"""Kuwo Data Ingestion Workflow."""

from datetime import datetime

from garcon import task
from garcon_contrib.dynamo_feed_status import garcon_feed_status

from feed_ingestion.flows.kuwo import config

STOP_RESPONSE = {'stop': True}


@task.decorate(timeout=1000)
def bootstrap(activity, date, licensor=None, reload=None,
              skip_corrupted_rows=None, dw_config=None):
    """Bootstrap workflow by getting the correct configurations.

    Args:
        activity (ActivityWorker): The Garcon activity worker.
        date (str): Reporting date (YYYY-MM-DD).
        licensor (str): The licensor to ingest.
    Returns:
        dict: Context.
    """
    feed_name = '_'.join([config.feed_name, licensor])

    date_obj = date or datetime.today().strftime('%Y-%m-%d')

    activity.logger.info(
        'Bootstrapping {feed_name} for {date}'.format(
            feed_name=feed_name, date=date_obj))

    replace_archive_files = True

    if reload == 'True':
        activity.logger.info(
            'Delete status for feed: {} {} '.format(feed_name, date_obj))
        garcon_feed_status.delete_status(feed_name, date_obj)
    else:
        overall_status = garcon_feed_status.get_overall_status(
            feed_name, date)
        if overall_status == garcon_feed_status.STATUS_INGESTED:
            return STOP_RESPONSE

    drop_path = config.s3['drop'][licensor]
    archive_path = config.s3['archive'][licensor].format(date=date_obj)
    s3_full_path = 's3://{data_bucket}/'.format(
        data_bucket=config.data_bucket) + archive_path

    # Select file name/format version by reporting date. The matching
    # staging_raw COPY version is resolved separately by SQLLoader via the
    # queries/<date>/ sub folder, using the same date keys as config.formats.
    file_format = config.format_for(date_obj)
    filename_template = file_format['filename']
    licensor_names = file_format['licensors'][licensor]
    source_file_pattern = file_format['source_file_pattern'][licensor]

    # array to store files to download
    expected_files = []
    licensor_files = licensor_names.split(',')
    for licensor_file in licensor_files:
        filename = filename_template.format(
            date=datetime.strptime(date_obj, '%Y-%m-%d'),
            licensor_filename=licensor_file)
        expected_files.append(filename)

    staging_raw_table = config.snowflake_table_names['staging_raw']

    corrupted_rows_error = skip_corrupted_rows or 'False'

    return dict(
        feed_name=feed_name,
        date=date_obj,
        licensor=licensor,
        store_id=config.storeid,
        s3_bucket=config.data_bucket,
        drop_path=drop_path,
        archive_path=archive_path,
        s3_full_path=s3_full_path,
        source_file_pattern=source_file_pattern,
        skip_corrupted_rows=corrupted_rows_error,
        expected_files=expected_files,
        secrets_path=config.secrets_path,
        staging_raw_table=staging_raw_table,
        replace_archive_files=replace_archive_files
    )