Merge pull request #7 from sharkutilities/docs/init-rtd

Adding Configuration for Sphinx Docs, RTD Configurations

.readthedocs.yaml

@@ -0,0 +1,14 @@
+version: 2
+
+build:
+    os: ubuntu-22.04
+    tools:
+        python: "3.10"
+
+python:
+    install:
+        - requirements: docs/requirements.txt
+
+sphinx:
+    fail_on_warning: false
+    configuration: docs/conf.py

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "liveServer.settings.port": 5501
+}

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     = .
+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/conf.py

@@ -0,0 +1,41 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+import os
+import sys
+
+# ? insert the project root to let sphinx recognize/find packages
+sys.path.insert(0, os.path.abspath(".."))
+
+# ? also import the module itself, to populate static contents like version
+sys.path.append(os.path.abspath(".."))
+import nlpurify
+
+project = 'NLPurify'
+copyright = '2024, shark-utilities developers'
+author = 'shark-utilities developers'
+release = nlpurify.__version__
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = [
+    'myst_parser',
+    'sphinx.ext.autodoc',
+    'sphinx.ext.autosummary'
+]
+
+templates_path = ['_templates']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = 'sphinx_rtd_theme'
+html_static_path = ['_static']

docs/index.md

@@ -0,0 +1,44 @@
+<h1 align = "center">NLPurify</h1>
+
+<div align = "center">
+
+[![GitHub Issues](https://img.shields.io/github/issues/sharkutilities/NLPurify?style=plastic)](https://github.com/sharkutilities/NLPurify/issues)
+[![GitHub Forks](https://img.shields.io/github/forks/sharkutilities/NLPurify?style=plastic)](https://github.com/sharkutilities/NLPurify/network)
+[![GitHub Stars](https://img.shields.io/github/stars/sharkutilities/NLPurify?style=plastic)](https://github.com/sharkutilities/NLPurify/stargazers)
+[![LICENSE File](https://img.shields.io/github/license/sharkutilities/NLPurify?style=plastic)](https://github.com/sharkutilities/NLPurify/blob/master/LICENSE)
+
+</div>
+
+<div align = "justify">
+
+A text cleaning and extraction engine was developed using a combination of traditional techniques like Unicode translations,
+cleaning using regular expressions, and modern tools like "natural language processing" and "large language models" to
+detect and clean long texts and create word vectors.
+
+## Getting Started
+
+The source code is hosted at GitHub: [**sharkutilities/NLPurify**](https://github.com/sharkutilities/NLPurify).
+The binary installers for the latest release are available at the [Python Package Index (PyPI)](https://pypi.org/project/NLPurify/).
+
+```bash
+pip install -U NLPurify
+```
+
+The module is currently under development, and new ideas are welcomed. Raise a new PR/issue for the same.
+The changes between each release are available [here](./CHANGELOG.md).
+
+---
+
+```{eval-rst}
+.. caution::
+  **This code depreciates the existing GitHub Gist which was previously designed.**
+  Check `#1 <https://github.com/sharkutilities/NLPurify/issues/1>`_ for more details.
+```
+
+```{eval-rst}
+.. note::
+  **Legacy codes are available as a submodule.**
+  Check `#5 <https://github.com/sharkutilities/NLPurify/issues/5>`_ for more details.
+```
+
+</div>

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=.
+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

docs/requirements.txt

@@ -0,0 +1,5 @@
+fuzzywuzzy
+python-Levenshtein
+sphinx==7.1.2
+myst-parser==2.0.0
+sphinx-rtd-theme==1.3.0rc1