# HG changeset patch # User sanbi-uwc # Date 1536358103 14400 # Node ID a4ee45e7237b725034e2be8c14f8ec641441b197 # Parent 300562c726cc8cb77510cc02848d17bbb5c18009 planemo upload for repository https://github.com/pvanheus/refseq_fasta_data_manager commit a0125981706495e0a8be4fafe2eb1af3f0cfdaa3-dirty diff -r 300562c726cc -r a4ee45e7237b data_manager/fetch_refseq.py --- 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): diff -r 300562c726cc -r a4ee45e7237b data_manager/fetch_refseq.xml --- 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 @@ - + Fetch FASTA data from NCBI RefSeq and update all_fasta data table python