dataprof 0.3.0__tar.gz

dataprof-0.3.0/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,101 @@
+name: Bug Report
+description: Report a bug or issue with DataProfiler
+title: "[Bug]: "
+labels: ["bug"]
+assignees: []
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to report a bug! Please fill out the information below to help us understand and fix the issue.
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Bug Description
+      description: A clear and concise description of what the bug is.
+      placeholder: Describe what happened and what you expected to happen...
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to Reproduce
+      description: Steps to reproduce the behavior
+      placeholder: |
+        1. Run command '...'
+        2. With file '...'
+        3. See error
+      value: |
+        1.
+        2.
+        3.
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: What you expected to happen
+      placeholder: Describe the expected behavior...
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual Behavior
+      description: What actually happened (include error messages if any)
+      placeholder: Describe what actually happened...
+    validations:
+      required: true
+
+  - type: textarea
+    id: sample-data
+    attributes:
+      label: Sample Data
+      description: If applicable, provide a small sample of the data that causes the issue (anonymized if needed)
+      placeholder: |
+        CSV/JSON sample or file structure that reproduces the issue
+      render: text
+
+  - type: dropdown
+    id: os
+    attributes:
+      label: Operating System
+      description: What operating system are you using?
+      options:
+        - Windows
+        - macOS
+        - Linux (Ubuntu)
+        - Linux (Other)
+        - Other
+    validations:
+      required: true
+
+  - type: input
+    id: rust-version
+    attributes:
+      label: Rust Version
+      description: Output of `rustc --version`
+      placeholder: rustc 1.70.0 (90c541806 2023-05-31)
+    validations:
+      required: true
+
+  - type: input
+    id: dataprof-version
+    attributes:
+      label: DataProfiler Version
+      description: Version or commit hash of DataProfiler you're using
+      placeholder: v0.1.0 or commit hash
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Add any other context about the problem here, including file sizes, data types, etc.
+      placeholder: Any additional information that might be helpful...

dataprof-0.3.0/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,8 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Questions & Support
+    url: https://github.com/AndreaBozzo/dataprof/discussions
+    about: Ask questions and discuss DataProfiler usage
+  - name: Security Issues
+    url: https://github.com/AndreaBozzo/dataprof/security/advisories/new
+    about: Report security vulnerabilities privately

dataprof-0.3.0/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,91 @@
+name: Feature Request
+description: Suggest a new feature or enhancement for DataProfiler
+title: "[Feature]: "
+labels: ["enhancement"]
+assignees: []
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for suggesting a new feature! Please provide as much detail as possible.
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem Description
+      description: Is your feature request related to a problem? Please describe.
+      placeholder: I'm frustrated when... / It would be helpful if...
+    validations:
+      required: true
+
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: Describe the solution you'd like to see
+      placeholder: I would like to see... / The feature should...
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternative Solutions
+      description: Describe any alternative solutions or features you've considered
+      placeholder: Alternative approaches could be...
+
+  - type: dropdown
+    id: category
+    attributes:
+      label: Feature Category
+      description: What category does this feature belong to?
+      options:
+        - Data Analysis (new statistics, metrics)
+        - Quality Detection (new issue types)
+        - File Format Support (new formats)
+        - Output/Reporting (new export formats)
+        - Performance Optimization
+        - CLI Interface (new commands, options)
+        - Library API (new functions)
+        - Other
+    validations:
+      required: true
+
+  - type: dropdown
+    id: priority
+    attributes:
+      label: Priority
+      description: How important is this feature to you?
+      options:
+        - Low - Nice to have
+        - Medium - Would be helpful
+        - High - Important for my use case
+        - Critical - Blocking my workflow
+    validations:
+      required: true
+
+  - type: textarea
+    id: use-case
+    attributes:
+      label: Use Case
+      description: Describe your specific use case for this feature
+      placeholder: I work with... and need to... because...
+    validations:
+      required: true
+
+  - type: textarea
+    id: example
+    attributes:
+      label: Example
+      description: If applicable, provide an example of how the feature would work
+      placeholder: |
+        Command: dataprof --new-feature data.csv
+        Output: ...
+      render: shell
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Add any other context, screenshots, or examples about the feature request
+      placeholder: Any additional information...

dataprof-0.3.0/.github/dependabot.yml

@@ -0,0 +1,22 @@
+version: 2
+updates:
+  # Cargo dependencies
+  - package-ecosystem: "cargo"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+      time: "06:00"
+    open-pull-requests-limit: 5
+    reviewers:
+      - "AndreaBozzo"
+    commit-message:
+      prefix: "deps"
+      include: "scope"
+
+  # GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+    open-pull-requests-limit: 3

dataprof-0.3.0/.github/pull_request_template.md

@@ -0,0 +1,68 @@
+# Pull Request
+
+## Summary
+
+Brief description of the changes in this PR.
+
+## Type of Change
+
+- [ ] Bug fix (non-breaking change that fixes an issue)
+- [ ] New feature (non-breaking change that adds functionality)
+- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
+- [ ] Documentation update
+- [ ] Performance improvement
+- [ ] Code refactoring (no functional changes)
+
+## Changes Made
+
+- List key changes here
+- Use bullet points for clarity
+- Include any new dependencies added
+
+## Testing
+
+- [ ] I have tested the changes locally
+- [ ] I have added tests for new functionality
+- [ ] All existing tests pass
+- [ ] I have tested with sample data files
+
+### Test Commands Run
+
+```bash
+# List the commands you used to test
+cargo test
+cargo build --release
+# Any specific test scenarios
+```
+
+## Documentation
+
+- [ ] I have updated the README if needed
+- [ ] I have updated inline documentation/comments
+- [ ] I have updated CONTRIBUTING.md if needed
+
+## Performance Impact
+
+- [ ] No performance impact
+- [ ] Performance improved
+- [ ] Performance may be affected (explain below)
+
+If performance is affected, explain:
+
+## Breaking Changes
+
+If this is a breaking change, describe what breaks and migration path:
+
+## Additional Notes
+
+Any additional information, screenshots, or context for reviewers:
+
+---
+
+## Checklist
+
+- [ ] My code follows the project's style guidelines
+- [ ] I have performed a self-review of my code
+- [ ] My changes generate no new warnings
+- [ ] I have made corresponding changes to the documentation
+- [ ] Any dependent changes have been merged and published

dataprof-0.3.0/.github/workflows/ci.yml

@@ -0,0 +1,55 @@
+name: CI
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  test:
+    name: Test
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v5
+
+    - name: Install Rust
+      uses: dtolnay/rust-toolchain@stable
+
+    - name: Cache dependencies
+      uses: actions/cache@v4
+      with:
+        path: |
+          ~/.cargo/registry
+          ~/.cargo/git
+          target
+        key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
+
+    - name: Run tests
+      run: cargo test --verbose
+
+    - name: Check formatting
+      run: cargo fmt --all -- --check
+
+    - name: Run clippy
+      run: cargo clippy --all-targets --all-features -- -D warnings
+
+  build:
+    name: Build
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+
+    steps:
+    - uses: actions/checkout@v5
+
+    - name: Install Rust
+      uses: dtolnay/rust-toolchain@stable
+
+    - name: Build
+      run: cargo build --release --verbose

dataprof-0.3.0/.github/workflows/python.yml

@@ -0,0 +1,133 @@
+name: Python Bindings
+
+on:
+  push:
+    branches: [ master ]
+    tags: [ 'v*' ]
+  pull_request:
+    branches: [ master ]
+
+permissions:
+  contents: read
+
+jobs:
+  linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [x86_64, aarch64, armv7, s390x, ppc64le]
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Build wheels
+      uses: PyO3/maturin-action@v1
+      with:
+        target: ${{ matrix.target }}
+        args: --release --out dist --find-interpreter --features python
+        sccache: 'true'
+        manylinux: auto
+    - name: Upload wheels
+      uses: actions/upload-artifact@v4
+      with:
+        name: wheels-linux-${{ matrix.target }}
+        path: dist
+
+  windows:
+    runs-on: windows-latest
+    strategy:
+      matrix:
+        target: [x64, x86]
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+        architecture: ${{ matrix.target }}
+    - name: Build wheels
+      uses: PyO3/maturin-action@v1
+      with:
+        target: ${{ matrix.target }}
+        args: --release --out dist --find-interpreter --features python
+        sccache: 'true'
+    - name: Upload wheels
+      uses: actions/upload-artifact@v4
+      with:
+        name: wheels-windows-${{ matrix.target }}
+        path: dist
+
+  macos:
+    runs-on: macos-latest
+    strategy:
+      matrix:
+        target: [x86_64, aarch64]
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Build wheels
+      uses: PyO3/maturin-action@v1
+      with:
+        target: ${{ matrix.target }}
+        args: --release --out dist --find-interpreter --features python
+        sccache: 'true'
+    - name: Upload wheels
+      uses: actions/upload-artifact@v4
+      with:
+        name: wheels-macos-${{ matrix.target }}
+        path: dist
+
+  sdist:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - 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
+
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/')
+    needs: [linux, windows, macos, sdist]
+    permissions:
+      id-token: write  # For trusted publishing
+    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:
+        packages-dir: dist/
+
+  test:
+    runs-on: ubuntu-latest
+    needs: [linux]
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - uses: actions/download-artifact@v4
+      with:
+        name: wheels-linux-x86_64
+        path: dist
+    - name: Install wheel
+      run: |
+        pip install --find-links dist dataprof
+        pip install pytest
+    - name: Test Python bindings
+      run: |
+        python python/tests/test_bindings.py

dataprof-0.3.0/.gitignore

@@ -0,0 +1,29 @@
+# Build artifacts
+/target
+**/*.rs.bk
+
+# IDE files
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# Test files
+test.csv
+*.tmp
+test_*.rs
+*.pdb
+*.exe
+*.dll
+example_usage/
+
+# Logs
+*.log
+
+# Claude files
+CLAUDE.md
+.claude/

dataprof-0.3.0/.markdownlint.yaml

@@ -0,0 +1,34 @@
+# Markdownlint configuration for DataProfiler v0.3.0
+
+# Extend default configuration
+extends: default
+
+# Rule customizations
+rules:
+  # Allow HTML in markdown (for badges, enhanced formatting)
+  MD033: false
+
+  # Allow long lines (for URLs, code examples)
+  MD013:
+    line_length: 200
+
+  # Allow multiple consecutive blank lines
+  MD012: false
+
+  # Allow multiple headings with same content
+  MD024: false
+
+  # Allow trailing punctuation in headers
+  MD026: false
+
+  # Allow bare URLs
+  MD034: false
+
+  # Allow emphasis as heading (for bold descriptions)
+  MD036: false
+
+  # Allow missing language on fenced code blocks
+  MD040: false
+
+  # Allow multiple top-level headings
+  MD025: false

dataprof-0.3.0/.pre-commit-config.yaml

@@ -0,0 +1,50 @@
+repos:
+  # Rust formatting and linting
+  - repo: local
+    hooks:
+      - id: cargo-fmt
+        name: cargo fmt
+        entry: cargo fmt --all --
+        language: system
+        types: [rust]
+        pass_filenames: false
+
+      - id: cargo-clippy
+        name: cargo clippy
+        entry: cargo clippy --all-targets --all-features -- -D warnings
+        language: system
+        types: [rust]
+        pass_filenames: false
+
+      - id: cargo-test
+        name: cargo test
+        entry: cargo test --lib
+        language: system
+        types: [rust]
+        pass_filenames: false
+
+  # General file formatting
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-toml
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-case-conflict
+      - id: mixed-line-ending
+
+  # Markdown formatting (disabled for now due to complex legacy docs)
+  # - repo: https://github.com/igorshubovych/markdownlint-cli
+  #   rev: v0.37.0
+  #   hooks:
+  #     - id: markdownlint
+  #       args: ['--fix']
+  #       files: '\.md$'
+
+# Configuration
+default_language_version:
+  python: python3
+fail_fast: false