Jean-Baptiste/email_parser

1from functools import wraps2import logging3import os4from time import time5import configparser6 7timer_functions = {}8 9# Loading configuration from config file10config = configparser.ConfigParser()11config.read(os.path.join(os.path.dirname(__file__), 'config.ini'))12 13 14def timing(f):15    @wraps(f)16    def wrap(*args, **kw):17        ts = time()18        result = f(*args, **kw)19        te = time()20        if f.__name__ in timer_functions.keys():21            current_elapsed_time = timer_functions[f.__name__]22        else:23            current_elapsed_time = 024        timer_functions[f.__name__] = current_elapsed_time + (te - ts)25        logging.debug('func:%r took: %2.4f sec' % \26                        (f.__name__, te - ts))27        return result28    return wrap29 30 31def f_read_config(path=None):32    """ read config file from specified file path33    34    :param path: file path35    :return: configparser object36    """37    # Loading configuration from config file38    config = configparser.ConfigParser()39    if path is None:40        path = os.path.join(os.path.dirname(__file__), 'config.ini')41    config.read(path, encoding='utf-8')42    return config43 44def f_setup_logger(level_sysout=logging.INFO, level_file=logging.DEBUG, folder_path="logs"):45    """Setup logger46 47    By default we display only INFO in console, and write everything in file48 49    Args:50        level_sysout: Level that is displayed in console (default INFO)51        level_file: Level that is written in file (default DEBUG)52 53    Returns:54        Nothing55 56    """57    if not os.path.isdir(folder_path):58        os.mkdir(folder_path)59 60    for handler in logging.root.handlers[:]:61        logging.root.removeHandler(handler)62 63    file_handler = logging.FileHandler(filename=os.path.join(folder_path, "amf_uce_nlp_{}.log".format(time())),64                                       encoding='utf-8')65    sysout_handler = logging.StreamHandler()66    file_handler.setLevel(level_file)67    sysout_handler.setLevel(level_sysout)68    logging.basicConfig(handlers=[file_handler, sysout_handler], level=logging.DEBUG,69                        format='%(asctime)s (%(levelname)s) %(message)s', datefmt='%m/%d/%y %I:%M:%S %p')70 71 72def get_model_full_path(model_name):73    path_models = config["DEFAULT"]["path_models"]74    return os.path.join(os.path.dirname(__file__), path_models, model_name)75 76 77def f_normalize_text(text):78    """Repair common mojibake patterns while leaving normal Unicode text unchanged."""79    if not isinstance(text, str) or text == "":80        return text81 82    suspicious_markers = ("Ã", "’", "“", "â€\x9d", "–", "—", "Â")83    if not any(marker in text for marker in suspicious_markers):84        return text85 86    for source_encoding in ("latin-1", "cp1252"):87        try:88            repaired = text.encode(source_encoding).decode("utf-8")89        except (UnicodeEncodeError, UnicodeDecodeError):90            continue91        if repaired != text:92            return repaired93    return text94