def createNsNode(inputDoc, namespaces):
nsNode = inputDoc.createElement("NAMESPACE")
st = StringTokenizer(namespaces)
while (st.hasMoreTokens()):
token = st.nextToken().split('=')
nsNode.setAttribute("xmlns:" + token[0], token[1])
return nsNode;
def _get_viewbox_values(view_box_str):
view_box_values = []
st = StringTokenizer(view_box_str," ")
while st.hasMoreTokens():
view_box_values.append(int(st.nextToken()))
return view_box_values
def _get_viewbox_values(view_box_str):
view_box_values = []
st = StringTokenizer(view_box_str, " ")
while st.hasMoreTokens():
ch = st.nextToken()
try:
view_box_values.append(float(ch))
except:
view_box_values.append(int(ch))
return view_box_values
def _get_viewbox_values(view_box_str):
view_box_values = []
st = StringTokenizer(view_box_str," ")
while st.hasMoreTokens():
ch = st.nextToken()
try:
view_box_values.append(float(ch))
except:
view_box_values.append(int(ch))
return view_box_values
def retrieve_ts(station,sensor,\
start_date, end_date='now',_verbose=1):
"""
retrieve(station,sensor, start_date, end_date='now',_verbose=1)
Retrieves data from cdec station and sensor and
constructs a regular time series with given pathname, units.
The start_date is a starting time value in format mm/dd/yyyy
e.g. 15-Jun-2000 would be 06/15/2000
The end_date can either be the keyword "now" or the same format as
the start_date
verbose=1 sets it to more verbose and 0 for silence
"""
_debug = 0
station_name = station.id
sensor_number = sensor.sensor_number
c_part = "%s_%s" % (sensor.type, sensor.subType)
f_part = "SENSOR %s" % (sensor.id)
pathname = '/%s/%s/%s//%s/%s/' % ('CDEC-RAW', station_name, c_part,
DSS_INTERVAL[sensor.duration],
"SENSOR " + sensor.id)
units = sensor.units
dur_code = sensor.getDurationCode()
c_url = URL('http://cdec.water.ca.gov/cgi-progs/queryCSV?' +
'station_id=' + str(station_name) + '&dur_code=' +
str(dur_code) + '&sensor_num=' + str(sensor_number) +
'&start_date=' + start_date + '&end_date=' + end_date)
if _verbose:
print "station name:%s & sensor number:%s " % (station_name,
sensor_number)
print "dur_code:%s " % (dur_code)
print "pathname:%s & units:%s" % (pathname, units)
print 'URL: %s' % c_url
lr = LineNumberReader(
InputStreamReader(c_url.openConnection().getInputStream()))
# jump all the way to data
lr.readLine()
lr.readLine()
lr.readLine()
# create starting date and time and of the format the
# data is at cdec
line = lr.readLine()
tf = TimeFactory.getInstance()
starray = string.split(line, ',')
dtm = starray[0] + ' ' + starray[1]
tp = tf.createTime(dtm, 'yyyyMMdd HHmm')
tp = tf.createTime(tp.getTimeInMinutes())
ti_str = '1HOUR'
irreg = 0 # indicates the data as irregular time series
if dur_code == 'E':
irreg = 1
ti_str = 'IR-DAY'
elif dur_code == 'D':
ti_str = '1DAY'
elif dur_code == 'H':
ti_str = '1HOUR'
elif dur_code == 'M':
ti_str = '1MON'
if not irreg:
ti = tf.createTimeInterval(ti_str)
ltime = tp
if _debug: print line, tp, dtm
yvals = []
if irreg:
tvals = []
if _verbose: print 'Data starting at ', tp
# read in all the data and append missing values if no data
# is available
while line != None:
st = StringTokenizer(line, ',')
if (st.countTokens() != 3):
raise "Invalid CDEC format, need 3 tokens on line: " + line
# get time
ctime = tf.createTime(st.nextToken() + ' ' + st.nextToken(),
'yyyyMMdd HHmm')
# if time is not in increasing order -> quit!
if ctime.compare(ltime) < 0:
raise "Invalid time sequence: %s followed by %s"+\
" ? -> should be always increasing"%(str(ctime),str(ltime))
# check if current time is only one time interval from last time
if not irreg:
nskip = ltime.getNumberOfIntervalsTo(ctime, ti)
# if skip is greater than one then fill with -901's
while nskip > 1:
yvals.append(Constants.MISSING_VALUE)
nskip = nskip - 1
ltime = ctime
# now get current value
val_str = st.nextToken()
try:
if (val_str == "m"): # if missing
val = Constants.MISSING_VALUE
else: # else just save the value
val = float(val_str)
if irreg:
tvals.append(ctime)
yvals.append(val)
except:
tvals.append(ctime)
yvals.append(Constants.MISSING_VALUE)
print "Exception! for string ", val_str
line = lr.readLine()
# create a time series data set from the array of values,
# the start time and the time interval
if irreg:
attr = DataSetAttr(DataType.IRREGULAR_TIME_SERIES, '', units, 'TIME',
'INST-VAL')
its = IrregularTimeSeries(pathname, tvals, yvals, None, attr)
return its
else:
attr = DataSetAttr(DataType.REGULAR_TIME_SERIES, '', units, 'TIME',
'INST-VAL')
rts = RegularTimeSeries(pathname, tp.toString(), ti_str, yvals, None,
attr)
return rts
def retrieve_ts(station,sensor,\
start_date, end_date='now',_verbose=1):
"""
retrieve(station,sensor, start_date, end_date='now',_verbose=1)
Retrieves data from cdec station and sensor and
constructs a regular time series with given pathname, units.
The start_date is a starting time value in format mm/dd/yyyy
e.g. 15-Jun-2000 would be 06/15/2000
The end_date can either be the keyword "now" or the same format as
the start_date
verbose=1 sets it to more verbose and 0 for silence
"""
_debug=0
station_name=station.id
sensor_number=sensor.sensor_number
c_part="%s_%s"%(sensor.type,sensor.subType)
f_part="SENSOR %s"%(sensor.id)
pathname='/%s/%s/%s//%s/%s/'%('CDEC-RAW',station_name,c_part,DSS_INTERVAL[sensor.duration],"SENSOR "+sensor.id)
units=sensor.units
dur_code = sensor.getDurationCode()
c_url = URL('http://cdec.water.ca.gov/cgi-progs/queryCSV?'
+'station_id='+str(station_name)
+'&dur_code='+str(dur_code)+'&sensor_num='+str(sensor_number)
+'&start_date='+start_date
+'&end_date='+end_date)
if _verbose:
print "station name:%s & sensor number:%s "%(station_name,sensor_number)
print "dur_code:%s "%(dur_code)
print "pathname:%s & units:%s"%(pathname,units)
print 'URL: %s'%c_url
lr = LineNumberReader(InputStreamReader(c_url.openConnection().getInputStream()))
# jump all the way to data
lr.readLine()
lr.readLine()
lr.readLine()
# create starting date and time and of the format the
# data is at cdec
line = lr.readLine()
tf = TimeFactory.getInstance()
starray = string.split(line,',')
dtm = starray[0] + ' ' + starray[1]
tp = tf.createTime(dtm,'yyyyMMdd HHmm')
tp = tf.createTime(tp.getTimeInMinutes())
ti_str='1HOUR'
irreg=0 # indicates the data as irregular time series
if dur_code=='E':
irreg=1
ti_str='IR-DAY'
elif dur_code=='D':
ti_str='1DAY'
elif dur_code=='H':
ti_str='1HOUR'
elif dur_code=='M':
ti_str='1MON'
if not irreg:
ti = tf.createTimeInterval(ti_str)
ltime = tp
if _debug: print line, tp,dtm
yvals = []
if irreg:
tvals=[]
if _verbose: print 'Data starting at ', tp
# read in all the data and append missing values if no data
# is available
while line != None:
st = StringTokenizer(line,',')
if ( st.countTokens() != 3 ) :
raise "Invalid CDEC format, need 3 tokens on line: " + line
# get time
ctime = tf.createTime(st.nextToken()+' '+st.nextToken(),'yyyyMMdd HHmm')
# if time is not in increasing order -> quit!
if ctime.compare(ltime) < 0:
raise "Invalid time sequence: %s followed by %s"+\
" ? -> should be always increasing"%(str(ctime),str(ltime))
# check if current time is only one time interval from last time
if not irreg:
nskip = ltime.getNumberOfIntervalsTo(ctime,ti)
# if skip is greater than one then fill with -901's
while nskip > 1:
yvals.append(Constants.MISSING_VALUE)
nskip=nskip-1
ltime = ctime
# now get current value
val_str = st.nextToken()
try :
if ( val_str == "m" ): # if missing
val=Constants.MISSING_VALUE
else: # else just save the value
val=float(val_str)
if irreg:
tvals.append(ctime)
yvals.append(val)
except:
tvals.append(ctime)
yvals.append(Constants.MISSING_VALUE)
print "Exception! for string " ,val_str
line = lr.readLine();
# create a time series data set from the array of values,
# the start time and the time interval
if irreg:
attr = DataSetAttr(DataType.IRREGULAR_TIME_SERIES,'',units,'TIME','INST-VAL')
its = IrregularTimeSeries(pathname,tvals,yvals,None,attr)
return its
else:
attr = DataSetAttr(DataType.REGULAR_TIME_SERIES,'',units,'TIME','INST-VAL')
rts = RegularTimeSeries(pathname,tp.toString(),ti_str,yvals,None,attr)
return rts
def testNullDelimiters(self):
"Tokenizing a string containing nulls"
tokenizer = StringTokenizer("a\000b\000c", "\000")
assert self._getTokens(tokenizer) == ['a', 'b', 'c']
def testDefaultTokenizing(self):
"Default tokenizing with whitespace delimiters"
tokenizer = StringTokenizer("mary had\t a\n little lamb")
assert self._getTokens(tokenizer) == [
'mary', 'had', 'a', 'little', 'lamb'
]
from java.util import StringTokenizer as ST from java.io import BufferedReader as BR ,InputStreamReader as IR from java.lang import System as S string = BR(IR(S.in)).readLine() st1 = ST(string," ") print (st1.countTokens()) while (st1.hasMoreTokens()): print (st1.nextToken())
