multi-convert 0.1.0__tar.gz

multi_convert-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) [2026] [Cobra Chicken]
+
+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 the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

multi_convert-0.1.0/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: multi_convert
+Version: 0.1.0
+Summary: A python package for converting multiple document formats
+Home-page: https://github.com/tasteslikecobrachicken/multi_convert
+Author: Cobra Chicken
+Author-email: Cobra Chicken <tasteslikecobrachicken@gmail.com>
+Project-URL: Homepage, https://github.com/tasteslikecobrachicken/multi_convert
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: markdown>=3.5
+Requires-Dist: markdown-pdf>=1.4
+Requires-Dist: html2text>=2024.2.26
+Requires-Dist: pypdf>=4.0
+Provides-Extra: test
+Requires-Dist: pytest>=8; extra == "test"
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# multi_convert
+
+Python package for converting document formats between Markdown, HTML, and PDF.
+
+## Installation
+
+```bash
+pip install multi_convert
+```
+
+Requires Python 3.10 or newer.
+
+## Usage
+
+### Library
+
+```python
+from multi_convert import convert
+
+convert("notes.md", "notes.pdf")
+convert("page.html", "page.md")
+```
+
+Both formats are inferred from the file extensions. `convert` returns the output
+path and raises `ConversionError` if the input is missing or either extension is
+not one of `.md`, `.html`, or `.pdf`.
+
+### Command line
+
+```bash
+multi-convert notes.md notes.pdf
+```
+
+## Supported conversions
+
+| From | To |
+| --- | --- |
+| Markdown | HTML, PDF |
+| HTML | Markdown, PDF |
+| PDF | Markdown, HTML |
+
+Every conversion routes through Markdown as an intermediate representation.
+Because PDF text extraction recovers plain text only, converting *from* PDF
+loses headings, tables, and emphasis; the other five directions preserve
+structure.
+
+## License
+
+MIT

multi_convert-0.1.0/README.md

@@ -0,0 +1,49 @@
+# multi_convert
+
+Python package for converting document formats between Markdown, HTML, and PDF.
+
+## Installation
+
+```bash
+pip install multi_convert
+```
+
+Requires Python 3.10 or newer.
+
+## Usage
+
+### Library
+
+```python
+from multi_convert import convert
+
+convert("notes.md", "notes.pdf")
+convert("page.html", "page.md")
+```
+
+Both formats are inferred from the file extensions. `convert` returns the output
+path and raises `ConversionError` if the input is missing or either extension is
+not one of `.md`, `.html`, or `.pdf`.
+
+### Command line
+
+```bash
+multi-convert notes.md notes.pdf
+```
+
+## Supported conversions
+
+| From | To |
+| --- | --- |
+| Markdown | HTML, PDF |
+| HTML | Markdown, PDF |
+| PDF | Markdown, HTML |
+
+Every conversion routes through Markdown as an intermediate representation.
+Because PDF text extraction recovers plain text only, converting *from* PDF
+loses headings, tables, and emphasis; the other five directions preserve
+structure.
+
+## License
+
+MIT

multi_convert-0.1.0/pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "multi_convert"
+version = "0.1.0"
+authors = [
+  { name="Cobra Chicken", email="tasteslikecobrachicken@gmail.com" },
+]
+description = "A python package for converting multiple document formats"
+readme = "README.md"
+requires-python = ">=3.10"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "markdown>=3.5",
+    "markdown-pdf>=1.4",
+    "html2text>=2024.2.26",
+    "pypdf>=4.0",
+]
+
+[project.optional-dependencies]
+test = ["pytest>=8"]
+
+[project.scripts]
+multi-convert = "multi_convert.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/tasteslikecobrachicken/multi_convert"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

multi_convert-0.1.0/setup.cfg

@@ -0,0 +1,7 @@
+[metadata]
+license_files = LICENSE
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

multi_convert-0.1.0/setup.py

@@ -0,0 +1,36 @@
+import os
+from setuptools import setup, find_packages
+
+this_directory = os.path.abspath(os.path.dirname(__file__))
+with open(os.path.join(this_directory, "README.md"), encoding="utf-8") as f:
+    long_description = f.read()
+
+setup(
+    name="multi_convert",
+    version="0.1.0",
+    author="Cobra Chicken",
+    author_email="tasteslikecobrachicken@gmail.com",
+    description="A python package for converting multiple document formats",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/tasteslikecobrachicken/multi_convert",
+    packages=find_packages(exclude=["tests", "tests.*"]),
+    python_requires=">=3.10",
+    install_requires=[
+        "markdown>=3.5",
+        "markdown-pdf>=1.4",
+        "html2text>=2024.2.26",
+        "pypdf>=4.0",
+    ],
+    extras_require={},
+    entry_points={
+        "console_scripts": [
+            "multi-convert=multi_convert.cli:main",
+        ],
+    },
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+)

multi_convert-0.1.0/src/multi_convert/__init__.py

@@ -0,0 +1,5 @@
+"""Convert documents between Markdown, HTML, and PDF."""
+
+from .core import FORMATS, ConversionError, convert
+
+__all__ = ["FORMATS", "ConversionError", "convert"]

multi_convert-0.1.0/src/multi_convert/cli.py

@@ -0,0 +1,23 @@
+"""Command line interface for multi_convert."""
+
+import argparse
+from pathlib import Path
+
+from .core import ConversionError, convert
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        prog="multi-convert",
+        description="Convert documents between Markdown, HTML, and PDF.",
+    )
+    parser.add_argument("input", type=Path, help="File to convert")
+    parser.add_argument("output", type=Path, help="Destination file; the format is taken from its extension")
+    args = parser.parse_args()
+
+    try:
+        convert(args.input, args.output)
+    except ConversionError as error:
+        parser.exit(1, f"error: {error}\n")
+
+    print(f"Converted {args.input} -> {args.output}")

multi_convert-0.1.0/src/multi_convert/core.py

@@ -0,0 +1,90 @@
+"""Document conversion between Markdown, HTML, and PDF."""
+
+from pathlib import Path
+
+import html2text
+import markdown
+from markdown_pdf import MarkdownPdf, Section
+from pypdf import PdfReader
+
+FORMATS = ("md", "html", "pdf")
+
+_HTML_HEAD = """<!DOCTYPE html>
+<html>
+<head>
+<meta charset="utf-8">
+<style>
+  body { font-family: -apple-system, sans-serif; line-height: 1.6; max-width: 800px; margin: 2rem auto; padding: 0 1rem; }
+  code { background: #f4f4f4; padding: 2px 4px; border-radius: 4px; }
+  pre { background: #f4f4f4; padding: 1rem; overflow-x: auto; }
+  table { border-collapse: collapse; width: 100%; }
+  th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
+</style>
+</head>
+<body>
+"""
+
+_HTML_TAIL = """
+</body>
+</html>
+"""
+
+
+class ConversionError(Exception):
+    """Raised when a conversion cannot be performed."""
+
+
+def _format_of(path):
+    fmt = path.suffix.lower().lstrip(".")
+    if fmt not in FORMATS:
+        raise ConversionError(f"Unsupported format {path.suffix!r}; expected one of {', '.join(FORMATS)}")
+    return fmt
+
+
+def _read_md(path):
+    return path.read_text(encoding="utf-8")
+
+
+def _read_html(path):
+    handler = html2text.HTML2Text()
+    handler.ignore_links = False
+    return handler.handle(path.read_text(encoding="utf-8"))
+
+
+def _read_pdf(path):
+    pages = (page.extract_text() for page in PdfReader(path).pages)
+    return "\n\n".join(page for page in pages if page)
+
+
+def _write_md(content, path):
+    path.write_text(content, encoding="utf-8")
+
+
+def _write_html(content, path):
+    body = markdown.markdown(content, extensions=["tables", "fenced_code"])
+    path.write_text(_HTML_HEAD + body + _HTML_TAIL, encoding="utf-8")
+
+
+def _write_pdf(content, path):
+    pdf = MarkdownPdf(toc_level=2)
+    pdf.add_section(Section(content))
+    pdf.save(str(path))
+
+
+_READERS = {"md": _read_md, "html": _read_html, "pdf": _read_pdf}
+_WRITERS = {"md": _write_md, "html": _write_html, "pdf": _write_pdf}
+
+
+def convert(source, target):
+    """Convert ``source`` to ``target``, inferring both formats from file extensions.
+
+    Every conversion routes through Markdown as an intermediate representation, so
+    reading a PDF yields extracted plain text rather than structured markup.
+    """
+    source, target = Path(source), Path(target)
+    if not source.is_file():
+        raise ConversionError(f"Input file not found: {source}")
+
+    reader, writer = _READERS[_format_of(source)], _WRITERS[_format_of(target)]
+    writer(reader(source), target)
+    return target

multi_convert-0.1.0/src/multi_convert.egg-info/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: multi_convert
+Version: 0.1.0
+Summary: A python package for converting multiple document formats
+Home-page: https://github.com/tasteslikecobrachicken/multi_convert
+Author: Cobra Chicken
+Author-email: Cobra Chicken <tasteslikecobrachicken@gmail.com>
+Project-URL: Homepage, https://github.com/tasteslikecobrachicken/multi_convert
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: markdown>=3.5
+Requires-Dist: markdown-pdf>=1.4
+Requires-Dist: html2text>=2024.2.26
+Requires-Dist: pypdf>=4.0
+Provides-Extra: test
+Requires-Dist: pytest>=8; extra == "test"
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# multi_convert
+
+Python package for converting document formats between Markdown, HTML, and PDF.
+
+## Installation
+
+```bash
+pip install multi_convert
+```
+
+Requires Python 3.10 or newer.
+
+## Usage
+
+### Library
+
+```python
+from multi_convert import convert
+
+convert("notes.md", "notes.pdf")
+convert("page.html", "page.md")
+```
+
+Both formats are inferred from the file extensions. `convert` returns the output
+path and raises `ConversionError` if the input is missing or either extension is
+not one of `.md`, `.html`, or `.pdf`.
+
+### Command line
+
+```bash
+multi-convert notes.md notes.pdf
+```
+
+## Supported conversions
+
+| From | To |
+| --- | --- |
+| Markdown | HTML, PDF |
+| HTML | Markdown, PDF |
+| PDF | Markdown, HTML |
+
+Every conversion routes through Markdown as an intermediate representation.
+Because PDF text extraction recovers plain text only, converting *from* PDF
+loses headings, tables, and emphasis; the other five directions preserve
+structure.
+
+## License
+
+MIT

multi_convert-0.1.0/src/multi_convert.egg-info/SOURCES.txt

@@ -0,0 +1,16 @@
+LICENSE
+README.md
+pyproject.toml
+setup.cfg
+setup.py
+src/multi_convert/__init__.py
+src/multi_convert/cli.py
+src/multi_convert/core.py
+src/multi_convert.egg-info/PKG-INFO
+src/multi_convert.egg-info/SOURCES.txt
+src/multi_convert.egg-info/dependency_links.txt
+src/multi_convert.egg-info/entry_points.txt
+src/multi_convert.egg-info/requires.txt
+src/multi_convert.egg-info/top_level.txt
+tests/test_cli.py
+tests/test_convert.py

multi_convert-0.1.0/src/multi_convert.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

multi_convert-0.1.0/src/multi_convert.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+multi-convert = multi_convert.cli:main

multi_convert-0.1.0/src/multi_convert.egg-info/requires.txt

@@ -0,0 +1,7 @@
+markdown>=3.5
+markdown-pdf>=1.4
+html2text>=2024.2.26
+pypdf>=4.0
+
+[test]
+pytest>=8

multi_convert-0.1.0/src/multi_convert.egg-info/top_level.txt

@@ -0,0 +1 @@
+multi_convert

multi_convert-0.1.0/tests/test_cli.py

@@ -0,0 +1,68 @@
+import pytest
+
+from multi_convert.cli import main
+
+
+def run(monkeypatch, *args):
+    monkeypatch.setattr("sys.argv", ["multi-convert", *(str(a) for a in args)])
+    main()
+
+
+class TestSuccess:
+    def test_converts_file(self, monkeypatch, capsys, md_file, tmp_path):
+        target = tmp_path / "out.html"
+        run(monkeypatch, md_file, target)
+
+        assert target.is_file()
+        assert "<h1>Title</h1>" in target.read_text(encoding="utf-8")
+
+    def test_reports_the_conversion(self, monkeypatch, capsys, md_file, tmp_path):
+        target = tmp_path / "out.html"
+        run(monkeypatch, md_file, target)
+        out = capsys.readouterr().out
+
+        assert str(md_file) in out
+        assert str(target) in out
+
+
+class TestFailure:
+    def test_missing_input_exits_nonzero(self, monkeypatch, capsys, tmp_path):
+        with pytest.raises(SystemExit) as exc:
+            run(monkeypatch, tmp_path / "nope.md", tmp_path / "out.html")
+
+        assert exc.value.code == 1
+        assert "Input file not found" in capsys.readouterr().err
+
+    def test_unsupported_format_exits_nonzero(self, monkeypatch, capsys, md_file, tmp_path):
+        with pytest.raises(SystemExit) as exc:
+            run(monkeypatch, md_file, tmp_path / "out.docx")
+
+        assert exc.value.code == 1
+        assert "Unsupported format" in capsys.readouterr().err
+
+    def test_failure_prints_nothing_to_stdout(self, monkeypatch, capsys, md_file, tmp_path):
+        with pytest.raises(SystemExit):
+            run(monkeypatch, md_file, tmp_path / "out.docx")
+
+        assert capsys.readouterr().out == ""
+
+
+class TestArguments:
+    def test_missing_output_argument_is_rejected(self, monkeypatch, capsys, md_file):
+        with pytest.raises(SystemExit) as exc:
+            run(monkeypatch, md_file)
+
+        assert exc.value.code == 2
+
+    def test_no_arguments_is_rejected(self, monkeypatch, capsys):
+        with pytest.raises(SystemExit) as exc:
+            run(monkeypatch)
+
+        assert exc.value.code == 2
+
+    def test_help_exits_zero(self, monkeypatch, capsys):
+        with pytest.raises(SystemExit) as exc:
+            run(monkeypatch, "--help")
+
+        assert exc.value.code == 0
+        assert "Markdown, HTML, and PDF" in capsys.readouterr().out

multi_convert-0.1.0/tests/test_convert.py

@@ -0,0 +1,158 @@
+import pytest
+from pypdf import PdfReader
+
+from multi_convert import ConversionError, convert
+
+
+def pdf_text(path):
+    return "\n".join(page.extract_text() or "" for page in PdfReader(path).pages)
+
+
+class TestFromMarkdown:
+    def test_to_html_preserves_structure(self, md_file, tmp_path):
+        out = convert(md_file, tmp_path / "out.html")
+        html = out.read_text(encoding="utf-8")
+
+        assert "<h1>Title</h1>" in html
+        assert "<strong>bold</strong>" in html
+        assert '<a href="https://example.com">link</a>' in html
+        assert "<table>" in html and "<th>A</th>" in html
+        assert '<code class="language-python">' in html
+
+    def test_to_html_wraps_in_full_document(self, md_file, tmp_path):
+        html = convert(md_file, tmp_path / "out.html").read_text(encoding="utf-8")
+
+        assert html.startswith("<!DOCTYPE html>")
+        assert html.rstrip().endswith("</html>")
+        assert "<meta charset=\"utf-8\">" in html
+        assert "font-family" in html
+
+    def test_to_pdf_is_readable_and_keeps_text(self, md_file, tmp_path):
+        out = convert(md_file, tmp_path / "out.pdf")
+
+        assert out.read_bytes().startswith(b"%PDF-")
+        assert "Title" in pdf_text(out)
+
+
+class TestFromHtml:
+    def test_to_markdown_preserves_structure(self, html_file, tmp_path):
+        md = convert(html_file, tmp_path / "out.md").read_text(encoding="utf-8")
+
+        assert "# Title" in md
+        assert "**bold**" in md
+        assert "(https://example.com)" in md
+        assert "first" in md and "second" in md
+
+    def test_to_markdown_strips_html_tags(self, html_file, tmp_path):
+        md = convert(html_file, tmp_path / "out.md").read_text(encoding="utf-8")
+
+        assert "<h1>" not in md
+        assert "<strong>" not in md
+
+    def test_to_pdf_is_readable_and_keeps_text(self, html_file, tmp_path):
+        out = convert(html_file, tmp_path / "out.pdf")
+
+        assert out.read_bytes().startswith(b"%PDF-")
+        assert "Title" in pdf_text(out)
+
+
+class TestFromPdf:
+    def test_to_markdown_extracts_text(self, pdf_file, tmp_path):
+        md = convert(pdf_file, tmp_path / "out.md").read_text(encoding="utf-8")
+
+        assert "Title" in md
+        assert "plain paragraph text" in md
+
+    def test_to_html_wraps_extracted_text(self, pdf_file, tmp_path):
+        html = convert(pdf_file, tmp_path / "out.html").read_text(encoding="utf-8")
+
+        assert html.startswith("<!DOCTYPE html>")
+        assert "Title" in html
+
+    def test_extraction_is_lossy(self, pdf_file, tmp_path):
+        """PDF text extraction recovers no Markdown structure; see README."""
+        md = convert(pdf_file, tmp_path / "out.md").read_text(encoding="utf-8")
+
+        assert "# Title" not in md
+
+
+class TestRoundTrip:
+    def test_markdown_survives_html_round_trip(self, md_file, tmp_path):
+        html = convert(md_file, tmp_path / "mid.html")
+        md = convert(html, tmp_path / "back.md").read_text(encoding="utf-8")
+
+        assert "# Title" in md
+        assert "**bold**" in md
+        assert "(https://example.com)" in md
+
+
+class TestApi:
+    def test_returns_target_path(self, md_file, tmp_path):
+        target = tmp_path / "out.html"
+
+        assert convert(md_file, target) == target
+
+    def test_accepts_string_paths(self, md_file, tmp_path):
+        target = tmp_path / "out.html"
+        convert(str(md_file), str(target))
+
+        assert target.is_file()
+
+    def test_same_format_copies_content(self, md_file, tmp_path):
+        out = convert(md_file, tmp_path / "copy.md")
+
+        assert out.read_text(encoding="utf-8") == md_file.read_text(encoding="utf-8")
+
+    def test_overwrites_existing_target(self, md_file, tmp_path):
+        target = tmp_path / "out.html"
+        target.write_text("stale", encoding="utf-8")
+        convert(md_file, target)
+
+        assert "stale" not in target.read_text(encoding="utf-8")
+
+
+class TestErrors:
+    def test_missing_input(self, tmp_path):
+        with pytest.raises(ConversionError, match="Input file not found"):
+            convert(tmp_path / "nope.md", tmp_path / "out.html")
+
+    def test_directory_as_input(self, tmp_path):
+        with pytest.raises(ConversionError, match="Input file not found"):
+            convert(tmp_path, tmp_path / "out.html")
+
+    def test_unsupported_source_extension(self, tmp_path):
+        source = tmp_path / "sample.docx"
+        source.write_text("x", encoding="utf-8")
+
+        with pytest.raises(ConversionError, match="Unsupported format '.docx'"):
+            convert(source, tmp_path / "out.html")
+
+    def test_unsupported_target_extension(self, md_file, tmp_path):
+        with pytest.raises(ConversionError, match="Unsupported format '.docx'"):
+            convert(md_file, tmp_path / "out.docx")
+
+    def test_extensionless_input(self, tmp_path):
+        source = tmp_path / "sample"
+        source.write_text("x", encoding="utf-8")
+
+        with pytest.raises(ConversionError, match="Unsupported format"):
+            convert(source, tmp_path / "out.html")
+
+    def test_extension_case_is_ignored(self, tmp_path):
+        source = tmp_path / "sample.MD"
+        source.write_text("# Title\n", encoding="utf-8")
+        out = convert(source, tmp_path / "out.HTML")
+
+        assert "<h1>Title</h1>" in out.read_text(encoding="utf-8")
+
+    def test_missing_input_checked_before_extensions(self, tmp_path):
+        """A nonexistent file reports the missing path, not its extension."""
+        with pytest.raises(ConversionError, match="Input file not found"):
+            convert(tmp_path / "nope.docx", tmp_path / "out.html")
+
+    def test_no_output_written_on_failure(self, md_file, tmp_path):
+        target = tmp_path / "out.docx"
+        with pytest.raises(ConversionError):
+            convert(md_file, target)
+
+        assert not target.exists()