From 95d4f499a6b62499133ef67485b7a3dd420b69d4 Mon Sep 17 00:00:00 2001
From: Jover Lee <joverlee521@gmail.com>
Date: Thu, 11 Apr 2024 17:14:54 -0700
Subject: [PATCH] wip: split out ingest

---
 .github/workflows/ingest-to-phylogenetic.yaml | 24 +---------
 .github/workflows/ingest.yaml                 | 47 +++++++++++++++++++
 2 files changed, 49 insertions(+), 22 deletions(-)
 create mode 100644 .github/workflows/ingest.yaml

diff --git a/.github/workflows/ingest-to-phylogenetic.yaml b/.github/workflows/ingest-to-phylogenetic.yaml
index 690e4f3..8b41b6d 100644
--- a/.github/workflows/ingest-to-phylogenetic.yaml
+++ b/.github/workflows/ingest-to-phylogenetic.yaml
@@ -42,30 +42,10 @@ jobs:
   ingest:
     permissions:
       id-token: write
-    uses: nextstrain/.github/.github/workflows/pathogen-repo-build.yaml@master
+    uses: ./.github/workflows/ingest.yaml
     secrets: inherit
     with:
-      # Starting with the default docker runtime
-      # We can migrate to AWS Batch when/if we need to for more resources or if
-      # the job runs longer than the GH Action limit of 6 hours.
-      runtime: docker
-      env: |
-        NEXTSTRAIN_DOCKER_IMAGE: ${{ inputs.ingest_image }}
-      run: |
-        nextstrain build \
-          --env AWS_ACCESS_KEY_ID \
-          --env AWS_SECRET_ACCESS_KEY \
-          ingest \
-            upload_all \
-            --configfile build-configs/nextstrain-automation/config.yaml
-      # Specifying artifact name to differentiate ingest build outputs from
-      # the phylogenetic build outputs
-      artifact-name: ingest-build-output
-      artifact-paths: |
-        ingest/results/
-        ingest/benchmarks/
-        ingest/logs/
-        ingest/.snakemake/log/
+      image: ${{ inputs.ingest_image }}
 
   # Check if ingest results include new data by checking for the cache
   # of the file with the results' Metadata.sh256sum (which should have been added within upload-to-s3)
diff --git a/.github/workflows/ingest.yaml b/.github/workflows/ingest.yaml
new file mode 100644
index 0000000..99dfd74
--- /dev/null
+++ b/.github/workflows/ingest.yaml
@@ -0,0 +1,47 @@
+name: Ingest
+
+defaults:
+  run:
+    # This is the same as GitHub Action's `bash` keyword as of 20 June 2023:
+    # https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsshell
+    #
+    # Completely spelling it out here so that GitHub can't change it out from under us
+    # and we don't have to refer to the docs to know the expected behavior.
+    shell: bash --noprofile --norc -eo pipefail {0}
+
+on:
+  workflow_call:
+    inputs:
+      image:
+        description: 'Specific container image to use for ingest workflow (will override the default of "nextstrain build")'
+        required: false
+        type: string
+
+jobs:
+  ingest:
+    permissions:
+      id-token: write
+    uses: nextstrain/.github/.github/workflows/pathogen-repo-build.yaml@master
+    secrets: inherit
+    with:
+      # Starting with the default docker runtime
+      # We can migrate to AWS Batch when/if we need to for more resources or if
+      # the job runs longer than the GH Action limit of 6 hours.
+      runtime: docker
+      env: |
+        NEXTSTRAIN_DOCKER_IMAGE: ${{ inputs.image }}
+      run: |
+        nextstrain build \
+          --env AWS_ACCESS_KEY_ID \
+          --env AWS_SECRET_ACCESS_KEY \
+          ingest \
+            upload_all \
+            --configfile build-configs/nextstrain-automation/config.yaml
+      # Specifying artifact name to differentiate ingest build outputs from
+      # the phylogenetic build outputs
+      artifact-name: ingest-build-output
+      artifact-paths: |
+        ingest/results/
+        ingest/benchmarks/
+        ingest/logs/
+        ingest/.snakemake/log/