Mercurial > repos > sanbi-uwc > data_manager_fetch_refseq
changeset 2:a4ee45e7237b draft
planemo upload for repository https://github.com/pvanheus/refseq_fasta_data_manager commit a0125981706495e0a8be4fafe2eb1af3f0cfdaa3-dirty
| author | sanbi-uwc |
|---|---|
| date | Fri, 07 Sep 2018 18:08:23 -0400 |
| parents | 300562c726cc |
| children | 4852eb1a75e5 |
| files | data_manager/fetch_refseq.py data_manager/fetch_refseq.xml |
| diffstat | 2 files changed, 5 insertions(+), 5 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/fetch_refseq.py Fri Sep 07 17:40:42 2018 -0400 +++ b/data_manager/fetch_refseq.py Fri Sep 07 18:08:23 2018 -0400 @@ -3,6 +3,7 @@ from __future__ import print_function, division import argparse from datetime import date +import functools import gzip import json from multiprocessing import Process, Queue @@ -52,11 +53,10 @@ if debug: print('Reading', input_filename, file=sys.stderr) with gzip.open(input_filename) as input_file: - data = input_file.read(chunk_size) - while data != '': + read_chunk = functools.partial(input_file.read, (chunk_size)) + for data in iter(read_chunk, ''): # use '' as a sentinel to stop the loop output_file.write(data) - data = input_file.read(chunk_size) - # os.unlink(input_filename) + os.unlink(input_filename) input_filename = conn.get() def get_refseq_division(division_name, mol_types, output_directory, debug=False, compress=False):
--- a/data_manager/fetch_refseq.xml Fri Sep 07 17:40:42 2018 -0400 +++ b/data_manager/fetch_refseq.xml Fri Sep 07 18:08:23 2018 -0400 @@ -1,4 +1,4 @@ -<tool id="data_manager_fetch_refseq" name="RefSeq data manager" version="0.0.2" tool_type="manage_data"> +<tool id="data_manager_fetch_refseq" name="RefSeq data manager" version="0.0.3" tool_type="manage_data"> <description>Fetch FASTA data from NCBI RefSeq and update all_fasta data table</description> <requirements> <requirement type="package" version="3">python</requirement>