Update workflows

.github/workflows/black.yml

@@ -0,0 +1,14 @@
+name: Black
+
+on: push
+
+jobs:
+  black:
+    runs-on: ubuntu-24.04
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+      - uses: psf/black@stable
+        with:
+          options: "--check"

.github/workflows/pypi-publish.yml

@@ -4,6 +4,7 @@ on:
   push:
     tags:
       - '[0-9]+.[0-9]+.[0-9]+'
+      - '[0-9]+.[0-9]+.[0-9]+\.dev[0-9]+'
 
 jobs:
   publish:
@@ -16,14 +17,18 @@ jobs:
       uses: actions/setup-python@v2
       with:
         python-version: '3.12'
-    - name: Install dependencies
+    - name: Install Poetry
       run: |
-        python -m pip install --upgrade pip
-        pip install setuptools wheel twine sphinx
-    - name: Build and publish
+        curl -sSL https://install.python-poetry.org | python3 -
+    - name: Install and publish project
       env:
-        TWINE_USERNAME: ${{ secrets.pcic_at_pypi_username }}
-        TWINE_PASSWORD: ${{ secrets.pcic_at_pypi_password }}
+        PCIC_PYPI_USERNAME: ${{ secrets.pcic_at_pypi_username }}
+        PCIC_PYPI_PASSWORD: ${{ secrets.pcic_at_pypi_password }}
       run: |
-        python setup.py sdist bdist_wheel
-        twine upload --repository-url https://pypi.pacificclimate.org/ --skip-existing -u $TWINE_USERNAME -p $TWINE_PASSWORD dist/*
+        # Configure Poetry to publish to PCIC private package repository
+        poetry config repositories.pcic https://pypi.pacificclimate.org/
+        poetry config http-basic.pcic $PCIC_PYPI_USERNAME $PCIC_PYPI_PASSWORD
+        # Install, build and publish
+        # poetry install
+        poetry build
+        poetry publish -r pcic

ce/api/__init__.py

@@ -1,10 +1,9 @@
-""" PCIC Climate Explorer backend API module
+"""PCIC Climate Explorer backend API module
 
 .. moduleauthor:: James Hiebert <hiebert@uvic.ca>
 
 """
 
-
 import inspect
 from datetime import datetime
 
@@ -169,8 +168,10 @@ def format_dates(obj):
     if not isinstance(obj, dict):
         return obj
     return {
-        key: val.strftime(time_format)
-        if isinstance(val, datetime)
-        else format_dates(val)
+        key: (
+            val.strftime(time_format)
+            if isinstance(val, datetime)
+            else format_dates(val)
+        )
         for key, val in obj.items()
     }

ce/api/data.py

@@ -1,5 +1,4 @@
-"""module for requesting data across multiple files through the API
-"""
+"""module for requesting data across multiple files through the API"""
 
 import numpy as np
 import os
@@ -61,9 +60,9 @@ def data(
         climatological_statistic (str): Statistical operation applied to variable in a
             climatological dataset (e.g "mean", "standard_deviation",
             "percentile). Defaulted to "mean".
-        
+
         percentile (float): if climatological_statistic is "percentile", specifies what
-            percentile value to use. A percentile value must be provided if the 
+            percentile value to use. A percentile value must be provided if the
             climatological_statistic is "percentile".
 
         is_thredds (bool): If set to `True` the filepath will be searched for

ce/api/geo.py

@@ -219,7 +219,7 @@ def polygon_to_mask(nc, resource, poly, variable):
 
 def make_masked_file_key(nc, resource, wkt, varname):
     """generates a key suitable for characterizing a masked netCDF file:
-       filename and polygon"""
+    filename and polygon"""
     return (resource, wkt)
 
 

ce/api/grid.py

@@ -1,5 +1,4 @@
-"""module for requesting the lat/lon grid for a given model run file
-"""
+"""module for requesting the lat/lon grid for a given model run file"""
 
 from sqlalchemy.orm.exc import NoResultFound
 

ce/api/health/regions.py

@@ -1,4 +1,5 @@
 """module for requesting a summary of stored region data status."""
+
 import os
 from csv import DictReader
 from ce.api.multimeta import multimeta
@@ -8,9 +9,9 @@
 
 def region_status(region, metadata):
     """Opens a stored data file for a region, checks the modtime of the
-      stored data against the current versions of each file (as listed
-      in the metadata) and returns a list of the each file from which
-      stored data was calculated and its status."""
+    stored data against the current versions of each file (as listed
+    in the metadata) and returns a list of the each file from which
+    stored data was calculated and its status."""
 
     date_format = "%Y-%m-%dT%H:%M:%SZ"
 

ce/api/lister.py

@@ -1,11 +1,9 @@
-"""module for requesting unique_ids from ensemble or model short name
-"""
+"""module for requesting unique_ids from ensemble or model short name"""
 
 from modelmeta import Ensemble
 
 
 def lister(sesh, ensemble_name="ce_files", model=None):
-
     """
     Args
         sesh (sqlalchemy.orm.session.Session): A database Session object

ce/api/metadata.py

@@ -1,5 +1,5 @@
-"""module for requesting metadata for one single file through the API
-"""
+"""module for requesting metadata for one single file through the API"""
+
 from sqlalchemy.orm.exc import NoResultFound
 
 from modelmeta import DataFile
@@ -131,4 +131,10 @@ def metadata(sesh, model_id, extras=""):
         }
     )
 
-    return {model_id: {**base_values, **requested_extra_values, **time_values,}}
+    return {
+        model_id: {
+            **base_values,
+            **requested_extra_values,
+            **time_values,
+        }
+    }

ce/api/models.py

@@ -1,11 +1,9 @@
-"""module for requesting list of available models
-"""
+"""module for requesting list of available models"""
 
 from modelmeta import Ensemble
 
 
 def models(sesh, ensemble_name="ce_files"):
-
     """
     Args
         sesh (sqlalchemy.orm.session.Session): A database Session object

ce/api/multimeta.py

@@ -1,5 +1,4 @@
-"""module for requesting metadata from multiple files based on model or ensemble
-"""
+"""module for requesting metadata from multiple files based on model or ensemble"""
 
 from modelmeta import DataFile, Model, Emission, Run
 from modelmeta import DataFileVariableGridded, VariableAlias, TimeSet
@@ -47,7 +46,7 @@ def multimeta(
         climatological_statistic(str): Statistical operation applied to variable in a
             climatological dataset (e.g "mean", "standard_deviation",
             "percentile"). Defaulted to "mean".
-        
+
         percentile(float): optionally, specify a a single percentile values to filter on.
 
     Returns:

ce/api/multistats.py

@@ -1,5 +1,4 @@
-"""module for requesting stats from multiple files based on model or ensemble
-"""
+"""module for requesting stats from multiple files based on model or ensemble"""
 
 from ce.api.stats import stats
 from ce.api.util import search_for_unique_ids

ce/api/stats.py

@@ -1,5 +1,4 @@
-"""module for requsting summary statistics, averaged across a region
-"""
+"""module for requsting summary statistics, averaged across a region"""
 
 import numpy as np
 import numpy.ma as ma
@@ -26,7 +25,12 @@
 
 
 def stats(
-    sesh, id_, time, area, variable, is_thredds=False,
+    sesh,
+    id_,
+    time,
+    area,
+    variable,
+    is_thredds=False,
 ):
     """Request and calculate summary statistics averaged across a region
 
@@ -133,7 +137,7 @@ def stats(
 
 def array_stats(array):
     """Return the min, max, mean, median, standard deviation and number
-       of cells of a 3d data grid (numpy.ma.MaskedArray)
+    of cells of a 3d data grid (numpy.ma.MaskedArray)
     """
     return {
         "min": np.min(array).item(),

ce/api/streamflow/downstream.py

@@ -14,6 +14,7 @@
 spatial tuple to a data index tuple and vice versa, also switch the
 dimension order accordingly.
 """
+
 from gettext import dpgettext
 from this import d
 from contexttimer import Timer
@@ -53,7 +54,7 @@ def downstream(sesh, station, ensemble_name):
     and converting their contents to `VicDataGrid` objects for consumption by
     `downstream_worker`, which as its name suggests, does most of the work.
     """
-    
+
     station_lonlat = setup(station)
 
     with get_time_invariant_variable_dataset(
@@ -75,7 +76,8 @@ def downstream(sesh, station, ensemble_name):
 
 
 def downstream_worker(
-    station_lonlat, flow_direction,
+    station_lonlat,
+    flow_direction,
 ):
     """Compute the watershed.
 
@@ -136,16 +138,16 @@ def build_downstream_watershed(target, routing, direction_map, debug=False):
         represented by an offset of +1 or -1, respectively.
     :param debug: Boolean indicating whether this function should compute
         and return debug information.
-    :return: Tuple of cells (cell indices as tuples) that drain from `target` in 
+    :return: Tuple of cells (cell indices as tuples) that drain from `target` in
         a downstream flow order.
 
     Notes:
 
     - In this function, a cell is represented by an (x, y) index pair.
 
-    - Routing graphs can and in practice do contain cycles. Variable 
-    `stream` is used to check whether a cell has already been 
-    visited during the traversal of the routing graph, i.e., whether we 
+    - Routing graphs can and in practice do contain cycles. Variable
+    `stream` is used to check whether a cell has already been
+    visited during the traversal of the routing graph, i.e., whether we
     are cycling, and if so not to repeat that subgraph.
     """
 
@@ -156,10 +158,12 @@ def downstream(stream):
         cell_routing = routing[stream[-1]]
         downstream_neighbour = vec_add(stream[-1], direction_map[int(cell_routing)])
 
-        if downstream_neighbour in stream or not is_valid_index(downstream_neighbour, routing.shape):
+        if downstream_neighbour in stream or not is_valid_index(
+            downstream_neighbour, routing.shape
+        ):
             return stream
 
         stream += (downstream_neighbour,)
         return downstream(stream)
-        
-    return downstream((target,))
+
+    return downstream((target,))

ce/api/streamflow/shared.py

@@ -55,7 +55,7 @@ def is_downstream(neighbour, cell, routing, direction_map):
 
 
 def VIC_direction_matrix(lat_step, lon_step):
-    """ Return a VIC direction matrix, which is a matrix indexed by the VIC
+    """Return a VIC direction matrix, which is a matrix indexed by the VIC
     streamflow direction codes 0...9, with the value at index `i` indicating
     the offsets from the data index in a streamflow file required to
     step in that streamflow direction.

ce/api/streamflow/watershed.py

@@ -14,6 +14,7 @@
 spatial tuple to a data index tuple and vice versa, also switch the
 dimension order accordingly.
 """
+
 import math
 from contexttimer import Timer
 
@@ -59,17 +60,21 @@ def watershed(sesh, station, ensemble_name):
     """
     station_lonlat = setup(station)
 
-    with get_time_invariant_variable_dataset(
-        sesh, ensemble_name, "flow_direction"
-    ) as flow_direction_ds, get_time_invariant_variable_dataset(
-        sesh, ensemble_name, "elev"
-    ) as elevation_ds, get_time_invariant_variable_dataset(
-        sesh, ensemble_name, "elevmin"
-    ) as elevation_min_ds, get_time_invariant_variable_dataset(
-        sesh, ensemble_name, "elevmax"
-    ) as elevation_max_ds, get_time_invariant_variable_dataset(
-        sesh, ensemble_name, "area"
-    ) as area_ds:
+    with (
+        get_time_invariant_variable_dataset(
+            sesh, ensemble_name, "flow_direction"
+        ) as flow_direction_ds,
+        get_time_invariant_variable_dataset(
+            sesh, ensemble_name, "elev"
+        ) as elevation_ds,
+        get_time_invariant_variable_dataset(
+            sesh, ensemble_name, "elevmin"
+        ) as elevation_min_ds,
+        get_time_invariant_variable_dataset(
+            sesh, ensemble_name, "elevmax"
+        ) as elevation_max_ds,
+        get_time_invariant_variable_dataset(sesh, ensemble_name, "area") as area_ds,
+    ):
         try:
             return worker(
                 station_lonlat,
@@ -218,7 +223,10 @@ def worker(
             "elevation_units": elevation_mean.units,
             "area_units": area.units,
         },
-        "melton_ratio": {"units": "km/km", "value": m_ratio,},
+        "melton_ratio": {
+            "units": "km/km",
+            "value": m_ratio,
+        },
         "boundary": geojson_feature(
             outline,
             properties={