INNER CODE UNIT · Python

extract_strings

2akouwu/reverify · reverify/cli.py:66

def extract_strings(data: bytes, min_len: int = 4) -> List[Dict[str, Any]]:
    """Extract ASCII and UTF-16LE strings with file offsets."""
    results = []
    # ASCII strings
    ascii_re = re.compile(rb"[\x20-\x7e]{" + str(min_len).encode() + rb",}")
    for m in ascii_re.finditer(data):
        results.append({
            "offset": hex(m.start()),
            "type": "ASCII",
            "string": m.group().decode("latin1", errors="ignore"),
        })
    # Unicode (UTF-16LE) strings
    uni_re = re.compile(rb"(?:[\x20-\x7e]\x00){" + str(min_len).encode() + rb",}")
    for m in uni_re.finditer(data):
        try:
            s = m.group().decode("utf-16le", errors="ignore")
            results.append({
                "offset": hex(m.start()),

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…