add collection_id to items (#12)

* optionally use `collection` when creating an item

* update ruff

.gitignore

@@ -142,4 +142,4 @@ cython_debug/
 scratch
 .Trash-0
 .virtual_documents
-
+.envrc

.pre-commit-config.yaml

@@ -25,6 +25,6 @@ repos:
  - click != 8.1.0
  - stactools
  - repo: https://github.com/astral-sh/ruff-pre-commit
- rev: v0.0.288
+ rev: v0.6.0
  hooks:
  - id: ruff

CHANGELOG.md

@@ -9,7 +9,7 @@ number as needed.
 
 ## [Unreleased]
 
-- Nothing.
+- Add `collection_id` to items
 
 [Unreleased]: <https://github.com/stactools-packages/noaa-hrrr/tree/main/>
 

pyproject.toml

@@ -37,7 +37,7 @@ dev = [
  "pre-commit~=3.4",
  "pytest-cov~=4.1",
  "pytest~=7.4",
- "ruff==0.0.288",
+ "ruff==0.6.0",
 ]
 docs = ["pystac~=1.8", "ipykernel~=6.25", "jinja2~=3.1"]
 
@@ -60,7 +60,7 @@ strict = true
 mypy_path = "src"
 
 [tool.ruff]
-select = ["E", "F", "I"]
+lint.select = ["E", "F", "I"]
 
 [tool.setuptools.package-data]
 "stactools.noaa_hrrr.data" = ["*.csv.gz"]

scripts/update-examples

@@ -4,8 +4,9 @@ import shutil
 from datetime import datetime
 from pathlib import Path
 
-import stactools.noaa_hrrr.stac
 from pystac import CatalogType
+
+import stactools.noaa_hrrr.stac
 from stactools.noaa_hrrr.metadata import (
  CloudProvider,
  Product,

src/stactools/noaa_hrrr/commands.py

@@ -4,16 +4,13 @@
 
 import click
 from click import Command, Group
+
 from stactools.noaa_hrrr import stac
 from stactools.noaa_hrrr.constants import (
  COLLECTION_ID_FORMAT,
  EXTENDED_FORECAST_MAX_HOUR,
 )
-from stactools.noaa_hrrr.metadata import (
- CloudProvider,
- Product,
- Region,
-)
+from stactools.noaa_hrrr.metadata import CloudProvider, Product, Region
 
 logger = logging.getLogger(__name__)
 

src/stactools/noaa_hrrr/inventory.py

@@ -1,19 +1,20 @@
 """Each .grib file in the HRRR dataset contains dozens or hundreds of distinct variables
 that represent data along several dimensions. The inventory files published by NOAA are
-useful for the human-readable descriptions, but more reliable inventory dataframes can 
+useful for the human-readable descriptions, but more reliable inventory dataframes can
 be generated by reading the sidecar .grib2.idx files.
 
 The functions in this module generate the metadata required to define the coordinates
 along the forecast_valid x level dimensions on which specific variables have data. These
 dataframes are used to populate the datacube extension metadata for each collection.
 
 The dimensions of interest are:
-1. forecast_valid: either the average, minimum, maximum, or accumulated value for a 
+1. forecast_valid: either the average, minimum, maximum, or accumulated value for a
  specific time range, e.g. 3-4 hours, 0-1 day, etc.
  For forecast hour 0, the level is "analysis"
-2. level: the models generate predictions of many of the variables for various levels 
+2. level: the models generate predictions of many of the variables for various levels
  in the atmosphere, e.g. 0-9000 ft, cloud surface, top of atmosphere, etc.
 """
+
 import logging
 import multiprocessing as mp
 from datetime import datetime, timedelta
@@ -23,6 +24,7 @@
 
 import httpx
 import pandas as pd
+
 from stactools.noaa_hrrr.constants import (
  BYTE_SIZE,
  DESCRIPTION,

src/stactools/noaa_hrrr/metadata.py

@@ -8,6 +8,7 @@
 from parse import Result, parse
 from rasterio.crs import CRS
 from rasterio.warp import transform_bounds
+
 from stactools.noaa_hrrr.constants import (
  EXTENDED_FORECAST_MAX_HOUR,
  STANDARD_FORECAST_MAX_HOUR,

src/stactools/noaa_hrrr/stac.py

@@ -1,17 +1,11 @@
 import logging
 import multiprocessing as mp
 from datetime import datetime, timedelta
-from typing import Union
+from typing import Optional, Union
 
 import pandas as pd
 import pystac
-from pystac import (
- Collection,
- Extent,
- Item,
- SpatialExtent,
- TemporalExtent,
-)
+from pystac import Collection, Extent, Item, SpatialExtent, TemporalExtent
 from pystac.catalog import CatalogType
 from pystac.extensions.datacube import (
  DatacubeExtension,
@@ -23,6 +17,7 @@
 from pystac.extensions.item_assets import AssetDefinition, ItemAssetsExtension
 from pystac.item_collection import ItemCollection
 from pystac.provider import Provider, ProviderRole
+
 from stactools.noaa_hrrr.constants import (
  BYTE_SIZE,
  COLLECTION_ID_FORMAT,
@@ -438,6 +433,7 @@ def create_item(
  cloud_provider: CloudProvider,
  reference_datetime: datetime,
  forecast_hour: int,
+ collection: Optional[Collection] = None,
 ) -> Item:
  """Creates a STAC item for a region x product x cloud provider x reference_datetime
  (cycle run hour) combination.
@@ -487,6 +483,7 @@ def create_item(
  cloud_provider=cloud_provider,
  reference_datetime=reference_datetime,
  forecast_hour=forecast_hour,
+ collection=collection,
  )
 
 
@@ -497,6 +494,7 @@ def create_item_from_idx_df(
  cloud_provider: CloudProvider,
  reference_datetime: datetime,
  forecast_hour: int,
+ collection: Optional[Collection] = None,
 ) -> Item:
  """Creates a STAC item for a region x product x cloud provider x reference_datetime
  (cycle run hour) combination and a provided idx dataframe.
@@ -550,6 +548,7 @@ def create_item_from_idx_df(
  geometry=region_config.geometry_4326,
  bbox=region_config.bbox_4326,
  datetime=forecast_datetime,
+ collection=collection,
  properties={
  "forecast:reference_time": reference_datetime.strftime(
  "%Y-%m-%dT%H:%M:%SZ"
@@ -613,11 +612,17 @@ def create_item_safe(
  cloud_provider: CloudProvider,
  reference_datetime: datetime,
  forecast_hour: int,
+ collection: Optional[Collection],
 ) -> Union[Item, None]:
  """Try to create an item and raise a warning if it fails"""
  try:
  return create_item(
- region, product, cloud_provider, reference_datetime, forecast_hour
+ region,
+ product,
+ cloud_provider,
+ reference_datetime,
+ forecast_hour,
+ collection,
  )
  except NotFoundError as e:
  logging.warning(e)
@@ -630,6 +635,7 @@ def create_item_collection(
  cloud_provider: CloudProvider,
  start_date: datetime,
  end_date: datetime,
+ collection: Optional[Collection] = None,
 ) -> pystac.ItemCollection:
  """Create an item collection containing all items for a date range"""
 
@@ -644,7 +650,14 @@ def create_item_collection(
  forecast_cycle_type = ForecastCycleType.from_timestamp(reference_datetime)
  for forecast_hour in forecast_cycle_type.generate_forecast_hours():
  tasks.append(
- (region, product, cloud_provider, reference_datetime, forecast_hour)
+ (
+ region,
+ product,
+ cloud_provider,
+ reference_datetime,
+ forecast_hour,
+ collection,
+ )
  )
 
  reference_date += one_day

tests/test_commands.py

@@ -4,6 +4,7 @@
 from click import Group
 from click.testing import CliRunner
 from pystac import Collection, Item
+
 from stactools.noaa_hrrr.commands import create_noaahrrr_command
 from stactools.noaa_hrrr.metadata import (
  CloudProvider,

tests/test_inventory.py

@@ -1,5 +1,6 @@
 import pandas as pd
 import pytest
+
 from stactools.noaa_hrrr.inventory import (
  DESCRIPTION_COLS,
  INVENTORY_COLS,

tests/test_stac.py

@@ -2,6 +2,7 @@
 from datetime import datetime, timedelta
 
 import pytest
+
 from stactools.noaa_hrrr import stac
 from stactools.noaa_hrrr.constants import (
  COLLECTION_ID_FORMAT,
@@ -81,6 +82,29 @@ def test_create_item(
  _ = json.dumps(item.to_dict())
 
 
+def test_create_item_with_collection() -> None:
+ region = Region.conus
+ product = Product.sfc
+ cloud_provider = CloudProvider.aws
+ item = stac.create_item(
+ region=region,
+ product=product,
+ cloud_provider=cloud_provider,
+ reference_datetime=datetime(year=2024, month=1, day=1, hour=6),
+ forecast_hour=12,
+ collection=stac.create_collection(
+ region=region,
+ product=product,
+ cloud_provider=cloud_provider,
+ ),
+ )
+ assert item.collection_id == COLLECTION_ID_FORMAT.format(
+ region=region.value,
+ product=product.value,
+ cloud_provider=cloud_provider.value,
+ )
+
+
 def test_create_item_collection() -> None:
  start_date = datetime(year=2024, month=5, day=1)
  item_collection = stac.create_item_collection(