def test_get_genbank_summary(self):
"""Get the summary!!"""
exp = GreengenesRecord({'ncbi_acc_w_ver':'AGIY01000001.1',
'ncbi_gi':'354825968',
'gold_id':'Gi05850',
'decision':'named_isolate',
'isolation_source':'anaerobic digested sludge',
'organism':'Methanolinea tarda NOBI-1',
'strain':'NOBI-1',
'prokmsaname':'Methanolinea tarda NOBI-1',
'specific_host':'Methanolinea tarda NOBI-1 ctg73, whole genome shotgun sequence.',
'authors':'Lucas,S., Han,J., Lapidus,A., Cheng,J.-F., Goodwin,L., Pitluck,S., Peters,L., Land,M.L., Hauser,L., Imachi,H., Sekiguchi,Y., Kamagata,Y., Cadillo-Quiroz,H., Zinder,S., Liu,W.T., Tamaki,H. and Woyke,T.J.',
'title':'The draft genome of Methanolinea tarda NOBI-1',
'submit_date':'31-OCT-2011',
'country':'Japan: Nagaoka',
#'NCBI_tax_id':'882090',
'ncbi_tax_string':'Archaea; Euryarchaeota; Methanomicrobia; Methanomicrobiales; Methanoregulaceae; Methanolinea'})
obs = get_genbank_summary(self.gb1)
self.assertEqual(obs,exp)
# verify the sequence is DNA. NCBI silently corrupts records
# every once and a while leading to crap in the sequence.
# Thanks NCBI.
seq_chars = set(sequence)
if not seq_chars.issubset(alpha):
logline = log_f("Corrupt sequence, accession: %s" % (accession))
logger.write(logline)
if verbose:
stdout.write(logline)
failure_count += 1
continue
# gg_record contains gb summary data
try:
gg_record = get_genbank_summary(next_record)
except KeyError, e:
failure_count += 1
continue
seen.add(accession)
write_sequence(sequences, accession, sequence)
write_gg_record(gg_records, gg_record)
write_obs_record(obs_records, accession)
if failure_count >= max_failures:
logline = log_f("MAX FAILURES OF %d REACHED IN %s" % (max_failures, \
gb_fp))
logger.write(logline)
stderr.write(logline)
else:
