Merge pull request #6 from nasa/implement-pre-commit

Author: owenlittlejohns

.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
+56dd43f69d901abbba6cfb765a98dee26ff71cfc

.github/pull_request_template.md

@@ -11,6 +11,6 @@ A short description of the changes in this PR.
 ## PR Acceptance Checklist
 * [ ] Jira ticket acceptance criteria met.
 * [ ] `CHANGELOG.md` updated to include high level summary of PR changes.
-* [ ] `VERSION` updated if publishing a release.
+* [ ] `docker/service_version.txt` updated if publishing a release.
 * [ ] Tests added/updated and passing.
 * [ ] Documentation updated (if needed).

.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

@@ -1,13 +1,19 @@
+## v1.0.4
+### 2024-04-05
+
+This version of HOSS implements `black` code formatting across the repository.
+There should be no functional changes in the service.
+
 ## v1.0.3
-### 2024-3-29
+### 2024-03-29
 
-This version of HOSS handles the error in the crs_wkt attribute in ATL19 where the 
-north polar crs variable has a leading iquotation mark escaped by back slash in the 
-crs_wkt attribute. This causes errors when the projection is being interpreted from 
-the crs variable attributes. 
+This version of HOSS handles the error in the crs_wkt attribute in ATL19 where the
+north polar crs variable has a leading iquotation mark escaped by back slash in the
+crs_wkt attribute. This causes errors when the projection is being interpreted from
+the crs variable attributes.
 
 ## v1.0.2
-### 2024-2-26
+### 2024-02-26
 
 This version of HOSS correctly handles edge-aligned geographic collections by
 adding the attribute `cell_alignment` with the value `edge` to `hoss_config.json`

README.md

@@ -240,6 +240,39 @@ newest release of the code (starting at the top of the file).
 ## vX.Y.Z
 ```
 
+### 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`.
+
 ## Get in touch:
 
 You can reach out to the maintainers of this repository via email:

docker/service_version.txt

@@ -1 +1 @@
-1.0.3
+1.0.4

docker/tests.Dockerfile

@@ -16,7 +16,7 @@ ENV PYTHONDONTWRITEBYTECODE=1
 COPY tests/pip_test_requirements.txt .
 RUN conda run --name hoss 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
 
 # Set conda environment to hoss, as conda run will not stream logging.

docs/HOSS_DAAC_Operator_Documentation.ipynb

@@ -170,8 +170,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "temporal_range = {'start': datetime(2020, 1, 1, 0, 0, 0),\n",
-    "                  'stop': datetime(2020, 1, 31, 23, 59, 59)}"
+    "temporal_range = {\n",
+    "    'start': datetime(2020, 1, 1, 0, 0, 0),\n",
+    "    'stop': datetime(2020, 1, 31, 23, 59, 59),\n",
+    "}"
    ]
   },
   {
@@ -273,14 +275,19 @@
    "outputs": [],
    "source": [
     "# Define the request:\n",
-    "variable_subset_request = Request(collection=collection, variables=[variable_to_subset], max_results=1)\n",
+    "variable_subset_request = Request(\n",
+    "    collection=collection, variables=[variable_to_subset], max_results=1\n",
+    ")\n",
     "\n",
     "# Submit the request and download the results\n",
     "variable_subset_job_id = harmony_client.submit(variable_subset_request)\n",
     "harmony_client.wait_for_processing(variable_subset_job_id, show_progress=True)\n",
-    "variable_subset_outputs = [file_future.result()\n",
-    "                           for file_future\n",
-    "                           in harmony_client.download_all(variable_subset_job_id, overwrite=True)]\n",
+    "variable_subset_outputs = [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        variable_subset_job_id, overwrite=True\n",
+    "    )\n",
+    "]\n",
     "\n",
     "replace(variable_subset_outputs[0], 'hoss_variable_subset.nc4')\n",
     "\n",
@@ -308,15 +315,22 @@
    "outputs": [],
    "source": [
     "# Define the request:\n",
-    "temporal_subset_request = Request(collection=collection, temporal=temporal_range,\n",
-    "                                  variables=[variable_to_subset], max_results=1)\n",
+    "temporal_subset_request = Request(\n",
+    "    collection=collection,\n",
+    "    temporal=temporal_range,\n",
+    "    variables=[variable_to_subset],\n",
+    "    max_results=1,\n",
+    ")\n",
     "\n",
     "# Submit the request and download the results\n",
     "temporal_subset_job_id = harmony_client.submit(temporal_subset_request)\n",
     "harmony_client.wait_for_processing(temporal_subset_job_id, show_progress=True)\n",
-    "temporal_subset_outputs = [file_future.result()\n",
-    "                           for file_future\n",
-    "                           in harmony_client.download_all(temporal_subset_job_id, overwrite=True)]\n",
+    "temporal_subset_outputs = [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        temporal_subset_job_id, overwrite=True\n",
+    "    )\n",
+    "]\n",
     "\n",
     "replace(temporal_subset_outputs[0], 'hoss_temporal_subset.nc4')\n",
     "\n",
@@ -351,14 +365,17 @@
    "outputs": [],
    "source": [
     "# Define the request:\n",
-    "bbox_subset_request = Request(collection=collection, spatial=bounding_box, max_results=1)\n",
+    "bbox_subset_request = Request(\n",
+    "    collection=collection, spatial=bounding_box, max_results=1\n",
+    ")\n",
     "\n",
     "# Submit the request and download the results\n",
     "bbox_subset_job_id = harmony_client.submit(bbox_subset_request)\n",
     "harmony_client.wait_for_processing(bbox_subset_job_id, show_progress=True)\n",
-    "bbox_subset_outputs = [file_future.result()\n",
-    "                       for file_future\n",
-    "                       in harmony_client.download_all(bbox_subset_job_id, overwrite=True)]\n",
+    "bbox_subset_outputs = [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(bbox_subset_job_id, overwrite=True)\n",
+    "]\n",
     "\n",
     "replace(bbox_subset_outputs[0], 'hoss_bbox_subset.nc4')\n",
     "\n",
@@ -389,14 +406,19 @@
    "outputs": [],
    "source": [
     "# Define the request:\n",
-    "shape_file_subset_request = Request(collection=collection, shape='shape_files/bermuda_triangle.geo.json', max_results=1)\n",
+    "shape_file_subset_request = Request(\n",
+    "    collection=collection, shape='shape_files/bermuda_triangle.geo.json', max_results=1\n",
+    ")\n",
     "\n",
     "# Submit the request and download the results\n",
     "shape_file_subset_job_id = harmony_client.submit(shape_file_subset_request)\n",
     "harmony_client.wait_for_processing(shape_file_subset_job_id, show_progress=True)\n",
-    "shape_file_subset_outputs = [file_future.result()\n",
-    "                             for file_future\n",
-    "                             in harmony_client.download_all(shape_file_subset_job_id, overwrite=True)]\n",
+    "shape_file_subset_outputs = [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        shape_file_subset_job_id, overwrite=True\n",
+    "    )\n",
+    "]\n",
     "\n",
     "replace(shape_file_subset_outputs[0], 'hoss_shape_file_subset.nc4')\n",
     "# Inspect the results:\n",

docs/HOSS_User_Documentation.ipynb

@@ -127,14 +127,19 @@
    "source": [
     "variables = ['atmosphere_cloud_liquid_water_content']\n",
     "\n",
-    "variable_subset_request = Request(collection=ghrc_collection, variables=variables, granule_id=[ghrc_granule_id])\n",
+    "variable_subset_request = Request(\n",
+    "    collection=ghrc_collection, variables=variables, granule_id=[ghrc_granule_id]\n",
+    ")\n",
     "variable_subset_job_id = harmony_client.submit(variable_subset_request)\n",
     "\n",
     "print(f'Processing job: {variable_subset_job_id}')\n",
     "\n",
-    "for filename in [file_future.result()\n",
-    "                 for file_future\n",
-    "                 in harmony_client.download_all(variable_subset_job_id, overwrite=True, directory=demo_directory)]:\n",
+    "for filename in [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        variable_subset_job_id, overwrite=True, directory=demo_directory\n",
+    "    )\n",
+    "]:\n",
     "    print(f'Downloaded: {filename}')"
    ]
   },
@@ -157,14 +162,19 @@
    "source": [
     "gpm_bounding_box = BBox(w=45, s=-45, e=75, n=-15)\n",
     "\n",
-    "bbox_request = Request(collection=gpm_collection, spatial=gpm_bounding_box, granule_id=[gpm_granule_id])\n",
+    "bbox_request = Request(\n",
+    "    collection=gpm_collection, spatial=gpm_bounding_box, granule_id=[gpm_granule_id]\n",
+    ")\n",
     "bbox_job_id = harmony_client.submit(bbox_request)\n",
     "\n",
     "print(f'Processing job: {bbox_job_id}')\n",
     "\n",
-    "for filename in [file_future.result()\n",
-    "                 for file_future\n",
-    "                 in harmony_client.download_all(bbox_job_id, overwrite=True, directory=demo_directory)]:\n",
+    "for filename in [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        bbox_job_id, overwrite=True, directory=demo_directory\n",
+    "    )\n",
+    "]:\n",
     "    print(f'Downloaded: {filename}')"
    ]
   },
@@ -196,15 +206,22 @@
     "gpm_bounding_box = BBox(w=45, s=-45, e=75, n=-15)\n",
     "gpm_variables = ['/Grid/precipitationCal']\n",
     "\n",
-    "combined_request = Request(collection=gpm_collection, spatial=gpm_bounding_box,\n",
-    "                           granule_id=[gpm_granule_id], variables=gpm_variables)\n",
+    "combined_request = Request(\n",
+    "    collection=gpm_collection,\n",
+    "    spatial=gpm_bounding_box,\n",
+    "    granule_id=[gpm_granule_id],\n",
+    "    variables=gpm_variables,\n",
+    ")\n",
     "combined_job_id = harmony_client.submit(combined_request)\n",
     "\n",
     "print(f'Processing job: {combined_job_id}')\n",
     "\n",
-    "for filename in [file_future.result()\n",
-    "                 for file_future\n",
-    "                 in harmony_client.download_all(combined_job_id, overwrite=True, directory=demo_directory)]:\n",
+    "for filename in [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        combined_job_id, overwrite=True, directory=demo_directory\n",
+    "    )\n",
+    "]:\n",
     "    print(f'Downloaded: {filename}')"
    ]
   },
@@ -229,14 +246,19 @@
    "source": [
     "ghrc_bounding_box = BBox(w=-30, s=-50, e=30, n=0)\n",
     "\n",
-    "edge_request = Request(collection=ghrc_collection, spatial=ghrc_bounding_box, granule_id=[ghrc_granule_id])\n",
+    "edge_request = Request(\n",
+    "    collection=ghrc_collection, spatial=ghrc_bounding_box, granule_id=[ghrc_granule_id]\n",
+    ")\n",
     "edge_job_id = harmony_client.submit(edge_request)\n",
     "\n",
     "print(f'Processing job: {edge_job_id}')\n",
     "\n",
-    "for filename in [file_future.result()\n",
-    "                 for file_future\n",
-    "                 in harmony_client.download_all(edge_job_id, overwrite=True, directory=demo_directory)]:\n",
+    "for filename in [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        edge_job_id, overwrite=True, directory=demo_directory\n",
+    "    )\n",
+    "]:\n",
     "    print(f'Downloaded: {filename}')"
    ]
   },
@@ -268,15 +290,22 @@
     "point_in_pixel_box = BBox(w=43.2222, s=-25.1111, e=43.2222, n=-25.1111)\n",
     "gpm_variables = ['/Grid/precipitationCal']\n",
     "\n",
-    "point_in_pixel_request = Request(collection=gpm_collection, spatial=point_in_pixel_box,\n",
-    "                                 granule_id=[gpm_granule_id], variables=gpm_variables)\n",
+    "point_in_pixel_request = Request(\n",
+    "    collection=gpm_collection,\n",
+    "    spatial=point_in_pixel_box,\n",
+    "    granule_id=[gpm_granule_id],\n",
+    "    variables=gpm_variables,\n",
+    ")\n",
     "point_in_pixel_job_id = harmony_client.submit(point_in_pixel_request)\n",
     "\n",
     "print(f'Processing job: {point_in_pixel_job_id}')\n",
     "\n",
-    "for filename in [file_future.result()\n",
-    "                 for file_future\n",
-    "                 in harmony_client.download_all(point_in_pixel_job_id, overwrite=True, directory=demo_directory)]:\n",
+    "for filename in [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        point_in_pixel_job_id, overwrite=True, directory=demo_directory\n",
+    "    )\n",
+    "]:\n",
     "    print(f'Downloaded: {filename}')"
    ]
   },
@@ -298,15 +327,22 @@
     "corner_point_box = BBox(w=160, s=20, e=160, n=20)\n",
     "gpm_variables = ['/Grid/precipitationCal']\n",
     "\n",
-    "corner_point_request = Request(collection=gpm_collection, spatial=corner_point_box,\n",
-    "                                 granule_id=[gpm_granule_id], variables=gpm_variables)\n",
+    "corner_point_request = Request(\n",
+    "    collection=gpm_collection,\n",
+    "    spatial=corner_point_box,\n",
+    "    granule_id=[gpm_granule_id],\n",
+    "    variables=gpm_variables,\n",
+    ")\n",
     "corner_point_job_id = harmony_client.submit(corner_point_request)\n",
     "\n",
     "print(f'Processing job: {corner_point_job_id}')\n",
     "\n",
-    "for filename in [file_future.result()\n",
-    "                 for file_future\n",
-    "                 in harmony_client.download_all(corner_point_job_id, overwrite=True, directory=demo_directory)]:\n",
+    "for filename in [\n",
+    "    file_future.result()\n",
+    "    for file_future in harmony_client.download_all(\n",
+    "        corner_point_job_id, overwrite=True, directory=demo_directory\n",
+    "    )\n",
+    "]:\n",
     "    print(f'Downloaded: {filename}')"
    ]
   }

docs/requirements.txt

@@ -1,4 +1,4 @@
-# 
+#
 # These requirements are used by the documentation Jupyter notebooks in the
 # harmony-opendap-subsetter/docs directory.
 #