docstudio 0.2.0__py3-none-any.whl

docstudio-0.2.0.dist-info/METADATA

@@ -0,0 +1,223 @@
+Metadata-Version: 2.4
+Name: docstudio
+Version: 0.2.0
+Summary: Bidirectional, Markdown-centric document conversion: reverse (X->Markdown) like markitdown, plus high-fidelity forward export (Markdown->PDF/Word/LaTeX/EPUB/Excel) and optional VLM image recognition.
+Project-URL: Homepage, https://github.com/Sudo-Biao/docstudio
+Project-URL: Repository, https://github.com/Sudo-Biao/docstudio
+Project-URL: Issues, https://github.com/Sudo-Biao/docstudio/issues
+Author-email: biaoli <biaoli@swufe.edu.cn>
+License: MIT
+License-File: LICENSE
+Keywords: conversion,document,docx,epub,latex,markdown,markitdown,ocr,pdf,vlm
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Office/Business
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.9
+Requires-Dist: markdown>=3.5
+Requires-Dist: markdownify>=0.11
+Provides-Extra: all
+Requires-Dist: ebooklib; extra == 'all'
+Requires-Dist: mammoth; extra == 'all'
+Requires-Dist: markitdown[all]; extra == 'all'
+Requires-Dist: openpyxl; extra == 'all'
+Requires-Dist: pdfminer-six; extra == 'all'
+Requires-Dist: pillow; extra == 'all'
+Requires-Dist: pymupdf; extra == 'all'
+Requires-Dist: pypdf; extra == 'all'
+Requires-Dist: pytesseract; extra == 'all'
+Requires-Dist: python-docx; extra == 'all'
+Requires-Dist: python-pptx; extra == 'all'
+Requires-Dist: requests; extra == 'all'
+Provides-Extra: llm
+Requires-Dist: requests; extra == 'llm'
+Provides-Extra: markitdown
+Requires-Dist: markitdown[all]; extra == 'markitdown'
+Provides-Extra: ocr
+Requires-Dist: pillow; extra == 'ocr'
+Requires-Dist: pymupdf; extra == 'ocr'
+Requires-Dist: pytesseract; extra == 'ocr'
+Provides-Extra: office
+Requires-Dist: ebooklib; extra == 'office'
+Requires-Dist: mammoth; extra == 'office'
+Requires-Dist: openpyxl; extra == 'office'
+Requires-Dist: python-docx; extra == 'office'
+Requires-Dist: python-pptx; extra == 'office'
+Provides-Extra: pdf
+Requires-Dist: pdfminer-six; extra == 'pdf'
+Requires-Dist: pypdf; extra == 'pdf'
+Provides-Extra: pdf-chrome
+Requires-Dist: playwright; extra == 'pdf-chrome'
+Provides-Extra: pdf-weasy
+Requires-Dist: weasyprint; extra == 'pdf-weasy'
+Description-Content-Type: text/markdown
+
+# DocumentStudio (Python)
+
+A **bidirectional, Markdown-centric** document converter — a Python library and
+CLI in the spirit of Microsoft's [`markitdown`](https://github.com/microsoft/markitdown),
+but going **both ways**:
+
+| Direction | Formats | Notes |
+|-----------|---------|-------|
+| **Reverse** `X → Markdown` | PDF, Word, PPT, Excel, EPUB, HTML, CSV/TSV, JSON, ZIP, images | like markitdown; can *delegate to* markitdown when installed |
+| **Forward** `Markdown → X` | HTML, **PDF**, **Word (.docx)**, **LaTeX**, EPUB, Excel (.xlsx), text | high-fidelity export — the part markitdown does **not** do |
+| **AI / VLM** | image & scanned-PDF recognition, "smart cleanup" | any OpenAI-compatible endpoint; vision model optional |
+| **AI assistant** | polish, translate, summarise, expand, continue, grammar, formalise, titles, outline, fix-LaTeX, free-form | one-shot ops on a document |
+| **Toolbox** | table of contents, merge PDFs, extract images | headless, no browser |
+| **Templates** | academic, techdoc, minutes, readme, weekly, blog | ready-to-edit Markdown |
+
+The design mirrors markitdown's: a small core, a converter **registry** that's open
+for extension, and **optional dependency extras** so a minimal install still works.
+
+## Install
+
+```bash
+pip install docstudio                 # core: csv/tsv/json/html  +  md→html/latex/text
+pip install "docstudio[office]"       # docx, pptx, xlsx, epub
+pip install "docstudio[pdf]"          # PDF text extraction (pdfminer.six)
+pip install "docstudio[ocr]"          # scanned-PDF / image OCR (PyMuPDF, pytesseract)
+pip install "docstudio[llm]"          # AI cleanup + VLM (requests)
+pip install "docstudio[markitdown]"   # reuse Microsoft markitdown for the reverse path
+pip install "docstudio[all]"
+```
+
+For **Markdown → PDF/DOCX/EPUB** with the best fidelity, install
+[`pandoc`](https://pandoc.org) plus a TeX engine (`xelatex`):
+```bash
+sudo apt install pandoc texlive-xetex texlive-latex-recommended fonts-noto-cjk
+```
+PDF also has two pure-Python backends as fallbacks: `weasyprint`
+(`docstudio[pdf-weasy]`) and headless-Chrome via `playwright`
+(`docstudio[pdf-chrome]`, full KaTeX math).
+
+## Library
+
+```python
+from docstudio import DocumentStudio
+ds = DocumentStudio()                       # use_markitdown=True by default
+
+# anything → Markdown
+md = ds.to_markdown("report.pdf")
+md = ds.to_markdown("slides.pptx")
+
+# Markdown → anything (non-md inputs are auto-converted first)
+ds.convert("paper.md",  to="pdf",   out="paper.pdf")
+ds.convert("paper.md",  to="docx",  out="paper.docx")
+ds.convert("scan.pdf",  to="docx",  out="scan.docx")   # PDF → md → docx
+ds.convert("table.png", to="xlsx",  out="table.xlsx")  # image → md → xlsx
+```
+
+### AI + Vision (VLM)
+
+```python
+from docstudio import DocumentStudio
+from docstudio.llm import LLM
+
+llm = LLM(base_url="https://api.openai.com", api_key="sk-...",
+          model="gpt-4o-mini", vlm_model="gpt-4o")
+
+print(LLM.fetch_models("https://api.openai.com", "sk-..."))   # pick from the list
+
+ds = DocumentStudio(llm=llm)
+md = ds.to_markdown("photographed_table.jpg")   # recognised by the vision model
+md = ds.to_markdown("scanned_book.pdf")         # page-by-page VLM when no text layer
+md = llm.cleanup_markdown(rough_text)           # turn messy OCR into clean Markdown
+```
+
+## AI assistant (operate on a document)
+
+One-shot AI operations on Markdown/text — the *AI Assistant* from the web app.
+Needs an `llm` (any OpenAI-compatible endpoint).
+
+```python
+from docstudio import DocumentStudio
+from docstudio.llm import LLM
+
+# any OpenAI-compatible endpoint — OpenAI, DeepSeek, vLLM, Ollama, a gateway…
+# you choose base_url + model; nothing is hard-coded to a provider
+ds = DocumentStudio(llm=LLM(base_url="https://api.openai.com",
+                            api_key="sk-...", model="gpt-4o-mini"))
+
+ds.assist(md, action="polish")     # 润色
+ds.assist(md, action="to_en")      # 翻译成英文（to_zh 反之）
+ds.assist(md, action="summary")    # 摘要
+ds.assist(md, action="outline")    # 生成大纲
+ds.assist(md, instruction="把所有表格改成要点列表")   # 自由指令
+
+DocumentStudio.assist_actions()
+# polish, to_en, to_zh, summary, expand, condense, continue,
+# grammar, formal, titles, outline, fix_latex
+```
+
+## Toolbox
+
+```python
+ds.generate_toc(md)                              # insert a Markdown table of contents
+ds.merge_pdfs(["a.pdf", "b.pdf"], "all.pdf")     # concatenate PDFs (needs pypdf)
+ds.extract_images("report.pdf", "./imgs")        # pull embedded images out (PDF/DOCX/PPTX/EPUB)
+```
+
+## Templates
+
+Six ready-to-edit Markdown templates: `academic`, `techdoc`, `minutes`,
+`readme`, `weekly`, `blog`.
+
+```python
+ds.templates()                # {slug: (title, description)}
+body = ds.template("academic")
+```
+
+## CLI
+
+```bash
+docstudio report.pdf                      # → report.md   (prints to stdout)
+docstudio report.pdf -o out.md
+cat report.pdf | docstudio                # stdin → stdout
+docstudio paper.md --to pdf -o paper.pdf  # Markdown → anything
+docstudio scan.pdf --to docx              # PDF → md → docx
+docstudio photo.jpg --vlm-model gpt-4o --base-url https://api.openai.com --api-key sk-...
+docstudio --list-formats
+
+docstudio paper.md --toc -o paper.md                     # insert a table of contents
+docstudio notes.md --assist polish --base-url https://api.openai.com --model gpt-4o-mini --api-key sk-... -o clean.md
+docstudio notes.md --instruction "翻译成英文" --base-url https://api.openai.com --model gpt-4o-mini --api-key sk-... -o en.md
+docstudio --merge a.pdf b.pdf -o all.pdf                 # merge PDFs
+docstudio report.pdf --extract-images ./imgs             # pull out images
+docstudio --template academic                            # print a template
+docstudio --list-templates
+```
+
+## Extending
+
+Register your own converter — exactly how the built-ins are defined:
+
+```python
+from docstudio.core import registry
+
+@registry.ingester("rtf")
+def rtf_to_md(source, ds=None, **opts):
+    ...
+    return markdown_text
+
+@registry.exporter("rst")
+def md_to_rst(md, out=None, ds=None, **opts):
+    ...
+    return out
+```
+
+## Relationship to markitdown
+
+`markitdown` is excellent at `X → Markdown` for LLM pipelines. DocumentStudio
+**reuses** it for that direction when present (`use_markitdown=True`), and adds the
+missing half: turning Markdown back into polished, human-facing **PDF / Word /
+LaTeX / EPUB / Excel**, plus a vision-model path for images and scanned PDFs.
+
+MIT licensed.

docstudio-0.2.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+docstudio/__init__.py,sha256=kVGwi7_703NTHmheC-wK-84ohgw9q57xy_YS1ZvoX1I,1683
+docstudio/assistant.py,sha256=1ybE7YRdZqzub5FQKyDcNe9o7xfL8t_SAFiTP33tW_E,4260
+docstudio/cli.py,sha256=DByz3ZO6tDGpDq1wYENpDIVEWN-Tu-x6Bqr18emVUVQ,6244
+docstudio/core.py,sha256=LXJXe40QiTjqcbVg4b5BbWVdftoo3m9o-KgUROPwv6c,6985
+docstudio/export.py,sha256=vtTZZ5SdDsthdl9fEVyRPdtzpNKHaWJeEP32axFVx-8,8184
+docstudio/ingest.py,sha256=15dWoxO1911CRgHsB1qF41fSJnFmn_5mrofhGUIxPc0,7429
+docstudio/latex.py,sha256=yre1Quqa9VIKSH1w7Bih0umgK4XJBhpcSbUhofKcSV0,4966
+docstudio/llm.py,sha256=WIlB1586XjZNlg0meCCbmy_DHVdkng4EqIDgmIkUrCI,4997
+docstudio/templates.py,sha256=ZxMwGITtHCvuAXrPb-XH9RlT74zASBEHTT4rpVhQPPc,3371
+docstudio/tools.py,sha256=IbfPUMEgmvJUhalv17AzCsyAcIGksM7BVT5PikUHtH0,3873
+docstudio-0.2.0.dist-info/METADATA,sha256=Dm-Uz_jJZEf9L-Zn9HBBLlEXlV9iP1kFk1PYSbKC0Uo,9074
+docstudio-0.2.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+docstudio-0.2.0.dist-info/entry_points.txt,sha256=_mHuZtnxd71tNH1cIQsnY0-zM_xkDyojB4TXl661zBs,49
+docstudio-0.2.0.dist-info/licenses/LICENSE,sha256=H8UokzgF-0yyokPYTdb8eEyqs2apQlLrGKAsNKT_yWo,1063
+docstudio-0.2.0.dist-info/RECORD,,

docstudio-0.2.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.30.1
+Root-Is-Purelib: true
+Tag: py3-none-any

docstudio-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+docstudio = docstudio.cli:main

docstudio-0.2.0.dist-info/licenses/LICENSE

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