product-54354138-1/tests/test_cli.py

"""Contract tests for the native-process CLI in :mod:`tools.example`."""

from __future__ import annotations

import json
import struct
import subprocess
import sys
import zlib
from pathlib import Path
from typing import Any, Sequence

import pytest

from tools import envelope, example
from tools.errors import SourceAccessError

REPO_ROOT = Path(__file__).resolve().parents[1]
EXAMPLE_REQUEST = REPO_ROOT / "examples" / "input.json"


def run_cli(*args: str) -> subprocess.CompletedProcess[str]:
    return subprocess.run(
        [sys.executable, "-m", "tools.example", *args],
        cwd=REPO_ROOT,
        capture_output=True,
        text=True,
        check=False,
    )


def single_document(result: subprocess.CompletedProcess[str]) -> dict[str, Any]:
    """Assert stdout holds exactly one machine-readable JSON document."""

    lines = [line for line in result.stdout.splitlines() if line.strip()]
    assert len(lines) == 1, result.stdout
    assert result.stderr == ""
    document = json.loads(lines[0])
    assert isinstance(document, dict)
    assert set(document) == {"status", "source", "request", "items", "error"}
    return document


def test_status_vocabulary_and_exit_codes_are_fixed() -> None:
    assert envelope.STATUS_EXIT_CODES == {
        "ok": 0,
        "dry_run": 0,
        "invalid_request": 2,
        "no_format": 3,
        "no_size": 4,
        "access_error": 5,
        "partial_download": 6,
    }
    assert envelope.STATUS_VOCABULARY == (
        "ok",
        "dry_run",
        "invalid_request",
        "no_format",
        "no_size",
        "access_error",
        "partial_download",
    )


def test_help_documents_every_parameter() -> None:
    result = run_cli("--help")

    assert result.returncode == 0
    for fragment in (
        "REQUEST.json",
        "--topic",
        "--width",
        "--height",
        "--format",
        "--source",
        "--count",
        "--download",
        "--output-dir",
        "--resize",
        "--dry-run",
        "png|ico",
        "JSON",
    ):
        assert fragment in result.stdout, fragment


def test_example_request_document_is_canonical_dry_run() -> None:
    document = json.loads(EXAMPLE_REQUEST.read_text(encoding="utf-8"))
    assert document["dry_run"] is True
    assert document["format"] in ("png", "ico")

    result = run_cli("examples/input.json")

    assert result.returncode == envelope.EXIT_OK
    payload = single_document(result)
    assert payload["status"] == envelope.STATUS_DRY_RUN
    assert payload["source"] == document["source"]
    assert payload["items"] == []
    assert payload["error"] is None
    assert payload["request"]["topic"] == document["topic"]
    assert payload["request"]["format"] == document["format"]


def test_flags_dry_run_emits_one_document() -> None:
    result = run_cli("--topic", "fox", "--format", "png", "--width", "640", "--dry-run")

    assert result.returncode == envelope.EXIT_OK
    payload = single_document(result)
    assert payload["status"] == envelope.STATUS_DRY_RUN
    assert payload["request"]["width"] == 640
    assert payload["request"]["dry_run"] is True


def test_unsupported_format_is_invalid_request() -> None:
    result = run_cli("--topic", "fox", "--format", "gif")

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    payload = single_document(result)
    assert payload["status"] == envelope.STATUS_INVALID_REQUEST
    assert payload["error"]["code"] == "request_format_unsupported"
    assert payload["error"]["details"]["accepted_formats"] == ["png", "ico"]


def test_unknown_source_lists_available_ids() -> None:
    result = run_cli("--topic", "fox", "--format", "png", "--source", "nope")

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    payload = single_document(result)
    assert payload["status"] == envelope.STATUS_INVALID_REQUEST
    assert payload["error"]["code"] == "source_unknown"
    available = payload["error"]["details"]["available_sources"]
    assert "nope" not in available
    assert "wikimedia_commons" in available
    assert len(available) >= 2


def test_no_request_is_invalid_request() -> None:
    result = run_cli()

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    payload = single_document(result)
    assert payload["status"] == envelope.STATUS_INVALID_REQUEST


def test_document_combined_with_flags_is_invalid_request() -> None:
    result = run_cli("examples/input.json", "--topic", "fox")

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    payload = single_document(result)
    assert payload["error"]["details"]["conflicting_flags"] == ["topic"]


@pytest.mark.parametrize(
    "arguments",
    [
        ("--format", "png"),
        ("--topic", "fox"),
        ("--topic", "fox", "--format", "png", "--count", "0"),
        ("--topic", "   ", "--format", "png"),
    ],
)
def test_incomplete_requests_are_invalid(arguments: Sequence[str]) -> None:
    result = run_cli(*arguments)

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    assert single_document(result)["status"] == envelope.STATUS_INVALID_REQUEST


def test_missing_document_file_is_invalid_request(tmp_path: Path) -> None:
    result = run_cli(str(tmp_path / "absent.json"))

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    assert single_document(result)["status"] == envelope.STATUS_INVALID_REQUEST


def test_malformed_document_is_invalid_request(tmp_path: Path) -> None:
    broken = tmp_path / "broken.json"
    broken.write_text("{not json", encoding="utf-8")

    result = run_cli(str(broken))

    assert result.returncode == envelope.EXIT_INVALID_REQUEST
    assert single_document(result)["status"] == envelope.STATUS_INVALID_REQUEST


class FakeCandidate:
    """Minimal stand-in for :class:`tools.sources.SourceCandidate`."""

    def __init__(
        self,
        title: str,
        file_url: str,
        mime_type: str,
        width: int | None,
        height: int | None,
        *,
        payload: bytes | None = None,
        fail: bool = False,
    ) -> None:
        self.source_id = "fake"
        self.title = title
        self.file_url = file_url
        self.page_url = file_url + ".html"
        self.mime_type = mime_type
        self.width = width
        self.height = height
        self.license = "CC0"
        self.creator = "tester"
        self._payload = payload
        self._fail = fail

    def to_dict(self) -> dict[str, Any]:
        return {
            "source_id": self.source_id,
            "title": self.title,
            "file_url": self.file_url,
            "page_url": self.page_url,
            "mime_type": self.mime_type,
            "width": self.width,
            "height": self.height,
        }

    def fetch_bytes(self) -> bytes:
        if self._fail:
            raise SourceAccessError("download refused", url=self.file_url)
        if self._payload is not None:
            return self._payload
        # Default to bytes that really are a PNG of the advertised size, because
        # the CLI filters on downloaded bytes and never on source metadata.
        return png_bytes(self.width or 1, self.height or 1)


class FakeRegistry:
    def __init__(self, candidates: Sequence[FakeCandidate] = (), error: Exception | None = None) -> None:
        self._candidates = list(candidates)
        self._error = error
        self.calls: list[tuple[str, str, int]] = []

    def available_sources(self) -> Sequence[str]:
        return ["fake"]

    def search(self, source_id: str, topic: str, limit: int = 10) -> list[FakeCandidate]:
        self.calls.append((source_id, topic, limit))
        if self._error is not None:
            raise self._error
        return self._candidates[:limit]




def run_main(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], registry: FakeRegistry, *args: str) -> tuple[int, dict[str, Any]]:
    monkeypatch.setattr(example, "default_registry", lambda: registry)
    code = example.main(list(args))
    captured = capsys.readouterr()
    assert captured.err == ""
    lines = [line for line in captured.out.splitlines() if line.strip()]
    assert len(lines) == 1, captured.out
    return code, json.loads(lines[0])


BASE_ARGS = ("--topic", "fox", "--format", "png", "--width", "100", "--height", "100", "--source", "fake")


def test_ok_lists_items_without_download(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]) -> None:
    registry = FakeRegistry([FakeCandidate("fox one", "https://example.test/a.png", "image/png", 100, 100)])

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS)

    assert code == envelope.EXIT_OK
    assert payload["status"] == envelope.STATUS_OK
    assert payload["source"] == "fake"
    item = payload["items"][0]
    assert item["url"] == "https://example.test/a.png"
    assert item["file_url"] == "https://example.test/a.png"
    assert item["source"] == "fake"
    assert item["format"] == "png"
    assert item["width"] == 100
    assert item["height"] == 100
    assert registry.calls == [("fake", "fox", example.candidate_cap(10))]


def test_no_format_when_every_payload_really_is_another_format(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
) -> None:
    registry = FakeRegistry(
        [FakeCandidate("fox", "https://example.test/a.jpg", "image/jpeg", 100, 100, payload=gif_bytes())]
    )

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS)

    assert code == envelope.EXIT_NO_FORMAT
    assert payload["status"] == envelope.STATUS_NO_FORMAT
    assert payload["error"]["details"]["unreadable_candidates"] == 0
    assert payload["error"]["details"]["requested_format"] == "png"


def test_no_size_when_only_smaller_images_exist(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]) -> None:
    registry = FakeRegistry([FakeCandidate("fox", "https://example.test/a.png", "image/png", 50, 50)])

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS)

    assert code == envelope.EXIT_NO_SIZE
    assert payload["status"] == envelope.STATUS_NO_SIZE


def test_requested_size_is_a_minimum_not_an_exact_match(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
) -> None:
    registry = FakeRegistry([FakeCandidate("fox", "https://example.test/a.png", "image/png", 400, 300)])

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS)

    assert code == envelope.EXIT_OK
    assert payload["status"] == envelope.STATUS_OK
    assert payload["request"]["resize"] is False
    assert [item["width"] for item in payload["items"]] == [400]
    assert [item["height"] for item in payload["items"]] == [300]


def test_exact_size_is_accepted(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]) -> None:
    registry = FakeRegistry([FakeCandidate("fox", "https://example.test/a.png", "image/png", 100, 100)])

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS)

    assert code == envelope.EXIT_OK
    assert len(payload["items"]) == 1


def test_resize_without_download_keeps_actual_size(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
) -> None:
    registry = FakeRegistry([FakeCandidate("fox", "https://example.test/a.png", "image/png", 400, 300)])

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS, "--resize")

    assert code == envelope.EXIT_OK
    assert payload["request"]["resize"] is True
    assert payload["items"][0]["width"] == 400
    assert "download" not in payload["items"][0]


def test_download_success_writes_files(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path) -> None:
    expected = png_bytes(100, 100)
    registry = FakeRegistry(
        [FakeCandidate("fox", "https://example.test/a.png", "image/png", 100, 100, payload=expected)]
    )

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS, "--download", "--output-dir", str(tmp_path))

    assert code == envelope.EXIT_OK
    download = payload["items"][0]["download"]
    assert download["ok"] is True
    target = Path(download["path"])
    assert target.parent == tmp_path
    # The verified bytes are stored verbatim, without a second download.
    assert target.read_bytes() == expected


def test_partial_download_reports_status(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path) -> None:
    registry = FakeRegistry(
        [
            FakeCandidate("fox", "https://example.test/a.png", "image/png", 100, 100),
            FakeCandidate("fox2", "https://example.test/b.png", "image/png", 100, 100, fail=True),
        ]
    )

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS, "--count", "2", "--download", "--output-dir", str(tmp_path))

    assert code == envelope.EXIT_PARTIAL_DOWNLOAD
    assert payload["status"] == envelope.STATUS_PARTIAL_DOWNLOAD
    # The readable candidate is still reported and downloaded.
    assert payload["items"][0]["download"]["ok"] is True
    assert payload["error"]["details"]["failed"] == 1


def test_all_downloads_failing_is_access_error(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path) -> None:
    registry = FakeRegistry([FakeCandidate("fox", "https://example.test/a.png", "image/png", 100, 100, fail=True)])

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS, "--download", "--output-dir", str(tmp_path))

    assert code == envelope.EXIT_ACCESS_ERROR
    assert payload["status"] == envelope.STATUS_ACCESS_ERROR
    assert payload["error"]["code"] == "candidate_unreadable"


def test_search_access_error_maps_to_access_error(monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]) -> None:
    registry = FakeRegistry(error=SourceAccessError("host unreachable", url="https://example.test"))

    code, payload = run_main(monkeypatch, capsys, registry, *BASE_ARGS)

    assert code == envelope.EXIT_ACCESS_ERROR
    assert payload["status"] == envelope.STATUS_ACCESS_ERROR
    assert payload["error"]["code"] == "source_access"


# ---------------------------------------------------------------------------
# Size filtering and real downscaling of downloaded images
# ---------------------------------------------------------------------------

PNG_SIGNATURE = b"\x89PNG\r\n\x1a\n"


def png_bytes(width: int, height: int, rgba: tuple[int, int, int, int] = (255, 0, 0, 255)) -> bytes:
    """Build a minimal, valid RGBA PNG without any third-party dependency."""

    raw = bytearray()
    for _ in range(height):
        raw.append(0)
        raw += bytes(rgba) * width

    def chunk(kind: bytes, data: bytes) -> bytes:
        crc = zlib.crc32(kind + data) & 0xFFFFFFFF
        return struct.pack(">I", len(data)) + kind + data + struct.pack(">I", crc)

    header = struct.pack(">IIBBBBB", width, height, 8, 6, 0, 0, 0)
    return (
        PNG_SIGNATURE
        + chunk(b"IHDR", header)
        + chunk(b"IDAT", zlib.compress(bytes(raw)))
        + chunk(b"IEND", b"")
    )


def gif_bytes(width: int = 100, height: int = 100) -> bytes:
    """Build a payload that really is a GIF, i.e. a format we must never accept."""

    return b"GIF89a" + struct.pack("<HH", width, height) + b"\x00" * 8


def png_size(payload: bytes) -> tuple[int, int]:
    assert payload.startswith(PNG_SIGNATURE)
    return struct.unpack(">II", payload[16:24])


def ico_bytes(inner_png: bytes, width: int, height: int) -> bytes:
    header = struct.pack("<HHH", 0, 1, 1)
    entry = struct.pack(
        "<BBBBHHII",
        width % 256,
        height % 256,
        0,
        0,
        1,
        32,
        len(inner_png),
        6 + 16,
    )
    return header + entry + inner_png


def ico_payload(payload: bytes) -> tuple[int, int, bytes]:
    reserved, kind, count = struct.unpack("<HHH", payload[:6])
    assert (reserved, kind, count) == (0, 1, 1)
    width, height, _colours, _reserved, _planes, _bits, size, offset = struct.unpack(
        "<BBBBHHII", payload[6:22]
    )
    return width or 256, height or 256, payload[offset : offset + size]


DOWNLOAD_ARGS = ("--topic", "fox", "--format", "png", "--source", "fake")


def test_download_resize_downscales_stored_image(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path
) -> None:
    payload = png_bytes(200, 100)
    registry = FakeRegistry(
        [FakeCandidate("fox", "https://example.test/a.png", "image/png", 200, 100, payload=payload)]
    )

    code, document = run_main(
        monkeypatch, capsys, registry, *BASE_ARGS, "--resize", "--download", "--output-dir", str(tmp_path)
    )

    assert code == envelope.EXIT_OK
    download = document["items"][0]["download"]
    assert download["ok"] is True
    assert download["resize"]["applied"] is True
    assert download["resize"]["from"] == {"width": 200, "height": 100}
    # --resize stores exactly the requested width and height, whatever the
    # source aspect ratio was.
    assert download["resize"]["to"] == {"width": 100, "height": 100}
    stored = Path(download["path"]).read_bytes()
    assert png_size(stored) == (100, 100)
    assert download["width"] == 100
    assert download["height"] == 100


def test_download_without_resize_keeps_original_payload(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path
) -> None:
    payload = png_bytes(200, 100)
    registry = FakeRegistry(
        [FakeCandidate("fox", "https://example.test/a.png", "image/png", 200, 100, payload=payload)]
    )

    code, document = run_main(
        monkeypatch, capsys, registry, *BASE_ARGS, "--download", "--output-dir", str(tmp_path)
    )

    assert code == envelope.EXIT_OK
    download = document["items"][0]["download"]
    assert "resize" not in download
    assert Path(download["path"]).read_bytes() == payload


def test_resize_never_scales_up(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path
) -> None:
    payload = png_bytes(50, 50)
    registry = FakeRegistry(
        [FakeCandidate("fox", "https://example.test/a.png", "image/png", 50, 50, payload=payload)]
    )

    code, document = run_main(
        monkeypatch, capsys, registry, *DOWNLOAD_ARGS, "--resize", "--download", "--output-dir", str(tmp_path)
    )

    assert code == envelope.EXIT_OK
    download = document["items"][0]["download"]
    assert download["resize"]["applied"] is False
    assert download["resize"]["reason"] == "already_fits"
    assert Path(download["path"]).read_bytes() == payload


def test_resize_downscales_png_stored_inside_ico(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path
) -> None:
    payload = ico_bytes(png_bytes(100, 100), 100, 100)
    registry = FakeRegistry(
        [FakeCandidate("fox", "https://example.test/a.ico", "image/x-icon", 100, 100, payload=payload)]
    )

    code, document = run_main(
        monkeypatch,
        capsys,
        registry,
        "--topic",
        "fox",
        "--format",
        "ico",
        "--source",
        "fake",
        "--width",
        "50",
        "--height",
        "50",
        "--resize",
        "--download",
        "--output-dir",
        str(tmp_path),
    )

    assert code == envelope.EXIT_OK
    download = document["items"][0]["download"]
    assert download["resize"]["to"] == {"width": 50, "height": 50}
    width, height, inner = ico_payload(Path(download["path"]).read_bytes())
    assert (width, height) == (50, 50)
    assert png_size(inner) == (50, 50)


def test_non_image_payload_is_no_format_not_access_error(
    monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], tmp_path: Path
) -> None:
    """A body that is not a png really is "not the requested format".

    Live sources answer with HTML error pages, licence documents and vector
    files; those must produce the topic verdict ``no_format`` (exit 3) instead
    of an access error or a partial download.
    """

    registry = FakeRegistry(
        [
            FakeCandidate(
                "fox", "https://example.test/a.png", "image/png", 100, 100, payload=b"not-an-image"
            )
        ]
    )

    code, document = run_main(
        monkeypatch, capsys, registry, *BASE_ARGS, "--resize", "--download", "--output-dir", str(tmp_path)
    )

    assert code == envelope.EXIT_NO_FORMAT
    assert document["status"] == envelope.STATUS_NO_FORMAT
    assert document["error"]["code"] == "no_format_match"
    assert document["error"]["details"]["other_format_candidates"] == 1
    assert document["items"] == []
    assert list(tmp_path.iterdir()) == []