"""Config for Spotify Workflow."""
import os

feed_name = 'spotify'
secrets_path = 'spotify'
feed_version = '3.1'
s3_feed_name = 'SpotifyV2'

storeid = 286
feedid = 1  # SELECT feedid FROM dim_feed WHERE feedname = 'Spotify Streams'

# just for historical records:
FIRST_USE_OF_PARTITIONED_ENDPOIUNT = '2024-01-22'

# environment to run in
environment = os.environ.get('Environment', 'dev')

# bucket for archived data
data_bucket = os.environ.get('FEED_INGESTION_DATA_BUCKET', 'dev-cucumbers')

# bucket for dropped data
drop_bucket = os.environ.get('FEED_INGESTION_DROP_BUCKET', 'dev-feed-drop')

# Multiprocessing pool size for report downloader.
pool_size = os.environ.get('SPOTIFY_POOL_SIZE', 5)

# S3 location for archived files
s3 = {
    'archive_path': (
        '{s3_feed_name}/archives/{{date:%Y-%m-%d}}/{{report_name}}/'
        '{{licensor}}/'.format(s3_feed_name=s3_feed_name)
    ),
    'drop_path': (
        'feed-drop/{s3_feed_name}/{{date:%Y-%m-%d}}/{{report_name}}/'
        '{{licensor}}/'.format(s3_feed_name=s3_feed_name))
}

reports = {
    'streams': {
        'staging_raw': 'staging_raw_spotify_v2',
        'use_countries': True,
        'separate_query_for_cleaning_staging_raw': True,
    },
    'sub_30_sec_streams': {
        # we can re-enable this and backfill data if needed
        # for backfill use context parameter:'{
        # "context_date": "backfilled-date",
        # "reports": "sub_30_sec_streams"}'
        # 'staging_raw': 'staging_raw_spotify_sub30',
        'use_countries': True,
    },
    'aggregated_streams': {
        'staging_raw': 'staging_raw_spotify_aggregated_streams',
        # it is needed to load filename in staging raw table
        'filename': True,
        'separate_query_for_cleaning_staging_raw': True,
    },
    'users': {},
    'tracks': {
        'staging_raw': 'spotify_tracks'}
}

common_reports = ['users', 'tracks']

# DS-6220 Due to sub_30_sec_streams is not used, it will be only downloaded,
# in case it will be used in the future
download_only_reports = ['sub_30_sec_streams']

fact_analytics_report = 'streams'

# report for load_aggregated_skips_and_saves
aggregated_report = 'aggregated_streams'

temp_staging_raw_table = (
    'temp_staging_raw_spotify_{report}_{date}_{licensor}')

transitional_temp_table = 'transitional_temp_table_{report}_{date}_{licensor}'

file_pattern = '{report_name}_{date:%Y-%m-%d}{country_code}_{licensor}.gz'

# The maximum allowed number of errors in the file
snowflake_error_limit = 10000

# list of licensors which data should be ingested
spotify_api_licensors = ['theorchard', 'sme', 'smejp',
                         'smejpintl', 'smecharity', 'altafonte']

# Retention policy for Spotify API
spotify_api_retention_days = 30

columbia_labelid = 32551

consumer_sf = {
    'db': os.environ.get('CONSUMER_DB', 'CONSUMER_REPORTING'),
    'schema': os.environ.get('CONSUMER_SCHEMA', 'SPOTIFY'),
}


def _get_environ(variable, licensor):
    licensor_specific_name = '{variable}_{licensor}'.format(
        variable=variable,
        licensor=licensor.upper())
    return os.environ.get(licensor_specific_name, os.environ.get(variable))


spotify_api_credentials = {}
for licensor in spotify_api_licensors:
    spotify_api_credentials[licensor] = {
        'client_id': _get_environ('SPOTIFY_API_CLIENT_ID', licensor),
        'client_secret': _get_environ('SPOTIFY_API_CLIENT_SECRET', licensor),
        'licensor': _get_environ('SPOTIFY_API_LICENSOR', licensor),
        'version': os.environ.get('SPOTIFY_API_VERSION', 'v1')
    }

countries = [
    'AD', 'AE', 'AF', 'AG', 'AI', 'AL', 'AM', 'AN', 'AO', 'AQ',
    'AR', 'AS', 'AT', 'AU', 'AW', 'AX', 'AZ', 'BA', 'BB', 'BD',
    'BE', 'BF', 'BG', 'BH', 'BI', 'BJ', 'BL', 'BM', 'BN', 'BO',
    'BQ', 'BR', 'BS', 'BT', 'BV', 'BW', 'BY', 'BZ', 'CA', 'CC',
    'CD', 'CF', 'CG', 'CH', 'CI', 'CK', 'CL', 'CM', 'CN', 'CO',
    'CR', 'CS', 'CU', 'CV', 'CW', 'CX', 'CY', 'CZ', 'DE', 'DJ',
    'DK', 'DM', 'DO', 'DZ', 'EC', 'EE', 'EG', 'EH', 'ER', 'ES',
    'ET', 'FI', 'FJ', 'FK', 'FM', 'FO', 'FR', 'GA', 'GB', 'GD',
    'GE', 'GF', 'GG', 'GH', 'GI', 'GL', 'GM', 'GN', 'GP', 'GQ',
    'GR', 'GS', 'GT', 'GU', 'GW', 'GY', 'HK', 'HM', 'HN', 'HR',
    'HT', 'HU', 'ID', 'IE', 'IL', 'IM', 'IN', 'IO', 'IQ', 'IR',
    'IS', 'IT', 'JE', 'JM', 'JO', 'JP', 'KE', 'KG', 'KH', 'KI',
    'KM', 'KN', 'KP', 'KR', 'KW', 'KY', 'KZ', 'LA', 'LB', 'LC',
    'LI', 'LK', 'LR', 'LS', 'LT', 'LU', 'LV', 'LY', 'MA', 'MC',
    'MD', 'ME', 'MF', 'MG', 'MH', 'MK', 'ML', 'MM', 'MN', 'MO',
    'MP', 'MQ', 'MR', 'MS', 'MT', 'MU', 'MV', 'MW', 'MX', 'MY',
    'MZ', 'NA', 'NC', 'NE', 'NF', 'NG', 'NI', 'NL', 'NO', 'NP',
    'NR', 'NU', 'NZ', 'OM', 'PA', 'PE', 'PF', 'PG', 'PH', 'PK',
    'PL', 'PM', 'PN', 'PR', 'PS', 'PT', 'PW', 'PY', 'QA', 'RE',
    'RO', 'RS', 'RU', 'RW', 'SA', 'SB', 'SC', 'SD', 'SE', 'SG',
    'SH', 'SI', 'SJ', 'SK', 'SL', 'SM', 'SN', 'SO', 'SR', 'SS',
    'ST', 'SV', 'SX', 'SY', 'SZ', 'TC', 'TD', 'TF', 'TG', 'TH',
    'TJ', 'TK', 'TL', 'TM', 'TN', 'TO', 'TR', 'TT', 'TV', 'TW',
    'TZ', 'UA', 'UG', 'UM', 'US', 'UY', 'UZ', 'VA', 'VC', 'VE',
    'VG', 'VI', 'VN', 'VU', 'WF', 'WS', 'XK', 'YE', 'YT', 'ZA',
    'ZM', 'ZW', 'ZZ']

expected_countries = [
    'AD', 'AR', 'AT', 'AU', 'BE', 'BG', 'BO', 'BR', 'CA', 'CH',
    'CL', 'CO', 'CR', 'CY', 'CZ', 'DE', 'DK', 'DO', 'EC', 'EE',
    'ES', 'FI', 'FR', 'GB', 'GR', 'GT', 'HK', 'HN', 'HU', 'IE',
    'IS', 'IT', 'LI', 'LT', 'LU', 'LV', 'MC', 'MT', 'MX', 'MY',
    'NI', 'NL', 'NO', 'NZ', 'PA', 'PE', 'PH', 'PL', 'PT', 'PY',
    'SE', 'SG', 'SK', 'SV', 'TR', 'TW', 'US', 'UY'
]

# config for the update_dim_tables task
dimension_tables = {
    'tables_to_update': [
        'dim_sourcetype', 'dim_subscriptiontype', 'dim_subscriptionpaytier',
        'dim_playlist', 'dim_user',
    ],
    'include_to_report': [
        'dim_sourcetype', 'dim_subscriptiontype', 'dim_subscriptionpaytier'
    ],
    'sns_topic': os.environ.get(
        'FEED_INGESTION_SNS_TOPIC',
        'arn:aws:sns:us-east-1:437795906767:dev-swf-feed-ingestion:'
        'e17576f8-b905-45a9-b863-0eaceca54f4d')
}

DBT_REQUIRED_REPORTS = [
    'streams',
    'aggregated_streams',
]

jenkins_config = {
    'feeds_required_for_jenkins_build': [
        f'spotify_{licensor}_{report}'
        for licensor in ['theorchard', 'sme']
        for report in DBT_REQUIRED_REPORTS
    ],
    'jenkins_username': os.environ.get('JENKINS_USER', 'jenkinsjobrunner'),
    'jenkins_secrets_path': 'swf-shared-jenkins',
    'jenkins_url': 'https://scheduler.theorchard.io',
    'jenkins_job': 'dbt-scheduler-analytics-pipeline',
    'jenkins_job_params': {'TRIGGERED_BY': feed_name},
}

SMART_DOWNLOADER_TASKS_DYNAMODB_TABLE = os.environ.get(
    'SMART_DOWNLOADER_TASKS_DYNAMODB_TABLE',
    default=f'{environment}_smart_downloader_tasks'
)

# how long wait completion of download tasks
# it has no sense to wait longer than
# ttl for partition link from SpotifyAPI (which is 15 minutes)
SMART_DOWNLOADER_TIMEOUT_SECONDS = 900

# How long we want to keep tasks in DynamoDB
SMART_DOWNLOADER_TASKS_TTL_SECONDS = 60 * 60 * 24 * 7

# How many partition files go to smart_downloader task
SMART_DOWNLOADER_BATCH_SIZE = 20