From 95030669dc346289ccc638a86c1fc1706ca17905 Mon Sep 17 00:00:00 2001
From: Rutger Vos <rutgeraldo@gmail.com>
Date: Fri, 16 Aug 2024 20:03:08 +0200
Subject: [PATCH] tarfile handling

---
 barcode_validator/taxonomy.py | 4 +++-
 config/config.yml             | 4 ++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/barcode_validator/taxonomy.py b/barcode_validator/taxonomy.py
index 0003c3b..f44f209 100644
--- a/barcode_validator/taxonomy.py
+++ b/barcode_validator/taxonomy.py
@@ -4,6 +4,7 @@
 import os
 import time
 import pandas as pd
+import tarfile
 from Bio import SeqIO
 from Bio.SeqRecord import SeqRecord
 from Bio.Blast import NCBIWWW, NCBIXML
@@ -20,7 +21,8 @@ def read_bold_taxonomy(spreadsheet):
 
 def read_ncbi_taxonomy(tarfile):
     logging.info("Reading NCBI taxonomy")
-    return NCBIParser(tarfile).parse()
+    tar = tarfile.open(tarfile, "r:gz")
+    return NCBIParser(tar).parse()
 
 
 def run_seqid(sequence, ncbi_tree):
diff --git a/config/config.yml b/config/config.yml
index 1c933a5..4d5a78a 100644
--- a/config/config.yml
+++ b/config/config.yml
@@ -29,8 +29,8 @@ word_size: 28
 BLASTDB_LMDB_MAP_SIZE: 180000000000 # MaaS 37, 180GB
 
 # Location of the NCBI taxonomy dump. This must be the tar file that contains the nodes.dmp and names.dmp files.
-# When downloaded, the tar file is gzip compressed. This needs to be uncompressed before use, e.g. with `gunzip`.
-ncbi_taxonomy: /home/rutger.vos/data/ncbi/taxdump/taxdump.tar
+# http://ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdump.tar.gz
+ncbi_taxonomy: /home/rutger.vos/data/ncbi/taxdump/taxdump.tar.gz
 
 # Configuration for logging. The verbosity level specified here is overridden by the value provided on the command
 # line with the -v/-verbosity argument. The log file is written to the current working directory.