# iterate files over subdirectories in `00_store`, store image files in hash table, delete files with same hash

import os
import hashlib


def check_same_image(file_path):
    sha256_hash = hashlib.sha256()
    with open(file_path, "rb") as f:
        for byte_block in iter(lambda: f.read(8192), b""):
            sha256_hash.update(byte_block)
    return sha256_hash.hexdigest()


def action(in_path):
    img_hash = {}
    for root, _, files in os.walk(in_path):
        for file in files:
            file_path = os.path.join(root, file)
            md5 = check_same_image(file_path)
            if md5 in img_hash:
                os.remove(file_path)
                print(file_path, "found")

            else:
                img_hash[md5] = file_path


action("/home/logic/_workspace/task-list/servers/logic-NUC8i5BEH/opencv-workdesk/001_monitor/src/003-crawler-mountain/output")
action("/home/logic/_workspace/task-list/servers/logic-NUC8i5BEH/opencv-workdesk/001_monitor/src/003-crawler-mountain/output_mountain")