Fix: Only use first white-space separated entry in contig name

Fixes issues for genomes where extra info may be added in the contig name after the name itself (separated by a space or a tab).
zjnolen · Jan 20, 2025 · b0ac754 · b0ac754
1 parent e1a2267
commit b0ac754
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/.test/data/ref/testref.fa b/.test/data/ref/testref.fa
diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
@@ -54,7 +54,7 @@ def chunkify(reference_fasta, chunk_size):
     with open(reference_fasta, "r") as fasta_in:
         for header, seq in itertools.groupby(fasta_in, lambda x: x.startswith(">")):
             if header:
-                contig = next(seq).strip(">").strip()
+                contig = next(seq).strip(">").strip().split(maxsplit=1)[0]
             seq_length = len("".join(seq).replace("\n", ""))
             if seq_length > 0:
                 contigs = contigs + [[contig, seq_length]]