;
private int level = DefaultCompressionLevel;
private readonly SafeCctxHandle handle;
public int Level
{
get => level;
set
{
if (level != value)
{
level = value;
SetParameter(ZSTD_cParameter.ZSTD_c_compressionLevel, value);
}
}
}
public void SetParameter(ZSTD_cParameter parameter, int value)
{
using var cctx = handle.Acquire();
Unsafe.Methods.ZSTD_CCtx_setParameter(cctx, parameter, value).EnsureZstdSuccess();
}
public int GetParameter(ZSTD_cParameter parameter)
{
using var cctx = handle.Acquire();
int value;
Unsafe.Methods.ZSTD_CCtx_getParameter(cctx, parameter, &value).EnsureZstdSuccess();
return value;
}
public void LoadDictionary(byte[] dict)
{
var dictReadOnlySpan = new ReadOnlySpan<byte>(dict);
LoadDictionary(dictReadOnlySpan);
}
public void LoadDictionary(ReadOnlySpan<byte> dict)
{
using var cctx = handle.Acquire();
fixed (byte* dictPtr = dict)
Unsafe
.Methods.ZSTD_CCtx_loadDictionary(cctx, dictPtr, (nuint)dict.Length)
.EnsureZstdSuccess();
}
public Compressor(int level = DefaultCompressionLevel)
{
handle = SafeCctxHandle.Create();
Level = level;
}
public static int GetCompressBound(int length) =>
(int)Unsafe.Methods.ZSTD_compressBound((nuint)length);
public static ulong GetCompressBoundLong(ulong length) =>
Unsafe.Methods.ZSTD_compressBound((nuint)length);
public Span<byte> Wrap(ReadOnlySpan<byte> src)
{
var dest = new byte[GetCompressBound(src.Length)];
var length = Wrap(src, dest);
return new Span<byte>(dest, 0, length);
}
public int Wrap(byte[] src, byte[] dest, int offset) =>
Wrap(src, new Span<byte>(dest, offset, dest.Length - offset));
public int Wrap(ReadOnlySpan<byte> src, Span<byte> dest)
{
fixed (byte* srcPtr = src)
fixed (byte* destPtr = dest)
{
using var cctx = handle.Acquire();
return (int)
Unsafe
.Methods.ZSTD_compress2(
cctx,
destPtr,
(nuint)dest.Length,
srcPtr,
(nuint)src.Length
)
.EnsureZstdSuccess();
}
}
public int Wrap(ArraySegment<byte> src, ArraySegment<byte> dest) =>
Wrap((ReadOnlySpan<byte>)src, dest);
public int Wrap(
byte[] src,
int srcOffset,
int srcLength,
byte[] dst,
int dstOffset,
int dstLength
) =>
Wrap(
new ReadOnlySpan<byte>(src, srcOffset, srcLength),
new Span<byte>(dst, dstOffset, dstLength)
);
public bool TryWrap(byte[] src, byte[] dest, int offset, out int written) =>
TryWrap(src, new Span<byte>(dest, offset, dest.Length - offset), out written);
public bool TryWrap(ReadOnlySpan<byte> src, Span<byte> dest, out int written)
{
fixed (byte* srcPtr = src)
fixed (byte* destPtr = dest)
{
nuint returnValue;
using (var cctx = handle.Acquire())
{
returnValue = Unsafe.Methods.ZSTD_compress2(
cctx,
destPtr,
(nuint)dest.Length,
srcPtr,
(nuint)src.Length
);
}
if (returnValue == unchecked(0 - (nuint)ZSTD_ErrorCode.ZSTD_error_dstSize_tooSmall))
{
written = default;
return false;
}
returnValue.EnsureZstdSuccess();
written = (int)returnValue;
return true;
}
}
public bool TryWrap(ArraySegment<byte> src, ArraySegment<byte> dest, out int written) =>
TryWrap((ReadOnlySpan<byte>)src, dest, out written);
public bool TryWrap(
byte[] src,
int srcOffset,
int srcLength,
byte[] dst,
int dstOffset,
int dstLength,
out int written
) =>
TryWrap(
new ReadOnlySpan<byte>(src, srcOffset, srcLength),
new Span<byte>(dst, dstOffset, dstLength),
out written
);
public void Dispose()
{
handle.Dispose();
GC.SuppressFinalize(this);
}
internal nuint CompressStream(
ref ZSTD_inBuffer_s input,
ref ZSTD_outBuffer_s output,
ZSTD_EndDirective directive
)
{
fixed (ZSTD_inBuffer_s* inputPtr = &input)
fixed (ZSTD_outBuffer_s* outputPtr = &output)
{
using var cctx = handle.Acquire();
return Unsafe
.Methods.ZSTD_compressStream2(cctx, outputPtr, inputPtr, directive)
.EnsureZstdSuccess();
}
}
public void SetPledgedSrcSize(ulong pledgedSrcSize)
{
using var cctx = handle.Acquire();
Unsafe.Methods.ZSTD_CCtx_setPledgedSrcSize(cctx, pledgedSrcSize).EnsureZstdSuccess();
}
}

View File

@@ -1,8 +0,0 @@
namespace SharpCompress.Compressors.ZStandard;
internal class Constants
{
//NOTE: https://docs.microsoft.com/en-us/dotnet/framework/configure-apps/file-schema/runtime/gcallowverylargeobjects-element#remarks
//NOTE: https://github.com/dotnet/runtime/blob/v5.0.0-rtm.20519.4/src/libraries/System.Private.CoreLib/src/System/Array.cs#L27
public const ulong MaxByteArrayLength = 0x7FFFFFC7;
}

View File

@@ -1,293 +0,0 @@
using System;
using System.Buffers;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
using SharpCompress.Compressors.ZStandard.Unsafe;
namespace SharpCompress.Compressors.ZStandard;
public class DecompressionStream : Stream
{
private readonly Stream innerStream;
private readonly byte[] inputBuffer;
private readonly int inputBufferSize;
private readonly bool preserveDecompressor;
private readonly bool leaveOpen;
private readonly bool checkEndOfStream;
private Decompressor? decompressor;
private ZSTD_inBuffer_s input;
private nuint lastDecompressResult = 0;
private bool contextDrained = true;
public DecompressionStream(
Stream stream,
int bufferSize = 0,
bool checkEndOfStream = true,
bool leaveOpen = true
)
: this(stream, new Decompressor(), bufferSize, checkEndOfStream, false, leaveOpen) { }
public DecompressionStream(
Stream stream,
Decompressor decompressor,
int bufferSize = 0,
bool checkEndOfStream = true,
bool preserveDecompressor = true,
bool leaveOpen = true
)
{
if (stream == null)
throw new ArgumentNullException(nameof(stream));
if (!stream.CanRead)
throw new ArgumentException("Stream is not readable", nameof(stream));
if (bufferSize < 0)
throw new ArgumentOutOfRangeException(nameof(bufferSize));
innerStream = stream;
this.decompressor = decompressor;
this.preserveDecompressor = preserveDecompressor;
this.leaveOpen = leaveOpen;
this.checkEndOfStream = checkEndOfStream;
inputBufferSize =
bufferSize > 0
? bufferSize
: (int)Unsafe.Methods.ZSTD_DStreamInSize().EnsureZstdSuccess();
inputBuffer = ArrayPool<byte>.Shared.Rent(inputBufferSize);
input = new ZSTD_inBuffer_s { pos = (nuint)inputBufferSize, size = (nuint)inputBufferSize };
}
public void SetParameter(ZSTD_dParameter parameter, int value)
{
EnsureNotDisposed();
decompressor.NotNull().SetParameter(parameter, value);
}
public int GetParameter(ZSTD_dParameter parameter)
{
EnsureNotDisposed();
return decompressor.NotNull().GetParameter(parameter);
}
public void LoadDictionary(byte[] dict)
{
EnsureNotDisposed();
decompressor.NotNull().LoadDictionary(dict);
}
~DecompressionStream() => Dispose(false);
protected override void Dispose(bool disposing)
{
if (decompressor == null)
return;
if (!preserveDecompressor)
{
decompressor.Dispose();
}
decompressor = null;
if (inputBuffer != null)
{
ArrayPool<byte>.Shared.Return(inputBuffer);
}
if (!leaveOpen)
{
innerStream.Dispose();
}
}
public override int Read(byte[] buffer, int offset, int count) =>
Read(new Span<byte>(buffer, offset, count));
#if !NETSTANDARD2_0 && !NETFRAMEWORK
public override int Read(Span<byte> buffer)
#else
public int Read(Span<byte> buffer)
#endif
{
EnsureNotDisposed();
// Guard against infinite loop (output.pos would never become non-zero)
if (buffer.Length == 0)
{
return 0;
}
var output = new ZSTD_outBuffer_s { pos = 0, size = (nuint)buffer.Length };
while (true)
{
// If there is still input available, or there might be data buffered in the decompressor context, flush that out
while (input.pos < input.size || !contextDrained)
{
nuint oldInputPos = input.pos;
nuint result = DecompressStream(ref output, buffer);
if (output.pos > 0 || oldInputPos != input.pos)
{
// Keep result from last decompress call that made some progress, so we known if we're at end of frame
lastDecompressResult = result;
}
// If decompression filled the output buffer, there might still be data buffered in the decompressor context
contextDrained = output.pos < output.size;
// If we have data to return, return it immediately, so we won't stall on Read
if (output.pos > 0)
{
return (int)output.pos;
}
}
// Otherwise, read some more input
int bytesRead;
if ((bytesRead = innerStream.Read(inputBuffer, 0, inputBufferSize)) == 0)
{
if (checkEndOfStream && lastDecompressResult != 0)
{
throw new EndOfStreamException("Premature end of stream");
}
return 0;
}
input.size = (nuint)bytesRead;
input.pos = 0;
}
}
#if !NETSTANDARD2_0 && !NETFRAMEWORK
public override Task<int> ReadAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken
) => ReadAsync(new Memory<byte>(buffer, offset, count), cancellationToken).AsTask();
public override async ValueTask<int> ReadAsync(
Memory<byte> buffer,
CancellationToken cancellationToken = default
)
#else
public override Task<int> ReadAsync(
byte[] buffer,
int offset,
int count,
CancellationToken cancellationToken
) => ReadAsync(new Memory<byte>(buffer, offset, count), cancellationToken);
public async Task<int> ReadAsync(
Memory<byte> buffer,
CancellationToken cancellationToken = default
)
#endif
{
EnsureNotDisposed();
// Guard against infinite loop (output.pos would never become non-zero)
if (buffer.Length == 0)
{
return 0;
}
var output = new ZSTD_outBuffer_s { pos = 0, size = (nuint)buffer.Length };
while (true)
{
// If there is still input available, or there might be data buffered in the decompressor context, flush that out
while (input.pos < input.size || !contextDrained)
{
nuint oldInputPos = input.pos;
nuint result = DecompressStream(ref output, buffer.Span);
if (output.pos > 0 || oldInputPos != input.pos)
{
// Keep result from last decompress call that made some progress, so we known if we're at end of frame
lastDecompressResult = result;
}
// If decompression filled the output buffer, there might still be data buffered in the decompressor context
contextDrained = output.pos < output.size;
// If we have data to return, return it immediately, so we won't stall on Read
if (output.pos > 0)
{
return (int)output.pos;
}
}
// Otherwise, read some more input
int bytesRead;
if (
(
bytesRead = await innerStream
.ReadAsync(inputBuffer, 0, inputBufferSize, cancellationToken)
.ConfigureAwait(false)
) == 0
)
{
if (checkEndOfStream && lastDecompressResult != 0)
{
throw new EndOfStreamException("Premature end of stream");
}
return 0;
}
input.size = (nuint)bytesRead;
input.pos = 0;
}
}
private unsafe nuint DecompressStream(ref ZSTD_outBuffer_s output, Span<byte> outputBuffer)
{
fixed (byte* inputBufferPtr = inputBuffer)
fixed (byte* outputBufferPtr = outputBuffer)
{
input.src = inputBufferPtr;
output.dst = outputBufferPtr;
return decompressor.NotNull().DecompressStream(ref input, ref output);
}
}
public override bool CanRead => true;
public override bool CanSeek => false;
public override bool CanWrite => false;
public override long Length => throw new NotSupportedException();
public override long Position
{
get => throw new NotSupportedException();
set => throw new NotSupportedException();
}
public override void Flush() => throw new NotSupportedException();
public override long Seek(long offset, SeekOrigin origin) => throw new NotSupportedException();
public override void SetLength(long value) => throw new NotSupportedException();
public override void Write(byte[] buffer, int offset, int count) =>
throw new NotSupportedException();
private void EnsureNotDisposed()
{
if (decompressor == null)
throw new ObjectDisposedException(nameof(DecompressionStream));
}
#if NETSTANDARD2_0 || NETFRAMEWORK
public virtual Task DisposeAsync()
{
try
{
Dispose();
return Task.CompletedTask;
}
catch (Exception exc)
{
return Task.FromException(exc);
}
}
#endif
}

View File

@@ -1,176 +0,0 @@
using System;
using SharpCompress.Compressors.ZStandard.Unsafe;
namespace SharpCompress.Compressors.ZStandard;
public unsafe class Decompressor : IDisposable
{
private readonly SafeDctxHandle handle;
public Decompressor()
{
handle = SafeDctxHandle.Create();
}
public void SetParameter(ZSTD_dParameter parameter, int value)
{
using var dctx = handle.Acquire();
Unsafe.Methods.ZSTD_DCtx_setParameter(dctx, parameter, value).EnsureZstdSuccess();
}
public int GetParameter(ZSTD_dParameter parameter)
{
using var dctx = handle.Acquire();
int value;
Unsafe.Methods.ZSTD_DCtx_getParameter(dctx, parameter, &value).EnsureZstdSuccess();
return value;
}
public void LoadDictionary(byte[] dict)
{
var dictReadOnlySpan = new ReadOnlySpan<byte>(dict);
this.LoadDictionary(dictReadOnlySpan);
}
public void LoadDictionary(ReadOnlySpan<byte> dict)
{
using var dctx = handle.Acquire();
fixed (byte* dictPtr = dict)
Unsafe
.Methods.ZSTD_DCtx_loadDictionary(dctx, dictPtr, (nuint)dict.Length)
.EnsureZstdSuccess();
}
public static ulong GetDecompressedSize(ReadOnlySpan<byte> src)
{
fixed (byte* srcPtr = src)
return Unsafe
.Methods.ZSTD_decompressBound(srcPtr, (nuint)src.Length)
.EnsureContentSizeOk();
}
public static ulong GetDecompressedSize(ArraySegment<byte> src) =>
GetDecompressedSize((ReadOnlySpan<byte>)src);
public static ulong GetDecompressedSize(byte[] src, int srcOffset, int srcLength) =>
GetDecompressedSize(new ReadOnlySpan<byte>(src, srcOffset, srcLength));
public Span<byte> Unwrap(ReadOnlySpan<byte> src, int maxDecompressedSize = int.MaxValue)
{
var expectedDstSize = GetDecompressedSize(src);
if (expectedDstSize > (ulong)maxDecompressedSize)
throw new ZstdException(
ZSTD_ErrorCode.ZSTD_error_dstSize_tooSmall,
$"Decompressed content size {expectedDstSize} is greater than {nameof(maxDecompressedSize)} {maxDecompressedSize}"
);
if (expectedDstSize > Constants.MaxByteArrayLength)
throw new ZstdException(
ZSTD_ErrorCode.ZSTD_error_dstSize_tooSmall,
$"Decompressed content size {expectedDstSize} is greater than max possible byte array size {Constants.MaxByteArrayLength}"
);
var dest = new byte[expectedDstSize];
var length = Unwrap(src, dest);
return new Span<byte>(dest, 0, length);
}
public int Unwrap(byte[] src, byte[] dest, int offset) =>
Unwrap(src, new Span<byte>(dest, offset, dest.Length - offset));
public int Unwrap(ReadOnlySpan<byte> src, Span<byte> dest)
{
fixed (byte* srcPtr = src)
fixed (byte* destPtr = dest)
{
using var dctx = handle.Acquire();
return (int)
Unsafe
.Methods.ZSTD_decompressDCtx(
dctx,
destPtr,
(nuint)dest.Length,
srcPtr,
(nuint)src.Length
)
.EnsureZstdSuccess();
}
}
public int Unwrap(
byte[] src,
int srcOffset,
int srcLength,
byte[] dst,
int dstOffset,
int dstLength
) =>
Unwrap(
new ReadOnlySpan<byte>(src, srcOffset, srcLength),
new Span<byte>(dst, dstOffset, dstLength)
);
public bool TryUnwrap(byte[] src, byte[] dest, int offset, out int written) =>
TryUnwrap(src, new Span<byte>(dest, offset, dest.Length - offset), out written);
public bool TryUnwrap(ReadOnlySpan<byte> src, Span<byte> dest, out int written)
{
fixed (byte* srcPtr = src)
fixed (byte* destPtr = dest)
{
nuint returnValue;
using (var dctx = handle.Acquire())
{
returnValue = Unsafe.Methods.ZSTD_decompressDCtx(
dctx,
destPtr,
(nuint)dest.Length,
srcPtr,
(nuint)src.Length
);
}
if (returnValue == unchecked(0 - (nuint)ZSTD_ErrorCode.ZSTD_error_dstSize_tooSmall))
{
written = default;
return false;
}
returnValue.EnsureZstdSuccess();
written = (int)returnValue;
return true;
}
}
public bool TryUnwrap(
byte[] src,
int srcOffset,
int srcLength,
byte[] dst,
int dstOffset,
int dstLength,
out int written
) =>
TryUnwrap(
new ReadOnlySpan<byte>(src, srcOffset, srcLength),
new Span<byte>(dst, dstOffset, dstLength),
out written
);
public void Dispose()
{
handle.Dispose();
GC.SuppressFinalize(this);
}
internal nuint DecompressStream(ref ZSTD_inBuffer_s input, ref ZSTD_outBuffer_s output)
{
fixed (ZSTD_inBuffer_s* inputPtr = &input)
fixed (ZSTD_outBuffer_s* outputPtr = &output)
{
using var dctx = handle.Acquire();
return Unsafe
.Methods.ZSTD_decompressStream(dctx, outputPtr, inputPtr)
.EnsureZstdSuccess();
}
}
}

View File

@@ -1,141 +0,0 @@
using System;
using System.Collections.Concurrent;
using System.Collections.Generic;
using System.Threading;
namespace SharpCompress.Compressors.ZStandard;
internal unsafe class JobThreadPool : IDisposable
{
private int numThreads;
private readonly List<JobThread> threads;
private readonly BlockingCollection<Job> queue;
private struct Job
{
public void* function;
public void* opaque;
}
private class JobThread
{
private Thread Thread { get; }
public CancellationTokenSource CancellationTokenSource { get; }
public JobThread(Thread thread)
{
CancellationTokenSource = new CancellationTokenSource();
Thread = thread;
}
public void Start()
{
Thread.Start(this);
}
public void Cancel()
{
CancellationTokenSource.Cancel();
}
public void Join()
{
Thread.Join();
}
}
private void Worker(object? obj)
{
if (obj is not JobThread poolThread)
return;
var cancellationToken = poolThread.CancellationTokenSource.Token;
while (!queue.IsCompleted && !cancellationToken.IsCancellationRequested)
{
try
{
if (queue.TryTake(out var job, -1, cancellationToken))
((delegate* managed<void*, void>)job.function)(job.opaque);
}
catch (InvalidOperationException) { }
catch (OperationCanceledException) { }
}
}
public JobThreadPool(int num, int queueSize)
{
numThreads = num;
queue = new BlockingCollection<Job>(queueSize + 1);
threads = new List<JobThread>(num);
for (var i = 0; i < numThreads; i++)
CreateThread();
}
private void CreateThread()
{
var poolThread = new JobThread(new Thread(Worker));
threads.Add(poolThread);
poolThread.Start();
}
public void Resize(int num)
{
lock (threads)
{
if (num < numThreads)
{
for (var i = numThreads - 1; i >= num; i--)
{
threads[i].Cancel();
threads.RemoveAt(i);
}
}
else
{
for (var i = numThreads; i < num; i++)
CreateThread();
}
}
numThreads = num;
}
public void Add(void* function, void* opaque)
{
queue.Add(new Job { function = function, opaque = opaque });
}
public bool TryAdd(void* function, void* opaque)
{
return queue.TryAdd(new Job { function = function, opaque = opaque });
}
public void Join(bool cancel = true)
{
queue.CompleteAdding();
List<JobThread> jobThreads;
lock (threads)
jobThreads = new List<JobThread>(threads);
if (cancel)
{
foreach (var thread in jobThreads)
thread.Cancel();
}
foreach (var thread in jobThreads)
thread.Join();
}
public void Dispose()
{
queue.Dispose();
}
public int Size()
{
// todo not implemented
// https://github.com/dotnet/runtime/issues/24200
return 0;
}
}

View File

@@ -1,163 +0,0 @@
using System;
using System.Runtime.InteropServices;
using SharpCompress.Compressors.ZStandard.Unsafe;
namespace SharpCompress.Compressors.ZStandard;
/// <summary>
/// Provides the base class for ZstdSharp <see cref="SafeHandle"/> implementations.
/// </summary>
/// <remarks>
/// Even though ZstdSharp is a managed library, its internals are using unmanaged
/// memory and we are using safe handles in the library's high-level API to ensure
/// proper disposal of unmanaged resources and increase safety.
/// </remarks>
/// <seealso cref="SafeCctxHandle"/>
/// <seealso cref="SafeDctxHandle"/>
internal abstract unsafe class SafeZstdHandle : SafeHandle
{
/// <summary>
/// Parameterless constructor is hidden. Use the static <c>Create</c> factory
/// method to create a new safe handle instance.
/// </summary>
protected SafeZstdHandle()
: base(IntPtr.Zero, true) { }
public sealed override bool IsInvalid => handle == IntPtr.Zero;
}
/// <summary>
/// Safely wraps an unmanaged Zstd compression context.
/// </summary>
internal sealed unsafe class SafeCctxHandle : SafeZstdHandle
{
/// <inheritdoc/>
private SafeCctxHandle() { }
/// <summary>
/// Creates a new instance of <see cref="SafeCctxHandle"/>.
/// </summary>
/// <returns></returns>
/// <exception cref="ZstdException">Creation failed.</exception>
public static SafeCctxHandle Create()
{
var safeHandle = new SafeCctxHandle();
bool success = false;
try
{
var cctx = Unsafe.Methods.ZSTD_createCCtx();
if (cctx == null)
throw new ZstdException(ZSTD_ErrorCode.ZSTD_error_GENERIC, "Failed to create cctx");
safeHandle.SetHandle((IntPtr)cctx);
success = true;
}
finally
{
if (!success)
{
safeHandle.SetHandleAsInvalid();
}
}
return safeHandle;
}
/// <summary>
/// Acquires a reference to the safe handle.
/// </summary>
/// <returns>
/// A <see cref="SafeHandleHolder{T}"/> instance that can be implicitly converted to a pointer
/// to <see cref="ZSTD_CCtx_s"/>.
/// </returns>
public SafeHandleHolder<ZSTD_CCtx_s> Acquire() => new(this);
protected override bool ReleaseHandle()
{
return Unsafe.Methods.ZSTD_freeCCtx((ZSTD_CCtx_s*)handle) == 0;
}
}
/// <summary>
/// Safely wraps an unmanaged Zstd compression context.
/// </summary>
internal sealed unsafe class SafeDctxHandle : SafeZstdHandle
{
/// <inheritdoc/>
private SafeDctxHandle() { }
/// <summary>
/// Creates a new instance of <see cref="SafeDctxHandle"/>.
/// </summary>
/// <returns></returns>
/// <exception cref="ZstdException">Creation failed.</exception>
public static SafeDctxHandle Create()
{
var safeHandle = new SafeDctxHandle();
bool success = false;
try
{
var dctx = Unsafe.Methods.ZSTD_createDCtx();
if (dctx == null)
throw new ZstdException(ZSTD_ErrorCode.ZSTD_error_GENERIC, "Failed to create dctx");
safeHandle.SetHandle((IntPtr)dctx);
success = true;
}
finally
{
if (!success)
{
safeHandle.SetHandleAsInvalid();
}
}
return safeHandle;
}
/// <summary>
/// Acquires a reference to the safe handle.
/// </summary>
/// <returns>
/// A <see cref="SafeHandleHolder{T}"/> instance that can be implicitly converted to a pointer
/// to <see cref="ZSTD_DCtx_s"/>.
/// </returns>
public SafeHandleHolder<ZSTD_DCtx_s> Acquire() => new(this);
protected override bool ReleaseHandle()
{
return Unsafe.Methods.ZSTD_freeDCtx((ZSTD_DCtx_s*)handle) == 0;
}
}
/// <summary>
/// Provides a convenient interface to safely acquire pointers of a specific type
/// from a <see cref="SafeHandle"/>, by utilizing <see langword="using"/> blocks.
/// </summary>
/// <typeparam name="T">The type of pointers to return.</typeparam>
/// <remarks>
/// Safe handle holders can be <see cref="Dispose"/>d to decrement the safe handle's
/// reference count, and can be implicitly converted to pointers to <see cref="T"/>.
/// </remarks>
internal unsafe ref struct SafeHandleHolder<T>
where T : unmanaged
{
private readonly SafeHandle _handle;
private bool _refAdded;
public SafeHandleHolder(SafeHandle safeHandle)
{
_handle = safeHandle;
_refAdded = false;
safeHandle.DangerousAddRef(ref _refAdded);
}
public static implicit operator T*(SafeHandleHolder<T> holder) =>
(T*)holder._handle.DangerousGetHandle();
public void Dispose()
{
if (_refAdded)
{
_handle.DangerousRelease();
_refAdded = false;
}
}
}

View File

@@ -1,22 +0,0 @@
using System.Threading;
namespace SharpCompress.Compressors.ZStandard;
internal static unsafe class SynchronizationWrapper
{
private static object UnwrapObject(void** obj) => UnmanagedObject.Unwrap<object>(*obj);
public static void Init(void** obj) => *obj = UnmanagedObject.Wrap(new object());
public static void Free(void** obj) => UnmanagedObject.Free(*obj);
public static void Enter(void** obj) => Monitor.Enter(UnwrapObject(obj));
public static void Exit(void** obj) => Monitor.Exit(UnwrapObject(obj));
public static void Pulse(void** obj) => Monitor.Pulse(UnwrapObject(obj));
public static void PulseAll(void** obj) => Monitor.PulseAll(UnwrapObject(obj));
public static void Wait(void** mutex) => Monitor.Wait(UnwrapObject(mutex));
}

View File

@@ -1,48 +0,0 @@
using SharpCompress.Compressors.ZStandard.Unsafe;
namespace SharpCompress.Compressors.ZStandard;
public static unsafe class ThrowHelper
{
private const ulong ZSTD_CONTENTSIZE_UNKNOWN = unchecked(0UL - 1);
private const ulong ZSTD_CONTENTSIZE_ERROR = unchecked(0UL - 2);
public static nuint EnsureZstdSuccess(this nuint returnValue)
{
if (Unsafe.Methods.ZSTD_isError(returnValue))
ThrowException(returnValue, Unsafe.Methods.ZSTD_getErrorName(returnValue));
return returnValue;
}
public static nuint EnsureZdictSuccess(this nuint returnValue)
{
if (Unsafe.Methods.ZDICT_isError(returnValue))
ThrowException(returnValue, Unsafe.Methods.ZDICT_getErrorName(returnValue));
return returnValue;
}
public static ulong EnsureContentSizeOk(this ulong returnValue)
{
if (returnValue == ZSTD_CONTENTSIZE_UNKNOWN)
throw new ZstdException(
ZSTD_ErrorCode.ZSTD_error_GENERIC,
"Decompressed content size is not specified"
);
if (returnValue == ZSTD_CONTENTSIZE_ERROR)
throw new ZstdException(
ZSTD_ErrorCode.ZSTD_error_GENERIC,
"Decompressed content size cannot be determined (e.g. invalid magic number, srcSize too small)"
);
return returnValue;
}
private static void ThrowException(nuint returnValue, string message)
{
var code = 0 - returnValue;
throw new ZstdException((ZSTD_ErrorCode)code, message);
}
}

View File

@@ -1,18 +0,0 @@
using System;
using System.Runtime.InteropServices;
namespace SharpCompress.Compressors.ZStandard;
/*
* Wrap object to void* to make it unmanaged
*/
internal static unsafe class UnmanagedObject
{
public static void* Wrap(object obj) => (void*)GCHandle.ToIntPtr(GCHandle.Alloc(obj));
private static GCHandle UnwrapGcHandle(void* value) => GCHandle.FromIntPtr((IntPtr)value);
public static T Unwrap<T>(void* value) => (T)UnwrapGcHandle(value).Target!;
public static void Free(void* value) => UnwrapGcHandle(value).Free();
}

View File

@@ -1,52 +0,0 @@
using System.Runtime.CompilerServices;
using static SharpCompress.Compressors.ZStandard.UnsafeHelper;
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
/* custom memory allocation functions */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void* ZSTD_customMalloc(nuint size, ZSTD_customMem customMem)
{
if (customMem.customAlloc != null)
return ((delegate* managed<void*, nuint, void*>)customMem.customAlloc)(
customMem.opaque,
size
);
return malloc(size);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void* ZSTD_customCalloc(nuint size, ZSTD_customMem customMem)
{
if (customMem.customAlloc != null)
{
/* calloc implemented as malloc+memset;
* not as efficient as calloc, but next best guess for custom malloc */
void* ptr = ((delegate* managed<void*, nuint, void*>)customMem.customAlloc)(
customMem.opaque,
size
);
memset(ptr, 0, (uint)size);
return ptr;
}
return calloc(1, size);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void ZSTD_customFree(void* ptr, ZSTD_customMem customMem)
{
if (ptr != null)
{
if (customMem.customFree != null)
((delegate* managed<void*, void*, void>)customMem.customFree)(
customMem.opaque,
ptr
);
else
free(ptr);
}
}
}

View File

@@ -1,14 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/* bitStream can mix input from multiple sources.
* A critical property of these streams is that they encode and decode in **reverse** direction.
* So the first bit sequence you add will be the last to be read, like a LIFO stack.
*/
public unsafe struct BIT_CStream_t
{
public nuint bitContainer;
public uint bitPos;
public sbyte* startPtr;
public sbyte* ptr;
public sbyte* endPtr;
}

View File

@@ -1,16 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public enum BIT_DStream_status
{
/* fully refilled */
BIT_DStream_unfinished = 0,
/* still some bits left in bitstream */
BIT_DStream_endOfBuffer = 1,
/* bitstream entirely consumed, bit-exact */
BIT_DStream_completed = 2,
/* user requested more bits than present in bitstream */
BIT_DStream_overflow = 3,
}

View File

@@ -1,13 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/*-********************************************
* bitStream decoding API (read backward)
**********************************************/
public unsafe struct BIT_DStream_t
{
public nuint bitContainer;
public uint bitsConsumed;
public sbyte* ptr;
public sbyte* start;
public sbyte* limitPtr;
}

View File

@@ -1,60 +0,0 @@
using System;
using System.Numerics;
using System.Runtime.CompilerServices;
using static SharpCompress.Compressors.ZStandard.UnsafeHelper;
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint ZSTD_countTrailingZeros32(uint val)
{
assert(val != 0);
return (uint)BitOperations.TrailingZeroCount(val);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint ZSTD_countLeadingZeros32(uint val)
{
assert(val != 0);
return (uint)BitOperations.LeadingZeroCount(val);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint ZSTD_countTrailingZeros64(ulong val)
{
assert(val != 0);
return (uint)BitOperations.TrailingZeroCount(val);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint ZSTD_countLeadingZeros64(ulong val)
{
assert(val != 0);
return (uint)BitOperations.LeadingZeroCount(val);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint ZSTD_NbCommonBytes(nuint val)
{
assert(val != 0);
if (BitConverter.IsLittleEndian)
{
return MEM_64bits
? (uint)BitOperations.TrailingZeroCount(val) >> 3
: (uint)BitOperations.TrailingZeroCount((uint)val) >> 3;
}
return MEM_64bits
? (uint)BitOperations.LeadingZeroCount(val) >> 3
: (uint)BitOperations.LeadingZeroCount((uint)val) >> 3;
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint ZSTD_highbit32(uint val)
{
assert(val != 0);
return (uint)BitOperations.Log2(val);
}
}

View File

@@ -1,739 +0,0 @@
using System;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;
using static SharpCompress.Compressors.ZStandard.UnsafeHelper;
#if NETCOREAPP3_0_OR_GREATER
using System.Runtime.Intrinsics.X86;
#endif
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
#if NET7_0_OR_GREATER
private static ReadOnlySpan<uint> Span_BIT_mask =>
new uint[32]
{
0,
1,
3,
7,
0xF,
0x1F,
0x3F,
0x7F,
0xFF,
0x1FF,
0x3FF,
0x7FF,
0xFFF,
0x1FFF,
0x3FFF,
0x7FFF,
0xFFFF,
0x1FFFF,
0x3FFFF,
0x7FFFF,
0xFFFFF,
0x1FFFFF,
0x3FFFFF,
0x7FFFFF,
0xFFFFFF,
0x1FFFFFF,
0x3FFFFFF,
0x7FFFFFF,
0xFFFFFFF,
0x1FFFFFFF,
0x3FFFFFFF,
0x7FFFFFFF,
};
private static uint* BIT_mask =>
(uint*)
System.Runtime.CompilerServices.Unsafe.AsPointer(
ref MemoryMarshal.GetReference(Span_BIT_mask)
);
#else
private static readonly uint* BIT_mask = GetArrayPointer(
new uint[32]
{
0,
1,
3,
7,
0xF,
0x1F,
0x3F,
0x7F,
0xFF,
0x1FF,
0x3FF,
0x7FF,
0xFFF,
0x1FFF,
0x3FFF,
0x7FFF,
0xFFFF,
0x1FFFF,
0x3FFFF,
0x7FFFF,
0xFFFFF,
0x1FFFFF,
0x3FFFFF,
0x7FFFFF,
0xFFFFFF,
0x1FFFFFF,
0x3FFFFFF,
0x7FFFFFF,
0xFFFFFFF,
0x1FFFFFFF,
0x3FFFFFFF,
0x7FFFFFFF,
}
);
#endif
/*-**************************************************************
* bitStream encoding
****************************************************************/
/*! BIT_initCStream() :
* `dstCapacity` must be > sizeof(size_t)
* @return : 0 if success,
* otherwise an error code (can be tested using ERR_isError()) */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_initCStream(ref BIT_CStream_t bitC, void* startPtr, nuint dstCapacity)
{
bitC.bitContainer = 0;
bitC.bitPos = 0;
bitC.startPtr = (sbyte*)startPtr;
bitC.ptr = bitC.startPtr;
bitC.endPtr = bitC.startPtr + dstCapacity - sizeof(nuint);
if (dstCapacity <= (nuint)sizeof(nuint))
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_dstSize_tooSmall));
return 0;
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_getLowerBits(nuint bitContainer, uint nbBits)
{
assert(nbBits < sizeof(uint) * 32 / sizeof(uint));
#if NETCOREAPP3_1_OR_GREATER
if (Bmi2.X64.IsSupported)
{
return (nuint)Bmi2.X64.ZeroHighBits(bitContainer, nbBits);
}
if (Bmi2.IsSupported)
{
return Bmi2.ZeroHighBits((uint)bitContainer, nbBits);
}
#endif
return bitContainer & BIT_mask[nbBits];
}
/*! BIT_addBits() :
* can add up to 31 bits into `bitC`.
* Note : does not check for register overflow ! */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void BIT_addBits(
ref nuint bitC_bitContainer,
ref uint bitC_bitPos,
nuint value,
uint nbBits
)
{
assert(nbBits < sizeof(uint) * 32 / sizeof(uint));
assert(nbBits + bitC_bitPos < (uint)(sizeof(nuint) * 8));
bitC_bitContainer |= BIT_getLowerBits(value, nbBits) << (int)bitC_bitPos;
bitC_bitPos += nbBits;
}
/*! BIT_addBitsFast() :
* works only if `value` is _clean_,
* meaning all high bits above nbBits are 0 */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void BIT_addBitsFast(
ref nuint bitC_bitContainer,
ref uint bitC_bitPos,
nuint value,
uint nbBits
)
{
assert(value >> (int)nbBits == 0);
assert(nbBits + bitC_bitPos < (uint)(sizeof(nuint) * 8));
bitC_bitContainer |= value << (int)bitC_bitPos;
bitC_bitPos += nbBits;
}
/*! BIT_flushBitsFast() :
* assumption : bitContainer has not overflowed
* unsafe version; does not check buffer overflow */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void BIT_flushBitsFast(
ref nuint bitC_bitContainer,
ref uint bitC_bitPos,
ref sbyte* bitC_ptr,
sbyte* bitC_endPtr
)
{
nuint nbBytes = bitC_bitPos >> 3;
assert(bitC_bitPos < (uint)(sizeof(nuint) * 8));
assert(bitC_ptr <= bitC_endPtr);
MEM_writeLEST(bitC_ptr, bitC_bitContainer);
bitC_ptr += nbBytes;
bitC_bitPos &= 7;
bitC_bitContainer >>= (int)(nbBytes * 8);
}
/*! BIT_flushBits() :
* assumption : bitContainer has not overflowed
* safe version; check for buffer overflow, and prevents it.
* note : does not signal buffer overflow.
* overflow will be revealed later on using BIT_closeCStream() */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void BIT_flushBits(
ref nuint bitC_bitContainer,
ref uint bitC_bitPos,
ref sbyte* bitC_ptr,
sbyte* bitC_endPtr
)
{
nuint nbBytes = bitC_bitPos >> 3;
assert(bitC_bitPos < (uint)(sizeof(nuint) * 8));
assert(bitC_ptr <= bitC_endPtr);
MEM_writeLEST(bitC_ptr, bitC_bitContainer);
bitC_ptr += nbBytes;
if (bitC_ptr > bitC_endPtr)
bitC_ptr = bitC_endPtr;
bitC_bitPos &= 7;
bitC_bitContainer >>= (int)(nbBytes * 8);
}
/*! BIT_closeCStream() :
* @return : size of CStream, in bytes,
* or 0 if it could not fit into dstBuffer */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_closeCStream(
ref nuint bitC_bitContainer,
ref uint bitC_bitPos,
sbyte* bitC_ptr,
sbyte* bitC_endPtr,
sbyte* bitC_startPtr
)
{
BIT_addBitsFast(ref bitC_bitContainer, ref bitC_bitPos, 1, 1);
BIT_flushBits(ref bitC_bitContainer, ref bitC_bitPos, ref bitC_ptr, bitC_endPtr);
if (bitC_ptr >= bitC_endPtr)
return 0;
return (nuint)(bitC_ptr - bitC_startPtr) + (nuint)(bitC_bitPos > 0 ? 1 : 0);
}
/*-********************************************************
* bitStream decoding
**********************************************************/
/*! BIT_initDStream() :
* Initialize a BIT_DStream_t.
* `bitD` : a pointer to an already allocated BIT_DStream_t structure.
* `srcSize` must be the *exact* size of the bitStream, in bytes.
* @return : size of stream (== srcSize), or an errorCode if a problem is detected
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_initDStream(BIT_DStream_t* bitD, void* srcBuffer, nuint srcSize)
{
if (srcSize < 1)
{
*bitD = new BIT_DStream_t();
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_srcSize_wrong));
}
bitD->start = (sbyte*)srcBuffer;
bitD->limitPtr = bitD->start + sizeof(nuint);
if (srcSize >= (nuint)sizeof(nuint))
{
bitD->ptr = (sbyte*)srcBuffer + srcSize - sizeof(nuint);
bitD->bitContainer = MEM_readLEST(bitD->ptr);
{
byte lastByte = ((byte*)srcBuffer)[srcSize - 1];
bitD->bitsConsumed = lastByte != 0 ? 8 - ZSTD_highbit32(lastByte) : 0;
if (lastByte == 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_GENERIC));
}
}
else
{
bitD->ptr = bitD->start;
bitD->bitContainer = *(byte*)bitD->start;
switch (srcSize)
{
case 7:
bitD->bitContainer += (nuint)((byte*)srcBuffer)[6] << sizeof(nuint) * 8 - 16;
goto case 6;
case 6:
bitD->bitContainer += (nuint)((byte*)srcBuffer)[5] << sizeof(nuint) * 8 - 24;
goto case 5;
case 5:
bitD->bitContainer += (nuint)((byte*)srcBuffer)[4] << sizeof(nuint) * 8 - 32;
goto case 4;
case 4:
bitD->bitContainer += (nuint)((byte*)srcBuffer)[3] << 24;
goto case 3;
case 3:
bitD->bitContainer += (nuint)((byte*)srcBuffer)[2] << 16;
goto case 2;
case 2:
bitD->bitContainer += (nuint)((byte*)srcBuffer)[1] << 8;
goto default;
default:
break;
}
{
byte lastByte = ((byte*)srcBuffer)[srcSize - 1];
bitD->bitsConsumed = lastByte != 0 ? 8 - ZSTD_highbit32(lastByte) : 0;
if (lastByte == 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
}
bitD->bitsConsumed += (uint)((nuint)sizeof(nuint) - srcSize) * 8;
}
return srcSize;
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_getUpperBits(nuint bitContainer, uint start)
{
return bitContainer >> (int)start;
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_getMiddleBits(nuint bitContainer, uint start, uint nbBits)
{
uint regMask = (uint)(sizeof(nuint) * 8 - 1);
assert(nbBits < sizeof(uint) * 32 / sizeof(uint));
#if NETCOREAPP3_1_OR_GREATER
if (Bmi2.X64.IsSupported)
{
return (nuint)Bmi2.X64.ZeroHighBits(bitContainer >> (int)(start & regMask), nbBits);
}
if (Bmi2.IsSupported)
{
return Bmi2.ZeroHighBits((uint)(bitContainer >> (int)(start & regMask)), nbBits);
}
#endif
return (nuint)(bitContainer >> (int)(start & regMask) & ((ulong)1 << (int)nbBits) - 1);
}
/*! BIT_lookBits() :
* Provides next n bits from local register.
* local register is not modified.
* On 32-bits, maxNbBits==24.
* On 64-bits, maxNbBits==56.
* @return : value extracted */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_lookBits(BIT_DStream_t* bitD, uint nbBits)
{
return BIT_getMiddleBits(
bitD->bitContainer,
(uint)(sizeof(nuint) * 8) - bitD->bitsConsumed - nbBits,
nbBits
);
}
/*! BIT_lookBitsFast() :
* unsafe version; only works if nbBits >= 1 */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_lookBitsFast(BIT_DStream_t* bitD, uint nbBits)
{
uint regMask = (uint)(sizeof(nuint) * 8 - 1);
assert(nbBits >= 1);
return bitD->bitContainer
<< (int)(bitD->bitsConsumed & regMask)
>> (int)(regMask + 1 - nbBits & regMask);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void BIT_skipBits(BIT_DStream_t* bitD, uint nbBits)
{
bitD->bitsConsumed += nbBits;
}
/*! BIT_readBits() :
* Read (consume) next n bits from local register and update.
* Pay attention to not read more than nbBits contained into local register.
* @return : extracted value. */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_readBits(BIT_DStream_t* bitD, uint nbBits)
{
nuint value = BIT_lookBits(bitD, nbBits);
BIT_skipBits(bitD, nbBits);
return value;
}
/*! BIT_readBitsFast() :
* unsafe version; only works if nbBits >= 1 */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_readBitsFast(BIT_DStream_t* bitD, uint nbBits)
{
nuint value = BIT_lookBitsFast(bitD, nbBits);
assert(nbBits >= 1);
BIT_skipBits(bitD, nbBits);
return value;
}
/*! BIT_reloadDStream_internal() :
* Simple variant of BIT_reloadDStream(), with two conditions:
* 1. bitstream is valid : bitsConsumed <= sizeof(bitD->bitContainer)*8
* 2. look window is valid after shifted down : bitD->ptr >= bitD->start
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static BIT_DStream_status BIT_reloadDStream_internal(BIT_DStream_t* bitD)
{
assert(bitD->bitsConsumed <= (uint)(sizeof(nuint) * 8));
bitD->ptr -= bitD->bitsConsumed >> 3;
assert(bitD->ptr >= bitD->start);
bitD->bitsConsumed &= 7;
bitD->bitContainer = MEM_readLEST(bitD->ptr);
return BIT_DStream_status.BIT_DStream_unfinished;
}
/*! BIT_reloadDStreamFast() :
* Similar to BIT_reloadDStream(), but with two differences:
* 1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold!
* 2. Returns BIT_DStream_overflow when bitD->ptr < bitD->limitPtr, at this
* point you must use BIT_reloadDStream() to reload.
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD)
{
if (bitD->ptr < bitD->limitPtr)
return BIT_DStream_status.BIT_DStream_overflow;
return BIT_reloadDStream_internal(bitD);
}
#if NET7_0_OR_GREATER
private static ReadOnlySpan<byte> Span_static_zeroFilled =>
new byte[] { 0, 0, 0, 0, 0, 0, 0, 0 };
private static nuint* static_zeroFilled =>
(nuint*)
System.Runtime.CompilerServices.Unsafe.AsPointer(
ref MemoryMarshal.GetReference(Span_static_zeroFilled)
);
#else
private static readonly nuint* static_zeroFilled = (nuint*)GetArrayPointer(
new byte[] { 0, 0, 0, 0, 0, 0, 0, 0 }
);
#endif
/*! BIT_reloadDStream() :
* Refill `bitD` from buffer previously set in BIT_initDStream() .
* This function is safe, it guarantees it will not never beyond src buffer.
* @return : status of `BIT_DStream_t` internal register.
* when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
{
if (bitD->bitsConsumed > (uint)(sizeof(nuint) * 8))
{
bitD->ptr = (sbyte*)&static_zeroFilled[0];
return BIT_DStream_status.BIT_DStream_overflow;
}
assert(bitD->ptr >= bitD->start);
if (bitD->ptr >= bitD->limitPtr)
{
return BIT_reloadDStream_internal(bitD);
}
if (bitD->ptr == bitD->start)
{
if (bitD->bitsConsumed < (uint)(sizeof(nuint) * 8))
return BIT_DStream_status.BIT_DStream_endOfBuffer;
return BIT_DStream_status.BIT_DStream_completed;
}
{
uint nbBytes = bitD->bitsConsumed >> 3;
BIT_DStream_status result = BIT_DStream_status.BIT_DStream_unfinished;
if (bitD->ptr - nbBytes < bitD->start)
{
nbBytes = (uint)(bitD->ptr - bitD->start);
result = BIT_DStream_status.BIT_DStream_endOfBuffer;
}
bitD->ptr -= nbBytes;
bitD->bitsConsumed -= nbBytes * 8;
bitD->bitContainer = MEM_readLEST(bitD->ptr);
return result;
}
}
/*! BIT_endOfDStream() :
* @return : 1 if DStream has _exactly_ reached its end (all bits consumed).
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint BIT_endOfDStream(BIT_DStream_t* DStream)
{
return DStream->ptr == DStream->start && DStream->bitsConsumed == (uint)(sizeof(nuint) * 8)
? 1U
: 0U;
}
/*-********************************************************
* bitStream decoding
**********************************************************/
/*! BIT_initDStream() :
* Initialize a BIT_DStream_t.
* `bitD` : a pointer to an already allocated BIT_DStream_t structure.
* `srcSize` must be the *exact* size of the bitStream, in bytes.
* @return : size of stream (== srcSize), or an errorCode if a problem is detected
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_initDStream(ref BIT_DStream_t bitD, void* srcBuffer, nuint srcSize)
{
if (srcSize < 1)
{
bitD = new BIT_DStream_t();
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_srcSize_wrong));
}
bitD.start = (sbyte*)srcBuffer;
bitD.limitPtr = bitD.start + sizeof(nuint);
if (srcSize >= (nuint)sizeof(nuint))
{
bitD.ptr = (sbyte*)srcBuffer + srcSize - sizeof(nuint);
bitD.bitContainer = MEM_readLEST(bitD.ptr);
{
byte lastByte = ((byte*)srcBuffer)[srcSize - 1];
bitD.bitsConsumed = lastByte != 0 ? 8 - ZSTD_highbit32(lastByte) : 0;
if (lastByte == 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_GENERIC));
}
}
else
{
bitD.ptr = bitD.start;
bitD.bitContainer = *(byte*)bitD.start;
switch (srcSize)
{
case 7:
bitD.bitContainer += (nuint)((byte*)srcBuffer)[6] << sizeof(nuint) * 8 - 16;
goto case 6;
case 6:
bitD.bitContainer += (nuint)((byte*)srcBuffer)[5] << sizeof(nuint) * 8 - 24;
goto case 5;
case 5:
bitD.bitContainer += (nuint)((byte*)srcBuffer)[4] << sizeof(nuint) * 8 - 32;
goto case 4;
case 4:
bitD.bitContainer += (nuint)((byte*)srcBuffer)[3] << 24;
goto case 3;
case 3:
bitD.bitContainer += (nuint)((byte*)srcBuffer)[2] << 16;
goto case 2;
case 2:
bitD.bitContainer += (nuint)((byte*)srcBuffer)[1] << 8;
goto default;
default:
break;
}
{
byte lastByte = ((byte*)srcBuffer)[srcSize - 1];
bitD.bitsConsumed = lastByte != 0 ? 8 - ZSTD_highbit32(lastByte) : 0;
if (lastByte == 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
}
bitD.bitsConsumed += (uint)((nuint)sizeof(nuint) - srcSize) * 8;
}
return srcSize;
}
/*! BIT_lookBits() :
* Provides next n bits from local register.
* local register is not modified.
* On 32-bits, maxNbBits==24.
* On 64-bits, maxNbBits==56.
* @return : value extracted */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_lookBits(nuint bitD_bitContainer, uint bitD_bitsConsumed, uint nbBits)
{
return BIT_getMiddleBits(
bitD_bitContainer,
(uint)(sizeof(nuint) * 8) - bitD_bitsConsumed - nbBits,
nbBits
);
}
/*! BIT_lookBitsFast() :
* unsafe version; only works if nbBits >= 1 */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_lookBitsFast(
nuint bitD_bitContainer,
uint bitD_bitsConsumed,
uint nbBits
)
{
uint regMask = (uint)(sizeof(nuint) * 8 - 1);
assert(nbBits >= 1);
return bitD_bitContainer
<< (int)(bitD_bitsConsumed & regMask)
>> (int)(regMask + 1 - nbBits & regMask);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void BIT_skipBits(ref uint bitD_bitsConsumed, uint nbBits)
{
bitD_bitsConsumed += nbBits;
}
/*! BIT_readBits() :
* Read (consume) next n bits from local register and update.
* Pay attention to not read more than nbBits contained into local register.
* @return : extracted value. */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_readBits(
nuint bitD_bitContainer,
ref uint bitD_bitsConsumed,
uint nbBits
)
{
nuint value = BIT_lookBits(bitD_bitContainer, bitD_bitsConsumed, nbBits);
BIT_skipBits(ref bitD_bitsConsumed, nbBits);
return value;
}
/*! BIT_readBitsFast() :
* unsafe version; only works if nbBits >= 1 */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint BIT_readBitsFast(
nuint bitD_bitContainer,
ref uint bitD_bitsConsumed,
uint nbBits
)
{
nuint value = BIT_lookBitsFast(bitD_bitContainer, bitD_bitsConsumed, nbBits);
assert(nbBits >= 1);
BIT_skipBits(ref bitD_bitsConsumed, nbBits);
return value;
}
/*! BIT_reloadDStreamFast() :
* Similar to BIT_reloadDStream(), but with two differences:
* 1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold!
* 2. Returns BIT_DStream_overflow when bitD->ptr < bitD->limitPtr, at this
* point you must use BIT_reloadDStream() to reload.
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static BIT_DStream_status BIT_reloadDStreamFast(
ref nuint bitD_bitContainer,
ref uint bitD_bitsConsumed,
ref sbyte* bitD_ptr,
sbyte* bitD_start,
sbyte* bitD_limitPtr
)
{
if (bitD_ptr < bitD_limitPtr)
return BIT_DStream_status.BIT_DStream_overflow;
return BIT_reloadDStream_internal(
ref bitD_bitContainer,
ref bitD_bitsConsumed,
ref bitD_ptr,
bitD_start
);
}
/*! BIT_reloadDStream() :
* Refill `bitD` from buffer previously set in BIT_initDStream() .
* This function is safe, it guarantees it will not never beyond src buffer.
* @return : status of `BIT_DStream_t` internal register.
* when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static BIT_DStream_status BIT_reloadDStream(
ref nuint bitD_bitContainer,
ref uint bitD_bitsConsumed,
ref sbyte* bitD_ptr,
sbyte* bitD_start,
sbyte* bitD_limitPtr
)
{
if (bitD_bitsConsumed > (uint)(sizeof(nuint) * 8))
{
bitD_ptr = (sbyte*)&static_zeroFilled[0];
return BIT_DStream_status.BIT_DStream_overflow;
}
assert(bitD_ptr >= bitD_start);
if (bitD_ptr >= bitD_limitPtr)
{
return BIT_reloadDStream_internal(
ref bitD_bitContainer,
ref bitD_bitsConsumed,
ref bitD_ptr,
bitD_start
);
}
if (bitD_ptr == bitD_start)
{
if (bitD_bitsConsumed < (uint)(sizeof(nuint) * 8))
return BIT_DStream_status.BIT_DStream_endOfBuffer;
return BIT_DStream_status.BIT_DStream_completed;
}
{
uint nbBytes = bitD_bitsConsumed >> 3;
BIT_DStream_status result = BIT_DStream_status.BIT_DStream_unfinished;
if (bitD_ptr - nbBytes < bitD_start)
{
nbBytes = (uint)(bitD_ptr - bitD_start);
result = BIT_DStream_status.BIT_DStream_endOfBuffer;
}
bitD_ptr -= nbBytes;
bitD_bitsConsumed -= nbBytes * 8;
bitD_bitContainer = MEM_readLEST(bitD_ptr);
return result;
}
}
/*! BIT_reloadDStream_internal() :
* Simple variant of BIT_reloadDStream(), with two conditions:
* 1. bitstream is valid : bitsConsumed <= sizeof(bitD->bitContainer)*8
* 2. look window is valid after shifted down : bitD->ptr >= bitD->start
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static BIT_DStream_status BIT_reloadDStream_internal(
ref nuint bitD_bitContainer,
ref uint bitD_bitsConsumed,
ref sbyte* bitD_ptr,
sbyte* bitD_start
)
{
assert(bitD_bitsConsumed <= (uint)(sizeof(nuint) * 8));
bitD_ptr -= bitD_bitsConsumed >> 3;
assert(bitD_ptr >= bitD_start);
bitD_bitsConsumed &= 7;
bitD_bitContainer = MEM_readLEST(bitD_ptr);
return BIT_DStream_status.BIT_DStream_unfinished;
}
/*! BIT_endOfDStream() :
* @return : 1 if DStream has _exactly_ reached its end (all bits consumed).
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static uint BIT_endOfDStream(
uint DStream_bitsConsumed,
sbyte* DStream_ptr,
sbyte* DStream_start
)
{
return DStream_ptr == DStream_start && DStream_bitsConsumed == (uint)(sizeof(nuint) * 8)
? 1U
: 0U;
}
}

View File

@@ -1,8 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public struct BlockSummary
{
public nuint nbSequences;
public nuint blockSize;
public nuint litSize;
}

View File

@@ -1,20 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/**
* COVER_best_t is used for two purposes:
* 1. Synchronizing threads.
* 2. Saving the best parameters and dictionary.
*
* All of the methods except COVER_best_init() are thread safe if zstd is
* compiled with multithreaded support.
*/
public unsafe struct COVER_best_s
{
public void* mutex;
public void* cond;
public nuint liveJobs;
public void* dict;
public nuint dictSize;
public ZDICT_cover_params_t parameters;
public nuint compressedSize;
}

View File

@@ -1,19 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/*-*************************************
* Context
***************************************/
public unsafe struct COVER_ctx_t
{
public byte* samples;
public nuint* offsets;
public nuint* samplesSizes;
public nuint nbSamples;
public nuint nbTrainSamples;
public nuint nbTestSamples;
public uint* suffix;
public nuint suffixSize;
public uint* freqs;
public uint* dmerAt;
public uint d;
}

View File

@@ -1,11 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/**
* Struct used for the dictionary selection function.
*/
public unsafe struct COVER_dictSelection
{
public byte* dictContent;
public nuint dictSize;
public nuint totalCompressedSize;
}

View File

@@ -1,10 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/**
*Number of epochs and size of each epoch.
*/
public struct COVER_epoch_info_t
{
public uint num;
public uint size;
}

View File

@@ -1,7 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public struct COVER_map_pair_t_s
{
public uint key;
public uint value;
}

View File

@@ -1,9 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public unsafe struct COVER_map_s
{
public COVER_map_pair_t_s* data;
public uint sizeLog;
public uint size;
public uint sizeMask;
}

View File

@@ -1,11 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/**
* A segment is a range in the source as well as the score of the segment.
*/
public struct COVER_segment_t
{
public uint begin;
public uint end;
public uint score;
}

View File

@@ -1,12 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/**
* Parameters for COVER_tryParameters().
*/
public unsafe struct COVER_tryParameters_data_s
{
public COVER_ctx_t* ctx;
public COVER_best_s* best;
public nuint dictBufferCapacity;
public ZDICT_cover_params_t parameters;
}

View File

@@ -1,849 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
private static readonly ZSTD_compressionParameters[][] ZSTD_defaultCParameters =
new ZSTD_compressionParameters[4][]
{
new ZSTD_compressionParameters[23]
{
new ZSTD_compressionParameters(
windowLog: 19,
chainLog: 12,
hashLog: 13,
searchLog: 1,
minMatch: 6,
targetLength: 1,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 19,
chainLog: 13,
hashLog: 14,
searchLog: 1,
minMatch: 7,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 20,
chainLog: 15,
hashLog: 16,
searchLog: 1,
minMatch: 6,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 21,
chainLog: 16,
hashLog: 17,
searchLog: 1,
minMatch: 5,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 21,
chainLog: 18,
hashLog: 18,
searchLog: 1,
minMatch: 5,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 21,
chainLog: 18,
hashLog: 19,
searchLog: 3,
minMatch: 5,
targetLength: 2,
strategy: ZSTD_strategy.ZSTD_greedy
),
new ZSTD_compressionParameters(
windowLog: 21,
chainLog: 18,
hashLog: 19,
searchLog: 3,
minMatch: 5,
targetLength: 4,
strategy: ZSTD_strategy.ZSTD_lazy
),
new ZSTD_compressionParameters(
windowLog: 21,
chainLog: 19,
hashLog: 20,
searchLog: 4,
minMatch: 5,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy
),
new ZSTD_compressionParameters(
windowLog: 21,
chainLog: 19,
hashLog: 20,
searchLog: 4,
minMatch: 5,
targetLength: 16,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 20,
hashLog: 21,
searchLog: 4,
minMatch: 5,
targetLength: 16,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 21,
hashLog: 22,
searchLog: 5,
minMatch: 5,
targetLength: 16,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 21,
hashLog: 22,
searchLog: 6,
minMatch: 5,
targetLength: 16,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 22,
hashLog: 23,
searchLog: 6,
minMatch: 5,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 22,
hashLog: 22,
searchLog: 4,
minMatch: 5,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 22,
hashLog: 23,
searchLog: 5,
minMatch: 5,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 23,
hashLog: 23,
searchLog: 6,
minMatch: 5,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 22,
chainLog: 22,
hashLog: 22,
searchLog: 5,
minMatch: 5,
targetLength: 48,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 23,
chainLog: 23,
hashLog: 22,
searchLog: 5,
minMatch: 4,
targetLength: 64,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 23,
chainLog: 23,
hashLog: 22,
searchLog: 6,
minMatch: 3,
targetLength: 64,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 23,
chainLog: 24,
hashLog: 22,
searchLog: 7,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 25,
chainLog: 25,
hashLog: 23,
searchLog: 7,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 26,
chainLog: 26,
hashLog: 24,
searchLog: 7,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 27,
chainLog: 27,
hashLog: 25,
searchLog: 9,
minMatch: 3,
targetLength: 999,
strategy: ZSTD_strategy.ZSTD_btultra2
),
},
new ZSTD_compressionParameters[23]
{
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 12,
hashLog: 13,
searchLog: 1,
minMatch: 5,
targetLength: 1,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 13,
hashLog: 14,
searchLog: 1,
minMatch: 6,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 14,
hashLog: 14,
searchLog: 1,
minMatch: 5,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 16,
hashLog: 16,
searchLog: 1,
minMatch: 4,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 16,
hashLog: 17,
searchLog: 3,
minMatch: 5,
targetLength: 2,
strategy: ZSTD_strategy.ZSTD_greedy
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 17,
hashLog: 18,
searchLog: 5,
minMatch: 5,
targetLength: 2,
strategy: ZSTD_strategy.ZSTD_greedy
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 3,
minMatch: 5,
targetLength: 4,
strategy: ZSTD_strategy.ZSTD_lazy
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 4,
minMatch: 4,
targetLength: 4,
strategy: ZSTD_strategy.ZSTD_lazy
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 4,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 5,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 6,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 5,
minMatch: 4,
targetLength: 12,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 7,
minMatch: 4,
targetLength: 12,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 4,
minMatch: 4,
targetLength: 16,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 4,
minMatch: 3,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 18,
hashLog: 19,
searchLog: 6,
minMatch: 3,
targetLength: 128,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 6,
minMatch: 3,
targetLength: 128,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 8,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 6,
minMatch: 3,
targetLength: 128,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 8,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 10,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 12,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 18,
chainLog: 19,
hashLog: 19,
searchLog: 13,
minMatch: 3,
targetLength: 999,
strategy: ZSTD_strategy.ZSTD_btultra2
),
},
new ZSTD_compressionParameters[23]
{
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 12,
hashLog: 12,
searchLog: 1,
minMatch: 5,
targetLength: 1,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 12,
hashLog: 13,
searchLog: 1,
minMatch: 6,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 13,
hashLog: 15,
searchLog: 1,
minMatch: 5,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 15,
hashLog: 16,
searchLog: 2,
minMatch: 5,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 17,
hashLog: 17,
searchLog: 2,
minMatch: 4,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 16,
hashLog: 17,
searchLog: 3,
minMatch: 4,
targetLength: 2,
strategy: ZSTD_strategy.ZSTD_greedy
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 16,
hashLog: 17,
searchLog: 3,
minMatch: 4,
targetLength: 4,
strategy: ZSTD_strategy.ZSTD_lazy
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 16,
hashLog: 17,
searchLog: 3,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 16,
hashLog: 17,
searchLog: 4,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 16,
hashLog: 17,
searchLog: 5,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 16,
hashLog: 17,
searchLog: 6,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 17,
hashLog: 17,
searchLog: 5,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 7,
minMatch: 4,
targetLength: 12,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 3,
minMatch: 4,
targetLength: 12,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 4,
minMatch: 3,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 6,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 6,
minMatch: 3,
targetLength: 128,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 8,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 10,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 5,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 7,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 9,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 17,
chainLog: 18,
hashLog: 17,
searchLog: 11,
minMatch: 3,
targetLength: 999,
strategy: ZSTD_strategy.ZSTD_btultra2
),
},
new ZSTD_compressionParameters[23]
{
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 12,
hashLog: 13,
searchLog: 1,
minMatch: 5,
targetLength: 1,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 15,
searchLog: 1,
minMatch: 5,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 15,
searchLog: 1,
minMatch: 4,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_fast
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 15,
searchLog: 2,
minMatch: 4,
targetLength: 0,
strategy: ZSTD_strategy.ZSTD_dfast
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 14,
searchLog: 4,
minMatch: 4,
targetLength: 2,
strategy: ZSTD_strategy.ZSTD_greedy
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 14,
searchLog: 3,
minMatch: 4,
targetLength: 4,
strategy: ZSTD_strategy.ZSTD_lazy
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 14,
searchLog: 4,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 14,
searchLog: 6,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 14,
hashLog: 14,
searchLog: 8,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_lazy2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 14,
searchLog: 5,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 14,
searchLog: 9,
minMatch: 4,
targetLength: 8,
strategy: ZSTD_strategy.ZSTD_btlazy2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 14,
searchLog: 3,
minMatch: 4,
targetLength: 12,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 14,
searchLog: 4,
minMatch: 3,
targetLength: 24,
strategy: ZSTD_strategy.ZSTD_btopt
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 14,
searchLog: 5,
minMatch: 3,
targetLength: 32,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 6,
minMatch: 3,
targetLength: 64,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 7,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 5,
minMatch: 3,
targetLength: 48,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 6,
minMatch: 3,
targetLength: 128,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 7,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 8,
minMatch: 3,
targetLength: 256,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 8,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 9,
minMatch: 3,
targetLength: 512,
strategy: ZSTD_strategy.ZSTD_btultra2
),
new ZSTD_compressionParameters(
windowLog: 14,
chainLog: 15,
hashLog: 15,
searchLog: 10,
minMatch: 3,
targetLength: 999,
strategy: ZSTD_strategy.ZSTD_btultra2
),
},
};
}

View File

@@ -1,61 +0,0 @@
using System.Runtime.CompilerServices;
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
/* @return 1 if @u is a 2^n value, 0 otherwise
* useful to check a value is valid for alignment restrictions */
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static int ZSTD_isPower2(nuint u)
{
return (u & u - 1) == 0 ? 1 : 0;
}
/**
* Helper function to perform a wrapped pointer difference without triggering
* UBSAN.
*
* @returns lhs - rhs with wrapping
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nint ZSTD_wrappedPtrDiff(byte* lhs, byte* rhs)
{
return (nint)(lhs - rhs);
}
/**
* Helper function to perform a wrapped pointer add without triggering UBSAN.
*
* @return ptr + add with wrapping
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static byte* ZSTD_wrappedPtrAdd(byte* ptr, nint add)
{
return ptr + add;
}
/**
* Helper function to perform a wrapped pointer subtraction without triggering
* UBSAN.
*
* @return ptr - sub with wrapping
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static byte* ZSTD_wrappedPtrSub(byte* ptr, nint sub)
{
return ptr - sub;
}
/**
* Helper function to add to a pointer that works around C's undefined behavior
* of adding 0 to NULL.
*
* @returns `ptr + add` except it defines `NULL + 0 == NULL`.
*/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static byte* ZSTD_maybeNullPtrAdd(byte* ptr, nint add)
{
return add > 0 ? ptr + add : ptr;
}
}

View File

@@ -1,444 +0,0 @@
using static SharpCompress.Compressors.ZStandard.UnsafeHelper;
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
private static int g_displayLevel = 0;
/**
* Returns the sum of the sample sizes.
*/
private static nuint COVER_sum(nuint* samplesSizes, uint nbSamples)
{
nuint sum = 0;
uint i;
for (i = 0; i < nbSamples; ++i)
{
sum += samplesSizes[i];
}
return sum;
}
/**
* Warns the user when their corpus is too small.
*/
private static void COVER_warnOnSmallCorpus(nuint maxDictSize, nuint nbDmers, int displayLevel)
{
double ratio = nbDmers / (double)maxDictSize;
if (ratio >= 10)
{
return;
}
}
/**
* Computes the number of epochs and the size of each epoch.
* We will make sure that each epoch gets at least 10 * k bytes.
*
* The COVER algorithms divide the data up into epochs of equal size and
* select one segment from each epoch.
*
* @param maxDictSize The maximum allowed dictionary size.
* @param nbDmers The number of dmers we are training on.
* @param k The parameter k (segment size).
* @param passes The target number of passes over the dmer corpus.
* More passes means a better dictionary.
*/
private static COVER_epoch_info_t COVER_computeEpochs(
uint maxDictSize,
uint nbDmers,
uint k,
uint passes
)
{
uint minEpochSize = k * 10;
COVER_epoch_info_t epochs;
epochs.num = 1 > maxDictSize / k / passes ? 1 : maxDictSize / k / passes;
epochs.size = nbDmers / epochs.num;
if (epochs.size >= minEpochSize)
{
assert(epochs.size * epochs.num <= nbDmers);
return epochs;
}
epochs.size = minEpochSize < nbDmers ? minEpochSize : nbDmers;
epochs.num = nbDmers / epochs.size;
assert(epochs.size * epochs.num <= nbDmers);
return epochs;
}
/**
* Checks total compressed size of a dictionary
*/
private static nuint COVER_checkTotalCompressedSize(
ZDICT_cover_params_t parameters,
nuint* samplesSizes,
byte* samples,
nuint* offsets,
nuint nbTrainSamples,
nuint nbSamples,
byte* dict,
nuint dictBufferCapacity
)
{
nuint totalCompressedSize = unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_GENERIC));
/* Pointers */
ZSTD_CCtx_s* cctx;
ZSTD_CDict_s* cdict;
void* dst;
/* Local variables */
nuint dstCapacity;
nuint i;
{
nuint maxSampleSize = 0;
i = parameters.splitPoint < 1 ? nbTrainSamples : 0;
for (; i < nbSamples; ++i)
{
maxSampleSize = samplesSizes[i] > maxSampleSize ? samplesSizes[i] : maxSampleSize;
}
dstCapacity = ZSTD_compressBound(maxSampleSize);
dst = malloc(dstCapacity);
}
cctx = ZSTD_createCCtx();
cdict = ZSTD_createCDict(dict, dictBufferCapacity, parameters.zParams.compressionLevel);
if (dst == null || cctx == null || cdict == null)
{
goto _compressCleanup;
}
totalCompressedSize = dictBufferCapacity;
i = parameters.splitPoint < 1 ? nbTrainSamples : 0;
for (; i < nbSamples; ++i)
{
nuint size = ZSTD_compress_usingCDict(
cctx,
dst,
dstCapacity,
samples + offsets[i],
samplesSizes[i],
cdict
);
if (ERR_isError(size))
{
totalCompressedSize = size;
goto _compressCleanup;
}
totalCompressedSize += size;
}
_compressCleanup:
ZSTD_freeCCtx(cctx);
ZSTD_freeCDict(cdict);
if (dst != null)
{
free(dst);
}
return totalCompressedSize;
}
/**
* Initialize the `COVER_best_t`.
*/
private static void COVER_best_init(COVER_best_s* best)
{
if (best == null)
return;
SynchronizationWrapper.Init(&best->mutex);
best->liveJobs = 0;
best->dict = null;
best->dictSize = 0;
best->compressedSize = unchecked((nuint)(-1));
best->parameters = new ZDICT_cover_params_t();
}
/**
* Wait until liveJobs == 0.
*/
private static void COVER_best_wait(COVER_best_s* best)
{
if (best == null)
{
return;
}
SynchronizationWrapper.Enter(&best->mutex);
while (best->liveJobs != 0)
{
SynchronizationWrapper.Wait(&best->mutex);
}
SynchronizationWrapper.Exit(&best->mutex);
}
/**
* Call COVER_best_wait() and then destroy the COVER_best_t.
*/
private static void COVER_best_destroy(COVER_best_s* best)
{
if (best == null)
{
return;
}
COVER_best_wait(best);
if (best->dict != null)
{
free(best->dict);
}
SynchronizationWrapper.Free(&best->mutex);
}
/**
* Called when a thread is about to be launched.
* Increments liveJobs.
*/
private static void COVER_best_start(COVER_best_s* best)
{
if (best == null)
{
return;
}
SynchronizationWrapper.Enter(&best->mutex);
++best->liveJobs;
SynchronizationWrapper.Exit(&best->mutex);
}
/**
* Called when a thread finishes executing, both on error or success.
* Decrements liveJobs and signals any waiting threads if liveJobs == 0.
* If this dictionary is the best so far save it and its parameters.
*/
private static void COVER_best_finish(
COVER_best_s* best,
ZDICT_cover_params_t parameters,
COVER_dictSelection selection
)
{
void* dict = selection.dictContent;
nuint compressedSize = selection.totalCompressedSize;
nuint dictSize = selection.dictSize;
if (best == null)
{
return;
}
{
nuint liveJobs;
SynchronizationWrapper.Enter(&best->mutex);
--best->liveJobs;
liveJobs = best->liveJobs;
if (compressedSize < best->compressedSize)
{
if (best->dict == null || best->dictSize < dictSize)
{
if (best->dict != null)
{
free(best->dict);
}
best->dict = malloc(dictSize);
if (best->dict == null)
{
best->compressedSize = unchecked(
(nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_GENERIC)
);
best->dictSize = 0;
SynchronizationWrapper.Pulse(&best->mutex);
SynchronizationWrapper.Exit(&best->mutex);
return;
}
}
if (dict != null)
{
memcpy(best->dict, dict, (uint)dictSize);
best->dictSize = dictSize;
best->parameters = parameters;
best->compressedSize = compressedSize;
}
}
if (liveJobs == 0)
{
SynchronizationWrapper.PulseAll(&best->mutex);
}
SynchronizationWrapper.Exit(&best->mutex);
}
}
private static COVER_dictSelection setDictSelection(byte* buf, nuint s, nuint csz)
{
COVER_dictSelection ds;
ds.dictContent = buf;
ds.dictSize = s;
ds.totalCompressedSize = csz;
return ds;
}
/**
* Error function for COVER_selectDict function. Returns a struct where
* return.totalCompressedSize is a ZSTD error.
*/
private static COVER_dictSelection COVER_dictSelectionError(nuint error)
{
return setDictSelection(null, 0, error);
}
/**
* Error function for COVER_selectDict function. Checks if the return
* value is an error.
*/
private static uint COVER_dictSelectionIsError(COVER_dictSelection selection)
{
return ERR_isError(selection.totalCompressedSize) || selection.dictContent == null
? 1U
: 0U;
}
/**
* Always call after selectDict is called to free up used memory from
* newly created dictionary.
*/
private static void COVER_dictSelectionFree(COVER_dictSelection selection)
{
free(selection.dictContent);
}
/**
* Called to finalize the dictionary and select one based on whether or not
* the shrink-dict flag was enabled. If enabled the dictionary used is the
* smallest dictionary within a specified regression of the compressed size
* from the largest dictionary.
*/
private static COVER_dictSelection COVER_selectDict(
byte* customDictContent,
nuint dictBufferCapacity,
nuint dictContentSize,
byte* samplesBuffer,
nuint* samplesSizes,
uint nbFinalizeSamples,
nuint nbCheckSamples,
nuint nbSamples,
ZDICT_cover_params_t @params,
nuint* offsets,
nuint totalCompressedSize
)
{
nuint largestDict = 0;
nuint largestCompressed = 0;
byte* customDictContentEnd = customDictContent + dictContentSize;
byte* largestDictbuffer = (byte*)malloc(dictBufferCapacity);
byte* candidateDictBuffer = (byte*)malloc(dictBufferCapacity);
double regressionTolerance = (double)@params.shrinkDictMaxRegression / 100 + 1;
if (largestDictbuffer == null || candidateDictBuffer == null)
{
free(largestDictbuffer);
free(candidateDictBuffer);
return COVER_dictSelectionError(dictContentSize);
}
memcpy(largestDictbuffer, customDictContent, (uint)dictContentSize);
dictContentSize = ZDICT_finalizeDictionary(
largestDictbuffer,
dictBufferCapacity,
customDictContent,
dictContentSize,
samplesBuffer,
samplesSizes,
nbFinalizeSamples,
@params.zParams
);
if (ZDICT_isError(dictContentSize))
{
free(largestDictbuffer);
free(candidateDictBuffer);
return COVER_dictSelectionError(dictContentSize);
}
totalCompressedSize = COVER_checkTotalCompressedSize(
@params,
samplesSizes,
samplesBuffer,
offsets,
nbCheckSamples,
nbSamples,
largestDictbuffer,
dictContentSize
);
if (ERR_isError(totalCompressedSize))
{
free(largestDictbuffer);
free(candidateDictBuffer);
return COVER_dictSelectionError(totalCompressedSize);
}
if (@params.shrinkDict == 0)
{
free(candidateDictBuffer);
return setDictSelection(largestDictbuffer, dictContentSize, totalCompressedSize);
}
largestDict = dictContentSize;
largestCompressed = totalCompressedSize;
dictContentSize = 256;
while (dictContentSize < largestDict)
{
memcpy(candidateDictBuffer, largestDictbuffer, (uint)largestDict);
dictContentSize = ZDICT_finalizeDictionary(
candidateDictBuffer,
dictBufferCapacity,
customDictContentEnd - dictContentSize,
dictContentSize,
samplesBuffer,
samplesSizes,
nbFinalizeSamples,
@params.zParams
);
if (ZDICT_isError(dictContentSize))
{
free(largestDictbuffer);
free(candidateDictBuffer);
return COVER_dictSelectionError(dictContentSize);
}
totalCompressedSize = COVER_checkTotalCompressedSize(
@params,
samplesSizes,
samplesBuffer,
offsets,
nbCheckSamples,
nbSamples,
candidateDictBuffer,
dictContentSize
);
if (ERR_isError(totalCompressedSize))
{
free(largestDictbuffer);
free(candidateDictBuffer);
return COVER_dictSelectionError(totalCompressedSize);
}
if (totalCompressedSize <= largestCompressed * regressionTolerance)
{
free(largestDictbuffer);
return setDictSelection(candidateDictBuffer, dictContentSize, totalCompressedSize);
}
dictContentSize *= 2;
}
dictContentSize = largestDict;
totalCompressedSize = largestCompressed;
free(candidateDictBuffer);
return setDictSelection(largestDictbuffer, dictContentSize, totalCompressedSize);
}
}

View File

@@ -1,12 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
/*-***************************/
/* generic DTableDesc */
/*-***************************/
public struct DTableDesc
{
public byte maxTableLog;
public byte tableType;
public byte tableLog;
public byte reserved;
}

View File

@@ -1,13 +0,0 @@
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public unsafe struct EStats_ress_t
{
/* dictionary */
public ZSTD_CDict_s* dict;
/* working context */
public ZSTD_CCtx_s* zc;
/* must be ZSTD_BLOCKSIZE_MAX allocated */
public void* workPlace;
}

View File

@@ -1,447 +0,0 @@
using System.Runtime.CompilerServices;
using static SharpCompress.Compressors.ZStandard.UnsafeHelper;
namespace SharpCompress.Compressors.ZStandard.Unsafe;
public static unsafe partial class Methods
{
/*=== Version ===*/
private static uint FSE_versionNumber()
{
return 0 * 100 * 100 + 9 * 100 + 0;
}
/*=== Error Management ===*/
private static bool FSE_isError(nuint code)
{
return ERR_isError(code);
}
private static string FSE_getErrorName(nuint code)
{
return ERR_getErrorName(code);
}
/* Error Management */
private static bool HUF_isError(nuint code)
{
return ERR_isError(code);
}
private static string HUF_getErrorName(nuint code)
{
return ERR_getErrorName(code);
}
/*-**************************************************************
* FSE NCount encoding-decoding
****************************************************************/
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint FSE_readNCount_body(
short* normalizedCounter,
uint* maxSVPtr,
uint* tableLogPtr,
void* headerBuffer,
nuint hbSize
)
{
byte* istart = (byte*)headerBuffer;
byte* iend = istart + hbSize;
byte* ip = istart;
int nbBits;
int remaining;
int threshold;
uint bitStream;
int bitCount;
uint charnum = 0;
uint maxSV1 = *maxSVPtr + 1;
int previous0 = 0;
if (hbSize < 8)
{
sbyte* buffer = stackalloc sbyte[8];
/* This function only works when hbSize >= 8 */
memset(buffer, 0, sizeof(sbyte) * 8);
memcpy(buffer, headerBuffer, (uint)hbSize);
{
nuint countSize = FSE_readNCount(
normalizedCounter,
maxSVPtr,
tableLogPtr,
buffer,
sizeof(sbyte) * 8
);
if (FSE_isError(countSize))
return countSize;
if (countSize > hbSize)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
return countSize;
}
}
assert(hbSize >= 8);
memset(normalizedCounter, 0, (*maxSVPtr + 1) * sizeof(short));
bitStream = MEM_readLE32(ip);
nbBits = (int)((bitStream & 0xF) + 5);
if (nbBits > 15)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_tableLog_tooLarge));
bitStream >>= 4;
bitCount = 4;
*tableLogPtr = (uint)nbBits;
remaining = (1 << nbBits) + 1;
threshold = 1 << nbBits;
nbBits++;
for (; ; )
{
if (previous0 != 0)
{
/* Count the number of repeats. Each time the
* 2-bit repeat code is 0b11 there is another
* repeat.
* Avoid UB by setting the high bit to 1.
*/
int repeats = (int)(ZSTD_countTrailingZeros32(~bitStream | 0x80000000) >> 1);
while (repeats >= 12)
{
charnum += 3 * 12;
if (ip <= iend - 7)
{
ip += 3;
}
else
{
bitCount -= (int)(8 * (iend - 7 - ip));
bitCount &= 31;
ip = iend - 4;
}
bitStream = MEM_readLE32(ip) >> bitCount;
repeats = (int)(ZSTD_countTrailingZeros32(~bitStream | 0x80000000) >> 1);
}
charnum += (uint)(3 * repeats);
bitStream >>= 2 * repeats;
bitCount += 2 * repeats;
assert((bitStream & 3) < 3);
charnum += bitStream & 3;
bitCount += 2;
if (charnum >= maxSV1)
break;
if (ip <= iend - 7 || ip + (bitCount >> 3) <= iend - 4)
{
assert(bitCount >> 3 <= 3);
ip += bitCount >> 3;
bitCount &= 7;
}
else
{
bitCount -= (int)(8 * (iend - 4 - ip));
bitCount &= 31;
ip = iend - 4;
}
bitStream = MEM_readLE32(ip) >> bitCount;
}
{
int max = 2 * threshold - 1 - remaining;
int count;
if ((bitStream & (uint)(threshold - 1)) < (uint)max)
{
count = (int)(bitStream & (uint)(threshold - 1));
bitCount += nbBits - 1;
}
else
{
count = (int)(bitStream & (uint)(2 * threshold - 1));
if (count >= threshold)
count -= max;
bitCount += nbBits;
}
count--;
if (count >= 0)
{
remaining -= count;
}
else
{
assert(count == -1);
remaining += count;
}
normalizedCounter[charnum++] = (short)count;
previous0 = count == 0 ? 1 : 0;
assert(threshold > 1);
if (remaining < threshold)
{
if (remaining <= 1)
break;
nbBits = (int)(ZSTD_highbit32((uint)remaining) + 1);
threshold = 1 << nbBits - 1;
}
if (charnum >= maxSV1)
break;
if (ip <= iend - 7 || ip + (bitCount >> 3) <= iend - 4)
{
ip += bitCount >> 3;
bitCount &= 7;
}
else
{
bitCount -= (int)(8 * (iend - 4 - ip));
bitCount &= 31;
ip = iend - 4;
}
bitStream = MEM_readLE32(ip) >> bitCount;
}
}
if (remaining != 1)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
if (charnum > maxSV1)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_maxSymbolValue_tooSmall));
if (bitCount > 32)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
*maxSVPtr = charnum - 1;
ip += bitCount + 7 >> 3;
return (nuint)(ip - istart);
}
/* Avoids the FORCE_INLINE of the _body() function. */
private static nuint FSE_readNCount_body_default(
short* normalizedCounter,
uint* maxSVPtr,
uint* tableLogPtr,
void* headerBuffer,
nuint hbSize
)
{
return FSE_readNCount_body(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
}
/*! FSE_readNCount_bmi2():
* Same as FSE_readNCount() but pass bmi2=1 when your CPU supports BMI2 and 0 otherwise.
*/
private static nuint FSE_readNCount_bmi2(
short* normalizedCounter,
uint* maxSVPtr,
uint* tableLogPtr,
void* headerBuffer,
nuint hbSize,
int bmi2
)
{
return FSE_readNCount_body_default(
normalizedCounter,
maxSVPtr,
tableLogPtr,
headerBuffer,
hbSize
);
}
/*! FSE_readNCount():
Read compactly saved 'normalizedCounter' from 'rBuffer'.
@return : size read from 'rBuffer',
or an errorCode, which can be tested using FSE_isError().
maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
private static nuint FSE_readNCount(
short* normalizedCounter,
uint* maxSVPtr,
uint* tableLogPtr,
void* headerBuffer,
nuint hbSize
)
{
return FSE_readNCount_bmi2(
normalizedCounter,
maxSVPtr,
tableLogPtr,
headerBuffer,
hbSize,
0
);
}
/*! HUF_readStats() :
Read compact Huffman tree, saved by HUF_writeCTable().
`huffWeight` is destination buffer.
`rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32.
@return : size read from `src` , or an error Code .
Note : Needed by HUF_readCTable() and HUF_readDTableX?() .
*/
private static nuint HUF_readStats(
byte* huffWeight,
nuint hwSize,
uint* rankStats,
uint* nbSymbolsPtr,
uint* tableLogPtr,
void* src,
nuint srcSize
)
{
uint* wksp = stackalloc uint[219];
return HUF_readStats_wksp(
huffWeight,
hwSize,
rankStats,
nbSymbolsPtr,
tableLogPtr,
src,
srcSize,
wksp,
sizeof(uint) * 219,
0
);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static nuint HUF_readStats_body(
byte* huffWeight,
nuint hwSize,
uint* rankStats,
uint* nbSymbolsPtr,
uint* tableLogPtr,
void* src,
nuint srcSize,
void* workSpace,
nuint wkspSize,
int bmi2
)
{
uint weightTotal;
byte* ip = (byte*)src;
nuint iSize;
nuint oSize;
if (srcSize == 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_srcSize_wrong));
iSize = ip[0];
if (iSize >= 128)
{
oSize = iSize - 127;
iSize = (oSize + 1) / 2;
if (iSize + 1 > srcSize)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_srcSize_wrong));
if (oSize >= hwSize)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
ip += 1;
{
uint n;
for (n = 0; n < oSize; n += 2)
{
huffWeight[n] = (byte)(ip[n / 2] >> 4);
huffWeight[n + 1] = (byte)(ip[n / 2] & 15);
}
}
}
else
{
if (iSize + 1 > srcSize)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_srcSize_wrong));
oSize = FSE_decompress_wksp_bmi2(
huffWeight,
hwSize - 1,
ip + 1,
iSize,
6,
workSpace,
wkspSize,
bmi2
);
if (FSE_isError(oSize))
return oSize;
}
memset(rankStats, 0, (12 + 1) * sizeof(uint));
weightTotal = 0;
{
uint n;
for (n = 0; n < oSize; n++)
{
if (huffWeight[n] > 12)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
rankStats[huffWeight[n]]++;
weightTotal += (uint)(1 << huffWeight[n] >> 1);
}
}
if (weightTotal == 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
{
uint tableLog = ZSTD_highbit32(weightTotal) + 1;
if (tableLog > 12)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
*tableLogPtr = tableLog;
{
uint total = (uint)(1 << (int)tableLog);
uint rest = total - weightTotal;
uint verif = (uint)(1 << (int)ZSTD_highbit32(rest));
uint lastWeight = ZSTD_highbit32(rest) + 1;
if (verif != rest)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
huffWeight[oSize] = (byte)lastWeight;
rankStats[lastWeight]++;
}
}
if (rankStats[1] < 2 || (rankStats[1] & 1) != 0)
return unchecked((nuint)(-(int)ZSTD_ErrorCode.ZSTD_error_corruption_detected));
*nbSymbolsPtr = (uint)(oSize + 1);
return iSize + 1;
}
/* Avoids the FORCE_INLINE of the _body() function. */
private static nuint HUF_readStats_body_default(
byte* huffWeight,
nuint hwSize,
uint* rankStats,
uint* nbSymbolsPtr,
uint* tableLogPtr,
void* src,
nuint srcSize,
void* workSpace,
nuint wkspSize
)
{
return HUF_readStats_body(
huffWeight,
hwSize,
rankStats,
nbSymbolsPtr,
tableLogPtr,
src,
srcSize,
workSpace,
wkspSize,
0
);
}
private static nuint HUF_readStats_wksp(
byte* huffWeight,
nuint hwSize,
uint* rankStats,
uint* nbSymbolsPtr,
uint* tableLogPtr,
void* src,
nuint srcSize,
void* workSpace,
nuint wkspSize,
int flags
)
{
return HUF_readStats_body_default(
huffWeight,
hwSize,
rankStats,
nbSymbolsPtr,
tableLogPtr,
src,
srcSize,
workSpace,
wkspSize
);
}
}

Some files were not shown because too many files have changed in this diff Show More