figcrop 0.1.0__py3-none-any.whl

figcrop-0.1.0.dist-info/METADATA

@@ -0,0 +1,218 @@
+Metadata-Version: 2.4
+Name: figcrop
+Version: 0.1.0
+Summary: High-quality figure extraction from dense research-paper PDFs
+Author: TadaLab Keio
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/tadalab-keio/figcrop
+Project-URL: Repository, https://github.com/tadalab-keio/figcrop
+Project-URL: Issues, https://github.com/tadalab-keio/figcrop/issues
+Keywords: pdf,figures,research-papers,layout-analysis,openvino
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Text Processing :: General
+Requires-Python: <3.14,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: mineru[core]<4,>=2
+Requires-Dist: openvino>=2025
+Requires-Dist: pymupdf>=1.24
+Requires-Dist: numpy
+Requires-Dist: pillow
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: mcp>=1.0
+Dynamic: license-file
+
+# figcrop
+
+Extract figures from research-paper PDFs by real figure number.
+
+figcrop uses MinerU's PP-DocLayoutV2 layout model for visual-region detection,
+then adds its own PDF-text and geometry logic to group panels into whole figures,
+remove captions, and trim page furniture. It is designed for dense semiconductor
+papers where simple heuristic tools often miss figures or split panels badly.
+
+## Features
+
+- Extract whole `Fig.N` outputs, including multi-panel figures, by the real figure
+  number found in the PDF text layer.
+- Keep figure-internal labels, process-flow text, axes, table borders, and panels,
+  while excluding the caption line.
+- Optionally include the matched caption text in the crop with
+  `caption_mode: "include"`.
+- Run as a persistent local HTTP server so the layout model is loaded once.
+- Use OpenVINO by default for fast local inference; torch backends remain available.
+- Trim modes:
+  - `mask` default: fast trim using an ignore mask for captions, page furniture,
+    neighbor frame lines, and thin anti-aliased edge bleed.
+  - `whiteband`: extra local whitespace snapping around the detector bbox. This is
+    slower but useful as a conservative safety mode for difficult crops.
+- Handles slide/poster-style cells in some PDFs by clipping giant page-level
+  fallback detections to the caption's local cell.
+
+## Requirements
+
+- Python 3.10-3.13. Windows is the main tested environment.
+- `uv` is recommended; the setup scripts install into the project-local `.venv`.
+- First run downloads model weights from Hugging Face.
+- OpenVINO GPU is the recommended default. NPU is not currently useful for this
+  RT-DETR layout model.
+
+## Setup
+
+Windows:
+
+```powershell
+powershell -ExecutionPolicy Bypass -File setup.ps1 -Device xpu
+```
+
+Linux/macOS:
+
+```bash
+bash setup.sh
+```
+
+`requirements.txt` is a manifest for the base packages. Device-specific torch
+packages are handled by the setup scripts.
+
+## Install From GitHub
+
+PyPI publishing is not required. Once packaging metadata is present, install the
+CLI directly from GitHub:
+
+```powershell
+pipx install git+https://github.com/tadalab-keio/figcrop.git
+```
+
+This exposes:
+
+```powershell
+figcrop help
+figcrop extract paper.pdf out --caption include
+figcrop serve
+figcrop-mcp
+```
+
+`figcrop` is the main human/agent CLI. `figcrop-mcp` is only needed when an MCP
+client should call figcrop as a registered tool instead of running shell
+commands.
+
+## Usage
+
+`<py>` means `.venv\Scripts\python.exe` on Windows or `.venv/bin/python` on Unix.
+
+For AI agents, the shortest path is:
+
+```powershell
+<py> figtools.py extract paper.pdf out auto caption=include
+```
+
+Then inspect the JPEGs and `out/figures.json`. Do not treat a successful command
+as a successful crop until representative images have been viewed.
+
+Start the local server:
+
+```powershell
+<py> figtools.py serve auto
+```
+
+Then request crops:
+
+```bash
+curl -s -X POST http://127.0.0.1:8077/extract \
+  -H "Content-Type: application/json" \
+  -d '{"pdf":"paper.pdf","out_dir":"out","figs":[1,2]}'
+```
+
+Useful request fields:
+
+- `figs`: real figure numbers to extract, for example `[1,2]`.
+- `top`: fallback positional extraction, for example `2` for the first two visual
+  regions per page.
+- `panels`: `true` to output detected panels/regions separately instead of whole
+  figures.
+- `trim_mode`: `"mask"` default or `"whiteband"`.
+- `caption_mode`: `"exclude"` default or `"include"` to include the matched
+  caption text below the figure.
+
+One-shot CLI:
+
+```powershell
+figcrop extract paper.pdf out auto
+figcrop extract paper.pdf out auto --figs 1,2
+figcrop extract paper.pdf out auto --top 3
+figcrop extract paper.pdf out auto --panels
+figcrop extract paper.pdf out_whiteband auto --trim whiteband
+figcrop extract paper.pdf out_with_captions auto --caption include
+figcrop help
+```
+
+Output files are JPEG crops plus a `figures.json` manifest in `out_dir`.
+
+## AI Connectors
+
+- OpenAPI/REST: start `figtools.py serve auto` and use `/openapi.json`.
+- MCP: install `requirements-mcp.txt` and run `figcrop_mcp.py`.
+
+See `CONNECTORS.md` for Claude/Codex/MCP examples and connector safety notes.
+
+## How It Works
+
+1. Render each PDF page at 150 dpi for layout detection.
+2. Run PP-DocLayoutV2 through OpenVINO or torch.
+3. Keep visual regions labeled `image`, `chart`, or `table`.
+4. Read `Fig.N` / `Table N` captions directly from the PDF text layer.
+5. Assign each region to the nearest same-column caption below it.
+6. Union regions with the same figure number into one whole-figure crop.
+7. If requested, extend the crop to the matched caption paragraph.
+8. Render the page at 300 dpi and crop with the selected trim mode.
+
+The numbering and whole-figure grouping are local geometry logic, not MinerU's
+full reading-order pipeline.
+
+## Performance
+
+For repeated extraction, use the server. In local tests, server mode avoids
+reloading the model for each request and is much faster than one-shot CLI runs,
+especially on one-page PDFs.
+
+For occasional use, the one-shot CLI is still practical: most ordinary papers
+finish in a few seconds on a local OpenVINO GPU setup, so running the server is a
+convenience rather than a hard requirement.
+
+The default `mask` trim mode is optimized for speed and is the recommended mode.
+`whiteband` is kept as a higher-conservatism option when local whitespace around
+the detector bbox matters more than speed.
+
+## Limitations
+
+- Very dense pages can still confuse region-to-caption assignment. Use `top=` or
+  `panels=true` as fallbacks.
+- Some PDFs contain slide/poster grids or decorative page furniture that can look
+  like a large table. figcrop has a local-cell fallback for common cases, but this
+  class of PDF may still need review.
+- Outputs are intended for local research workflow use. Always inspect crops when
+  building datasets or publications.
+
+## Agent Notes
+
+See `AGENTS.md`, `CLAUDE.md`, and `CONNECTORS.md` for machine-oriented commands,
+connector setup, verification checks, and commit attribution conventions. In
+short: prefer `caption=include` only when captions are needed, make montages for
+visual QA, and use `--force-with-lease` rather than plain `--force` if rewriting
+a pushed history.
+
+## License
+
+Apache-2.0. See `LICENSE`.
+
+Built on MinerU and OpenVINO. See `NOTICE` for attribution and dependency notes.

figcrop-0.1.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+figcrop_mcp.py,sha256=TicYwr45zS2g4FWGuqkOEXCuC7kiU-TSKsMCxNhLqiA,2148
+figtools.py,sha256=94_qEsPBST-wHlroGrFR9AqhS7pytmFHrT2KdXxDEFI,68096
+figcrop-0.1.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+figcrop-0.1.0.dist-info/licenses/NOTICE,sha256=0YmQ4CQZrPvQCaSAiR69_4R-5kVFG8JNdSbhja67ay4,869
+figcrop-0.1.0.dist-info/METADATA,sha256=An2wLNbdFIRApTCV8RR5xgxwTWXg7G_3rBMMSbS53ww,7790
+figcrop-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+figcrop-0.1.0.dist-info/entry_points.txt,sha256=oMtGsBhzvcsHXPILkPNd5nZpKmpScG2AwRm87zSfuzA,73
+figcrop-0.1.0.dist-info/top_level.txt,sha256=6h7DeGVaUgaTsAm7Lhw7K_exTr38hZVF_gU-OQVzwdQ,21
+figcrop-0.1.0.dist-info/RECORD,,

figcrop-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

figcrop-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+figcrop = figtools:main
+figcrop-mcp = figcrop_mcp:main

figcrop-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

figcrop-0.1.0.dist-info/licenses/NOTICE

@@ -0,0 +1,19 @@
+figcrop
+Copyright 2026 TadaLab (Keio University)
+
+Licensed under the Apache License, Version 2.0.
+
+This product depends on and is built upon third-party software:
+
+- MinerU (https://github.com/opendatalab/MinerU)
+  Licensed under the "MinerU Open Source License" (based on Apache 2.0 with
+  additional terms). figcrop uses MinerU's layout model (PP-DocLayoutV2) and
+  adapts a small portion of MinerU's detection post-processing logic and its
+  class-label list into figtools.py (the OpenVINO path). MinerU itself is not
+  redistributed here; it is installed as a dependency.
+
+- OpenVINO (https://github.com/openvinotoolkit/openvino) — Apache License 2.0.
+- PyMuPDF (https://github.com/pymupdf/PyMuPDF).
+
+Model weights (PP-DocLayoutV2 etc.) are downloaded at runtime from Hugging Face
+and are governed by their own licenses; they are not included in this repository.

figcrop-0.1.0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+figcrop_mcp
+figtools

figcrop_mcp.py

@@ -0,0 +1,84 @@
+"""Optional MCP server for figcrop.
+
+Run with:
+    python figcrop_mcp.py
+
+Requires:
+    uv pip install --python .venv\\Scripts\\python.exe -r requirements-mcp.txt
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+import figtools
+
+
+try:
+    from mcp.server.fastmcp import FastMCP
+except ImportError as exc:  # pragma: no cover - exercised only without optional deps
+    raise SystemExit(
+        "Missing optional MCP dependency. Install with:\n"
+        "  uv pip install --python .venv\\Scripts\\python.exe -r requirements-mcp.txt"
+    ) from exc
+
+
+mcp = FastMCP("figcrop")
+_MODEL_CACHE: dict[str, tuple[Any, str]] = {}
+
+
+def _model(device: str) -> tuple[Any, str]:
+    key = device or "auto"
+    if key not in _MODEL_CACHE:
+        _MODEL_CACHE[key] = figtools._engine(key)
+    return _MODEL_CACHE[key]
+
+
+@mcp.tool()
+def extract_figures(
+    pdf: str,
+    out_dir: str,
+    figs: list[int] | None = None,
+    top: int | None = None,
+    panels: bool = False,
+    trim_mode: str = "mask",
+    caption_mode: str = "exclude",
+    device: str = "auto",
+) -> dict[str, Any]:
+    """Extract figures/tables from a research-paper PDF.
+
+    Args:
+        pdf: Path to the input PDF.
+        out_dir: Directory where JPEG crops and figures.json will be written.
+        figs: Optional real Fig/Table numbers to extract.
+        top: Optional positional fallback: first N visual regions per page.
+        panels: Output detected regions/panels separately instead of whole figures.
+        trim_mode: "mask" (default) or "whiteband".
+        caption_mode: "exclude" (default) or "include".
+        device: Layout backend/device, usually "auto".
+    """
+    manifest = figtools.extract(
+        pdf,
+        out_dir,
+        model=_model(device),
+        figs=figs,
+        top=top,
+        panels=panels,
+        trim_mode=trim_mode,
+        caption_mode=caption_mode,
+    )
+    clean_out = out_dir.rstrip("/\\")
+    return {
+        "out_dir": out_dir,
+        "count": len(manifest),
+        "figures_json": f"{clean_out}\\figures.json",
+        "figures": manifest,
+    }
+
+
+def main():
+    mcp.run()
+
+
+if __name__ == "__main__":
+    main()