Kaifei He

import fnmatch
import hashlib
import inspect
from datetime import datetime, timezone
from typing import Any

from redb.extractors.enum import Tag
from redb.extractors.apk_extractor import APKExtractor
from redb.models.dataclasses import APKNativeLib

# Known packer/protector native library names
KNOWN_PACKER_LIBS = {
    # Jiagu (360/Qihoo)
    "libjiagu.so", "libjiagu_a64.so", "libjiagu_x86.so", "libjiagu_x64.so",
    # Bangcle/SecNeo
    "libsecexe.so", "libsecmain.so", "libSecShell.so",
    # Baidu
    "libbaiduprotect.so",
    # Tencent (Legu)
    "libtxAppProtect.so", "libBugly.so",
    # iJiami
    "libexec.so", "libexecmain.so",
    # Alibaba
    "libmobisec.so", "libaliprotect.so",
    # APKProtect
    "libAPKProtect.so",
    # Pangxie (Pangolin)
    "libdexjni.so",
    # DexProtector
    "libdexprotector.so",
    # AppSolid
    "libAppSolid.so",
    # Kiwisec
    "libkwscmm.so",
    # DingXiang
    "libx3g.so",
    # NQ Shield
    "libnqshield.so",
    # Generic / other
    "libprotectClass.so",
    "libDexHelper.so",
    "libdexloader.so",
    "libfdog.so",
}

# Glob-style patterns for packer libs (e.g. libshella-*.so)
KNOWN_PACKER_PATTERNS = [
    "libshella-*.so",
    "libshell-super.*.so",
]


def is_known_packer_lib(filename):
    """Check if a native library filename matches known packer signatures."""
    if filename in KNOWN_PACKER_LIBS:
        return True
    for pattern in KNOWN_PACKER_PATTERNS:
        if fnmatch.fnmatch(filename, pattern):
            return True
    return False


class APKNativeLibExtractor(APKExtractor):

    def __init__(
        self, filepath, log, exporters=None, index_prefix=None,
        known_benign=False, known_malicious=False,
        apk=None,
    ):
        super().__init__(
            filepath, log, exporters, index_prefix,
            known_benign, known_malicious, apk,
        )
        self.native_libs = []
        self.abis = set()
        self.log.debug(inspect.currentframe().f_code.co_name)

    def tag(self):
        return Tag.APK_NATIVE_LIBS.value

    def extract(self):
        if not self._is_valid_apk():
            self.log.error(f"Invalid APK for {self.hash.sha256}")
            return None

        self.native_libs = []
        self.abis = set()

        zf = self._get_zip_file()
        if not zf:
            return None

        with zf:
            for info in zf.infolist():
                if not (info.filename.startswith("lib/") and info.filename.endswith(".so")):
                    continue
                parts = info.filename.split("/")
                if len(parts) < 3:
                    continue

                abi = parts[1]
                filename = parts[-1]
                self.abis.add(abi)

                try:
                    data = zf.read(info.filename)
                    lib_sha256 = hashlib.sha256(data).hexdigest()
                except Exception as e:
                    self.log.warning(f"Error reading native lib {info.filename}: {e}")
                    continue

                self.native_libs.append(APKNativeLib(
                    abi=abi,
                    filename=filename,
                    size=info.file_size,
                    sha256=lib_sha256,
                    is_known_packer=is_known_packer_lib(filename),
                ))

        if not self.native_libs:
            return None

        return {
            "native_lib_count": len(self.native_libs),
            "abis": sorted(self.abis),
            "native_libs": self.native_libs,
            "known_packer_libs": [
                lib for lib in self.native_libs if lib.is_known_packer
            ],
        }

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ClickHouseExporter":
            if not self.native_libs:
                return None

            current_time = datetime.now(timezone.utc)
            data = []
            for lib in self.native_libs:
                data.append([
                    self.sha256,
                    lib.abi,
                    lib.filename,
                    lib.size,
                    lib.sha256,
                    int(lib.is_known_packer),
                    current_time,
                ])

            column_names = [
                'sha256', 'lib_abi', 'lib_filename', 'lib_size',
                'lib_sha256', 'lib_is_known_packer', 'analysis_date',
            ]

            column_type_names = [
                'FixedString(64)', 'LowCardinality(String)', 'String', 'UInt64',
                'FixedString(64)', 'UInt8', "DateTime64(3, 'UTC')",
            ]

            return (data, column_names, column_type_names)

    def get_clickhouse_table(self) -> str:
        return "redb_apk_native_libs"