James Bradbury

18 papers A* 1Journal 9Unranked 8
YearRankTypeTitle / Venue / Authors
2020 J jnl
CoRR
Kazuma Hashimoto, Raffaella Buschiazzo, James Bradbury, Teresa Marshall, Richard Socher, Caiming Xiong
2019 conf
WMT (1)
Kazuma Hashimoto, Raffaella Buschiazzo, James Bradbury, Teresa Marshall, Richard Socher, Caiming Xiong
2018 conf
ICLR (Workshop)
Martin Schrimpf, Stephen Merity, James Bradbury, Richard Socher
2018 conf
ICLR (Poster)
Jiatao Gu, James Bradbury, Caiming Xiong, Victor O. K. Li, Richard Socher
2017 J jnl
CoRR
Martin Schrimpf, Stephen Merity, James Bradbury, Richard Socher
2017 J jnl
CoRR
Huishuai Zhang, Caiming Xiong, James Bradbury, Richard Socher
2017 conf
NIPS
Bryan McCann, James Bradbury, Caiming Xiong, Richard Socher
2017 J jnl
CoRR
Bryan McCann, James Bradbury, Caiming Xiong, Richard Socher
2017 J jnl
CoRR
Jiatao Gu, James Bradbury, Caiming Xiong, Victor O. K. Li, Richard Socher
2017 conf
ICLR (Poster)
Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher
2017 conf
ICLR (Poster)
James Bradbury, Stephen Merity, Caiming Xiong, Richard Socher
2017 conf
SPNLP@EMNLP
James Bradbury, Richard Socher
2017 J jnl
CoRR
James Bradbury, Richard Socher
2016 A* conf
ICML
Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher
2016 conf
WMT
James Bradbury, Richard Socher
2016 J jnl
CoRR
Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher
2016 J jnl
CoRR
James Bradbury, Stephen Merity, Caiming Xiong, Richard Socher
2015 J jnl
CoRR
Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher
redb/utils/sort_files_by_type.py
← Index redb/utils/sort_files_by_type.py python
import os
import sys
from collections import defaultdict
import tempfile
from magika import Magika
import py7zr
import pyzipper
import shutil

"""
This script is used to sort files by their type. 
It reads all the files in the provided directory and splits them into different 
directories based on their type. Mainly, it classifies the files into the following types:
- PE Binaries
- Mach-O Binaries
- ELF Binaries
- APK 
- Other Files

It outputs the count of files for each file extension and file type.

Command line example:
nohup python3 sort_files_by_type.py /mnt/samples/consilience/malware/vx-bazaar-expanded/Bazaar.2020.12 \
    /mnt/samples/consilience/malware/_sorted_samples/vx-bazaar/2020/ > \
    /mnt/samples/consilience/malware/ops-logs/20241014-SORT_FILES-bazaar_2020.12.output.log 2>&1 &
"""


def process_zip_file(filepath):
    print(f"[INFO] - Processing zip file: {filepath}")
    with tempfile.TemporaryDirectory() as temp_dir:
        try:
            with pyzipper.AESZipFile(filepath) as zf:
                zf.pwd = b"infected"
                filename = zf.namelist()[0]
                zf.extractall(temp_dir)
                extracted_zip_path = os.path.join(temp_dir, filename)
                return process_binary_file(extracted_zip_path)
        except Exception as e:
            print(f"[ERR] - Error processing zip file {filepath}: {str(e)}")
            return None


def process_7z_file(filepath):
    print(f"[INFO] - Processing 7z file: {filepath}")
    with tempfile.TemporaryDirectory() as temp_dir:
        try:
            with py7zr.SevenZipFile(filepath, mode="r", password="infected") as z:
                z.extractall(path=temp_dir)
                for root, _, files in os.walk(temp_dir):
                    for file in files:
                        extracted_file_path = os.path.join(root, file)
                        return process_binary_file(extracted_file_path)
        except Exception as e:
            print(f"[ERR] - Error processing 7z file {filepath}: {str(e)}")
            return None


def process_binary_file(filepath):
    print(f"[INFO] - Processing binary file: {filepath}")
    try:
        with open(filepath, "rb") as f:
            data = f.read(512 * 1024)  # 512KB
        return Magika().identify_bytes(data).output.ct_label
    except Exception as e:
        print(f"[ERR] - Error processing binary file {filepath}: {str(e)}")
        return "ERROR"


def count_file_extensions(path, dest_dir):
    # A defaultdict to store file extension counts
    extension_count = defaultdict(int)
    filetype_count = defaultdict(int)
    tot_files = 0

    # Walk through the directory
    for root, dirs, files in os.walk(path):
        for file in files:
            if file.startswith("."):
                continue

            tot_files += 1
            # Split the file extension from the file name
            _, ext = os.path.splitext(file)
            ext = ext.lower()

            # Count the extensions
            extension_count[ext] += 1
            filepath = os.path.join(root, file)
            filetype = ""

            if ext == ".7z":
                filetype = process_7z_file(filepath)
            elif ext == ".zip":
                filetype = process_zip_file(filepath)
            else:
                filetype = process_binary_file(filepath)

            filetype_count[filetype] += 1

            if filetype == "pebin":
                dest = os.path.join(dest_dir, "pebin")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            elif filetype == "macho":
                dest = os.path.join(dest_dir, "macho")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            elif filetype == "elf":
                dest = os.path.join(dest_dir, "elf")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            elif filetype == "apk":
                dest = os.path.join(dest_dir, "apk")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            else:
                dest = os.path.join(dest_dir, "other")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            print(f"[STATUS] - Progres: {tot_files}/{len(files)} files processed")

    # Print the results
    # print("- File Extension Statistics:")
    # for ext, count in extension_count.items():
    #     if ext:  # To exclude files with no extension
    #         print(f"\t{ext}: {count} files")

    # if "" in extension_count:
    #     print(f'\t{extension_count[""]} files with no extension')

    print(f"- Total Number of Files: {tot_files}")
    print("\n- File Type Statistics:")
    for filetype, count in sorted(filetype_count.items()):
        print(f"\t{filetype:<15}{count:>8}")


if __name__ == "__main__":
    # Check if the path was passed as a command-line argument
    if len(sys.argv) != 3:
        print("Usage: python3 script.py <input_path> <dest_dir>")
        sys.exit(1)

    # Get the path from the command-line arguments
    input_path = sys.argv[1]
    dest_dir = sys.argv[2]

    # Check if the provided path is valid
    if not os.path.isdir(input_path):
        print(f"The path '{input_path}' is not a valid directory.")
        sys.exit(1)

    # Call the function to count file extensions
    count_file_extensions(input_path, dest_dir)