Source code for pycif.plugins.datastreams.fields.oldlmdz_prescrconcs.utils

import datetime
import glob
import os
import calendar 
import numpy as np



def find_valid_file(ref_dir, file_format, dd):
    
    # Get all files and dates matching the file and format
    list_files_orig = os.listdir(ref_dir)
    list_files_avail = [] #list available files
    # if dd first hour of the month, needs file of the month before
    for f in list_files_orig:
      try:
         check = datetime.datetime.strptime(f, file_format)
         if check.year == dd.year and check.month == dd.month:
           list_files_avail.append(f)
         if dd.hour == 0:
           if -1 > (check - dd).days >= -31:
             list_files_avail.append(f)             
      except:
            continue
    #print(list_files_avail)

    list_files = []
    list_dates = []
    # actually in each file, information every hour
    # but at half hours
    delta_t = 1
    for f in list_files_avail:
      date_beg = datetime.datetime.strptime(f, file_format) + datetime.timedelta(hours = 0.5)
      date_end = date_beg + datetime.timedelta( days = calendar.mdays[date_beg.month] + calendar.isleap(date_beg.year))
      nb_deltas = int((date_end - date_beg).days * 24 / delta_t)
      #print(f,date_beg,date_end,nb_deltas)
      list_dates_covered = [ date_beg + ( k + 1 ) * datetime.timedelta( hours = delta_t ) for k in range(nb_deltas) ]
      #print(list_dates_covered)
      for d in list_dates_covered:
         list_files.append(f)
         list_dates.append(d)

    list_files = np.array(list_files)
    list_dates = np.array(list_dates)
    # Sorting along dates
    isort = np.argsort(list_dates)
    list_dates = list_dates[isort]
    list_files = list_files[isort]   
    if list_files == []:
        raise Exception("Did not find any valid files for prescribed concentrations in {} "
                        "with format {}. Please check your yml file"
                        .format(ref_dir, file_format))

   
    # Compute deltas
    mask = (list_dates - dd) <= datetime.timedelta(0)
    #print(mask)
    file_ref1 = ref_dir + list_files[mask][np.argmax(list_dates[mask])]
    date_ref1 = list_dates[mask].max()
    #print(file_ref1, date_ref1,dd)
    mask = (list_dates - dd) >= datetime.timedelta(0)
    #print('mmmm',mask)
    file_ref2 = ref_dir + list_files[mask][np.argmin(list_dates[mask])]
    date_ref2 = list_dates[mask].min()
    #print(file_ref2, date_ref2,dd)

    return  [file_ref1, file_ref2], [date_ref1, date_ref2]