List all acronyms and/or keywords in your documents to avoid duplicate acronym definitions

checkAcronym.py

import re,sys,subprocess
from colorama import init as colorama_init, Fore, Style

colorama_init()



keywords = [
  # provide keywords
]



with open(sys.argv[1]) as f: # provide with command line
    txt = f.read()

# list all acronyms
allWords = list(dict.fromkeys(re.findall('\\b[A-Z](?:[A-Z])+s?\\b', txt)))
txt = txt.splitlines()

# specifically made for latex files

for word in allWords:
    res = []
    
    for n,line in enumerate(txt,start=1):
        if line.startswith('%'): # comment in latex
            continue
        if re.search(rf'\b{word}\b',line) and not re.search(rf'(?<={{).*({word}).*(?=}})',line):
            #^ if match but not inside a `{}`, these are usually commands
            #^ second one may not work properly sometimes
            res.append(f"{n}:  {line}")


    if res: # print if found 
        print(f"{word} {'='*50}")
        for i in res: 
            print(re.sub(word,f'{Fore.RED}{word}{Style.RESET_ALL}',i))
        print('\n\n')
    res = []




for word in keywords: # search the provided keywords
    res = []
    
    for n,line in enumerate(txt,start=1):
        if line.startswith('%'): # comment in latex
            continue
        if re.search(rf'\b{word}\b',line,re.IGNORECASE) :
            res.append(f"{n}:  {line}")


    if res:
        print(f"{word} {'='*50}")
        for i in res: 
            print(re.sub(word,f'{Fore.RED}{word}{Style.RESET_ALL}',i))
        print('\n\n')
    res = []



# a bash way
# cat file | grep -wo "[A-Z]\+\{2,10\}" | sort | uniq