Source code for pycif.plugins.datastreams.fluxes.VPRM_nc.fetch

import datetime
import glob
import os
from logging import info

import numpy as np
import pandas as pd

from .....utils import path
from .utils import find_valid_file




def fetch(ref_dir, ref_file, input_interval, target_dir, tracer=None, **kwargs):
    """Fetch VPRM flux files and build hourly date intervals covering the simulation window.

    Iterates hourly over `input_interval`; for each hour, uses
    `find_valid_file` to locate the nearest available (forecast-style)
    file bracketing it, considering the current directory as well as the
    previous/next hour's directory when close to a boundary, and links the
    nearest file into `target_dir` if it exists.

    Args:
        ref_dir (str): Directory (or ``strftime`` pattern) containing the
            reference input files.
        ref_file (str): Filename pattern of the input files (a ``strftime``
            format string).
        input_interval (list[datetime.datetime]): ``[date_i, date_f]``
            simulation interval to cover.
        target_dir (str): Directory where the resolved files are linked.
        tracer: Unused directly, kept for interface consistency with other
            flux plugins.

    Returns:
        tuple[dict, dict]: ``(list_files, list_dates)``, each keyed by the
        hourly date, mapping to the list of resolved file paths and a
        single-element list with the ``[start, end]`` one-hour date
        interval.
    """

    # Inputs:
    # ---------
    # ref_dir: directory where the original files are found
    # ref_file: (template) name of the original files
    # input_interval: list of the periods to simulate, each item is the list of the dates of the period
    # target_dir: directory where the links to the orginal files are created
    #
    # Ouputs:
    # ---------
    # list_files: for each date that begins a period, an array containing the names of the files that are available
    # for the dates within this period
    # list_dates: for each date that begins a period, an array containing the names of the dates mathcin the files
    # listed in list_files
    list_period_dates = pd.date_range(input_interval[0], input_interval[1], freq="1h")
    list_dates = {}
    list_files = {}
    for dd in list_period_dates:
        dir_dd = dd.strftime(ref_dir)
        dir_dd_next = (dd + datetime.timedelta(hours=1)).strftime(ref_dir)
        dir_dd_previous = (dd - datetime.timedelta(hours=1)).strftime(ref_dir)
        files_3d, dates_3d = find_valid_file(
            dir_dd, ref_file, dd, dir_dd_next, ref_dir_previous=dir_dd_previous
        )

        if os.path.isfile(files_3d[0]):
            list_dates[dd] = [[dd, dd + datetime.timedelta(hours=1)]]
            list_files[dd] = [files_3d]

            # the  to fetch is a forecast
            local_files = []
            target_file = f"{target_dir}/{dd.strftime(ref_file)}"
            path.link(files_3d[0], target_file)
            local_files.append(target_file)

    return list_files, list_dates