comparison data_manager/fetch_mlst_data.py @ 4:577ff220eaea draft default tip

Uploaded

3:eb9321fec577

import csv
import shutil
from urlparse import urlparse
import time
import subprocess

try:
    from galaxy.util.json import from_json_string, to_json_string
    has_galaxy = True
except ImportError:
    sys.stderr.write("Will download some stuff to the current dir but can't do Galaxy stuff!")
    has_galaxy = False

# --------------------------------------------------------------------------------------------------

def parse_args():
    parser = ArgumentParser(description='Download MLST datasets by species'

    assert len(found_species) == 1
    species_info = found_species[0]
    species_name_underscores = species_info.name.replace(' ', '_')
    timestamp = time.strftime("%Y%m%d%H%M%S")

    params = None
    if has_galaxy == True:
        params = from_json_string(open(args.outfile).read())
        folder = os.path.join(params['output_data'][0]['extra_files_path'], species_name_underscores, timestamp)
    else:
        folder = os.path.join(os.path.dirname(os.path.realpath(__file__)), species_name_underscores, timestamp)

    if not os.path.isdir(folder):
        os.makedirs(folder)

    profile_doc = url.urlopen(species_info.profiles_url)

    get_reference(folder, args.reference)


    # do Galaxy stuff
    if has_galaxy == True:
        data_manager_dict = {}
        data_manager_dict['data_tables'] = {}
        name = "%s-%s" % (species_info.name, timestamp)
        data_manager_dict['data_tables']['mlst_data'] = [dict(value=species_name_underscores,
                                                              dbkey=species_name_underscores,
                                                              name=name,
                                                              time_stamp=timestamp,
                                                              file_path=folder)]
        #save info to json file
        with open(args.outfile, 'wb') as fjson:
            fjson.write(to_json_string(data_manager_dict))

# end of main --------------------------------------------------------------------------------------

def get_reference(folder, acc):

4:577ff220eaea

import csv
import shutil
from urlparse import urlparse
import time
import subprocess
from json import dumps
from json import loads

# --------------------------------------------------------------------------------------------------

def parse_args():
    parser = ArgumentParser(description='Download MLST datasets by species'

    assert len(found_species) == 1
    species_info = found_species[0]
    species_name_underscores = species_info.name.replace(' ', '_')
    timestamp = time.strftime("%Y%m%d%H%M%S")

    params = loads(open(args.outfile).read())
    folder = os.path.join(params['output_data'][0]['extra_files_path'], species_name_underscores, timestamp)

    if not os.path.isdir(folder):
        os.makedirs(folder)

    profile_doc = url.urlopen(species_info.profiles_url)

    get_reference(folder, args.reference)


    # do Galaxy stuff
    data_manager_dict = {}
    data_manager_dict['data_tables'] = {}
    name = "%s-%s" % (species_info.name, timestamp)
    data_manager_dict['data_tables']['mlst_data'] = [dict(value=species_name_underscores,
                                                          dbkey=species_name_underscores,
                                                          name=name,
                                                          time_stamp=timestamp,
                                                          file_path=folder)]
    #save info to json file
    with open(args.outfile, 'wb') as fjson:
        fjson.write(dumps(data_manager_dict))

# end of main --------------------------------------------------------------------------------------

def get_reference(folder, acc):