Ida Marie Schytt Lassen

12 papers Journal 4Unranked 8
YearRankTypeTitle / Venue / Authors
2025 J jnl
Big Data Soc.
Ida Marie Schytt Lassen, Jens Christian Bjerring, Kristoffer L. Nielbo
2024 conf
LREC/COLING
Yuri Bizzoni, Pascale Feldkamp Moreira, Ida Marie Schytt Lassen, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2024 J jnl
Digit. Scholarsh. Humanit.
Ida Marie Schytt Lassen, Ross Deans Kristensen-McLachlan, Mina Almasi, Kenneth C. Enevoldsen, Kristoffer L. Nielbo
2024 J jnl
CoRR
Yuri Bizzoni, Pascale Feldkamp Moreira, Ida Marie Schytt Lassen, Mia Jacobsen, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2024 conf
CHR
Ida Marie Schytt Lassen, Pascale Feldkamp Moreira, Yuri Bizzoni, Kristoffer L. Nielbo
2023 conf
NoDaLiDa
Yuri Bizzoni, Pascale Moreira, Nicole Dwenger, Ida Marie Schytt Lassen, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2023 conf
CHR
Ida Marie Schytt Lassen, Pascale Feldkamp Moreira, Yuri Bizzoni, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2023 conf
DH
Ida Marie Schytt Lassen, Yuri Bizzoni, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2022 conf
CHR
Yuri Bizzoni, Mads Rosendahl Thomsen, Ida Marie Schytt Lassen, Kristoffer L. Nielbo
2022 conf
NLPerspectives@LREC
Yuri Bizzoni, Ida Marie Schytt Lassen, Telma Peura, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2022 conf
CHR
Ida Marie Schytt Lassen, Yuri Bizzoni, Telma Peura, Mads Rosendahl Thomsen, Kristoffer L. Nielbo
2022 J jnl
CoRR
Ida Marie Schytt Lassen, Yuri Bizzoni, Telma Peura, Mads Rosendahl Thomsen, Kristoffer Laigaard Nielbo
redb/extractors/apk_extractor.py
← Index redb/extractors/apk_extractor.py python
import logging
import zipfile
from abc import ABCMeta, abstractmethod

from redb.extractors.extractor import Extractor

logger = logging.getLogger(__name__)


@abstractmethod
class APKExtractor(Extractor, metaclass=ABCMeta):

    def __init__(
        self,
        filepath,
        log,
        exporters=None,
        index_prefix=None,
        known_benign=False,
        known_malicious=False,
        apk=None,
    ):
        # Read binary data before calling super().__init__ so that the
        # binary property override is available during hash computation.
        with open(filepath, "rb") as f:
            self._binary_data = f.read()

        self.apk = apk if apk else self._generate_apk_object(filepath)

        super().__init__(
            filepath,
            log,
            exporters,
            index_prefix,
            known_benign=known_benign,
            known_malicious=known_malicious,
        )

    @property
    def binary(self):
        """Override to use already-read binary data."""
        return self._binary_data

    def _generate_apk_object(self, filepath):
        """Parse APK using androguard."""
        apk = None
        try:
            # Suppress verbose androguard loguru DEBUG/INFO output
            from loguru import logger as loguru_logger
            loguru_logger.disable("androguard")
            from androguard.core.apk import APK
            apk = APK(filepath)
            if not apk.is_valid_APK():
                logger.warning(
                    f"APK validation warning for {filepath}"
                )
                # Still return the object — partial parsing may still work
        except Exception as e:
            logger.error(
                f"Format error parsing APK {filepath}: {e}"
            )
        return apk

    def _is_valid_apk(self):
        """Check if the APK object was parsed successfully."""
        return self.apk is not None

    def _get_zip_file(self):
        """Get a zipfile.ZipFile handle for direct archive inspection."""
        try:
            return zipfile.ZipFile(self.filepath, 'r')
        except (zipfile.BadZipFile, Exception) as e:
            self.log.error(f"Failed to open APK as ZIP: {e}")
            return None

    def _list_files(self):
        """List all files in the APK archive."""
        if not self._is_valid_apk():
            return []
        try:
            return self.apk.get_files()
        except Exception as e:
            self.log.error(f"Error listing APK files: {e}")
            return []