infoextract-cidoc 0.1.0__tar.gz

infoextract_cidoc-0.1.0/.codecov.yml

@@ -0,0 +1,40 @@
+coverage:
+  status:
+    project:
+      default:
+        target: 70%
+        threshold: 2%
+    patch:
+      default:
+        target: 75%
+
+component_management:
+  default_rules:
+    statuses:
+      - type: project
+        target: 70%
+  individual_components:
+    - component_id: extraction
+      name: Extraction Pipeline
+      paths:
+        - src/infoextract_cidoc/extraction/**
+    - component_id: io
+      name: I/O Modules
+      paths:
+        - src/infoextract_cidoc/io/**
+    - component_id: models
+      name: CRM Models
+      paths:
+        - src/infoextract_cidoc/models/**
+    - component_id: validators
+      name: Validators
+      paths:
+        - src/infoextract_cidoc/validators/**
+    - component_id: visualization
+      name: Visualization
+      paths:
+        - src/infoextract_cidoc/visualization/**
+
+ignore:
+  - "src/infoextract_cidoc/codegen/**"
+  - "src/infoextract_cidoc/tests/**"

infoextract_cidoc-0.1.0/.coderabbit.yaml

@@ -0,0 +1,23 @@
+language: "en-US"
+early_access: false
+reviews:
+  profile: "chill"
+  request_changes_workflow: false
+  high_level_summary: true
+  poem: false
+  review_status: true
+  collapse_walkthrough: false
+  path_filters:
+    - "!src/infoextract_cidoc/models/generated/**"
+    - "!src/infoextract_cidoc/codegen/**"
+  path_instructions:
+    - path: "src/infoextract_cidoc/extraction/**"
+      instructions: |
+        Review for CIDOC CRM correctness. Ensure entity types and property codes
+        are valid CRM identifiers. Check that confidence scores are in [0.0, 1.0].
+    - path: "src/infoextract_cidoc/tests/**"
+      instructions: |
+        Verify test isolation and meaningful assertions. Check that LLM tests
+        are marked with @pytest.mark.llm.
+chat:
+  auto_reply: true

infoextract_cidoc-0.1.0/.cursor/rules/astral-uv.mdc

@@ -0,0 +1,65 @@
+---
+description: Ensure Cursor uses Astral UV Python tooling and Astral Ruff for all Python development tasks
+globs:
+alwaysApply: true
+---
+
+# Astral UV and Ruff Python Tooling Rule
+
+## Python Package Management
+- **ALWAYS** use `uv` for all Python package management tasks
+- Use `uv add <package>` instead of `pip install`
+- Use `uv remove <package>` instead of `pip uninstall`
+- Use `uv sync` to install dependencies from `uv.lock`
+- Use `uv run <command>` to run Python scripts and tools
+- Use `uv add --dev <package>` for development dependencies
+
+## Code Formatting and Linting
+- **ALWAYS** use `ruff` for code formatting and linting
+- Use `uv run ruff format` to format Python code
+- Use `uv run ruff check` to check for linting issues
+- Use `uv run ruff check --fix` to automatically fix fixable issues
+- Configure ruff settings in `pyproject.toml` under `[tool.ruff]`
+
+## Development Workflow
+- When running tests, use `uv run pytest` or `uv run python -m pytest`
+- When running scripts, use `uv run python <script.py>`
+- When installing new dependencies, always update `pyproject.toml` and run `uv lock`
+- When creating virtual environments, use `uv venv` instead of `python -m venv`
+
+## Code Quality Standards
+- Ensure all Python code follows ruff's formatting standards
+- Fix all ruff warnings and errors before committing
+- Use ruff's import sorting and organization features
+- Maintain consistent code style across the project
+
+## Project Structure
+- Keep `pyproject.toml` as the single source of truth for dependencies
+- Use `uv.lock` for reproducible builds
+- Ensure all Python tools are run through `uv run` to maintain consistency
+
+## Examples
+```bash
+# Install a new package
+uv add requests
+
+# Install a development dependency
+uv add --dev pytest
+
+# Format code
+uv run ruff format
+
+# Check and fix linting issues
+uv run ruff check --fix
+
+# Run tests
+uv run pytest
+
+# Run a Python script
+uv run python src/collie/main.py
+```
+
+## Error Handling
+- If you encounter issues with `uv` or `ruff`, check the project's `pyproject.toml` configuration
+- Ensure the Python version specified in `pyproject.toml` is compatible
+- Use `uv --version` and `uv run ruff --version` to verify tool versions

infoextract_cidoc-0.1.0/.cursor/rules/docs-and-todo.mdc

@@ -0,0 +1,65 @@
+---
+description: Agent workflow rule for documentation-driven development
+globs:
+alwaysApply: true
+---
+
+## Agent Workflow Rule: Documentation-Driven Development
+
+The agent MUST follow this exact workflow for ALL tasks:
+
+### 1. Initial Documentation Review
+- **ALWAYS** read `docs/mission.md` first to understand the project's purpose and goals
+- **ALWAYS** read `docs/todo.md` to understand current tasks, priorities, and acceptance criteria
+- Review any other relevant documentation files in the `docs/` directory
+- Understand the current state of the project before proceeding
+
+### 2. Planning Phase
+- Create a detailed plan based on the task requirements and current documentation
+- Break down complex tasks into manageable steps
+- Identify dependencies and potential risks
+- Consider how the task aligns with the project mission
+
+### 3. Todo Evaluation and Update
+- **ALWAYS** evaluate if the planned task requires modification of `docs/todo.md`
+- If the task involves:
+  - Adding new features → Update todo.md with new tasks
+  - Completing existing tasks → Mark them as completed
+  - Changing priorities → Reorder tasks accordingly
+  - Discovering new requirements → Add them to the todo list
+- Update `docs/todo.md` BEFORE starting implementation
+
+### 4. Task Execution
+- Execute the planned tasks systematically
+- Follow the acceptance criteria defined in the documentation
+- Implement changes according to the project's standards and mission
+- Test functionality as appropriate
+
+### 5. Post-Task Evaluation
+- **ALWAYS** evaluate if the completed changes meet the acceptance criteria
+- Verify that the implementation aligns with the project mission
+- Check if any additional tasks were discovered during implementation
+
+### 6. Documentation Updates
+- **ALWAYS** update `docs/todo.md` to reflect:
+  - Completed tasks (mark as done)
+  - New tasks discovered during implementation
+  - Updated priorities or timelines
+  - Any blockers or issues encountered
+- Update other documentation files (`docs/mission.md`, etc.) if:
+  - The project scope or mission has evolved
+  - New features require documentation
+  - Architecture or approach changes need to be documented
+  - User-facing changes require updated instructions
+
+### 7. Final Verification
+- Ensure all documentation accurately reflects the current state of the code
+- Verify that the todo list is up-to-date and properly prioritized
+- Confirm that the mission statement still accurately describes the project
+
+### Key Principles:
+- **Documentation First**: Always start with reading existing docs
+- **Plan Before Acting**: Create a clear plan before implementation
+- **Continuous Documentation**: Keep docs updated throughout the process
+- **Acceptance Criteria Driven**: Always verify against defined criteria
+- **Mission Alignment**: Ensure all work aligns with project goals

infoextract_cidoc-0.1.0/.editorconfig

@@ -0,0 +1,21 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.py]
+indent_style = space
+indent_size = 4
+
+[*.{yml,yaml,json,toml}]
+indent_style = space
+indent_size = 2
+
+[*.md]
+trim_trailing_whitespace = false
+
+[Makefile]
+indent_style = tab

infoextract_cidoc-0.1.0/.github/CODEOWNERS

@@ -0,0 +1,11 @@
+# Default owner
+* @decisionnerd
+
+# Extraction pipeline
+src/infoextract_cidoc/extraction/ @decisionnerd
+
+# Models (auto-generated; review carefully)
+src/infoextract_cidoc/models/ @decisionnerd
+
+# CI/CD
+.github/ @decisionnerd

infoextract_cidoc-0.1.0/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,53 @@
+name: Bug Report
+description: Report a bug in infoextract-cidoc
+labels: ["bug"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for reporting a bug! Please fill out the information below.
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Bug Description
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to Reproduce
+      description: Steps to reproduce the behavior.
+      placeholder: |
+        1. Import `infoextract_cidoc`
+        2. Call `...`
+        3. See error
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: What you expected to happen.
+    validations:
+      required: true
+
+  - type: textarea
+    id: environment
+    attributes:
+      label: Environment
+      description: |
+        - Python version:
+        - infoextract-cidoc version:
+        - OS:
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Context
+      description: Any other context, stack traces, or screenshots.

infoextract_cidoc-0.1.0/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Documentation
+    url: https://decisionnerd.github.io/infoextract-cidoc/
+    about: Read the full documentation

infoextract_cidoc-0.1.0/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,35 @@
+name: Feature Request
+description: Suggest a new feature for infoextract-cidoc
+labels: ["enhancement"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for suggesting a feature!
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem Statement
+      description: What problem does this feature solve?
+    validations:
+      required: true
+
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: Describe the feature you'd like to see.
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives Considered
+      description: Any alternative approaches you've considered.
+
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Context

infoextract_cidoc-0.1.0/.github/ISSUE_TEMPLATE/question.yml

@@ -0,0 +1,17 @@
+name: Question
+description: Ask a question about infoextract-cidoc
+labels: ["question"]
+body:
+  - type: textarea
+    id: question
+    attributes:
+      label: Question
+      description: What would you like to know?
+    validations:
+      required: true
+
+  - type: textarea
+    id: context
+    attributes:
+      label: Context
+      description: Any relevant context or code snippets.

infoextract_cidoc-0.1.0/.github/SECURITY.md

@@ -0,0 +1,18 @@
+# Security Policy
+
+## Supported Versions
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 0.1.x   | :white_check_mark: |
+
+## Reporting a Vulnerability
+
+Please do **not** report security vulnerabilities via public GitHub issues.
+
+Instead, report them via GitHub's private vulnerability reporting:
+1. Go to the repository's **Security** tab
+2. Click **Report a vulnerability**
+3. Provide a clear description of the issue, steps to reproduce, and potential impact
+
+We will acknowledge your report within 48 hours and provide a resolution timeline.

infoextract_cidoc-0.1.0/.github/dependabot.yml

@@ -0,0 +1,20 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+    open-pull-requests-limit: 5
+    labels:
+      - "dependencies"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+    open-pull-requests-limit: 5
+    labels:
+      - "ci-cd"
+      - "dependencies"

infoextract_cidoc-0.1.0/.github/labeler.yml

@@ -0,0 +1,24 @@
+extraction:
+  - changed-files:
+    - any-glob-to-any-file: "src/infoextract_cidoc/extraction/**"
+
+io:
+  - changed-files:
+    - any-glob-to-any-file: "src/infoextract_cidoc/io/**"
+
+models:
+  - changed-files:
+    - any-glob-to-any-file: "src/infoextract_cidoc/models/**"
+
+tests:
+  - changed-files:
+    - any-glob-to-any-file: "src/infoextract_cidoc/tests/**"
+
+documentation:
+  - changed-files:
+    - any-glob-to-any-file: "docs/**"
+    - any-glob-to-any-file: "*.md"
+
+ci-cd:
+  - changed-files:
+    - any-glob-to-any-file: ".github/**"

infoextract_cidoc-0.1.0/.github/pull_request_template.md

@@ -0,0 +1,25 @@
+## Summary
+
+<!-- What does this PR do? 1-3 bullet points -->
+-
+
+## Type of Change
+
+- [ ] Bug fix
+- [ ] New feature
+- [ ] Refactoring
+- [ ] Documentation
+- [ ] CI/CD
+- [ ] Breaking change
+
+## Testing
+
+- [ ] Existing tests pass (`make test`)
+- [ ] New tests added for new functionality
+- [ ] `make pre-push` passes
+
+## Checklist
+
+- [ ] CHANGELOG.md updated under `[Unreleased]`
+- [ ] Documentation updated if needed
+- [ ] No new security vulnerabilities introduced

infoextract_cidoc-0.1.0/.github/workflows/changelog-check.yml

@@ -0,0 +1,23 @@
+name: Changelog Check
+
+on:
+  pull_request:
+    branches: ["main"]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check CHANGELOG updated
+        run: |
+          if git diff --name-only origin/main...HEAD | grep -q "CHANGELOG.md"; then
+            echo "CHANGELOG.md was updated."
+          else
+            echo "ERROR: CHANGELOG.md was not updated in this PR."
+            echo "Please add an entry under [Unreleased] in CHANGELOG.md."
+            exit 1
+          fi

infoextract_cidoc-0.1.0/.github/workflows/docs.yml

@@ -0,0 +1,48 @@
+name: Docs
+
+on:
+  push:
+    branches: ["main"]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "latest"
+
+      - name: Install dependencies
+        run: uv sync --group docs
+
+      - name: Build docs
+        run: uv run mkdocs build --strict
+
+      - name: Upload pages artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: site/
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

infoextract_cidoc-0.1.0/.github/workflows/pr-labeler.yml

@@ -0,0 +1,17 @@
+name: PR Labeler
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+
+permissions:
+  pull-requests: write
+
+jobs:
+  label:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/labeler@v5
+        with:
+          configuration-path: .github/labeler.yml
+          sync-labels: true

infoextract_cidoc-0.1.0/.github/workflows/publish.yaml

@@ -0,0 +1,29 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  id-token: write
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "latest"
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Build package
+        run: uv build
+
+      - name: Publish to PyPI
+        run: uv publish --trusted-publishing always

infoextract_cidoc-0.1.0/.github/workflows/release-tracking.yml

@@ -0,0 +1,24 @@
+name: Release Readiness
+
+on:
+  schedule:
+    - cron: "0 9 * * 1"  # Every Monday at 9am UTC
+  workflow_dispatch:
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "latest"
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Check release readiness
+        run: uv run python scripts/check_release_needed.py
+        continue-on-error: true

infoextract_cidoc-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,64 @@
+name: Test
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "latest"
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Cache uv dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/uv
+          key: ${{ runner.os }}-uv-${{ hashFiles('**/uv.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-uv-
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Format check
+        run: uv run ruff format --check src/
+
+      - name: Lint
+        run: uv run ruff check src/
+
+      - name: Type check
+        run: uv run mypy src/infoextract_cidoc/
+        continue-on-error: true
+
+      - name: Security check
+        run: uv run bandit -c pyproject.toml -r src/infoextract_cidoc/
+        continue-on-error: true
+
+      - name: Run tests with coverage
+        run: uv run pytest src/infoextract_cidoc/tests/ --cov=src/infoextract_cidoc --cov-report=xml -v
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          file: coverage.xml
+          fail_ci_if_error: false
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}