Olli-P. Kallioniemi

"""
Unit tests for --decompile-modules flag.

Tests that:
1. CLI argument parsing and validation works correctly
2. decompile_modules is threaded through the entire call chain
3. BinaryNinjaDecompiler.analyze_binary() gates extractions per selected modules
4. DecompileBinja.prepare_export_data() filters DB tables per selected modules
"""
import os
import pytest
from unittest.mock import Mock, patch, MagicMock

pytestmark = [pytest.mark.unit]


# ============================================================================
# CLI Argument Parsing Tests
# ============================================================================

class TestDecompileModulesCliArgument:
    """Tests for --decompile-modules CLI argument parsing in start.py."""

    def _parse_args(self, args_list):
        """Helper to parse CLI args without running main()."""
        import argparse

        parser = argparse.ArgumentParser()
        input_group = parser.add_mutually_exclusive_group(required=True)
        input_group.add_argument("--path")
        input_group.add_argument("--s3", action="store_true")
        input_group.add_argument("--s3-solo", metavar="S3_KEY")
        input_group.add_argument("--nomad-job", action="store_true")
        input_group.add_argument("--date", metavar="YYYY-MM-DD")
        input_group.add_argument("--range", nargs=2)
        input_group.add_argument("--analyzed", action="store_true")

        parser.add_argument("--repo")
        parser.add_argument("--index_prefix", default="redb")
        parser.add_argument("-d", "--decompile", action="store_true")
        parser.add_argument("-m", "--modules", default="all")
        parser.add_argument("--decompile-modules", default="all")
        parser.add_argument("--force", action="store_true")
        parser.add_argument("--dry-run", action="store_true")

        return parser.parse_args(args_list)

    def test_decompile_modules_default_all(self):
        """--decompile-modules defaults to 'all'."""
        args = self._parse_args(["--path", "/tmp/test", "--repo", "test"])
        assert args.decompile_modules == "all"

    def test_decompile_modules_single(self):
        """--decompile-modules accepts a single module."""
        args = self._parse_args([
            "--path", "/tmp/test", "--repo", "test",
            "-d", "--decompile-modules", "strings"
        ])
        assert args.decompile_modules == "strings"

    def test_decompile_modules_comma_separated(self):
        """--decompile-modules accepts comma-separated modules."""
        args = self._parse_args([
            "--path", "/tmp/test", "--repo", "test",
            "-d", "--decompile-modules", "cfg,llil,strings"
        ])
        assert args.decompile_modules == "cfg,llil,strings"

    def test_decompile_modules_with_decompile_flag(self):
        """--decompile-modules works with -d flag."""
        args = self._parse_args([
            "--path", "/tmp/test", "--repo", "test",
            "-d", "--decompile-modules", "disassembly"
        ])
        assert args.decompile is True
        assert args.decompile_modules == "disassembly"


# ============================================================================
# Validation Tests
# ============================================================================

class TestDecompileModulesValidation:
    """Tests for --decompile-modules validation logic in start.py."""

    def test_valid_modules_set_parsing(self):
        """Valid comma-separated modules are parsed into a set."""
        VALID = {"all", "decompilation", "disassembly", "cfg", "llil", "strings"}
        raw = "cfg,llil,strings"
        modules_set = {m.strip() for m in raw.split(",")}
        invalid = modules_set - VALID
        assert invalid == set()
        assert modules_set == {"cfg", "llil", "strings"}

    def test_invalid_module_detected(self):
        """Invalid module names are detected."""
        VALID = {"all", "decompilation", "disassembly", "cfg", "llil", "strings"}
        raw = "cfg,invalid_module"
        modules_set = {m.strip() for m in raw.split(",")}
        invalid = modules_set - VALID
        assert invalid == {"invalid_module"}

    def test_all_keyword_as_set(self):
        """'all' is parsed into {'all'} set."""
        raw = "all"
        if raw == "all":
            modules_set = {"all"}
        assert modules_set == {"all"}

    def test_whitespace_handling(self):
        """Whitespace around module names is stripped."""
        raw = " cfg , llil , strings "
        modules_set = {m.strip() for m in raw.split(",")}
        assert modules_set == {"cfg", "llil", "strings"}


# ============================================================================
# Ingestor Parameter Storage Tests
# ============================================================================

class TestIngestorDecompileModules:
    """Tests that Ingestor stores decompile_modules correctly."""

    @patch('builtins.open', MagicMock())
    @patch('redb.ingestor.multiprocessing')
    @patch('redb.ingestor.datetime')
    def test_ingestor_stores_decompile_modules(self, mock_datetime, mock_mp):
        """Ingestor stores the decompile_modules set."""
        mock_mp.Manager.return_value.dict = Mock(side_effect=[{}, {}])
        mock_datetime.today.return_value.strftime.return_value = "20260222"

        from redb.ingestor import Ingestor
        ingestor = Ingestor(
            path="/tmp/test", repository="test", index_prefix="redb",
            decompile_modules={"cfg", "strings"}
        )
        assert ingestor.decompile_modules == {"cfg", "strings"}

    @patch('builtins.open', MagicMock())
    @patch('redb.ingestor.multiprocessing')
    @patch('redb.ingestor.datetime')
    def test_ingestor_defaults_to_all(self, mock_datetime, mock_mp):
        """Ingestor defaults decompile_modules to {'all'} when not provided."""
        mock_mp.Manager.return_value.dict = Mock(side_effect=[{}, {}])
        mock_datetime.today.return_value.strftime.return_value = "20260222"

        from redb.ingestor import Ingestor
        ingestor = Ingestor(
            path="/tmp/test", repository="test", index_prefix="redb"
        )
        assert ingestor.decompile_modules == {"all"}

    @patch('builtins.open', MagicMock())
    @patch('redb.ingestor.multiprocessing')
    @patch('redb.ingestor.datetime')
    def test_ingestor_none_defaults_to_all(self, mock_datetime, mock_mp):
        """Ingestor converts None decompile_modules to {'all'}."""
        mock_mp.Manager.return_value.dict = Mock(side_effect=[{}, {}])
        mock_datetime.today.return_value.strftime.return_value = "20260222"

        from redb.ingestor import Ingestor
        ingestor = Ingestor(
            path="/tmp/test", repository="test", index_prefix="redb",
            decompile_modules=None
        )
        assert ingestor.decompile_modules == {"all"}


# ============================================================================
# Function Chain Threading Tests
# ============================================================================

class TestDecompileModulesThreading:
    """Tests that decompile_modules is correctly threaded through the call chain."""

    @patch('redb.workers.process_binary_file')
    @patch('redb.workers.is_binary_file', return_value=True)
    def test_process_file_internal_passes_decompile_modules(self, mock_is_binary, mock_process):
        """_process_file_internal passes decompile_modules to process_binary_file."""
        from redb.ingestor import _process_file_internal

        mock_process.return_value = (Mock(), "pebin")
        logger = Mock()
        modules = {"cfg", "strings"}

        _process_file_internal(
            "/tmp/test.bin", False, "redb", logger,
            decompile_modules=modules
        )

        mock_process.assert_called_once()
        call_kwargs = mock_process.call_args[1]
        assert call_kwargs["decompile_modules"] == modules

    @patch('redb.workers.process_binary_file')
    @patch('redb.workers.is_binary_file', return_value=True)
    def test_process_file_internal_default_decompile_modules_none(self, mock_is_binary, mock_process):
        """_process_file_internal defaults decompile_modules to None."""
        from redb.ingestor import _process_file_internal

        mock_process.return_value = (Mock(), "pebin")
        logger = Mock()

        _process_file_internal("/tmp/test.bin", False, "redb", logger)

        call_kwargs = mock_process.call_args[1]
        assert call_kwargs["decompile_modules"] is None

    @patch('redb.workers._process_file_internal')
    def test_process_file_passes_decompile_modules(self, mock_internal):
        """process_file passes decompile_modules to _process_file_internal."""
        from redb.workers import process_file

        mock_internal.return_value = (Mock(), "pebin")
        modules = {"llil", "disassembly"}

        with patch('redb.workers.setup_direct_logger', return_value=Mock()):
            process_file(
                "/tmp/test.bin", False, "redb", "/tmp/log", 1, 1,
                decompile_modules=modules
            )

        mock_internal.assert_called_once()
        call_kwargs = mock_internal.call_args[1]
        assert call_kwargs["decompile_modules"] == modules

    @patch('redb.workers._process_file_internal')
    def test_process_s3_file_passes_decompile_modules(self, mock_internal):
        """process_s3_file passes decompile_modules to _process_file_internal."""
        from redb.workers import process_s3_file

        mock_internal.return_value = (Mock(), "pebin")
        modules = {"cfg"}

        with patch('redb.workers.setup_direct_logger', return_value=Mock()), \
             patch('redb.workers.download_s3_object', return_value="/tmp/downloaded.bin"):
            process_s3_file(
                "bucket", "key", "/tmp", False, "redb", "/tmp/log", 1, 1,
                decompile_modules=modules
            )

        mock_internal.assert_called_once()
        call_kwargs = mock_internal.call_args[1]
        assert call_kwargs["decompile_modules"] == modules

    @patch('redb.workers.process_binary_file')
    def test_process_zip_passes_decompile_modules(self, mock_process):
        """process_zip_file passes decompile_modules to process_binary_file."""
        from redb.workers import process_zip_file

        mock_process.return_value = (Mock(), "pebin")
        logger = Mock()
        modules = {"strings", "decompilation"}

        import tempfile
        import zipfile

        with tempfile.NamedTemporaryFile(suffix=".zip", delete=False) as tmp:
            tmp_path = tmp.name

        try:
            with zipfile.ZipFile(tmp_path, 'w') as zf:
                zf.writestr("test.bin", b"\x00" * 100)

            process_zip_file(
                tmp_path, False, "redb", logger, "all",
                decompile_modules=modules
            )

            mock_process.assert_called_once()
            call_kwargs = mock_process.call_args[1]
            assert call_kwargs["decompile_modules"] == modules
        finally:
            os.unlink(tmp_path)

    @patch('redb.workers.process_binary_file')
    def test_process_7zip_passes_decompile_modules(self, mock_process):
        """process_7zip_file passes decompile_modules to process_binary_file."""
        from redb.workers import process_7zip_file

        mock_process.return_value = (Mock(), "pebin")
        logger = Mock()
        modules = {"cfg", "llil"}

        with patch('redb.workers.py7zr') as mock_py7zr:
            mock_zf = Mock()
            mock_py7zr.SevenZipFile.return_value.__enter__ = Mock(return_value=mock_zf)
            mock_py7zr.SevenZipFile.return_value.__exit__ = Mock(return_value=False)

            def fake_extractall(path):
                dest = os.path.join(path, "test.bin")
                with open(dest, "wb") as f:
                    f.write(b"\x00" * 100)

            mock_zf.extractall = fake_extractall

            process_7zip_file(
                "/tmp/test.7z", False, "redb", logger, "all",
                decompile_modules=modules
            )

            if mock_process.called:
                call_kwargs = mock_process.call_args[1]
                assert call_kwargs["decompile_modules"] == modules

    def test_worker_unpacks_decompile_modules(self):
        """worker() correctly unpacks decompile_modules from args tuple."""
        from redb.workers import worker

        modules = {"strings", "cfg"}

        with patch('redb.workers.process_file') as mock_pf, \
             patch('redb.workers.signal'), \
             patch('redb.workers.gc'):
            mock_pf.return_value = (Mock(), "pebin")

            args = (
                "/tmp/test.bin",  # filepath
                True,             # decompile
                "redb",           # index_prefix
                "/tmp/log",       # log_file
                1,                # file_number
                10,               # total_files
                "all",            # selected_modules
                False,            # dry_run
                False,            # yara_scan
                False,            # with_yara
                False,            # force
                modules,          # decompile_modules
            )

            worker(args)

            mock_pf.assert_called_once()
            call_kwargs = mock_pf.call_args[1]
            assert call_kwargs["decompile_modules"] == modules


# ============================================================================
# BinaryNinjaDecompiler._module_selected() Tests
# ============================================================================

class TestModuleSelected:
    """Tests for BinaryNinjaDecompiler._module_selected() helper."""

    def _make_decompiler(self, decompile_modules):
        """Create a minimal BinaryNinjaDecompiler-like object for testing _module_selected."""

        class FakeDecompiler:
            def __init__(self, modules):
                self.decompile_modules = modules

            def _module_selected(self, module_name):
                return "all" in self.decompile_modules or module_name in self.decompile_modules

        return FakeDecompiler(decompile_modules)

    def test_all_selects_everything(self):
        d = self._make_decompiler({"all"})
        assert d._module_selected("strings") is True
        assert d._module_selected("decompilation") is True
        assert d._module_selected("disassembly") is True
        assert d._module_selected("cfg") is True
        assert d._module_selected("llil") is True

    def test_specific_module_selected(self):
        d = self._make_decompiler({"cfg", "strings"})
        assert d._module_selected("cfg") is True
        assert d._module_selected("strings") is True
        assert d._module_selected("decompilation") is False
        assert d._module_selected("disassembly") is False
        assert d._module_selected("llil") is False

    def test_empty_set_selects_nothing(self):
        d = self._make_decompiler(set())
        assert d._module_selected("strings") is False
        assert d._module_selected("decompilation") is False

    def test_single_module(self):
        d = self._make_decompiler({"llil"})
        assert d._module_selected("llil") is True
        assert d._module_selected("cfg") is False
        assert d._module_selected("strings") is False


# ============================================================================
# analyze_binary() Selective Execution Tests
# ============================================================================

class TestAnalyzeBinaryGating:
    """Tests that analyze_binary() gates extraction per decompile_modules.

    Uses a FakeDecompiler to test the gating logic without importing binaryninja.
    """

    def _make_analyze_binary_runner(self, decompile_modules):
        """Create a test harness that simulates the gating logic of analyze_binary()."""
        run_all = "all" in decompile_modules
        run_strings = run_all or "strings" in decompile_modules
        run_decompilation = run_all or "decompilation" in decompile_modules
        run_disassembly = run_all or "disassembly" in decompile_modules
        run_llil = run_all or "llil" in decompile_modules
        run_cfg = run_all or "cfg" in decompile_modules
        need_per_function = run_decompilation or run_disassembly or run_llil or run_cfg

        return {
            "run_strings": run_strings,
            "run_decompilation": run_decompilation,
            "run_disassembly": run_disassembly,
            "run_llil": run_llil,
            "run_cfg": run_cfg,
            "need_per_function": need_per_function,
        }

    def test_all_runs_everything(self):
        r = self._make_analyze_binary_runner({"all"})
        assert r["run_strings"] is True
        assert r["run_decompilation"] is True
        assert r["run_disassembly"] is True
        assert r["run_llil"] is True
        assert r["run_cfg"] is True
        assert r["need_per_function"] is True

    def test_strings_only_skips_per_function_loop(self):
        """Selecting only 'strings' should skip the per-function loop entirely."""
        r = self._make_analyze_binary_runner({"strings"})
        assert r["run_strings"] is True
        assert r["run_decompilation"] is False
        assert r["run_disassembly"] is False
        assert r["run_llil"] is False
        assert r["run_cfg"] is False
        assert r["need_per_function"] is False

    def test_cfg_only_runs_cfg_and_disassembly_in_loop(self):
        """Selecting only 'cfg' should run the per-function loop but skip decompilation/llil/strings."""
        r = self._make_analyze_binary_runner({"cfg"})
        assert r["run_strings"] is False
        assert r["run_decompilation"] is False
        assert r["run_disassembly"] is False  # Not selected (but backbone runs anyway in real code)
        assert r["run_llil"] is False
        assert r["run_cfg"] is True
        assert r["need_per_function"] is True

    def test_decompilation_only(self):
        r = self._make_analyze_binary_runner({"decompilation"})
        assert r["run_decompilation"] is True
        assert r["run_strings"] is False
        assert r["run_cfg"] is False
        assert r["run_llil"] is False
        assert r["need_per_function"] is True

    def test_multiple_modules(self):
        r = self._make_analyze_binary_runner({"cfg", "llil", "strings"})
        assert r["run_strings"] is True
        assert r["run_cfg"] is True
        assert r["run_llil"] is True
        assert r["run_decompilation"] is False
        assert r["run_disassembly"] is False
        assert r["need_per_function"] is True

    def test_disassembly_only(self):
        r = self._make_analyze_binary_runner({"disassembly"})
        assert r["run_disassembly"] is True
        assert r["run_decompilation"] is False
        assert r["run_strings"] is False
        assert r["run_cfg"] is False
        assert r["run_llil"] is False
        assert r["need_per_function"] is True


# ============================================================================
# prepare_export_data() Table Filtering Tests
# ============================================================================

class TestPrepareExportDataFiltering:
    """Tests that prepare_export_data() only includes tables for selected modules.

    Simulates the filtering logic from DecompileBinja.prepare_export_data()
    without importing binaryninja.
    """

    def _get_export_tables(self, decompile_modules):
        """Simulate the table selection logic from prepare_export_data()."""
        run_all = "all" in decompile_modules
        run_decompilation = run_all or "decompilation" in decompile_modules
        run_disassembly = run_all or "disassembly" in decompile_modules
        run_llil = run_all or "llil" in decompile_modules
        run_cfg = run_all or "cfg" in decompile_modules
        run_strings = run_all or "strings" in decompile_modules

        tables = set()
        if run_decompilation:
            tables.update(["decompiled_content", "decompiled_refs"])
        if run_disassembly:
            tables.update(["disassembled_content", "disassembled_refs", "function_similarity_metrics"])
        if run_llil:
            tables.update(["llil_content", "llil_refs"])
        if run_cfg:
            tables.update(["cfg_functions"])
        if run_strings:
            tables.update(["strings_raw"])
        # Errors always included if per-function loop ran
        if run_decompilation or run_disassembly or run_llil or run_cfg:
            tables.add("function_analysis_errors")

        return tables

    def test_all_includes_all_tables(self):
        tables = self._get_export_tables({"all"})
        assert "decompiled_content" in tables
        assert "decompiled_refs" in tables
        assert "disassembled_content" in tables
        assert "disassembled_refs" in tables
        assert "function_similarity_metrics" in tables
        assert "llil_content" in tables
        assert "llil_refs" in tables
        assert "cfg_functions" in tables
        assert "strings_raw" in tables
        assert "function_analysis_errors" in tables

    def test_strings_only_includes_only_strings(self):
        tables = self._get_export_tables({"strings"})
        assert tables == {"strings_raw"}

    def test_cfg_only_includes_cfg_and_errors(self):
        tables = self._get_export_tables({"cfg"})
        assert tables == {"cfg_functions", "function_analysis_errors"}

    def test_decompilation_only_tables(self):
        tables = self._get_export_tables({"decompilation"})
        assert tables == {"decompiled_content", "decompiled_refs", "function_analysis_errors"}

    def test_disassembly_only_tables(self):
        tables = self._get_export_tables({"disassembly"})
        assert tables == {
            "disassembled_content", "disassembled_refs",
            "function_similarity_metrics", "function_analysis_errors"
        }

    def test_llil_only_tables(self):
        tables = self._get_export_tables({"llil"})
        assert tables == {"llil_content", "llil_refs", "function_analysis_errors"}

    def test_combined_cfg_strings_tables(self):
        tables = self._get_export_tables({"cfg", "strings"})
        assert tables == {"cfg_functions", "strings_raw", "function_analysis_errors"}

    def test_no_errors_table_for_strings_only(self):
        """Error table should NOT be included when only strings is selected (no per-function loop)."""
        tables = self._get_export_tables({"strings"})
        assert "function_analysis_errors" not in tables


# ============================================================================
# DecompileBinja Parameter Acceptance Tests
# ============================================================================

class TestDecompileBinjaDecompileModules:
    """Tests that DecompileBinja accepts and stores decompile_modules.

    Since DecompileBinja imports binaryninja (which requires blake3 etc),
    we test the default/init logic in isolation.
    """

    def test_default_decompile_modules(self):
        """decompile_modules defaults to {'all'} when None."""
        modules = None
        result = modules or {"all"}
        assert result == {"all"}

    def test_explicit_decompile_modules(self):
        """Explicit decompile_modules is preserved."""
        modules = {"cfg", "llil"}
        result = modules or {"all"}
        assert result == {"cfg", "llil"}

    def test_empty_set_becomes_all(self):
        """Empty set is falsy and defaults to {'all'}."""
        modules = set()
        result = modules or {"all"}
        assert result == {"all"}


# ============================================================================
# Integration-Style: analyze_binary() Per-Function Gating (Logic Tests)
# ============================================================================

class TestAnalyzeBinaryPerFunctionGating:
    """Test that the per-function extraction gating produces correct results structures.

    These test the logic patterns from analyze_binary() using mock data,
    verifying that:
    - Unselected modules produce empty result lists
    - Selected modules produce populated result lists
    - Disassembly always runs when any per-function module is selected
    - Cross-linkage None handling works when counterparts are skipped
    """

    def _simulate_per_function_results(self, decompile_modules, num_functions=3):
        """Simulate the per-function extraction loop from analyze_binary().

        Returns results dict with the same structure as analyze_binary().
        """
        run_all = "all" in decompile_modules
        run_strings = run_all or "strings" in decompile_modules
        run_decompilation = run_all or "decompilation" in decompile_modules
        run_disassembly = run_all or "disassembly" in decompile_modules
        run_llil = run_all or "llil" in decompile_modules
        run_cfg = run_all or "cfg" in decompile_modules
        need_per_function = run_decompilation or run_disassembly or run_llil or run_cfg

        results = {
            "decompiled": [],
            "disassembled": [],
            "cfg": [],
            "llil": [],
            "errors": [],
            "strings": [],
        }

        if run_strings:
            results["strings"] = [{"string": f"str_{i}"} for i in range(5)]

        if not need_per_function:
            return results

        for i in range(num_functions):
            hlil_json = {"decompiled_function_hash": f"hlil_{i}"} if run_decompilation else None
            disass_json = {"disassembled_function_hash": f"disass_{i}", "disassembled_function_name": f"func_{i}", "disassembled_function_address": i * 100}  # always
            cfg_json = {"function_address": i * 100, "cyclomatic_complexity": 5} if run_cfg else None
            lowlevel_json = {"sha256_llil": f"llil_{i}", "tlsh_llil": "def", "minhash": [1, 2]} if run_llil else None

            # Simulate cross-linkage (same pattern as real code)
            if hlil_json and disass_json:
                hlil_json["disassembled_function_hash"] = disass_json["disassembled_function_hash"]
                disass_json["decompiled_function_hash"] = hlil_json["decompiled_function_hash"]
                results["decompiled"].append(hlil_json)
                if run_disassembly:
                    results["disassembled"].append(disass_json)
            elif hlil_json:
                hlil_json["disassembled_function_hash"] = None
                results["decompiled"].append(hlil_json)
            elif disass_json:
                disass_json["decompiled_function_hash"] = None
                if run_disassembly:
                    results["disassembled"].append(disass_json)

            if lowlevel_json and disass_json:
                lowlevel_json["disassembled_function_hash"] = disass_json["disassembled_function_hash"]
                disass_json["tlsh_llil"] = lowlevel_json.get("tlsh_llil")
                disass_json["minhash"] = lowlevel_json.get("minhash")
            elif lowlevel_json:
                lowlevel_json["disassembled_function_hash"] = None
            elif disass_json:
                disass_json["tlsh_llil"] = None
                disass_json["minhash"] = None

            if lowlevel_json:
                results["llil"].append(lowlevel_json)

            if cfg_json and disass_json:
                cfg_json["disassembled_function_hash"] = disass_json["disassembled_function_hash"]
                disass_json["cyclomatic_complexity"] = cfg_json.get("cyclomatic_complexity")
                results["cfg"].append(cfg_json)
            elif cfg_json:
                cfg_json["disassembled_function_hash"] = None
                results["cfg"].append(cfg_json)

            if disass_json and "cyclomatic_complexity" not in disass_json:
                disass_json["cyclomatic_complexity"] = None

        return results

    def test_all_populates_everything(self):
        r = self._simulate_per_function_results({"all"}, 3)
        assert len(r["decompiled"]) == 3
        assert len(r["disassembled"]) == 3
        assert len(r["cfg"]) == 3
        assert len(r["llil"]) == 3
        assert len(r["strings"]) == 5

    def test_strings_only_populates_strings(self):
        r = self._simulate_per_function_results({"strings"}, 3)
        assert len(r["strings"]) == 5
        assert len(r["decompiled"]) == 0
        assert len(r["disassembled"]) == 0
        assert len(r["cfg"]) == 0
        assert len(r["llil"]) == 0

    def test_cfg_only_populates_cfg_no_disassembly_export(self):
        """With only 'cfg' selected, cfg list is populated but disassembled is empty
        (disassembly runs internally but not exported)."""
        r = self._simulate_per_function_results({"cfg"}, 3)
        assert len(r["cfg"]) == 3
        assert len(r["disassembled"]) == 0  # Not selected for export
        assert len(r["decompiled"]) == 0
        assert len(r["llil"]) == 0
        assert len(r["strings"]) == 0

    def test_cfg_has_disassembled_function_hash_linkage(self):
        """CFG entries get disassembled_function_hash from backbone disassembly."""
        r = self._simulate_per_function_results({"cfg"}, 2)
        for cfg in r["cfg"]:
            assert cfg["disassembled_function_hash"] is not None
            assert cfg["disassembled_function_hash"].startswith("disass_")

    def test_decompilation_only_has_none_disassembly_linkage_when_no_disasm(self):
        """When only decompilation selected, disassembled still runs (backbone)
        so linkage is still available."""
        r = self._simulate_per_function_results({"decompilation"}, 2)
        assert len(r["decompiled"]) == 2
        # Disassembly runs as backbone, so linkage hash is present
        for d in r["decompiled"]:
            assert d["disassembled_function_hash"] is not None

    def test_disassembly_without_llil_has_none_fuzzy_hashes(self):
        """When LLIL is not selected, disassembly records have None fuzzy hashes."""
        r = self._simulate_per_function_results({"disassembly"}, 2)
        for d in r["disassembled"]:
            assert d["tlsh_llil"] is None
            assert d["minhash"] is None

    def test_disassembly_without_decompilation_has_none_decompiled_hash(self):
        """When decompilation is not selected, disassembly has None decompiled_function_hash."""
        r = self._simulate_per_function_results({"disassembly"}, 2)
        for d in r["disassembled"]:
            assert d["decompiled_function_hash"] is None

    def test_disassembly_without_cfg_has_none_cyclomatic(self):
        """When CFG is not selected, disassembly has None cyclomatic_complexity."""
        r = self._simulate_per_function_results({"disassembly"}, 2)
        for d in r["disassembled"]:
            assert d["cyclomatic_complexity"] is None

    def test_all_linkage_populated(self):
        """When all modules run, all cross-linkage fields are populated."""
        r = self._simulate_per_function_results({"all"}, 2)
        for d in r["disassembled"]:
            assert d["decompiled_function_hash"] is not None
            assert d["tlsh_llil"] is not None
            assert d["cyclomatic_complexity"] is not None
        for h in r["decompiled"]:
            assert h["disassembled_function_hash"] is not None
        for c in r["cfg"]:
            assert c["disassembled_function_hash"] is not None
        for ll in r["llil"]:
            assert ll["disassembled_function_hash"] is not None


# ============================================================================
# IOC Extraction Gating by decompile_modules
# ============================================================================

class TestIOCExtractionGating:
    """Tests that IOC extraction only runs when its data sources are present.

    IOCExtractorFromResults consumes in-memory analysis_results['strings']
    and analysis_results['decompiled']. It runs automatically (implicit
    dependency) when 'decompilation' or 'strings' modules produce data.
    It is NOT a standalone selectable module.
    """

    @staticmethod
    def _is_ioc_relevant(decompile_modules):
        """Replicate the gating logic from workers.py."""
        return (
            not decompile_modules
            or "all" in decompile_modules
            or "decompilation" in decompile_modules
            or "strings" in decompile_modules
        )

    def test_all_triggers_ioc(self):
        assert self._is_ioc_relevant({"all"}) is True

    def test_decompilation_triggers_ioc(self):
        assert self._is_ioc_relevant({"decompilation"}) is True

    def test_strings_triggers_ioc(self):
        assert self._is_ioc_relevant({"strings"}) is True

    def test_decompilation_and_strings_triggers_ioc(self):
        assert self._is_ioc_relevant({"decompilation", "strings"}) is True

    def test_cfg_only_skips_ioc(self):
        assert self._is_ioc_relevant({"cfg"}) is False

    def test_disassembly_only_skips_ioc(self):
        assert self._is_ioc_relevant({"disassembly"}) is False

    def test_llil_only_skips_ioc(self):
        assert self._is_ioc_relevant({"llil"}) is False

    def test_cfg_and_disassembly_skips_ioc(self):
        assert self._is_ioc_relevant({"cfg", "disassembly"}) is False

    def test_cfg_and_llil_skips_ioc(self):
        assert self._is_ioc_relevant({"cfg", "llil"}) is False

    def test_cfg_and_decompilation_triggers_ioc(self):
        """If decompilation is included alongside cfg, IOC should run."""
        assert self._is_ioc_relevant({"cfg", "decompilation"}) is True

    def test_disassembly_and_strings_triggers_ioc(self):
        """If strings is included alongside disassembly, IOC should run."""
        assert self._is_ioc_relevant({"disassembly", "strings"}) is True

    def test_none_modules_triggers_ioc(self):
        """When decompile_modules is None (default), IOC should run."""
        assert self._is_ioc_relevant(None) is True

    def test_empty_set_triggers_ioc(self):
        """When decompile_modules is empty set, IOC should run (falsy)."""
        assert self._is_ioc_relevant(set()) is True