From 23077006b0fdbbf645652d1f76e4be3fe374537f Mon Sep 17 00:00:00 2001 From: Daniel Schadt Date: Sun, 22 Aug 2021 23:52:06 +0200 Subject: Add some initial documentation --- doc/Makefile | 20 +++++++++++++ doc/conf.py | 63 +++++++++++++++++++++++++++++++++++++++++ doc/document.rst | 5 ++++ doc/formats.rst | 5 ++++ doc/index.rst | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ doc/make.bat | 35 +++++++++++++++++++++++ doc/templates.rst | 5 ++++ 7 files changed, 217 insertions(+) create mode 100644 doc/Makefile create mode 100644 doc/conf.py create mode 100644 doc/document.rst create mode 100644 doc/formats.rst create mode 100644 doc/index.rst create mode 100644 doc/make.bat create mode 100644 doc/templates.rst (limited to 'doc') diff --git a/doc/Makefile b/doc/Makefile new file mode 100644 index 0000000..d4bb2cb --- /dev/null +++ b/doc/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 = . +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) diff --git a/doc/conf.py b/doc/conf.py new file mode 100644 index 0000000..327cc49 --- /dev/null +++ b/doc/conf.py @@ -0,0 +1,63 @@ +# 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('.')) + + +# -- Project information ----------------------------------------------------- + +project = 'Wikimini' +copyright = '2021, Daniel Schadt' +author = 'Daniel Schadt' + + +# -- 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.napoleon", + "sphinx_autodoc_typehints", + "sphinx.ext.intersphinx", +] + +# 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'] + + +# -- 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 = 'alabaster' + +# 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'] + +# -- Intersphinx mappings ---------------------------------------------------- +intersphinx_mapping = { + 'mwparserfromhell': ('https://mwparserfromhell.readthedocs.io/en/latest/', + None), + 'stdlib': ('https://docs.python.org/3', None), +} diff --git a/doc/document.rst b/doc/document.rst new file mode 100644 index 0000000..9acbb93 --- /dev/null +++ b/doc/document.rst @@ -0,0 +1,5 @@ +The Document representation +=========================== + +.. automodule:: wikimini.document + :members: diff --git a/doc/formats.rst b/doc/formats.rst new file mode 100644 index 0000000..ddf01be --- /dev/null +++ b/doc/formats.rst @@ -0,0 +1,5 @@ +Output Formats +============== + +.. automodule:: wikimini.formats + :members: diff --git a/doc/index.rst b/doc/index.rst new file mode 100644 index 0000000..9eaecfc --- /dev/null +++ b/doc/index.rst @@ -0,0 +1,84 @@ +.. Wikimini documentation master file, created by + sphinx-quickstart on Tue Aug 17 00:07:39 2021. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +Welcome to Wikimini's documentation! +==================================== + +.. toctree:: + :maxdepth: 2 + :caption: Contents: + + document + templates + formats + +Wikimini is a library that takes Wikimedia Markup and renders it into a text +format, such as `Gemtext +`__:: + + from wikimini import Wikimini + from wikimini.formats.gemtext import Gemtext + import sys + + # The English Wikipedia is the default source. + wiki = Wikimini() + _, markup = wiki.retrieve("Coffee") + document = wiki.convert_to_document(markup) + Gemtext(sys.stdout).render(document) + +The reason why Wikimini is "better" than simply stripping all markup (such as +:meth:`mwparserfromhell.wikicode.Wikicode.strip_code` does) is that you can +keep a lot more information: Some interesting bits are implemented as templates +in Wikipedia (markup like ``{{lang|ar|قَهْوَة}}``), and leaving them out either +means missing out on the provided information, or having nonsensical +punctuation in your output. + +The Wikimini pipeline is made to work in three steps: + +#. We start with the parsed :class:`~mwparserfromhell.wikicode.Wikicode`, which + is a parsed representation of Wikipedia's markup language +#. Then convert the :class:`~mwparserfromhell.wikicode.Wikicode` to our + internal representation, the :class:`~wikimini.document.Document`. This step + already executes the templates and provides a stripped-down markup that only + keeps the essential meta information (like heading). +#. Lastly, we convert our :class:`~wikimini.document.Document` to our desired + format with the help of a :class:`~wikimini.formats.Format`. + +Extensibility +------------- + +Wikimini is extensible in multiple ways: + +The easiest extension is to make Wikimini work for different Mediawiki +instances. This can be done by passing the correct API URL to the constructor +of :class:`~wikimini.Wikimini`. + +You can also extend Wikimini by teaching it about more templates, for that, see +:doc:`templates`. + +Additionally, you can implement other output formats, see :doc:`formats` for +that. + +Reference +--------- + +Most of the interaction with Wikimini is done through the +:class:`wikimini.Wikimini` object: + +.. autoclass:: wikimini.Wikimini + :members: + +Additionally, the module defines some constants: + +.. autodata:: wikimini.API_URL + +.. autodata:: wikimini.TABLE_FORMAT + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` diff --git a/doc/make.bat b/doc/make.bat new file mode 100644 index 0000000..2119f51 --- /dev/null +++ b/doc/make.bat @@ -0,0 +1,35 @@ +@ECHO OFF + +pushd %~dp0 + +REM Command file for Sphinx documentation + +if "%SPHINXBUILD%" == "" ( + set SPHINXBUILD=sphinx-build +) +set SOURCEDIR=. +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 diff --git a/doc/templates.rst b/doc/templates.rst new file mode 100644 index 0000000..b0b36fb --- /dev/null +++ b/doc/templates.rst @@ -0,0 +1,5 @@ +Templates +========= + +.. automodule:: wikimini.templates + :members: -- cgit v1.2.3