import torch

from src.config import Config
from src.data import (build_examples, decode_tokens, encode_int, get_splits,
                      make_batch, next_prime, sieve_primes)


def test_sieve_primes_known():
    assert sieve_primes(30) == [2, 3, 5, 7, 11, 13, 17, 19, 23, 29]
    assert sieve_primes(1) == []
    assert sieve_primes(2) == [2]


def test_next_prime():
    p = sieve_primes(200)
    assert next_prime(42, p) == 43
    assert next_prime(100, p) == 101
    assert next_prime(2, p) == 3
    assert next_prime(97, p) == 101


def test_encode_decode_roundtrip_digits():
    cfg = Config(vocab_mode="digits")
    for n in [2, 7, 10, 42, 99, 100]:
        assert decode_tokens(encode_int(n, cfg) + [cfg.eos_id], cfg) == n
    assert encode_int(42, cfg) == [4, 2]


def test_encode_decode_roundtrip_integers():
    cfg = Config(vocab_mode="integers", range_end=100)
    for n in [2, 42, 100]:
        assert decode_tokens(encode_int(n, cfg) + [cfg.eos_id], cfg) == n
    assert cfg.vocab == 103  # values 0..101, EOS=102, pad=103 (no alias with target 101)


def test_splits_sizes_and_no_overlap():
    cfg = Config()
    tr, va = get_splits(cfg)
    assert len(tr) == 69 and len(va) == 30
    assert not set(tr) & set(va)
    assert set(tr) | set(va) == set(range(2, 101))


def test_splits_seed_stable():
    a1, b1 = get_splits(Config(seed=3))
    a2, b2 = get_splits(Config(seed=3))
    assert a1 == a2 and b1 == b2
    a3, _ = get_splits(Config(seed=4))
    assert a1 != a3


def test_build_examples_targets():
    cfg = Config()
    ex = build_examples([2, 42, 99, 100], cfg)
    assert [decode_tokens(y, cfg) for _, y in ex] == [3, 43, 101, 101]
    assert ex[0][1][-1] == cfg.eos_id  # EOS-terminated


def test_make_batch_shapes_and_padding():
    cfg = Config()
    ex = build_examples([2, 7, 42, 99], cfg)
    b = make_batch(ex, cfg)
    assert b["x"].shape == (4, 3)          # GLOBAL layout: left-padded to 3 digits (max of [2,100])
    assert b["y"].shape == (4, 4)          # GLOBAL layout: right-padded to 4 ("101"+EOS)
    assert b["y_in"].shape == (4, 4)
    assert b["y_mask"].shape == (4, 4)
    # pad positions masked out
    assert not b["y_mask"][0, 3]           # "3"+EOS row has pad at index 3
    assert b["y_mask"][0, 1]
    # BOS position of y_in is eos_id
    assert (b["y_in"][:, 0] == cfg.eos_id).all()
    # LEFT-padding: input 2 sits at the last column, pads at the front
    assert b["x"][0, 2] == 2 and b["x"][0, 0] == cfg.pad_id
    assert b["x"][2, 1] == 4 and b["x"][2, 2] == 2


def test_flagged_composites_are_composite():
    # sanity: the diagnostic set in eval.py really is composite and needs divisors > 7
    for n in (121, 143, 169, 187):
        assert any(n % d == 0 for d in range(2, int(n ** 0.5) + 1))
        assert all(n % d != 0 for d in (2, 3, 5, 7))