Parameterize the record ID field for output sequences

Include a `--output-id-field` parameter in augur parse to indicate the ID
field for the output sequences file, such as using "accession" instead of
"strain".

It is important to note that the `--output-id-field` parameter is not required,
and augur parse will fall back to the DEFAULT_ID_COLUMNS (e.g. ('strain','name'))
if it is not present. If none of the DEFAULT_ID_COLUMNS are present in the fields,
fall back to using the first field.

The `--output-id-field` parameter is designed to accept a single field name,
not multiple. User are required to provide a `--fields col1 col2 strain accession`
argument in the same invocation. It seems reasonable to expect the user to
choose a specific field name for the ID.

To prevent unintended behaviors, if `--output-id-field` is not present in
`--fields` (e.g., due to a typo), augur parse will raise an error instead of
falling back to DEFAULT_ID_COLUMNS.

augur/parse.py

@@ -6,6 +6,7 @@
 
 from .io.file import open_file
 from .io.sequences import read_sequences, write_sequences
+from .io.metadata import DEFAULT_ID_COLUMNS
 from .dates import get_numerical_date_from_value
 from .errors import AugurError
 
@@ -133,8 +134,6 @@ def parse_sequence(sequence, fields, strain_key="strain", separator="|", prettif
             dayfirst=fix_dates_format=='dayfirst'
         )
 
-    metadata["strain"] = sequence.id
-
     return sequence, metadata
 
 
@@ -143,6 +142,8 @@ def register_parser(parent_subparsers):
     parser.add_argument('--sequences', '-s', required=True, help="sequences in fasta or VCF format")
     parser.add_argument('--output-sequences', required=True, help="output sequences file")
     parser.add_argument('--output-metadata', required=True, help="output metadata file")
+    parser.add_argument('--output-id-field', required=False,
+                        help="The record field to use as the sequence identifier in the FASTA output.")
     parser.add_argument('--fields', required=True, nargs='+', help="fields in fasta header")
     parser.add_argument('--prettify-fields', nargs='+', help="apply string prettifying operations (underscores to spaces, capitalization, etc) to specified metadata fields")
     parser.add_argument('--separator', default='|', help="separator of fasta header")
@@ -162,12 +163,17 @@ def run(args):
     # field to index the dictionary and the data frame
     meta_data = {}
 
-    if 'name' in args.fields:
-        strain_key = 'name'
-    elif 'strain' in args.fields:
-        strain_key = 'strain'
+    if args.output_id_field:
+        if args.output_id_field not in args.fields:
+            raise AugurError(f"Output id field '{args.output_id_field}' not found in fields {args.fields}.")
+        strain_key = args.output_id_field
     else:
-        strain_key = args.fields[0]
+        for possible_id in DEFAULT_ID_COLUMNS:
+            if possible_id in args.fields:
+                strain_key = possible_id
+                break
+        if not strain_key:
+            strain_key = args.fields[0]
 
     # loop over sequences, parse fasta header of each sequence
     with open_file(args.output_sequences, "wt") as handle:

tests/functional/parse.t

@@ -15,6 +15,7 @@ This should fail.
   .* (re)
   .* (re)
   .* (re)
+  .* (re)
   augur parse: error: the following arguments are required: --fields
   [2]
 
@@ -32,6 +33,35 @@ Parse Zika sequences into sequences and metadata.
   $ diff -u "parse/metadata.tsv" "$TMP/metadata.tsv"
   $ rm -f "$TMP/sequences.fasta" "$TMP/metadata.tsv"
 
+Parse Zika sequences into sequences and metadata using a different metadata field as record id (e.g. accession)
+
+  $ ${AUGUR} parse \
+  >   --sequences parse/zika.fasta \
+  >   --output-sequences "$TMP/sequences.fasta" \
+  >   --output-metadata "$TMP/metadata.tsv" \
+  >   --output-id-field accession \
+  >   --fields strain virus accession date region country division city db segment authors url title journal paper_url \
+  >   --prettify-fields region country division city \
+  >   --fix-dates monthfirst
+
+  $ diff -u "parse/sequences_acc.fasta" "$TMP/sequences.fasta"
+  $ diff -u "parse/metadata.tsv" "$TMP/metadata.tsv"
+  $ rm -f "$TMP/sequences.fasta" "$TMP/metadata.tsv"
+
+Try to parse Zika sequences with a misspelled field.
+This should fail.
+
+  $ ${AUGUR} parse \
+  >   --sequences parse/zika.fasta \
+  >   --output-sequences "$TMP/sequences.fasta" \
+  >   --output-metadata "$TMP/metadata.tsv" \
+  >   --output-id-field notexist \
+  >   --fields strain virus accession date region country division city db segment authors url title journal paper_url \
+  >   --prettify-fields region country division city \
+  >   --fix-dates monthfirst
+  ERROR: Output id field 'notexist' not found in fields ['strain', 'virus', 'accession', 'date', 'region', 'country', 'division', 'city', 'db', 'segment', 'authors', 'url', 'title', 'journal', 'paper_url'].
+  [2]
+
 Parse compressed Zika sequences into sequences and metadata.
 
   $ ${AUGUR} parse \