"""Local-filesystem blob storage."""

from __future__ import annotations

from pathlib import Path

import pytest

from ocr_sprint.storage.blob import LocalFsBlobStorage


@pytest.fixture
def storage(tmp_path: Path) -> LocalFsBlobStorage:
    return LocalFsBlobStorage(tmp_path / "blobs")


def test_put_returns_dated_key(storage: LocalFsBlobStorage) -> None:
    key = storage.put(b"hello", original_filename="surat.pdf")
    # Layout is YYYY/MM/DD/<uuid>.pdf
    parts = key.split("/")
    assert len(parts) == 4
    assert parts[3].endswith(".pdf")
    assert storage.exists(key)
    assert storage.get(key) == b"hello"


def test_put_unknown_extension_falls_back_to_bin(storage: LocalFsBlobStorage) -> None:
    key = storage.put(b"x", original_filename="weird.xyz")
    assert key.endswith(".bin")


def test_put_strips_directory_traversal(storage: LocalFsBlobStorage) -> None:
    # ext is taken via Path().suffix, not from the raw filename, so a name
    # like "../../etc/passwd" is harmless — the only thing the caller can
    # influence is the extension.
    key = storage.put(b"y", original_filename="../../etc/passwd")
    assert "etc" not in key
    assert key.endswith(".bin")


def test_put_handles_missing_filename(storage: LocalFsBlobStorage) -> None:
    key = storage.put(b"z", original_filename=None)
    assert key.endswith(".bin")


def test_get_unknown_key_raises(storage: LocalFsBlobStorage) -> None:
    with pytest.raises(FileNotFoundError):
        storage.get("2026/01/01/bogus.pdf")


def test_delete_is_idempotent(storage: LocalFsBlobStorage) -> None:
    key = storage.put(b"q", original_filename="x.png")
    storage.delete(key)
    assert not storage.exists(key)
    storage.delete(key)  # second delete must not raise


def test_resolve_rejects_path_escape(storage: LocalFsBlobStorage) -> None:
    with pytest.raises(ValueError, match="escapes storage root"):
        storage._resolve("../../../etc/passwd")


def test_resolve_rejects_directory_prefix_collision(tmp_path: Path) -> None:
    """Regression: ``startswith`` would mis-accept sibling dirs whose names
    happen to begin with the storage root's basename. ``is_relative_to``
    handles this correctly.
    """
    root = tmp_path / "blobs"
    root.mkdir()
    sibling = tmp_path / "blobs_evil"
    sibling.mkdir()
    storage = LocalFsBlobStorage(root)
    with pytest.raises(ValueError, match="escapes storage root"):
        storage._resolve("../blobs_evil/secret.txt")


def test_exists_returns_false_for_escaped_key(storage: LocalFsBlobStorage) -> None:
    # exists() must not raise even for malicious keys.
    assert storage.exists("../../etc/passwd") is False


def test_open_streams_content(storage: LocalFsBlobStorage) -> None:
    key = storage.put(b"streamed", original_filename="x.png")
    with storage.open(key) as fh:
        assert fh.read() == b"streamed"