MalGraph/samples/funCount.py

import json
import os
from itertools import islice
import heapq

from tqdm import tqdm

if __name__ == '__main__':
    mal_file_name = '/home/king/python/data/jsonl/infected_jsonl/'
    ben_file_name = '/home/king/python/data/jsonl/refind_jsonl/'
    fun_name_dict = {}
    for file in tqdm(os.listdir(mal_file_name)):
        with open(mal_file_name + file, 'r') as item:
            item = json.loads(item.readline())
            item_fun_list = item['function_names']
            for fun_name in item_fun_list:
                if fun_name != 'start' and fun_name != 'start_0' and 'sub_' not in fun_name:
                    if fun_name_dict.get(fun_name) is not None:
                        fun_name_dict[fun_name] += 1
                    else:
                        fun_name_dict[fun_name] = 1
    for file in tqdm(os.listdir(ben_file_name)):
        with open(ben_file_name + file, 'r') as item:
            item = json.loads(item.readline())
            item_fun_list = item['function_names']
            for fun_name in item_fun_list:
                if fun_name != 'start' and fun_name != 'start_0' and 'sub_' not in fun_name:
                    if fun_name_dict.get(fun_name) is not None:
                        fun_name_dict[fun_name] += 1
                    else:
                        fun_name_dict[fun_name] = 1
    with open('/home/king/python/data/processed_dataset/train_external_function_name_vocab.jsonl', 'w') as file:
        largest_10000_items = heapq.nlargest(10000, fun_name_dict.items(), key=lambda item: item[1])
        for key, value in largest_10000_items:
            temp = {"f_name": key, "count": value}
            file.write(json.dumps(temp) + '\n')