def test_now(self):
s = strict_rfc3339.now_to_rfc3339_localoffset()
w = strict_rfc3339.rfc3339_to_timestamp(s)
assert s[-6:] == ["-05:00", "-04:00"][time.localtime(w).tm_isdst]
d = int(time.time()) - w
assert d == 0 or d == 1
s = strict_rfc3339.now_to_rfc3339_localoffset(False)
assert abs(strict_rfc3339.rfc3339_to_timestamp(s) - time.time()) <= 0.1
def test_now(self):
s = strict_rfc3339.now_to_rfc3339_localoffset()
w = strict_rfc3339.rfc3339_to_timestamp(s)
assert s[-6:] == ["-05:00", "-04:00"][time.localtime(w).tm_isdst]
d = int(time.time()) - w
assert d == 0 or d == 1
s = strict_rfc3339.now_to_rfc3339_localoffset(False)
assert abs(strict_rfc3339.rfc3339_to_timestamp(s) - time.time()) <= 0.1
def process(self, element):
logging.info('CountAverages start: %s %r' % (type(element), element))
stat_names = ["temperature",
"pressure",
"humidity",
"windgen",
"solargen"]
avg_e = {}
aggr = {}
for k in stat_names:
aggr[k] = (0, 0)
avg_e['clientid'] = element[0]
avg_e['timestamp'] = strict_rfc3339.now_to_rfc3339_localoffset()
# Emit sum and count for each metric
for elem_map in element[1]:
for key in stat_names:
if key in elem_map:
value = elem_map[key]
aggr[key] = (aggr[key][0] + value, aggr[key][1] + 1)
# Calculate average and set in return map
for key, value in aggr.iteritems():
if value[1] == 0:
avg_e[key] = 0
else:
avg_e[key] = value[0] / value[1]
logging.info('CountAverages end: {}'.format(avg_e))
return [avg_e]
def process(self, element):
stat_names = ["I", "U", "Tm"]
avg_e = {}
aggr = {}
for k in stat_names:
aggr[k] = (0, 0)
avg_e['deviceid'] = element[0]
avg_e['timestamp'] = strict_rfc3339.now_to_rfc3339_localoffset()
# Emit sum and count for each metric
for elem_map in element[1]:
for key in stat_names:
if key in elem_map:
value = elem_map[key]
aggr[key] = (aggr[key][0] + value, aggr[key][1] + 1)
# Calculate average and set in return map
for key, value in aggr.items():
if value[1] == 0:
avg_e[key] = 0
else:
avg_e[key] = value[0] / value[1]
logging.info('Engine_avr: {}'.format(avg_e))
return [avg_e]
for dataset in data_all:
## Skip big lottery for testing
#if dataset['identifier'] == 'a002400000Z58cqAAB':
# continue
metadata = dataset.get('datagetter_metadata', {})
dataset['datagetter_metadata'] = metadata
if not dataset['license'] in acceptable_licenses + unacceptable_licenses:
raise ValueError('Unrecognised license ' + dataset['license'])
url = dataset['distribution'][0]['downloadURL']
if args.download:
metadata[
'datetime_downloaded'] = strict_rfc3339.now_to_rfc3339_localoffset(
)
try:
r = requests.get(
url,
headers={
'User-Agent':
'datagetter (https://github.com/ThreeSixtyGiving/datagetter)'
})
r.raise_for_status()
except:
print("\n\nDownload failed for dataset {}\n".format(
dataset['identifier']))
traceback.print_exc()
exit_status = 1
metadata['downloads'] = False
else:
def fetch_and_convert(args, dataset):
r = None
metadata = dataset.get('datagetter_metadata', {})
dataset['datagetter_metadata'] = metadata
if not dataset['license'] in acceptable_licenses + unacceptable_licenses:
raise ValueError('Unrecognised license ' + dataset['license'])
url = dataset['distribution'][0]['downloadURL']
if args.download:
proxies = None
metadata[
'datetime_downloaded'] = strict_rfc3339.now_to_rfc3339_localoffset(
)
if args.socks5_proxy:
proxies = {
'http': args.socks5_proxy,
'https': args.socks5_proxy,
}
try:
print("Fetching %s" % url)
r = requests.get(
url,
headers={
'User-Agent':
'datagetter (https://github.com/ThreeSixtyGiving/datagetter)'
},
proxies=proxies)
r.raise_for_status()
metadata['downloads'] = True
except Exception as e:
if isinstance(e, KeyboardInterrupt):
raise
print("\n\nDownload {} failed for dataset {}\n".format(
url, dataset['identifier']))
traceback.print_exc()
metadata['downloads'] = False
metadata['error'] = str(e)
if not isinstance(e, requests.exceptions.HTTPError):
return
content_type = r.headers.get('content-type', '').split(';')[0].lower()
if content_type and content_type in CONTENT_TYPE_MAP:
file_type = CONTENT_TYPE_MAP[content_type]
elif 'content-disposition' in r.headers:
file_type = rfc6266.parse_requests_response(
r).filename_unsafe.split('.')[-1]
else:
file_type = url.split('.')[-1]
if file_type not in CONTENT_TYPE_MAP.values():
print("\n\nUnrecognised file type {}\n".format(file_type))
return
# Check that the downloaded json file is valid json and not junk from the webserver
# e.g. a 500 error being output without the proper status code.
if file_type == "json":
try:
json.loads(r.text)
except ValueError:
print("\n\nJSON file provided by webserver is invalid")
metadata['downloads'] = False
metadata['error'] = "Invalid JSON file provided by webserver"
return
metadata['file_type'] = file_type
file_name = args.data_dir + '/original/' + dataset[
'identifier'] + '.' + file_type
with open(file_name, 'wb') as fp:
fp.write(r.content)
else:
# --no-download arg
# We require the metadata to exist, it won't if the file failed to download correctly
if metadata['downloads'] == False:
print(
"Skipping %s as it was not marked as successfully downloaded" %
dataset['identifier'])
return
file_type = metadata['file_type']
file_name = args.data_dir + '/original/' + dataset[
'identifier'] + '.' + file_type
json_file_name = '{}/json_all/{}.json'.format(args.data_dir,
dataset['identifier'])
metadata['file_size'] = os.path.getsize(file_name)
if args.convert and (args.convert_big_files
or metadata['file_size'] < 10 * 1024 * 1024):
if file_type == 'json':
os.link(file_name, json_file_name)
metadata['json'] = json_file_name
else:
try:
print("Running convert on %s to %s" %
(file_name, json_file_name))
convert_spreadsheet(file_name, json_file_name, file_type)
except KeyboardInterrupt:
raise
except Exception:
print(
"\n\nUnflattening failed for file {}\n".format(file_name))
traceback.print_exc()
metadata['json'] = None
metadata["valid"] = False
metadata["error"] = "Could not unflatten file"
else:
metadata['json'] = json_file_name
metadata['acceptable_license'] = dataset['license'] in acceptable_licenses
# We can only do anything with the JSON if it did successfully convert.
if metadata.get('json'):
format_checker = FormatChecker()
if args.validate:
try:
with open(json_file_name, 'r') as fp:
validate(json.load(fp),
schema,
format_checker=format_checker)
except (ValidationError, ValueError):
metadata['valid'] = False
else:
metadata['valid'] = True
if metadata['valid']:
os.link(
json_file_name,
'{}/json_valid/{}.json'.format(args.data_dir,
dataset['identifier']))
data_valid.append(dataset)
if metadata['acceptable_license']:
os.link(
json_file_name,
'{}/json_acceptable_license_valid/{}.json'.format(
args.data_dir, dataset['identifier']))
data_acceptable_license_valid.append(dataset)
if metadata['acceptable_license']:
os.link(
json_file_name, '{}/json_acceptable_license/{}.json'.format(
args.data_dir, dataset['identifier']))
data_acceptable_license.append(dataset)
def set_up_db_reading(report_label):
"""Get values db connection, makes connection and specifies output filenames.
Args:
arg1 (str): A "report_label" string for the output files (logs and data).
Returns:
dict: A dict of various values for the script to make db_connection, name files, etc.
"""
# Parse command line inputs.
parser = argparse.ArgumentParser(description='inputs')
parser.add_argument('-v',
'--verbose',
action='store_true',
help='DEBUG-level logging.',
required=False)
parser.add_argument('-a',
'--alliance',
action='store_true',
help='Filenames for AGR export.',
required=False)
parser.add_argument('-c',
'--config_file',
help='Supply filepath to credentials, optional.',
required=False)
parser.add_argument('-t',
'--testing',
action='store_true',
help='Rollback db writes.',
required=False)
# Use parse_known_args() instead of parse_args() to handle only the args relevant here without crashing.
# Extra arguments that may be relevant to specific scripts using this module are safely ignored.
# args = parser.parse_args()
args, extra_args = parser.parse_known_args()
# Determine whether script is to run locally or in docker.
config_file = args.config_file
# Determine values for key variables.
if config_file:
config = configparser.ConfigParser()
config.read(config_file)
server = config['default']['Server']
database = config['default']['Database']
username = config['default']['User']
password = config['default']['PGPassword']
database_release = config['default']['Release']
assembly = config['default']['Assembly']
annotation_release = config['default']['AnnotationRelease']
alliance_schema = config['default']['AllianceSchema']
alliance_release = config['default']['AllianceRelease']
svn_username = config['default']['SVNUsername']
svn_password = config['default']['SVNPassword']
output_dir = './'
input_dir = './'
log_dir = './'
else:
server = os.environ['SERVER']
database = os.environ['DATABASE']
username = os.environ['USER']
password = os.environ['PGPASSWORD']
database_release = os.environ['RELEASE']
assembly = os.environ['ASSEMBLY']
annotation_release = os.environ['ANNOTATIONRELEASE']
alliance_schema = os.environ['ALLIANCESCHEMA']
alliance_release = os.environ['ALLIANCERELEASE']
svn_username = os.environ['SVNUSER']
svn_password = os.environ['SVNPASSWORD']
output_dir = '/src/output/'
input_dir = '/src/input/'
log_dir = '/src/logs/'
# Send values to a dict.
set_up_dict = {}
set_up_dict['server'] = server
set_up_dict['database'] = database
set_up_dict['username'] = username
set_up_dict['password'] = password
set_up_dict['database_release'] = database_release
set_up_dict['assembly'] = assembly
set_up_dict['annotation_release'] = annotation_release
set_up_dict['alliance_schema'] = alliance_schema
set_up_dict['alliance_release'] = alliance_release
set_up_dict['svn_username'] = svn_username
set_up_dict['svn_password'] = svn_password
set_up_dict['input_dir'] = input_dir
set_up_dict['output_dir'] = output_dir
# Determine if testing variable is True or false.
set_up_dict['testing'] = args.testing
# Output filename
alliance = args.alliance
if alliance is True:
set_up_dict[
'output_filename'] = output_dir + 'FB_' + alliance_schema + '_' + report_label + '.json'
else:
set_up_dict[
'output_filename'] = output_dir + report_label + '_' + database + '.tsv'
# Handle logging
if alliance is True:
log_filename = output_dir + 'FB_' + alliance_schema + '_' + report_label + '.log'
else:
log_filename = log_dir + report_label + '_' + database + '.log'
file_handler = logging.FileHandler(log_filename, mode='a')
formatter = logging.Formatter(
'%(asctime)s : %(levelname)s : Line No %(lineno)d : %(message)s')
file_handler.setFormatter(formatter)
log.addHandler(file_handler)
# Determine log level.
verbose = args.verbose
if verbose is True:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
sys.stdout = open(log_filename, 'a')
set_up_dict['log'] = logging.getLogger(__name__)
# Establish database connection.
set_up_dict['conn'], conn_description = establish_db_connection(
server, database, username, password)
# Official timestamp for this script.
set_up_dict['the_time'] = strict_rfc3339.now_to_rfc3339_localoffset()
log.info('Done setting up the environment, db connections and logging.')
log.info(conn_description)
if extra_args != []:
log.info(
'These extra arguments were not used by set_up_db_reading(): {}'.
format(extra_args))
return set_up_dict
def now():
"""the current time point"""
return str(strict_rfc3339.now_to_rfc3339_localoffset())
def now():
"""the current time point"""
return str(strict_rfc3339.now_to_rfc3339_localoffset())
