Aman
a32b7508c7
PaddleOCR with preprocessing, scispaCy NER, figure/table detection, citation extraction, and chunked Markdown output with frontmatter. Includes watch mode and notebook reprocessing.
27 lines
672 B
YAML
27 lines
672 B
YAML
repos:
|
|
- repo: https://github.com/astral-sh/ruff-pre-commit
|
|
rev: v0.2.0
|
|
hooks:
|
|
- id: ruff
|
|
args: [--fix]
|
|
- id: ruff-format
|
|
|
|
- repo: https://github.com/pre-commit/mirrors-mypy
|
|
rev: v1.8.0
|
|
hooks:
|
|
- id: mypy
|
|
additional_dependencies: [pydantic, pyyaml, typer, rich, structlog, numpy, opencv-python-headless]
|
|
|
|
- repo: https://github.com/pre-commit/pre-commit-hooks
|
|
rev: v4.5.0
|
|
hooks:
|
|
- id: trailing-whitespace
|
|
- id: end-of-file-fixer
|
|
- id: check-yaml
|
|
- id: check-toml
|
|
- id: check-added-large-files
|
|
|
|
- repo: https://github.com/pycqa/isort
|
|
rev: 5.13.2
|
|
hooks:
|
|
- id: isort |