Kallol Das

18 papers B 2C 3Journal 4Unranked 8
YearRankTypeTitle / Venue / Authors
2025 B conf
PIMRC
Giacomo Mazzola, Sakshi Agarwal, Kallol Das, Remco Litjens, Haibin Zhang
2024 conf
EuCNC/6G Summit
Sakshi Agarwal, Kallol Das, Remco Litjens
2021 conf
VTC Spring
Sabari Nathan Anbalagan, Remco Litjens, Kallol Das, Alessandro Chiumento, Paul J. M. Havinga, Hans van den Berg
2021 J jnl
Int. J. Inf. Manag.
Linda D. Hollebeek, Kallol Das, Yupal Shukla
2020 conf
VTC Spring
Che-Wei Hsu, Kallol Das, Ljupco Jorguseski
2018 conf
WF-IoT
Eyuel Debebe Ayele, Kallol Das, Nirvana Meratnia, Paul J. M. Havinga
2017 J jnl
IEEE Internet Comput.
Kallol Das, Pouria Zand, Paul J. M. Havinga
2015 conf
ICIT
Kallol Das, Emi Mathews, Pouria Zand, Andrea Sanchez Ramirez, Paul J. M. Havinga
2015
Kallol Das
2014 C conf
ETFA
Pouria Zand, Kallol Das, Emi Mathews, Paul J. M. Havinga
2014 C conf
WoWMoM
Pouria Zand, Kallol Das, Emi Mathews, Paul J. M. Havinga
2014 C conf
WoWMoM
Pouria Zand, Emi Mathews, Kallol Das, Arta Dilo, Paul J. M. Havinga
2013 B conf
SECON
Kallol Das, Paul J. M. Havinga
2012 J jnl
IEEE J. Sel. Areas Commun.
Kallol Das, Henk Wymeersch
2012 conf
IOT
Kallol Das, Paul J. M. Havinga
2012 conf
VANET@MOBICOM
Ramon S. Schwartz, Kallol Das, Hans Scholten, Paul J. M. Havinga
2012 J jnl
J. Sens. Actuator Networks
Pouria Zand, Supriyo Chatterjea, Kallol Das, Paul J. M. Havinga
2011 conf
WPNC
Kallol Das, Henk Wymeersch
redb/extractor_registry.py
← Index redb/extractor_registry.py python
"""
Extractor registry with lazy loading by file type.

Groups extractors by file type (pe, elf, macho, apk) and only imports
the relevant group when that file type is first encountered. This avoids
loading heavy dependencies (pefile, lief, androguard, etc.) into workers
that don't need them.
"""
import importlib
import logging

logger = logging.getLogger(__name__)

# Registry: group name -> list of (module_path, class_names)
_REGISTRY = {
    "pe": [
        ("redb.extractors.pe_extractors", [
            "PEFeaturesExtractor",
            "PEImportExtractor",
            "PEResourceExtractor",
            "PEOverlayExtractor",
            "PESectionExtractor",
            "PESignatureExtractor",
            "PEExtraFindings",
            "PEInconstistencyTestsExtractor",
            "PEDotNetExtractor",
        ]),
    ],
    "elf": [
        ("redb.extractors.elf_extractors", [
            "ELFFeaturesExtractor",
            "ELFSegmentExtractor",
            "ELFSectionExtractor",
            "ELFDependencyExtractor",
            "ELFSymbolExtractor",
            "ELFImportExtractor",
            "ELFExportExtractor",
            "ELFRelocationExtractor",
            "ELFNotesExtractor",
        ]),
    ],
    "macho": [
        ("redb.extractors.macho_extractors", [
            "MachOFeaturesExtractor",
            "MachOSegmentExtractor",
            "MachOImportExtractor",
            "MachOExportExtractor",
            "MachODylibExtractor",
            "MachOSignatureExtractor",
        ]),
    ],
    "apk": [
        ("redb.extractors.apk_extractors", [
            "APKFeaturesExtractor",
            "APKManifestExtractor",
            "APKPermissionsExtractor",
            "APKSignatureExtractor",
            "APKDexExtractor",
            "APKResourceExtractor",
            "APKNativeLibExtractor",
            "APKInconsistencyTestsExtractor",
        ]),
        ("redb.extractors.decompiler.DecompileAPK", [
            "DecompileAPK",
        ]),
    ],
    "js": [
        ("redb.extractors.js_extractors", [
            "JSFeaturesExtractor",
            "JSSuspiciousAPIsExtractor",
            "JSStringsExtractor",
            "JSDeobfuscationExtractor",
            "JSContentExtractor",
        ]),
    ],
}

# Map filetype labels (from Magika) to registry group names
FILETYPE_TO_GROUP = {
    "pebin": "pe",
    "elf": "elf",
    "macho": "macho",
    "apk": "apk",
    "javascript": "js",
}

# Cache: group name -> {class_name: class}
_group_cache = {}


def _load_group(group_name):
    """Import all extractors for a group. Cached after first call."""
    if group_name in _group_cache:
        return _group_cache[group_name]

    logger.debug(f"Loading extractor group: {group_name}")

    # Suppress androguard logging before importing APK extractors
    if group_name == "apk":
        from loguru import logger as loguru_logger
        loguru_logger.disable("androguard")

    classes = {}
    for module_path, class_names in _REGISTRY[group_name]:
        mod = importlib.import_module(module_path)
        for name in class_names:
            classes[name] = getattr(mod, name)

    _group_cache[group_name] = classes
    return classes


def get_filetype_modules(filetype):
    """Get the list of format-specific extractor classes for a filetype.

    Returns only analysis extractors (excludes decompilers like DecompileAPK).
    """
    group = FILETYPE_TO_GROUP.get(filetype)
    if not group:
        return []
    classes = _load_group(group)
    return [cls for name, cls in classes.items() if not name.startswith("Decompile")]


def get_extractor_class(name):
    """Look up a single extractor class by name across all groups.

    Checks cached groups first, then loads groups on demand.
    """
    # Check already-loaded groups first
    for group_classes in _group_cache.values():
        if name in group_classes:
            return group_classes[name]

    # Search all groups (triggers lazy loading)
    for group_name in _REGISTRY:
        classes = _load_group(group_name)
        if name in classes:
            return classes[name]

    return None