From d9165d64840daca222305a6bf8d414a77a3cff21 Mon Sep 17 00:00:00 2001
From: AndreaGuarracino
Date: Sun, 15 Nov 2020 14:23:09 +0100
Subject: fix sequencing_coverage
---
scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
(limited to 'scripts')
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 17b741a..788f7e9 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
@@ -225,7 +225,8 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml)
# A regular expression would be better!
try:
info_for_yaml_dict['technology'][field_in_yaml] = [
- float(tech_info_to_parse.strip('(average)').strip("reads/nt").strip('(average for 6 sequences)').replace(',', '.').strip(' xX>'))
+ float(tech_info_to_parse.replace('(average)', '').replace("reads/nt", '').
+ replace('(average for 6 sequences)', '').replace(',', '.').strip(' xX>'))
]
except ValueError:
print(accession_version, "Couldn't make sense of Coverage '%s'" % tech_info_to_parse)
--
cgit v1.2.3