"""Config for Amazon Music Ingestion Workflow."""
import datetime
import os
import re

feed_name = 'amazon_music'
secrets_path = 'amazon_music'
feed_version = '1.0'
storeid = 187

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

SOURCE_SFTP = 'sftp'
SOURCE_DATAPULSE = 'datapulse'
sources = [SOURCE_SFTP, SOURCE_DATAPULSE]
# Licensors mapped from datapulse ENTITY_NAME column.
DATAPULSE_LICENSORS = ['theorchard', 'sme']
# Maps the amazon_music licensor to the datapulse ENTITY_NAME value.
DATAPULSE_ENTITY_NAME_BY_LICENSOR = {
    'sme': 'Sony',
    'theorchard': 'ZQOR',
    'awal': 'ZQAWA',
    'red': 'ZQRED',
}
# Maps amazon_music report_name to the datapulse SERVICE partition value.
DATAPULSE_SERVICE_BY_REPORT = {
    'unlimited': 'Unlimited',
    'prime': 'Prime',
    'adsupported': 'FreeTier',
}
# Single unified staging_raw table loaded from the datapulse Snowflake tables.
# Holds all reports (services) and licensors for a given date in one place,
# replacing the per-report staging_raw_amazon_<report> tables.
DATAPULSE_STAGING_RAW_TABLE = 'staging_raw_amazon_music'

reports = {
    'unlimited': {
        'feedid': 37,
        'staging_raw_table': 'staging_raw_amazon_unlimited',
        'cucumber_drop_feed_name': 'AmazonUnlimited',
        'cucumber_feed_name': 'AmazonUnlimitedV2',
        'awal_ftp_folder_name': 'Unlimited',
        'awal_report_name_in_filename': 'Unlimited',
        'altafonte_ftp_folder_name': 'Unlimited',
        'altafonte_report_name_in_filename': 'Unlimited',
        'unstable_countries': []},
    'prime': {
        'feedid': 35,
        'staging_raw_table': 'staging_raw_amazon_prime',
        'cucumber_feed_name': 'AmazonPrime',
        'awal_ftp_folder_name': 'Prime',
        'awal_report_name_in_filename': 'Prime',
        'altafonte_ftp_folder_name': 'Prime',
        'altafonte_report_name_in_filename': 'Prime',
        'unstable_countries': []},
    'adsupported': {
        'feedid': 36,
        'staging_raw_table': 'staging_raw_amazon_adsupported',
        'cucumber_feed_name': 'AmazonAdSupported',
        'awal_ftp_folder_name': 'Ad-Supported',
        'awal_report_name_in_filename': 'ADS',
        'altafonte_ftp_folder_name': 'Ad-Supported',
        'altafonte_report_name_in_filename': 'ADS',
        'unstable_countries': []},
}

# execution of the flow can take up to 2 hours
# so let's clean up for period 3 times more
MAX_EXECUTION_TIMEOUT = 3 * 2 * 3600

DATE_FORMAT = '%Y-%m-%d'

# This is original file template for The Orchard.
file_template = (
    '{org}_{country}_{date:%Y%m%d}_Daily_{report_type}_Report.txt.zip')
file_name_regexp = re.compile(
    r'(?P<org>[A-Z]{4,5})_(?P<country>[A-Z_]{2,6})_(?P<file_date>[\d]+)_Daily_'
    r'(?P<report_type>[a-zA-Z]+)_Report.txt.zip')

# This is file template will be for other licensors in archive ../clean folder.
gz_file_template = (
    '{org}_{country}_{date}_Daily_{report_type}_Report.txt.gz')
table_name_template = (
    '{feed_name}_daily_{licensor}_{report_type}_report_{org}_{country}_{date}')

# default report types
report_types = ['Playlist', 'Activity', 'User']

SME_AWS_ACCESS_KEY_ID_NAME = 'SME_AWS_ACCESS_KEY_ID'
SME_AWS_SECRET_ACCESS_KEY_NAME = 'SME_AWS_SECRET_ACCESS_KEY'

# example filename in sme bucket:
# PCO3_A_AU_20190220_20190220_Activity_20190221.txt.zip
sme_file_name_regexp = re.compile(
    r'(?P<org>[A-Z\d]{4})_A_(?P<country>[A-Z_]{2,6})_'
    r'(?P<file_date_start>[\d]+)_(?P<file_date_end>[\d]+)_'
    r'(?P<report_type>[a-zA-Z]+)_(?P<file_timestamp>[\d]+).txt.zip')

licensors_config = {
    'theorchard': {
        'report_types': report_types,
        'file_name_regexp': file_name_regexp,
        'file_template': file_template
    },
    'sme': {
        'report_types': report_types,
        # filename example in sme bucket:
        # PCO3_A_AU_20190220_20190220_Activity_20190221.txt.zip
        'file_name_regexp': sme_file_name_regexp,
        'file_template': file_template
    },
    'awal': {
        # there is only one type of files for awal
        'report_types': ['Activity'],
        # filename example on awal ftp
        # ZQAWA_Daily_Unlimited_Activity_20220710_US.txt.zip
        'file_name_regexp': re.compile(
            r'(?P<org>[A-Z]{5})_Daily_(?P<report>[a-zA-Z]+)_Activity'
            r'_(?P<file_date>[\d]+)_(?P<country>[A-Z_]{2,6}).txt.zip'),
        # original file_template on awal ftp
        'file_template': (
            '{org}_Daily_{report}_Activity_{date:%Y%m%d}_{country}.txt.zip'),
        'org': 'ZQAWA'
    },
    'altafonte': {
        # there is only one type of files for altafonte
        'report_types': ['Activity'],
        # filename example on altafonte ftp
        # ZQALT_Daily_Unlimited_Activity_20250122_US.txt.zip
        'file_name_regexp': re.compile(
            r'(?P<org>[A-Z]{5})_Daily_(?P<report>[a-zA-Z]+)_Activity'
            r'_(?P<file_date>[\d]+)_(?P<country>[A-Z_]{2,6}).txt.zip'),
        # original file_template on altafonte ftp
        'file_template': (
            '{org}_Daily_{report}_Activity_{date:%Y%m%d}_{country}.txt.zip'),
        'org': 'ZQALT'
    },
}

# bucket for dropped data
drop_bucket = os.environ.get('FEED_INGESTION_DROP_BUCKET', 'dev-feed-drop')
sme_drop_bucket = os.environ.get('SME_FEED_INGESTION_DROP_BUCKET',
                                 'sme-ca-prod-partners')

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

awal_drop_bucket = os.environ.get(
    'FEED_INGESTION_AWAL_DROP_BUCKET', 'prod-orcd-awal-drop')
awal_s3_folder = 'amazon_usage'
awal_s3_drop_bucket = (
    f's3://{awal_drop_bucket}/AWAL_TO_ORCH/'
    f'ANALYTICS_BACKFILL/{awal_s3_folder}/')
awal_s3_path = (
    's3://{drop_bucket}/AWAL_TO_ORCH/ANALYTICS_BACKFILL/{awal_s3_folder}/'
    'version={version}/year={date:%Y}/month={date:%Y%m}/day={date:%Y%m%d}/'
    'service={report_type}/iso_territory_code={country_code}/')

altafonte_drop_bucket = os.environ.get(
    'FEED_INGESTION_ALTAFONTE_DROP_BUCKET', 'prod-orcd-ftp')
altafonte_s3_folder = 'Amazon'
altafonte_s3_drop_bucket = (
    f's3://{altafonte_drop_bucket}/ftp/'
    f'altafonte/{altafonte_s3_folder}/sales/')
altafonte_s3_path = (
    's3://{drop_bucket}/ftp/altafonte/{altafonte_s3_folder}/sales/'
    'version={version}/year={date:%Y}/month={date:%Y%m}/day={date:%Y%m%d}/'
    'service={report_type}/iso_territory_code={country_code}/')

s3 = {
    'drop_path': {
        'sme': 's3://{s3_bucket}/amazon/in/{{report_location}}'
               '/{{date:%Y/%m/%d}}/'.format(s3_bucket=sme_drop_bucket),
        'theorchard': (
            's3://{s3_bucket}/feed-drop/{{cucumber_feed_name}}/'.format(
                s3_bucket=drop_bucket)),
        # source for awal files is sftp, it is just placeholder
        'awal': 's3://placeholder',
        # source for altafonte files is sftp, it is just placeholder
        'altafonte': 's3://placeholder'
    },
    'archive_path': (
        's3://{s3_bucket}/{{cucumber_feed_name}}/archives/'
        '{{date:%Y-%m-%d}}/{{licensor}}/').format(s3_bucket=archive_bucket),
    'clean_dir': 'clean/'
}

# sftp config for awal data
sftp = {
    'host': os.environ.get(
        'AMAZON_MUSIC_AWAL_SFTP_HOST',
        'prod.reporting.amazonmusiccatalog.com'),
    'username': 'AMAZON_MUSIC_AWAL_SFTP_USERNAME',
    'password': 'AMAZON_MUSIC_AWAL_SFTP_PASSWORD',
    'port': int(os.environ.get('AMAZON_MUSIC_AWAL_SFTP_PORT', 22)),
    'path': 'sales/{country}/Daily/{awal_ftp_folder_name}/'
}

# sftp config for altafonte data
sftp_altafonte = {
    'host': os.environ.get(
        'AMAZON_MUSIC_ALTAFONTE_SFTP_HOST',
        'digital-music-ftp.amazonmp3.com'),
    'username': 'AMAZON_MUSIC_ALTAFONTE_SFTP_USERNAME',
    'password': 'AMAZON_MUSIC_ALTAFONTE_SFTP_PASSWORD',
    'port': int(os.environ.get('AMAZON_MUSIC_ALTAFONTE_SFTP_PORT', 22)),
    'path': 'sales/{country}/Daily/{altafonte_ftp_folder_name}/'
}

aggregated_staging_raw_table = 'staging_raw_amazon_aggregated_streams'

FEED_DELAY = 3

# Number of days for monitoring
MONITORING_PERIOD_OF_UNSTABLE_COUNTRIES = 15
# A country becomes stable if the ratio of stable days to the number of
# monitoring days is more than this value
REQUIRED_PERCENT_OF_STABLE_DAYS = 0.8

UNEXPECTED_FILES_NOTIFICATION_SUBJECT = (
    'Alert: Amazon {report} Analytics ({licensor}). '
    'Unexpected files were found in S3 location.')
UNEXPECTED_FILES_NOTIFICATION_MESSAGE = ('Unexpected files:\n{}')

NEW_STABLE_COUNTRIES_NOTIFICATION_SUBJECT = (
    'Alert: Amazon {report} Analytics ({licensor}). '
    'New stable countries were detected.')
NEW_STABLE_COUNTRIES_NOTIFICATION_MESSAGE = 'Country stability:\n{}'

# 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')
}

dimension_tables_awal = {
    'tables_to_update': ['dim_sourcetype', 'dim_playlist', 'dim_user'],
    'include_to_report': ['dim_sourcetype'],
    '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')
}

dimension_tables_altafonte = {
    'tables_to_update': ['dim_sourcetype', 'dim_playlist', 'dim_user'],
    'include_to_report': ['dim_sourcetype'],
    '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')
}

# Dimension tables for the datapulse source.
# The _datapulse queries read from the
# unified staging_raw_amazon_music table and apply the legacy value mappings.
dimension_tables_datapulse = {
    'tables_to_update': [
        'dim_sourcetype_datapulse', 'dim_subscriptiontype_datapulse',
        'dim_subscriptionpaytier_datapulse', 'dim_playlist_datapulse',
        'dim_user_datapulse'
    ],
    'include_to_report': [
        'dim_sourcetype_datapulse', 'dim_subscriptiontype_datapulse',
        'dim_subscriptionpaytier_datapulse'
    ],
    'sns_topic': dimension_tables['sns_topic']
}

# The maximum allowed number of errors in the file
snowflake_error_limit = 5

# The maximum allowed number of errors in the file during file preparation
malformed_rows_limit = 20

# NOTE: Amazon includes two rows at the beginning and at the end of file
# that do not match the columns expected for the file; skip them.
SKIP_LINE_COLUMNS = 4


def parse_date(date_str):
    """Parse date from YYYY-MM-DD and return dattime object."""
    return datetime.datetime.strptime(date_str, DATE_FORMAT)


jenkins_config = {
    'feeds_required_for_jenkins_build': [
        '_'.join([feed_name, licensor, report_name])
        for licensor in DBT_REQUIRED_LICENSORS
        for report_name in reports
    ],
    'jenkins_username': os.environ.get('JENKINS_USER', 'jenkinsjobrunner'),
    'jenkins_secrets_path': 'swf_feed_ingestion',
    'jenkins_url': 'https://scheduler.theorchard.io',
    'jenkins_job': 'dbt-scheduler-analytics-pipeline',
    'jenkins_job_params': {'TRIGGERED_BY': feed_name}
}