kb-skills/tests/test_processors/test_archive.py

"""Tests for ArchiveProcessor

Tests that ArchiveProcessor:
- Copies md file to correct platform directory
- Uses correct filename format {YYYYMMDD}_{content_id}_analysis.md
- Skips when step already completed
- Detects existing archive by content_id
- Handles missing analysis file with error
"""

import pytest
from datetime import datetime
from pathlib import Path
from unittest.mock import patch, MagicMock

from kb_workflow.pipeline.processors.archive import ArchiveProcessor
from kb_workflow.pipeline.schemas import ArchiveInput, ArchiveOutput
from kb_workflow.pipeline.state import WorkflowStateManager


# =============================================================================
# Fixtures
# =============================================================================


@pytest.fixture
def archive_test_env(tmp_path):
    """Create test environment for archive tests"""
    # Create intermediate content directory
    content_dir = tmp_path / "intermediate" / "bilibili_BV1test"
    content_dir.mkdir(parents=True)

    # Create analysis file
    analysis_file = content_dir / "analysis.md"
    analysis_file.write_text("# Test Analysis\n\nContent here.")

    # Create archive directory
    archive_dir = tmp_path / "archive"
    archive_dir.mkdir(parents=True)

    # Create state manager
    state_manager = WorkflowStateManager(content_dir)

    return {
        "content_dir": content_dir,
        "analysis_file": analysis_file,
        "archive_dir": archive_dir,
        "state_manager": state_manager,
    }


# =============================================================================
# ArchiveProcessor Tests
# =============================================================================


class TestArchiveProcessorCopyToPlatformDir:
    """Test that archive file is copied to correct platform directory"""

    @pytest.mark.asyncio
    async def test_copies_to_platform_dir(self, archive_test_env):
        """Test that archive file is copied to correct platform directory"""
        mock_settings = MagicMock()
        mock_settings.archive_path = str(archive_test_env["archive_dir"])

        with patch('kb_workflow.pipeline.processors.archive.get_settings') as mock_get_settings:
            mock_get_settings.return_value = mock_settings

            processor = ArchiveProcessor()
            # Mock _ask_overwrite to return True (user says yes) in case of collision
            processor._ask_overwrite = lambda f: True

            input_data = ArchiveInput(
                content_id="BV1test",
                platform="bilibili",
                content_dir=str(archive_test_env["content_dir"]),
                analysis_file=str(archive_test_env["analysis_file"]),
                content_type="video"
            )

            result = await processor.process(input_data)

            assert result.success is True
            assert result.skipped is False
            assert "bilibili" in result.archive_file
            assert result.archive_file.endswith("_analysis.md")


class TestArchiveProcessorFilenameFormat:
    """Test that archive filename follows correct format"""

    @pytest.mark.asyncio
    async def test_filename_format(self, archive_test_env):
        """Test that archive filename follows {YYYYMMDD}_{content_id}_analysis.md format"""
        mock_settings = MagicMock()
        mock_settings.archive_path = str(archive_test_env["archive_dir"])

        with patch('kb_workflow.pipeline.processors.archive.get_settings') as mock_get_settings:
            mock_get_settings.return_value = mock_settings

            processor = ArchiveProcessor()
            # Mock _ask_overwrite to return True (user says yes) in case of collision
            processor._ask_overwrite = lambda f: True

            input_data = ArchiveInput(
                content_id="BV1test",
                platform="bilibili",
                content_dir=str(archive_test_env["content_dir"]),
                analysis_file=str(archive_test_env["analysis_file"]),
                content_type="video"
            )

            result = await processor.process(input_data)

            # Check filename format
            archive_path = Path(result.archive_file)
            filename = archive_path.name
            today = datetime.now().strftime("%Y%m%d")
            expected = f"{today}_BV1test_analysis.md"
            assert filename == expected


class TestArchiveProcessorSkipsCompleted:
    """Test that archive step is skipped when already completed"""

    @pytest.mark.asyncio
    async def test_skips_completed(self, archive_test_env):
        """Test that archive step is skipped when already completed"""
        mock_settings = MagicMock()
        mock_settings.archive_path = str(archive_test_env["archive_dir"])

        # Create state with archive already completed
        state = archive_test_env["state_manager"].get_or_create(
            content_id="BV1test",
            platform="bilibili",
            source_url="https://test.com"
        )
        state.mark_step_completed("archive")
        archive_test_env["state_manager"].save(state)

        with patch('kb_workflow.pipeline.processors.archive.get_settings') as mock_get_settings:
            mock_get_settings.return_value = mock_settings

            processor = ArchiveProcessor(state_manager=archive_test_env["state_manager"])
            input_data = ArchiveInput(
                content_id="BV1test",
                platform="bilibili",
                content_dir=str(archive_test_env["content_dir"]),
                analysis_file=str(archive_test_env["analysis_file"]),
                content_type="video"
            )

            result = await processor.process(input_data)

            assert result.success is True
            assert result.skipped is True


class TestArchiveProcessorDetectsExisting:
    """Test that archive processor detects existing archive by content_id"""

    @pytest.mark.asyncio
    async def test_detects_existing_archive(self, archive_test_env):
        """Test that archive processor detects existing archive by content_id"""
        mock_settings = MagicMock()
        mock_settings.archive_path = str(archive_test_env["archive_dir"])

        # Create existing archive with different timestamp
        platform_dir = archive_test_env["archive_dir"] / "bilibili"
        platform_dir.mkdir(parents=True, exist_ok=True)
        existing = platform_dir / "20260101_BV1test_analysis.md"
        existing.write_text("Old content")

        with patch('kb_workflow.pipeline.processors.archive.get_settings') as mock_get_settings:
            mock_get_settings.return_value = mock_settings

            processor = ArchiveProcessor()
            # Mock _ask_overwrite to return False (user says no)
            processor._ask_overwrite = lambda f: False

            input_data = ArchiveInput(
                content_id="BV1test",
                platform="bilibili",
                content_dir=str(archive_test_env["content_dir"]),
                analysis_file=str(archive_test_env["analysis_file"]),
                content_type="video"
            )

            result = await processor.process(input_data)

            assert result.success is True
            assert result.skipped is True


class TestArchiveProcessorHandlesMissingFile:
    """Test that archive processor handles missing analysis file"""

    @pytest.mark.asyncio
    async def test_handles_missing_file(self, archive_test_env):
        """Test that archive processor handles missing analysis file"""
        mock_settings = MagicMock()
        mock_settings.archive_path = str(archive_test_env["archive_dir"])

        with patch('kb_workflow.pipeline.processors.archive.get_settings') as mock_get_settings:
            mock_get_settings.return_value = mock_settings

            processor = ArchiveProcessor()
            # Mock _ask_overwrite to avoid stdin issues
            processor._ask_overwrite = lambda f: True

            input_data = ArchiveInput(
                content_id="BV1test",
                platform="bilibili",
                content_dir=str(archive_test_env["content_dir"]),
                analysis_file="/nonexistent/analysis.md",  # Missing file
                content_type="video"
            )

            result = await processor.process(input_data)

            assert result.success is False
            assert "not found" in result.error_message.lower()