import os

environment = os.environ.get('Environment', 'dev')

# spark variables
spark_master = os.environ.get('SPARK_MASTER_URL')
spark_app = 'spark_tester'
spark_s3_temp_dir = 's3n://dev-cucumbers/YouTubeMonthly/spark/'

# aws creds
aws_access_key  = os.environ.get('AWS_ACCESS_KEY_ID')
aws_secret_key = os.environ.get('AWS_SECRET_ACCESS_KEY')

# redshift source 1
redshift_url_1 = 'jdbc:redshift://{HOST}:{PORT}/{DB}?user={USER}&password={PASS}'.format(
        HOST=os.environ.get('REDSHIFT_READ_WRITE_HOST'), PORT=os.environ.get('REDSHIFT_READ_WRITE_PORT'),
        DB=os.environ.get('REDSHIFT_READ_WRITE_DB'), USER=os.environ.get('REDSHIFT_READ_WRITE_USER'),
        PASS=os.environ.get('REDSHIFT_READ_WRITE_PASSWORD'))

###################
# tables to analyze
###################

tables = ['lory_test', 'lory_test_another']

lory_test = {
    'source': redshift_url_1,
    'query': 'SELECT video_id, custom_id, extracted_upc, extracted_upc_long from lory_test',
    'columns': {
        'video_id': 'string',
        'custom_id': 'string',
        'extracted_upc': 'string',
        'extracted_upc_long': 'integer'
    }
}

lory_test_another = {
    'source': redshift_url_1,
    'query': 'SELECT video_id, custom_id, extracted_upc, extracted_upc_long from lory_test_another',
    'columns': {
        'video_id': 'string',
        'custom_id': 'string',
        'extracted_upc': 'string',
        'extracted_upc_long': 'integer'
    }
}

##################
# tests to perform
##################

tests = ['test_aggregate']

test_comparison = {
    'tables': ['lory_test', 'lory_test_another'],
    'columns': ['video_id']
}

test_aggregate = {
    'tables': ['lory_test', 'lory_test_another'],
    'columns': ['extracted_upc_long']
}