30 lines
812 B
Python
30 lines
812 B
Python
import re
|
|
import argparse
|
|
|
|
def read_document(path):
|
|
'''Reads a file when provided with its path, and returns a string
|
|
containing the lines of the file.'''
|
|
file_given = open(path)
|
|
f = ""
|
|
for line in file_given:
|
|
f += line + " "
|
|
file_given.close()
|
|
return f
|
|
|
|
def apply_preprocessing(f):
|
|
'''Removes non-alphabetic characters, replaces all whitespace characters
|
|
with a single whitespace, and changes all uppercase characters to
|
|
lowercase'''
|
|
f = re.sub(r'[^a-zA-Z\s]', r'', f)
|
|
f = re.sub(r'\s+', r' ', f)
|
|
f = f.lower()
|
|
return f
|
|
|
|
# parse input arguments
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('path_to_file', help = 'path to document')
|
|
args = parser.parse_args()
|
|
|
|
f = read_document(args.path_to_file)
|
|
f = apply_preprocessing(f)
|
|
print(f)
|