Python DatasetNetCDF.unload方法代碼示例

# 需要導入模塊: from geodata.netcdf import DatasetNetCDF [as 別名]
# 或者: from geodata.netcdf.DatasetNetCDF import unload [as 別名]

#.........這裏部分代碼省略.........
  
  ## extract meta data from arguments
  module, dataargs, loadfct, filepath, 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 
            
  # determine age of source file
  if not loverwrite: sourceage = datetime.fromtimestamp(os.path.getmtime(filepath))    
          
  # get filename for target dataset and do some checks
  filename = getTargetFile(stndata.name, dataset, mode, module, dataargs, lwrite)
  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 > sourceage and os.path.getsize(filepath) > 1e5: lskip = True
        # N.B.: NetCDF files smaller than 100kB are usually incomplete header fragments from a previous crashed
      if not lskip: os.remove(filepath) # recompute
  
  # 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"