import csv
import os

from integration_scripts import logger

from integration_scripts import s3_backoff_utils as s3_utils
from integration_scripts import db_utils
# from apocrypha.general_use import print_log

app_logger = logger.app_logger

bucket_name = 'pf-thumb-migrate'
path = 'INT-411_2'
folders = [
    'INT-394',
    'INT-395',
    'INT-396',
    'INT-397',
    'INT-397_2',
    'INT-398',
    'INT-402'
]

sql = """
    CREATE TABLE TEMP_SMEG_RITV_TABLE_2019_10_23 AS
    SELECT * FROM INTEGRATION.DEV.SMEG_RITV_VIEW;
"""


def main():
    master_log = list()
    duplicate_log = dict()
    master_file_count = 0
    master_found_count = 0
    # missing_count = 0
    # Convert view to table

    # Loop through
    for folder in folders:

        source_key_folder = s3_utils.get_s3_file_key(path, folder) + '/'

        # Get all keys
        file_list = s3_utils.filter_file_keys(source_key_folder, bucket_name)

        file_count = len(file_list)

        master_file_count += file_count

        if not file_list:
            msg = '{} has no files.'.format(folder)
            logger.info(msg)
            continue

        upc_list = [os.path.splitext(f)[0] for f in file_list]
        found_list = db_utils.get_ingestion_table_row_by_upc_list(upc_list)

        found_count = len(found_list)

        master_found_count += found_count

        if found_count != file_count:
            msg = '{}: Expected {} rows, retrieved {}.'.format(
                folder, file_count, found_count)
            logger.info(msg)

        for found in found_list:
            log_row = dict(
                upc='',
                file_name='',
                found=False)

            # Make log
            log_row['source_folder'] = folder
            log_row['file_name'] = str(found['upc']) + '.tif'
            # upc = os.path.splitext(found)[0]
            log_row['expected_folder'] = found['batch'][:7]
            log_row['upc'] = found['upc']

            if not duplicate_log.get('upc'):
                duplicate_log[found['upc']] = 1
            else:
                duplicate_log[found['upc']] += 1

            if log_row['expected_folder'] == log_row['source_folder']:
                msg = '{}: found in folder {}, as expected'.format(
                    log_row['file_name'], folder)
            else:
                msg = '{}: found in folder {}. EXPECTED: {}'.format(
                    log_row['file_name'], folder, found['batch'][:7])

            logger.info(msg)

            log_row['batch'] = found['batch']

            # msg = 'ERROR: {} not found in Tracking table!'.format(
            #     log_row['file_name'])
            # logger.info(msg)
            # missing_count += 1

            master_log.append(log_row)

    if not master_log:
        return

    logger.info('{} files expected.', master_file_count)
    logger.info('{} files found.', master_found_count)
    if master_file_count > master_found_count:
        diff = master_file_count - master_found_count
        logger.info('{} files missing.', diff)
    elif master_file_count < master_found_count:
        diff = master_found_count - master_file_count
        logger.info('{} duplicate files found.', diff)

    duplicate_log = {k: v for k, v in duplicate_log.items() if int(v) > 1}

    logger.info('Duplicates:')
    logger.info(duplicate_log)

    with open('s3_asset_validation_log.csv', 'w', newline='') as csvfile:
        fieldnames = master_log[0].keys()
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)

        writer.writeheader()

        for row in master_log:
            writer.writerow(row)


if __name__ == '__main__':
    main()