app/analytics.py

import re
from collections import defaultdict

TOPICS: dict[str, list[str]] = {
    "Mathematics": [
        "equation", "solve", "integral", "derivative", "matrix",
        "polynomial", "algebra", "geometry", "theorem", "proof",
        "calculate", "function", "variable", "coefficient", "logarithm",
        "trigonometry", "sine", "cosine", "tangent", "factorial",
        "prime", "fraction", "ratio", "percentage", "probability",
    ],
    "Physics": [
        "force", "energy", "mass", "velocity", "acceleration",
        "momentum", "gravity", "electric", "magnetic", "wave",
        "thermodynamics", "entropy", "quantum", "relativity", "circuit",
        "friction", "tension", "pressure", "temperature", "current",
        "voltage", "resistance", "frequency", "amplitude", "optics",
    ],
    "Chemistry": [
        "atom", "molecule", "reaction", "element", "compound",
        "bond", "acid", "base", "electron", "proton", "ion",
        "periodic", "oxidation", "catalyst", "solution", "mole",
        "valence", "isotope", "equilibrium", "titration", "polymer",
        "organic", "inorganic", "covalent", "ionic", "redox",
    ],
    "Biology": [
        "cell", "dna", "rna", "protein", "evolution", "organism",
        "photosynthesis", "gene", "mutation", "enzyme", "tissue",
        "nervous", "metabolism", "ecosystem", "species", "mitosis",
        "meiosis", "chromosome", "ribosome", "membrane", "bacteria",
        "virus", "antibody", "hormone", "respiration",
    ],
    "Computer Science": [
        "algorithm", "array", "loop", "recursion", "complexity",
        "binary", "sorting", "compiler", "runtime", "memory",
        "stack", "queue", "pointer", "variable", "function",
        "class", "object", "inheritance", "database", "network",
        "protocol", "encryption", "cache", "thread", "process",
    ],
}


def detect_topic(text: str) -> str:
    text_lower = text.lower()
    scores: dict[str, int] = defaultdict(int)

    for topic, keywords in TOPICS.items():
        for kw in keywords:
            if re.search(rf"\b{re.escape(kw)}\b", text_lower):
                scores[topic] += 1

    if not scores:
        return "General STEM"

    return max(scores, key=scores.get)