How can I replace matches in a Python regex with a modified version of the match?

I wrote this code to search a specific folder's text files for word matches and to specify them:

import re, os, sys
from pathlib import Path
#Usage: regs directory
try:
if len(sys.argv) == 2:
folder = sys.argv[1]
fList = os.listdir(folder)
uInput = input('input a regex: ')
regObj = re.compile(f'''{uInput}''')
wordReg = re.compile(r'''([A-Za-z0-9]+|\s+|[^\w\s]+)''')
matches = []
print(fList)
for file in fList:
if not os.path.isdir(Path(folder)/Path(file)):
currentFileObj = open(f'{folder}/{file}')
content = currentFileObj.readlines()
currentFileObj.seek(0)
text = currentFileObj.read()
words = wordReg.findall(text)
matches = list(filter(regObj.match, words))
instances = 0
print(f"matches in ({file}):\n'", end='')
for word in words:
if word in matches:
print("\u0333".join(f"{word} "), end='')
else:
print(word, end='')
print("'")
for line in content:
matches = regObj.findall(line)
for match in matches:
print("\u0333".join(f"{match} "), end=' ')
print(f"in line number {content.index(line)+1}")
if match != '':
instances = instances + 1
print(f'number of instances found: {instances}\n')
else:
continue
else:
print('Usage: regs directory')
except FileNotFoundError:
print("that file doesn't exist.")
except PermissionError:
print("you don't have permission to search that folder.")

it works for the most part except for a few regular expressions, if the regular expression has punctuation or a white space character next to other characters it wouldn't underline it, it may work if i find out a way to substitute matches with a modified version of the match (replacing the match with an underlined version)
Anyone knows a fix ?

here's what it looks like for any other regex.

you can see in the first text file it doesn't underline the match (out.)

i tried looking for functions that would substitute matches with a modification of said match, doesn't appear like there's any ?

also there's the minor problems of it not being able to underline whitespaces and punctuation properly, and the underline character doesn't appear in the windows7 command prompt, maybe a different character other than the underline can work ?

If your goal is to underline the matches in your code, you can modify the printing logic to replace the matches with an underlined version by using \u0332 so

underlined_match = "\u0332".join(f"{match}\u0332")
print(underlined_match, end=' ')

Else if your goal is to change the regex so that it captures punctuation marks and blanks between normal characters (a-z0-9) then this regex might help you

(?:[A-Za-z0-9]+(?:[^\w\s]*[A-Za-z0-9]+[^\w\s]*)*)|(?:[^\w\s]+)

I've figured out the answer:
using a lambda function as a repl= variable with re.sub i was capable of modifying the matches and then using them to substitute.

    import re, os, sys
from pathlib import Path
#Usage:regs directory
try:
if len(sys.argv) == 2:
folder = sys.argv[1]
fList = os.listdir(folder)
print("folder contents: ", end=' ')
for f in fList:
if not f == fList[-1]:
print(f, end=', ')
else:
print(f, end='.\n\n')
uInput = input('input a regex: ')
print()
regObj = re.compile(f'''{uInput}''')
wordReg = re.compile(r'''([A-Za-z0-9]+|\s+|[^\w\s]+)''')
matches = []
for file in fList:
if os.path.isfile(Path(folder)/Path(file)):
currentFileObj = open(f'{folder}/{file}')
lines = currentFileObj.readlines()
currentFileObj.seek(0)
text = currentFileObj.read()
words = wordReg.findall(text)
matches = list(filter(regObj.match, words))
instances = 0
print(f"matches in ({file}):\n'", end='')
print(regObj.sub(lambda match: "(" + match.group() + ")", text)+"'")
for line in lines:
matches = regObj.findall(line)
for match in matches:
print((f"({match})"), end=' ')
print(f"in line number {lines.index(line)+1}")
if match != '':
instances = instances + 1
print(f'number of instances found: {instances}\n')
else:
continue
else:
print('Usage:regs directory')
except FileNotFoundError:
print("that file doesn't exist.")
except PermissionError:
print("you don't have permission to search that folder.")

instead of having a loop that goes over the list of the string's words, it just prints the match group between parenthesis like so:

            print(regObj.sub(lambda match: "(" + match.group() + ")", text)+"'")

The output now looks like this.

it also prints the folder contents now.