import gzip
import json
import unittest
from datetime import datetime

import pytest
from requests import Response

from slz_appreciationengine_scrapper.const import RATE_LIMIT_HOUR_HEADER
from slz_appreciationengine_scrapper.content_status_service import ContentStatusService
from slz_appreciationengine_scrapper.dsp.appreciationengine.clients import PaginateClientPartial
from slz_appreciationengine_scrapper.dsp.entities import MetaDataKey
from slz_appreciationengine_scrapper.entities import Job


def resp_mock_activityfeed_us_columbia_partial():
    data = [
        {
            'totalSize': 1000,
            'items': [{
                'RecordDate': '2020-11-04 23:17:16'
            }, ]
        },
        # request to check filtering rule
        {
            'totalSize': 1000,
            'items': [{
                'RecordDate': '2020-11-04 23:17:16'
            }, ]
        },
        {
            'totalSize':
                1000,
            'items':
                [
                    {
                        'RecordDate': '2020-11-04 23:17:17'
                    },
                    {
                        'RecordDate': '2020-11-04 23:17:18'
                    },
                    {
                        'RecordDate': '2020-11-04 23:17:19'
                    },
                ]
        },
        {
            'totalSize':
                1000,
            'items':
                [
                    {
                        'RecordDate': '2020-11-04 23:17:20'
                    },
                    {
                        'RecordDate': '2020-11-04 23:17:21'
                    },
                    {
                        'RecordDate': '2020-11-04 23:17:22'
                    },
                    {
                        'RecordDate': '2020-11-04 23:17:23'
                    },
                    {
                        'RecordDate': '2020-11-04 23:17:25'
                    },
                ]
        },
        {
            'totalSize': 1,
            'items': [{
                'RecordDate': '2020-11-04 23:17:27'
            }]
        }
    ]
    rate_limit = 7
    for dt in data:
        resp_mock = unittest.mock.MagicMock(spec=Response)
        resp_mock.status_code = 200
        resp_mock.ok = True
        resp_mock.url = ''
        resp_mock.content = bytes(json.dumps(dt), encoding='utf8')
        resp_mock.headers = {RATE_LIMIT_HOUR_HEADER: rate_limit}
        rate_limit -= 1
        yield resp_mock


@pytest.mark.integration
@unittest.mock.patch(
    'slz_appreciationengine_scrapper.dsp.appreciationengine.ae_io.time.sleep', return_value=None
)
@unittest.mock.patch('slz_appreciationengine_scrapper.dsp.appreciationengine.clients.get_secret')
@unittest.mock.patch('requests.get')
@unittest.mock.patch(
    'slz_appreciationengine_scrapper.dsp.appreciationengine.clients.datetime',
    wraps=datetime,
    now=lambda *args, **kwargs: datetime(year=2021, month=6, day=5, hour=1, minute=1, second=1)
)
def test_downloading_paginate_partial(
    datetime_mock,
    requests_get,
    get_secret,
    patched_time_sleep,
    db,
    params,
    s3_client,
    ae_mapping,
):
    for bucket in ['bucket-archive-quarantine', 'bucket-decompressed-quarantine']:
        s3_client.create_bucket(Bucket=bucket)

    uow_dict = {
        'uow_id': 'appreciationengine-20201104-sme-activityfeed-v1',
        'dsp': 'appreciationengine',
        'report_type': 'activityfeed',
        'version': 'v1',
        'report_date': '2020-11-04',
        'licensor': 'sme',
        'extension': 'json',
        'context': 'US_Columbia',
    }

    # Client initialization
    logger = unittest.mock.Mock()
    timer = unittest.mock.Mock()
    client = PaginateClientPartial(logger=logger)

    # Mock secrets
    get_secret.return_value = json.dumps({
        "Sony Music US - Columbia": "afa0d1d",
    })

    params.scrapper.min_rate_limit_remaining_hour = 5

    client.configure(params)
    job = Job.from_dict(uow_dict)

    expected_file_content = ''.join(
        [
            '{"RecordDate": "2020-11-04 23:17:16"}\n',
            '{"RecordDate": "2020-11-04 23:17:17"}\n',
            '{"RecordDate": "2020-11-04 23:17:18"}\n',
            '{"RecordDate": "2020-11-04 23:17:19"}\n',
            '{"RecordDate": "2020-11-04 23:17:20"}\n',
            '{"RecordDate": "2020-11-04 23:17:21"}\n',
            '{"RecordDate": "2020-11-04 23:17:22"}\n',
            '{"RecordDate": "2020-11-04 23:17:23"}\n',
        ]
    )
    # Mock response from source API
    requests_get.return_value.__enter__.side_effect = resp_mock_activityfeed_us_columbia_partial()

    content_status_service = ContentStatusService(logger=logger, db_conn=db)
    meta, meta_data, io_exception = client.download(
        job,
        chunk_size=1,
        timer=timer,
        timeslot=None,
        content_status_service=content_status_service
    )

    # read data from mocked S3 buckets
    path = 'appreciationengine/activityfeed/v1/report_date=2020-11-04/report_licensor=sme'
    actual_decompressed = s3_client.get_object(
        Bucket='bucket-decompressed-quarantine',
        Key=f'{path}/US_Columbia_20201104_20210605010101.json',
    )['Body'].read()
    actual_compressed = s3_client.get_object(
        Bucket='bucket-archive-quarantine',
        Key=f'{path}/US_Columbia_20201104_20210605010101.json.gz',
    )['Body'].read()

    assert expected_file_content == actual_decompressed.decode('utf8')
    assert expected_file_content == gzip.decompress(actual_compressed).decode('utf8')
    assert meta_data[MetaDataKey.NEW_START_DATE.value] == "2020-11-04 23:17:24"


def resp_mock_activityfeed_us_columbia_partial_small_resp():
    data = [
        {
            'totalSize': 1,
            'items': [{
                'RecordDate': '2020-11-04 19:31:16'
            }, ]
        },
        # request to check filtering rule
        {
            'totalSize': 1,
            'items': [{
                'RecordDate': '2020-11-04 19:31:16'
            }, ]
        },
        {
            'totalSize': 0,
            'items': []
        }
    ]
    rate_limit = 7
    for dt in data:
        resp_mock = unittest.mock.MagicMock(spec=Response)
        resp_mock.status_code = 200
        resp_mock.ok = True
        resp_mock.url = ''
        resp_mock.content = bytes(json.dumps(dt), encoding='utf8')
        resp_mock.headers = {RATE_LIMIT_HOUR_HEADER: rate_limit}
        rate_limit -= 1
        yield resp_mock


@pytest.mark.integration
@unittest.mock.patch(
    'slz_appreciationengine_scrapper.dsp.appreciationengine.ae_io.time.sleep', return_value=None
)
@unittest.mock.patch('slz_appreciationengine_scrapper.dsp.appreciationengine.clients.get_secret')
@unittest.mock.patch('requests.get')
@unittest.mock.patch(
    'slz_appreciationengine_scrapper.dsp.appreciationengine.clients.datetime',
    wraps=datetime,
    now=lambda *args, **kwargs: datetime(year=2021, month=6, day=5, hour=1, minute=1, second=1)
)
def test_downloading_paginate_partial_small_resp(
    datetime_mock, requests_get, get_secret, patched_time_sleep, db, params, s3_client, ae_mapping,
    logger_test
):
    for bucket in ['bucket-archive-quarantine', 'bucket-decompressed-quarantine']:
        s3_client.create_bucket(Bucket=bucket)

    uow_dict = {
        'uow_id': 'appreciationengine-20201104-sme-activityfeed-v1',
        'dsp': 'appreciationengine',
        'report_type': 'activityfeed',
        'version': 'v1',
        'report_date': '2020-11-04',
        'licensor': 'sme',
        'extension': 'json',
        'context': 'US_Columbia',
    }

    # Client initialization
    logger = unittest.mock.Mock()
    timer = unittest.mock.Mock()
    client = PaginateClientPartial(logger=logger_test)

    # Mock secrets
    get_secret.return_value = json.dumps({
        "Sony Music US - Columbia": "afa0d1d",
    })
    params.scrapper.min_rate_limit_remaining_hour = 5
    client.configure(params)
    job = Job.from_dict(uow_dict)

    expected_file_content = ''.join([
        '{"RecordDate": "2020-11-04 19:31:16"}\n',
    ])
    # Mock response from source API
    requests_get.return_value.__enter__.side_effect = resp_mock_activityfeed_us_columbia_partial_small_resp(
    )

    meta_data_initial = {MetaDataKey.NEW_START_DATE.value: "2020-11-04 19:30:01"}
    content_status_service = ContentStatusService(logger=logger, db_conn=db)
    meta, meta_data, io_exception = client.download(
        job,
        chunk_size=1,
        timer=timer,
        meta_data=meta_data_initial,
        timeslot=None,
        content_status_service=content_status_service
    )

    # read data from mocked S3 buckets
    path = 'appreciationengine/activityfeed/v1/report_date=2020-11-04/report_licensor=sme'
    actual_decompressed = s3_client.get_object(
        Bucket='bucket-decompressed-quarantine',
        Key=f'{path}/US_Columbia_20201104_20210605010101.json',
    )['Body'].read()
    actual_compressed = s3_client.get_object(
        Bucket='bucket-archive-quarantine',
        Key=f'{path}/US_Columbia_20201104_20210605010101.json.gz',
    )['Body'].read()

    assert expected_file_content == actual_decompressed.decode('utf8')
    assert expected_file_content == gzip.decompress(actual_compressed).decode('utf8')
    assert meta_data[MetaDataKey.PARTIAL_DOWNLOAD_COMPLETED_AT.value] is not None