Ingest: Derive URL column during ingest

nextstrain · Dec 11, 2024 · 58a9a99 · 58a9a99
1 parent a443038
commit 58a9a99
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/ingest/defaults/config.yaml b/ingest/defaults/config.yaml
@@ -121,4 +121,5 @@ curate:
     "authors",
     "full_authors",
     "institution",
+    "url",
   ]
diff --git a/ingest/rules/curate.smk b/ingest/rules/curate.smk
@@ -107,6 +107,8 @@ rule curate:
                 --abbr-authors-field {params.abbr_authors_field} \
             | augur curate apply-geolocation-rules \
                 --geolocation-rules {input.all_geolocation_rules} \
+            |  jq -c --arg GENBANK "{params.id_field}" \
+                '. |= (.url="https://www.ncbi.nlm.nih.gov/nuccore/" + .[$GENBANK])' \
             | augur curate apply-record-annotations \
                 --annotations {input.annotations} \
                 --id-field {params.annotations_id} \