diffpdf 0.1.2__tar.gz → 0.3.0__tar.gz

diffpdf-0.3.0/.github/workflows/build.yml

@@ -0,0 +1,35 @@
+name: Build
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+        python-version: ["3.10", "3.x"]
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package with dev dependencies
+        run: pip install -e .[dev]
+
+      - name: Run ruff
+        run: ruff check .
+
+      - name: Run pytest
+        run: pytest tests/ -v --cov --cov-branch --cov-report=xml
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}

{diffpdf-0.1.2 → diffpdf-0.3.0}/.github/workflows/pypi-publish.yml

@@ -11,10 +11,10 @@ jobs:
       id-token: write
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v6
 
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: '3.10'
 

diffpdf-0.3.0/PKG-INFO

@@ -0,0 +1,96 @@
+Metadata-Version: 2.4
+Name: diffpdf
+Version: 0.3.0
+Summary: A tool for comparing PDF files
+Project-URL: Homepage, https://github.com/JustusRijke/DiffPDF
+Project-URL: Issues, https://github.com/JustusRijke/DiffPDF/issues
+Author-email: Justus Rijke <justusrijke@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Requires-Dist: click
+Requires-Dist: colorlog
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: pixelmatch-fast>=1.1.0
+Requires-Dist: pymupdf>=1.23.0
+Provides-Extra: dev
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# DiffPDF
+
+[![Build](https://github.com/JustusRijke/DiffPDF/actions/workflows/build.yml/badge.svg)](https://github.com/JustusRijke/DiffPDF/actions/workflows/build.yml)
+[![codecov](https://codecov.io/gh/JustusRijke/DiffPDF/graph/badge.svg?token=O3ZJFG6X7A)](https://codecov.io/gh/JustusRijke/DiffPDF)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+CLI tool for detecting structural, textual, and visual differences between PDF files, for use in automatic regression tests.
+
+## How It Works
+
+DiffPDF uses a fail-fast sequential pipeline to compare PDFs:
+
+1. **Hash Check** - SHA-256 comparison. If identical, exit immediately with pass.
+2. **Page Count** - Verify both PDFs have the same number of pages.
+3. **Text Content** - Extract and compare text from all pages (ignoring whitespace).
+4. **Visual Check** - Render pages to images and compare using [pixelmatch-fast](https://pypi.org/project/pixelmatch-fast/).
+
+Each stage only runs if all previous stages pass.
+
+## Installation
+
+```bash
+pip install diffpdf
+```
+
+## CLI Usage
+```
+Usage: diffpdf [OPTIONS] REFERENCE ACTUAL
+
+  Compare two PDF files for structural, textual, and visual differences.
+
+Options:
+  --threshold FLOAT       Pixelmatch threshold (0.0-1.0)
+  --dpi INTEGER           Render resolution
+  --output-dir DIRECTORY  Diff image output directory (optional, if not specified no diff images are saved)
+  -v, --verbose           Increase verbosity (-v for INFO, -vv for DEBUG)
+  --save-log              Write log output to log.txt
+  --version               Show the version and exit.
+  --help                  Show this message and exit.
+```
+
+**Exit Codes**
+
+- `0` — Pass (PDFs are equivalent)
+- `1` — Fail (differences detected)
+- `2` — Error (invalid input or processing error)
+
+## Library Usage
+
+```python
+from diffpdf import diffpdf
+
+# Basic usage (no diff images saved)
+diffpdf("reference.pdf", "actual.pdf")
+
+# With options (save diff images to ./output directory)
+diffpdf("reference.pdf", "actual.pdf", output_dir="./output", threshold=0.2, dpi=150, verbosity=2)
+```
+
+## Development
+
+```bash
+pip install -e .[dev]
+pytest tests/ -v
+ruff check .
+```
+
+## Acknowledgements
+
+Built with [PyMuPDF](https://pymupdf.readthedocs.io/) for PDF parsing and [pixelmatch-fast](https://pypi.org/project/pixelmatch-fast/) (Python port of [pixelmatch](https://github.com/mapbox/pixelmatch)) for visual comparison.

diffpdf-0.3.0/README.md

@@ -0,0 +1,71 @@
+# DiffPDF
+
+[![Build](https://github.com/JustusRijke/DiffPDF/actions/workflows/build.yml/badge.svg)](https://github.com/JustusRijke/DiffPDF/actions/workflows/build.yml)
+[![codecov](https://codecov.io/gh/JustusRijke/DiffPDF/graph/badge.svg?token=O3ZJFG6X7A)](https://codecov.io/gh/JustusRijke/DiffPDF)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+CLI tool for detecting structural, textual, and visual differences between PDF files, for use in automatic regression tests.
+
+## How It Works
+
+DiffPDF uses a fail-fast sequential pipeline to compare PDFs:
+
+1. **Hash Check** - SHA-256 comparison. If identical, exit immediately with pass.
+2. **Page Count** - Verify both PDFs have the same number of pages.
+3. **Text Content** - Extract and compare text from all pages (ignoring whitespace).
+4. **Visual Check** - Render pages to images and compare using [pixelmatch-fast](https://pypi.org/project/pixelmatch-fast/).
+
+Each stage only runs if all previous stages pass.
+
+## Installation
+
+```bash
+pip install diffpdf
+```
+
+## CLI Usage
+```
+Usage: diffpdf [OPTIONS] REFERENCE ACTUAL
+
+  Compare two PDF files for structural, textual, and visual differences.
+
+Options:
+  --threshold FLOAT       Pixelmatch threshold (0.0-1.0)
+  --dpi INTEGER           Render resolution
+  --output-dir DIRECTORY  Diff image output directory (optional, if not specified no diff images are saved)
+  -v, --verbose           Increase verbosity (-v for INFO, -vv for DEBUG)
+  --save-log              Write log output to log.txt
+  --version               Show the version and exit.
+  --help                  Show this message and exit.
+```
+
+**Exit Codes**
+
+- `0` — Pass (PDFs are equivalent)
+- `1` — Fail (differences detected)
+- `2` — Error (invalid input or processing error)
+
+## Library Usage
+
+```python
+from diffpdf import diffpdf
+
+# Basic usage (no diff images saved)
+diffpdf("reference.pdf", "actual.pdf")
+
+# With options (save diff images to ./output directory)
+diffpdf("reference.pdf", "actual.pdf", output_dir="./output", threshold=0.2, dpi=150, verbosity=2)
+```
+
+## Development
+
+```bash
+pip install -e .[dev]
+pytest tests/ -v
+ruff check .
+```
+
+## Acknowledgements
+
+Built with [PyMuPDF](https://pymupdf.readthedocs.io/) for PDF parsing and [pixelmatch-fast](https://pypi.org/project/pixelmatch-fast/) (Python port of [pixelmatch](https://github.com/mapbox/pixelmatch)) for visual comparison.

{diffpdf-0.1.2 → diffpdf-0.3.0}/pyproject.toml

@@ -24,7 +24,7 @@ dependencies = [
     "click",
     "colorlog",
     "pymupdf>=1.23.0",
-    "pixelmatch>=0.3.0",
+    "pixelmatch-fast>=1.1.0",
     "Pillow>=10.0.0",
 ]
 
@@ -33,13 +33,23 @@ Homepage = "https://github.com/JustusRijke/DiffPDF"
 Issues = "https://github.com/JustusRijke/DiffPDF/issues"
 
 [project.optional-dependencies]
-dev = ["pytest", "ruff"]
+dev = [
+    "pytest",
+    "pytest-cov",
+    "ruff",
+]
 
 [project.scripts]
-diffpdf = "diffpdf:main"
+diffpdf = "diffpdf.cli:cli"
 
 [tool.hatch.version]
 source = "vcs"
 
 [tool.hatch.version.raw-options]
 local_scheme = "no-local-version"
+
+[tool.ruff]
+target-version = "py310"
+
+[tool.ruff.lint]
+extend-select = ["I"] # Sort imports

diffpdf-0.3.0/src/diffpdf/__init__.py

@@ -0,0 +1,27 @@
+from importlib.metadata import version
+from pathlib import Path
+
+from .comparators import compare_pdfs
+from .logger import setup_logging
+
+__version__ = version("diffpdf")
+
+
+def diffpdf(
+    reference: str | Path,
+    actual: str | Path,
+    threshold: float = 0.1,
+    dpi: int = 96,
+    output_dir: str | Path | None = None,
+    verbosity: int = 0,
+    save_log: bool = False,
+) -> None:
+    ref_path = Path(reference) if isinstance(reference, str) else reference
+    actual_path = Path(actual) if isinstance(actual, str) else actual
+    out_path = Path(output_dir) if isinstance(output_dir, str) else output_dir
+
+    logger = setup_logging(verbosity, save_log)
+    compare_pdfs(ref_path, actual_path, threshold, dpi, out_path, logger)
+
+
+__all__ = ["diffpdf", "__version__"]

diffpdf-0.3.0/src/diffpdf/cli.py

@@ -0,0 +1,43 @@
+import sys
+from pathlib import Path
+
+import click
+
+from .comparators import compare_pdfs
+from .logger import setup_logging
+
+
+@click.command()
+@click.argument(
+    "reference", type=click.Path(exists=True, dir_okay=False, path_type=Path)
+)
+@click.argument("actual", type=click.Path(exists=True, dir_okay=False, path_type=Path))
+@click.option(
+    "--threshold", type=float, default=0.1, help="Pixelmatch threshold (0.0-1.0)"
+)
+@click.option("--dpi", type=int, default=96, help="Render resolution")
+@click.option(
+    "--output-dir",
+    type=click.Path(file_okay=False, path_type=Path),
+    default=None,
+    help="Diff image output directory (if not specified, no diff images are saved)",
+)
+@click.option(
+    "-v",
+    "--verbose",
+    "verbosity",
+    count=True,
+    help="Increase verbosity (-v for INFO, -vv for DEBUG)",
+)
+@click.option("--save-log", is_flag=True, help="Write log output to log.txt")
+@click.version_option(package_name="diffpdf")
+def cli(reference, actual, threshold, dpi, output_dir, verbosity, save_log):
+    """Compare two PDF files for structural, textual, and visual differences."""
+    logger = setup_logging(verbosity, save_log)
+    logger.debug("Debug logging enabled")
+
+    try:
+        compare_pdfs(reference, actual, threshold, dpi, output_dir, logger)
+    except Exception as e:  # pragma: no cover
+        logger.critical(f"Error: {e}", exc_info=True)
+        sys.exit(2)

{diffpdf-0.1.2 → diffpdf-0.3.0}/src/diffpdf/comparators.py

@@ -8,7 +8,7 @@ from .visual_check import check_visual_content
 
 
 def compare_pdfs(
-    ref: Path, actual: Path, threshold: float, dpi: int, output_dir: Path, logger
+    ref: Path, actual: Path, threshold: float, dpi: int, output_dir: Path | None, logger
 ) -> None:
     check_hash(ref, actual, logger)
 

diffpdf-0.3.0/src/diffpdf/logger.py

@@ -0,0 +1,45 @@
+import logging
+
+import colorlog
+
+LOG_FORMAT = (
+    "%(asctime)s %(levelname)-8s %(filename)s:%(lineno)d (%(funcName)s): %(message)s"
+)
+DATE_FORMAT = "%Y-%m-%d %H:%M:%S"
+LOG_COLORS = {
+    "DEBUG": "cyan",
+    "INFO": "green",
+    "WARNING": "yellow",
+    "ERROR": "red",
+    "CRITICAL": "red,bg_white",
+}
+
+
+def setup_logging(verbosity, save_log):
+    if verbosity == 0:
+        level = logging.WARNING
+    elif verbosity == 1:
+        level = logging.INFO
+    else:
+        level = logging.DEBUG
+
+    formatter = colorlog.ColoredFormatter(
+        f"%(log_color)s{LOG_FORMAT}%(reset)s",
+        datefmt=DATE_FORMAT,
+        log_colors=LOG_COLORS,
+    )
+
+    console_handler = logging.StreamHandler()
+    console_handler.setFormatter(formatter)
+
+    logger = logging.getLogger()
+    logger.setLevel(level)
+    logger.addHandler(console_handler)
+
+    if save_log:  # pragma: no cover
+        file_formatter = logging.Formatter(LOG_FORMAT, datefmt=DATE_FORMAT)
+        file_handler = logging.FileHandler("log.txt")
+        file_handler.setFormatter(file_formatter)
+        logger.addHandler(file_handler)
+
+    return logger

{diffpdf-0.1.2 → diffpdf-0.3.0}/src/diffpdf/text_check.py

@@ -1,6 +1,8 @@
 import difflib
+import re
 import sys
 from pathlib import Path
+from typing import Iterable
 
 import fitz
 
@@ -14,32 +16,34 @@ def extract_text(pdf_path: Path) -> str:
     return text.strip()
 
 
-def generate_diff(ref_text: str, actual_text: str) -> str:
+def generate_diff(
+    ref_text: str, ref: Path, actual_text: str, actual: Path
+) -> Iterable[str]:
     ref_lines = ref_text.splitlines(keepends=True)
     actual_lines = actual_text.splitlines(keepends=True)
 
     diff = difflib.unified_diff(
         ref_lines,
         actual_lines,
-        fromfile="reference.pdf",
-        tofile="actual.pdf",
+        fromfile=ref.name,
+        tofile=actual.name,
         lineterm="",
     )
 
-    return "".join(diff)
+    return diff
 
 
 def check_text_content(ref: Path, actual: Path, logger) -> None:
     logger.info("[3/4] Checking text content...")
 
-    ref_text = extract_text(ref)
-    actual_text = extract_text(actual)
+    # Extract text and remove whitespace
+    ref_text = re.sub(r"\s+", " ", extract_text(ref)).strip()
+    actual_text = re.sub(r"\s+", " ", extract_text(actual)).strip()
 
     if ref_text != actual_text:
-        diff = generate_diff(ref_text, actual_text)
-        logger.error("Text content mismatch")
-        for line in diff.splitlines():
-            logger.error(line)
+        diff = generate_diff(ref_text, ref, actual_text, actual)
+        diff_text = "\n".join(diff)
+        logger.error(f"Text content mismatch:\n {diff_text}")
         sys.exit(1)
 
     logger.info("Text content matches")

{diffpdf-0.1.2 → diffpdf-0.3.0}/src/diffpdf/visual_check.py

@@ -3,7 +3,7 @@ from pathlib import Path
 
 import fitz
 from PIL import Image
-from pixelmatch.contrib.PIL import pixelmatch
+from pixelmatch import pixelmatch
 
 
 def render_page_to_image(pdf_path: Path, page_num: int, dpi: int) -> Image.Image:
@@ -16,24 +16,28 @@ def render_page_to_image(pdf_path: Path, page_num: int, dpi: int) -> Image.Image
 
 
 def compare_images(
-    ref_img: Image.Image, actual_img: Image.Image, threshold: float, output_path: Path
+    ref_img: Image.Image,
+    actual_img: Image.Image,
+    threshold: float,
+    output_path: Path | None,
 ) -> bool:
-    diff_img = Image.new("RGB", ref_img.size)
-    mismatch_count = pixelmatch(ref_img, actual_img, diff_img, threshold=threshold)
+    mismatch_count = pixelmatch(
+        ref_img, actual_img, diff_path=output_path, threshold=threshold
+    )
 
     if mismatch_count > 0:
-        diff_img.save(output_path)
         return False
 
     return True
 
 
 def check_visual_content(
-    ref: Path, actual: Path, threshold: float, dpi: int, output_dir: Path, logger
+    ref: Path, actual: Path, threshold: float, dpi: int, output_dir: Path | None, logger
 ) -> None:
     logger.info("[4/4] Checking visual content...")
 
-    output_dir.mkdir(parents=True, exist_ok=True)
+    if output_dir is not None:
+        output_dir.mkdir(parents=True, exist_ok=True)
 
     ref_doc = fitz.open(ref)
     page_count = len(ref_doc)
@@ -45,11 +49,13 @@ def check_visual_content(
         ref_img = render_page_to_image(ref, page_num, dpi)
         actual_img = render_page_to_image(actual, page_num, dpi)
 
-        ref_name = ref.stem
-        actual_name = actual.stem
-        output_path = (
-            output_dir / f"{ref_name}_vs_{actual_name}_page{page_num + 1}_diff.png"
-        )
+        output_path = None
+        if output_dir is not None:
+            ref_name = ref.stem
+            actual_name = actual.stem
+            output_path = (
+                output_dir / f"{ref_name}_vs_{actual_name}_page{page_num + 1}_diff.png"
+            )
 
         passed = compare_images(ref_img, actual_img, threshold, output_path)
 

diffpdf-0.3.0/tests/test_api.py

@@ -0,0 +1,16 @@
+from pathlib import Path
+
+import pytest
+
+from diffpdf import diffpdf
+
+TEST_ASSETS_DIR = Path(__file__).parent / "assets"
+
+
+def test_diffpdf():
+    with pytest.raises(SystemExit) as exc_info:
+        diffpdf(
+            TEST_ASSETS_DIR / "pass/identical-A.pdf",
+            TEST_ASSETS_DIR / "pass/identical-B.pdf",
+        )
+    assert exc_info.value.code == 0

diffpdf-0.3.0/tests/test_cli.py

@@ -0,0 +1,36 @@
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from diffpdf.cli import cli
+
+TEST_ASSETS_DIR = Path(__file__).parent / "assets"
+
+
+def test_verbose_flag():
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        [
+            str(TEST_ASSETS_DIR / "pass/identical-A.pdf"),
+            str(TEST_ASSETS_DIR / "pass/identical-B.pdf"),
+            "-v",
+        ],
+    )
+    assert result.exit_code == 0
+    assert "INFO" in result.output
+    assert "DEBUG" not in result.output
+
+
+def test_double_verbose_flag():
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        [
+            str(TEST_ASSETS_DIR / "pass/identical-A.pdf"),
+            str(TEST_ASSETS_DIR / "pass/identical-B.pdf"),
+            "-vv",
+        ],
+    )
+    assert result.exit_code == 0
+    assert "DEBUG" in result.output

diffpdf-0.1.2/tests/test_cli.py → diffpdf-0.3.0/tests/test_comparators.py

@@ -5,6 +5,8 @@ from click.testing import CliRunner
 
 from diffpdf.cli import cli
 
+TEST_ASSETS_DIR = Path(__file__).parent / "assets"
+
 
 @pytest.mark.parametrize(
     "ref_pdf_rel,actual_pdf_rel,expected_exit_code",
@@ -22,14 +24,25 @@ from diffpdf.cli import cli
         ("nonexistent.pdf", "another.pdf", 2),
     ],
 )
-def test_cli(ref_pdf_rel, actual_pdf_rel, expected_exit_code):
-    """Parametric integration test: CLI should exit with correct code for various PDF pairs."""
+def test_comparators(ref_pdf_rel, actual_pdf_rel, expected_exit_code):
     runner = CliRunner()
-    test_assets_dir = Path(__file__).parent / "assets"
 
-    ref_pdf = str(test_assets_dir / ref_pdf_rel)
-    actual_pdf = str(test_assets_dir / actual_pdf_rel)
+    ref_pdf = str(TEST_ASSETS_DIR / ref_pdf_rel)
+    actual_pdf = str(TEST_ASSETS_DIR / actual_pdf_rel)
 
     result = runner.invoke(cli, [ref_pdf, actual_pdf])
 
     assert result.exit_code == expected_exit_code
+
+
+def test_comparators_with_output_dir():
+    runner = CliRunner()
+
+    with runner.isolated_filesystem():
+        ref_pdf = str(TEST_ASSETS_DIR / "fail/major-color-diff-A.pdf")
+        actual_pdf = str(TEST_ASSETS_DIR / "fail/major-color-diff-B.pdf")
+
+        result = runner.invoke(cli, [ref_pdf, actual_pdf, "--output-dir", "./diff"])
+
+        assert result.exit_code == 1
+        assert Path("./diff").exists()

diffpdf-0.1.2/.github/workflows/ci.yml

@@ -1,41 +0,0 @@
-name: CI
-
-on:
-  push:
-  pull_request:
-
-jobs:
-  test:
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, windows-latest]
-
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      - name: Set up Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.10"
-
-      - name: Install package with dev dependencies
-        run: pip install -e .[dev]
-
-      - name: Run ruff
-        run: ruff check .
-
-      - name: Run pytest
-        run: pytest tests/ -v
-
-      - name: Verify version detection
-        run: |
-          VERSION=$(diffpdf --version | sed -n 's/.*version \([0-9]\+\.[0-9]\+\.[0-9]\+\).*/\1/p')
-          if [ "$VERSION" = "0.0.0" ]; then
-            echo "Error: Version is 0.0.0, setuptools-scm failed to detect version"
-            exit 1
-          fi
-          echo "Version detected correctly: $VERSION"
-        shell: bash

diffpdf-0.1.2/PKG-INFO

@@ -1,82 +0,0 @@
-Metadata-Version: 2.4
-Name: diffpdf
-Version: 0.1.2
-Summary: A tool for comparing PDF files
-Project-URL: Homepage, https://github.com/JustusRijke/DiffPDF
-Project-URL: Issues, https://github.com/JustusRijke/DiffPDF/issues
-Author-email: Justus Rijke <justusrijke@gmail.com>
-License-Expression: MIT
-License-File: LICENSE
-Classifier: Development Status :: 4 - Beta
-Classifier: Operating System :: Microsoft :: Windows
-Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.10
-Requires-Dist: click
-Requires-Dist: colorlog
-Requires-Dist: pillow>=10.0.0
-Requires-Dist: pixelmatch>=0.3.0
-Requires-Dist: pymupdf>=1.23.0
-Provides-Extra: dev
-Requires-Dist: pytest; extra == 'dev'
-Requires-Dist: ruff; extra == 'dev'
-Description-Content-Type: text/markdown
-
-# DiffPDF
-
-[![CI](https://github.com/JustusRijke/DiffPDF/actions/workflows/ci.yml/badge.svg)](https://github.com/JustusRijke/DiffPDF/actions/workflows/ci.yml)
-
-CLI tool for detecting structural, textual, and visual differences between PDF files, for use in automatic regression tests.
-
-## Installation
-
-```bash
-pip install diffpdf
-```
-
-## Usage
-
-```bash
-diffpdf <baseline.pdf> <actual.pdf> [OPTIONS]
-```
-
-## How It Works
-
-DiffPDF uses a fail-fast sequential pipeline to compare PDFs:
-
-1. **Hash Check** - SHA-256 comparison. If identical, exit immediately with pass.
-2. **Page Count** - Verify both PDFs have the same number of pages.
-3. **Text Content** - Extract and compare text from all pages.
-4. **Visual Check** - Render pages to images and compare using pixelmatch.
-
-Each stage only runs if all previous stages pass.
-
-**⚠️ Performance Warning:** The Python port of pixelmatch is extremely slow.
-
-## Options
-
-| Option | Default | Description |
-|--------|---------|-------------|
-| `--threshold` | 0.1 | Pixelmatch threshold (0.0-1.0) |
-| `--dpi` | 96 | Render resolution |
-| `--output-dir` | ./ | Directory for diff images |
-| `--debug` | - | Verbose logging |
-| `--save-log` | - | Write log to log.txt |
-
-## Exit Codes
-
-- `0` — Pass (PDFs are equivalent)
-- `1` — Fail (differences detected)
-- `2` — Error (invalid input or processing error)
-
-## Development
-
-```bash
-pip install -e .[dev]
-pytest tests/ -v
-ruff check .
-```
-
-## Acknowledgements
-
-Built with [PyMuPDF](https://pymupdf.readthedocs.io/) for PDF parsing and [pixelmatch-py](https://github.com/whtsky/pixelmatch-py) (Python port of [pixelmatch](https://github.com/mapbox/pixelmatch)) for visual comparison.

diffpdf-0.1.2/README.md

@@ -1,58 +0,0 @@
-# DiffPDF
-
-[![CI](https://github.com/JustusRijke/DiffPDF/actions/workflows/ci.yml/badge.svg)](https://github.com/JustusRijke/DiffPDF/actions/workflows/ci.yml)
-
-CLI tool for detecting structural, textual, and visual differences between PDF files, for use in automatic regression tests.
-
-## Installation
-
-```bash
-pip install diffpdf
-```
-
-## Usage
-
-```bash
-diffpdf <baseline.pdf> <actual.pdf> [OPTIONS]
-```
-
-## How It Works
-
-DiffPDF uses a fail-fast sequential pipeline to compare PDFs:
-
-1. **Hash Check** - SHA-256 comparison. If identical, exit immediately with pass.
-2. **Page Count** - Verify both PDFs have the same number of pages.
-3. **Text Content** - Extract and compare text from all pages.
-4. **Visual Check** - Render pages to images and compare using pixelmatch.
-
-Each stage only runs if all previous stages pass.
-
-**⚠️ Performance Warning:** The Python port of pixelmatch is extremely slow.
-
-## Options
-
-| Option | Default | Description |
-|--------|---------|-------------|
-| `--threshold` | 0.1 | Pixelmatch threshold (0.0-1.0) |
-| `--dpi` | 96 | Render resolution |
-| `--output-dir` | ./ | Directory for diff images |
-| `--debug` | - | Verbose logging |
-| `--save-log` | - | Write log to log.txt |
-
-## Exit Codes
-
-- `0` — Pass (PDFs are equivalent)
-- `1` — Fail (differences detected)
-- `2` — Error (invalid input or processing error)
-
-## Development
-
-```bash
-pip install -e .[dev]
-pytest tests/ -v
-ruff check .
-```
-
-## Acknowledgements
-
-Built with [PyMuPDF](https://pymupdf.readthedocs.io/) for PDF parsing and [pixelmatch-py](https://github.com/whtsky/pixelmatch-py) (Python port of [pixelmatch](https://github.com/mapbox/pixelmatch)) for visual comparison.

diffpdf-0.1.2/ruff.toml

@@ -1,2 +0,0 @@
-target-version = "py312"
-lint.select = ["I"]

diffpdf-0.1.2/src/diffpdf/__init__.py

@@ -1,15 +0,0 @@
-from importlib.metadata import version
-
-from .cli import cli
-
-__version__ = version("diffpdf")
-
-
-def main(args=None):  # pragma: no cover
-    if args is None:
-        cli()
-    else:
-        cli(args, standalone_mode=False)
-
-
-__all__ = ["main", "__version__"]

diffpdf-0.1.2/src/diffpdf/cli.py

@@ -1,71 +0,0 @@
-import logging
-import sys
-from pathlib import Path
-
-import click
-import colorlog
-
-from .comparators import compare_pdfs
-
-
-def setup_logging(debug, save_log):  # pragma: no cover
-    level = logging.DEBUG if debug else logging.INFO
-
-    formatter = colorlog.ColoredFormatter(
-        "%(log_color)s%(asctime)s %(levelname)-8s%(reset)s %(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S",
-        log_colors={
-            "DEBUG": "cyan",
-            "INFO": "green",
-            "WARNING": "yellow",
-            "ERROR": "red",
-            "CRITICAL": "red,bg_white",
-        },
-    )
-
-    console_handler = logging.StreamHandler()
-    console_handler.setFormatter(formatter)
-
-    logger = logging.getLogger()
-    logger.setLevel(level)
-    logger.addHandler(console_handler)
-
-    if save_log:
-        file_formatter = logging.Formatter(
-            "%(asctime)s %(levelname)-8s %(message)s",
-            datefmt="%Y-%m-%d %H:%M:%S",
-        )
-        file_handler = logging.FileHandler("log.txt")
-        file_handler.setFormatter(file_formatter)
-        logger.addHandler(file_handler)
-
-    return logger
-
-
-@click.command()
-@click.argument(
-    "reference", type=click.Path(exists=True, dir_okay=False, path_type=Path)
-)
-@click.argument("actual", type=click.Path(exists=True, dir_okay=False, path_type=Path))
-@click.option(
-    "--threshold", type=float, default=0.1, help="Pixelmatch threshold (0.0-1.0)"
-)
-@click.option("--dpi", type=int, default=96, help="Render resolution")
-@click.option(
-    "--output-dir",
-    type=click.Path(file_okay=False, path_type=Path),
-    default="./",
-    help="Diff image output directory",
-)
-@click.option("--debug", is_flag=True, help="Verbose logging")
-@click.option("--save-log", is_flag=True, help="Write log output to log.txt")
-@click.version_option(package_name="diffpdf")
-def cli(reference, actual, threshold, dpi, output_dir, debug, save_log):
-    """Compare two PDF files for structural, textual, and visual differences."""
-    logger = setup_logging(debug, save_log)
-
-    try:
-        compare_pdfs(reference, actual, threshold, dpi, output_dir, logger)
-    except Exception as e:  # pragma: no cover
-        logger.critical(f"Error: {e}")
-        sys.exit(2)