def sanitize_downloads(self, logger):
"""
Should be run after the MiniSEED and StationXML downloads finished.
It will make sure that every MiniSEED file also has a corresponding
StationXML file.
It will delete MiniSEED files but never a StationXML file. The logic
of the download helpers does not allow for a StationXML file with no
data.
"""
from obspy.io.mseed.util import get_start_and_end_time
# All or nothing for each channel.
for id in self.miss_station_information.keys():
logger.warning("Station information could not be downloaded for "
"%s.%s.%s.%s. MiniSEED files outside of the "
"station information period "
"will be deleted!" % (
self.network, self.station, id[0], id[1]))
channel = [_i for _i in self.channels if
(_i.location, _i.channel) == id][0]
for time_interval in channel.intervals:
# Check that the time_interval.start and end are correct!
time_interval.start, time_interval.end = \
get_start_and_end_time(time_interval.filename)
# Only delete downloaded things!
if time_interval.status == STATUS.DOWNLOADED:
# Only delete if the station data are actually missing
# for this time
miss_start, miss_end = self.miss_station_information[id]
if miss_start <= time_interval.start <= miss_end and \
miss_start <= time_interval.end <= miss_end:
utils.safe_delete(time_interval.filename)
time_interval.status = STATUS.DOWNLOAD_REJECTED
def test_getStartAndEndTime(self):
"""
Tests getting the start- and endtime of a file.
The values are compared with the results of reading the full files.
"""
mseed_filenames = ['BW.BGLD.__.EHE.D.2008.001.first_10_records',
'test.mseed', 'timingquality.mseed']
for _i in mseed_filenames:
filename = os.path.join(self.path, 'data', _i)
# Get the start- and end time.
(start, end) = util.get_start_and_end_time(filename)
# Parse the whole file.
stream = _read_mseed(filename)
self.assertEqual(start, stream[0].stats.starttime)
self.assertEqual(end, stream[0].stats.endtime)
def test_getStartAndEndTime(self):
"""
Tests getting the start- and endtime of a file.
The values are compared with the results of reading the full files.
"""
mseed_filenames = [
'BW.BGLD.__.EHE.D.2008.001.first_10_records', 'test.mseed',
'timingquality.mseed'
]
for _i in mseed_filenames:
filename = os.path.join(self.path, 'data', _i)
# Get the start- and end time.
(start, end) = util.get_start_and_end_time(filename)
# Parse the whole file.
stream = _read_mseed(filename)
self.assertEqual(start, stream[0].stats.starttime)
self.assertEqual(end, stream[0].stats.endtime)