aswi2020sebela-gitlab/modules/crawler/DatasetProcessing/JISProcessor.py @ 342ea08a

from Utilities.CSV import CSVDataLine
from Utilities import DateFormating


def process_file(filename):
    """
    Method that take path to crawled file and outputs date dictionary:
    Date dictionary is a dictionary where keys are dates in format ddmmYYYYhh (0804201815)
    and value is dictionary where keys devices (specified in configuration file)
    and value is CSVDataLine.CSVDataLine with device,date and occurrence

    Args:
    filename: name of processed file

    Returns:
    None if not implemented
    date_dict when implemented
    """
    date_dict = dict()

    with open(filename, "r", encoding="utf-8") as file:

        for line in file:

            array = line.split(";")

            date = DateFormating.date_time_formatter(array[1][1:-1])
            name = array[0][1:-1]
            occurrence = array[2][:-1]

            if date not in date_dict:
                date_dict[date] = dict()

            if name in date_dict[date]:
                date_dict[date][name].occurrence += int(occurrence)
            else:
                date_dict[date][name] = CSVDataLine.CSVDataLine(name, date, occurrence)

    return date_dict