From 3165a31e321cbf4641f9afdcbea511ee66f673bb Mon Sep 17 00:00:00 2001
From: AndreaGuarracino
Date: Fri, 28 Aug 2020 11:16:24 +0200
Subject: added control (locally and in the validation) that sample_id has to
 be the same in the metadata and in the FASTA header #103

---
 scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'scripts/download_genbank_data')

diff --git a/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py b/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
index 8ef76e1..8f765d7 100755
--- a/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
+++ b/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
@@ -412,6 +412,8 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml)
                 not_created_accession_dict[accession_version].append('host_species not found')
 
             if len(GBSeq_sequence.text) < min_len_to_count:
+                if accession_version not in not_created_accession_dict:
+                    not_created_accession_dict[accession_version] = []
                 not_created_accession_dict[accession_version].append('sequence shorter than {} bp'.format(min_len_to_count))
 
             if accession_version not in not_created_accession_dict:
-- 
cgit v1.2.3