Script for detecting and treating files whether utf-8 or ansi files

ansi_or_utf8_text_processing.py

import sys
try:
  FILE_PATH =sys.argv[1]
except IndexError:
  print("need pass a file as input parameter\npython my_script.py my_csv_file.csv")
  exit()

def predict_encoding(file_path, n_lines=20):
    '''Predict a file's encoding using chardet'''
    import chardet

    # Open the file as binary data
    with open(file_path, 'rb') as f:
        # Join binary lines for specified number of lines
        rawdata = b''.join([f.readline() for _ in range(n_lines)])
    a = chardet.detect(rawdata)['encoding']

    return chardet.detect(rawdata)['encoding']
    
ANSI_CODE = "ISO-8859-1"
FILE_ENCODE = predict_encoding(FILE_PATH)
    
def ansiToUtf8(string, FILE_ENCODE):
    if ANSI_CODE == FILE_ENCODE:
        return unicode(string, "cp1252")
    else:
        return string.decode("utf-8")