smart-pdf-compare 0.1.0__tar.gz

smart_pdf_compare-0.1.0/.github/workflows/tests.yml

@@ -0,0 +1,16 @@
+name: tests
+on: [push, pull_request]
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+        python: ['3.9', '3.12']
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: {python-version: ${{ matrix.python }}}
+      - run: python -m pip install -e ".[dev]"
+      - run: python -m pytest
+      - run: python -m build

smart_pdf_compare-0.1.0/.gitignore

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

smart_pdf_compare-0.1.0/CHANGELOG.md

@@ -0,0 +1,5 @@
+# Changelog
+
+## 0.1.0 - 2026-10-28
+
+Initial public release: text extraction through the current PyMuPDF API (`import pymupdf`), Unicode-aware word diffs, three page alignment strategies, highlighted copies, a side-by-side report, CLI, packaging, and tests.

smart_pdf_compare-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,3 @@
+# Contributing
+
+Create a virtual environment, install `python -m pip install -e ".[dev]"`, and run `python -m pytest` before opening a pull request. Tests create their own PDFs with PyMuPDF and must not depend on network files. Keep the public API typed and documented. Run `python -m build` and `python -m twine check dist/*` before a release.

smart_pdf_compare-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 SmartPDFCompare contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

smart_pdf_compare-0.1.0/PKG-INFO

@@ -0,0 +1,204 @@
+Metadata-Version: 2.5
+Name: smart-pdf-compare
+Version: 0.1.0
+Summary: Text-aware PDF comparison, highlighting, and reports.
+Project-URL: Homepage, https://github.com/SmartPDFCompare/SmartPDFCompare
+Project-URL: Issues, https://github.com/SmartPDFCompare/SmartPDFCompare/issues
+Author-email: Abdelrahman Elsheikh <abdelrahmanelsheikh39@gmail.com>
+Maintainer-email: Abdelrahman Elsheikh <abdelrahmanelsheikh39@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: comparison,diff,pdf,pymupdf
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
+Requires-Dist: pymupdf>=2.0
+Provides-Extra: dev
+Requires-Dist: build>=1.0; extra == 'dev'
+Requires-Dist: pytest>=7.4; extra == 'dev'
+Requires-Dist: twine>=5.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+<div align="center">
+  <a href="https://github.com/SmartPDFCompare/SmartPDFCompare">
+    <img src="https://raw.githubusercontent.com/SmartPDFCompare/SmartPDFCompare/main/docs/assets/cover.svg" alt="SmartPDFCompare" width="760">
+  </a>
+  <br>
+  <a href="https://github.com/SmartPDFCompare/SmartPDFCompare">
+    <img src="https://readme-typing-svg.demolab.com?font=Inter&weight=700&size=25&duration=3200&pause=900&color=2563EB&center=true&vCenter=true&width=650&lines=Find+the+words+that+changed+in+your+PDFs;Compare.+Highlight.+Review." alt="Animated SmartPDFCompare introduction">
+  </a>
+  <br><br>
+  <a href="https://github.com/SmartPDFCompare/SmartPDFCompare/actions/workflows/tests.yml"><img src="https://github.com/SmartPDFCompare/SmartPDFCompare/actions/workflows/tests.yml/badge.svg" alt="Tests"></a>
+  <a href="https://pypi.org/project/smart-pdf-compare/"><img src="https://img.shields.io/pypi/v/smart-pdf-compare.svg?color=2563eb" alt="PyPI"></a>
+  <a href="https://pypi.org/project/smart-pdf-compare/"><img src="https://img.shields.io/pypi/pyversions/smart-pdf-compare.svg" alt="Supported Python versions"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-2563eb.svg" alt="MIT license"></a>
+  <a href="https://pymupdf.readthedocs.io/en/latest/"><img src="https://img.shields.io/badge/powered%20by-PyMuPDF%202-16a34a.svg" alt="Powered by PyMuPDF 2"></a>
+</div>
+
+<p align="center">
+  <a href="#quick-start"><strong>Quick start</strong></a> ·
+  <a href="#features"><strong>Features</strong></a> ·
+  <a href="#command-line"><strong>CLI</strong></a> ·
+  <a href="docs/api.md"><strong>API</strong></a> ·
+  <a href="docs/architecture.md"><strong>Architecture</strong></a> ·
+  <a href="#limitations"><strong>Limitations</strong></a>
+</p>
+
+**SmartPDFCompare** is a lightweight Python library for comparing the extractable text in two PDF versions. It gives applications structured word and page changes, then uses the **same coordinates** to write readable highlighted PDFs and an optional side-by-side review report.
+
+> [!IMPORTANT]
+> SmartPDFCompare uses the current [PyMuPDF 2](https://pymupdf.readthedocs.io/en/latest/) API exclusively: `import pymupdf`.
+
+## Features
+
+- **[Structured comparison](docs/api.md)** — added, removed, replaced, added-page, removed-page, and moved-page records with JSON serialization.
+- **[Unicode-aware text extraction](https://pymupdf.readthedocs.io/en/latest/textpage.html)** — PyMuPDF word coordinates, NFKC normalization, case folding, ligatures, NBSPs, and dash/minus variants.
+- **[Practical page alignment](docs/architecture.md)** — content matching for inserted/moved pages, bounded sequential look-ahead, and index-by-index comparison.
+- **[Visual review](#highlighted-output)** — native PDF highlights or boxes in safe output copies; optional side-by-side report pages.
+- **[Small CLI](#command-line)** — terminal summary, JSON result, highlighted output, report, alignment policy, and style controls.
+
+## Install
+
+```bash
+python -m pip install --upgrade smart-pdf-compare
+```
+
+The package tracks the current major [PyMuPDF](https://pypi.org/project/PyMuPDF/) release. Create a virtual environment first for a predictable setup:
+
+```bash
+python -m venv .venv
+# Windows: .venv\Scripts\activate
+# macOS/Linux: source .venv/bin/activate
+python -m pip install --upgrade smart-pdf-compare
+```
+
+## Quick start
+
+```python
+from smart_pdf_compare import compare_pdfs, highlight_differences
+
+result = compare_pdfs("original.pdf", "revised.pdf")
+
+print(result.is_identical)
+print(result.summary)
+for change in result.differences:
+    print(f"{change.change_type}: {change.old_text!r} -> {change.new_text!r}")
+
+outputs = highlight_differences(
+    "original.pdf",
+    "revised.pdf",
+    output_dir="diff-output",
+    result=result,
+    include_report=True,
+)
+print(outputs)
+```
+
+### Work with JSON
+
+```python
+import json
+
+with open("comparison.json", "w", encoding="utf-8") as file:
+    json.dump(result.to_dict(), file, indent=2)
+```
+
+`result.truncated` is `True` when `max_differences` limits returned detail entries. Aggregate counts in `result.summary` always cover the full comparison.
+
+## Highlighted output
+
+<table>
+  <tr>
+    <td width="50%"><strong>Original</strong><br>Removed or replaced text receives red markup.</td>
+    <td width="50%"><strong>Revised</strong><br>Added or replaced text receives green markup.</td>
+  </tr>
+  <tr>
+    <td><code>original_highlighted.pdf</code></td>
+    <td><code>revised_highlighted.pdf</code></td>
+  </tr>
+</table>
+
+Use real PDF annotations by default, or boxes where highlights are not desired:
+
+```python
+from smart_pdf_compare import highlight_differences
+
+highlight_differences(
+    "original.pdf", "revised.pdf", "diff-output",
+    style="box",          # "highlight" is the default
+    include_report=True,   # creates difference_report.pdf
+)
+```
+
+Source PDFs are never overwritten. The side-by-side report contains only pages with differences, displays page labels, and leaves a clearly labeled blank side for an inserted or removed page.
+
+## Alignment choices
+
+```python
+from smart_pdf_compare import ComparisonOptions, compare_pdfs
+
+result = compare_pdfs(
+    "original.pdf", "revised.pdf",
+    options=ComparisonOptions(
+        alignment="content",       # default
+        similarity_threshold=0.60,
+        lookahead=5,
+        max_differences=1_000,
+    ),
+)
+```
+
+| Strategy | Best for | Trade-off |
+| --- | --- | --- |
+| `content` | Documents with inserted, deleted, or moved pages | Greedy matching; not globally optimal for highly repetitive pages. |
+| `sequential` | Mostly ordered revisions | Resynchronizes only inside `lookahead`. |
+| `index` | Stable page-for-page documents | An insertion can make later pages appear modified. |
+
+Normalization is deliberately conservative: it uses NFKC, case folding, ligature compatibility, non-breaking-space cleanup, and dash/minus unification. Punctuation remains significant by default, so decimal values, negative numbers, negation, and contractions do not silently disappear.
+
+## Command line
+
+```bash
+smart-pdf-compare original.pdf revised.pdf \
+  --alignment content \
+  --output-dir diff-output \
+  --style highlight \
+  --report \
+  --json diff-output/comparison.json
+```
+
+| Exit code | Meaning |
+| --- | --- |
+| `0` | Textually identical under the chosen policy. |
+| `1` | Changes were found. |
+| `2` | Input, extraction, or configuration error. |
+
+## Limitations
+
+SmartPDFCompare compares the PDF **text layer**, not rendered pixels. It does not perform OCR, visual-diff analysis, or image comparison. If either document has no extractable text, it raises `MissingTextLayerError` instead of falsely claiming that two scanned PDFs are identical. Complex tables and multi-column PDFs can also expose an unreliable reading order from the source PDF.
+
+PyMuPDF is available under [AGPL or commercial terms](https://pymupdf.readthedocs.io/en/latest/about.html#license-and-copyright). Confirm that its license is appropriate for your use case.
+
+## Development
+
+```bash
+python -m pip install -e ".[dev]"
+python -m pytest
+python -m build
+python -m twine check dist/*
+```
+
+Read the [contribution guide](CONTRIBUTING.md), [public API](docs/api.md), [architecture notes](docs/architecture.md), and [changelog](CHANGELOG.md). Before publishing, verify availability of `smart-pdf-compare` on [PyPI](https://pypi.org/), upload to TestPyPI, install the artifact in a clean environment, and use [PyPI Trusted Publishing](https://docs.pypi.org/trusted-publishers/) for the production release.
+
+## License
+
+SmartPDFCompare’s own source code is licensed under the [MIT License](LICENSE). Its PyMuPDF dependency has separate licensing, described above.
+
+---
+
+<div align="center"><sub>Built for clear, reviewable PDF changes.</sub></div>

smart_pdf_compare-0.1.0/README.md

@@ -0,0 +1,178 @@
+<div align="center">
+  <a href="https://github.com/SmartPDFCompare/SmartPDFCompare">
+    <img src="https://raw.githubusercontent.com/SmartPDFCompare/SmartPDFCompare/main/docs/assets/cover.svg" alt="SmartPDFCompare" width="760">
+  </a>
+  <br>
+  <a href="https://github.com/SmartPDFCompare/SmartPDFCompare">
+    <img src="https://readme-typing-svg.demolab.com?font=Inter&weight=700&size=25&duration=3200&pause=900&color=2563EB&center=true&vCenter=true&width=650&lines=Find+the+words+that+changed+in+your+PDFs;Compare.+Highlight.+Review." alt="Animated SmartPDFCompare introduction">
+  </a>
+  <br><br>
+  <a href="https://github.com/SmartPDFCompare/SmartPDFCompare/actions/workflows/tests.yml"><img src="https://github.com/SmartPDFCompare/SmartPDFCompare/actions/workflows/tests.yml/badge.svg" alt="Tests"></a>
+  <a href="https://pypi.org/project/smart-pdf-compare/"><img src="https://img.shields.io/pypi/v/smart-pdf-compare.svg?color=2563eb" alt="PyPI"></a>
+  <a href="https://pypi.org/project/smart-pdf-compare/"><img src="https://img.shields.io/pypi/pyversions/smart-pdf-compare.svg" alt="Supported Python versions"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-2563eb.svg" alt="MIT license"></a>
+  <a href="https://pymupdf.readthedocs.io/en/latest/"><img src="https://img.shields.io/badge/powered%20by-PyMuPDF%202-16a34a.svg" alt="Powered by PyMuPDF 2"></a>
+</div>
+
+<p align="center">
+  <a href="#quick-start"><strong>Quick start</strong></a> ·
+  <a href="#features"><strong>Features</strong></a> ·
+  <a href="#command-line"><strong>CLI</strong></a> ·
+  <a href="docs/api.md"><strong>API</strong></a> ·
+  <a href="docs/architecture.md"><strong>Architecture</strong></a> ·
+  <a href="#limitations"><strong>Limitations</strong></a>
+</p>
+
+**SmartPDFCompare** is a lightweight Python library for comparing the extractable text in two PDF versions. It gives applications structured word and page changes, then uses the **same coordinates** to write readable highlighted PDFs and an optional side-by-side review report.
+
+> [!IMPORTANT]
+> SmartPDFCompare uses the current [PyMuPDF 2](https://pymupdf.readthedocs.io/en/latest/) API exclusively: `import pymupdf`.
+
+## Features
+
+- **[Structured comparison](docs/api.md)** — added, removed, replaced, added-page, removed-page, and moved-page records with JSON serialization.
+- **[Unicode-aware text extraction](https://pymupdf.readthedocs.io/en/latest/textpage.html)** — PyMuPDF word coordinates, NFKC normalization, case folding, ligatures, NBSPs, and dash/minus variants.
+- **[Practical page alignment](docs/architecture.md)** — content matching for inserted/moved pages, bounded sequential look-ahead, and index-by-index comparison.
+- **[Visual review](#highlighted-output)** — native PDF highlights or boxes in safe output copies; optional side-by-side report pages.
+- **[Small CLI](#command-line)** — terminal summary, JSON result, highlighted output, report, alignment policy, and style controls.
+
+## Install
+
+```bash
+python -m pip install --upgrade smart-pdf-compare
+```
+
+The package tracks the current major [PyMuPDF](https://pypi.org/project/PyMuPDF/) release. Create a virtual environment first for a predictable setup:
+
+```bash
+python -m venv .venv
+# Windows: .venv\Scripts\activate
+# macOS/Linux: source .venv/bin/activate
+python -m pip install --upgrade smart-pdf-compare
+```
+
+## Quick start
+
+```python
+from smart_pdf_compare import compare_pdfs, highlight_differences
+
+result = compare_pdfs("original.pdf", "revised.pdf")
+
+print(result.is_identical)
+print(result.summary)
+for change in result.differences:
+    print(f"{change.change_type}: {change.old_text!r} -> {change.new_text!r}")
+
+outputs = highlight_differences(
+    "original.pdf",
+    "revised.pdf",
+    output_dir="diff-output",
+    result=result,
+    include_report=True,
+)
+print(outputs)
+```
+
+### Work with JSON
+
+```python
+import json
+
+with open("comparison.json", "w", encoding="utf-8") as file:
+    json.dump(result.to_dict(), file, indent=2)
+```
+
+`result.truncated` is `True` when `max_differences` limits returned detail entries. Aggregate counts in `result.summary` always cover the full comparison.
+
+## Highlighted output
+
+<table>
+  <tr>
+    <td width="50%"><strong>Original</strong><br>Removed or replaced text receives red markup.</td>
+    <td width="50%"><strong>Revised</strong><br>Added or replaced text receives green markup.</td>
+  </tr>
+  <tr>
+    <td><code>original_highlighted.pdf</code></td>
+    <td><code>revised_highlighted.pdf</code></td>
+  </tr>
+</table>
+
+Use real PDF annotations by default, or boxes where highlights are not desired:
+
+```python
+from smart_pdf_compare import highlight_differences
+
+highlight_differences(
+    "original.pdf", "revised.pdf", "diff-output",
+    style="box",          # "highlight" is the default
+    include_report=True,   # creates difference_report.pdf
+)
+```
+
+Source PDFs are never overwritten. The side-by-side report contains only pages with differences, displays page labels, and leaves a clearly labeled blank side for an inserted or removed page.
+
+## Alignment choices
+
+```python
+from smart_pdf_compare import ComparisonOptions, compare_pdfs
+
+result = compare_pdfs(
+    "original.pdf", "revised.pdf",
+    options=ComparisonOptions(
+        alignment="content",       # default
+        similarity_threshold=0.60,
+        lookahead=5,
+        max_differences=1_000,
+    ),
+)
+```
+
+| Strategy | Best for | Trade-off |
+| --- | --- | --- |
+| `content` | Documents with inserted, deleted, or moved pages | Greedy matching; not globally optimal for highly repetitive pages. |
+| `sequential` | Mostly ordered revisions | Resynchronizes only inside `lookahead`. |
+| `index` | Stable page-for-page documents | An insertion can make later pages appear modified. |
+
+Normalization is deliberately conservative: it uses NFKC, case folding, ligature compatibility, non-breaking-space cleanup, and dash/minus unification. Punctuation remains significant by default, so decimal values, negative numbers, negation, and contractions do not silently disappear.
+
+## Command line
+
+```bash
+smart-pdf-compare original.pdf revised.pdf \
+  --alignment content \
+  --output-dir diff-output \
+  --style highlight \
+  --report \
+  --json diff-output/comparison.json
+```
+
+| Exit code | Meaning |
+| --- | --- |
+| `0` | Textually identical under the chosen policy. |
+| `1` | Changes were found. |
+| `2` | Input, extraction, or configuration error. |
+
+## Limitations
+
+SmartPDFCompare compares the PDF **text layer**, not rendered pixels. It does not perform OCR, visual-diff analysis, or image comparison. If either document has no extractable text, it raises `MissingTextLayerError` instead of falsely claiming that two scanned PDFs are identical. Complex tables and multi-column PDFs can also expose an unreliable reading order from the source PDF.
+
+PyMuPDF is available under [AGPL or commercial terms](https://pymupdf.readthedocs.io/en/latest/about.html#license-and-copyright). Confirm that its license is appropriate for your use case.
+
+## Development
+
+```bash
+python -m pip install -e ".[dev]"
+python -m pytest
+python -m build
+python -m twine check dist/*
+```
+
+Read the [contribution guide](CONTRIBUTING.md), [public API](docs/api.md), [architecture notes](docs/architecture.md), and [changelog](CHANGELOG.md). Before publishing, verify availability of `smart-pdf-compare` on [PyPI](https://pypi.org/), upload to TestPyPI, install the artifact in a clean environment, and use [PyPI Trusted Publishing](https://docs.pypi.org/trusted-publishers/) for the production release.
+
+## License
+
+SmartPDFCompare’s own source code is licensed under the [MIT License](LICENSE). Its PyMuPDF dependency has separate licensing, described above.
+
+---
+
+<div align="center"><sub>Built for clear, reviewable PDF changes.</sub></div>

smart_pdf_compare-0.1.0/docs/api.md

@@ -0,0 +1,7 @@
+# API reference
+
+`compare_pdfs(old_pdf, new_pdf, options=None)` returns `ComparisonResult`. Configure `ComparisonOptions(alignment, similarity_threshold, lookahead, max_differences, normalization)`. Call `result.to_dict()` for JSON data.
+
+`highlight_differences(old_pdf, new_pdf, output_dir, result=None, options=None, style="highlight", include_report=False)` returns paths for highlighted copies and optionally the report. `create_side_by_side_report` accepts an existing result and output path.
+
+Invalid files raise `InvalidPDFError`; documents with no text layer raise `MissingTextLayerError`; unsupported choices raise `ConfigurationError`.

smart_pdf_compare-0.1.0/docs/architecture.md

@@ -0,0 +1,3 @@
+# Architecture
+
+`extraction` reads positioned words from PyMuPDF. `normalization` produces conservative comparison keys. `alignment` creates one-to-one page pairs. `diff` uses those same word streams for structured text records and annotation coordinates. `api` aggregates the result; `highlighting` consumes its private geometry, so summaries and marks cannot diverge. `cli` calls only the public API.

smart_pdf_compare-0.1.0/docs/assets/cover.svg

@@ -0,0 +1,15 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="310" viewBox="0 0 1200 310" role="img" aria-labelledby="title description">
+  <title id="title">SmartPDFCompare</title>
+  <desc id="description">A blue document icon with highlighted differences and the SmartPDFCompare title.</desc>
+  <defs>
+    <linearGradient id="background" x1="0" x2="1" y1="0" y2="1"><stop stop-color="#eff6ff"/><stop offset="1" stop-color="#dbeafe"/></linearGradient>
+    <linearGradient id="blue" x1="0" x2="1"><stop stop-color="#2563eb"/><stop offset="1" stop-color="#0ea5e9"/></linearGradient>
+    <filter id="shadow" x="-20%" y="-20%" width="140%" height="140%"><feDropShadow dx="0" dy="8" stdDeviation="10" flood-color="#1e3a8a" flood-opacity=".17"/></filter>
+  </defs>
+  <rect width="1200" height="310" rx="30" fill="url(#background)"/>
+  <g filter="url(#shadow)"><rect x="88" y="48" width="174" height="214" rx="16" fill="white"/><path d="M214 48v50h48" fill="#bfdbfe"/><path d="M214 48v50h48" fill="none" stroke="#2563eb" stroke-width="7" stroke-linejoin="round"/><path d="M124 126h92M124 154h92M124 210h92" stroke="#93c5fd" stroke-width="11" stroke-linecap="round"/><path d="M124 182h58" stroke="#ef4444" stroke-width="15" stroke-linecap="round"/><path d="M124 234h76" stroke="#22c55e" stroke-width="15" stroke-linecap="round"/></g>
+  <circle cx="309" cy="150" r="42" fill="white" stroke="#2563eb" stroke-width="11"/><path d="m341 182 35 35" stroke="#2563eb" stroke-width="16" stroke-linecap="round"/>
+  <text x="425" y="143" fill="#0f172a" font-family="Arial, Helvetica, sans-serif" font-size="69" font-weight="700">SmartPDFCompare</text>
+  <text x="429" y="196" fill="#475569" font-family="Arial, Helvetica, sans-serif" font-size="29">Clear, coordinate-aware PDF text comparison</text>
+  <rect x="429" y="220" width="172" height="10" rx="5" fill="url(#blue)"/>
+</svg>

smart_pdf_compare-0.1.0/examples/basic_comparison.py

@@ -0,0 +1,4 @@
+from smart_pdf_compare import compare_pdfs
+
+result = compare_pdfs("original.pdf", "revised.pdf")
+print(result.to_dict())

smart_pdf_compare-0.1.0/examples/highlight_changes.py

@@ -0,0 +1,4 @@
+from smart_pdf_compare import highlight_differences
+
+outputs = highlight_differences("original.pdf", "revised.pdf", "diff-output", include_report=True)
+print(outputs)

smart_pdf_compare-0.1.0/pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["hatchling>=1.21"]
+build-backend = "hatchling.build"
+
+[project]
+name = "smart-pdf-compare"
+version = "0.1.0"
+description = "Text-aware PDF comparison, highlighting, and reports."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+
+authors = [
+    {name = "Abdelrahman Elsheikh", email = "abdelrahmanelsheikh39@gmail.com"}
+]
+maintainers = [
+    {name = "Abdelrahman Elsheikh", email = "abdelrahmanelsheikh39@gmail.com"}
+]
+
+keywords = ["pdf", "comparison", "diff", "pymupdf"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+]
+dependencies = ["PyMuPDF>=2.0"]
+
+[project.optional-dependencies]
+dev = ["build>=1.0", "pytest>=7.4", "twine>=5.0"]
+
+[project.urls]
+Homepage = "https://github.com/SmartPDFCompare/SmartPDFCompare"
+Issues = "https://github.com/SmartPDFCompare/SmartPDFCompare/issues"
+
+[project.scripts]
+smart-pdf-compare = "smart_pdf_compare.cli:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/smart_pdf_compare"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra"
+
+[tool.ruff]
+line-length = 100

smart_pdf_compare-0.1.0/src/smart_pdf_compare/__init__.py

@@ -0,0 +1,14 @@
+"""SmartPDFCompare: structured text comparison and PDF highlighting."""
+from .api import ComparisonOptions, compare_pdfs
+from .exceptions import ConfigurationError, InvalidPDFError, MissingTextLayerError, PDFComparisonError
+from .highlighting import HighlightOutputs, create_side_by_side_report, highlight_differences
+from .normalization import NormalizationOptions
+from .results import ChangeType, ComparisonResult, ComparisonSummary, Difference
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "ChangeType", "ComparisonOptions", "ComparisonResult", "ComparisonSummary", "ConfigurationError",
+    "Difference", "HighlightOutputs", "InvalidPDFError", "MissingTextLayerError", "NormalizationOptions",
+    "PDFComparisonError", "compare_pdfs", "create_side_by_side_report", "highlight_differences",
+]

smart_pdf_compare-0.1.0/src/smart_pdf_compare/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+raise SystemExit(main())