Hajime Ohiwa

17 papers A 1B 1Journal 2Unranked 13
YearRankTypeTitle / Venue / Authors
2008 conf
HCE3
Ken Okada, Manabu Sugiura, Yoshiaki Matsuzawa, Megumi Araki, Hajime Ohiwa
2007 B conf
ICALT
Yoshiaki Matsuzawa, Hajime Ohiwa
2006 conf
ITEM
Manabu Sugiura, Hajime Ohiwa
2005 conf
MSE
Ryuichi Takahashi, Hajime Ohiwa
2004 conf
C5
Yoshiaki Matsuzawa, Manabu Sugiura, Hajime Ohiwa
2004 conf
SAINT Workshops
Jun Murai, Yasuo Hibata, Kenji Kumasaka, Akira Maeda, Hajime Ohiwa, Nobuo Saito, Hiroshi Shimizu
2004 conf
History of Computing in Education
Hajime Ohiwa
2003 conf
C5
Hajime Ohiwa
2003 conf
SBCCI
Ryuichi Takahashi, Hajime Ohiwa
1999 conf
ICMCS, Vol. 2
Yoshihiro Ohmi, Kazuhisa Kawai, Hajime Ohiwa
1997 J jnl
Syst. Comput. Jpn.
Yoshihiro Ohmi, Naohiko Takeda, Kazuhisa Kawai, Hajime Ohiwa
1997 conf
Informatics in Higher Education
Hajime Ohiwa, Nobumasa Takahashi, Tsurayuki Kado
1997 J jnl
Knowl. Based Syst.
Hajime Ohiwa, Naohiko Takeda, Kazuhisa Kawai, Akichika Shiomi
1993 conf
HCI (2)
Hajime Ohiwa, Kazuhisa Kawai, Akichika Shiomi, Naohiko Takeda
1993 conf
HCI (2)
Naohiko Takeda, Akichika Shiomi, Kazuhisa Kawai, Hajime Ohiwa
1993 A conf
RE
Naohiko Takeda, Akichika Shiomi, Kazuhisa Kawai, Hajime Ohiwa
1992 conf
VL
Naohiko Takeda, Kazuhisa Kawai, Masanobu Koyama, Akichika Shiomi, Hajime Ohiwa
redb/extractors/macho_extractors/macho_exports.py
← Index redb/extractors/macho_extractors/macho_exports.py python
import inspect
from datetime import datetime, timezone
from typing import Any

from redb.extractors.enum import Tag
from redb.extractors.macho_extractor import MachOExtractor
from redb.models.dataclasses import MachOExport


class MachOExportExtractor(MachOExtractor):

    def __init__(
        self,
        filepath,
        log,
        exporters=None,
        index_prefix=None,
        elastic_index=None,
        known_benign=False,
        known_malicious=False,
        macho=None,
    ):
        super().__init__(
            filepath,
            log,
            exporters,
            index_prefix,
            elastic_index,
            known_benign,
            known_malicious,
            macho,
        )
        self.elastic_index = self.index_prefix + "-macho_exports"
        self.log.debug(inspect.currentframe().f_code.co_name)

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

    def _extract_exports(self, arch_name=None):
        """Extract export information from the MachO binary for a specific architecture."""
        self.log.debug(inspect.currentframe().f_code.co_name)

        if not self.macho:
            return None

        try:
            # Get exported symbols using new API for specific architecture
            exported_symbols = self.macho.get_exported_symbols(arch=arch_name)

            # Extract all exported symbols (may be empty for some binaries)
            # Handle None or empty dict
            if not exported_symbols:
                exported_symbols = {}
            all_symbols = []
            for dylib_name, symbols in exported_symbols.items():
                # Process symbol names
                for symbol in symbols:
                    if isinstance(symbol, bytes):
                        symbol = symbol.decode('utf-8', errors='replace')
                    all_symbols.append(symbol)

            # Create export dataclass
            macho_export = MachOExport(
                macho_exports_total=len(all_symbols),
                macho_export_symbols=all_symbols  # Empty list is fine, but None is not allowed for Array type
            )

            return macho_export

        except Exception as e:
            self.log.error(f"Error extracting MachO exports for arch {arch_name}: {e}")
            return None

    def extract(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            # Get architectures (macho is already parsed in base class)
            architectures = self.macho.get_architectures()
            if len(architectures) > 1:
                # FAT binary - return list of exports for each architecture
                results = []
                for arch_name in architectures:
                    exports = self._extract_exports(arch_name)
                    if exports:
                        exports.arch_identifier = arch_name
                        results.append(exports)
                return results
            else:
                # Single architecture - return single result
                return self._extract_exports(architectures[0] if architectures else None)
        except Exception as e:
            self.log.error(f"Error extracting MachO exports: {e}")
            return None

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

            # Get architectures (macho is already parsed in base class)
            try:
                architectures = self.macho.get_architectures()
                is_fat = len(architectures) > 1
            except Exception as e:
                self.log.error(f"Could not get architectures: {e}")
                return None

            data = []
            current_time = datetime.now(timezone.utc)

            # Loop through each architecture (1 for single, multiple for FAT)
            for arch_name in architectures:
                # Get architecture-specific sha256
                try:
                    arch_general_info = self.macho.get_general_info(arch=arch_name)
                    arch_header_raw = self.macho.get_macho_header(arch=arch_name)
                    arch_sha256 = arch_general_info.get('SHA256', self.sha256)
                    arch_cputype_raw = arch_header_raw.get('cputype', 0) if arch_header_raw else 0
                except Exception as e:
                    self.log.warning(f"Could not get arch-specific data for {arch_name}: {e}")
                    arch_sha256 = self.sha256
                    arch_cputype_raw = 0

                # Get exports for this architecture
                macho_export = self._extract_exports(arch_name)
                if not macho_export:
                    continue

                data.append([
                    arch_sha256,                          # sha256 (arch-specific)
                    macho_export.macho_exports_total,     # macho_exports_total
                    macho_export.macho_export_symbols,    # macho_export_symbols (keep as array!)
                    current_time,                         # analysis_date
                ])

            column_names = [
                'sha256',
                'macho_exports_total', 'macho_export_symbols',
                'analysis_date'
            ]

            if not data:
                return None

            column_type_names = [
                'FixedString(64)',
                'UInt32', 'Array(Nullable(String))',
                'DateTime64(3, \'UTC\')'
            ]

            return (data, column_names, column_type_names)

        return None

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