"""Config for Deezer Ingestion Workflow."""

from datetime import datetime
import os

environment = os.environ.get('Environment', 'dev')
feed_name = 'deezer_daily'
secrets_path = 'deezer_daily' if environment == 'prod' else 'swf-deezer'
feedid = 9  # SELECT feedid from dim_feed where feedname = 'Deezer'

licensors = ['theorchard', 'sme', 'altafonte']

# file name as ingested from the service
drop_file_name = {
    'theorchard_v1':
        'TheOrchard_{datestamp_YYYYMMDD}_{datestamp_YYYYMMDD}.zip',
    'theorchard_v3':
        'deezer_daily_report_theorchard_activity_metrics_{datestamp_YYYYMMDD}.zip', # noqa
    'sme_v2':
        'sony_{datestamp_YYYYMMDD}_{datestamp_YYYYMMDD}.zip',
    'sme_v3':
        'deezer_daily_report_sony_activity_metrics_{datestamp_YYYYMMDD}.zip',
    'altafonte_v4': '{datestamp_YYYYMMDD}-AltafonteMERLIN.zip'
}

local_downloads_dir = './deezer_downloads'

# root AWS bucket
s3_bucket = os.environ.get(
    'FEED_INGESTION_DATA_BUCKET', 'dev-cucumbers')
sme_drop_bucket = os.environ.get('SME_FEED_INGESTION_DROP_BUCKET',
                                 'sme-ca-prod-partners')
sme_drop_path = os.environ.get('SME_DROP_PATH', 'deezer/in/PG45/')

altafonte_drop_bucket = os.environ.get('ALTAFONTE_FEED_INGESTION_DROP_BUCKET',
                                       'prod-orcd-ftp')

altafonte_drop_path = os.environ.get('ALTAFONTE_DROP_PATH',
                                     'ftp/altafonte/merlin/dzr-deezer/{date:%Y-%m-%d}/') # noqa

altafonte_reports_prefix = 'AltafonteMERLIN_{date:%Y%m%d}_{date:%Y%m%d}'

if environment == 'production':
    s3_bucket = 'cucumbers'

# TODO: define exact dates for v3 switch
spec_version = {
    'theorchard': [
        {'since': '2000-01-01', 'version': 1},
        {'since': '2024-02-01', 'version': 3}
    ],
    'sme': [
        {'since': '2000-01-01', 'version': 2},
        {'since': '2024-01-01', 'version': 3}
    ],
    'altafonte': [
        {'since': '2024-05-01', 'version': 4},
    ],
}

zephir = {
    'username': os.environ.get('ZEPHIR_DEEZER_USERNAME', 'fake_deezer_user'),
    'password': os.environ.get('ZEPHIR_DEEZER_PASSWORD', 'FakePassword123'),
    'host': os.environ.get('ZEPHIR_DEEZER_HOST', 'https://zephir.deezer.com'),
    'path': os.environ.get('ZEPHIR_DEEZER_PATH',
                           '/external/download?file=daily/')
}

# TODO: rename _bucket to _full_path
s3 = {
    'archive_bucket':
        's3://{s3_bucket}/DeezerV{spec_version}'
        '/archives/{datestamp}/{licensor}/',
    'temp_staging_raw_bucket':
        's3://{s3_bucket}/DeezerV{spec_version}'
        '/temp/{datestamp}/{licensor}/',
}

# intermediate entity to avoid v3 names duplication
names_alias = {
    'theorchard_v1': 'v1',
    'sme_v2': 'v2',
    'theorchard_v3': 'v3',
    'sme_v3': 'v3',
    'altafonte_v4': 'v4',
}

snowflake_table_names = {
    'staging_raw': {
        'v1': 'staging_raw_deezer_v1',
        'v2': 'staging_raw_deezer_v2',
        'v3': [
            'staging_raw_deezer_v3_activity_metrics',
            'staging_raw_deezer_v3_detailed_content_identifiers',
            'staging_raw_deezer_v3_playlist_metrics',
            'staging_raw_deezer_v3_stream_source',
            'staging_raw_deezer_v3_user_activity_metrics',
            'staging_raw_deezer_v3_user_details',
            'staging_raw_deezer_v3_vendor_product_details',
            'staging_raw_deezer_v3_fraud_report'
        ],
        'v4': 'staging_raw_deezer_v4',
    },
}

# source files format specs
file_suffixes = {
    'v1': ['.txt', '_TB.txt'],
    'v2': ['_FR.txt', '_ROW.txt', '_TB.txt'],
    'v3': [
        'sony_activity_metrics_daily.csv',
        'sony_detailed_content_identifiers_daily.csv',
        'sony_playlist_metrics.csv',
        'sony_stream_source.csv',
        'sony_user_activity_metrics.csv',
        'sony_user_details.csv',
        'sony_vendor_product_details_daily.csv',
        'fraud_report_*.txt'
    ],
    'v4': ['.txt', '_TB.txt'],
}

v3_files_fraud = ['fraud_report_*.txt']


# Snowflake destination for the fraud report table
# (separate from the default facts.prod)
fraud_report_sf = {
    'db': os.environ.get('FRAUD_REPORTING_DB', 'fraud_reporting'),
    'schema': os.environ.get('FRAUD_REPORTING_SCHEMA', 'deezer'),
}

# Mapping from licensor name to the identifier Deezer uses
# in fraud report filenames.
# e.g. sme -> fraud_report_sony-YYYYMMDD.txt,
# theorchard -> fraud_report_theorchard-YYYYMMDD.txt
fraud_report_licensor_names = {
    'sme': 'sony',
    'theorchard': 'theorchard',
}

# config for the update_dim_tables task
dimension_tables = {
    'tables_to_update': [
        'dim_playlist', 'dim_user',
    ],
    'include_to_report': [
        'dim_playlist', 'dim_user',
    ],
    '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')
}

jenkins_config = {
    'feeds_needed_for_jenkins_build': ['deezer_daily_licensorplaceholder'],  # plus licensor in runtime, this is for get_overall_status + date  # noqa
    '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}
}


def get_version(rules, lookup_date):
    """Get version of the report by date."""
    version = ''
    for rule in rules:
        period_start_str = rule['since']
        period_start = datetime.strptime(
            period_start_str, '%Y-%m-%d').date()
        if period_start > lookup_date:
            break
        version = rule['version']
    return version