pdf-figure-table-extractor 0.1.0__tar.gz

pdf_figure_table_extractor-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,20 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+      - run: uv build
+      - run: uv publish --trusted-publishing always

pdf_figure_table_extractor-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,22 @@
+name: Tests
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - run: uv sync --locked --all-groups
+      - run: uv run ruff check .
+      - run: uv run pytest
+      - run: uv build

pdf_figure_table_extractor-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+.venv/
+.pytest_cache/
+.ruff_cache/
+__pycache__/
+dist/
+*.egg-info/
+output/
+.DS_Store

pdf_figure_table_extractor-0.1.0/.python-version

@@ -0,0 +1 @@
+3.11

pdf_figure_table_extractor-0.1.0/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.5
+Name: pdf-figure-table-extractor
+Version: 0.1.0
+Summary: Extract tightly cropped, high-resolution figures and tables from PDF files.
+Keywords: academic-papers,figure-extraction,pdf,table-extraction
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Utilities
+Requires-Python: >=3.11
+Requires-Dist: loguru<1,>=0.7
+Requires-Dist: pymupdf<2,>=1.26
+Description-Content-Type: text/markdown
+
+# PDF Figure and Table Extractor
+
+Extract labeled figures and tables from PDF files into tightly cropped,
+high-resolution PNG images. The extractor uses PDF-native captions, vector
+paths, embedded images, and text positions; it does not require OCR or a
+vision model for text-based PDFs.
+
+## Features
+
+- Extracts labeled `Figure`, `Fig.`, and `Table` regions.
+- Handles figure captions below content and table titles above or below content.
+- Supports vector figures, raster figures, ruled tables, and unruled tables.
+- Includes complete captions by default.
+- Produces a JSON manifest with page numbers, captions, crop boxes, and filenames.
+- Re-running into the same directory removes only files recorded by the previous manifest.
+
+## Installation
+
+Install the command-line tool with `uv`:
+
+```bash
+uv tool install pdf-figure-table-extractor
+```
+
+Or add it to a project:
+
+```bash
+uv add pdf-figure-table-extractor
+```
+
+## Usage
+
+```bash
+pdf-figure-table-extractor paper.pdf extracted-assets
+```
+
+The default resolution is 400 DPI. For larger output:
+
+```bash
+pdf-figure-table-extractor paper.pdf extracted-assets --dpi 600
+```
+
+To omit figure captions while keeping table titles:
+
+```bash
+pdf-figure-table-extractor paper.pdf extracted-assets --exclude-figure-captions
+```
+
+The Python API is also available:
+
+```python
+from pdf_figure_table_extractor import extract_assets
+
+assets = extract_assets("paper.pdf", "extracted-assets", dpi=400)
+```
+
+## Output
+
+```text
+extracted-assets/
+├── figure-001-1-page-001.png
+├── table-001-1-page-002.png
+└── manifest.json
+```
+
+`manifest.json` records the source PDF, DPI, detected caption, page number,
+crop box, and output filename for every asset.
+
+## Scope and limitations
+
+The extractor targets PDFs with machine-readable text and conventional labeled
+captions. Scanned documents, rotated captions, unusual caption formats, and
+figures spanning multiple pages may require OCR or manual correction. Always
+visually inspect extracted assets before using them in publications or reports.
+
+## Development
+
+```bash
+uv sync --all-groups
+uv run ruff check .
+uv run pytest
+uv build
+```
+
+Before publishing, choose and add an appropriate `LICENSE`, update the version,
+and add repository URLs to `pyproject.toml` after the GitHub repository exists.
+See [PUBLISHING.md](PUBLISHING.md) for the Trusted Publishing setup and release checklist.

pdf_figure_table_extractor-0.1.0/PUBLISHING.md

@@ -0,0 +1,49 @@
+# Publishing
+
+This project is configured for PyPI Trusted Publishing through GitHub Actions.
+No long-lived PyPI token is required.
+
+## Before the first release
+
+1. Choose a license, add a `LICENSE` file, and add its SPDX identifier to
+   `pyproject.toml`.
+2. Create the GitHub repository and push this directory as its root.
+3. Add the repository URLs to `pyproject.toml`, for example:
+
+   ```toml
+   [project.urls]
+   Homepage = "https://github.com/OWNER/pdf-figure-table-extractor"
+   Issues = "https://github.com/OWNER/pdf-figure-table-extractor/issues"
+   Source = "https://github.com/OWNER/pdf-figure-table-extractor"
+   ```
+
+4. On PyPI, create a pending trusted publisher for:
+   - PyPI project: `pdf-figure-table-extractor`
+   - GitHub owner and repository: the repository created above
+   - Workflow filename: `publish.yml`
+   - Environment name: `pypi`
+5. In the GitHub repository, create an environment named `pypi` and optionally
+   require manual approval for deployments.
+
+## Validate locally
+
+```bash
+uv sync --locked --all-groups
+uv run ruff check .
+uv run pytest
+uv build
+uvx --from twine twine check dist/*
+```
+
+## Release
+
+1. Update `version` in `pyproject.toml` and run `uv lock`.
+2. Commit the version change and create a matching tag such as `v0.1.0`.
+3. Create a GitHub Release from that tag.
+4. The `Publish to PyPI` workflow builds the distributions and runs:
+
+   ```bash
+   uv publish --trusted-publishing always
+   ```
+
+The package name is not reserved until the first successful PyPI upload.

pdf_figure_table_extractor-0.1.0/README.md

@@ -0,0 +1,87 @@
+# PDF Figure and Table Extractor
+
+Extract labeled figures and tables from PDF files into tightly cropped,
+high-resolution PNG images. The extractor uses PDF-native captions, vector
+paths, embedded images, and text positions; it does not require OCR or a
+vision model for text-based PDFs.
+
+## Features
+
+- Extracts labeled `Figure`, `Fig.`, and `Table` regions.
+- Handles figure captions below content and table titles above or below content.
+- Supports vector figures, raster figures, ruled tables, and unruled tables.
+- Includes complete captions by default.
+- Produces a JSON manifest with page numbers, captions, crop boxes, and filenames.
+- Re-running into the same directory removes only files recorded by the previous manifest.
+
+## Installation
+
+Install the command-line tool with `uv`:
+
+```bash
+uv tool install pdf-figure-table-extractor
+```
+
+Or add it to a project:
+
+```bash
+uv add pdf-figure-table-extractor
+```
+
+## Usage
+
+```bash
+pdf-figure-table-extractor paper.pdf extracted-assets
+```
+
+The default resolution is 400 DPI. For larger output:
+
+```bash
+pdf-figure-table-extractor paper.pdf extracted-assets --dpi 600
+```
+
+To omit figure captions while keeping table titles:
+
+```bash
+pdf-figure-table-extractor paper.pdf extracted-assets --exclude-figure-captions
+```
+
+The Python API is also available:
+
+```python
+from pdf_figure_table_extractor import extract_assets
+
+assets = extract_assets("paper.pdf", "extracted-assets", dpi=400)
+```
+
+## Output
+
+```text
+extracted-assets/
+├── figure-001-1-page-001.png
+├── table-001-1-page-002.png
+└── manifest.json
+```
+
+`manifest.json` records the source PDF, DPI, detected caption, page number,
+crop box, and output filename for every asset.
+
+## Scope and limitations
+
+The extractor targets PDFs with machine-readable text and conventional labeled
+captions. Scanned documents, rotated captions, unusual caption formats, and
+figures spanning multiple pages may require OCR or manual correction. Always
+visually inspect extracted assets before using them in publications or reports.
+
+## Development
+
+```bash
+uv sync --all-groups
+uv run ruff check .
+uv run pytest
+uv build
+```
+
+Before publishing, choose and add an appropriate `LICENSE`, update the version,
+and add repository URLs to `pyproject.toml` after the GitHub repository exists.
+See [PUBLISHING.md](PUBLISHING.md) for the Trusted Publishing setup and release checklist.

pdf_figure_table_extractor-0.1.0/pyproject.toml

@@ -0,0 +1,58 @@
+[project]
+name = "pdf-figure-table-extractor"
+version = "0.1.0"
+description = "Extract tightly cropped, high-resolution figures and tables from PDF files."
+readme = "README.md"
+requires-python = ">=3.11"
+keywords = [
+    "academic-papers",
+    "figure-extraction",
+    "pdf",
+    "table-extraction",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Utilities",
+]
+dependencies = [
+    "loguru>=0.7,<1",
+    "pymupdf>=1.26,<2",
+]
+
+[project.scripts]
+pdf-assets = "pdf_figure_table_extractor.cli:main"
+pdf-figure-table-extractor = "pdf_figure_table_extractor.cli:main"
+
+[dependency-groups]
+dev = [
+    "pytest>=8,<10",
+    "ruff>=0.8",
+]
+
+[build-system]
+requires = ["hatchling>=1.27"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/pdf_figure_table_extractor"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP"]

pdf_figure_table_extractor-0.1.0/src/pdf_figure_table_extractor/__init__.py

@@ -0,0 +1,9 @@
+"""High-resolution PDF figure and table extraction."""
+
+from importlib.metadata import version
+
+from .extractor import Asset, extract_assets
+
+__version__ = version("pdf-figure-table-extractor")
+
+__all__ = ["Asset", "__version__", "extract_assets"]

pdf_figure_table_extractor-0.1.0/src/pdf_figure_table_extractor/cli.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+from loguru import logger
+
+from .extractor import extract_assets
+from .logging import configure_logging
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description="Extract figures and tables from a PDF as tightly cropped PNG files."
+    )
+    parser.add_argument("pdf", type=Path, help="Input PDF file")
+    parser.add_argument("output", type=Path, help="Output directory")
+    parser.add_argument("--dpi", type=int, default=400, help="Output resolution (default: 400)")
+    parser.add_argument(
+        "--exclude-figure-captions",
+        action="store_true",
+        help="Export figure bodies only. By default, complete figure captions are included.",
+    )
+    return parser
+
+
+def main() -> None:
+    args = build_parser().parse_args()
+    configure_logging()
+    assets = extract_assets(
+        args.pdf,
+        args.output,
+        dpi=args.dpi,
+        include_figure_captions=not args.exclude_figure_captions,
+    )
+    figures = sum(asset.kind == "figure" for asset in assets)
+    tables = sum(asset.kind == "table" for asset in assets)
+    logger.info(
+        "Extracted {} assets ({} figures, {} tables) into {}",
+        len(assets),
+        figures,
+        tables,
+        args.output.resolve(),
+    )
+
+
+if __name__ == "__main__":
+    main()

pdf_figure_table_extractor-0.1.0/src/pdf_figure_table_extractor/extractor.py

@@ -0,0 +1,398 @@
+from __future__ import annotations
+
+import json
+import re
+import statistics
+from dataclasses import asdict, dataclass
+from pathlib import Path
+
+import pymupdf
+from loguru import logger
+
+CAPTION_RE = re.compile(
+    r"^\s*(?P<kind>fig(?:ure)?\.?|table)\s+"
+    r"(?P<label>[A-Z]?\d+(?:[.:-]\d+)*)\s*(?:[|:.\-\u2013\u2014])\s*",
+    re.IGNORECASE,
+)
+
+
+@dataclass(frozen=True)
+class Caption:
+    kind: str
+    label: str
+    text: str
+    rect: pymupdf.Rect
+
+
+@dataclass(frozen=True)
+class Asset:
+    kind: str
+    label: str
+    page: int
+    caption: str
+    bbox: tuple[float, float, float, float]
+    file: str
+
+
+def _line_text(line: dict) -> str:
+    return "".join(span["text"] for span in line["spans"]).strip()
+
+
+def _find_captions(page: pymupdf.Page) -> list[Caption]:
+    captions: list[Caption] = []
+    data = page.get_text("dict", flags=pymupdf.TEXTFLAGS_TEXT)
+    for block in data["blocks"]:
+        if "lines" not in block:
+            continue
+        lines = block["lines"]
+        for index, line in enumerate(lines):
+            text = _line_text(line)
+            match = CAPTION_RE.match(text)
+            if not match:
+                continue
+
+            rect = pymupdf.Rect(line["bbox"])
+            full_text = text
+            for continuation in lines[index + 1 :]:
+                next_rect = pymupdf.Rect(continuation["bbox"])
+                if next_rect.y0 - rect.y1 > 4 or abs(next_rect.x0 - rect.x0) > 12:
+                    break
+                full_text += " " + _line_text(continuation)
+                rect |= next_rect
+
+            raw_kind = match.group("kind").lower()
+            kind = "table" if raw_kind == "table" else "figure"
+            captions.append(Caption(kind, match.group("label"), full_text.strip(), rect))
+
+    text_blocks = [block for block in data["blocks"] if "lines" in block]
+    extended: list[Caption] = []
+    for caption in captions:
+        rect = pymupdf.Rect(caption.rect)
+        text = caption.text
+        for block in text_blocks:
+            block_rect = pymupdf.Rect(block["bbox"])
+            if (
+                0 <= block_rect.y0 - rect.y1 <= 3
+                and abs(block_rect.x0 - rect.x0) <= 3
+                and block_rect.width >= rect.width * 0.75
+            ):
+                text += " " + " ".join(_line_text(line) for line in block["lines"])
+                rect |= block_rect
+        extended.append(Caption(caption.kind, caption.label, text, rect))
+    return extended
+
+
+def _column_rect(page_rect: pymupdf.Rect, caption: Caption) -> pymupdf.Rect:
+    margin = max(24.0, page_rect.width * 0.045)
+    midpoint = page_rect.x0 + page_rect.width / 2
+    if caption.rect.width > page_rect.width * 0.46:
+        return pymupdf.Rect(
+            page_rect.x0 + margin,
+            page_rect.y0 + margin,
+            page_rect.x1 - margin,
+            page_rect.y1 - margin,
+        )
+    if caption.rect.x1 <= midpoint + 12:
+        return pymupdf.Rect(
+            page_rect.x0 + margin,
+            page_rect.y0 + margin,
+            midpoint - 7,
+            page_rect.y1 - margin,
+        )
+    return pymupdf.Rect(
+        midpoint + 7,
+        page_rect.y0 + margin,
+        page_rect.x1 - margin,
+        page_rect.y1 - margin,
+    )
+
+
+def _graphic_rects(page: pymupdf.Page) -> list[pymupdf.Rect]:
+    rects = [pymupdf.Rect(item["rect"]) for item in page.get_drawings()]
+    for image in page.get_images(full=True):
+        rects.extend(page.get_image_rects(image[0]))
+    return [rect for rect in rects if rect.width > 1 and rect.height > 1]
+
+
+def _distance(a: pymupdf.Rect, b: pymupdf.Rect) -> tuple[float, float]:
+    dx = max(a.x0 - b.x1, b.x0 - a.x1, 0)
+    dy = max(a.y0 - b.y1, b.y0 - a.y1, 0)
+    return dx, dy
+
+
+def _cluster_rects(rects: list[pymupdf.Rect]) -> list[pymupdf.Rect]:
+    clusters = [pymupdf.Rect(rect) for rect in rects]
+    changed = True
+    while changed:
+        changed = False
+        merged: list[pymupdf.Rect] = []
+        while clusters:
+            current = clusters.pop()
+            index = 0
+            while index < len(clusters):
+                other = clusters[index]
+                dx, dy = _distance(current, other)
+                x_overlap = min(current.x1, other.x1) - max(current.x0, other.x0)
+                if (dx <= 8 and dy <= 8) or (x_overlap > 0 and dy <= 5):
+                    current |= clusters.pop(index)
+                    changed = True
+                    index = 0
+                else:
+                    index += 1
+            merged.append(current)
+        clusters = merged
+    return clusters
+
+
+def _next_caption_limit(captions: list[Caption], caption: Caption, default: float) -> float:
+    candidates = [
+        other.rect.y0
+        for other in captions
+        if other is not caption
+        and other.rect.y0 > caption.rect.y1
+        and min(other.rect.x1, caption.rect.x1) > max(other.rect.x0, caption.rect.x0)
+    ]
+    return min(candidates, default=default)
+
+
+def _pick_graphics(
+    page: pymupdf.Page,
+    caption: Caption,
+    captions: list[Caption],
+) -> pymupdf.Rect | None:
+    column = _column_rect(page.rect, caption)
+    clusters = _cluster_rects(
+        [rect & column for rect in _graphic_rects(page) if not (rect & column).is_empty]
+    )
+    candidates: list[tuple[float, pymupdf.Rect]] = []
+
+    if caption.kind == "figure":
+        for rect in clusters:
+            gap = caption.rect.y0 - rect.y1
+            if (
+                -8 <= gap <= 360
+                and rect.y0 < caption.rect.y0
+                and rect.width >= 35
+                and rect.height >= 25
+            ):
+                candidates.append((max(gap, 0), rect))
+    else:
+        limit = _next_caption_limit(captions, caption, column.y1)
+        for rect in clusters:
+            below_gap = rect.y0 - caption.rect.y1
+            above_gap = caption.rect.y0 - rect.y1
+            if -8 <= below_gap <= 90 and rect.y1 < limit and rect.width >= 35:
+                candidates.append((max(below_gap, 0), rect))
+            if -8 <= above_gap <= 90 and rect.y0 < caption.rect.y0 and rect.width >= 35:
+                candidates.append((max(above_gap, 0), rect))
+
+    if not candidates:
+        return None
+    candidates.sort(key=lambda item: (item[0], -item[1].get_area()))
+    return candidates[0][1]
+
+
+def _word_rects(page: pymupdf.Page) -> list[pymupdf.Rect]:
+    return [pymupdf.Rect(word[:4]) for word in page.get_text("words")]
+
+
+def _expand_to_content(
+    page: pymupdf.Page,
+    caption: Caption,
+    graphics: pymupdf.Rect,
+    include_figure_captions: bool,
+) -> pymupdf.Rect:
+    if caption.kind == "figure":
+        crop = pymupdf.Rect(graphics)
+        search = pymupdf.Rect(graphics.x0 - 8, graphics.y0 - 10, graphics.x1 + 8, graphics.y1 + 8)
+        if include_figure_captions:
+            crop |= caption.rect
+            search |= caption.rect
+    else:
+        crop = graphics | caption.rect
+        search = pymupdf.Rect(crop.x0 - 5, caption.rect.y0 - 2, crop.x1 + 5, crop.y1 + 5)
+
+    for word in _word_rects(page):
+        if word.intersects(search):
+            crop |= word
+    crop += (-3, -3, 3, 3)
+    return crop & page.rect
+
+
+def _fallback_crop(
+    page: pymupdf.Page,
+    caption: Caption,
+    captions: list[Caption],
+    include_figure_captions: bool,
+) -> pymupdf.Rect | None:
+    column = _column_rect(page.rect, caption)
+    block_data: list[tuple[pymupdf.Rect, float]] = []
+    for block in page.get_text("dict", flags=pymupdf.TEXTFLAGS_TEXT)["blocks"]:
+        if "lines" not in block:
+            continue
+        rect = pymupdf.Rect(block["bbox"])
+        sizes = [
+            span["size"]
+            for line in block["lines"]
+            for span in line["spans"]
+            if span["text"].strip()
+        ]
+        if (
+            sizes
+            and rect.intersects(column)
+            and rect.y0 > page.rect.y0 + 65
+            and rect.y1 < page.rect.y1 - 65
+        ):
+            block_data.append((rect, statistics.median(sizes)))
+    blocks = [rect for rect, _ in block_data]
+    if caption.kind == "figure":
+        above = [rect for rect in blocks if rect.y1 < caption.rect.y0 - 2]
+        if not above:
+            return None
+        nearest = max(above, key=lambda rect: rect.y1)
+        top = max(column.y0, nearest.y0)
+        crop = pymupdf.Rect(column.x0, top, column.x1, caption.rect.y0 - 2)
+        if include_figure_captions:
+            crop |= caption.rect
+        return crop
+
+    bottom = _next_caption_limit(captions, caption, column.y1)
+    above = sorted(
+        (item for item in block_data if item[0].y1 < caption.rect.y0),
+        key=lambda item: item[0].y1,
+        reverse=True,
+    )
+    below = sorted(
+        (item for item in block_data if caption.rect.y1 < item[0].y0 < bottom),
+        key=lambda item: item[0].y0,
+    )
+    if not above and not below:
+        return None
+
+    above_gap = caption.rect.y0 - above[0][0].y1 if above else float("inf")
+    below_gap = below[0][0].y0 - caption.rect.y1 if below else float("inf")
+    above_size = above[0][1] if above else float("inf")
+    below_size = below[0][1] if below else float("inf")
+    previous_table = any(
+        other is not caption
+        and other.kind == "table"
+        and other.rect.y1 < caption.rect.y0
+        and min(other.rect.x1, caption.rect.x1) > max(other.rect.x0, caption.rect.x0)
+        for other in captions
+    )
+    wider_below = (
+        above
+        and below
+        and below[0][0].width > above[0][0].width * 1.5
+        and below_gap <= above_gap + 5
+    )
+    use_above = (
+        not previous_table
+        and not wider_below
+        and (
+            above_size + 0.75 < below_size
+            or abs(above_size - below_size) <= 0.75
+            and above_gap < below_gap
+        )
+    )
+    if use_above:
+        crop = caption.rect | above[0][0]
+        for rect, _ in above[1:]:
+            if crop.y0 - rect.y1 > 18:
+                break
+            crop |= rect
+    else:
+        crop = caption.rect | below[0][0]
+        for rect, _ in below[1:]:
+            if rect.y0 - crop.y1 > 18:
+                break
+            crop |= rect
+    return (crop + (-3, -3, 3, 3)) & page.rect
+
+
+def _safe_label(label: str) -> str:
+    return re.sub(r"[^A-Za-z0-9.-]+", "-", label).strip("-").lower()
+
+
+def _clear_previous_assets(output_dir: Path) -> None:
+    manifest_path = output_dir / "manifest.json"
+    if not manifest_path.is_file():
+        return
+    manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
+    for asset in manifest.get("assets", []):
+        filename = asset.get("file", "")
+        if filename and Path(filename).name == filename:
+            (output_dir / filename).unlink(missing_ok=True)
+    manifest_path.unlink()
+
+
+def extract_assets(
+    pdf_path: str | Path,
+    output_dir: str | Path,
+    *,
+    dpi: int = 400,
+    include_figure_captions: bool = True,
+) -> list[Asset]:
+    pdf_path = Path(pdf_path)
+    output_dir = Path(output_dir)
+    if not pdf_path.is_file() or pdf_path.suffix.lower() != ".pdf":
+        raise ValueError(f"Input is not a PDF file: {pdf_path}")
+    if dpi < 72:
+        raise ValueError("DPI must be at least 72")
+
+    output_dir.mkdir(parents=True, exist_ok=True)
+    _clear_previous_assets(output_dir)
+
+    document = pymupdf.open(pdf_path)
+    assets: list[Asset] = []
+    counters = {"figure": 0, "table": 0}
+    scale = dpi / 72
+
+    for page_index, page in enumerate(document):
+        captions = _find_captions(page)
+        logger.debug("Page {}: found {} captions", page_index + 1, len(captions))
+        for caption in captions:
+            graphics = _pick_graphics(page, caption, captions)
+            crop = (
+                _expand_to_content(page, caption, graphics, include_figure_captions)
+                if graphics
+                else _fallback_crop(page, caption, captions, include_figure_captions)
+            )
+            if crop is None or crop.width < 30 or crop.height < 15:
+                logger.warning(
+                    "Skipped {} {} on page {}: no content boundary found",
+                    caption.kind,
+                    caption.label,
+                    page_index + 1,
+                )
+                continue
+
+            counters[caption.kind] += 1
+            filename = (
+                f"{caption.kind}-{counters[caption.kind]:03d}-"
+                f"{_safe_label(caption.label)}-page-{page_index + 1:03d}.png"
+            )
+            pixmap = page.get_pixmap(matrix=pymupdf.Matrix(scale, scale), clip=crop, alpha=False)
+            pixmap.save(output_dir / filename)
+            assets.append(
+                Asset(
+                    kind=caption.kind,
+                    label=caption.label,
+                    page=page_index + 1,
+                    caption=caption.text,
+                    bbox=tuple(round(value, 2) for value in crop),
+                    file=filename,
+                )
+            )
+
+    document.close()
+    manifest = {
+        "source": str(pdf_path.resolve()),
+        "dpi": dpi,
+        "asset_count": len(assets),
+        "assets": [asdict(asset) for asset in assets],
+    }
+    (output_dir / "manifest.json").write_text(
+        json.dumps(manifest, ensure_ascii=False, indent=2) + "\n", encoding="utf-8"
+    )
+    return assets

pdf_figure_table_extractor-0.1.0/src/pdf_figure_table_extractor/logging.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+import sys
+
+from loguru import logger
+
+_CONFIGURED = False
+
+
+def configure_logging() -> None:
+    global _CONFIGURED
+    if _CONFIGURED:
+        return
+
+    logger.remove()
+    logger.add(sys.stderr, level="INFO", format="{time:HH:mm:ss} | {level} | {message}")
+    _CONFIGURED = True

pdf_figure_table_extractor-0.1.0/tests/test_extractor.py

@@ -0,0 +1,82 @@
+import json
+from pathlib import Path
+
+import pymupdf
+
+from pdf_figure_table_extractor import extract_assets
+
+
+def create_test_pdf(path: Path) -> None:
+    document = pymupdf.open()
+
+    figure_page = document.new_page(width=612, height=792)
+    figure_page.draw_rect(pymupdf.Rect(60, 100, 280, 260), width=1)
+    figure_page.draw_line((80, 220), (140, 150), width=2)
+    figure_page.draw_line((140, 150), (240, 205), width=2)
+    figure_page.insert_text((90, 125), "Synthetic Architecture", fontsize=12)
+    figure_page.insert_textbox(
+        pymupdf.Rect(60, 275, 285, 310),
+        "Figure 1: Synthetic architecture used to verify complete caption extraction.",
+        fontsize=9,
+    )
+
+    ruled_table_page = document.new_page(width=612, height=792)
+    ruled_table_page.insert_textbox(
+        pymupdf.Rect(60, 80, 285, 115),
+        "Table 1: Synthetic ruled table with two columns and complete title.",
+        fontsize=9,
+    )
+    for y in (130, 155, 180, 205):
+        ruled_table_page.draw_line((60, y), (280, y), width=1)
+    for x in (60, 170, 280):
+        ruled_table_page.draw_line((x, 130), (x, 205), width=1)
+    ruled_table_page.insert_text((80, 148), "Method", fontsize=9)
+    ruled_table_page.insert_text((195, 148), "Score", fontsize=9)
+    ruled_table_page.insert_text((80, 173), "Baseline", fontsize=9)
+    ruled_table_page.insert_text((205, 173), "0.75", fontsize=9)
+    ruled_table_page.insert_text((80, 198), "Ours", fontsize=9)
+    ruled_table_page.insert_text((205, 198), "0.91", fontsize=9)
+
+    unruled_table_page = document.new_page(width=612, height=792)
+    unruled_table_page.insert_text((80, 120), "Model        Accuracy", fontsize=9)
+    unruled_table_page.insert_text((80, 142), "Small        82.0", fontsize=9)
+    unruled_table_page.insert_text((80, 164), "Large        91.5", fontsize=9)
+    unruled_table_page.insert_textbox(
+        pymupdf.Rect(60, 185, 285, 220),
+        "Table 2: Synthetic unruled table whose title appears below the data.",
+        fontsize=9,
+    )
+
+    document.save(path)
+    document.close()
+
+
+def test_extracts_figures_and_tables(tmp_path: Path) -> None:
+    pdf_path = tmp_path / "paper.pdf"
+    output_dir = tmp_path / "assets"
+    create_test_pdf(pdf_path)
+
+    assets = extract_assets(pdf_path, output_dir, dpi=144)
+
+    assert [asset.kind for asset in assets] == ["figure", "table", "table"]
+    assert all((output_dir / asset.file).is_file() for asset in assets)
+    manifest = json.loads((output_dir / "manifest.json").read_text(encoding="utf-8"))
+    assert manifest["asset_count"] == 3
+    assert len(list(output_dir.glob("*.png"))) == 3
+
+    figure = pymupdf.Pixmap(output_dir / assets[0].file)
+    assert figure.width > 400
+    assert figure.height > 300
+
+
+def test_rerun_preserves_unrelated_files(tmp_path: Path) -> None:
+    pdf_path = tmp_path / "paper.pdf"
+    output_dir = tmp_path / "assets"
+    create_test_pdf(pdf_path)
+    extract_assets(pdf_path, output_dir, dpi=144)
+    unrelated = output_dir / "notes.txt"
+    unrelated.write_text("keep", encoding="utf-8")
+
+    extract_assets(pdf_path, output_dir, dpi=144)
+
+    assert unrelated.read_text(encoding="utf-8") == "keep"

pdf_figure_table_extractor-0.1.0/uv.lock

@@ -0,0 +1,156 @@
+version = 1
+revision = 3
+requires-python = ">=3.11"
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
+]
+
+[[package]]
+name = "iniconfig"
+version = "2.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" },
+]
+
+[[package]]
+name = "loguru"
+version = "0.7.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "win32-setctime", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/3a/05/a1dae3dffd1116099471c643b8924f5aa6524411dc6c63fdae648c4f1aca/loguru-0.7.3.tar.gz", hash = "sha256:19480589e77d47b8d85b2c827ad95d49bf31b0dcde16593892eb51dd18706eb6", size = 63559, upload-time = "2024-12-06T11:20:56.608Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c", size = 61595, upload-time = "2024-12-06T11:20:54.538Z" },
+]
+
+[[package]]
+name = "packaging"
+version = "26.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/fa/3944b40b07da9ce895c0e6303a5ab7d53da063554f534556b134a54d6093/packaging-26.3.tar.gz", hash = "sha256:94edc256424af38762eb31306eed28beb9f0efc50a8837492c9d6fd6004aed79", size = 313412, upload-time = "2026-08-04T18:15:28.737Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/63/34/ba1c580383c9eada3711951fef0795c80b829a078d72188184bcab9dd527/packaging-26.3-py3-none-any.whl", hash = "sha256:d7193f7c8e4e93f444fde0262bf90af30e16fa0ad0ad44cb553c87339b23cd1c", size = 129956, upload-time = "2026-08-04T18:15:27.159Z" },
+]
+
+[[package]]
+name = "pdf-figure-table-extractor"
+version = "0.1.0"
+source = { editable = "." }
+dependencies = [
+    { name = "loguru" },
+    { name = "pymupdf" },
+]
+
+[package.dev-dependencies]
+dev = [
+    { name = "pytest" },
+    { name = "ruff" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "loguru", specifier = ">=0.7,<1" },
+    { name = "pymupdf", specifier = ">=1.26,<2" },
+]
+
+[package.metadata.requires-dev]
+dev = [
+    { name = "pytest", specifier = ">=8,<10" },
+    { name = "ruff", specifier = ">=0.8" },
+]
+
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
+]
+
+[[package]]
+name = "pygments"
+version = "2.21.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/49/2e/ced460408999b33da6b31b0021b0f37d329e202d4169aeb164493778f25b/pygments-2.21.0.tar.gz", hash = "sha256:610ca751c9bc2492b38eb9a38a7fbc93edbbb2d7182edaf34e66ae493dee5c8c", size = 5005329, upload-time = "2026-08-17T08:02:48.824Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/71/46/17f022dd3e953bf20a04a028a21ec746d942f8d2af30fa0f124fa0e6a684/pygments-2.21.0-py3-none-any.whl", hash = "sha256:2363c69b61c4a97c838da3b130dcd6468f4848992b21a82f2a63ec34377137d9", size = 1250147, upload-time = "2026-08-17T08:02:44.912Z" },
+]
+
+[[package]]
+name = "pymupdf"
+version = "1.28.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a3/fb/b6761fa2d5266f2cdb24c3b91f4023070ab7848381417678e7a289a1d52a/pymupdf-1.28.2.tar.gz", hash = "sha256:5e0be7908a715aa20333caddd73f1d6f01e4cd0c26e869fa2dd0b7f344da2249", size = 87903557, upload-time = "2026-08-06T21:43:23.321Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b4/51/550c9a75c4ff3245cb4ecb7bb95cbe2ab7374230b8e2b7a1f7259444150b/pymupdf-1.28.2-cp310-abi3-macosx_10_15_x86_64.whl", hash = "sha256:5fc315b425ff1f7afdd1ea2f348205cb19b806767daae7ce4d64115799c2bae1", size = 24645079, upload-time = "2026-08-06T21:37:25.001Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/01/3591f781b417b382a8487a2356e927acfe858b1043bab0ec47f6805bb109/pymupdf-1.28.2-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:7113846b35dbf0a033f088e4f4fb543dabeb4b0b12c112966a1ca1ee2d5eacae", size = 23875605, upload-time = "2026-08-06T21:37:40.369Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/86/4a68f080b71b46802178346af46486e1697508e760855ff5f3b218a6dff7/pymupdf-1.28.2-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3050a233dde1211efe89ada74e2add6238436434159f46097a1423aad2842545", size = 25095554, upload-time = "2026-08-06T21:37:58.485Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/06/dace3e27af26690cb20bead80dbac42941b0841eb689b8aabbd67dde16f0/pymupdf-1.28.2-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:397d6715c1f0df7548a92d0afd8ce370fc48fa47aeefac16be2bc04a16a8227f", size = 25762500, upload-time = "2026-08-06T21:38:17.438Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/61/4146dfa1d8172a1ce8d59f0eed94896ddefb8deb2274534d0522fbb8abf5/pymupdf-1.28.2-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f89fb2d86d07d643a269f17a093105057e20c79c1d06c103b53600067b6d2b01", size = 25986309, upload-time = "2026-08-06T21:38:35.472Z" },
+    { url = "https://files.pythonhosted.org/packages/52/60/1fb6e64676f7500ebe89054b9e5bbbe14d3101c92d5f1a40ac9a35227673/pymupdf-1.28.2-cp310-abi3-win32.whl", hash = "sha256:530ef543a3885b3b81cb72a854e7c5a625a9233201221132bb6c31698c6a2bdb", size = 18525353, upload-time = "2026-08-06T21:38:47.697Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/61/d563bbccba262f9dd6d2d35ccb72593648184d886188efb12d9ce8f34dd6/pymupdf-1.28.2-cp310-abi3-win_amd64.whl", hash = "sha256:ebd244918798502d7b4504c90410d1711a4d7675a32584ca30f1bab419ecbffe", size = 19826532, upload-time = "2026-08-06T21:39:00.213Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/93/08f404a1f0155fe24137cf2d3aabd3e2b4b08c62053ed89c60f2611be3e9/pymupdf-1.28.2-cp310-abi3-win_arm64.whl", hash = "sha256:ffe91a24edc75c80da2a4b62f50fc0f54632d34fc8fe4cbc48e5c7ff07cf8fb4", size = 19759252, upload-time = "2026-08-06T21:39:12.937Z" },
+    { url = "https://files.pythonhosted.org/packages/58/8c/d897dcd32a25b58186c968b15ce4324ca029e9d96460de12325314e390be/pymupdf-1.28.2-cp313-abi3-pyemscripten_2025_0_wasm32.whl", hash = "sha256:2e1b574c0fd2cb238021033fd3c0f9c4388816638df064e4bfb56d9d81736dc8", size = 18399403, upload-time = "2026-08-06T21:39:25.008Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/f1/de34a1c53fe2bf8c6e71db84b0ced782d408970c9810d2b456a2ae96814c/pymupdf-1.28.2-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:fd481ed48bef56305c41fb7e05a055c03345c899c7b101dad086258b438f8168", size = 25802333, upload-time = "2026-08-06T21:39:41.426Z" },
+]
+
+[[package]]
+name = "pytest"
+version = "9.1.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "iniconfig" },
+    { name = "packaging" },
+    { name = "pluggy" },
+    { name = "pygments" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e4/47/b9efed96c114afcfa3c9d3fe98a76a1d14c74a9e266d397cf6eb64be5e01/pytest-9.1.1.tar.gz", hash = "sha256:1088fbde8f2b49d95a549a195707afa7a76a3ce9bcadc26b6d71f0ffda5fe313", size = 1636369, upload-time = "2026-06-19T10:58:32.857Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/24/25/1de2678b631f5a49215c6c96fff41ba892b0a34df68d6d80292b1b48aa7f/pytest-9.1.1-py3-none-any.whl", hash = "sha256:37a86b45efb9a47a61a36449063e8e18d0cab3161329fc099eb21783169c4f0c", size = 386536, upload-time = "2026-06-19T10:58:31.347Z" },
+]
+
+[[package]]
+name = "ruff"
+version = "0.16.10"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/c4/49/23802c45f093eb14bde54b141d2b2f058edfa63a06db7beed047308cc08f/ruff-0.16.10.tar.gz", hash = "sha256:eff4728c4eaae93f0955cd264d24b2ab348e74bf59986ccf282ba6dc16b3b017", size = 4958724, upload-time = "2026-10-01T18:03:21.697Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2f/21/ebce22e1d90cdb2cd691026b9c6e9bec6499f0b396089481755b5d49efff/ruff-0.16.10-py3-none-linux_armv6l.whl", hash = "sha256:488b0fe3f3574210e5cf80d9f59b9e3ab17a127a8155de3f307b392589cfb511", size = 10095557, upload-time = "2026-10-01T18:02:36.072Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/98/a54de85876a8b2612bfa0d84c7b9abfb39c6a3354aee7800b09c1649b9e3/ruff-0.16.10-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:e748ff95c934c4e978783b8e687bc174e7bd84e8ad24e3243e1ecfcda5e0282d", size = 10340577, upload-time = "2026-10-01T18:02:39.258Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/16/1a5a4a2657effe4806110f2b907313802f1367fcdbb29e8122766e407fab/ruff-0.16.10-py3-none-macosx_11_0_arm64.whl", hash = "sha256:3031a4a2e8e7b8a46f70be45f198c35a11ece509a94b80334d8d397a33c67550", size = 9774282, upload-time = "2026-10-01T18:02:41.79Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/fb/470085af734da396e68cd80fb0a3e7c109a459716ae59588c0f6fab8a17d/ruff-0.16.10-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:494401c86df4c4c25f69b9419605d944467ee98c42fb6ad405ef4fa40b8fb67d", size = 9920895, upload-time = "2026-10-01T18:02:44.458Z" },
+    { url = "https://files.pythonhosted.org/packages/57/de/f10cffe4f88a37ea6615ec460f01bf76f0bc1477737a35d9ee61a630a78b/ruff-0.16.10-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d203abc0ff2b773ee33d00ab8df0bb67046fbc7c07b119332f08b9b345cf8221", size = 9902707, upload-time = "2026-10-01T18:02:47.041Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/44/3fdcedf83ae60ef837dd239170e480dce606a9142cfa2db911afdf855fd9/ruff-0.16.10-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd83d1235a5258d318477bc5b576303974cbdef5df0c01a1bff14efcc23bd12a", size = 10619287, upload-time = "2026-10-01T18:02:49.485Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/62/02e76a5574002153618eafbb70e159468addc72a5d2c488e65cbb4639d2d/ruff-0.16.10-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bc2610fb269fa56dd8a68669ae470fa6272902668c0fc2ebc3aa112b2633d5b8", size = 11339942, upload-time = "2026-10-01T18:02:52.008Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/c4/cde27d47ad8d4126c587e608c67c46e7feac11763f606d261a1bc8a489e6/ruff-0.16.10-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3e70175e29cc94c26ea296c80e470180b744b7419026898e58f520c6ab32578e", size = 10934316, upload-time = "2026-10-01T18:02:54.811Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/03/17234145f302a645a123e8c3bb2411ecf4669fbc350de3b0d803230a1729/ruff-0.16.10-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f33f43a864a8483eebd160e713336c8bab02c934feaff0a33cf5ccb41546d09a", size = 10387968, upload-time = "2026-10-01T18:02:57.497Z" },
+    { url = "https://files.pythonhosted.org/packages/71/29/2493af60240ee7644b38a4b821f5f9c3b5a4fa3178770fe1d0c685217395/ruff-0.16.10-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:1dfc6f0088149fb6a362c1c446bcbb3fd2157b3852fe2fa68409276eab9ad9b3", size = 10537906, upload-time = "2026-10-01T18:03:00.006Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/9a/f56b28f3b143bb9e518c34fb89ab191b626bca8b70dbf8af0d2e2d473572/ruff-0.16.10-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:6553498afc35f580f036030795810b9e6bcea31604b0fd9e8d352795473042e3", size = 10012938, upload-time = "2026-10-01T18:03:03.006Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/c4/fca37362848ea4d4d80712df13632e645e7c7cfb1bdedf140699ac7a090b/ruff-0.16.10-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:a3b8471dea115d37f123882be852bed13403746d3a76c11de4a19ec5f9ff5a03", size = 9897945, upload-time = "2026-10-01T18:03:05.818Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/c7/e0bc57664d6e0c61fd22f620af260fe9662d7e1ddb320ea7f160e76ef165/ruff-0.16.10-py3-none-musllinux_1_2_i686.whl", hash = "sha256:92e59a70bcbd9d3a5483656da906ec28edfdacfce00afd99edb8b4e9d15644be", size = 10333134, upload-time = "2026-10-01T18:03:08.25Z" },
+    { url = "https://files.pythonhosted.org/packages/21/aa/5c9f3b68737c0e4a33a1db5dfab44f7b786d96ca91a7233112ddab1e6dc2/ruff-0.16.10-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:7ae7375f803b5520dc9f546bed7e3a0acb70b91812e9bb4b19927de22f25b77d", size = 10741702, upload-time = "2026-10-01T18:03:10.775Z" },
+    { url = "https://files.pythonhosted.org/packages/78/fa/0f9c2020dc316c53d983be011720b8157cc052b97e3f4dfa7db6d0f880a6/ruff-0.16.10-py3-none-win32.whl", hash = "sha256:2a12e01cb9156c10c466f63b46eaae5ecea28dfbd21b5836353ae498e7d1349a", size = 10139176, upload-time = "2026-10-01T18:03:13.267Z" },
+    { url = "https://files.pythonhosted.org/packages/99/29/cfb0df9448d4d4ad48c2de029ada9ebd71baa6da983a6c77ee6c6cd0fe82/ruff-0.16.10-py3-none-win_amd64.whl", hash = "sha256:97f2015c92aa97105b0eab19eb5d224884399281cfc5da86a92db4ab5e7fb2ca", size = 10584734, upload-time = "2026-10-01T18:03:16.006Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/05/c16957eb287c3fc062e032619a25868d93d408a844b725bcf514f7a378ff/ruff-0.16.10-py3-none-win_arm64.whl", hash = "sha256:25a65fe998c4e6861ec079ada5826a2fc605e6cbccbe9dcd7fac1f54e791621b", size = 10366440, upload-time = "2026-10-01T18:03:19.04Z" },
+]
+
+[[package]]
+name = "win32-setctime"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b3/8f/705086c9d734d3b663af0e9bb3d4de6578d08f46b1b101c2442fd9aecaa2/win32_setctime-1.2.0.tar.gz", hash = "sha256:ae1fdf948f5640aae05c511ade119313fb6a30d7eabe25fef9764dca5873c4c0", size = 4867, upload-time = "2024-12-07T15:28:28.314Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e1/07/c6fe3ad3e685340704d314d765b7912993bcb8dc198f0e7a89382d37974b/win32_setctime-1.2.0-py3-none-any.whl", hash = "sha256:95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390", size = 4083, upload-time = "2024-12-07T15:28:26.465Z" },
+]