import re
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer


def _ensure_nltk_data():
    try:
        stopwords.words("english")
    except LookupError:
        nltk.download("stopwords", quiet=True)

    try:
        nltk.data.find("corpora/wordnet")
    except LookupError:
        nltk.download("wordnet", quiet=True)


_ensure_nltk_data()

stop_words = set(stopwords.words("english"))
lemmatizer = WordNetLemmatizer()


def preprocess_text(text):
    text = text.lower()
    text = re.sub(r"[^a-z\s]", " ", text)

    tokens = text.split()

    cleaned_tokens = [
        lemmatizer.lemmatize(token)
        for token in tokens
        if token not in stop_words and len(token) > 2
    ]

    return " ".join(cleaned_tokens)