PIG-Demo/envs/wordle_five/tests/test_engine.py

"""The duplicate-letter cases first, because they are the ones that get shipped wrong."""

from __future__ import annotations

import pytest

from wordle_five.engine import (
    Game,
    answer_for_seed,
    answers,
    conformance_digest,
    guesses,
    hard_mode_violation,
    is_consistent,
    score_guess,
)

# Every one of these was verified against an independent implementation and
# against TextArena's own scorer before being written down. They are the
# regression surface for the two-pass rule.
VECTORS = [
    ("alloy", "llama", "YGYXX"),   # greens claim first, yellows take the rest
    ("speed", "erase", "YXYYX"),   # both E's yellow: exactly two are available
    ("array", "radar", "YYYGX"),   # double-double with one green
    ("sassy", "basis", "YGGXX"),   # 3 S guessed, 2 in answer: one Y, one X
    ("eerie", "rebel", "YGYXX"),   # the same shape on E
    ("level", "eagle", "YYXYX"),   # two repeated letters, no greens at all
    ("geese", "these", "XXGGG"),   # greens exhaust the pool, leading E greys
    ("abbey", "abbot", "GGGXX"),
    ("crane", "plane", "XXGGG"),
    ("alloy", "balmy", "YXGXG"),
    ("tares", "tares", "GGGGG"),
]


@pytest.mark.parametrize("guess,answer,expected", VECTORS)
def test_scoring_vectors(guess: str, answer: str, expected: str) -> None:
    assert score_guess(guess, answer) == expected


def test_score_is_case_insensitive() -> None:
    assert score_guess("ALLOY", "LLAMA") == score_guess("alloy", "llama")


def test_a_letter_is_never_marked_more_often_than_it_occurs() -> None:
    """The invariant the two passes exist to preserve, checked over the list."""
    pool = answers()[:200]
    for answer in pool:
        for guess in pool[:50]:
            pattern = score_guess(guess, answer)
            for letter in set(guess):
                marked = sum(
                    1 for i, c in enumerate(guess) if c == letter and pattern[i] != "X"
                )
                assert marked <= answer.count(letter)


def test_consistency_is_symmetric_with_scoring() -> None:
    """`is_consistent` must agree with `score_guess`, since the reward uses it."""
    for answer in answers()[:100]:
        guess = "tares"
        pattern = score_guess(guess, answer)
        assert is_consistent(answer, guess, pattern)


def test_every_answer_is_guessable() -> None:
    assert set(answers()) <= guesses()


def test_seeded_answer_is_deterministic() -> None:
    assert answer_for_seed(42) == answer_for_seed(42)
    assert answer_for_seed(1) != answer_for_seed(2)


# Pinned so the browser cannot drift. `src/demos/wordle/__tests__/engine.test.ts`
# asserts the same twelve words for the same twelve seeds. If a language's
# built-in RNG were used instead of the shared hash, these two lists would
# differ and every ?seed= permalink would show a different word than the
# recorded run it claims to replay.
SEED_VECTORS = [
    "wants", "amber", "spume", "toady", "divot", "filly",
    "bobby", "clews", "hikes", "lawns", "wreak", "twist",
]


def test_seed_vectors_match_the_typescript_port() -> None:
    assert [answer_for_seed(s) for s in range(12)] == SEED_VECTORS


def test_rejections_do_not_consume_a_row() -> None:
    game = Game(seed=3, answer="tares")
    assert game.play("zzzzz")[1] is not None      # not a word
    assert game.play("four")[1] is not None       # wrong length
    assert len(game.history) == 0
    assert game.rejected == 2
    assert game.play("crane")[0] is not None
    assert len(game.history) == 1


def test_a_repeat_is_rejected() -> None:
    game = Game(seed=3, answer="tares")
    game.play("crane")
    assert "already been guessed" in (game.play("crane")[1] or "")


def test_game_never_raises_on_junk() -> None:
    game = Game(seed=3, answer="tares")
    for junk in ["", "   ", "!!!!!", "a", "abcdefghij", "12345"]:
        pattern, reason = game.play(junk)
        assert pattern is None and reason is not None


def test_solving_ends_the_game() -> None:
    game = Game(seed=3, answer="tares")
    game.play("tares")
    assert game.solved and game.over


# ------------------------------------------------------------- hard mode --


def test_hard_mode_locks_greens() -> None:
    assert hard_mode_violation("crown", "crane", "GGXXX") is None
    assert hard_mode_violation("blown", "crane", "GGXXX") is not None


def test_hard_mode_counts_yellows_rather_than_testing_membership() -> None:
    """Two revealed E's require two E's, not merely one."""
    pattern = score_guess("speed", "erase")     # YXYYX — two E's revealed
    assert hard_mode_violation("ester", "speed", pattern) is None      # two E's
    assert hard_mode_violation("crest", "speed", pattern) is not None   # only one E


def test_hard_mode_does_not_ban_grey_letters() -> None:
    """The rule most implementations add and the real game does not have."""
    pattern = score_guess("crane", "tares")     # C grey
    assert pattern[0] == "X", "C should be grey against TARES"
    # A guess reusing that grey C is legal, so long as it still satisfies every
    # green and yellow that was revealed.
    assert hard_mode_violation("stare", "crane", pattern) is None


# ------------------------------------------------------ cross-language gate --


def test_conformance_digest_matches_the_committed_value() -> None:
    """The gate that keeps the TypeScript port honest.

    This hashes every (guess, answer) pair in the answer list. If it changes,
    either the scorer changed or the word list did, and `src/demos/wordle/
    engine.ts` must be re-verified against it — `pnpm conformance` does the
    other half.
    """
    from pathlib import Path

    committed = (Path(__file__).parent.parent / "CONFORMANCE.txt").read_text().split()[0]
    assert conformance_digest() == committed