Merge pull request #9 from Vizzuality/update-package

Update project tooling and structure

.github/workflows/run-tests.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.9', '3.10', '3.11']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v2

.gitignore

@@ -4,6 +4,8 @@ dist
 __pycache__
 .pytest_cache
 .mypy_cache
+.ruff_cache
+.venv
 .tox
 dask-worker-space
 *.egg-info
@@ -19,4 +21,4 @@ output.tif.msk
 .DS_Store
 
 *#
-*~
+*~

.pre-commit-config.yaml

@@ -1,25 +1,24 @@
-exclude: 'docs|test|setup.py'
-repos:  
-  - repo: https://github.com/psf/black
-    rev: 21.7b0
+exclude: "docs"
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
     hooks:
-      - id: black
-        language_version: python
+      - id: check-yaml
+      - id: check-toml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
 
-  - repo: https://github.com/PyCQA/flake8
-    rev: 3.9.2
-    hooks: 
-      - id: flake8
-        language_version: python
-
-  - repo: https://github.com/PyCQA/pydocstyle
-    rev: 6.1.1
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.2
     hooks:
-      - id: pydocstyle
-        language_version: python
+      - id: ruff
+        args: [ --fix ]
+        types_or: [ python, pyi, jupyter ]
+
+      - id: ruff-format
+        types_or: [ python, pyi, jupyter ]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v0.910'
+    rev: v1.10.0
     hooks:
       - id: mypy
-        language_version: python

pyproject.toml

@@ -0,0 +1,96 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cog_worker"
+description = "Scalable geospatial analysis on Cloud Optimized GeoTIFFs."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { file = "LICENSE.txt" }
+authors = [
+    { name = "Francis Gassert", email = "[email protected]" },
+]
+keywords = ["cog", "geotiff", "raster", "gdal", "rasterio", "dask"]
+classifiers = [
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: GIS",
+]
+dynamic = ["version"]
+dependencies = [
+    "numpy>=1,<2",
+    "pyproj>=3.0.0,<4",
+    "rasterio>=1.3,<2",
+    "morecantile>=4.3.0,<5",
+    "rio_tiler>=5.0.0,<6",
+]
+
+[project.urls]
+Homepage = "https://github.com/vizzuality/cog_worker"
+Issues = "https://github.com/vizzuality/cog_worker/issues"
+
+[project.optional-dependencies]
+test = ["pytest"]
+dev = ["pre-commit"]
+distributed = ["dask[distributed]"]
+docs = ["Sphinx", "sphinxcontrib-napoleon", "furo", "nbsphinx", "nbconvert"]
+
+[tool.ruff]
+line-length = 120
+extend-include = ["*.ipynb"]
+src = ["src"]
+
+[tool.ruff.lint]
+select = [
+    "D1", # pydocstyle errors
+    "E",  # pycodestyle errors
+    "W",  # pycodestyle warnings
+    "F",  # flake8
+    "C",  # flake8-comprehensions
+    "B",  # flake8-bugbear
+    "N",  # Naming conventions
+    "I",  # isort
+]
+pydocstyle.convention = "google"
+pydocstyle.ignore-decorators = ["property"]
+
+[tool.ruff.lint.per-file-ignores]
+"**/{tests}/*" = [
+    "D103", # Missing docstring in public function
+    "D100", # Missing docstring in public module
+]
+
+[tool.bumpversion]
+current_version = "0.2.0"
+parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
+serialize = ["{major}.{minor}.{patch}"]
+search = "{current_version}"
+replace = "{new_version}"
+regex = false
+ignore_missing_version = false
+ignore_missing_files = false
+tag = true
+sign_tags = false
+tag_name = "v{new_version}"
+tag_message = "Bump version: {current_version} → {new_version}"
+allow_dirty = false
+commit = true
+message = "Bump version: {current_version} → {new_version}"
+commit_args = ""
+
+[[tool.bumpversion.files]]
+filename = "src/cog_worker/__init__.py"
+
+[[tool.bumpversion.files]]
+filename = "sphinx_docs/source/conf.py"
+
+[[tool.bumpversion.files]]
+filename = "pyproject.toml"

cog_worker/distributed.py → src/cog_worker/distributed.py

@@ -27,17 +27,17 @@ def my_analysis(worker):
         results = manager.chunk_execute(my_analysis)
         total = sum(results)
 """
-from typing import Iterable, Iterator, Mapping, Union, Tuple, Any
+
 import logging
+from typing import Any, Iterable, Iterator, Mapping, Tuple, Union
 
 import dask
 import dask.distributed
 from dask.delayed import Delayed
 from pyproj import Proj
 
 import cog_worker
-from cog_worker.types import WorkerFunction, BoundingBox
-
+from cog_worker.types import BoundingBox, WorkerFunction
 
 logger = logging.getLogger(__name__)
 
@@ -79,11 +79,11 @@ def __init__(
     def execute(
         self,
         f: WorkerFunction,
-        f_args: Iterable = None,
-        f_kwargs: Mapping = None,
+        f_args: Union[Iterable, None] = None,
+        f_kwargs: Union[Mapping, None] = None,
         clip: bool = True,
         compute: bool = True,
-        **kwargs
+        **kwargs,
     ) -> Union[Tuple[Any, BoundingBox], Delayed]:
         """Execute a cog_worker function in the DaskManager's cluster.
 
@@ -134,11 +134,11 @@ def execute(
     def chunk_execute(
         self,
         f: WorkerFunction,
-        f_args: Iterable = None,
-        f_kwargs: Mapping = None,
+        f_args: Union[Iterable, None] = None,
+        f_kwargs: Union[Mapping, None] = None,
         chunksize: int = 512,
         compute: bool = True,
-    ) -> Union[Iterator[Tuple[Any, BoundingBox]], Iterator[Delayed]]:
+    ) -> Union[Iterator[Tuple[Any, BoundingBox]], Iterator[Delayed]]:  # type: ignore
         """Compute chunks in parallel in the DaskManager's cluster.
 
         Chunks will be yielded as they are completed. The order in which they
@@ -169,10 +169,8 @@ def chunk_execute(
         ]
         if compute:
             futures = self.client.compute(tasks)
-            for future, result in dask.distributed.as_completed(
-                futures, with_results=True
-            ):
+            for future, result in dask.distributed.as_completed(futures, with_results=True):
                 future.release()
                 yield result
         else:
-            return tasks
+            return tasks  # type: ignore