from __future__ import annotations

from leanbench.detect import KIND_PROBLEM, KIND_STATEMENT, detect_document
from leanbench.document import Document
from leanbench.llm import ScriptedClient

from .conftest import detection_reply


def test_single_page_detection_reports_page_and_index(two_page_book: Document) -> None:
    client = ScriptedClient(
        [
            detection_reply(
                [
                    {
                        "kind": "statement",
                        "label": "Definition 1.6.1",
                        "summary": "divisibility",
                        "start_quote": "Definition 1.6.1. Let a and b be integers.",
                        "end_quote": "b = a k.",
                        "continues_past_end": False,
                    }
                ]
            ),
            detection_reply([]),
        ]
    )
    report = detect_document(client, two_page_book, max_window_pages=3)
    assert len(report.detections) == 1
    found = report.detections[0]
    assert found.kind == KIND_STATEMENT
    assert found.start_page == 1 and found.end_page == 1
    page = two_page_book.page(1).text
    assert page[found.start_index : found.end_index].startswith("Definition 1.6.1")
    assert page[found.start_index : found.end_index].endswith("b = a k.")


def test_item_running_off_the_page_triggers_a_second_page(two_page_book: Document) -> None:
    truncated = detection_reply(
        [
            {
                "kind": "statement",
                "label": "Theorem 1.6.3",
                "summary": "gcd exists",
                "start_quote": "Theorem 1.6.3. Let a and b be nonzero integers.",
                "end_quote": "the set of common",
                "continues_past_end": True,
            }
        ]
    )
    whole = detection_reply(
        [
            {
                "kind": "statement",
                "label": "Theorem 1.6.3",
                "summary": "gcd exists",
                "start_quote": "Theorem 1.6.3. Let a and b be nonzero integers.",
                "end_quote": "the greatest common divisor.",
                "continues_past_end": False,
            },
            {
                "kind": "problem",
                "label": "Exercise 1.6.5",
                "summary": "odd + odd is even",
                "start_quote": "Exercise 1.6.5. Prove that the sum of two odd",
                "end_quote": "odd integers is even.",
                "continues_past_end": False,
            },
        ]
    )
    client = ScriptedClient([truncated, whole])
    report = detect_document(client, two_page_book, max_window_pages=3)

    assert len(client.calls) == 2, "the page should be re-read with its successor"
    theorem = report.detections[0]
    assert theorem.start_page == 1
    assert theorem.end_page == 2, "the span must cross the page boundary"
    assert theorem.spans_pages == 2
    assert not theorem.truncated
    assert two_page_book.page(2).text[: theorem.end_index].endswith("greatest common divisor.")

    exercise = report.detections[1]
    assert exercise.kind == KIND_PROBLEM
    assert exercise.start_page == 2


def test_window_stops_growing_at_the_limit_and_says_so(two_page_book: Document) -> None:
    always_truncated = detection_reply(
        [
            {
                "kind": "statement",
                "label": "",
                "summary": "",
                "start_quote": "Definition 1.6.1. Let a and b be integers.",
                "end_quote": "b = a k.",
                "continues_past_end": True,
            }
        ]
    )
    client = ScriptedClient([always_truncated] * 4)
    report = detect_document(client, two_page_book, max_window_pages=2)
    assert len(client.calls) == 2
    assert report.detections[0].truncated is True


def test_unresolvable_quotes_are_recorded_not_invented(two_page_book: Document) -> None:
    client = ScriptedClient(
        [
            detection_reply(
                [
                    {
                        "kind": "statement",
                        "label": "Hallucination 9",
                        "summary": "not in the book",
                        "start_quote": "Theorem 9.9.9 about topological quantum widgets",
                        "end_quote": "which is absurd.",
                        "continues_past_end": False,
                    }
                ]
            ),
            detection_reply([]),
        ]
    )
    report = detect_document(client, two_page_book)
    assert report.detections == []
    assert len(report.unresolved) == 1


def test_a_failing_page_does_not_kill_the_run(two_page_book: Document) -> None:
    client = ScriptedClient(["not json at all", detection_reply([])])
    report = detect_document(client, two_page_book)
    assert report.pages_scanned == 2
    assert any("detector failed" in u.get("reason", "") for u in report.unresolved)