comparison data_manager/fetch_refseq.py @ 2:a4ee45e7237b draft

planemo upload for repository https://github.com/pvanheus/refseq_fasta_data_manager commit a0125981706495e0a8be4fafe2eb1af3f0cfdaa3-dirty

1:300562c726cc

#!/usr/bin/env python

from __future__ import print_function, division
import argparse
from datetime import date
import gzip
import json
from multiprocessing import Process, Queue
import os
import os.path

    with open_output(os.path.join(out_dir, output_filename), 'wb') as output_file:
        while input_filename != 'STOP':
            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 != '':
                    output_file.write(data)
                    data = input_file.read(chunk_size)
            # os.unlink(input_filename)
            input_filename = conn.get()

def get_refseq_division(division_name, mol_types, output_directory, debug=False, compress=False):
    base_url = 'https://ftp.ncbi.nlm.nih.gov/refseq/release/'
    valid_divisions = set(['archea', 'bacteria', 'complete', 'fungi', 'invertebrate', 'mitochondrion', 'other',

2:a4ee45e7237b

#!/usr/bin/env python

from __future__ import print_function, division
import argparse
from datetime import date
import functools
import gzip
import json
from multiprocessing import Process, Queue
import os
import os.path

    with open_output(os.path.join(out_dir, output_filename), 'wb') as output_file:
        while input_filename != 'STOP':
            if debug:
                print('Reading', input_filename, file=sys.stderr)
            with gzip.open(input_filename) as input_file:
                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)
            os.unlink(input_filename)
            input_filename = conn.get()

def get_refseq_division(division_name, mol_types, output_directory, debug=False, compress=False):
    base_url = 'https://ftp.ncbi.nlm.nih.gov/refseq/release/'
    valid_divisions = set(['archea', 'bacteria', 'complete', 'fungi', 'invertebrate', 'mitochondrion', 'other',