Fix ruff errors and modernize project config and build

.github/actions/test-and-coverage/action.yml

@@ -0,0 +1,41 @@
+name: Test and coverage
+description: Set up Python, run checks, and upload coverage to Codecov.
+
+inputs:
+  codecov-token:
+    description: Token used to upload coverage to Codecov.
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: 🐍 Set up Python
+      uses: actions/setup-python@v6.2.0
+      with:
+        python-version-file: .python-version
+        cache: pip
+        cache-dependency-path: pyproject.toml
+
+    - name: 📥 Install dependencies
+      shell: bash
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y libkrb5-dev
+
+    - name: 🏗 Install module
+      shell: bash
+      run: pip install .[tests]
+
+    - name: 🧶 Lint
+      shell: bash
+      run: ruff check --output-format=github .
+
+    - name: 🧪 Run pytest
+      shell: bash
+      run: pytest
+
+    - name: ⬆️ Upload coverage to Codecov
+      uses: codecov/codecov-action@v7
+      with:
+        token: ${{ inputs.codecov-token }}
+        files: ./cov.xml

.github/copilot-instructions.md

@@ -1,5 +1,21 @@
 # palletjack - Agent Onboarding Guide
 
-## Commits
+## Project Structure
 
-Use conventional commits as outlined here: https://github.com/agrc/release-composite-action/blob/main/README.md#commits
+Palletjack updates ArcGIS Online feature services from external data using an extract-transform-load workflow. Keep source-specific loading in `extract.py`, DataFrame cleanup and geocoding in `transform.py`, and ArcGIS service updates in `load.py`. Put shared helpers, such as retry behavior, in `utils.py`.
+
+Preserve pandas DataFrame interfaces. Use type hints and Google-style docstrings for public APIs. Follow the existing module-level logging pattern: `logger = logging.getLogger(__name__)`.
+
+## Python Environment and Validation
+
+Use the Conda environment named `palletjack` for all Python commands, tests, and build validation. Python 3.11 through 3.14 are supported.
+
+Run focused tests for changed behavior with `pytest tests/test_<module>.py`, then run `pytest` when the change affects shared or public behavior. Run `ruff check .` before completion. Do not introduce unconfigured formatters or type checkers.
+
+Tests use `pytest-mock`; prefer `mocker.patch(..., autospec=True)` where practical. Use standard assertions and `pandas.testing` helpers when comparing DataFrames.
+
+## Documentation and Commits
+
+Keep public documentation in Google-style docstrings, which are rendered with pdoc3. Update README or docs examples when changing the public API.
+
+Use conventional commits as outlined here: https://github.com/agrc/release-composite-action/blob/main/README.md#commits. Use a relevant scope when helpful, such as `fix(extract):`, `feat(load):`, or `docs:`.

.github/workflows/pull_request.yml

@@ -20,29 +20,7 @@ jobs:
         with:
           show-progress: false
 
-      - name: 🐍 Set up Python
-        uses: actions/setup-python@v6.2.0
+      - name: 🧪 Test and upload coverage
+        uses: ./.github/actions/test-and-coverage
         with:
-          python-version-file: .python-version
-          cache: pip
-          cache-dependency-path: setup.py
-
-      - name: 📥 Install dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y libkrb5-dev
-
-      - name: 🏗 Install module
-        run: pip install .[tests]
-
-      - name: 🧶 Lint
-        run: ruff check --output-format=github .
-
-      - name: 🧪 Run pytest
-        run: pytest
-
-      - name: ⬆️ Upload coverage to Codecov
-        uses: codecov/codecov-action@v7
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          files: ./cov.xml
+          codecov-token: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/push.yml

@@ -11,7 +11,22 @@
   cancel-in-progress: true
 
 jobs:
+  update-base-coverage:
+    name: Update base code coverage
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: ⬇️ Set up code
+        uses: actions/checkout@v7
+        with:
+          show-progress: false
+
+      - name: 🧪 Test and upload coverage
+        uses: ./.github/actions/test-and-coverage
+        with:
+          codecov-token: ${{ secrets.CODECOV_TOKEN }}
+
   release-please:
     name: Create release
     runs-on: ubuntu-latest
     permissions:

.github/workflows/release.yml

@@ -21,7 +21,7 @@ jobs:
         with:
           python-version-file: .python-version
           cache: pip
-          cache-dependency-path: setup.py
+          cache-dependency-path: pyproject.toml
 
       - name: 📦 Build package
         run: pipx run build

.vscode/settings.json

@@ -1,5 +1,6 @@
 {
   "cSpell.words": [
+    "addopts",
     "agol",
     "AGRC",
     "arcgis",
@@ -8,6 +9,7 @@
     "astype",
     "authed",
     "auths",
+    "autospec",
     "caplog",
     "casefolded",
     "castable",
@@ -37,6 +39,7 @@
     "Geocoder",
     "geodatabase",
     "geodataframe",
+    "geodatasets",
     "geojsons",
     "geopandas",
     "getbuffer",
@@ -54,15 +57,19 @@
     "itertuples",
     "keyscan",
     "knownhosts",
+    "libkrb",
     "localpath",
     "mapserv",
     "minval",
+    "minversion",
     "nans",
     "ndarray",
     "nojekyll",
+    "norecursedirs",
     "oids",
     "Overwriter",
     "palletjack",
+    "paramiko",
     "PARENTOBJECTID",
     "pdoc",
     "PGSQL",
@@ -74,33 +81,31 @@
     "pyogrio",
     "pypa",
     "pypi",
+    "pyproject",
     "pysftp",
     "pytest",
     "reclassifier",
     "Reproject",
     "sedf",
+    "setuptools",
     "sftploader",
     "SOQL",
     "sqlalchemy",
     "subsetted",
     "subsetting",
+    "testpaths",
     "trycount",
     "ugrc",
     "ujson",
     "unclassed",
+    "unconfigured",
     "upserted",
     "upserting",
     "upserts",
     "webmap",
     "wkid",
     "yapf"
   ],
-  "coverage-gutters.highlightdark": "rgb(61, 153, 112, .05)",
-  "coverage-gutters.noHighlightDark": "rgb(255, 65, 54, .05)",
-  "coverage-gutters.partialHighlightDark": "rgb(255, 133, 27, .05)",
-  "coverage-gutters.showGutterCoverage": true,
-  "coverage-gutters.showLineCoverage": true,
-  "coverage-gutters.showRulerCoverage": false,
   "editor.codeActionsOnSave": {
     "source.organizeImports": "explicit"
   },

README.md

@@ -13,7 +13,7 @@ Pallet jack: [forklift's](https://www.github.com/agrc/forklift) little brother.
 
 ## Dependencies
 
-`palletjack` relies on the dependencies listed in `setup.py`. These are all available on PyPI and can be installed in most environments, including Google Cloud Functions.
+`palletjack` relies on the dependencies listed in `pyproject.toml`. These are all available on PyPI and can be installed in most environments, including Google Cloud Functions.
 
 The `arcgis` library does all the heavy lifting for spatial data. If the `arcpy` library is not available (such as in a cloud function), it relies on `shapely` for its geometry engine.
 
@@ -34,20 +34,20 @@ The `arcgis` library does all the heavy lifting for spatial data. If the `arcpy`
 
    #: Load the data from a Google Sheet
    gsheet_extractor = extract.GSheetLoader(path_to_service_account_json)
-   sheet_df = gsheet_extractor.load_specific_worksheet_into_dataframe(sheet_id, 'title of desired sheet', by_title=True)
+   sheet_df = gsheet_extractor.load_specific_worksheet_into_dataframe(sheet_id, "title of desired sheet", by_title=True)
 
    #: Convert the data to points using lat/long fields, clean for uploading
-   spatial_df = pd.DataFrame.spatial.from_xy(input_df, x_column='longitude', y_column='latitude')
+   spatial_df = pd.DataFrame.spatial.from_xy(input_df, x_column="longitude", y_column="latitude")
    renamed_df = transform.DataCleaning.rename_dataframe_columns_for_agol(spatial_df)
-   cleaned_df = transform.DataCleaning.switch_to_nullable_int(renamed_df, ['an_int_field_with_null_values'])
+   cleaned_df = transform.DataCleaning.switch_to_nullable_int(renamed_df, ["an_int_field_with_null_values"])
 
    #: Truncate the existing feature service data and load the new data
-   gis = arcgis.gis.GIS('my_agol_org_url', 'username', 'super-duper-secure-password')
-   updater = load.ServiceUpdater(gis, 'feature_service_item_id')
+   gis = arcgis.gis.GIS("my_agol_org_url", "username", "super-duper-secure-password")
+   updater = load.ServiceUpdater(gis, "feature_service_item_id")
    updates = updater.truncate_and_load(cleaned_df)
 
    #: It even works with stand-alone tables!
-   table_updater = load.TableUpdater(gis, 'table_service_item_id', service_type='table')
+   table_updater = load.TableUpdater(gis, "table_service_item_id", service_type="table")
    table_updates = table_updater.truncate_and_load(cleaned_df)
    ```
 

docs/README.md

@@ -57,9 +57,9 @@ palletjack takes full advantage of python's built-in [`logging`](https://docs.py
 The client can get a reference to the palletjack logger and add their handlers, formatters, etc to it alongside its own logger:
 
 ```python
-myapp_logger = logging.getLogger('my_app')
+myapp_logger = logging.getLogger("my_app")
 myapp_logger.setLevel(logging.INFO)
-palletjack_logger = logging.getLogger('palletjack')
+palletjack_logger = logging.getLogger("palletjack")
 palletjack_logger.setLevel(logging.INFO)
 #: set up handlers and formatters
 #: ...

docs/examples.py

@@ -7,6 +7,7 @@
 import arcgis
 import pandas as pd
 from arcgis.features import GeoAccessor, GeoSeriesAccessor
+
 from palletjack import extract, load, transform, utils
 
 
@@ -122,5 +123,5 @@ def download_from_sftp_update_agol_reclassify_map():
     #: Try to clean up the tempdir (we don't use a context manager); print any errors as a heads up
     try:
         tempdir.cleanup()
-    except Exception as error:
+    except OSError as error:
         print(error)

pyproject.toml

@@ -1,8 +1,63 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "ugrc-palletjack"
+version = "6.0.4"
+description = "Updating AGOL feature services with data from external tables."
+readme = { file = "README.md", content-type = "text/markdown" }
+requires-python = ">=3.11,<3.15"
+authors = [{ name = "UGRC Developers", email = "ugrc-developers@utah.gov" }]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Topic :: Utilities",
+]
+keywords = ["gis"]
+dependencies = [
+  "arcgis>=2.3,<2.4.3",
+  "geopandas>=0.14,<1.2",
+  "geodatasets>=2023.12,<=2026.5.1",
+  "pg8000>=1.29,<1.32",
+  "psycopg2-binary==2.9.*",
+  "pygsheets==2.0.*",
+  "pysftp==0.2.9",
+  "setuptools>=80,<83",
+  "paramiko>=3.0,<6.0",
+  "SQLAlchemy>=1.4,<2.1",
+]
+
+[project.urls]
+Homepage = "https://github.com/agrc/palletjack"
+"Issue Tracker" = "https://github.com/agrc/palletjack/issues"
+
+[project.optional-dependencies]
+tests = [
+  "pdoc3>=0.10,<0.12",
+  "pytest-cov>=3,<8",
+  "pytest-instafail~=0.5",
+  "pytest-mock>=3.10,<3.16",
+  "pytest-watch~=4.2",
+  "pytest>=6,<10",
+  "requests-mock==1.*",
+  "ruff==0.*",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/palletjack"]
+
+[tool.hatch.build]
+exclude = ["/.github", "/.vscode"]
+
 [tool.ruff]
 line-length = 120
 lint.ignore = ["E501"]
+
 [tool.ruff.lint.per-file-ignores]
 "tests/*.py" = ["F841"]
+
 [tool.pytest.ini_options]
 minversion = "6.0"
 testpaths = ["tests", "src"]