Source code for pycif.plugins.datastreams.fields.noaa_glob_avg.fetch

import os
import numpy as np
from dateutil import relativedelta
import datetime
import pandas as pd
from .....utils import path




def fetch(ref_dir, ref_file, date_interval, target_dir, tracer=None, **kwargs):
    """Fetch monthly NOAA global-average files.

    Forces the start date to the beginning of its month and extends the
    end date by one month, then for each month (stepped at
    ``tracer.file_freq``) links the corresponding file into
    ``target_dir`` if it exists, with a one-month ``list_dates``
    interval.

    Args:
        ref_dir: directory where the original files are found.
        ref_file: (template) name of the original files.
        date_interval: list of two dates, the beginning and end of the
            simulation.
        target_dir: directory where links to the original files are
            created.
        tracer: the fields Plugin, giving access to ``file_freq``.

    Returns:
        list_files: for each monthly date, a one-element list with the
            file path.
        list_dates: for each monthly date, a one-element list with the
            ``[start, end]`` interval covering that month.
    """
    datei, datef = date_interval
    datei = datetime.datetime(year=datei.year, month=datei.month, day=1)
    datef = datef + relativedelta.relativedelta(months=1)
    list_period_dates = pd.date_range(datei, datef, freq=tracer.file_freq)

    list_dates = {}
    list_files = {}
    for dd in list_period_dates:
        file = dd.strftime(f"{ref_dir}/{ref_file}")
        if os.path.isfile(file):
            list_dates[dd] = [[dd, dd + relativedelta.relativedelta(months=1)]]
            list_files[dd] = [file]
            
            # Fetching
            target_file = f"{target_dir}/{os.path.basename(file)}"
            path.link(file, target_file)
    
    return list_files, list_dates