R. J. J. H. van Son

34 papers A 11B 1C 1Journal 7Unranked 13
YearRankTypeTitle / Venue / Authors
2023 C conf
ASRU
Bence Mark Halpern, Wen-Chin Huang, Lester Phillip Violeta, R. J. J. H. van Son, Tomoki Toda
2023 J jnl
CoRR
Bence Mark Halpern, Wen-Chin Huang, Lester Phillip Violeta, R. J. J. H. van Son, Tomoki Toda
2019 A conf
INTERSPEECH
Kicky G. van Leeuwen, Paula Bos, Stefano Trebeschi, Maarten J. A. van Alphen, Luuk Voskuilen, Ludi E. Smeele, Ferdi van der Heijden, R. J. J. H. van Son
2013 A conf
INTERSPEECH
Renee Peje Clapham, Corina J. van As-Brooks, Michiel W. M. van den Brekel, Frans J. M. Hilgers, R. J. J. H. van Son
2012 B conf
LREC
Renee Peje Clapham, Lisette van der Molen, R. J. J. H. van Son, Michiel W. M. van den Brekel, Frans J. M. Hilgers
2010 A conf
INTERSPEECH
R. J. J. H. van Son, Irene Jacobi, Frans J. M. Hilgers
2010 J jnl
CoRR
R. J. J. H. van Son
2009 ch.
Multimodal Corpora
R. J. J. H. van Son, Wieneke Wesseling, Eric Sanders, Henk van den Heuvel
2009 J jnl
CoRR
R. J. J. H. van Son
2007 A conf
INTERSPEECH
Paola Escudero, Jelle Kastelein, Klara A. Weiand, R. J. J. H. van Son
2007 A conf
INTERSPEECH
David Weenink, Guangqin Chen, Zongyan Chen, Stefan de Konink, Dennis Vierkant, Eveline van Hagen, R. J. J. H. van Son
2007 A conf
INTERSPEECH
Wieneke Wesseling, R. J. J. H. van Son, Louis C. W. Pols
2005 J jnl
Speech Commun.
R. J. J. H. van Son, Jan P. H. van Santen
2005 conf
SIGDIAL Workshop
Wieneke Wesseling, R. J. J. H. van Son
2005 A conf
INTERSPEECH
Wieneke Wesseling, R. J. J. H. van Son
2004 conf
SSW
Jelske Dijkstra, Louis C. W. Pols, R. J. J. H. van Son
2003 A conf
INTERSPEECH
R. J. J. H. van Son, Louis C. W. Pols
2002 A conf
INTERSPEECH
R. J. J. H. van Son, Louis C. W. Pols
2001 A conf
INTERSPEECH
R. J. J. H. van Son, Diana Binnenpoorte, Henk van den Heuvel, Louis C. W. Pols
2000 A conf
INTERSPEECH
R. J. J. H. van Son, Barbertje M. Streefkerk, Louis C. W. Pols
1999 J jnl
Speech Commun.
R. J. J. H. van Son, Louis C. W. Pols
1999 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
1999 J jnl
Speech Commun.
R. J. J. H. van Son, Louis C. W. Pols
1998 conf
ICSLP
R. J. J. H. van Son, Florien J. Koopmans-van Beinum, Louis C. W. Pols
1997 conf
EUROSPEECH
R. J. J. H. van Son, Jan P. H. van Santen
1997 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
1996 conf
ICSLP
R. J. J. H. van Son, Louis C. W. Pols
1995 conf
EUROSPEECH
R. J. J. H. van Son
1995 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
1995 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
1993 J jnl
Speech Commun.
Louis C. W. Pols, R. J. J. H. van Son
1993 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
1991 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
1989 conf
EUROSPEECH
R. J. J. H. van Son, Louis C. W. Pols
tests/unit/test_database_exporters.py
← Index tests/unit/test_database_exporters.py python
"""
Unit tests for database exporters.
"""
import pytest
import json
from dataclasses import dataclass, asdict
from datetime import datetime, timezone
from unittest.mock import Mock, patch, MagicMock

pytestmark = [pytest.mark.unit, pytest.mark.exporters]


# ============================================================================
# Sample Dataclass for Testing
# ============================================================================

@dataclass
class SampleData:
    """Sample dataclass for export testing."""
    sha256: str = "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    name: str = "test_sample"
    value: int = 42
    _id: str = "test_id"


# ============================================================================
# PrintExporter Tests
# ============================================================================

class TestPrintExporter:
    """Tests for PrintExporter class."""

    def test_initialization(self, mock_logger):
        """Test PrintExporter initialization."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")

        assert exporter.index_prefix == "test_index"
        assert exporter.log is mock_logger

    def test_export_dataclass(self, mock_logger, capsys):
        """Test exporting a dataclass."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")
        sample = SampleData()

        result = exporter.export(sample)

        assert result is True
        captured = capsys.readouterr()
        assert "test_sample" in captured.out

    def test_export_list_of_dataclasses(self, mock_logger, capsys):
        """Test exporting a list of dataclasses."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")
        samples = [SampleData(name="sample1"), SampleData(name="sample2")]

        result = exporter.export(samples)

        assert result is True
        captured = capsys.readouterr()
        assert "sample1" in captured.out
        assert "sample2" in captured.out

    def test_export_dict(self, mock_logger, capsys):
        """Test exporting a dictionary."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")
        data = {"key": "value", "number": 42}

        result = exporter.export(data)

        assert result is True
        captured = capsys.readouterr()
        assert "key" in captured.out
        assert "value" in captured.out

    def test_export_none(self, mock_logger):
        """Test exporting None."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")

        result = exporter.export(None)

        assert result is True

    def test_export_empty_list(self, mock_logger):
        """Test exporting empty list."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")

        result = exporter.export([])

        assert result is True


# ============================================================================
# ElasticsearchExporter Tests
# ============================================================================

class TestElasticsearchExporter:
    """Tests for ElasticsearchExporter class."""

    def test_initialization(self, mock_logger):
        """Test ElasticsearchExporter initialization."""
        with patch('redb.settings.get_elasticsearch_client') as mock_client:
            mock_client.return_value = Mock()
            from redb.extractors.database_exporters import ElasticsearchExporter

            exporter = ElasticsearchExporter(mock_logger, "test_index")

            assert exporter.index_prefix == "test_index"
            assert exporter.log is mock_logger
            assert exporter.client is not None

    def test_export_dataclass(self, mock_logger):
        """Test exporting a dataclass to Elasticsearch."""
        with patch('redb.settings.get_elasticsearch_client') as mock_get_client:
            mock_client = Mock()
            mock_get_client.return_value = mock_client

            from redb.extractors.database_exporters import ElasticsearchExporter

            exporter = ElasticsearchExporter(mock_logger, "test_index")
            sample = SampleData()

            result = exporter.export(
                sample,
                index="test_index",
                tag="test_tag",
                hashes={"sha256": sample.sha256}
            )

            assert result is True
            mock_client.index.assert_called()

    def test_export_list(self, mock_logger):
        """Test exporting a list to Elasticsearch."""
        with patch('redb.settings.get_elasticsearch_client') as mock_get_client:
            mock_client = Mock()
            mock_get_client.return_value = mock_client

            from redb.extractors.database_exporters import ElasticsearchExporter

            exporter = ElasticsearchExporter(mock_logger, "test_index")
            samples = [SampleData(name="sample1"), SampleData(name="sample2")]

            result = exporter.export(
                samples,
                index="test_index",
                tag="test_tag",
                hashes={"sha256": "test_hash"}
            )

            assert result is True
            # Should be called twice (once per sample)
            assert mock_client.index.call_count == 2

    def test_export_failure(self, mock_logger):
        """Test handling export failure."""
        with patch('redb.settings.get_elasticsearch_client') as mock_get_client:
            mock_client = Mock()
            mock_client.index.side_effect = Exception("Connection failed")
            mock_get_client.return_value = mock_client

            from redb.extractors.database_exporters import ElasticsearchExporter

            exporter = ElasticsearchExporter(mock_logger, "test_index")
            sample = SampleData()

            result = exporter.export(
                sample,
                index="test_index",
                tag="test_tag",
                hashes={"sha256": sample.sha256}
            )

            assert result is False
            mock_logger.error.assert_called()

    def test_export_with_custom_id(self, mock_logger):
        """Test exporting with custom _id field."""
        with patch('redb.settings.get_elasticsearch_client') as mock_get_client:
            mock_client = Mock()
            mock_get_client.return_value = mock_client

            from redb.extractors.database_exporters import ElasticsearchExporter

            exporter = ElasticsearchExporter(mock_logger, "test_index")
            sample = SampleData(_id="custom_id")

            result = exporter.export(
                sample,
                index="test_index",
                tag="test_tag",
                hashes={"sha256": sample.sha256}
            )

            assert result is True


# ============================================================================
# ClickHouseExporter Tests
# ============================================================================

class TestClickHouseExporter:
    """Tests for ClickHouseExporter class."""

    def test_initialization(self, mock_logger):
        """Test ClickHouseExporter initialization."""
        from redb.extractors.database_exporters import ClickHouseExporter

        mock_client = Mock()
        exporter = ClickHouseExporter(mock_logger, "test_index", client=mock_client)

        assert exporter.index_prefix == "test_index"
        assert exporter.log is mock_logger
        assert exporter.client is mock_client

    def test_export_tuple_data(self, mock_logger):
        """Test exporting tuple data to ClickHouse."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_client.insert.return_value = True
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            data = [["hash123", "sample.exe", 1024]]
            column_names = ["sha256", "name", "size"]
            column_type_names = ["String", "String", "UInt64"]

            result = exporter.export(
                (data, column_names, column_type_names),
                table="test_table"
            )

            assert result is True

    def test_export_multi_table(self, mock_logger):
        """Test exporting multi-table data to ClickHouse."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_client.insert.return_value = True
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            data = {
                'multi_table': True,
                'table1': {
                    'table': 'test_table1',
                    'data': [["hash123", "sample.exe"]],
                    'column_names': ["sha256", "name"],
                    'column_type_names': ["String", "String"]
                }
            }

            result = exporter.export(data)

            assert result is True

    def test_export_failure(self, mock_logger):
        """Test handling export failure."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_client.insert.side_effect = Exception("Connection failed")
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            data = [["hash123", "sample.exe", 1024]]
            column_names = ["sha256", "name", "size"]
            column_type_names = ["String", "String", "UInt64"]

            result = exporter.export(
                (data, column_names, column_type_names),
                table="test_table"
            )

            assert result is False

    def test_export_missing_table(self, mock_logger):
        """Test export without table name raises error."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            data = [["hash123", "sample.exe", 1024]]
            column_names = ["sha256", "name", "size"]
            column_type_names = ["String", "String", "UInt64"]

            result = exporter.export(
                (data, column_names, column_type_names)
                # Missing table parameter
            )

            assert result is False

    def test_get_client(self, mock_logger):
        """Test get_client method."""
        from redb.extractors.database_exporters import ClickHouseExporter

        mock_client = Mock()
        exporter = ClickHouseExporter(mock_logger, "test_index", client=mock_client)

        result = exporter.get_client()

        assert result is mock_client

    def test_get_client_creates_new(self, mock_logger):
        """Test get_client creates new client if none exists."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_new_client = Mock()
            mock_create.return_value = mock_new_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            result = exporter.get_client()

            assert result is mock_new_client


# ============================================================================
# DatabaseExporter Abstract Base Class Tests
# ============================================================================

class TestDatabaseExporter:
    """Tests for DatabaseExporter abstract base class."""

    def test_cannot_instantiate_abstract(self):
        """Test that DatabaseExporter cannot be instantiated directly."""
        from redb.extractors.database_exporters import DatabaseExporter

        with pytest.raises(TypeError):
            DatabaseExporter()

    def test_subclass_must_implement_export(self):
        """Test that subclasses must implement export method."""
        from redb.extractors.database_exporters import DatabaseExporter

        # Define incomplete subclass
        class IncompleteExporter(DatabaseExporter):
            pass

        with pytest.raises(TypeError):
            IncompleteExporter()


# ============================================================================
# Null/Edge Case Tests
# ============================================================================

class TestExporterEdgeCases:
    """Tests for edge cases in exporters."""

    def test_print_exporter_with_complex_nested_data(self, mock_logger, capsys):
        """Test PrintExporter with complex nested data."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")
        data = {
            "level1": {
                "level2": {
                    "level3": [1, 2, 3]
                }
            },
            "array": [{"a": 1}, {"b": 2}]
        }

        result = exporter.export(data)

        assert result is True
        captured = capsys.readouterr()
        assert "level1" in captured.out

    def test_clickhouse_null_handling(self, mock_logger):
        """Test ClickHouse exporter handles null values."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_client.insert.return_value = True
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            # Multi-table data with null values
            data = {
                'multi_table': True,
                'table1': {
                    'table': 'test_table',
                    'data': [[None, "sample.exe", None]],
                    'column_names': ["sha256", "name", "size"],
                    'column_type_names': ["Nullable(String)", "String", "Nullable(UInt64)"]
                }
            }

            result = exporter.export(data)

            # Should handle nulls appropriately
            assert result is True

    def test_clickhouse_array_handling(self, mock_logger):
        """Test ClickHouse exporter handles array types."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_client.insert.return_value = True
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            data = {
                'multi_table': True,
                'table1': {
                    'table': 'test_table',
                    'data': [["hash", ["tag1", "tag2"]]],
                    'column_names': ["sha256", "tags"],
                    'column_type_names': ["String", "Array(String)"]
                }
            }

            result = exporter.export(data)

            assert result is True


# ============================================================================
# Type Conversion Tests
# ============================================================================

class TestExporterTypeConversions:
    """Tests for type conversions in exporters."""

    def test_clickhouse_datetime_handling(self, mock_logger):
        """Test ClickHouse exporter handles datetime values."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_client.insert.return_value = True
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            now = datetime.now(timezone.utc)
            data = {
                'multi_table': True,
                'table1': {
                    'table': 'test_table',
                    'data': [["hash", now]],
                    'column_names': ["sha256", "timestamp"],
                    'column_type_names': ["String", "DateTime64(3, 'UTC')"]
                }
            }

            result = exporter.export(data)

            assert result is True

    def test_print_exporter_datetime_serialization(self, mock_logger, capsys):
        """Test PrintExporter handles datetime serialization."""
        from redb.extractors.database_exporters import PrintExporter

        exporter = PrintExporter(mock_logger, "test_index")
        now = datetime.now(timezone.utc)
        data = {"timestamp": now, "name": "test"}

        result = exporter.export(data)

        assert result is True
        captured = capsys.readouterr()
        assert "timestamp" in captured.out


# ============================================================================
# Connection Context Manager Tests
# ============================================================================

class TestClickHouseConnectionManager:
    """Tests for ClickHouse connection context manager."""

    def test_clickhouse_connection_context(self, mock_logger):
        """Test clickhouse_connection context manager."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            with exporter.clickhouse_connection() as client:
                assert client is mock_client

            # Client should be closed after context exits
            mock_client.close.assert_called()

    def test_clickhouse_connection_close_on_error(self, mock_logger):
        """Test client is closed even if operation fails."""
        with patch('redb.settings.create_clickhouse_client') as mock_create:
            mock_client = Mock()
            mock_create.return_value = mock_client

            from redb.extractors.database_exporters import ClickHouseExporter

            exporter = ClickHouseExporter(mock_logger, "test_index")

            try:
                with exporter.clickhouse_connection() as client:
                    raise ValueError("Test error")
            except ValueError:
                pass

            # Client should still be closed
            mock_client.close.assert_called()