6efa96c983
* feat: add support for `ocrmac` OCR engine on macOS - Integrates `ocrmac` as an OCR engine option for macOS users. - Adds configuration options and dependencies for `ocrmac`. - Updates documentation to reflect new engine support. This change allows macOS users to utilize `ocrmac` for improved OCR performance and compatibility. Signed-off-by: Suhwan Seo <nuridol@gmail.com> * updated the poetry lock Signed-off-by: Suhwan Seo <nuridol@gmail.com> * Fix linting issues, update CLI docs, and add error for ocrmac use on non-Mac systems - Resolved formatting and linting issues - Updated `--ocr-engine` CLI option documentation for `ocrmac` - Added RuntimeError for attempts to use `ocrmac` on non-Mac platforms Signed-off-by: Suhwan Seo <nuridol@gmail.com> * feat: add support for `ocrmac` OCR engine on macOS - Integrates `ocrmac` as an OCR engine option for macOS users. - Adds configuration options and dependencies for `ocrmac`. - Updates documentation to reflect new engine support. This change allows macOS users to utilize `ocrmac` for improved OCR performance and compatibility. Signed-off-by: Suhwan Seo <nuridol@gmail.com> * docs: update examples and installation for ocrmac support - Added `OcrMacOptions` to `custom_convert.py` and `full_page_ocr.py` examples. - Included usage comments and examples for `OcrMacOptions` in OCR pipelines. - Updated installation guide to include instructions for installing `ocrmac`, noting macOS version requirements (10.15+). - Highlighted that `ocrmac` leverages Apple's Vision framework as an OCR backend. This enhances documentation for users working on macOS to leverage `ocrmac` effectively. Signed-off-by: Suhwan Seo <nuridol@gmail.com> * fix: update `ocrmac` dependency with macOS-specific marker - Added `sys_platform == 'darwin'` marker to the `ocrmac` dependency in `pyproject.toml` to specify macOS compatibility. - Updated the content hash in `poetry.lock` to reflect the changes. This ensures the `ocrmac` dependency is only installed on macOS systems. Signed-off-by: Suhwan Seo <nuridol@gmail.com> --------- Signed-off-by: Suhwan Seo <nuridol@gmail.com> Co-authored-by: Suhwan Seo <nuridol@gmail.com>
159 lines
4.5 KiB
TOML
159 lines
4.5 KiB
TOML
[tool.poetry]
|
|
name = "docling"
|
|
version = "2.6.0" # DO NOT EDIT, updated automatically
|
|
description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
|
|
authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Panos Vagenas <pva@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
repository = "https://github.com/DS4SD/docling"
|
|
homepage = "https://github.com/DS4SD/docling"
|
|
keywords= ["docling", "convert", "document", "pdf", "docx", "html", "markdown", "layout model", "segmentation", "table structure", "table former"]
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Operating System :: MacOS :: MacOS X",
|
|
"Operating System :: POSIX :: Linux",
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Programming Language :: Python :: 3"
|
|
]
|
|
packages = [{include = "docling"}]
|
|
|
|
[tool.poetry.dependencies]
|
|
######################
|
|
# actual dependencies:
|
|
######################
|
|
python = "^3.10"
|
|
pydantic = "^2.0.0"
|
|
docling-core = "^2.4.0"
|
|
docling-ibm-models = "^2.0.3"
|
|
deepsearch-glm = "^0.26.1"
|
|
filetype = "^1.2.0"
|
|
pypdfium2 = "^4.30.0"
|
|
pydantic-settings = "^2.3.0"
|
|
huggingface_hub = ">=0.23,<1"
|
|
requests = "^2.32.3"
|
|
easyocr = "^1.7"
|
|
tesserocr = { version = "^2.7.1", optional = true }
|
|
docling-parse = "^2.0.2"
|
|
certifi = ">=2024.7.4"
|
|
rtree = "^1.3.0"
|
|
scipy = "^1.14.1"
|
|
pyarrow = "^16.1.0"
|
|
typer = "^0.12.5"
|
|
python-docx = "^1.1.2"
|
|
python-pptx = "^1.0.2"
|
|
beautifulsoup4 = "^4.12.3"
|
|
pandas = "^2.1.4"
|
|
marko = "^2.1.2"
|
|
openpyxl = "^3.1.5"
|
|
ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true }
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
black = {extras = ["jupyter"], version = "^24.4.2"}
|
|
pytest = "^7.2.2"
|
|
pre-commit = "^3.7.1"
|
|
mypy = "^1.10.1"
|
|
isort = "^5.10.1"
|
|
python-semantic-release = "^7.32.2"
|
|
flake8 = "^6.0.0"
|
|
pyproject-flake8 = "^6.0.0"
|
|
pytest-xdist = "^3.3.1"
|
|
types-requests = "^2.31.0.2"
|
|
flake8-pyproject = "^1.2.3"
|
|
pylint = "^2.17.5"
|
|
pandas-stubs = "^2.1.4.231227"
|
|
ipykernel = "^6.29.5"
|
|
ipywidgets = "^8.1.5"
|
|
nbqa = "^1.9.0"
|
|
types-openpyxl = "^3.1.5.20241114"
|
|
|
|
[tool.poetry.group.docs.dependencies]
|
|
mkdocs-material = "^9.5.40"
|
|
mkdocs-jupyter = "^0.25.0"
|
|
mkdocs-click = "^0.8.1"
|
|
|
|
[tool.poetry.group.examples.dependencies]
|
|
datasets = "^2.21.0"
|
|
python-dotenv = "^1.0.1"
|
|
langchain-huggingface = "^0.0.3"
|
|
langchain-milvus = "^0.1.4"
|
|
langchain-text-splitters = "^0.2.4"
|
|
|
|
[tool.poetry.group.mac_intel]
|
|
optional = true
|
|
|
|
[tool.poetry.group.mac_intel.dependencies]
|
|
torch = [
|
|
{markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2"},
|
|
{markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2"}
|
|
]
|
|
torchvision = [
|
|
{markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0"},
|
|
{markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2"}
|
|
]
|
|
|
|
[tool.poetry.extras]
|
|
tesserocr = ["tesserocr"]
|
|
ocrmac = ["ocrmac"]
|
|
|
|
[tool.poetry.scripts]
|
|
docling = "docling.cli.main:app"
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.black]
|
|
line-length = 88
|
|
target-version = ["py310"]
|
|
include = '\.pyi?$'
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
line_length = 88
|
|
py_version=311
|
|
|
|
[tool.mypy]
|
|
pretty = true
|
|
# strict = true
|
|
no_implicit_optional = true
|
|
plugins = "pydantic.mypy"
|
|
python_version = "3.10"
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"docling_parse.*",
|
|
"pypdfium2.*",
|
|
"networkx.*",
|
|
"scipy.*",
|
|
"filetype.*",
|
|
"tesserocr.*",
|
|
"docling_ibm_models.*",
|
|
"easyocr.*",
|
|
"ocrmac.*",
|
|
"deepsearch_glm.*",
|
|
"lxml.*",
|
|
"bs4.*",
|
|
"huggingface_hub.*"
|
|
]
|
|
ignore_missing_imports = true
|
|
|
|
[tool.flake8]
|
|
max-line-length = 88
|
|
extend-ignore = ["E203", "E501"]
|
|
|
|
[tool.semantic_release]
|
|
# for default values check:
|
|
# https://github.com/python-semantic-release/python-semantic-release/blob/v7.32.2/semantic_release/defaults.cfg
|
|
|
|
version_source = "tag_only"
|
|
branch = "main"
|
|
|
|
# configure types which should trigger minor and patch version bumps respectively
|
|
# (note that they must be a subset of the configured allowed types):
|
|
parser_angular_allowed_types = "build,chore,ci,docs,feat,fix,perf,style,refactor,test"
|
|
parser_angular_minor_types = "feat"
|
|
parser_angular_patch_types = "fix,perf"
|