smoothify 0.2.2__tar.gz → 0.3.0__tar.gz

smoothify-0.3.0/.github/workflows/ci.yml

@@ -0,0 +1,40 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0  # full history so setuptools-scm can read tags
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - uses: astral-sh/setup-uv@v8.0.0
+        with:
+          cache-suffix: ${{ matrix.python-version }}
+
+      - run: uv sync --all-extras --dev
+
+      - name: Lint
+        run: uv run ruff check .
+
+      - name: Type check
+        run: uv run mypy smoothify/
+
+      - name: Test
+        run: uv run pytest tests/ -x -q
+
+      - name: Notebook smoke test
+        if: matrix.python-version == '3.11'
+        run: uv run pytest --nbmake examples/*.ipynb -q

smoothify-0.3.0/.github/workflows/publish.yml

@@ -0,0 +1,75 @@
+name: Publish to PyPI
+
+# Triggered by pushing a tag that looks like a version, e.g. `v1.0.0`.
+# The version comes from the git tag itself (via setuptools-scm) — no file to bump.
+# Publishing uses PyPI trusted publishing (OIDC) — no API tokens, no secrets.
+# To enable: at https://pypi.org/manage/project/smoothify/settings/publishing/
+# add a publisher with:
+#   Owner            DPIRD-DMA
+#   Repository name  Smoothify
+#   Workflow name    publish.yml
+#   Environment      pypi
+
+on:
+  push:
+    tags:
+      - "v[0-9]+.[0-9]+.[0-9]+*"
+
+jobs:
+  build:
+    name: Build distribution
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0  # full history so setuptools-scm can read tags
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.11"
+
+      - uses: astral-sh/setup-uv@v8.0.0
+
+      - name: Build sdist + wheel
+        run: uv build
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    name: Publish to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/smoothify
+    permissions:
+      id-token: write  # required for trusted publishing
+
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: Create GitHub Release
+    needs: publish-to-pypi
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # required to create releases
+
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+          generate_release_notes: true

smoothify-0.3.0/.gitignore

@@ -0,0 +1,189 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+private test data/*
+*.gpkg-shm
+*.gpkg-wal
+*.DS_Store
+test data/output/*
+examples/Water_Smoothed.gpkg
+
+# setuptools-scm generated version file
+smoothify/_version.py
+
+# uv lockfile (not tracked — library, resolve fresh)
+uv.lock
+
+# Benchmarks
+benchmarks/baseline_output.gpkg

smoothify-0.3.0/.pre-commit-config.yaml

@@ -0,0 +1,21 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.8
+    hooks:
+      - id: ruff-check
+      - id: ruff-format
+  - repo: local
+    hooks:
+      - id: mypy
+        name: mypy
+        entry: uv run mypy smoothify/
+        language: system
+        pass_filenames: false
+        always_run: true
+      - id: pytest
+        name: pytest
+        entry: uv run pytest tests/ -x -q -m "not slow"
+        language: system
+        pass_filenames: false
+        always_run: true
+        stages: [pre-push]

smoothify-0.3.0/.python-version

@@ -0,0 +1 @@
+3.13

smoothify-0.3.0/.vscode/settings.json

@@ -0,0 +1,43 @@
+{
+    "cSpell.words": [
+        "brentq",
+        "capstyle",
+        "chaikin",
+        "darkgreen",
+        "edgecolor",
+        "facecolor",
+        "figsize",
+        "fontsize",
+        "fontweight",
+        "geodataframe",
+        "geopandas",
+        "gpkg",
+        "hausdorffs",
+        "ipykernel",
+        "joblib",
+        "lightgreen",
+        "linalg",
+        "linearing",
+        "linestrings",
+        "matplotlib",
+        "multipolygons",
+        "ndarray",
+        "numpy",
+        "polygonized",
+        "pytest",
+        "scipy",
+        "segmentize",
+        "setuptools",
+        "shapley",
+        "smoothify",
+        "soomthify",
+        "suptitle",
+        "xlabel",
+        "xlim",
+        "xticks",
+        "xtol",
+        "ylabel",
+        "ylim",
+        "yticks"
+    ],
+}

smoothify-0.3.0/CHANGELOG.md

@@ -0,0 +1,61 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## [Unreleased]
+
+## [0.3.0] - 2026-06-12
+
+### Changed
+- Single-core smoothing is ~3.5x faster on typical raster-derived data (benchmarked on `examples/Water.gpkg`: 6.8s → 1.9s, including the cost of the new fold-repair check below). Output differences are sub-pixel (bounded by the algorithm's own start-point noise floor); area preservation accuracy is unchanged or slightly better. The main changes:
+  - Removed the reversed-direction smoothing variants for polygons: Chaikin corner cutting is direction-invariant on closed rings, so they duplicated the forward variants bit-for-bit and only inflated the variant union (output unchanged).
+  - Holes are now subtracted in a single `difference` call against their union instead of one `intersection` + `difference` pair per hole (output unchanged).
+  - The tiny merge/dissolve buffer now uses mitre joins, which keep corners as single vertices instead of adding ~8 arc vertices per corner (boundary differences at the millimetre scale of the buffer itself).
+  - Pre-union Chaikin smoothing of the start-point variants is capped at 2 iterations; detail beyond that was erased by the post-union simplify anyway, while doubling the vertex count entering the expensive union. The final smoothing pass still runs the full `smooth_iterations`.
+  - The area-preservation root finder brackets the root from one side using its linear estimate, caches evaluations, and uses a step tolerance derived from the area tolerance via the perimeter, roughly halving the number of buffer operations.
+  - Congruent geometries (translated copies of the same shape, common in raster-derived data) are now smoothed once and the result translated to each occurrence; this also reduces work dispatched to parallel workers.
+
+### Added
+- New `merge_holes` option (default `True`): holes that touch or nearly touch (e.g. diagonally adjacent raster cells) are joined before smoothing, so they smooth into one coherent opening instead of separate overlapping shapes leaving a fake land bridge. Pass `merge_holes=False` for the previous per-hole behaviour. Mirrors what `merge_multipolygons` does for shells.
+- `examples/merge_holes_examples.ipynb`: worked examples of `merge_holes` and its interplay with `merge_collection` (touching holes, overlapping donuts, holes split across features).
+- `benchmarks/bench_water.py`: single-core timing/profiling benchmark with baseline output comparison.
+
+### Fixed
+- Fixed sharp concave folds in smoothed output on shapes with features about one `segment_length` wide (e.g. a hole with a one-pixel-wide arm, as produced by `merge_holes` joining a small hole to a larger one). The start-point smoothing variants can disagree about such features, leaving a forked slit in their union that the area-preservation shrink sharpens into a cusp. The final result is now checked for sharp concave turns and, when one is found, recomputed from the variant union sealed with a small closing (dilate-erode at `segment_length / 4`).
+- Fixed sharp cusps where a smoothed hole crosses the independently smoothed exterior and gets clipped by the hole subtraction (previously up to a 180-degree fold at the tangential crossing points). When detected, the result is repaired with a small opening + closing (at `segment_length / 4`), which removes hair-thin material needles and seals thin slits without visibly moving the boundary.
+- Fixed shapes with long straight edges being massively over-rounded (e.g. a large square with a small `segment_length` collapsed into a circle). The simplify steps strip all collinear vertices from straight edges, and Chaikin's corner cuts scale with segment length, so corner rounding grew with edge length instead of `segment_length`. Geometries are now re-segmentized after each simplify step, capping corner rounding at roughly `segment_length` while still smoothing raster staircase artifacts into curves. Applies to all geometry types. Note: outputs are somewhat denser (more vertices) and smoothing is ~20% slower on typical raster-derived data.
+
+## [0.2.3] - 2026-06-02
+
+### Added
+- The package now ships inline type hints and a `py.typed` marker, so type checkers (mypy, Pyright/Pylance) pick up `smoothify()`'s signatures and overloads in downstream code.
+
+### Changed
+- Invalid geometries (e.g. self-intersecting polygons) are now returned unchanged with a warning instead of crashing with a cryptic error or silently collapsing to an empty geometry. Behaviour is consistent across single geometries, lists/collections, and GeoDataFrames (and regardless of `merge_collection`). Repair them with shapely's `make_valid()` first if you want them smoothed.
+
+## [0.2.2] - 2026-03-24
+
+### Fixed
+- Fixed LineString smoothing: self-intersecting lines are no longer run through the polygon-only `make_valid`/`unary_union` step, which could split them into a MultiLineString at crossing points
+- Preserve coordinate dimensionality during Chaikin corner cutting instead of forcing 2D output, so smoothed geometries keep their original dimensions
+
+## [0.2.1] - 2026-02-25
+
+### Fixed
+- Fixed `TopologyException` crash on thin/elongated polygons by validating smoothed variants before union
+- Fixed crash when hole subtraction splits a polygon into a MultiPolygon (e.g. tiny holes relative to segment length)
+
+## [0.2.0] - 2026-02-25
+
+### Fixed
+- `smooth_iterations=0` now returns the original input unchanged instead of running the geometry through segmentize/simplify pipeline without smoothing
+
+## [0.1.0] - 2025-11-25
+
+### Added
+- Initial public release
+- Core smoothing functionality using Chaikin's corner-cutting algorithm
+- Support for all Shapely geometry types (Polygon, LineString, MultiPolygon, etc.)
+- Automatic segment length detection
+- Parallel processing support
+- Area preservation for polygons

{smoothify-0.2.2 → smoothify-0.3.0}/PKG-INFO

@@ -1,11 +1,26 @@
 Metadata-Version: 2.4
 Name: smoothify
-Version: 0.2.2
+Version: 0.3.0
 Summary: Transform pixelated geometries from raster data into smooth natural looking features
 Author-email: Nick Wright <nicholas.wright@dpird.wa.gov.au>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DPIRD-DMA/Smoothify
+Project-URL: Repository, https://github.com/DPIRD-DMA/Smoothify
+Project-URL: Issues, https://github.com/DPIRD-DMA/Smoothify/issues
+Project-URL: Changelog, https://github.com/DPIRD-DMA/Smoothify/blob/main/CHANGELOG.md
 Keywords: geometry,smoothing,smooth,GIS,raster,vector,chaikin,shapely,geopandas
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: GIS
+Classifier: Topic :: Scientific/Engineering :: Image Processing
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -16,15 +31,18 @@ Requires-Dist: scipy>=1.11.0
 Requires-Dist: shapely>=2.0.2
 Dynamic: license-file
 
-<p align="left">
+<p align="center">
   <img src="https://raw.githubusercontent.com/DPIRD-DMA/Smoothify/main/images/smoothify_logo.png" alt="Smoothify Text" width="600">
 </p>
 
-[![Python Version](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org/downloads/)
-[![License](https://img.shields.io/badge/license-MIT-green)](https://github.com/DPIRD-DMA/Smoothify/blob/main/LICENSE)
-[![PyPI version](https://img.shields.io/pypi/v/smoothify.svg)](https://pypi.org/project/smoothify/)
-[![Conda version](https://img.shields.io/conda/vn/conda-forge/smoothify.svg)](https://anaconda.org/conda-forge/smoothify)
-[![Tutorials](https://img.shields.io/badge/Tutorials-Learn-brightgreen)](https://github.com/DPIRD-DMA/Smoothify/tree/main/examples)
+<p align="center">
+  <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10%2B-blue" alt="Python Version"></a>
+  <a href="https://github.com/DPIRD-DMA/Smoothify/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="License"></a>
+  <a href="https://pypi.org/project/smoothify/"><img src="https://img.shields.io/pypi/v/smoothify.svg" alt="PyPI version"></a>
+  <a href="https://pepy.tech/projects/smoothify"><img src="https://static.pepy.tech/badge/smoothify" alt="PyPI downloads"></a>
+  <a href="https://anaconda.org/conda-forge/smoothify"><img src="https://img.shields.io/conda/vn/conda-forge/smoothify.svg" alt="Conda version"></a>
+  <a href="https://github.com/DPIRD-DMA/Smoothify/tree/main/examples"><img src="https://img.shields.io/badge/Tutorials-Learn-brightgreen" alt="Tutorials"></a>
+</p>
 
 📋 [View Changelog](https://github.com/DPIRD-DMA/Smoothify/blob/main/CHANGELOG.md)
 
@@ -43,7 +61,7 @@ Polygons and lines derived from classified raster data (e.g., ML model predictio
 Smoothify applies an optimized implementation of Chaikin's corner-cutting algorithm along with other geometric processing to create smooth, natural-looking features while:
 
 - Preserving the general shape and area of polygons
-- Supporting all shapley geometry types
+- Supporting all shapely geometry types
 - Handling shapes with interior holes
 - Efficiently processing large datasets with multiprocessing
 
@@ -100,6 +118,7 @@ Example notebooks:
 - [Usage examples](https://github.com/DPIRD-DMA/Smoothify/blob/main/examples/usage_examples.ipynb)
 - [Smoothify vs. Shapely comparison](https://github.com/DPIRD-DMA/Smoothify/blob/main/examples/smoothify_vs_shapely_comparison.ipynb)
 - [Real-world water example](https://github.com/DPIRD-DMA/Smoothify/blob/main/examples/real_world_water_example.ipynb)
+- [Merging holes](https://github.com/DPIRD-DMA/Smoothify/blob/main/examples/merge_holes_examples.ipynb)
 
 
 ### Basic Polygon Smoothing
@@ -204,6 +223,7 @@ smoothed = smoothify(
 | `merge_collection` | bool | True | Whether to merge/dissolve adjacent geometries in collections before smoothing |
 | `merge_field` | str | None | **GeoDataFrame only**: Column name to use for dissolving geometries. Only valid when `merge_collection=True`. If None, dissolves all geometries together. If specified, dissolves geometries grouped by the column values |
 | `merge_multipolygons` | bool | True | Whether to merge adjacent polygons within MultiPolygons before smoothing |
+| `merge_holes` | bool | True | Whether to join holes that touch or nearly touch (e.g. diagonally adjacent raster cells) before smoothing, so they smooth into one coherent opening instead of separate overlapping shapes |
 | `preserve_area` | bool | True | Whether to restore original area after smoothing via buffering (applies to Polygons only) |
 | `area_tolerance` | float | 0.01 | Percentage of original area allowed as error (e.g., 0.01 = 0.01% error = 99.99% preservation). Only affects Polygons when preserve_area=True |
 
@@ -211,21 +231,64 @@ smoothed = smoothify(
 
 Smoothify uses an advanced multi-step smoothing pipeline:
 
+<p align="left">
+  <img src="https://raw.githubusercontent.com/DPIRD-DMA/Smoothify/main/images/pipeline_steps.png" alt="Smoothify pipeline steps" width="800">
+</p>
+
+
+1. Joins touching holes (for Polygons, when `merge_holes=True`) so they smooth as one opening
+2. Adds intermediate vertices along line segments (segmentize)
+3. Generates multiple rotated variants (for Polygons) to avoid artifacts
+4. Simplifies each variant to remove noise
+5. Applies Chaikin corner cutting to smooth
+6. Merges all variants via union to eliminate start-point artifacts
+7. Applies final smoothing pass
+8. Optionally restores original area via buffering (for Polygons)
+9. Detects and repairs any sharp folds left by features near the smoothing scale (e.g. one-pixel-wide arms), using a small morphological opening/closing bounded at `segment_length / 4`
 
-1. Adds intermediate vertices along line segments (segmentize)
-2. Generates multiple rotated variants (for Polygons) to avoid artifacts
-3. Simplifies each variant to remove noise
-4. Applies Chaikin corner cutting to smooth
-5. Merges all variants via union to eliminate start-point artifacts
-6. Applies final smoothing pass
-7. Optionally restores original area via buffering (for Polygons)
+## Invalid Geometries
+
+Smoothify does not repair invalid input. If it encounters an invalid geometry (e.g. a self-intersecting polygon), it returns that geometry **unchanged** and emits a warning, instead of crashing or silently producing an empty geometry. This is consistent whether you pass a single geometry, a list/collection, or a GeoDataFrame.
+
+If you want invalid geometries smoothed, repair them first with shapely's `make_valid()`:
+
+```python
+# GeoDataFrame
+gdf.geometry = gdf.geometry.make_valid()
+smoothed_gdf = smoothify(gdf, segment_length=10.0)
+
+# Single geometry
+from shapely import make_valid
+smoothed = smoothify(make_valid(polygon), segment_length=1.0)
+```
 
 ## Performance Considerations
 
 - **Parallel Processing**: For large GeoDataFrames or collections, use `num_cores` = 0 to enable parallel processing
+- **Duplicate Shapes**: Geometries that are translated copies of the same shape (common in raster-derived data, e.g. single-pixel polygons) are automatically smoothed once and the result reused
 - **Smoothing Iterations**: Values of 3-5 typically provide good results. Higher values create smoother output but increase processing time and vertex count
 - **Memory Usage**: Scales with geometry complexity. The algorithm creates multiple variants during smoothing
-- **Optimal segment_length**: Should match the original raster cell size (pixel size) or be slightly larger for best results
+- **Optimal segment_length**: Anything from about half the original raster pixel size and up should produce reasonable output — larger values produce more rounded output, smaller values stay more faithful to the original geometry
+
+## Running the Tests
+
+Smoothify uses [pytest](https://pytest.org/). After cloning the repository, install the development dependencies and run the suite with [uv](https://docs.astral.sh/uv/):
+
+```bash
+# Install dependencies (including the dev group)
+uv sync
+
+# Run all tests
+uv run pytest tests/
+
+# Run with coverage
+uv run pytest tests/ --cov=smoothify --cov-report=html
+
+# Run a single test
+uv run pytest tests/test_chaikin.py::TestChaikinCornerCutting::test_simple_square_polygon
+```
+
+If you prefer not to use uv, install the dev dependencies into your environment and run `pytest tests/` directly.
 
 ## Contributing