ccdown 0.6.1__tar.gz

ccdown-0.6.1/.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,38 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. iOS]
+ - Browser [e.g. chrome, safari]
+ - Version [e.g. 22]
+
+**Smartphone (please complete the following information):**
+ - Device: [e.g. iPhone6]
+ - OS: [e.g. iOS8.1]
+ - Browser [e.g. stock browser, safari]
+ - Version [e.g. 22]
+
+**Additional context**
+Add any other context about the problem here.

ccdown-0.6.1/.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

ccdown-0.6.1/.github/pull_request_template.md

@@ -0,0 +1,11 @@
+## Description
+
+<!-- A summary of what this pull request achieves and a rough list of changes. Please also refence any related issue here -->
+
+## Breaking Changes
+
+<!-- Optional, if there are any breaking changes document them, including how to migrate older code. -->
+
+## Notes & open questions
+
+<!-- Any notes, remarks or open questions you have to make about the PR. -->

ccdown-0.6.1/.github/workflows/python.yml

@@ -0,0 +1,92 @@
+name: Python
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [x86_64]
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          args: --release --out dist --find-interpreter
+          manylinux: auto
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-linux-${{ matrix.target }}
+          path: dist
+
+  macos:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - runner: macos-latest
+            target: x86_64
+          - runner: macos-latest
+            target: aarch64
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-macos-${{ matrix.platform.target }}
+          path: dist
+
+  sdist:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v5
+      - name: Build sdist
+        uses: PyO3/maturin-action@v1
+        with:
+          command: sdist
+          args: --out dist
+      - name: Upload sdist
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-sdist
+          path: dist
+
+  publish:
+    name: Publish to PyPI
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    needs: [linux, macos, sdist]
+    environment: prod
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          pattern: wheels-*
+          merge-multiple: true
+          path: dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true

ccdown-0.6.1/.github/workflows/release-plz.yml

@@ -0,0 +1,24 @@
+name: Release Plz
+
+permissions:
+  pull-requests: write
+  contents: write
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  release-plz:
+    runs-on: ubuntu-latest
+    environment: prod
+    steps:
+      - uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: MarcoIeni/release-plz-action@v0.5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}

ccdown-0.6.1/.github/workflows/release.yml

@@ -0,0 +1,58 @@
+name: Release
+
+permissions:
+  contents: write
+
+on:
+  push:
+    tags:
+      - v[0-9]+.*
+
+jobs:
+  create-release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v5
+      - uses: taiki-e/create-gh-release-action@v1
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+  upload-assets:
+    needs: create-release
+    strategy:
+      matrix:
+        include:
+          - target: aarch64-unknown-linux-gnu
+            os: ubuntu-latest
+          - target: x86_64-unknown-linux-gnu
+            os: ubuntu-latest
+          - target: x86_64-apple-darwin
+            os: macos-latest
+          - target: aarch64-apple-darwin
+            os: macos-latest
+          - target: x86_64-pc-windows-msvc
+            os: windows-latest
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v5
+      - uses: taiki-e/upload-rust-binary-action@v1
+        with:
+          bin: ccdown
+          target: ${{ matrix.target }}
+          archive: $bin-$tag-$target
+          tar: unix
+          zip: windows
+          include: LICENSE-APACHE,LICENSE-MIT,README.md
+          checksum: sha512
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+  publish-crate:
+    needs: create-release
+    runs-on: ubuntu-latest
+    environment: prod
+    steps:
+      - uses: actions/checkout@v5
+      - uses: dtolnay/rust-toolchain@stable
+      - run: cargo publish
+        env:
+          CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}

ccdown-0.6.1/.github/workflows/rust.yml

@@ -0,0 +1,25 @@
+name: Rust
+
+on:
+  push:
+    branches: [ "main", "dev" ]
+  pull_request:
+    branches: [ "main", "dev" ]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v5
+    - name: Build
+      run: cargo build --verbose
+    - name: Run tests
+      run: cargo test --verbose
+    - name: Run clippy
+      run: cargo clippy --verbose
+      

ccdown-0.6.1/.gitignore

@@ -0,0 +1,44 @@
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# Generated by Cargo
+# will have compiled files and executables
+debug/
+target/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
+Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb
+
+# Project specific files
+test-download

ccdown-0.6.1/CHANGELOG.md

@@ -0,0 +1,57 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.6.5](https://github.com/4thel00z/ccdown/compare/v0.6.4...v0.6.5) - 2026-04-01
+
+### Other
+
+- add Python bindings and --strict flag to README
+- Merge pull request #4 from 4thel00z/release-plz-2026-04-01T02-58-41Z
+- drop linux aarch64, keep macos aarch64
+
+## [0.6.4](https://github.com/4thel00z/ccdown/compare/v0.6.3...v0.6.4) - 2026-04-01
+
+### Fixed
+
+- add --find-interpreter for linux manylinux builds
+- replace macos-13 with macos-latest, fix QEMU setup for aarch64
+- add QEMU for aarch64 linux, drop --find-interpreter
+
+### Other
+
+- drop windows support
+- drop musllinux support
+- Merge pull request #2 from 4thel00z/release-plz-2026-04-01T02-45-16Z
+
+## [0.6.3](https://github.com/4thel00z/ccdown/compare/v0.6.2...v0.6.3) - 2026-04-01
+
+### Added
+
+- add unrecoverable error handling, Python bindings, lib refactor, and tests
+
+### Fixed
+
+- bump PyO3 to 0.28 for Python 3.14 support
+
+### Other
+
+- Merge pull request #1 from 4thel00z/release-plz-2026-04-01T01-35-18Z
+
+## [0.6.2](https://github.com/4thel00z/ccdown/compare/v0.6.1...v0.6.2) - 2026-04-01
+
+### Other
+
+- add logo, badges, modernize README layout
+- add changelog, bump actions/checkout to v5
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

ccdown-0.6.1/CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+pedro@commoncrawl.org.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

ccdown-0.6.1/CONTRIBUTING.md

@@ -0,0 +1,80 @@
+# How to contribute to ccdown?
+
+[![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg)](CODE_OF_CONDUCT.md)
+
+`ccdown` is an open source project, so all contributions and suggestions are welcome.
+
+You can contribute in many different ways: giving ideas, answering questions, reporting bugs, proposing enhancements,
+improving the documentation, fixing bugs,...
+
+Many thanks in advance to every contributor.
+
+In order to facilitate healthy, constructive behavior in an open and inclusive community, we all respect and abide by
+our [code of conduct](CODE_OF_CONDUCT.md).
+
+## How to work on an open Issue?
+
+You have the list of open Issues at: [https://github.com/4thel00z/ccdown/issues](https://github.com/4thel00z/ccdown/issues)
+
+Some of them may have the label `help wanted`: that means that any contributor is welcomed!
+
+If you would like to work on any of the open Issues:
+
+1. Make sure it is not already assigned to someone else. You have the assignee (if any) on the top of the right column of the Issue page.
+
+2. You can self-assign it by commenting on the Issue page with the keyword: `#self-assign`.
+
+3. Work on your self-assigned issue and eventually create a Pull Request.
+
+## How to create a Pull Request?
+
+1. Fork the [repository](https://github.com/4thel00z/ccdown) by clicking on the 'Fork' button on the repository's page. This creates a copy of the code under your GitHub user account.
+
+2. Clone your fork to your local disk, and add the base repository as a remote:
+
+    ```bash
+    git clone git@github.com:<your Github handle>/ccdown.git
+    cd datasets
+    git remote add upstream git@github.com:4thel00z/ccdown.git
+    ```
+
+3. Switch to the `dev` branch and then create a new branch to hold your development changes:
+
+    ```bash
+    git checkout dev
+    git checkout -b a-descriptive-name-for-my-changes
+    ```
+
+    **do not** work on the `main` or `dev` branches.
+
+4. Develop the features on your branch.
+
+5. Once you're happy with your contribution, add your changed files and make a commit to record your changes locally:
+
+    ```bash
+    git add -u
+    git commit
+    ```
+
+    It is a good idea to sync your copy of the code with the original
+    repository regularly. This way you can quickly account for changes:
+
+    ```bash
+    git fetch upstream
+    git rebase upstream/dev
+    ```
+
+6. Once you are satisfied, push the changes to your fork repo using:
+
+   ```bash
+   git push -u origin a-descriptive-name-for-my-changes
+   ```
+
+   Go the webpage of your fork on GitHub. Click on "Pull request" to send your to the project maintainers for review, and select the `dev` branch as the brach you'd like to merge your changes into.
+
+Thank you for your contribution!
+
+## Code of conduct
+
+This project adheres to the HuggingFace [code of conduct](CODE_OF_CONDUCT.md).
+By participating, you are expected to abide by this code.