[docs] initialize sphinx

docs/Makefile

@@ -0,0 +1,20 @@
+# 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     = source
+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)

docs/README.md

@@ -0,0 +1,29 @@
+EduNLP document and tutorial folder
+===================================
+
+Requirements
+------------
+See the requirements `docs_deps` in `setup.py`:
+```sh
+pip install -e .[doc]
+```
+
+
+Build documents
+---------------
+First, clean up existing files:
+```
+make clean
+```
+
+Then build:
+```
+make html
+```
+
+Render locally
+--------------
+```
+cd build/html
+python3 -m http.server 8000
+```

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+if "%1" == "" goto help
+
+%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.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/source/api/formula.rst

@@ -0,0 +1,6 @@
+EduNLP.Formula
+=======================
+
+.. automodule:: EduNLP.Formula.ast
+   :members:
+   :imported-members:

docs/source/api/i2v.rst

@@ -0,0 +1,6 @@
+EduNLP.I2V
+============
+
+.. automodule:: EduNLP.I2V.i2v
+   :members:
+   :imported-members:

docs/source/api/index.rst

@@ -0,0 +1,2 @@
+EduNLP
+======

docs/source/api/sif.rst

@@ -0,0 +1,39 @@
+EduNLP.SIF
+==============
+
+SIF
+----------
+.. automodule:: EduNLP.SIF.sif
+   :members:
+   :imported-members:
+
+
+Segment
+----------
+.. automodule:: EduNLP.SIF.segment
+   :members:
+   :imported-members:
+
+
+Parser
+--------
+.. automodule:: EduNLP.SIF.parser
+   :members:
+   :imported-members:
+
+
+Tokenization
+---------------
+
+tokenize
+^^^^^^^^^^
+.. automodule:: EduNLP.SIF.tokenization.tokenization
+   :members:
+   :imported-members:
+
+
+formula
+^^^^^^^^^
+.. automodule:: EduNLP.SIF.tokenization.formula
+   :members:
+   :imported-members:

docs/source/conf.py

@@ -0,0 +1,68 @@
+# 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 sys
+sys.path.insert(0, os.path.abspath('../'))
+
+import sphinx_rtd_theme
+
+# -- Project information -----------------------------------------------------
+
+project = 'EduNLP'
+copyright = '2021, bigdata-ustc'
+author = 'bigdata-ustc'
+
+
+# -- 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.autodoc',
+    'sphinx.ext.autosummary',
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.napoleon',
+    'sphinx.ext.mathjax',
+    'sphinx_toggleprompt',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = 'en'
+
+# 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 = []
+
+
+# -- 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_rtd_theme"
+html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+
+# 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']

docs/source/index.rst

@@ -0,0 +1,100 @@
+.. EduNLP documentation master file, created by
+   sphinx-quickstart on Sat Aug  7 19:55:39 2021.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+===============================================
+Welcome to EduNLP's Tutorials and Documentation
+===============================================
+.. Logo
+.. image:: _static/EduNLP.png
+   :width: 200px
+   :align: center
+
+.. Badges
+.. image:: https://img.shields.io/pypi/v/EduNLP.svg
+   :target: https://pypi.python.org/pypi/EduNLP
+
+.. image:: https://github.com/bigdata-ustc/EduNLP/actions/workflows/python-test.yml/badge.svg?branch=master
+   :target: https://github.com/bigdata-ustc/EduNLP/actions/workflows/python-test.yml
+
+.. todo: add all badges in EduNLP/REAMD.md
+
+`EduNLP <https://github.com/bigdata-ustc/EduNLP>`_ is a library for advanced Natural Language Processing in Python and is one of the projects of `EduX <https://github.com/bigdata-ustc/EduX>`_ plan of BDAA.
+It's built on the very latest research, and was designed from day one to be used in real educational products.
+
+EduNLP now comes with pretrained pipelines and currently supports segment, tokenization and vertorization. It supports varies of preprocessing for NLP in educational scenario, such as formula parsing, multi-modal segment.
+
+EduNLP is commercial open-source software, released under the `Apache-2.0 license <https://github.com/bigdata-ustc/EduNLP/blob/master/LICENSE>`_.
+
+Install
+---------
+EduNLP requires Python version 3.6, 3.7, 3.8 or 3.9. EduNLP use PyTorch as the backend tensor library.
+
+We recommend installing EduNLP by ``pip``:
+
+::
+
+   pip install EduNLP
+
+But you can also install from source:
+
+::
+
+   git clone https://github.com/bigdata-ustc/EduNLP.git
+   cd EduNLP
+   pip install .
+
+
+
+Getting Started
+------------------
+For absolute beginners, start with the `Tutorial to EduNLP <tutorial/en/index>`_ `(中文版) <tutorial/zh/index>`_.
+It covers the basic concepts of EduNLP and
+a step-by-step on training, loading and using the language models.
+
+
+Contribution
+--------------
+EduNLP is free software; you can redistribute it and/or modify it under the terms of the Apache License 2.0.
+We welcome contributions. Join us on GitHub and check out our `contribution guidelines <https://github.com/bigdata-ustc/EduNLP/blob/master/CONTRIBUTE.md>`_ `(中文版) <https://github.com/bigdata-ustc/EduNLP/blob/master/CONTRIBUTE_CH.md>`_.
+
+.. toctree::
+   :caption: Introduction
+   :hidden:
+
+   self
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Tutorial
+   :hidden:
+   :glob:
+
+   tutorial/en/index
+   tutorial/en/sif
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 用户指南
+   :hidden:
+
+   tutorial/zh/index
+   tutorial/zh/sif
+   tutorial/zh/seg
+   tutorial/zh/parse
+   tutorial/zh/tokenize
+   tutorial/zh/vectorization
+   tutorial/zh/pretrain
+
+
+.. toctree::
+   :maxdepth: 2
+   :caption: API Reference
+   :hidden:
+   :glob:
+
+   api/index
+   api/i2v
+   api/sif
+   api/formula

docs/source/tutorial/en/index.rst

@@ -0,0 +1,2 @@
+Get Started
+===========

docs/source/tutorial/en/sif.rst

@@ -0,0 +1,2 @@
+Standard Item Format
+====================

docs/source/tutorial/zh/index.rst

@@ -0,0 +1,12 @@
+入门
+=====
+
+.. toctree::
+  :maxdepth: 1
+  :titlesonly:
+
+  sif
+  seg
+  parse
+  tokenize
+  vectorization

docs/source/tutorial/zh/parse.rst

@@ -0,0 +1,10 @@
+语法解析
+=========
+
+在教育资源中，文本、公式都具有内在的隐式或显式的语法结构，提取这种结构对后续进一步的处理是大有裨益的：
+
+* 文本语法结构解析
+* 公式语法结构解析
+
+公式语法结构解析
+--------------------

docs/source/tutorial/zh/pretrain.rst

@@ -0,0 +1,19 @@
+预训练
+=======
+
+在自然语言处理领域中，预训练语言模型（Pre-trained Language Models）已成为非常重要的基础技术。
+我们将在本章节介绍EduNLP中预训练工具：
+
+* 如何从零开始用一份语料训练得到一个预训练模型
+* 如何加载预训练模型
+* 公开的预训练模型
+
+
+训练模型
+---------
+
+装载模型
+--------
+
+公开模型一览
+------------

docs/source/tutorial/zh/seg.rst

@@ -0,0 +1,18 @@
+成分分解
+=========
+
+由于教育资源是一种多模态数据，包含了诸如文本、图片、公式等数据结构；
+同时在语义上也可能包含不同组成部分，例如题干、选项等，因此我们首先需要对教育资源的不同组成成分进行识别并进行分解：
+
+* 语义成分分解
+* 结构成分分解
+
+语义成分分解
+------------
+
+结构成分分解
+------------
+
+
+
+

docs/source/tutorial/zh/sif.rst

@@ -0,0 +1,2 @@
+标准项目格式
+============