Model/model_data/utils.py
2023-07-03 18:12:23 +01:00

61 lines
1.9 KiB
Python

import logging
import re
from textblob import TextBlob
# Pre-compile the regular expression
PERCENTAGE_PATTERN = re.compile(r'^\d+%?$')
def setup_logger(log_file=None, level=logging.INFO, overwrite_handler=False):
# Create a logger and set the logging level
logger = logging.getLogger()
logger.setLevel(level)
# if logger already has handlers, just return it
if logger.hasHandlers() and not overwrite_handler:
return logger
# Define the log message format
log_format = "%(asctime)s [%(levelname)s] %(message)s"
date_format = "%Y-%m-%d %H:%M:%S"
formatter = logging.Formatter(log_format, datefmt=date_format)
# Create a file handler and set the file path and format
if log_file:
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(level)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Create a console handler and set the format
console_handler = logging.StreamHandler()
console_handler.setLevel(level)
# Set the formatter for the handlers
console_handler.setFormatter(formatter)
# Add the handlers to the logger
logger.addHandler(console_handler)
return logger
def is_percentage_or_number(s):
# re.match returns None if the string does not match the pattern
return PERCENTAGE_PATTERN.match(s) is not None
def correct_spelling(text):
words = text.split()
corrected_words = []
for word in words:
if is_percentage_or_number(word):
corrected_words.append(word)
else:
blob = TextBlob(word) # create a TextBlob object
corrected_word = blob.correct() # use the correct method to correct spelling
corrected_words.append(str(corrected_word)) # convert corrected word back to string
corrected_text = ' '.join(corrected_words)
return corrected_text