"""Unit tests for tasks of YouTube Asset Report Workflow."""
from datetime import datetime
import re
from unittest.mock import MagicMock
from unittest.mock import patch

from freezegun import freeze_time
import pytest

from feed_ingestion.flows.youtube_asset import config
from feed_ingestion.flows.youtube_asset import tasks

_date = '2018-11-16'


class TestBootstrap(object):
    """Test bootstrap."""

    @pytest.fixture(params=[
        'theorchard',
        'sme',
    ])
    def mock_s3(self, request):
        """Yield s3_mock, licensor."""
        licensor = request.param
        s3utils_path = (
            'feed_ingestion.flows.youtube_asset.tasks.s3')

        files = []
        if licensor == 'theorchard':
            files = [
                'content_owner_asset_a3.IODA.csv.gz',
                'content_owner_asset_a3.ENT.csv.gz',
                # all below should be ignored
                'asset_full_report_IODA_L_v1-2.csv.gz',
                'asset_full_report_dmgi_L_v1-2.csv.gz',
                'asset_full_report_dmgi_L_v1-0.csv.gz',
                'asset_full_report_dmgi_L_v1-2.csv',
                'ignore_me_full_report_dmgi_L_v1-2.csv.gz',
            ]
        if licensor == 'sme':
            files = [
                '20201022_172646_00050_y255y_038fffee-d7a3-4197-b75b-a6487479db64',  # noqa:E501
                '20201022_172646_00050_y255y_05506ca6-f9fd-4968-b321-8fbfc298c639',  # noqa:E501
                # all below should be ignored
                'NO20201022_172646_00050_y255y_05506ca6-f9fd-4968-b321-8fbfc298c639',  # noqa:E501
                'wrong_path/20201022_172646_00050_y255y_05506ca6-f9fd-4968-b321-8fbfc298c639',  # noqa:E501
            ]
        with patch(s3utils_path) as s3:
            s3.get_list_of_files_and_directories = MagicMock(
                return_value=files)

            s3.get_key_size = MagicMock(return_value=42)
            yield s3, licensor

    @pytest.fixture
    def expected_bootstrap_response(self):
        """Response for bootstrap task."""
        date = datetime.strptime(_date, '%Y-%m-%d')

        return {
            'date': _date,
            'feed_name': 'youtube_asset_theorchard',
            'skip_grab_reports_files': None,
            'licensor': 'theorchard',
            'credentials_path': config.credentials_paths.get('theorchard'),
            'cms_dict': config.cms_dict,
            's3_bucket': config.s3_bucket,
            's3_dir_path': 's3://{}/{}'.format(
                config.s3_bucket,
                config.s3['archive_path'].format(
                    date=date, licensor='theorchard')
            ),
            's3_archive_path':
                config.s3['archive_path'].format(
                    date=date, licensor='theorchard')}

    @freeze_time(_date)
    @patch('feed_ingestion.flows.youtube_asset.tasks.garcon_feed_status')
    def test_bootstrap_no_date_is_passed(
            self, feed_status_mock,
            expected_bootstrap_response):
        """Date should be set to today if it is not provided."""
        context = {
            'activity': MagicMock(),
            'date': None,
            'skip_grab_reports_files': None,
            'licensor': 'theorchard',
            'reload': False}
        result = tasks.bootstrap(**context)
        assert result == expected_bootstrap_response

    @patch('feed_ingestion.flows.youtube_asset.tasks.garcon_feed_status')
    def test_bootstrap_date_is_passed(
            self, feed_status_mock,
            expected_bootstrap_response):
        """Date should be returned if it is provided."""
        context = {
            'activity': MagicMock(),
            'date': _date,
            'skip_grab_reports_files': None,
            'licensor': 'theorchard',
            'reload': False}
        result = tasks.bootstrap(**context)
        assert result == expected_bootstrap_response

    @patch('feed_ingestion.flows.youtube_asset.tasks.garcon_feed_status')
    def test_source_files(
            self, feed_status_mock,
            mock_s3, expected_bootstrap_response):
        """Date should be returned if it is provided."""
        s3, licensor = mock_s3
        files = []
        if licensor == 'theorchard':
            files = [{'file_name': 'content_owner_asset_a3.IODA.csv.gz',
                      'file_size': 42},
                     {'file_name': 'content_owner_asset_a3.ENT.csv.gz',
                      'file_size': 42}]
        if licensor == 'sme':
            files = [{
                'file_name': '20201022_172646_00050_y255y_038fffee-d7a3-4197-b75b-a6487479db64',  # noqa: E501
                'file_size': 42},
                {'file_name': '20201022_172646_00050_y255y_05506ca6-f9fd-4968-b321-8fbfc298c639',  # noqa: E501
                 'file_size': 42}]
        expected_result = {'source_files_dict': {'files': files}}
        result = tasks.source_files(
            activity=MagicMock(),
            licensor=licensor,
            s3_bucket=MagicMock(),
            s3_archive_path='/archive')
        assert result == expected_result

    @pytest.mark.parametrize('string, prefix, result', (
            ('qwerty', 'qw', 'erty'),
            ('qwerty', 'qwerty', ''),
            ('qwerty', 'NOqwerty', 'qwerty'),
            ('/path/file', '/path/', 'file'),
            ('/path/file', '/path', '/file'),
            ('/path/file', '/nopath', '/path/file'),
    ))
    def test_remove_prefix(self, string, prefix, result):
        """Test remove_prefix function."""
        assert tasks.remove_prefix(string, prefix) == result

    def test_sme_source_file_pattern(self):
        """Test generated parquet filenames created with Athena CTAS query."""
        # sample filenames created by Athena Query
        filenames = [
            '20201022_172646_00050_y255y_038fffee-d7a3-4197-b75b-a6487479db64',
            '20201022_172646_00050_y255y_05506ca6-f9fd-4968-b321-8fbfc298c636',
            '20201022_172646_00050_y255y_1d980cac-287b-424c-b2cf-06abd3f84aae',
            '20201022_172646_00050_y255y_24840d90-f760-4f5e-838b-f7f59c60245c',
            '20201022_172646_00050_y255y_37588958-24e8-4692-88f7-16cc812c5760',
            '20201022_172646_00050_y255y_38783bac-caa6-47dc-8c63-bb464465f428',
            '20201022_172646_00050_y255y_38fac22d-5519-4a76-886c-1cb51c9cbe87',
            '20201022_172646_00050_y255y_427b53f7-3537-43dd-a3ee-e09ac66d04bf',
            '20201022_172646_00050_y255y_4b6c601d-d642-4e6e-8851-2a2a118dcf23',
            '20201022_172646_00050_y255y_6bd57cdc-2518-47b7-8712-1ff722353261',
        ]
        file_pattern = config.source_file_pattern['sme']
        for filename in filenames:
            assert re.match(file_pattern, filename), \
                f"File {filename} doesn't match to sme_source_file_pattern"