Olga Fajarda

14 papers B 1Journal 4Unranked 9
YearRankTypeTitle / Venue / Authors
2023 conf
EPIA (1)
Richard Adolph Aires Jonker, Roshan Poudel, Olga Fajarda, José Luís Oliveira, Rui Pedro Lopes, Sérgio Matos
2023 J jnl
Comput. Biol. Medicine
Olga Fajarda, João Rafael Almeida, Sara Duarte-Pereira, Raquel M. Silva, José Luís Oliveira
2022 conf
ADBIS (Short Papers)
Alina Yanchuk, Alina Trifan, Olga Fajarda, José Luís Oliveira
2022 conf
SMM4H@COLING
Edgar Morais, José Luís Oliveira, Alina Trifan, Olga Fajarda
2022 J jnl
Oper. Res.
Olga Fajarda, Cristina Requejo
2022 B conf
ASONAM
Richard Adolph Aires Jonker, Roshan Poudel, Olga Fajarda, Sérgio Matos, José Luís Oliveira, Rui Pedro Lopes
2020 conf
HEALTHINF
João Rafael Almeida, Pedro Freire, Olga Fajarda, José Luís Oliveira
2020 conf
CLEF
João Rafael Almeida, Olga Fajarda, José Luís Oliveira
2020 J jnl
SoftwareX
João Rafael Almeida, Armando J. Pinho, José Luís Oliveira, Olga Fajarda, Diogo Pratas
2020 J jnl
BioData Min.
Olga Fajarda, Sara Duarte-Pereira, Raquel M. Silva, José Luís Oliveira
2019 conf
CLEF (Working Notes)
João Rafael Almeida, Pedro Freire, Olga Fajarda, José Luís Oliveira
2019 conf
HEALTHINF
João Rafael Almeida, Olga Fajarda, Arnaldo Pereira, José Luís Oliveira
2018 conf
HEALTHINF
Olga Fajarda, Luís A. Bastião Silva, Peter R. Rijnbeek, Michel Van Speybroeck, José Luís Oliveira
2018 conf
BIOSTEC (Selected Papers)
Olga Fajarda, Alina Trifan, Michel Van Speybroeck, Peter R. Rijnbeek, José Luís Oliveira
redb/extractors/detectiteasy.py
← Index redb/extractors/detectiteasy.py python
import inspect
from pprint import pprint
import subprocess
import json
from typing import Any
from datetime import datetime, timezone
import os
from dotenv import load_dotenv

from redb.extractors.enum import Tag
from redb.models.dataclasses import DIEinfo
from redb.extractors.extractor import Extractor

load_dotenv(override=True)

class DIEExtractor(Extractor):

    def __init__(
        self,
        filepath,
        log,
        exporters=None,
        index_prefix=None,
        elastic_index=None,
        known_benign=False,
        known_malicious=False,
        precomputed_hashes=None,
    ):
        super().__init__(
            filepath, log, exporters, index_prefix, elastic_index, known_benign, known_malicious,
            precomputed_hashes=precomputed_hashes
        )
        self.log.debug(inspect.currentframe().f_code.co_name)
        self.die_info = None
        self.die_info_dict = {}
        self.elastic_index = self.index_prefix + "-die"

    def _recursive_entry(self, die_dict, master_key):
        self.log.debug(inspect.currentframe().f_code.co_name)
        if master_key:
            self.die_info_dict[master_key] = {}
        else:
            self.die_info_dict = {}
        for value in die_dict:
            if "type" in value:
                type_key = value["type"].lower().replace(" ", "_")
                name = value.get("name", "")
                version = f"({value.get('version')})" if value.get("version") else ""
                info = f"[{value.get('info')}]" if value.get("info") else ""

                if master_key:
                    self.die_info_dict[master_key][type_key] = f"{name}"
                    self.die_info_dict[master_key][f'{type_key}(full)'] = f"{name}{version}{info}"
                else:
                    self.die_info_dict[type_key] = f"{name}"
                    self.die_info_dict[f'{type_key}(full)'] = f"{name}{version}{info}"

            elif "parentfilepart" in value:
                child_key = (
                    value["parentfilepart"].lower().replace(" ", "_")
                    + "."
                    + value["filetype"].lower().replace(" ", "_")
                )
                if master_key:
                    self._recursive_entry(value["values"], f"{master_key}.{child_key}")
                else:
                    self._recursive_entry(value["values"], f"{child_key}")

    def _extract_dieinfo(self):
        """
        Execute a command-line binary with arguments and parse its JSON output.

        :param command: The command or path to the binary to execute
        :param args: Additional arguments to pass to the command
        :return: Parsed JSON output as a Python object
        """
        self.log.debug(inspect.currentframe().f_code.co_name)

        # Construct the full command
        # command = "nfdc" # UNCOMMENT FOR PROD
        # command = "/Users/p4c0/_tools/NFD.app/Contents/MacOS/nfdc" # COMMENT FOR TESTING ON MAC
        command = os.getenv("DIE_PATH")
        args = ["-durj", self.filepath]
        full_command = [command] + list(args)
        TIMEOUT = int(os.getenv("DIE_TIMEOUT", "180"))

        try:
            # Execute the command and capture its output
            result = subprocess.run(
                full_command,
                capture_output=True,
                text=True,
                check=True,
                timeout=TIMEOUT,
            )

            # Parse the JSON output
            nfdc_output = json.loads(result.stdout)

            # Extract the DIE information from the json output
            for die_entry in nfdc_output["detects"]:
                if die_entry["parentfilepart"] == "Header":
                    master_key = (
                        die_entry["parentfilepart"].lower().replace(" ", "_")
                        + "."
                        + die_entry["filetype"].lower().replace(" ", "_")
                    )
                    self._recursive_entry(die_entry["values"], None)

            # pprint(json.dumps(self.die_info_dict, indent=2)) #debug
            self.die_info = DIEinfo(result.stdout, self.die_info_dict)
            self.log.debug(f"NFDC-DIE JSON dump: todo")
        except subprocess.TimeoutExpired:
            self.log.error(f"The DIE command timed out after {TIMEOUT} seconds")
            return None
        except subprocess.CalledProcessError as e:
            self.log.error(f"Error executing DIE command: {e}")
            self.log.error(f"Command output (stderr): {e.stderr}")
            return None
        except json.JSONDecodeError as e:
            self.log.error(f"Error parsing DIE JSON output: {e}")
            self.log.error(f"Raw output: {result.stdout}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.die_info
        elif exporter_type == "ClickHouseExporter":
            # Convert DIE info to JSON string
            die_info_json = json.dumps(self.die_info_dict)
            
            data = [[
                self.sha256,
                self.md5,
                self.sha1,
                die_info_json,
                datetime.now(timezone.utc)
            ]]
            
            column_names = [
                'sha256', 'md5', 'sha1', 'die_info', 'analysis_date'
            ]
            
            column_type_names = [
                'String', 'String', 'String', 'JSON', 'DateTime64(3, \'UTC\')'
            ]
            
            return (data, column_names, column_type_names)

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

    def extract(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            self._extract_dieinfo()
            
            # Check if there's a packer in the DIE results
            is_packed = False
            if self.die_info_dict:
                # Check if 'packer' exists in the DIE results
                is_packed = bool(self.die_info_dict.get('packer'))
            
            return self.die_info  # Return the extracted data instead of exporting directly
        except Exception as e:
            self.log.error(f"Error extracting DIE information: {e}")
            return None

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