jostack-mdparse 0.1.0__tar.gz

jostack_mdparse-0.1.0/.editorconfig

@@ -0,0 +1,18 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+charset = utf-8
+
+[*.py]
+indent_style = space
+indent_size = 4
+
+[*.{yml,yaml,json,toml,md}]
+indent_style = space
+indent_size = 2
+
+[Makefile]
+indent_style = tab

jostack_mdparse-0.1.0/.gitattributes

@@ -0,0 +1,5 @@
+* text=auto eol=lf
+*.py text eol=lf
+*.md text eol=lf
+*.yml text eol=lf
+*.json text eol=lf

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

@@ -0,0 +1,39 @@
+name: Bug Report
+description: Report a bug in md-extract
+labels: [bug]
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear description of the bug.
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to Reproduce
+      description: Steps to reproduce the behavior.
+    validations:
+      required: true
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: What you expected to happen.
+    validations:
+      required: true
+  - type: input
+    id: version
+    attributes:
+      label: Version
+      description: md-extract version
+    validations:
+      required: true
+  - type: input
+    id: python
+    attributes:
+      label: Python Version
+      description: Python version (e.g. 3.12)
+    validations:
+      required: true

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

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Questions & Discussions
+    url: https://github.com/hyunhee-jo/md-extract/discussions
+    about: Ask questions and discuss ideas

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

@@ -0,0 +1,23 @@
+name: Feature Request
+description: Suggest a new feature
+labels: [enhancement]
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear description of the feature you'd like.
+    validations:
+      required: true
+  - type: textarea
+    id: motivation
+    attributes:
+      label: Motivation
+      description: Why is this feature important?
+    validations:
+      required: true
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives Considered
+      description: Any alternative solutions you've considered.

jostack_mdparse-0.1.0/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,17 @@
+## Summary
+
+<!-- Brief description of the changes -->
+
+## Changes
+
+<!-- List of changes made -->
+
+-
+
+## Test Plan
+
+<!-- How were these changes tested? -->
+
+- [ ] Unit tests pass (`pytest tests/ -v`)
+- [ ] Linting passes (`ruff check src/ tests/`)
+- [ ] Type checking passes (`mypy src/`)

jostack_mdparse-0.1.0/.github/dependabot.yml

@@ -0,0 +1,17 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      uv:
+        patterns: ["*"]
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      actions:
+        patterns: ["*"]

jostack_mdparse-0.1.0/.github/release.yml

@@ -0,0 +1,14 @@
+changelog:
+  categories:
+    - title: "🚀 Features"
+      labels: [enhancement]
+    - title: "🐛 Bug Fixes"
+      labels: [bug]
+    - title: "📖 Documentation"
+      labels: [documentation]
+    - title: "🔧 Maintenance"
+      labels: [chore, dependencies]
+    - title: "🔒 Security"
+      labels: [security]
+  exclude:
+    labels: [skip-changelog]

jostack_mdparse-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,52 @@
+name: CI
+
+on:
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+concurrency:
+  group: ci-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+permissions: {}
+
+jobs:
+  unit-test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.12', '3.13']
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: pip install -e . pytest pytest-socket pytest-cov
+      - name: Run tests
+        run: pytest tests/ -v --disable-socket --allow-unix-socket --cov=md_extract --cov-report=xml
+      - name: Upload coverage
+        if: matrix.python-version == '3.13'
+        uses: codecov/codecov-action@v5
+        with:
+          files: coverage.xml
+          fail_ci_if_error: false
+
+  lint:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.13'
+      - name: Install ruff and mypy
+        run: pip install ruff mypy
+      - name: Ruff check
+        run: ruff check src/ tests/
+      - name: Ruff format check
+        run: ruff format --check src/ tests/
+      - name: Mypy
+        run: mypy src/

jostack_mdparse-0.1.0/.github/workflows/claude-code-review.yml

@@ -0,0 +1,29 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  review:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - uses: anthropics/claude-code-action@v1
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          review_comment: |
+            Review this PR for:
+            - Code quality and bugs
+            - Performance issues
+            - Security vulnerabilities
+            - Test coverage gaps
+          allowed_tools: |
+            gh pr comment
+            gh pr view
+            gh pr diff

jostack_mdparse-0.1.0/.github/workflows/codeql.yml

@@ -0,0 +1,23 @@
+name: CodeQL
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  schedule:
+    - cron: '0 6 * * 1'
+
+permissions:
+  security-events: write
+
+jobs:
+  analyze:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@v4
+      - uses: github/codeql-action/init@v3
+        with:
+          languages: python
+      - uses: github/codeql-action/analyze@v3

jostack_mdparse-0.1.0/.github/workflows/notify-downstream.yml

@@ -0,0 +1,24 @@
+name: Notify Downstream
+
+on:
+  release:
+    types: [published]
+
+permissions: {}
+
+jobs:
+  notify:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - name: Extract version
+        id: version
+        run: echo "version=${GITHUB_REF_NAME#v}" >> "$GITHUB_OUTPUT"
+
+      - name: Trigger langchain sync
+        uses: peter-evans/repository-dispatch@v3
+        with:
+          token: ${{ secrets.LANGCHAIN_SYNC_TOKEN }}
+          repository: hyunhee-jo/langchain-md-extract
+          event-type: upstream-release
+          client-payload: '{"version": "${{ steps.version.outputs.version }}"}'

jostack_mdparse-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,58 @@
+name: Release
+
+on:
+  push:
+    tags: ['v*']
+
+permissions:
+  contents: write
+  id-token: write
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    environment:
+      name: pypi
+      url: https://pypi.org/p/md-extract
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.13'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Extract version
+        id: version
+        run: |
+          VERSION="${GITHUB_REF_NAME#v}"
+          echo "value=$VERSION" >> "$GITHUB_OUTPUT"
+
+      - name: Inject version
+        env:
+          VERSION: ${{ steps.version.outputs.value }}
+        run: |
+          sed -i "s/^version = \".*\"/version = \"${VERSION}\"/" pyproject.toml
+
+      - name: Build
+        run: uv build
+
+      - name: Verify build
+        run: |
+          pip install twine
+          twine check dist/*
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Create GitHub Release
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          TAG: ${{ github.ref_name }}
+        run: |
+          gh release create "$TAG" dist/* \
+            --title "$TAG" \
+            --generate-notes

jostack_mdparse-0.1.0/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

jostack_mdparse-0.1.0/CHANGELOG.md

@@ -0,0 +1,18 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/),
+and this project adheres to [Semantic Versioning](https://semver.org/).
+
+## [Unreleased]
+
+### Added
+
+- Initial project structure with CLI and Python API
+- `extract` command: parse Markdown to JSON, text, or HTML
+- `toc` command: print heading tree
+- `meta` command: print frontmatter metadata
+- 12 extraction options via `options.json` (Single Source of Truth)
+- CI workflow with Python 3.10/3.12/3.13 matrix
+- Claude Code automated PR review

jostack_mdparse-0.1.0/CLAUDE.md

@@ -0,0 +1,32 @@
+# CLAUDE.md
+
+## Project Overview
+
+jostack-mdparse is a Markdown file parser and structured extraction tool with CLI and Python API.
+
+## Architecture
+
+- `src/jostack_mdparse/extract.py` — Core extraction logic
+- `src/jostack_mdparse/cli.py` — CLI entry point (argparse, 3 subcommands: extract/toc/meta)
+- `options.json` — Single Source of Truth for all CLI options (12 options)
+- `scripts/generate-options.mjs` — Code generation from options.json
+
+## Key Design Decisions
+
+- **options.json is SsoT**: All CLI options are defined here, not in code
+- **SYNCED markers**: Used in langchain-jostack-mdparse for auto-sync
+- **Version 0.0.0**: Version is injected at build time via sed in release.yml
+
+## Commands
+
+```bash
+make test     # Run tests (pytest + pytest-socket)
+make lint     # Run ruff + mypy
+make format   # Auto-format with ruff
+```
+
+## Conventions
+
+- Commits: conventional commit format (English)
+- PRs: single purpose, <10 files, <500 lines
+- Python: ruff lint + ruff format + mypy strict

jostack_mdparse-0.1.0/CODE_OF_CONDUCT.md

@@ -0,0 +1,18 @@
+# Code of Conduct
+
+## Our Pledge
+
+We are committed to providing a friendly, safe and welcoming environment for all.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment:
+
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting the maintainer.

jostack_mdparse-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,33 @@
+# Contributing
+
+Thank you for your interest in contributing to jostack-mdparse!
+
+## Development Setup
+
+```bash
+git clone https://github.com/hyunhee-jo/jostack-mdparse.git
+cd jostack-mdparse
+pip install -e .
+pip install pytest pytest-socket ruff mypy
+```
+
+## Running Tests
+
+```bash
+make test
+```
+
+## Code Style
+
+This project uses [ruff](https://docs.astral.sh/ruff/) for linting and formatting, and [mypy](https://mypy-lang.org/) for type checking.
+
+```bash
+make lint    # Check
+make format  # Auto-fix
+```
+
+## Pull Requests
+
+- One PR per feature/fix (keep PRs small: <10 files, <500 lines)
+- All tests must pass
+- Follow conventional commit messages