import gzip
from collections.abc import Iterator

import pytest
from botocore.exceptions import ClientError
from moto import mock_aws

from infrastructure.s3.gzip_csv_s3_client import GzipCsvS3Client
from tests.infrastructure import make_boto_client

BUCKET = "gzip-csv-bucket"


@pytest.fixture
def gzip_client() -> Iterator[GzipCsvS3Client]:
    with mock_aws():
        boto_client = make_boto_client("s3")
        boto_client.create_bucket(Bucket=BUCKET)
        yield GzipCsvS3Client(boto_client, BUCKET)


def test_read_csv_gz_decodes_gzipped_csv_into_dataframe(
    gzip_client: GzipCsvS3Client,
) -> None:
    # arrange
    csv = "ADDRESS,UPRN\n47 GORDON ROAD,100\n48 GORDON ROAD,200\n"
    gzip_client.put_object("historical_epc/AB338AL/data.csv.gz", gzip.compress(csv.encode()))

    # act
    df = gzip_client.read_csv_gz("historical_epc/AB338AL/data.csv.gz")

    # assert
    assert list(df.columns) == ["ADDRESS", "UPRN"]
    assert df.shape == (2, 2)
    assert df["ADDRESS"].tolist() == ["47 GORDON ROAD", "48 GORDON ROAD"]


def test_read_csv_gz_raises_no_such_key_when_object_missing(
    gzip_client: GzipCsvS3Client,
) -> None:
    # act / assert — a missing object surfaces as a ClientError; translating that
    # into a domain miss is the Repo's job, not the client's.
    with pytest.raises(ClientError) as exc_info:
        gzip_client.read_csv_gz("historical_epc/ZZ999ZZ/data.csv.gz")
    assert exc_info.value.response["Error"]["Code"] == "NoSuchKey"