Add CI workflow and configs for ingest and phylogeny workflows [#2]

Also add custom rule import bits to phylogenetic/Snakefile

.github/workflows/ci.yaml

@@ -0,0 +1,12 @@
+name: CI
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  ci:
+    uses: nextstrain/.github/.github/workflows/pathogen-repo-ci.yaml@master

ingest/build-configs/ci/config.yaml

@@ -0,0 +1,2 @@
+custom_rules:
+  - build-configs/ci/copy_example_data.smk

ingest/build-configs/ci/copy_example_data.smk

@@ -0,0 +1,12 @@
+rule copy_example_data:
+    input:
+        ncbi_dataset="example-data/ncbi_dataset.zip"
+    output:
+        ncbi_dataset=temp("data/ncbi_dataset.zip")
+    shell:
+        """
+        cp -f {input.ncbi_dataset} {output.ncbi_dataset}
+        """
+
+# force this rule over NCBI data fetch
+ruleorder: copy_example_data > fetch_ncbi_dataset_package

phylogenetic/Snakefile

@@ -26,3 +26,8 @@ rule clean:
         """
         rm -rfv {params.targets}
         """
+
+# Import custom rules provided via the config.
+if "custom_rules" in config:
+  for rule_file in config["custom_rules"]:
+    include: rule_file

phylogenetic/build-configs/ci/config.yaml

@@ -1,7 +1,2 @@
-# This configuration file contains the custom configurations
-# parameters for the CI workflow to run with the example data.
-
-# Custom rules to run as part of the CI automated workflow. The paths
-# should be relative to the phylogenetic directory.
 custom_rules:
   - build-configs/ci/copy_example_data.smk

phylogenetic/build-configs/ci/copy_example_data.smk

@@ -1,18 +1,16 @@
 rule copy_example_data:
     input:
-        sequences="example_data/sequences.fasta",
-        metadata="example_data/metadata.tsv",
+        sequences="example-data/sequences.fasta.zst",
+        metadata="example-data/metadata.tsv.zst",
     output:
-        sequences="data/sequences.fasta",
-        metadata="data/metadata.tsv",
+        sequences=temp("data/sequences.fasta.zst"),
+        metadata=temp("data/metadata.tsv.zst"),
     shell:
         """
         cp -f {input.sequences} {output.sequences}
         cp -f {input.metadata} {output.metadata}
         """
 
 
-# Add a Snakemake ruleorder directive here if you need to resolve
-# ambiguous rules that have the same output as the copy_example_data
-# rule.
-# ruleorder: copy_example_data > ...
+# force this rule over downloading from nextstrain
+ruleorder: copy_example_data > download