Merge pull request #38 from nextstrain/ingest-no-curation

ingest: Provide target for raw metadata from NCBI Datasets

ingest/README.md

@@ -25,6 +25,18 @@ This produces the default outputs of the ingest workflow:
 - metadata      = results/metadata.tsv
 - sequences     = results/sequences.fasta
 
+### Dumping the full raw metadata from NCBI Datasets
+
+The workflow has a target for dumping the full raw metadata from NCBI Datasets.
+
+```
+nextstrain build ingest dump_ncbi_dataset_report
+```
+
+This will produce the file `ingest/data/ncbi_dataset_report_raw.tsv`,
+which you can inspect to determine what fields and data to use if you want to
+configure the workflow for your pathogen.
+
 ## Defaults
 
 The defaults directory contains all of the default configurations for the ingest workflow.

ingest/rules/fetch_from_ncbi.smk

@@ -52,6 +52,20 @@ rule fetch_ncbi_dataset_package:
             --filename {output.dataset_package}
         """
 
+# Note: This rule is not part of the default workflow!
+# It is intended to be used as a specific target for users to be able
+# to inspect and explore the full raw metadata from NCBI Datasets.
+rule dump_ncbi_dataset_report:
+    input:
+        dataset_package="data/ncbi_dataset.zip",
+    output:
+        ncbi_dataset_tsv="data/ncbi_dataset_report_raw.tsv",
+    shell:
+        """
+        dataformat tsv virus-genome \
+            --package {input.dataset_package} > {output.ncbi_dataset_tsv}
+        """
+
 
 rule extract_ncbi_dataset_sequences:
     input: