Neil Chueh-An Lee

16 papers Journal 9Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Inf. Manag.
Gloria Hui Wen Liu, Cecil Eng Huang Chua, Neil Chueh-An Lee, Jenny Hua-Jen Wu
2024 J jnl
IEEE Trans. Engineering Management
Neil Chueh-An Lee, Gloria Hui Wen Liu
2023 J jnl
Inf. Technol. People
Cheng-Kui Huang, Neil Chueh-An Lee, Wen-Chi Chen
2023 J jnl
Pac. Asia J. Assoc. Inf. Syst.
Gloria Hui Wen Liu, Cecil Chua, Neil Chueh-An Lee
2022 conf
PACIS
Neil Chueh-An Lee, Gloria H. W. Liu
2022 J jnl
ACM SIGMIS Database
Neil Chueh-An Lee, Eric T. G. Wang, Varun Grover
2021 conf
HICSS
Gloria H. W. Liu, Mengdi Sun, Neil Chueh-An Lee
2021 J jnl
Inf.
Hota Chia-Sheng Lin, Neil Chueh-An Lee, Yi-Chieh Lu
2020 J jnl
J. Strateg. Inf. Syst.
Neil Chueh-An Lee, Eric T. G. Wang, Varun Grover
2019 conf
PACIS
Cheng Hui Wang, Gloria H. W. Liu, Neil Chueh-An Lee, Kuang-Jung Chen
2014 J jnl
Inf. Manag.
Eric T. G. Wang, Frank K. Y. Chou, Neil Chueh-An Lee, S. Z. Lai
2014 conf
PACIS
Neil Chueh-An Lee, Eric T. G. Wang, Jeffrey C. F. Tai
2013 conf
PACIS
Neil Chueh-An Lee, Eric T. G. Wang
2013 conf
ECIS
Chi-Feng Tai, Eric T. G. Wang, Neil Chueh-An Lee
2013 J jnl
Ind. Manag. Data Syst.
Eric T. G. Wang, Neil Chueh-An Lee
2012 conf
PACIS
Eric T. G. Wang, Neil Chueh-An Lee
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