Jai-Kyung Lee

16 papers A 1C 5Journal 4Unranked 6
YearRankTypeTitle / Venue / Authors
2023 J jnl
Sensors
Seungjin Yoo, Joon Ha Jung, Jai-Kyung Lee, Sang Woo Shin, Dal Sik Jang
2022 J jnl
CoRR
Seungin Oh, Hanmin Lee, Jai-Kyung Lee, Hyungchul Yoon, Jin-Gyun Kim
2009 conf
FGIT-ASEA
Jai-Kyung Lee, Seong-Whan Park, Moohyun Cha, Seung Hak Kuk, Hyeon Soo Kim
2008 J jnl
Comput. Ind.
Seung Hak Kuk, Hyeon Soo Kim, Jai-Kyung Lee, Seungho Han, Seong-Whan Park
2008 A conf
ICWS
Seung Hak Kuk, Hyeon Soo Kim, Jai-Kyung Lee, Seong-Whan Park
2008 conf
IEEE SCC (2)
Jai-Kyung Lee, Seung Hak Kuk, Hyeon Soo Kim, Seong-Whan Park
2007 conf
CSCWD (Selected Papers)
Jai-Kyung Lee, Seong-Whan Park, Hyeon Soo Kim, Seung Hak Kuk
2007 C conf
CSCWD
Seung Hak Kuk, Il Noh Oh, Hyeon Soo Kim, Jai-Kyung Lee, Seong-Whan Park
2007 C conf
CSCWD
Jai-Kyung Lee, Seong-Whan Park, Hyeon Soo Kim
2007 conf
IEEE SCC
Jai-Kyung Lee, Seung Hak Kuk, Hyeon Soo Kim, Seong-Whan Park
2006 C conf
CDVE
Hanmin Lee, Seong-Whan Park, Jai-Kyung Lee, Je-Sung Bang, Jaeho Lee
2006 J jnl
Comput. Ind.
Qi Hao, Weiming Shen, Zhan Zhang, Seong-Whan Park, Jai-Kyung Lee
2006 C conf
CDVE
Jai-Kyung Lee, Hyeon Soo Kim, Seung Hak Kuk, Seong-Whan Park
2005 conf
CSCWD (Selected papers)
Seong-Whan Park, Jai-Kyung Lee, Je-Sung Bang, Byung-Chun Shin
2005 conf
CSCWD (1)
Seong-Whan Park, Jai-Kyung Lee, Byung-Chun Shin
2004 C conf
IEA/AIE
Qi Hao, Weiming Shen, Seong-Whan Park, Jai-Kyung Lee, Zhan Zhang, Byung-Chun Shin
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