Merge pull request #314 from perrygeo/mp/pyogrio

[v0.21.0] pyogrio generator

Author: perrygeo

.gitignore

@@ -17,6 +17,8 @@ Vagrantfile
 venv
 .eggs
 .cache
+.python-version
+*.lprof
 
 # no uv lockfile until this is fixed:
 # https://github.com/astral-sh/uv/issues/10845

CHANGELOG.txt

@@ -1,3 +1,12 @@
+0.21.0
+- Replace fiona with pyogrio as the default vector io engine #314
+    - Binary wheel support for python 3.14
+    - Promises better performance. See improvements in PR.
+    - Pass `engine=fiona` to use the old code path.
+    - Vector file detection now also uses pyogrio, so driver discovery etc may have changed for edge cases.
+- fix bug in progress bar #304
+- build, tooling, and test improvements #306 #308 #309 #310
+
 0.20.0
 - Progress bar for interactive use (#300)
 - Fixes to support Fiona 1.10 (#301)

docs/index.rst

@@ -22,6 +22,10 @@ Quickstart
 
 Install::
 
+    uv add rasterstats
+
+Or with pip::
+
     pip install rasterstats
 
 

docs/installation.rst

@@ -1,19 +1,37 @@
 Installation
 ============
 
-Depends on libgdal, rasterio, fiona, shapely and numpy
+Depends on libgdal, rasterio, fiona, shapely and numpy.
 
-Using Ubuntu 14.04::
+Using ``uv`` (recommended)::
 
-   sudo apt-get install python-numpy libgdal1h gdal-bin libgdal-dev
-   pip install rasterstats
+    uv add rasterstats
 
-Or homebrew on OS X::
+Or with pip::
 
-    brew install gdal
     pip install rasterstats
 
-For Windows, follow the `rasterio installation <https://github.com/mapbox/rasterio#windows-1>`_ and then run::
+Platform-specific GDAL setup
+-----------------------------
 
-    pip install rasterstats
+**Ubuntu**::
+
+    sudo apt-get install libgdal-dev gdal-bin
+
+then install rasterstats as above.
+
+**macOS** (Homebrew)::
+
+    brew install gdal
+
+then install rasterstats as above.
+
+**Windows**: follow the `rasterio installation <https://github.com/mapbox/rasterio#windows-1>`_,
+then install rasterstats as above.
+
+Tests
+-----
+
+To run the python unit tests
 
+    uv run pytest

docs/manual.rst

@@ -41,14 +41,19 @@ while ``point_query`` gives us a list of raster values corresponding to each inp
 Vector Data Sources
 -------------------
 The most common use case is having vector data sources in a file such as an ESRI Shapefile or any
-other format supported by ``fiona``. The path to the file can be passed in directly as the first argument::
+other format supported by ``pyogrio``. The path to the file can be passed in directly as the first argument::
     
     >>> zs = zonal_stats('tests/data/polygons.shp', 'tests/data/slope.tif')
 
 If you have multi-layer sources, you can specify the ``layer`` by either name or index::
 
     >>> zs = zonal_stats('tests/data', 'tests/data/slope.tif', layer="polygons")
 
+If you have ``fiona`` installed and want to use it as the vector iteration engine
+instead of the default ``pyogrio``, you can optionally add ``engine='fiona'``
+
+    >>> zs = zonal_stats("tests/data/polygons.shp", "tests/data/slope.tif", engine="fiona")
+
 In addition to the basic usage above, rasterstats supports other
 mechanisms of specifying vector geometries. 
 
@@ -294,5 +299,3 @@ command line tool, as well as GRASS's `r.statistics <https://grass.osgeo.org/gra
 They were suitable for offline analyses but were rather clunky to deploy in a large python application.
 In 2013, I implemented a proof-of-concept zonal stats function which eventually became ``rasterstats``. It has
 been in production in several large python web applications ever since, replacing the starspan wrapper `madrona.raster_stats <https://github.com/Ecotrust/madrona/blob/master/docs/raster_stats.rst>`_.
-
-

pyproject.toml

@@ -1,65 +1,64 @@
+# Note: code auto-formatted with `taplo fmt`
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [project]
 name = "rasterstats"
 description = "Summarize geospatial raster datasets based on vector geometries"
-authors = [
-    {name = "Matthew Perry", email = "perrygeo@gmail.com"},
-]
+authors = [{ name = "Matthew Perry", email = "perrygeo@gmail.com" }]
 readme = "README.rst"
-keywords = ["gis", "geospatial", "geographic", "raster", "vector", "zonal statistics"]
+keywords = [
+  "gis",
+  "geospatial",
+  "geographic",
+  "raster",
+  "vector",
+  "zonal statistics",
+]
 dynamic = ["version"]
-license = {text = "BSD-3-Clause"}
+license = { text = "BSD-3-Clause" }
 classifiers = [
-    "Development Status :: 4 - Beta",
-    "Intended Audience :: Developers",
-    "Intended Audience :: Science/Research",
-    "License :: OSI Approved :: BSD License",
-    "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Topic :: Utilities",
-    "Topic :: Scientific/Engineering :: GIS",
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: BSD License",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+  "Topic :: Utilities",
+  "Topic :: Scientific/Engineering :: GIS",
 ]
 requires-python = ">=3.9"
 dependencies = [
-    "affine",
-    "click >7.1, !=8.2.1",
-    "cligj >=0.4",
-    "fiona",
-    "numpy >=1.9",
-    "rasterio >=1.0",
-    "simplejson",
-    "shapely",
+  "affine",
+  "click >7.1, !=8.2.1",
+  "cligj >=0.4",
+  "numpy >=1.9",
+  "pyogrio",
+  "rasterio >=1.0",
+  "simplejson",
+  "shapely",
 ]
 
 [project.optional-dependencies]
-progress = [
-    "tqdm"
-]
-docs = [
-    "numpydoc",
-    "sphinx",
-    "sphinx-rtd-theme",
-]
+progress = ["tqdm"]
+fiona = ["fiona"]
+docs = ["numpydoc", "sphinx", "sphinx-rtd-theme"]
 test = [
-    "coverage",
-    "geopandas",
-    "pyshp >=1.1.4",
-    "pytest >=4.6",
-    "pytest-cov >=2.2.0",
-    "simplejson",
-]
-dev = [
-    "rasterstats[test]",
-    "ruff",
-    "twine",
+  "coverage",
+  "geopandas",
+  "pyshp >=1.1.4",
+  "pytest >=4.6",
+  "pytest-cov >=2.2.0",
+  "simplejson",
 ]
+dev = ["rasterstats[test,fiona]", "ruff", "twine"]
 
 [project.entry-points."rasterio.rio_plugins"]
 zonalstats = "rasterstats.cli:zonalstats"
@@ -73,31 +72,28 @@ Documentation = "https://pythonhosted.org/rasterstats/"
 only-include = ["src", "tests"]
 
 [tool.pytest.ini_options]
-filterwarnings = [
-    "error",
-    "ignore::UserWarning",
-]
+filterwarnings = ["error", "ignore::UserWarning"]
 testpaths = ["tests"]
-# addopts = "--verbose -rf --ipdb --maxfail=1"
+addopts = "--verbose -rf --cov rasterstats --cov-report html"
 
 [tool.setuptools.dynamic]
-version = {attr = "rasterstats._version.__version__"}
+version = { attr = "rasterstats._version.__version__" }
 
 [tool.hatch.version]
 path = "src/rasterstats/_version.py"
 
 [tool.ruff.lint]
 select = [
-    "E",    # pycodestyle
-    "F",    # Pyflakes
-    "I",    # isort
-    "RUF",  # Ruff-specific rules
-    "UP",   # pyupgrade
+  "E",   # pycodestyle
+  "F",   # Pyflakes
+  "I",   # isort
+  "RUF", # Ruff-specific rules
+  "UP",  # pyupgrade
 ]
 ignore = [
-    "RUF005",  # Consider iterable unpacking instead of concatenation
+  "E501",   # Disable: line too long
+  "RUF005", # Disable: Consider iterable unpacking instead of concatenation
 ]
 
 [tool.ruff]
-# TODO: files in docs/notebooks/ use old versions and are incompatible with modern tools
 extend-exclude = ["*.ipynb"]