fix: make collections valid

Includes:

- A simple script to validate all collection files
- A new CI/CD step to run the validation script

There wasn't an obvious place to add the validation to a lambda test, so I make
it its own thing.

.github/workflows/cicd.yml

@@ -33,3 +33,24 @@ jobs:
     uses: ./.github/workflows/test_python_lambda.yml
     with:
       path_to_lambda: lambdas/data-transfer
+
+  validate-collections:
+    name: Validate collections
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install poetry
+        run: pipx install poetry
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.8" # NOTE: Should match Lambda runtime specified in CDK code
+          cache: "poetry"
+          cache-dependency-path: |
+            poetry.lock
+            labmdas/build-stac/requirements**.txt
+      - name: Install requirements
+        run: |
+          poetry install
+          poetry add $(cat lambdas/build-stac/requirements**.txt )
+      - name: Validate collections
+        run: scripts/validate_collections.py

data/collections/caldor-fire-behavior.json

@@ -8,10 +8,10 @@
         "spatial":{
             "bbox":[
                 [
-                    "-180",
-                    "90",
-                    "-90",
-                    "180"
+                    -180,
+                    90,
+                    -90,
+                    180
                 ]
             ]
         },

data/collections/caldor-fire-burn-severity.json

@@ -8,10 +8,10 @@
         "spatial":{
             "bbox":[
                 [
-                    "-180",
-                    "90",
-                    "-90",
-                    "180"
+                    -180,
+                    90,
+                    -90,
+                    180
                 ]
             ]
         },

data/collections/ecco-surface-height-change.json

@@ -8,10 +8,10 @@
         "spatial":{
             "bbox":[
                 [
-                    "-180",
-                    "90",
-                    "-90",
-                    "180"
+                    -180,
+                    90,
+                    -90,
+                    180
                 ]
             ]
         },

data/collections/lis-tws-nonstationarity-index.json

@@ -20,7 +20,7 @@
             ]
         }
     },
-    "license": "Creative Commons Zero (CC0-1.0)",
+    "license": "CC0-1.0",
     "description": "The global Terrestrial Water Storage (TWS) non-stationarity index integrates the trend, seasonal shifts, and variability change of TWS for the period of 2003 - 2020. TWS is derived by jointly assimilating the MODIS Leaf Area Index, the ESA CCI surface soil moisture, and the GSFC GRACE mascon-based TWS anomalies into the Noah-MP land surface model within the NASA Land Information System (LIS) at 10 km spatial resolution forced by the combination of MERRA2 and IMERG meteorological fields. The smaller the non-stationarity index is, the more the water cycle is under a non-stationary process. Glaciers and Greenland are excluded from the analysis.",
     "item_assets": {
         "cog_default": {

data/collections/mtbs-burn-severity.json

@@ -8,10 +8,10 @@
         "spatial":{
             "bbox":[
                 [
-                    "-126.49459612498832",
-                    "24.0478678762251",
-                    "-71.50752568733597",
-                    "50.55916724898132"
+                    -126.4945961,
+                    24.0478678,
+                    -71.5075256,
+                    50.5591672
                 ]
             ]
         },

data/collections/nceo-africa-2017.json

@@ -12,7 +12,7 @@
     "title": "NCEO Africa Aboveground Woody Biomass 2017",
     "extent": {
         "spatial": {
-        "   bbox": [[-18.2735295, -35.054059, 51.8642329, 37.7310386]]
+            "bbox": [[-18.2735295, -35.054059, 51.8642329, 37.7310386]]
         },
         "temporal": {
             "interval": [["2017-01-01T00:00:00Z", "2018-01-01T00:00:00Z"]]

scripts/validate_collections.py

@@ -0,0 +1,28 @@
+import sys
+from pathlib import Path
+
+from pystac import Collection
+from pystac.errors import STACValidationError
+
+root = Path(__file__).parents[1]
+collections = root / "data" / "collections"
+
+errors = False
+for path in collections.glob("*.json"):
+    try:
+        collection = Collection.from_file(str(path))
+    except Exception as err:
+        errors = True
+        print(
+            f"ERROR [{path.name}]: could not read collection because {type(err)}: {err}"
+        )
+    try:
+        collection.validate()
+    except STACValidationError as err:
+        errors = True
+        print(
+            f"VALIDATION [{path.name}]: {collection.id} is invalid because {err.source}"
+        )
+
+if errors:
+    sys.exit(1)