"""Step 1 of Image Asset Migration from S3 Bucket to S3 Bucket.

Command line script to identify all images in an S3 bucket and write batch files for further processing.

Example Usage:

$ python create_batch_keys_script.py
"""

# !/usr/bin/env python
# -*- coding: utf-8 -*-

import argparse
import datetime
import hashlib
import logging
import os
from os.path import dirname
from os.path import join
import re
import sys
import time
import uuid

import boto3
from dotenv import load_dotenv
import requests


dotenv_path = join(dirname(__file__), '.env')
load_dotenv(dotenv_path)

OWS_PRODUCT_URL = os.environ.get('OWS_PRODUCT_URL')
SOURCE_BUCKET_NAME = os.environ.get('SOURCE_BUCKET_NAME')
SOURCE_SUB_FOLDER = os.environ.get('SOURCE_SUB_FOLDER')


def step_through_images_from_s3_bucket_and_create_batch_files(
        source_bucket, source_bucket_name, source_sub_folder,
        batch_size, max_objects):
    """Loop through objects in an AWS S3 bucket and create batch files for further processing.

    Args:
        source_bucket (class): AWS S3 Bucket to copy objects from
        source_bucket_name (str): name of source bucket
        source_sub_folder (str): name of folder to search within
        batch_size (int): number of lines in a batch file
        max_objects (int): number of objects to copy

    """
    start_time = time.time()
    count = 0
    batch_count = 0
    file_count = 1
    file_prefix = 'image-asset-migration-batch-key-'
    correlation_id = str(uuid.uuid4())
    logging.warning('Date of execution: {}'.format(datetime.datetime.now()))
    logging.warning('Now running migration with Correlation-Id: {}'.format(
        correlation_id))
    f = open(file_prefix + str(file_count), 'w')
    for s3_object in source_bucket.objects.filter(Prefix=source_sub_folder):
        # Look for S3 objects that end with .jpg or .jpeg
        file_match = re.search('[^\/]*\..+$', s3_object.key, re.IGNORECASE)
        if file_match:
            filename = file_match.group(0)
            file_extension = re.search('\..+$', filename).group(0)
            upc = re.search('\d+', filename).group(0)
            file_line = '{bucket},{key},{upc},{file_extension},{correlation_id}'.format(
                bucket=source_bucket_name,
                key=s3_object.key,
                upc=upc,
                file_extension=file_extension,
                correlation_id=correlation_id)
            f.write(file_line + os.linesep)
            count += 1
            batch_count += 1
            if batch_count == batch_size:
                f.close()
                file_count += 1
                batch_count = 0
                f = open(file_prefix + str(file_count), 'w')
            if count == max_objects:
                break
            

    run_time = time.time() - start_time
    logging.warning('wrote {} batch files in {} seconds'.format(file_count, run_time))
    sys.exit(0)


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument(
        'batch_size', nargs='?', default=1000, type=int,
        help='the max size of the batch files to be written')
    parser.add_argument(
        'max_objects', nargs='?', default=10000, type=int,
        help='the max number of objects copied')
    args = parser.parse_args()
    s3 = boto3.resource('s3')
    source_bucket = s3.Bucket(SOURCE_BUCKET_NAME)
    logging.basicConfig(
        filename='create_batch_keys.log', level=logging.WARNING)
    step_through_images_from_s3_bucket_and_create_batch_files(
        source_bucket, SOURCE_BUCKET_NAME, SOURCE_SUB_FOLDER,
        args.batch_size, args.max_objects)