mdpack 0.0.1__tar.gz

mdpack-0.0.1/.gitignore

@@ -0,0 +1,9 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+build/
+dist/
+.venv/
+.pytest_cache/
+.ruff_cache/
+.DS_Store

mdpack-0.0.1/CHANGELOG.md

@@ -0,0 +1,13 @@
+# Changelog
+
+## 0.0.1 (2026-04-16)
+
+Placeholder release to reserve the `mdpack` name on PyPI. No functional code yet.
+
+Planned for 0.1.0:
+- DOCX → Markdown (pandoc-backed)
+- CSV → Markdown tables
+- XLSX → Markdown (one section per sheet)
+- `mdpack convert <path>` CLI with directory mirroring
+- Frontmatter injection (`source`, `converted_at`, `converter`)
+- Stripping inline base64 images

mdpack-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Andy Lei
+
+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.

mdpack-0.0.1/PKG-INFO

@@ -0,0 +1,64 @@
+Metadata-Version: 2.4
+Name: mdpack
+Version: 0.0.1
+Summary: Convert any directory of docs (DOCX, CSV, XLSX, PDF, PPTX, HTML) to clean Markdown.
+Project-URL: Homepage, https://github.com/andyleimc-source/mdpack
+Project-URL: Issues, https://github.com/andyleimc-source/mdpack/issues
+Author-email: Andy Lei <leimingcan@icloud.com>
+License: MIT
+License-File: LICENSE
+Keywords: converter,docx,llm,markdown,pdf,pptx,rag,xlsx
+Classifier: Development Status :: 1 - Planning
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.10
+Requires-Dist: click>=8.0
+Description-Content-Type: text/markdown
+
+# mdpack
+
+> Convert any directory of docs to clean Markdown, ready for RAG / LLM ingestion.
+
+> 🚧 **WIP.** `0.0.1` is a name placeholder on PyPI — real functionality lands in `0.1.0`.
+
+## What this will be
+
+A single CLI that walks a folder full of mixed-format documents (DOCX, CSV, XLSX, PDF, PPTX, HTML)
+and emits clean Markdown, mirroring the source directory structure. Designed to feed downstream
+RAG / LLM pipelines — in particular [mdrag](https://github.com/andyleimc-source/mdrag), a local
+semantic-search MCP server for Markdown folders.
+
+Why a separate tool? Conversion is a messy, format-specific problem (pandoc for DOCX, Docling for
+PDF, openpyxl for XLSX, and so on). Keeping it out of `mdrag` keeps both tools focused: `mdpack`
+produces Markdown, `mdrag` indexes Markdown.
+
+## Planned MVP (0.1.0)
+
+| Format | Backend | Status |
+|--------|---------|--------|
+| DOCX   | pandoc  | planned |
+| CSV    | stdlib  | planned |
+| XLSX   | openpyxl | planned |
+
+Later (0.2.0+): PDF (Docling, non-OCR), PPTX, HTML, EPUB.
+
+## Install (placeholder)
+
+```bash
+pip install mdpack
+mdpack --version      # 0.0.1 (placeholder — no conversion yet)
+```
+
+## Companion project
+
+- **[mdrag](https://github.com/andyleimc-source/mdrag)** — give any local Markdown folder a
+  semantic-search MCP server. Run `mdpack` first to convert mixed-format docs, then point `mdrag`
+  at the output directory.
+
+## License
+
+[MIT](./LICENSE)

mdpack-0.0.1/README.md

@@ -0,0 +1,43 @@
+# mdpack
+
+> Convert any directory of docs to clean Markdown, ready for RAG / LLM ingestion.
+
+> 🚧 **WIP.** `0.0.1` is a name placeholder on PyPI — real functionality lands in `0.1.0`.
+
+## What this will be
+
+A single CLI that walks a folder full of mixed-format documents (DOCX, CSV, XLSX, PDF, PPTX, HTML)
+and emits clean Markdown, mirroring the source directory structure. Designed to feed downstream
+RAG / LLM pipelines — in particular [mdrag](https://github.com/andyleimc-source/mdrag), a local
+semantic-search MCP server for Markdown folders.
+
+Why a separate tool? Conversion is a messy, format-specific problem (pandoc for DOCX, Docling for
+PDF, openpyxl for XLSX, and so on). Keeping it out of `mdrag` keeps both tools focused: `mdpack`
+produces Markdown, `mdrag` indexes Markdown.
+
+## Planned MVP (0.1.0)
+
+| Format | Backend | Status |
+|--------|---------|--------|
+| DOCX   | pandoc  | planned |
+| CSV    | stdlib  | planned |
+| XLSX   | openpyxl | planned |
+
+Later (0.2.0+): PDF (Docling, non-OCR), PPTX, HTML, EPUB.
+
+## Install (placeholder)
+
+```bash
+pip install mdpack
+mdpack --version      # 0.0.1 (placeholder — no conversion yet)
+```
+
+## Companion project
+
+- **[mdrag](https://github.com/andyleimc-source/mdrag)** — give any local Markdown folder a
+  semantic-search MCP server. Run `mdpack` first to convert mixed-format docs, then point `mdrag`
+  at the output directory.
+
+## License
+
+[MIT](./LICENSE)

mdpack-0.0.1/pyproject.toml

@@ -0,0 +1,41 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "mdpack"
+version = "0.0.1"
+description = "Convert any directory of docs (DOCX, CSV, XLSX, PDF, PPTX, HTML) to clean Markdown."
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.10"
+authors = [
+    {name = "Andy Lei", email = "leimingcan@icloud.com"}
+]
+keywords = ["markdown", "converter", "docx", "pdf", "xlsx", "pptx", "rag", "llm"]
+classifiers = [
+    "Development Status :: 1 - Planning",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Text Processing :: Markup :: Markdown",
+]
+dependencies = [
+    "click>=8.0",
+]
+
+[project.scripts]
+mdpack = "mdpack.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/andyleimc-source/mdpack"
+Issues = "https://github.com/andyleimc-source/mdpack/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/mdpack"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"

mdpack-0.0.1/src/mdpack/__init__.py

@@ -0,0 +1,3 @@
+"""mdpack — convert any directory of docs to clean Markdown."""
+
+__version__ = "0.0.1"

mdpack-0.0.1/src/mdpack/cli.py

@@ -0,0 +1,24 @@
+"""mdpack CLI entry point (placeholder)."""
+
+from __future__ import annotations
+
+import click
+
+from . import __version__
+
+
+@click.group(invoke_without_command=True)
+@click.version_option(__version__, prog_name="mdpack")
+@click.pass_context
+def main(ctx: click.Context) -> None:
+    """Convert any directory of docs to clean Markdown.
+
+    This is a 0.0.1 placeholder release to reserve the name on PyPI.
+    Real conversion commands will land in 0.1.0. Track progress at
+    https://github.com/andyleimc-source/mdpack.
+    """
+    if ctx.invoked_subcommand is None:
+        click.echo(
+            f"mdpack {__version__} — placeholder release, no conversion yet. "
+            "See https://github.com/andyleimc-source/mdpack for roadmap."
+        )