From 1c4e055b8a9dc53b7fdbdf12d4b0a7e877fbc2ef Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Mon, 4 Jan 2021 08:58:38 +0000 Subject: Started on normalization --- workflows/pull-data/genbank/genbank.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'workflows/pull-data/genbank/genbank.py') diff --git a/workflows/pull-data/genbank/genbank.py b/workflows/pull-data/genbank/genbank.py index 26cb5e7..85d615c 100644 --- a/workflows/pull-data/genbank/genbank.py +++ b/workflows/pull-data/genbank/genbank.py @@ -1,4 +1,6 @@ # Genbank XML parser +# +# Pjotr Prins (c) 2021 from collections import namedtuple import dateutil @@ -59,7 +61,7 @@ Example of an output JSON: def get_metadata(id, gbseq): """This is a minimal data parser from genbank XML records. Inference on, for example geo location, is not allowed in this function and - happens downstream. + happens downstream (in normalize). That is to keep the parsing simple. -- cgit v1.2.3