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

import os
import numpy as np

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




def fetch(ref_dir, ref_file, input_interval, target_dir, tracer=None, **kwargs):
    """Fetch legacy LMDZ4 prescribed-concentration files.

    ``input_interval`` is a mapping of key dates to lists of sub-dates;
    for each sub-date, calls :func:`~.utils.find_valid_file` to locate
    the two straddling files, links them into ``target_dir``, and
    deduplicates the resulting file/date pairs.

    Args:
        ref_dir: directory where the original files are found.
        ref_file: (template) name of the original files.
        input_interval: mapping of key dates to the list of sub-dates
            covered under each key.
        target_dir: directory where links to the original files are
            created.
        tracer: unused, accepted for interface compatibility.

    Returns:
        list_files: for each key date, the deduplicated array of file
            paths matching ``list_dates``.
        list_dates: for each key date, the deduplicated, sorted array of
            dates found by :func:`~.utils.find_valid_file`.
    """

    list_files = {}
    list_dates = {}
    for datei in input_interval:
        tmp_files = []
        tmp_dates = []
        for dd in input_interval[datei]:
            # print('Date to simulate',dd)
            files_orig, dates_orig = find_valid_file(ref_dir, ref_file, dd)
            # print(files_orig,dates_orig)
            tmp_files.extend(files_orig)
            tmp_dates.extend(dates_orig)
        # print('wwwwwwwwwwwwwwww',tmp_dates)
        # Fetching
        local_files = []
        for f, dd in zip(tmp_files, tmp_dates):
            target_file = f"{target_dir}/{dd.strftime(ref_file)}"
            # print('ttt',target_file)
            path.link(f, target_file)
            local_files.append(target_file)

        unique_dates, unique_index = np.unique(tmp_dates, return_index=True)
        list_files[datei] = np.array(tmp_files)[unique_index]
        list_dates[datei] = unique_dates

    return list_files, list_dates