# app/normalizer.py
import re
import spacy

# Load spaCy model (fast, production-grade)
nlp = spacy.load("en_core_web_sm")

def normalize_query(query: str) -> str:
    """
    Production-grade query normalization using spaCy.

    Steps:
    1. Lowercase + remove special characters
    2. spaCy POS-aware lemmatization (correct results)
    3. Light stopword removal (keeps meaning-critical words)
    """
    # Step 1: lowercase + remove special chars
    q = query.lower().strip()
    q = re.sub(r"[^a-z0-9\s]", "", q)
    q = re.sub(r"\s+", " ", q).strip()

    # Step 2: spaCy pipeline (POS tagging + lemmatization)
    doc = nlp(q)

    # Step 3: lemmatize, keep stopwords that carry meaning
    KEEP_STOPWORDS = {"not", "no", "best", "worst", "cheap", "free"}
    words = []
    for token in doc:
        # Skip pure stopwords UNLESS they carry meaning
        if token.is_stop and token.text not in KEEP_STOPWORDS:
            continue
        # Skip punctuation and spaces
        if token.is_punct or token.is_space:
            continue
        # Use POS-aware lemma
        words.append(token.lemma_)

    return " ".join(words)