Pull request #18: IP-241 implement pre commit

Merge in SITC/harmony-regridding-service from IP-241-implement-pre-commit to main

* commit '48d218cb9592f5ee844d6760d3657956f6123dad':
  IP-241 - Increment service for black formatting changes.
  IP-241 - Add .git-blame-ignore-revs.
  IP-241 - Implement black code formatting across repository.
  IP-241 - Implement pre-commit.

.git-blame-ignore-revs

@@ -0,0 +1,5 @@
+# For more information, see:
+# https://docs.github.com/en/repositories/working-with-files/using-files/viewing-a-file#ignore-commits-in-the-blame-view
+
+# Black code formatting of entire repository
+2967ed10ef6e38d4346735c1693212a56c756902

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-json
+      - id: check-yaml
+      - id: check-added-large-files
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.3.4
+    hooks:
+      - id: ruff
+        args: ["--fix", "--show-fixes"]
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 24.3.0
+    hooks:
+      - id: black-jupyter
+        args: ["--skip-string-normalization"]
+        language_version: python3.11

CHANGELOG.md

@@ -1,3 +1,10 @@
+## v0.0.4
+### 2024-04-10
+
+This version of the Harmony Regridding service implements `black` code
+formatting across the entire repository. There should be no functional changes
+to the service.
+
 ## v0.0.3
 ### 2023-12-18
 

README.md

@@ -74,6 +74,39 @@ CI/CD pipeline. In future, this project will be migrated from Bitbucket to
 GitHub, at which point the CI/CD will be migrated to workflows that use GitHub
 Actions.
 
+## pre-commit hooks:
+
+This repository uses [pre-commit](https://pre-commit.com/) to enable pre-commit
+checking the repository for some coding standard best practices. These include:
+
+* Removing trailing whitespaces.
+* Removing blank lines at the end of a file.
+* JSON files have valid formats.
+* [ruff](https://github.com/astral-sh/ruff) Python linting checks.
+* [black](https://black.readthedocs.io/en/stable/index.html) Python code
+  formatting checks.
+
+To enable these checks:
+
+```bash
+# Install pre-commit Python package as part of test requirements:
+pip install -r tests/pip_test_requirements.txt
+
+# Install the git hook scripts:
+pre-commit install
+
+# (Optional) Run against all files:
+pre-commit run --all-files
+```
+
+When you try to make a new commit locally, `pre-commit` will automatically run.
+If any of the hooks detect non-compliance (e.g., trailing whitespace), that
+hook will state it failed, and also try to fix the issue. You will need to
+review and `git add` the changes before you can make a commit.
+
+It is planned to implement additional hooks, possibly including tools such as
+`mypy`.
+
 ## Versioning:
 
 Service Docker images for the Harmony Regridding Service adhere to semantic

docker/service_version.txt

@@ -1 +1 @@
-0.0.3
+0.0.4

docker/tests.Dockerfile

@@ -16,7 +16,7 @@ ENV PYTHONDONTWRITEBYTECODE=1
 COPY tests/pip_test_requirements.txt .
 RUN pip install --no-input -r pip_test_requirements.txt
 
-# Copy test directory containing Python unittest suite, test data and utilities 
+# Copy test directory containing Python unittest suite, test data and utilities
 COPY ./tests tests
 
 # Configure a container to be executable via the `docker run` command.

harmony_regridding_service/__main__.py

@@ -1,4 +1,5 @@
 """ Run the Harmony Regridding Service Adapter via the Harmony CLI. """
+
 from argparse import ArgumentParser
 from sys import argv
 from typing import List
@@ -9,12 +10,13 @@
 
 
 def main(arguments: List[str]):
-    """ Parse command line arguments and invoke the appropriate method to
-        respond to them
+    """Parse command line arguments and invoke the appropriate method to
+    respond to them
 
     """
-    parser = ArgumentParser(prog='harmony-regridding-service',
-                            description='Run Harmony regridding service.')
+    parser = ArgumentParser(
+        prog='harmony-regridding-service', description='Run Harmony regridding service.'
+    )
 
     setup_cli(parser)
     harmony_arguments, _ = parser.parse_known_args(arguments[1:])

harmony_regridding_service/adapter.py

@@ -5,6 +5,7 @@
     another grid as specified in the input Harmony message.
 
 """
+
 from os.path import basename
 from shutil import rmtree
 from tempfile import mkdtemp
@@ -13,49 +14,53 @@
 from harmony import BaseHarmonyAdapter
 from harmony.message import Source as HarmonySource
 from harmony.message_utility import has_self_consistent_grid
-from harmony.util import (bbox_to_geometry, download, generate_output_filename,
-                          stage)
+from harmony.util import bbox_to_geometry, download, generate_output_filename, stage
 from pystac import Asset, Catalog, Item
 
-from harmony_regridding_service.exceptions import (InvalidInterpolationMethod,
-                                                   InvalidTargetCRS,
-                                                   InvalidTargetGrid)
+from harmony_regridding_service.exceptions import (
+    InvalidInterpolationMethod,
+    InvalidTargetCRS,
+    InvalidTargetGrid,
+)
 from harmony_regridding_service.regridding_service import regrid
-from harmony_regridding_service.utilities import (get_file_mime_type,
-                                                  has_valid_crs,
-                                                  has_valid_interpolation)
+from harmony_regridding_service.utilities import (
+    get_file_mime_type,
+    has_valid_crs,
+    has_valid_interpolation,
+)
 
 
 class RegriddingServiceAdapter(BaseHarmonyAdapter):
-    """ This class extends the BaseHarmonyAdapter class from the
-        harmony-service-lib package to implement regridding operations.
+    """This class extends the BaseHarmonyAdapter class from the
+    harmony-service-lib package to implement regridding operations.
 
     """
+
     def __init__(self, message, catalog=None, config=None):
         super().__init__(message, catalog=catalog, config=config)
         self.cache = {'grids': {}}
 
     def invoke(self) -> Catalog:
-        """ Adds validation to process_item based invocations. """
+        """Adds validation to process_item based invocations."""
         self.validate_message()
         return super().invoke()
 
     def validate_message(self):
-        """ Validates that the contents of the Harmony message provides all
-            necessary parameters.
-
-            For an input Harmony message to be considered valid it must:
-
-            * Contain a valid target grid, with `format.scaleExtent` and either
-              `format.scaleSize` or both `format.height` and `format.width`
-              fully populated.
-            * Not specify an incompatible target CRS. Initially, the target CRS
-              is limited to geographic. The message should either specify a
-              geographic CRS, or not specify one at all.
-            * Not specify an incompatible interpolation method. Initially, the
-              Harmony Regridding Service will use Elliptical Weighted Averaging
-              to interpolate when needed. The message should either specify
-              this interpolation method, or not specify one at all.
+        """Validates that the contents of the Harmony message provides all
+        necessary parameters.
+
+        For an input Harmony message to be considered valid it must:
+
+        * Contain a valid target grid, with `format.scaleExtent` and either
+          `format.scaleSize` or both `format.height` and `format.width`
+          fully populated.
+        * Not specify an incompatible target CRS. Initially, the target CRS
+          is limited to geographic. The message should either specify a
+          geographic CRS, or not specify one at all.
+        * Not specify an incompatible interpolation method. Initially, the
+          Harmony Regridding Service will use Elliptical Weighted Averaging
+          to interpolate when needed. The message should either specify
+          this interpolation method, or not specify one at all.
 
         """
         if not has_valid_crs(self.message):
@@ -68,54 +73,72 @@ def validate_message(self):
             raise InvalidTargetGrid()
 
     def process_item(self, item: Item, source: HarmonySource) -> Item:
-        """ Processes a single input STAC item. """
+        """Processes a single input STAC item."""
         try:
             working_directory = mkdtemp()
             results = item.clone()
             results.assets = {}
 
-            asset = next((item_asset for item_asset in item.assets.values()
-                          if 'data' in (item_asset.roles or [])))
+            asset = next(
+                (
+                    item_asset
+                    for item_asset in item.assets.values()
+                    if 'data' in (item_asset.roles or [])
+                )
+            )
 
             # Download the input:
-            input_filepath = download(asset.href, working_directory,
-                                      logger=self.logger, cfg=self.config,
-                                      access_token=self.message.accessToken)
+            input_filepath = download(
+                asset.href,
+                working_directory,
+                logger=self.logger,
+                cfg=self.config,
+                access_token=self.message.accessToken,
+            )
 
             transformed_file_name = regrid(self, input_filepath, source)
 
             # Stage the transformed output:
             transformed_mime_type = get_file_mime_type(transformed_file_name)
-            staged_url = self.stage_output(transformed_file_name, asset.href,
-                                           transformed_mime_type)
+            staged_url = self.stage_output(
+                transformed_file_name, asset.href, transformed_mime_type
+            )
 
-            return self.create_output_stac_item(item, staged_url,
-                                                transformed_mime_type)
+            return self.create_output_stac_item(item, staged_url, transformed_mime_type)
         except Exception as exception:
             self.logger.exception(exception)
             raise exception
         finally:
             rmtree(working_directory)
 
-    def stage_output(self, transformed_file: str, input_file: str,
-                     transformed_mime_type: Optional[str]) -> str:
-        """ Generate an output file name based on the input asset URL and the
-            operations performed to produce the output. Use this name to stage
-            the output in the S3 location specified in the input Harmony
-            message.
+    def stage_output(
+        self,
+        transformed_file: str,
+        input_file: str,
+        transformed_mime_type: Optional[str],
+    ) -> str:
+        """Generate an output file name based on the input asset URL and the
+        operations performed to produce the output. Use this name to stage
+        the output in the S3 location specified in the input Harmony
+        message.
 
         """
-        output_file_name = generate_output_filename(input_file,
-                                                    is_regridded=True)
-
-        return stage(transformed_file, output_file_name, transformed_mime_type,
-                     location=self.message.stagingLocation,
-                     logger=self.logger, cfg=self.config)
+        output_file_name = generate_output_filename(input_file, is_regridded=True)
+
+        return stage(
+            transformed_file,
+            output_file_name,
+            transformed_mime_type,
+            location=self.message.stagingLocation,
+            logger=self.logger,
+            cfg=self.config,
+        )
 
-    def create_output_stac_item(self, input_stac_item: Item, staged_url: str,
-                                transformed_mime_type: str) -> Item:
-        """ Create an output STAC item used to access the transformed and
-            staged output in S3.
+    def create_output_stac_item(
+        self, input_stac_item: Item, staged_url: str, transformed_mime_type: str
+    ) -> Item:
+        """Create an output STAC item used to access the transformed and
+        staged output in S3.
 
         """
         output_stac_item = input_stac_item.clone()
@@ -127,8 +150,10 @@ def create_output_stac_item(self, input_stac_item: Item, staged_url: str,
         output_stac_item.geometry = bbox_to_geometry(output_stac_item.bbox)
 
         output_stac_item.assets['data'] = Asset(
-            staged_url, title=basename(staged_url),
-            media_type=transformed_mime_type, roles=['data']
+            staged_url,
+            title=basename(staged_url),
+            media_type=transformed_mime_type,
+            roles=['data'],
         )
 
         return output_stac_item

harmony_regridding_service/exceptions.py

@@ -3,38 +3,45 @@
     application.
 
 """
+
 from harmony.util import HarmonyException
 
 
 class RegridderException(HarmonyException):
-    """ Base service exception. """
+    """Base service exception."""
+
     def __init__(self, message=None):
         super().__init__(message, 'sds/harmony-regridder')
 
 
 class InvalidTargetCRS(RegridderException):
-    """ Raised when a request specifies an unsupported target Coordinate
-        Reference System.
+    """Raised when a request specifies an unsupported target Coordinate
+    Reference System.
 
     """
+
     def __init__(self, target_crs: str):
         super().__init__(f'Target CRS not supported: "{target_crs}"')
 
 
 class InvalidInterpolationMethod(RegridderException):
-    """ Raised when a user specifies an unsupported interpolation method. """
+    """Raised when a user specifies an unsupported interpolation method."""
+
     def __init__(self, interpolation_method: str):
-        super().__init__('Interpolation method not supported: '
-                         f'"{interpolation_method}"')
+        super().__init__(
+            'Interpolation method not supported: ' f'"{interpolation_method}"'
+        )
 
 
 class InvalidTargetGrid(RegridderException):
-    """ Raised when a request specifies an incomplete or invalid grid. """
+    """Raised when a request specifies an incomplete or invalid grid."""
+
     def __init__(self):
         super().__init__('Insufficient or invalid target grid parameters.')
 
 
 class InvalidSourceDimensions(RegridderException):
-    """ Raised when a source granule does not meet the expected dimension shapes. """
+    """Raised when a source granule does not meet the expected dimension shapes."""
+
     def __init__(self, message: str):
         super().__init__(message)