Merge pull request #7 from opendatalab/dev

Dev

magic_pdf/utils/annotations.py

+
+from loguru import logger
+
+
+def ImportPIL(f):
+    try:
+        import PIL  # noqa: F401
+    except ImportError:
+        logger.error('Pillow not installed, please install by pip.')
+        exit(1)
+    return f

next_docs/en/.readthedocs.yaml

+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.10"
+
+formats:
+  - epub
+
+python:
+  install:
+    - requirements: docs/requirements.txt
+
+sphinx:
+  configuration: docs/en/conf.py

next_docs/en/Makefile

+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

next_docs/en/api.rst

+Data Api
+------------------
+
+.. toctree::
+   :maxdepth: 2
+
+   api/dataset.rst
+   api/data_reader_writer.rst
+   api/read_api.rst

next_docs/en/api/data_reader_writer.rst

+
+Data Reader Writer
+--------------------
+
+.. autoclass:: magic_pdf.data.data_reader_writer.DataReader
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.DataWriter
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.S3DataReader
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.S3DataWriter
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.FileBasedDataReader
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.FileBasedDataWriter
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.S3DataReader
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.S3DataWriter
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.MultiBucketS3DataReader
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.data_reader_writer.MultiBucketS3DataWriter
+   :members:
+   :inherited-members:
+

next_docs/en/api/dataset.rst

+Dataset Api
+------------------
+
+.. autoclass:: magic_pdf.data.dataset.PageableData
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.Dataset
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.ImageDataset
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.PymuDocDataset
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.Doc
+   :members:
+   :inherited-members:

next_docs/en/api/read_api.rst

+read_api Api
+------------------
+
+.. automodule:: magic_pdf.data.read_api
+   :members:
+   :inherited-members:

next_docs/en/api/utils.rst

+

next_docs/en/conf.py

+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+
+import os
+import subprocess
+import sys
+
+from sphinx.ext import autodoc
+
+
+def install(package):
+    subprocess.check_call([sys.executable, '-m', 'pip', 'install', package])
+
+
+requirements_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'requirements.txt'))
+if os.path.exists(requirements_path):
+    with open(requirements_path) as f:
+        packages = f.readlines()
+    for package in packages:
+        install(package.strip())
+
+sys.path.insert(0, os.path.abspath('../..'))
+
+# -- Project information -----------------------------------------------------
+
+project = 'MinerU'
+copyright = '2024, MinerU Contributors'
+author = 'OpenDataLab'
+
+# The full version, including alpha/beta/rc tags
+version_file = '../../magic_pdf/libs/version.py'
+with open(version_file) as f:
+    exec(compile(f.read(), version_file, 'exec'))
+__version__ = locals()['__version__']
+# The short X.Y version
+version = __version__
+# The full version, including alpha/beta/rc tags
+release = __version__
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.napoleon',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.intersphinx',
+    'sphinx_copybutton',
+    'sphinx.ext.autodoc',
+    'sphinx.ext.autosummary',
+    'myst_parser',
+    'sphinxarg.ext',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# Exclude the prompt "$" when copying code
+copybutton_prompt_text = r'\$ '
+copybutton_prompt_is_regexp = True
+
+language = 'en'
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_book_theme'
+html_logo = '_static/image/logo.png'
+html_theme_options = {
+    'path_to_docs': 'docs/en',
+    'repository_url': 'https://github.com/opendatalab/MinerU',
+    'use_repository_button': True,
+}
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+# html_static_path = ['_static']
+
+# Mock out external dependencies here.
+autodoc_mock_imports = [
+    'cpuinfo',
+    'torch',
+    'transformers',
+    'psutil',
+    'prometheus_client',
+    'sentencepiece',
+    'vllm.cuda_utils',
+    'vllm._C',
+    'numpy',
+    'tqdm',
+]
+
+
+class MockedClassDocumenter(autodoc.ClassDocumenter):
+    """Remove note about base class when a class is derived from object."""
+
+    def add_line(self, line: str, source: str, *lineno: int) -> None:
+        if line == '   Bases: :py:class:`object`':
+            return
+        super().add_line(line, source, *lineno)
+
+
+autodoc.ClassDocumenter = MockedClassDocumenter
+
+navigation_with_keys = False

next_docs/en/index.rst

+.. xtuner documentation master file, created by
+   sphinx-quickstart on Tue Jan  9 16:33:06 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to the MinerU Documentation
+==============================================
+
+.. figure:: ./_static/image/logo.png
+  :align: center
+  :alt: mineru
+  :class: no-scaled-link
+
+.. raw:: html
+
+   <p style="text-align:center">
+   <strong>A one-stop, open-source, high-quality data extraction tool
+   </strong>
+   </p>
+
+   <p style="text-align:center">
+   <script async defer src="https://buttons.github.io/buttons.js"></script>
+   <a class="github-button" href="https://github.com/opendatalab/MinerU" data-show-count="true" data-size="large" aria-label="Star">Star</a>
+   <a class="github-button" href="https://github.com/opendatalab/MinerU/subscription" data-icon="octicon-eye" data-size="large" aria-label="Watch">Watch</a>
+   <a class="github-button" href="https://github.com/opendatalab/MinerU/fork" data-icon="octicon-repo-forked" data-size="large" aria-label="Fork">Fork</a>
+   </p>
+
+
+API Reference
+-------------
+
+If you are looking for information on a specific function, class or
+method, this part of the documentation is for you.
+
+.. toctree::
+   :maxdepth: 2
+
+   api

next_docs/en/make.bat

+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

next_docs/requirements.txt

+boto3>=1.28.43
+loguru>=0.6.0
+myst-parser
+Pillow==8.4.0
+pydantic>=2.7.2,<2.8.0
+PyMuPDF>=1.24.9
+sphinx
+sphinx-argparse
+sphinx-book-theme
+sphinx-copybutton
+sphinx_rtd_theme

next_docs/zh_cn/.readthedocs.yaml

+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.10"
+
+formats:
+  - epub
+
+python:
+  install:
+    - requirements: docs/requirements.txt
+
+sphinx:
+  configuration: docs/zh_cn/conf.py

next_docs/zh_cn/Makefile

+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

next_docs/zh_cn/conf.py

+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+
+import os
+import subprocess
+import sys
+
+from sphinx.ext import autodoc
+
+
+def install(package):
+    subprocess.check_call([sys.executable, '-m', 'pip', 'install', package])
+
+
+requirements_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'requirements.txt'))
+if os.path.exists(requirements_path):
+    with open(requirements_path) as f:
+        packages = f.readlines()
+    for package in packages:
+        install(package.strip())
+
+sys.path.insert(0, os.path.abspath('../..'))
+
+# -- Project information -----------------------------------------------------
+
+project = 'MinerU'
+copyright = '2024, OpenDataLab'
+author = 'MinerU Contributors'
+
+# The full version, including alpha/beta/rc tags
+version_file = '../../magic_pdf/libs/version.py'
+with open(version_file) as f:
+    exec(compile(f.read(), version_file, 'exec'))
+__version__ = locals()['__version__']
+# The short X.Y version
+version = __version__
+# The full version, including alpha/beta/rc tags
+release = __version__
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.napoleon',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.intersphinx',
+    'sphinx_copybutton',
+    'sphinx.ext.autodoc',
+    'sphinx.ext.autosummary',
+    'myst_parser',
+    'sphinxarg.ext',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# Exclude the prompt "$" when copying code
+copybutton_prompt_text = r'\$ '
+copybutton_prompt_is_regexp = True
+
+language = 'zh_CN'
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_book_theme'
+html_logo = '_static/image/logo.png'
+html_theme_options = {
+    'path_to_docs': 'docs/zh_cn',
+    'repository_url': 'https://github.com/opendatalab/MinerU',
+    'use_repository_button': True,
+}
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+# html_static_path = ['_static']
+
+# Mock out external dependencies here.
+autodoc_mock_imports = [
+    'cpuinfo',
+    'torch',
+    'transformers',
+    'psutil',
+    'prometheus_client',
+    'sentencepiece',
+    'vllm.cuda_utils',
+    'vllm._C',
+    'numpy',
+    'tqdm',
+]
+
+
+class MockedClassDocumenter(autodoc.ClassDocumenter):
+    """Remove note about base class when a class is derived from object."""
+
+    def add_line(self, line: str, source: str, *lineno: int) -> None:
+        if line == '   Bases: :py:class:`object`':
+            return
+        super().add_line(line, source, *lineno)
+
+
+autodoc.ClassDocumenter = MockedClassDocumenter
+
+navigation_with_keys = False

next_docs/zh_cn/index.rst

+.. xtuner documentation master file, created by
+   sphinx-quickstart on Tue Jan  9 16:33:06 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+欢迎来到 MinerU 的中文文档
+==============================================
+
+.. figure:: ./_static/image/logo.png
+  :align: center
+  :alt: mineru
+  :class: no-scaled-link
+
+.. raw:: html
+
+   <p style="text-align:center">
+   <strong> 一站式开源高质量数据提取工具
+   </strong>
+   </p>
+
+   <p style="text-align:center">
+   <script async defer src="https://buttons.github.io/buttons.js"></script>
+   <a class="github-button" href="https://github.com/opendatalab/MinerU" data-show-count="true" data-size="large" aria-label="Star">Star</a>
+   <a class="github-button" href="https://github.com/opendatalab/MinerU/subscription" data-icon="octicon-eye" data-size="large" aria-label="Watch">Watch</a>
+   <a class="github-button" href="https://github.com/opendatalab/MinerU/fork" data-icon="octicon-repo-forked" data-size="large" aria-label="Fork">Fork</a>
+   </p>