Xiaojiang Huang

19 papers A* 1B 4Journal 8Unranked 6
YearRankTypeTitle / Venue / Authors
2025 J jnl
IEEE Trans. Instrum. Meas.
Dongming Li, Jiamei Wang, Han Wang, Xiaojiang Huang, Jiejie Yang, Yueming Gao, Hung-Chun Li, Mang I Vai, Sio-Hang Pun
2025 J jnl
CoRR
Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xing Fan, Xiang Li, Chenlei Guo, Ruhi Sarikaya, Heng Ji
2024 J jnl
CoRR
Shambhavi Krishna, Zheng Chen, Vaibhav Kumar, Xiaojiang Huang, Yingjie Li, Fan Yang, Xiang Li
2024 conf
NAACL-HLT (Findings)
Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Yanbin Lu, Xiaojiang Huang, Yingzhen Yang
2023 conf
EMNLP (Industry Track)
Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan
2023 J jnl
CoRR
Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Yingzhen Yang
2020 J jnl
CoRR
Yunmo Chen, Sixing Lu, Fan Yang, Xiaojiang Huang, Xing Fan, Chenlei Guo
2015 A* conf
EMNLP
Gang Luo, Xiaojiang Huang, Chin-Yew Lin, Zaiqing Nie
2015 J jnl
CoRR
Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao
2015 J jnl
IEEE Trans. Ind. Electron.
Xinglong Ju, Lei Dong, Xiaojiang Huang, Xiaozhong Liao
2014 conf
ACL (1)
Hongzhao Huang, Yunbo Cao, Xiaojiang Huang, Heng Ji, Chin-Yew Lin
2014 J jnl
Knowl. Inf. Syst.
Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao
2013 conf
TAC
Xiaojiang Huang, Yunbo Cao, Chin-Yew Lin, Danqing Huang
2012 B conf
WISE
Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao
2012 B conf
WISE
Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao
2011 conf
ACL (2)
Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao
2011 B conf
IJCNLP
Xiaojun Wan, Liang Zong, Xiaojiang Huang, Tengfei Ma, Houping Jia, Yuqian Wu, Jianguo Xiao
2010 conf
TAC
Houping Jia, Xiaojiang Huang, Tengfei Ma, Xiaojun Wan, Jianguo Xiao
2008 B conf
PRICAI
Xiaojiang Huang, Xiaojun Wan, Jianwu Yang, Jianguo Xiao
tests/integration/test_elf_extractor.py
← Index tests/integration/test_elf_extractor.py python
"""
Integration tests for the ELFExtractor base class.
"""
import pytest
from unittest.mock import Mock, patch, MagicMock

pytestmark = [pytest.mark.integration, pytest.mark.elf]


class TestELFExtractorInitialization:
    """Tests for ELFExtractor initialization."""

    def test_elf_extractor_with_valid_elf(self, elf_binary_path, mock_logger):
        """Test ELFExtractor initialization with valid ELF file."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            assert extractor.filepath == elf_binary_path
            assert extractor._is_elf_file() is True

    def test_elf_extractor_with_invalid_file(self, pe_binary_path, mock_logger):
        """Test ELFExtractor initialization with non-ELF file."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(pe_binary_path, mock_logger)

            # Should not be a valid ELF
            assert extractor._is_elf_file() is False

    def test_elf_extractor_with_text_file(self, temp_text_file, mock_logger):
        """Test ELFExtractor initialization with text file."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(temp_text_file, mock_logger)

            # Should not be a valid ELF
            assert extractor._is_elf_file() is False


class TestELFExtractorMethods:
    """Tests for ELFExtractor helper methods."""

    def test_is_elf_file_true(self, elf_binary_path, mock_logger):
        """Test _is_elf_file returns True for valid ELF."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            assert extractor._is_elf_file() is True

    def test_is_elf_file_cached(self, elf_binary_path, mock_logger):
        """Test _is_elf_file result is cached."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            # First call
            result1 = extractor._is_elf_file()
            # Second call should use cached value
            result2 = extractor._is_elf_file()

            assert result1 == result2
            # Cache should be set
            assert extractor._elf_file_valid is not None

    def test_is_64bit(self, elf_binary_path, mock_logger):
        """Test _is_64bit method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._is_64bit()
            # Result depends on the test binary
            assert isinstance(result, bool)

    def test_is_stripped(self, elf_binary_path, mock_logger):
        """Test _is_stripped method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._is_stripped()
            assert isinstance(result, bool)

    def test_has_debug_info(self, elf_binary_path, mock_logger):
        """Test _has_debug_info method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._has_debug_info()
            assert isinstance(result, bool)

    def test_get_architecture(self, elf_binary_path, mock_logger):
        """Test _get_architecture method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._get_architecture()
            # Should return a string (architecture name)
            assert isinstance(result, str)
            assert result != ""

    def test_get_endianness(self, elf_binary_path, mock_logger):
        """Test _get_endianness method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._get_endianness()
            # Should be one of: "little", "big", or "unknown"
            assert result in ["little", "big", "unknown"]

    def test_get_file_type(self, elf_binary_path, mock_logger):
        """Test _get_file_type method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._get_file_type()
            # Should return a file type string
            assert isinstance(result, str)
            # Common values: "executable", "shared_object", "relocatable", etc.
            expected_types = ["none", "relocatable", "executable", "shared_object", "core_dump", "unknown"]
            assert result in expected_types or result.startswith("ET_")

    def test_is_pie(self, elf_binary_path, mock_logger):
        """Test _is_pie method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._is_pie()
            assert isinstance(result, bool)

    def test_has_stack_protection(self, elf_binary_path, mock_logger):
        """Test _has_stack_protection method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._has_stack_protection()
            assert isinstance(result, bool)

    def test_has_nx_bit(self, elf_binary_path, mock_logger):
        """Test _has_nx_bit method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._has_nx_bit()
            assert isinstance(result, bool)

    def test_has_relro(self, elf_binary_path, mock_logger):
        """Test _has_relro method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._has_relro()
            assert isinstance(result, bool)

    def test_get_build_id(self, elf_binary_path, mock_logger):
        """Test _get_build_id method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._get_build_id()
            # Could be None if no build ID, or a hex string
            assert result is None or isinstance(result, str)

    def test_count_sections(self, elf_binary_path, mock_logger):
        """Test _count_sections method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._count_sections()
            assert isinstance(result, int)
            assert result >= 0

    def test_count_segments(self, elf_binary_path, mock_logger):
        """Test _count_segments method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._count_segments()
            assert isinstance(result, int)
            assert result >= 0

    def test_count_symbols(self, elf_binary_path, mock_logger):
        """Test _count_symbols method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._count_symbols()
            assert isinstance(result, int)
            assert result >= 0

    def test_get_dependencies(self, elf_binary_path, mock_logger):
        """Test _get_dependencies method."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor._get_dependencies()
            assert isinstance(result, list)


class TestWithELFFile:
    """Tests for the _with_elf_file context manager method."""

    def test_with_elf_file_success(self, elf_binary_path, mock_logger):
        """Test _with_elf_file executes operation successfully."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            # Define a simple operation
            def get_header(elf):
                return elf.header is not None

            result = extractor._with_elf_file(get_header)
            assert result is True

    def test_with_elf_file_error_handling(self, temp_text_file, mock_logger):
        """Test _with_elf_file handles errors gracefully."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(temp_text_file, mock_logger)

            # Define an operation that would fail
            def get_header(elf):
                return elf.header

            result = extractor._with_elf_file(get_header)
            # Should return None on error
            assert result is None


class TestELFExtractorTag:
    """Tests for tag method in ELF extractors."""

    def test_elf_features_tag(self, elf_binary_path, mock_logger):
        """Test that ELFFeaturesExtractor returns correct tag."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)
            tag = extractor.tag()
            # Should return the tag string
            assert isinstance(tag, str)
            assert "elf" in tag.lower() or "features" in tag.lower()


class TestELFExtractorClickHouseTable:
    """Tests for get_clickhouse_table method in ELF extractors."""

    def test_elf_features_clickhouse_table(self, elf_binary_path, mock_logger):
        """Test that ELFFeaturesExtractor returns correct ClickHouse table name."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)
            assert extractor.get_clickhouse_table() == "redb_elf_features"


class TestELFExtractorExtract:
    """Tests for extract method in ELF extractors."""

    def test_elf_features_extract(self, elf_binary_path, mock_logger):
        """Test ELFFeaturesExtractor.extract() returns valid data."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor
        from redb.models.dataclasses import ELFFeatures

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            result = extractor.extract()
            assert result is not None
            assert isinstance(result, ELFFeatures)

            # Check some expected fields
            assert isinstance(result.ei_class, int)
            assert isinstance(result.ei_data, int)
            assert isinstance(result.e_entry, int)
            assert isinstance(result.number_of_sections, int)
            assert isinstance(result.number_of_segments, int)

    def test_elf_features_extract_invalid_file(self, pe_binary_path, mock_logger):
        """Test ELFFeaturesExtractor.extract() handles invalid ELF."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(pe_binary_path, mock_logger)

            result = extractor.extract()
            # Should return None for invalid ELF
            assert result is None


class TestELFExtractorPrepareExportData:
    """Tests for prepare_export_data method in ELF extractors."""

    def test_elf_features_prepare_export_elasticsearch(self, elf_binary_path, mock_logger):
        """Test prepare_export_data for Elasticsearch."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            # First extract
            extractor.extract()
            result = extractor.prepare_export_data("ElasticsearchExporter")
            # Should return the elf_features dataclass
            assert result is extractor.elf_features

    def test_elf_features_prepare_export_clickhouse(self, elf_binary_path, mock_logger):
        """Test prepare_export_data for ClickHouse."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_binary_path, mock_logger)

            # First extract
            extractor.extract()
            result = extractor.prepare_export_data("ClickHouseExporter")

            # Should return tuple of (data, column_names, column_type_names)
            assert isinstance(result, tuple)
            assert len(result) == 3
            data, column_names, column_type_names = result
            assert isinstance(data, list)
            assert isinstance(column_names, list)
            assert isinstance(column_type_names, list)
            # Column names and types should match in length
            assert len(column_names) == len(column_type_names)


class TestELFExtractorAdvanced:
    """Advanced tests for ELF extraction using hello_advanced binary."""

    def test_elf_advanced_features(self, elf_advanced_binary_path, mock_logger):
        """Test ELFFeaturesExtractor with more complex ELF binary."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_advanced_binary_path, mock_logger)

            result = extractor.extract()
            assert result is not None

            # Check that we can extract meaningful data
            assert result.number_of_sections > 0
            assert result.number_of_segments > 0

    def test_elf_advanced_architecture(self, elf_advanced_binary_path, mock_logger):
        """Test architecture detection for advanced ELF binary."""
        from redb.extractors.elf_extractors.elf_features import ELFFeaturesExtractor

        with patch('redb.settings.ELASTIC_BINARIES_COLLECTION', 'test'):
            extractor = ELFFeaturesExtractor(elf_advanced_binary_path, mock_logger)

            arch = extractor._get_architecture()
            # Should detect a valid architecture
            assert arch != "unknown"
            assert arch != ""