asc 파일을 m_id별로 분리하기

asc 파일을 CAN 메시지 아이디별로 분리 저장한다.¶

• 차에서 받은 CAN 트레이스에는 여러 메시지 아이디(m_id)들의 메시지들이 있다.
• m_id별 분석을 위해서 m_id별로 asc 파일을 만들어 메시지들을 저장한다.

In [1]:

from pathlib import Path
import pandas as pd

In [2]:

# 아래 asc 파일을 대상으로 한다.
path_to_data_asc = Path(r'C:\Users\haese\OneDrive\01_Projects\1_picode\05_tosun\30_기술\00_교육_자료\CySec\IDS\20240725_venue2024_07_26_09_17_29.asc')

# 현재 디렉토리 아래에 asc_per_id 디렉토리를 만든다. 
dir_output = Path('.').absolute()/'asc_per_id'
dir_output.mkdir(exist_ok=True)

In [3]:

def get_m_ids(input_file):
    '''
    input_file에 있는 CAN 메시지의 ID를 반환한다.
    claudi.ai가 작성한 filter_can_messages() 코드를 조금 수정하였다.
    '''
    
    m_ids = set() 
    with open(input_file, 'r') as infile:
        # Skip metadata
        for _ in range(4):
            line = infile.readline()

        # Process CAN messages
        for line in infile:
            parts = line.split()
            if len(parts) >= 3:
                m_id = parts[2]
                m_ids.add(m_id)

    return m_ids

In [7]:

# asc 파일에 있는 CAN 메시지 ID를 가져온다.
m_ids = get_m_ids(path_to_data_asc)
print(f'{len(m_ids) = :,}')
print(m_ids)

len(m_ids) = 59
{'549', '394', '111', '340', '044', '153', '4E6', '436', '200', '124', '316', '593', '502', '329', '541', '113', '545', '557', '5CF', '4A7', '492', '53E', '50C', '346', '080', '556', '34C', '4E7', '547', '483', '50E', '043', '38D', '500', '164', '5A0', '417', '042', '386', '4E5', '381', '251', '553', '112', '5B0', '5FA', '220', '2B0', '52A', '4F1', '280', '374', '383', '5CE', '260', '18F', '507', '081', '387'}

In [5]:

def filter_can_messages(input_file, output_file, filter_ids, filter_type):
    '''
    written by claude.ai
    Filter CAN messages based on message IDs
    '''
    with open(input_file, 'r') as infile, open(output_file, 'w') as outfile:
        # Write metadata
        for _ in range(4):
            line = infile.readline()
            outfile.write(line)
        
        # Process CAN messages
        for line in infile:
            parts = line.split()
            if len(parts) >= 3:
                m_id = parts[2]
                if filter_type == 'pass':
                    if m_id in filter_ids:
                        outfile.write(line)
                elif filter_type == 'stop':
                    if m_id not in filter_ids:
                        outfile.write(line)

In [6]:

for m_id in m_ids:
    output_file = dir_output/f'{m_id}.asc'
    print(f'Filtering {m_id} to {output_file.name}')
    filter_can_messages(path_to_data_asc, dir_output/f'{m_id}.asc', [m_id], 'pass')

Filtering 549 to 549.asc
Filtering 394 to 394.asc
Filtering 111 to 111.asc
Filtering 340 to 340.asc
Filtering 044 to 044.asc
Filtering 153 to 153.asc
Filtering 4E6 to 4E6.asc
Filtering 436 to 436.asc
Filtering 200 to 200.asc
Filtering 124 to 124.asc
Filtering 316 to 316.asc
Filtering 593 to 593.asc
Filtering 502 to 502.asc
Filtering 329 to 329.asc
Filtering 541 to 541.asc
Filtering 113 to 113.asc
Filtering 545 to 545.asc
Filtering 557 to 557.asc
Filtering 5CF to 5CF.asc
Filtering 4A7 to 4A7.asc
Filtering 492 to 492.asc
Filtering 53E to 53E.asc
Filtering 50C to 50C.asc
Filtering 346 to 346.asc
Filtering 080 to 080.asc
Filtering 556 to 556.asc
Filtering 34C to 34C.asc
Filtering 4E7 to 4E7.asc
Filtering 547 to 547.asc
Filtering 483 to 483.asc
Filtering 50E to 50E.asc
Filtering 043 to 043.asc
Filtering 38D to 38D.asc
Filtering 500 to 500.asc
Filtering 164 to 164.asc
Filtering 5A0 to 5A0.asc
Filtering 417 to 417.asc
Filtering 042 to 042.asc
Filtering 386 to 386.asc
Filtering 4E5 to 4E5.asc
Filtering 381 to 381.asc
Filtering 251 to 251.asc
Filtering 553 to 553.asc
Filtering 112 to 112.asc
Filtering 5B0 to 5B0.asc
Filtering 5FA to 5FA.asc
Filtering 220 to 220.asc
Filtering 2B0 to 2B0.asc
Filtering 52A to 52A.asc
Filtering 4F1 to 4F1.asc
Filtering 280 to 280.asc
Filtering 374 to 374.asc
Filtering 383 to 383.asc
Filtering 5CE to 5CE.asc
Filtering 260 to 260.asc
Filtering 18F to 18F.asc
Filtering 507 to 507.asc
Filtering 081 to 081.asc
Filtering 387 to 387.asc