"""Shared hashed char n-gram utilities for AdVig experiments."""
import numpy as np


def hash_grams(domain, n_range=(3, 4, 5), buckets=1 << 15, seed=2166136261):
    """FNV-1a hashed char n-grams over '.domain.' with sign trick."""
    d = "." + domain.lower().strip() + "."
    feats = {}
    for ng in n_range:
        for i in range(len(d) - ng + 1):
            g = d[i:i + ng]
            h = seed
            for ch in g.encode():
                h ^= ch
                h = (h * 16777619) & 0xFFFFFFFF
            idx = h % buckets
            val = 1.0 if (h >> 31) & 1 else -1.0
            feats[idx] = feats.get(idx, 0.0) + val
    return feats


def to_sparse(domains, buckets=1 << 16):
    from scipy.sparse import coo_matrix
    rows, cols, vals = [], [], []
    for r, dom in enumerate(domains):
        f = hash_grams(dom, buckets=buckets)
        for c, v in f.items():
            rows.append(r); cols.append(c); vals.append(np.sign(v))
    return coo_matrix((vals, (rows, cols)), shape=(len(domains), buckets)).tocsr()


def fold(X, buckets):
    """fold hashing-trick columns modulo a smaller bucket count."""
    from scipy.sparse import coo_matrix
    coo = X.tocoo()
    return coo_matrix((coo.data, (coo.row, coo.col % buckets)),
                      shape=(X.shape[0], buckets)).tocsr()


def clf_metrics(yte, pred, pte):
    from sklearn.metrics import (accuracy_score, confusion_matrix, f1_score,
                                 precision_score, recall_score, roc_auc_score)
    tn, fp, fn, tp = confusion_matrix(yte, pred).ravel()
    return {"acc": accuracy_score(yte, pred), "prec": precision_score(yte, pred),
            "rec": recall_score(yte, pred), "f1": f1_score(yte, pred),
            "auc": roc_auc_score(yte, pte), "fpr": fp / (fp + tn),
            "fn": int(fn), "fp": int(fp), "tp": int(tp), "tn": int(tn)}