Copy cached reference dataset queries during pod init. (#25)

* more formal

* remove 37

* Bump version

* Simplify the list of queries

* remember ht

* bump version

charts/hail-search/Chart.yaml

@@ -18,7 +18,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.12
+version: 0.1.13
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

charts/hail-search/values.yaml

@@ -48,7 +48,17 @@ initContainers: |-
     volumeMounts:
       - mountPath: {{ $.Values.environment.DATASETS_DIR }}
         name: datasets
+  {{ end -}}
   {{ end }}
+  {{- range $path, $queries := $.Values.cachedReferenceDatasetQueries -}}
+  {{- range $query := $queries -}}
+  - name: sync-cached-reference-dataset-queries-{{ $path | replace "/" "-" | replace "_" "-" | lower}}
+    image: gcr.io/google.com/cloudsdktool/google-cloud-cli:latest
+    command: ['gsutil', '-m', 'cp', '-r', '{{ $.Values.sourceCachedReferenceDatasetQueriesDir }}/{{ $path }}/cached_reference_dataset_queries/{{ $query }}.ht', '{{ $.Values.environment.DATASETS_DIR }}/{{ $path }}']
+    volumeMounts:
+      - mountPath: {{ $.Values.environment.DATASETS_DIR }}
+        name: datasets
+  {{ end -}}
   {{ end }}
 
 # Prefer to be scheduled away from other hail-search pods and seqr application pods
@@ -74,6 +84,14 @@ affinity: |-
 nodeSelector: 
   {}
 
+sourceCachedReferenceDatasetQueriesDir: 'gs://seqr-reference-data/v03'
+cachedReferenceDatasetQueries:
+  GRCh38/SNV_INDEL:
+    - 'clinvar_path_variants'
+    - 'high_af_variants'
+  GRCh38/MITO:
+    - 'clinvar_path_variants'
+
 global:
   hail_search:
     sourceDatasetsDir: ''