word2html 0.2.0__tar.gz → 0.4.0__tar.gz

word2html-0.4.0/.gitignore

@@ -0,0 +1,33 @@
+# Virtual environments
+env/
+.venv/
+venv/
+
+# Python artifacts
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+
+# Distribution / packaging
+build/
+dist/
+*.egg-info/
+.eggs/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# OS
+.DS_Store
+Thumbs.db

{word2html-0.2.0 → word2html-0.4.0}/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2017, Brad Montgomery <brad@bradmontgomery.net>
+Copyright (c) 2025, Brad Montgomery <brad@bradmontgomery.net>
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in

word2html-0.4.0/PKG-INFO

@@ -0,0 +1,73 @@
+Metadata-Version: 2.4
+Name: word2html
+Version: 0.4.0
+Summary: A quick and dirty script to convert a Word (docx) document to html.
+Project-URL: Homepage, https://github.com/bradmontgomery/word2html
+Author-email: Brad Montgomery <brad@bradmontgomery.net>
+License: MIT
+License-File: LICENSE.txt
+Keywords: html,to,word
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Text Processing
+Classifier: Topic :: Utilities
+Requires-Python: >=3.12
+Requires-Dist: pypandoc>=1.16.2
+Requires-Dist: pytidylib>=0.3.2
+Description-Content-Type: text/markdown
+
+# 🌟 Convert a Word Doc to html
+
+## 🚀 Quick Start with uvx
+
+The easiest way to run word2html without installing is using `uvx`:
+
+    uvx word2html /path/to/MyGloriousDoc.docx
+
+This will give you a new file, `/path/to/MyGloriousDoc.html`, that's (hopefully)
+decent-looking html.
+
+## 💾 Installation
+
+To install with uv:
+
+    uv tool install word2html
+
+Or with pip:
+
+    pip install word2html
+
+Then run:
+
+    word2html /path/to/MyGloriousDoc.docx
+
+## 🧪 Note on tests & versions
+
+- This project has NO TESTS! (feel free to add some of you think it should).
+- This project requires Python 3.12 or greater
+
+## 📝 Note on Licenses
+
+While this code is MIT-licensed, it uses boty pypandoc and pytidylib, both of
+which depend on other software that may not be MIT-licensed and must be installed
+for this to work.
+
+* [pytidylib](https://pypi.python.org/pypi/pytidylib/) is available under the
+  MIT license, and [Tidy](http://tidy.sourceforge.net/#license) is available
+  under an MIT-like license
+* [pypandoc](https://pypi.python.org/pypi/pypandoc/) is available under the MIT
+  license, while [Pandoc](http://pandoc.org/) is released under the GPL.
+
+## ⭐ Star History
+
+This project _really_ started out as a joke -- although this is something I've done too many times. I'm always
+amazed at how many people have starred this repo. 🤩
+
+<a href="https://www.star-history.com/#bradmontgomery/word2html&type=date&legend=top-left">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=bradmontgomery/word2html&type=date&theme=dark&legend=top-left" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=bradmontgomery/word2html&type=date&legend=top-left" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=bradmontgomery/word2html&type=date&legend=top-left" />
+ </picture>
+</a>

word2html-0.4.0/README.md

@@ -0,0 +1,54 @@
+# 🌟 Convert a Word Doc to html
+
+## 🚀 Quick Start with uvx
+
+The easiest way to run word2html without installing is using `uvx`:
+
+    uvx word2html /path/to/MyGloriousDoc.docx
+
+This will give you a new file, `/path/to/MyGloriousDoc.html`, that's (hopefully)
+decent-looking html.
+
+## 💾 Installation
+
+To install with uv:
+
+    uv tool install word2html
+
+Or with pip:
+
+    pip install word2html
+
+Then run:
+
+    word2html /path/to/MyGloriousDoc.docx
+
+## 🧪 Note on tests & versions
+
+- This project has NO TESTS! (feel free to add some of you think it should).
+- This project requires Python 3.12 or greater
+
+## 📝 Note on Licenses
+
+While this code is MIT-licensed, it uses boty pypandoc and pytidylib, both of
+which depend on other software that may not be MIT-licensed and must be installed
+for this to work.
+
+* [pytidylib](https://pypi.python.org/pypi/pytidylib/) is available under the
+  MIT license, and [Tidy](http://tidy.sourceforge.net/#license) is available
+  under an MIT-like license
+* [pypandoc](https://pypi.python.org/pypi/pypandoc/) is available under the MIT
+  license, while [Pandoc](http://pandoc.org/) is released under the GPL.
+
+## ⭐ Star History
+
+This project _really_ started out as a joke -- although this is something I've done too many times. I'm always
+amazed at how many people have starred this repo. 🤩
+
+<a href="https://www.star-history.com/#bradmontgomery/word2html&type=date&legend=top-left">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=bradmontgomery/word2html&type=date&theme=dark&legend=top-left" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=bradmontgomery/word2html&type=date&legend=top-left" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=bradmontgomery/word2html&type=date&legend=top-left" />
+ </picture>
+</a>

word2html-0.4.0/pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "word2html"
+version = "0.4.0"
+description = "A quick and dirty script to convert a Word (docx) document to html."
+readme = "README.md"
+requires-python = ">=3.12"
+license = { text = "MIT" }
+keywords = ["word", "to", "html"]
+authors = [
+    { name = "Brad Montgomery", email = "brad@bradmontgomery.net" }
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "License :: OSI Approved :: MIT License",
+    "Intended Audience :: Developers",
+    "Topic :: Text Processing",
+    "Topic :: Utilities",
+]
+dependencies = [
+    "pypandoc>=1.16.2",
+    "pytidylib>=0.3.2",
+]
+
+[project.urls]
+Homepage = "https://github.com/bradmontgomery/word2html"
+
+[project.scripts]
+word2html = "word2html.main:main"
+
+[tool.uv]
+dev-dependencies = []

word2html-0.4.0/word2html/__init__.py

@@ -0,0 +1,20 @@
+"""word2html - Convert Word documents to HTML.
+
+Copyright (c) 2025, Brad Montgomery <brad@bradmontgomery.net>
+Licensed under the MIT License. See LICENSE.txt for details.
+"""
+
+try:
+    from importlib.metadata import version, PackageNotFoundError
+    try:
+        __version__ = version("word2html")
+    except PackageNotFoundError:
+        __version__ = "0.0.0+dev"
+except ImportError:
+    __version__ = "0.0.0+dev"
+
+VERSION = __version__
+
+from .main import convert_to_html
+
+__all__ = ["convert_to_html", "__version__", "VERSION"]

word2html-0.4.0/word2html/main.py

@@ -0,0 +1,85 @@
+"""Quick & dirty script to convert a Word Docx file to HTML.
+
+Copyright (c) 2025, Brad Montgomery <brad@bradmontgomery.net>
+Licensed under the MIT License. See LICENSE.txt for details.
+"""
+
+import argparse
+import os
+import sys
+from pathlib import Path
+
+try:
+    import pypandoc
+    from tidylib import tidy_document
+except ImportError as e:
+    print(f"\n\nError: Missing required dependency: {e.name}\n", file=sys.stderr)
+    print("Install dependencies with: uv pip install pypandoc pytidylib\n", file=sys.stderr)
+    sys.exit(1)
+
+
+def convert_to_html(filename: str) -> None:
+    """Convert a Word document to HTML.
+    
+    Args:
+        filename: Path to the Word document to convert.
+        
+    Raises:
+        FileNotFoundError: If the input file doesn't exist.
+        ValueError: If the input file is not a .docx file.
+    """
+    input_path = Path(filename)
+    
+    # Validate input file
+    if not input_path.exists():
+        raise FileNotFoundError(f"File not found: {filename}")
+    
+    if input_path.suffix.lower() != ".docx":
+        raise ValueError(f"Expected .docx file, got: {input_path.suffix}")
+    
+    # Do the conversion with pandoc
+    output = pypandoc.convert_file(str(input_path), "html")
+
+    # Clean up with tidy
+    output, errors = tidy_document(
+        output,
+        options={
+            "numeric-entities": 1,
+            "wrap": 80,
+        },
+    )
+    
+    if errors:
+        print(f"Tidy warnings/errors:\n{errors}", file=sys.stderr)
+
+    # Replace smart quotes with HTML entities
+    output = output.replace("\u2018", "&lsquo;").replace("\u2019", "&rsquo;")
+    output = output.replace("\u201c", "&ldquo;").replace("\u201d", "&rdquo;")
+
+    # Write the output
+    output_path = input_path.with_suffix(".html")
+    output_path.write_text(output, encoding="utf-8")
+
+    print(f"Done! Output written to: {output_path}")
+
+
+def main() -> None:
+    """Main entry point for the command-line interface."""
+    parser = argparse.ArgumentParser(
+        description="Convert a Word document to an HTML document."
+    )
+    parser.add_argument("path", type=str, help="Path to your Word document (.docx)")
+    args = parser.parse_args()
+    
+    try:
+        convert_to_html(args.path)
+    except (FileNotFoundError, ValueError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+    except Exception as e:
+        print(f"Unexpected error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

word2html-0.2.0/MANIFEST.in

@@ -1,2 +0,0 @@
-include LICENSE.txt README.md
-recursive-include word2html *.py

word2html-0.2.0/PKG-INFO

@@ -1,45 +0,0 @@
-Metadata-Version: 1.1
-Name: word2html
-Version: 0.2.0
-Summary: A quick and dirty script to convert a Word (docx) document to html.
-Home-page: https://github.com/bradmontgomery/word2html
-Author: Brad Montgomery
-Author-email: brad@bradmontgomery.net
-License: MIT
-Description: Convert a Word Doc to html
-        ==========================
-        
-        
-        To install, run:
-        
-            pip install word2html
-        
-        This will give you a command-line script, which you can run:
-        
-            $ word2html /path/to/MyGloriousDoc.docx
-        
-        This will give you a new file, `/path/to/MyGloriousDoc.html`, that's (hopefully)
-        decent-looking html.
-        
-        
-        Notes
-        -----
-        
-        While this code is MIT-licensed, it uses boty pypandoc and pytidylib, both of
-        which depend on other software that may not be MIT-licensed and must be installed
-        for this to work.
-        
-        * [pytidylib](https://pypi.python.org/pypi/pytidylib/) is available under the
-          MIT license, and [Tidy](http://tidy.sourceforge.net/#license) is available
-          under an MIT-like license
-        * [pypandoc](https://pypi.python.org/pypi/pypandoc/) is available under the MIT
-          license, while [Pandoc](http://pandoc.org/) is released under the GPL.
-        
-        
-Keywords: word to html
-Platform: UNKNOWN
-Classifier: Development Status :: 3 - Alpha
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Text Processing
-Classifier: Topic :: Utilities

word2html-0.2.0/README.md

@@ -1,29 +0,0 @@
-Convert a Word Doc to html
-==========================
-
-
-To install, run:
-
-    pip install word2html
-
-This will give you a command-line script, which you can run:
-
-    $ word2html /path/to/MyGloriousDoc.docx
-
-This will give you a new file, `/path/to/MyGloriousDoc.html`, that's (hopefully)
-decent-looking html.
-
-
-Notes
------
-
-While this code is MIT-licensed, it uses boty pypandoc and pytidylib, both of
-which depend on other software that may not be MIT-licensed and must be installed
-for this to work.
-
-* [pytidylib](https://pypi.python.org/pypi/pytidylib/) is available under the
-  MIT license, and [Tidy](http://tidy.sourceforge.net/#license) is available
-  under an MIT-like license
-* [pypandoc](https://pypi.python.org/pypi/pypandoc/) is available under the MIT
-  license, while [Pandoc](http://pandoc.org/) is released under the GPL.
-

word2html-0.2.0/setup.cfg

@@ -1,5 +0,0 @@
-[egg_info]
-tag_build = 
-tag_date = 0
-tag_svn_revision = 0
-

word2html-0.2.0/setup.py

@@ -1,45 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-"""Setup script for python-bitbucket."""
-
-from setuptools import setup
-from word2html import VERSION
-
-SHORT_DESC = (
-    "A quick and dirty script to convert a Word "
-    "(docx) document to html."
-)
-
-setup(
-    name='word2html',
-    version=VERSION,
-    description=SHORT_DESC,
-    long_description=open('README.md').read(),
-    keywords='word to html',
-    author='Brad Montgomery',
-    author_email='brad@bradmontgomery.net',
-    url='https://github.com/bradmontgomery/word2html',
-    license='MIT',
-    packages=['word2html'],
-    include_package_data=True,
-    package_data={'': ['README.md', 'LICENSE.txt']},
-    zip_safe=False,
-    install_requires=[
-        'pypandoc',
-        'pytidylib',
-    ],
-    entry_points={
-        'console_scripts': [
-            'word2html = word2html.main:main',
-        ],
-    },
-    # Get strings from http://pypi.python.org/pypi?%3Aaction=list_classifiers
-    classifiers=[
-        'Development Status :: 3 - Alpha',
-        'License :: OSI Approved :: MIT License',
-        'Intended Audience :: Developers',
-        'Topic :: Text Processing',
-        'Topic :: Utilities',
-    ],
-)

word2html-0.2.0/word2html/__init__.py

@@ -1,4 +0,0 @@
-__version__ = '0.2.0'
-VERSION = __version__
-
-from .main import convert_to_html

word2html-0.2.0/word2html/main.py

@@ -1,51 +0,0 @@
-"""
-Quick & dirt script to convert a Word Docx file to HTML.
-
-Requires pypandoc pytidylib  (see requirements.txt)
-
-"""
-import os
-import sys
-try:
-    import pypandoc
-    from tidylib import tidy_document
-except ImportError:
-    print("\n\nRequires pypandoc and pytidylib. See requirements.txt\n\n")
-
-
-def convert_to_html(filename):
-    # Do the conversion with pandoc
-    output = pypandoc.convert(filename, 'html')
-
-    # Clean up with tidy...
-    output, errors = tidy_document(output,  options={
-        'numeric-entities': 1,
-        'wrap': 80,
-    })
-    print(errors)
-
-    # replace smart quotes.
-    output = output.replace(u"\u2018", '‘').replace(u"\u2019", '’')
-    output = output.replace(u"\u201c", "“").replace(u"\u201d", "”")
-
-    # write the output
-    filename, ext = os.path.splitext(filename)
-    filename = "{0}.html".format(filename)
-    with open(filename, 'w') as f:
-        # Python 2 "fix". If this isn't a string, encode it.
-        if type(output) is not str:
-            output = output.encode('utf-8')
-        f.write(output)
-
-    print("Done! Output written to: {}\n".format(filename))
-
-
-def main():
-    if len(sys.argv) == 2:
-        convert_to_html(sys.argv[1])
-    else:
-        print("\nUSAGE: word2html <filename>\n")
-
-
-if __name__ == "__main__":
-    main()

word2html-0.2.0/word2html.egg-info/PKG-INFO

@@ -1,45 +0,0 @@
-Metadata-Version: 1.1
-Name: word2html
-Version: 0.2.0
-Summary: A quick and dirty script to convert a Word (docx) document to html.
-Home-page: https://github.com/bradmontgomery/word2html
-Author: Brad Montgomery
-Author-email: brad@bradmontgomery.net
-License: MIT
-Description: Convert a Word Doc to html
-        ==========================
-        
-        
-        To install, run:
-        
-            pip install word2html
-        
-        This will give you a command-line script, which you can run:
-        
-            $ word2html /path/to/MyGloriousDoc.docx
-        
-        This will give you a new file, `/path/to/MyGloriousDoc.html`, that's (hopefully)
-        decent-looking html.
-        
-        
-        Notes
-        -----
-        
-        While this code is MIT-licensed, it uses boty pypandoc and pytidylib, both of
-        which depend on other software that may not be MIT-licensed and must be installed
-        for this to work.
-        
-        * [pytidylib](https://pypi.python.org/pypi/pytidylib/) is available under the
-          MIT license, and [Tidy](http://tidy.sourceforge.net/#license) is available
-          under an MIT-like license
-        * [pypandoc](https://pypi.python.org/pypi/pypandoc/) is available under the MIT
-          license, while [Pandoc](http://pandoc.org/) is released under the GPL.
-        
-        
-Keywords: word to html
-Platform: UNKNOWN
-Classifier: Development Status :: 3 - Alpha
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Text Processing
-Classifier: Topic :: Utilities

word2html-0.2.0/word2html.egg-info/SOURCES.txt

@@ -1,13 +0,0 @@
-LICENSE.txt
-MANIFEST.in
-README.md
-setup.py
-word2html/__init__.py
-word2html/main.py
-word2html.egg-info/PKG-INFO
-word2html.egg-info/SOURCES.txt
-word2html.egg-info/dependency_links.txt
-word2html.egg-info/entry_points.txt
-word2html.egg-info/not-zip-safe
-word2html.egg-info/requires.txt
-word2html.egg-info/top_level.txt

word2html-0.2.0/word2html.egg-info/dependency_links.txt

@@ -1 +0,0 @@
-

word2html-0.2.0/word2html.egg-info/entry_points.txt

@@ -1,3 +0,0 @@
-[console_scripts]
-word2html = word2html.main:main
-

word2html-0.2.0/word2html.egg-info/not-zip-safe

@@ -1 +0,0 @@
-

word2html-0.2.0/word2html.egg-info/requires.txt

@@ -1,2 +0,0 @@
-pypandoc
-pytidylib

word2html-0.2.0/word2html.egg-info/top_level.txt

@@ -1 +0,0 @@
-word2html