def performExtraction(dataset,
mode,
stnfct,
dataargs,
loverwrite=False,
varlist=None,
lwrite=True,
lreturn=False,
ldebug=False,
lparallel=False,
pidstr='',
logger=None):
''' worker function to extract point data from gridded dataset '''
# input checking
if not isinstance(dataset, basestring): raise TypeError
if not isinstance(dataargs, dict):
raise TypeError # all dataset arguments are kwargs
if not callable(stnfct):
raise TypeError # function to load station dataset
if lparallel:
if not lwrite:
raise IOError, 'In parallel mode we can only write to disk (i.e. lwrite = True).'
if lreturn:
raise IOError, 'Can not return datasets in parallel mode (i.e. lreturn = False).'
# logging
if logger is None: # make new logger
logger = logging.getLogger() # new logger
logger.addHandler(logging.StreamHandler())
else:
if isinstance(logger, basestring):
logger = logging.getLogger(name=logger) # connect to existing one
elif not isinstance(logger, logging.Logger):
raise TypeError, 'Expected logger ID/handle in logger KW; got {}'.format(
str(logger))
lclim = False
lts = False
if mode == 'climatology': lclim = True
elif mode == 'time-series': lts = True
else: raise NotImplementedError, "Unrecognized Mode: '{:s}'".format(mode)
## extract meta data from arguments
dataargs, loadfct, srcage, datamsgstr = getMetaData(
dataset, mode, dataargs)
dataset_name = dataargs.dataset_name
periodstr = dataargs.periodstr
avgfolder = dataargs.avgfolder
# load template dataset
stndata = stnfct() # load station dataset from function
if not isinstance(stndata, Dataset): raise TypeError
# N.B.: the loading function is necessary, because DataseNetCDF instances do not pickle well
# get filename for target dataset and do some checks
filename = getTargetFile(dataset=dataset,
mode=mode,
dataargs=dataargs,
lwrite=lwrite,
station=stndata.name)
if ldebug: filename = 'test_' + filename
if not os.path.exists(avgfolder):
raise IOError, "Dataset folder '{:s}' does not exist!".format(
avgfolder)
lskip = False # else just go ahead
if lwrite:
if lreturn:
tmpfilename = filename # no temporary file if dataset is passed on (can't rename the file while it is open!)
else:
if lparallel: tmppfx = 'tmp_exstns_{:s}_'.format(pidstr[1:-1])
else: tmppfx = 'tmp_exstns_'.format(pidstr[1:-1])
tmpfilename = tmppfx + filename
filepath = avgfolder + filename
tmpfilepath = avgfolder + tmpfilename
if os.path.exists(filepath):
if not loverwrite:
age = datetime.fromtimestamp(os.path.getmtime(filepath))
# if source file is newer than sink file or if sink file is a stub, recompute, otherwise skip
if age > srcage and os.path.getsize(filepath) > 1e5:
lskip = True
# N.B.: NetCDF files smaller than 100kB are usually incomplete header fragments from a previous crashed
# depending on last modification time of file or overwrite setting, start computation, or skip
if lskip:
# print message
skipmsg = "\n{:s} >>> Skipping: file '{:s}' in dataset '{:s}' already exists and is newer than source file.".format(
pidstr, filename, dataset_name)
skipmsg += "\n{:s} >>> ('{:s}')\n".format(pidstr, filepath)
logger.info(skipmsg)
else:
## actually load datasets
source = loadfct() # load source
# check period
if 'period' in source.atts and dataargs.periodstr != source.atts.period: # a NetCDF attribute
raise DateError, "Specifed period is inconsistent with netcdf records: '{:s}' != '{:s}'".format(
periodstr, source.atts.period)
# print message
if lclim:
opmsgstr = "Extracting '{:s}'-type Point Data from Climatology ({:s})".format(
stndata.name, periodstr)
elif lts:
opmsgstr = "Extracting '{:s}'-type Point Data from Time-series".format(
stndata.name)
else:
raise NotImplementedError, "Unrecognized Mode: '{:s}'".format(mode)
# print feedback to logger
logger.info(
'\n{0:s} *** {1:^65s} *** \n{0:s} *** {2:^65s} *** \n'
.format(pidstr, datamsgstr, opmsgstr))
if not lparallel and ldebug: logger.info('\n' + str(source) + '\n')
## create new sink/target file
# set attributes
atts = source.atts.copy()
atts[
'period'] = dataargs.periodstr if dataargs.periodstr else 'time-series'
atts['name'] = dataset_name
atts['station'] = stndata.name
atts['title'] = '{:s} (Stations) from {:s} {:s}'.format(
stndata.title, dataset_name, mode.title())
# make new dataset
if lwrite: # write to NetCDF file
if os.path.exists(tmpfilepath):
os.remove(tmpfilepath) # remove old temp files
sink = DatasetNetCDF(folder=avgfolder,
filelist=[tmpfilename],
atts=atts,
mode='w')
else:
sink = Dataset(atts=atts) # ony create dataset in memory
# initialize processing
CPU = CentralProcessingUnit(source,
sink,
varlist=varlist,
tmp=False,
feedback=ldebug)
# extract data at station locations
CPU.Extract(template=stndata, flush=True)
# get results
CPU.sync(flush=True)
# print dataset
if not lparallel and ldebug:
logger.info('\n' + str(sink) + '\n')
# write results to file
if lwrite:
sink.sync()
writemsg = "\n{:s} >>> Writing to file '{:s}' in dataset {:s}".format(
pidstr, filename, dataset_name)
writemsg += "\n{:s} >>> ('{:s}')\n".format(pidstr, filepath)
logger.info(writemsg)
# rename file to proper name
if not lreturn:
sink.unload()
sink.close()
del sink # destroy all references
if os.path.exists(filepath):
os.remove(filepath) # remove old file
os.rename(tmpfilepath, filepath)
# N.B.: there is no temporary file if the dataset is returned, because an open file can't be renamed
# clean up and return
source.unload()
del source #, CPU
if lreturn:
return sink # return dataset for further use (netcdf file still open!)
else:
return 0 # "exit code"
