from __future__ import annotations

import copy
import hashlib
import json
import sys
from pathlib import Path

import pytest

REPO_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(REPO_ROOT / "scripts"))

import compile_kb_source_packet as compiler  # noqa: E402, I001


ARTIFACT_BYTES = b"%PDF-1.7\nsource compiler fixture\x00\xff\n%%EOF\n"
EXTRACTED_TEXT = (
    "Source packet compiler note.\n\n"
    "A staged proposal remains non-canonical until a human review and guarded apply both succeed.\n\n"
    "Every proposed claim must retain an exact quote from the extracted source text."
)
CLAIM_QUOTE = "A staged proposal remains non-canonical until a human review and guarded apply both succeed."
EVIDENCE_QUOTE = "Every proposed claim must retain an exact quote from the extracted source text."


def _sha256(value: bytes) -> str:
    return hashlib.sha256(value).hexdigest()


def _manifest() -> dict:
    artifact_sha256 = _sha256(ARTIFACT_BYTES)
    text_bytes = EXTRACTED_TEXT.encode("utf-8")
    return {
        "schema": compiler.MANIFEST_SCHEMA,
        "artifact_sha256": artifact_sha256,
        "extracted_text_sha256": _sha256(text_bytes),
        "extractor": {"name": "fixture-text-extractor", "version": "1"},
        "source": {
            "identity": f"document:sha256:{artifact_sha256}",
            "source_key": "source_compiler_note",
            "source_type": "article",
            "title": "Source packet compiler note",
            "locator": f"artifact://sha256/{artifact_sha256}",
        },
        "claims": [
            {
                "claim_key": "review_gate_precedes_canonical_apply",
                "type": "structural",
                "text": "A staged proposal is not canonical knowledge until review and guarded apply succeed.",
                "quote": CLAIM_QUOTE,
                "confidence": 0.99,
                "tags": ["review", "provenance"],
                "evidence": [{"quote": EVIDENCE_QUOTE, "role": "grounds"}],
            }
        ],
    }


def _write_inputs(tmp_path: Path, manifest: dict | None = None, prefix: str = "input") -> tuple[Path, Path, Path]:
    tmp_path.mkdir(parents=True, exist_ok=True)
    artifact = tmp_path / f"{prefix}.bin"
    text = tmp_path / f"{prefix}.txt"
    manifest_path = tmp_path / f"{prefix}.json"
    artifact.write_bytes(ARTIFACT_BYTES)
    text.write_text(EXTRACTED_TEXT, encoding="utf-8")
    manifest_path.write_text(json.dumps(manifest or _manifest(), indent=2), encoding="utf-8")
    return artifact, text, manifest_path


def _compile(tmp_path: Path, manifest: dict | None = None) -> dict:
    paths = _write_inputs(tmp_path, manifest)
    return compiler.compile_source_packet(*paths)


def test_compiles_deterministic_hash_bound_pending_review_bundle_without_db_write(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    artifact, text, manifest_path = _write_inputs(tmp_path, prefix="first")

    def unexpected_db_call(*_args, **_kwargs):
        raise AssertionError("compiler attempted a database write")

    monkeypatch.setattr(compiler.stage, "stage_normalized_child", unexpected_db_call)
    monkeypatch.setattr(compiler.stage.bound, "_psql_json", unexpected_db_call)
    first = compiler.compile_source_packet(artifact, text, manifest_path)

    copied = tmp_path / "copied"
    copied.mkdir()
    copied_paths = _write_inputs(copied, prefix="different-path")
    second = compiler.compile_source_packet(*copied_paths)

    assert first == second
    assert first["status"] == "pending_review"
    assert first["build_only"] is True
    assert first["database_write_performed"] is False
    assert first["canonical_apply_performed"] is False
    assert first["stage_preview"]["executed"] is False
    assert len(first["stage_preview"]["stage_sql_sha256"]) == 64

    parent = first["parent_proposal"]
    child = first["strict_child_proposal"]
    apply_payload = child["payload"]["apply_payload"]
    assert parent["status"] == child["status"] == "pending_review"
    assert len(parent["payload"]["source_candidates"]) == 1
    assert parent["payload"]["source_candidates"][0]["source_key"] == "source_compiler_note"
    assert child["proposal_type"] == "approve_claim"
    assert apply_payload["contract_version"] == 2
    assert apply_payload["source_proposal_id"] == parent["id"]
    assert len(apply_payload["claims"]) == 1
    assert apply_payload["claims"][0]["text"] == _manifest()["claims"][0]["text"]
    assert apply_payload["claims"][0]["text"] != CLAIM_QUOTE
    assert len(apply_payload["sources"]) == 2
    assert len(apply_payload["evidence"]) == 2
    assert first["hashes"]["artifact_sha256"] in {row["hash"] for row in apply_payload["sources"]}
    assert first["compiler_contract"]["source_from_chat_labels"] is False
    assert parent["payload"]["claim_candidates"][0]["headline"] == _manifest()["claims"][0]["text"]
    assert parent["payload"]["claim_candidates"][0]["body"] == CLAIM_QUOTE

    without_bundle_hash = copy.deepcopy(first)
    bundle_hash = without_bundle_hash["hashes"].pop("bundle_content_sha256")
    assert bundle_hash == compiler.canonical_sha256(without_bundle_hash)


def test_v2_manifest_carries_canonical_dedupe_candidates_into_review_packet(tmp_path: Path) -> None:
    manifest = _manifest()
    manifest["schema"] = compiler.MANIFEST_SCHEMA_V2
    candidate_id = "11111111-1111-4111-8111-111111111111"
    manifest["dedupe"] = {
        "database_search_query": "review guarded canonical apply",
        "candidate_claims": [
            {
                "id": candidate_id,
                "text": "Canonical writes require a guarded apply step.",
                "score": 3,
                "evidence_count": 2,
                "edge_count": 1,
            }
        ],
        "duplicates": [
            {
                "claim_id": candidate_id,
                "source_quote": CLAIM_QUOTE,
                "reason": "The retrieved row already captures the review-before-apply argument.",
            }
        ],
    }

    bundle = _compile(tmp_path, manifest)
    assessment = bundle["parent_proposal"]["payload"]["dedupe_conflict_assessment"]

    assert bundle["validated_manifest"]["schema"] == compiler.MANIFEST_SCHEMA_V2
    assert assessment["database_search_query"] == "review guarded canonical apply"
    assert assessment["canonical_candidates"][0]["id"] == candidate_id
    assert assessment["potential_existing_claim_ids"] == [candidate_id]
    assert assessment["conflicts"][0]["source_quote"] == CLAIM_QUOTE
    staged_assessment = bundle["strict_child_proposal"]["payload"]["apply_payload"]["normalization_manifest"][
        "dedupe_conflict_assessment"
    ]
    assert staged_assessment == assessment


def test_rejects_normalized_child_that_replaces_atomic_claim_text_with_quote(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    original = compiler.stage.prepare_normalized_child

    def replace_claim_text(parent: dict) -> dict:
        child = original(parent)
        child["payload"]["apply_payload"]["claims"][0]["text"] = CLAIM_QUOTE
        return child

    monkeypatch.setattr(compiler.stage, "prepare_normalized_child", replace_claim_text)

    with pytest.raises(compiler.CompilerError, match="claim text differs from the extracted atomic propositions"):
        _compile(tmp_path)


def test_v2_manifest_rejects_unretrieved_or_unbound_duplicate_judgments(tmp_path: Path) -> None:
    manifest = _manifest()
    manifest["schema"] = compiler.MANIFEST_SCHEMA_V2
    manifest["dedupe"] = {
        "database_search_query": "review guarded canonical apply",
        "candidate_claims": [
            {
                "id": "11111111-1111-4111-8111-111111111111",
                "text": "Canonical writes require a guarded apply step.",
                "score": 3,
                "evidence_count": 2,
                "edge_count": 1,
            }
        ],
        "duplicates": [
            {
                "claim_id": "22222222-2222-4222-8222-222222222222",
                "source_quote": CLAIM_QUOTE,
                "reason": "Not retrieved.",
            }
        ],
    }
    with pytest.raises(compiler.CompilerError, match="was not present in the canonical retrieval candidates"):
        _compile(tmp_path / "unretrieved", manifest)

    manifest["dedupe"]["duplicates"][0]["claim_id"] = "11111111-1111-4111-8111-111111111111"
    manifest["dedupe"]["duplicates"][0]["source_quote"] = "Invented duplicate quote."
    with pytest.raises(compiler.CompilerError, match="source_quote is not an exact substring"):
        _compile(tmp_path / "unbound", manifest)


def test_cli_emits_structured_json_to_stdout_and_optional_output(tmp_path: Path, capsys: pytest.CaptureFixture) -> None:
    artifact, text, manifest_path = _write_inputs(tmp_path)
    output = tmp_path / "compiled" / "packet.json"

    status = compiler.main(
        [
            "--artifact",
            str(artifact),
            "--text",
            str(text),
            "--manifest",
            str(manifest_path),
            "--output",
            str(output),
        ]
    )

    stdout = capsys.readouterr().out
    assert status == 0
    assert output.read_text(encoding="utf-8") == stdout
    assert json.loads(stdout)["status"] == "pending_review"


@pytest.mark.parametrize(
    ("field", "expected"),
    [
        ("artifact_sha256", "artifact SHA-256 does not match"),
        ("extracted_text_sha256", "extracted text SHA-256 does not match"),
    ],
)
def test_rejects_hash_mismatches(tmp_path: Path, field: str, expected: str) -> None:
    manifest = _manifest()
    manifest[field] = "0" * 64

    with pytest.raises(compiler.CompilerError, match=expected):
        _compile(tmp_path, manifest)


@pytest.mark.parametrize(
    ("target", "expected"),
    [
        ("claim", "claims\\[0\\]\\.quote is not an exact substring"),
        ("evidence", "evidence\\[0\\]\\.quote is not an exact substring"),
    ],
)
def test_rejects_hallucinated_claim_or_evidence_quote(tmp_path: Path, target: str, expected: str) -> None:
    manifest = _manifest()
    if target == "claim":
        manifest["claims"][0]["quote"] = "This quote was invented by the extractor."
    else:
        manifest["claims"][0]["evidence"][0]["quote"] = "This evidence was invented by the extractor."

    with pytest.raises(compiler.CompilerError, match=expected):
        _compile(tmp_path, manifest)


def test_rejects_duplicate_claim_and_derived_source_keys(tmp_path: Path) -> None:
    duplicate_claim = _manifest()
    duplicate_claim["claims"].append(copy.deepcopy(duplicate_claim["claims"][0]))
    with pytest.raises(compiler.CompilerError, match="duplicate claim_key"):
        _compile(tmp_path / "claim", duplicate_claim)

    duplicate_source = _manifest()
    duplicate_source["source"]["source_key"] = "review_gate_precedes_canonical_apply__proposal_body"
    with pytest.raises(compiler.CompilerError, match="duplicate source_key after normalization"):
        _compile(tmp_path / "source", duplicate_source)


@pytest.mark.parametrize(
    ("target", "expected"),
    [
        ("claim", "claims\\[0\\]\\.type must be one of"),
        ("source", "source\\.source_type must be one of"),
        ("evidence", "evidence\\[0\\]\\.role must be one of"),
    ],
)
def test_rejects_types_outside_current_taxonomies(tmp_path: Path, target: str, expected: str) -> None:
    manifest = _manifest()
    if target == "claim":
        manifest["claims"][0]["type"] = "fact"
    elif target == "source":
        manifest["source"]["source_type"] = "document"
    else:
        manifest["claims"][0]["evidence"][0]["role"] = "proves"

    with pytest.raises(compiler.CompilerError, match=expected):
        _compile(tmp_path, manifest)


@pytest.mark.parametrize("field", ["identity", "locator"])
def test_rejects_missing_or_unstable_source_provenance(tmp_path: Path, field: str) -> None:
    manifest = _manifest()
    manifest["source"][field] = "message from Alice"

    with pytest.raises(compiler.CompilerError, match="stable URI-like reference"):
        _compile(tmp_path, manifest)


@pytest.mark.parametrize(
    ("reference", "expected"),
    [
        ("javascript:alert(1)", "unsafe URI scheme"),
        ("https:/missing-host", "must include a host"),
        ("https://user:password@example.com/source", "must not embed credentials"),
        ("telegram:Alice", "stable chat or message identifier"),
    ],
)
def test_rejects_unsafe_or_non_specific_source_references(tmp_path: Path, reference: str, expected: str) -> None:
    manifest = _manifest()
    manifest["source"]["locator"] = reference

    with pytest.raises(compiler.CompilerError, match=expected):
        _compile(tmp_path, manifest)


def test_rejects_tags_with_ambiguous_whitespace(tmp_path: Path) -> None:
    manifest = _manifest()
    manifest["claims"][0]["tags"] = [" review"]

    with pytest.raises(compiler.CompilerError, match="tags must be a list of non-empty strings"):
        _compile(tmp_path, manifest)


def test_rejects_path_gaps_invalid_utf8_and_output_overwrite(tmp_path: Path, capsys: pytest.CaptureFixture) -> None:
    artifact, text, manifest_path = _write_inputs(tmp_path)
    with pytest.raises(compiler.CompilerError, match="artifact path is not a regular file"):
        compiler.compile_source_packet(tmp_path / "missing.bin", text, manifest_path)

    text.write_bytes(b"\xff\xfe")
    with pytest.raises(compiler.CompilerError, match="valid UTF-8"):
        compiler.compile_source_packet(artifact, text, manifest_path)

    status = compiler.main(
        [
            "--artifact",
            str(artifact),
            "--text",
            str(text),
            "--manifest",
            str(manifest_path),
            "--output",
            str(artifact),
        ]
    )
    rejection = json.loads(capsys.readouterr().out)
    assert status == 2
    assert rejection["status"] == "rejected"
    assert rejection["database_write_performed"] is False
    assert "must not overwrite" in rejection["error"]


def test_cli_reports_output_write_failure_as_structured_rejection(
    tmp_path: Path, capsys: pytest.CaptureFixture, monkeypatch: pytest.MonkeyPatch
) -> None:
    artifact, text, manifest_path = _write_inputs(tmp_path)
    output = tmp_path / "packet.json"
    original_write_text = Path.write_text

    def guarded_write_text(path: Path, data: str, *args, **kwargs):
        if path == output:
            raise PermissionError("fixture output denied")
        return original_write_text(path, data, *args, **kwargs)

    monkeypatch.setattr(Path, "write_text", guarded_write_text)
    status = compiler.main(
        [
            "--artifact",
            str(artifact),
            "--text",
            str(text),
            "--manifest",
            str(manifest_path),
            "--output",
            str(output),
        ]
    )

    rejection = json.loads(capsys.readouterr().out)
    assert status == 2
    assert rejection["status"] == "rejected"
    assert rejection["database_write_performed"] is False
    assert "could not write output" in rejection["error"]


def test_rejects_attempt_to_invent_source_from_chat_label(tmp_path: Path) -> None:
    manifest = _manifest()
    manifest["claims"][0]["evidence"][0]["source_label"] = "Alice in Telegram"

    with pytest.raises(compiler.CompilerError, match="unsupported keys: source_label"):
        _compile(tmp_path, manifest)


def test_compiles_stable_telegram_message_as_review_candidate_without_learning_from_chat(tmp_path: Path) -> None:
    manifest = _manifest()
    locator = "telegram://chat/-5146042086/message/12345"
    manifest["source"].update(
        {
            "identity": locator,
            "source_key": "telegram_message_12345",
            "source_type": "transcript",
            "title": "Telegram discussion message 12345",
            "locator": locator,
        }
    )

    bundle = _compile(tmp_path, manifest)
    source = bundle["parent_proposal"]["payload"]["source_candidates"][0]

    assert bundle["status"] == "pending_review"
    assert bundle["database_write_performed"] is False
    assert bundle["canonical_apply_performed"] is False
    assert bundle["compiler_contract"]["source_from_chat_labels"] is False
    assert source["source_type"] == "transcript"
    assert source["storage_path"] == locator
    assert source["content_sha256"] == manifest["artifact_sha256"]


def test_rejects_quotes_that_cannot_fit_the_reviewable_canonical_excerpt(tmp_path: Path) -> None:
    long_quote = "x" * 8100
    text = f"prefix {long_quote} suffix"
    artifact = tmp_path / "long.bin"
    text_path = tmp_path / "long.txt"
    manifest_path = tmp_path / "long.json"
    artifact.write_bytes(ARTIFACT_BYTES)
    text_path.write_text(text, encoding="utf-8")
    manifest = _manifest()
    manifest["extracted_text_sha256"] = _sha256(text.encode("utf-8"))
    manifest["claims"][0]["quote"] = long_quote
    manifest["claims"][0]["evidence"] = [{"quote": long_quote, "role": "grounds"}]
    manifest_path.write_text(json.dumps(manifest), encoding="utf-8")

    with pytest.raises(compiler.CompilerError, match=r"truncated|excerpt capacity"):
        compiler.compile_source_packet(artifact, text_path, manifest_path)