fixup: add two tests (1) use 'name' (2) use first column

nextstrain · Feb 2, 2024 · fc6c6cc · fc6c6cc
1 parent 0ea9dc3
commit fc6c6cc
Showing 1 changed file with 33 additions and 0 deletions.
diff --git a/tests/functional/parse.t b/tests/functional/parse.t
@@ -75,6 +75,39 @@ Parse Zika sequences into sequences and metadata, preferred default ids is 'stra
   $ diff -u "parse/sequences.fasta" "$TMP/sequences.fasta"
   $ rm -f "$TMP/sequences.fasta" "$TMP/metadata.tsv"
 
+Parse Zika sequences into sequences and metadata when there is no 'strain' field.
+This should use the 2nd entry in DEFAULT_ID_COLUMNS ('strain', 'name') instead.
+
+  $ ${AUGUR} parse \
+  >   --sequences parse/zika.fasta \
+  >   --output-sequences "$TMP/sequences.fasta" \
+  >   --output-metadata "$TMP/metadata.tsv" \
+  >   --fields col1 virus name 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_other.fasta" "$TMP/sequences.fasta"
+  $ rm -f "$TMP/sequences.fasta" "$TMP/metadata.tsv"
+
+Parse Zika sequences into sequences and metadata when no output-id-field is provided and none of the fields match DEFAULT_ID_COLUMNS (e.g. ('strain', 'name')).
+This should use the first field as the id field and the metadata should not have an extra strain or name column.
+
+  $ ${AUGUR} parse \
+  >   --sequences parse/zika.fasta \
+  >   --output-sequences "$TMP/sequences.fasta" \
+  >   --output-metadata "$TMP/metadata.tsv" \
+  >   --fields col1 virus col3 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.fasta" "$TMP/sequences.fasta"
+  $ diff "parse/metadata.tsv" "$TMP/metadata.tsv" | tr '>' '+' | tr '<' '-'
+  1c1
+  - strain\tvirus\taccession\tdate\tregion\tcountry\tdivision\tcity\tdb\tsegment\tauthors\turl\ttitle\tjournal\tpaper_url (esc)
+  ---
+  + col1\tvirus\tcol3\tdate\tregion\tcountry\tdivision\tcity\tdb\tsegment\tauthors\turl\ttitle\tjournal\tpaper_url (esc)
+  $ rm -f "$TMP/sequences.fasta" "$TMP/metadata.tsv"
+
 Parse compressed Zika sequences into sequences and metadata.
 
   $ ${AUGUR} parse \