Second approach a non-frequent approach to build up a regex

check_numbers2a.py

regex = r"\b("

remaining_numbers = []
remaining_numbers2 = []
for i in range(10000, 1000, -1):
    if i%10==0:
        # these are numbers that could cause false matching 
        # these numbers ends with zero but we may have something more in the text 
        # three thousand forty (3040) vs three thousand forty one
        remaining_numbers.append(i)
    elif (i%100 > 1) and (i%100<10):
        # these are numbers that could cause false matching
        # e.g. three thousand four (3004) vs three thousand four hundred
        remaining_numbers2.append(i)
    else:
        current_number = num2words(i)
        current_number = re.sub(" and ", " ", current_number)
        splitter = current_number.split(",")
        numb = ""
        for splitt in splitter: 
            dash_split = splitt.split("-")
            for elem in dash_split:
                for subelem in elem.split():
                    if subelem==" ":
                        continue 
                    else:
                        numb+= rf"\s{subelem.strip()}"
        
        regex+=f"{numb}"
        regex+=r"|"

# sort the number in ascending order, from Rare to Frequent
remaining_numbers.sort(reverse=True)
for val in remaining_numbers:
    current_number = num2words(val)
    current_number = re.sub(" and ", " ", current_number)
    splitter = current_number.split(",")
    numb = ""
    for splitt in splitter: 
        dash_split = splitt.split("-")
        for elem in dash_split:
            for subelem in elem.split():
                if subelem==" ":
                    continue 
                else:
                    numb+= rf"\s{subelem.strip()}"

    regex+=f"{numb}"
    regex+=r"|"

# add the remaining nubmers which ends in 1-9
remaining_numbers2.sort(reverse=True)
for val in remaining_numbers2:
    current_number = num2words(val)
    current_number = re.sub(" and ", " ", current_number)
    splitter = current_number.split(",")
    numb = ""
    for splitt in splitter: 
        dash_split = splitt.split("-")
        for elem in dash_split:
            for subelem in elem.split():
                if subelem==" ":
                    continue 
                else:
                    numb+= rf"\s{subelem.strip()}"

    regex+=f"{numb}"
    regex+=r"|"

    
# add the final numbers 
for i in range(1000, -1, -1):
    current_number = num2words(i)
    current_number = re.sub(" and ", " ", current_number)
    splitter = current_number.split(",")
    numb = ""
    for splitt in splitter: 
        dash_split = splitt.split("-")
        for elem in dash_split:
            for subelem in elem.split():
                numb+= rf"\s{subelem.strip()}"
    
    regex+=f"{numb}"

    if i==0:
        regex+=r")\b"
    else:
        regex+=r"|"

# run the query - pick the book name from the books
match_dict = {}
for i, val in enumerate(glob.glob("books/*.txt"),0):
    book_name = val.split("/")[-1].split(".")[0]
    match_dict[book_name] = {}
    matches = re.findall(regex, data[i])
    for numb in matches:
        if numb.strip() in match_dict[book_name]:
            match_dict[book_name][numb.strip()]+=1 
        else:
            match_dict[book_name][numb.strip()] = 1