def dateformat(value):
"""Return seconds since epoch for provided YYYYMMDD or number with suffix 'd' for days"""
msg = 'Unacceptable date format, value=%s, type=%s,' \
% (value, type(value))
msg += " supported format is YYYYMMDD or number with suffix 'd' for days"
value = str(value).lower()
if PAT_YYYYMMDD.match(value): # we accept YYYYMMDD
if len(value) == 8: # YYYYMMDD
year = value[0:4]
if not PAT_YYYY.match(year):
raise Exception(msg +
', fail to parse the year part, %s' % year)
month = value[4:6]
date = value[6:8]
ddd = datetime.date(int(year), int(month), int(date))
else:
raise Exception(msg)
return calendar.timegm((ddd.timetuple()))
elif value.endswith('d'):
try:
days = int(value[:-1])
except ValueError:
raise Exception(msg)
return time.time() - days * 24 * 60 * 60
else:
raise Exception(msg)
def dateformat(value):
"""Return seconds since epoch for provided YYYYMMDD or number with suffix 'd' for days"""
msg = 'Unacceptable date format, value=%s, type=%s,' \
% (value, type(value))
msg += " supported format is YYYYMMDD or number with suffix 'd' for days"
value = str(value).lower()
if PAT_YYYYMMDD.match(value): # we accept YYYYMMDD
if len(value) == 8: # YYYYMMDD
year = value[0:4]
if not PAT_YYYY.match(year):
raise Exception(msg + ', fail to parse the year part, %s' % year)
month = value[4:6]
date = value[6:8]
ddd = datetime.date(int(year), int(month), int(date))
else:
raise Exception(msg)
return calendar.timegm((ddd.timetuple()))
elif value.endswith('d'):
try:
days = int(value[:-1])
except ValueError:
raise Exception(msg)
return time.time()-days*24*60*60
else:
raise Exception(msg)
def hdfs_file(odir, name):
"""
Given HDFS dir and file name create appropriate dir structure on HDFS
and return full path of the file. We rely on odir/YYYY/MM/DD dir structure.
"""
tstamp = name.split('/')[-1].split('_')[
0] # each file is in form YYYYMMDD_HHMM.ext
if not PAT_YYYYMMDD.match(tstamp):
raise Exception(
"Given file name '%s' does not contain YYYYMMDD stamp" % name)
year = tstamp[:4]
if not PAT_YYYY.match(year):
raise Exception("Given file name '%s' does not contain YYYY stamp" %
name)
month = tstamp[4:6]
if not PAT_MM.match(month):
raise Exception("Given file name '%s' does not contain MM stamp" %
name)
day = tstamp[6:8]
if not PAT_DD.match(day):
raise Exception("Given file name '%s' does not contain DD stamp" %
name)
if not hdfs.path.isdir(odir):
hdfs.mkdir(odir)
for subdir in [year, month, day]:
odir = os.path.join(odir, subdir)
if not hdfs.path.isdir(odir):
hdfs.mkdir(odir)
return os.path.join(odir, name)
def test_pat_yyyy(self):
"Test PAT_YYYY pattern"
date = '2015'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, True)
date = '2123'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
date = '20151'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
date = '3015'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
date = '1015'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
def test_pat_yyyy(self):
"Test PAT_YYYY pattern"
date = '2015'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, True)
date = '2123'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
date = '20151'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
date = '3015'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
date = '1015'
res = True if PAT_YYYY.match(date) else False
self.assertEqual(res, False)
def hdfs_file(odir, name):
"""
Given HDFS dir and file name create appropriate dir structure on HDFS
and return full path of the file. We rely on odir/YYYY/MM/DD dir structure.
"""
tstamp = name.split('/')[-1].split('_')[0] # each file is in form YYYYMMDD_HHMM.ext
if not PAT_YYYYMMDD.match(tstamp):
raise Exception("Given file name '%s' does not contain YYYYMMDD stamp" % name)
year = tstamp[:4]
if not PAT_YYYY.match(year):
raise Exception("Given file name '%s' does not contain YYYY stamp" % name)
month = tstamp[4:6]
if not PAT_MM.match(month):
raise Exception("Given file name '%s' does not contain MM stamp" % name)
day = tstamp[6:8]
if not PAT_DD.match(day):
raise Exception("Given file name '%s' does not contain DD stamp" % name)
if not hdfs.path.isdir(odir):
hdfs.mkdir(odir)
for subdir in [year, month, day]:
odir = os.path.join(odir, subdir)
if not hdfs.path.isdir(odir):
hdfs.mkdir(odir)
return os.path.join(odir, name)