aboutsummaryrefslogtreecommitdiff
path: root/workflows/pull-data/genbank/genbank.py
diff options
context:
space:
mode:
authorPjotr Prins2021-01-04 08:58:38 +0000
committerPjotr Prins2021-01-04 08:58:38 +0000
commit1c4e055b8a9dc53b7fdbdf12d4b0a7e877fbc2ef (patch)
tree34cc42ef12b81c05be8a57ca2a973b97e52f8461 /workflows/pull-data/genbank/genbank.py
parentba4161b1660c3a67090dd3715e9862906fb1cc5f (diff)
downloadbh20-seq-resource-1c4e055b8a9dc53b7fdbdf12d4b0a7e877fbc2ef.tar.gz
bh20-seq-resource-1c4e055b8a9dc53b7fdbdf12d4b0a7e877fbc2ef.tar.lz
bh20-seq-resource-1c4e055b8a9dc53b7fdbdf12d4b0a7e877fbc2ef.zip
Started on normalization
Diffstat (limited to 'workflows/pull-data/genbank/genbank.py')
-rw-r--r--workflows/pull-data/genbank/genbank.py4
1 files changed, 3 insertions, 1 deletions
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.