test(05-03): add Pipeline archive integration tests

- Test pipeline includes archive step
- Test archive uses platform directory structure
- Test no date-based subdirectories in archive
- Update default steps assertion to include archive

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-16 23:26:14 +08:00
parent be783f97fa
commit 360aee200f
+193 -1
View File
@@ -122,7 +122,7 @@ class TestPipelineConfig:
config = PipelineConfig()
assert hasattr(config, "steps")
assert isinstance(config.steps, list)
assert config.steps == ["parse", "download", "asr", "analyze"]
assert config.steps == ["parse", "download", "asr", "analyze", "archive"]
def test_schema_pipeline_config_allows_custom_steps(self):
"""PipelineConfig allows custom steps list"""
@@ -303,3 +303,195 @@ class TestPipelineParseUrl:
assert result.platform == "bilibili"
assert result.content_type == "video"
assert result.content_id == "BV1xx411c7mD"
# =============================================================================
# Archive Integration Tests
# =============================================================================
@pytest.fixture
def mock_processors_with_archive():
"""Create mock processors including archive"""
processors = []
for step_name in ["parse", "download", "asr", "analyze", "archive"]:
processor = MagicMock()
processor.STEP_NAME = step_name
processor.process = AsyncMock()
if step_name == "parse":
processor.process.return_value = MagicMock(
success=True,
platform="bilibili",
content_type="video",
content_id="BV1test",
resolved_url="https://www.bilibili.com/video/BV1test",
original_url="https://www.bilibili.com/video/BV1test"
)
elif step_name == "download":
processor.process.return_value = MagicMock(
success=True,
metadata_file="/tmp/metadata.json",
content_file="/tmp/content.json",
title="Test Video",
author="Test Author"
)
elif step_name == "asr":
processor.process.return_value = MagicMock(
success=True,
tool="whisper",
has_subtitle=False,
output_files={"json": "/tmp/subtitle.json"}
)
elif step_name == "analyze":
processor.process.return_value = MagicMock(
success=True,
analysis_file="/tmp/analysis.md",
summary="Test summary",
main_topics=["topic1"],
key_insights=["insight1"],
tags=["tag1"],
stats={}
)
elif step_name == "archive":
processor.process.return_value = MagicMock(
success=True,
skipped=False,
platform="bilibili",
archive_file="/archive/bilibili/20260316_BV1test_analysis.md"
)
processors.append(processor)
return processors
class TestPipelineArchiveStep:
"""Test archive step integration in pipeline"""
@pytest.mark.asyncio
async def test_pipeline_includes_archive_step(self, mock_processors_with_archive, tmp_path):
"""Test that pipeline includes archive as final step"""
from kb_pipeline.pipeline import Pipeline
from kb_pipeline.schemas import PipelineConfig
config = PipelineConfig(
steps=["parse", "download", "asr", "analyze", "archive"],
output_dir=tmp_path,
skip_completed=False
)
with patch("kb_pipeline.pipeline.get_settings") as mock_settings:
mock_settings.return_value = MagicMock(intermediate_path=str(tmp_path))
pipeline = Pipeline(
processors=mock_processors_with_archive,
config=config,
output_dir=tmp_path
)
# Mock _parse_url and _get_content_dir
with patch.object(pipeline, '_parse_url') as mock_parse, \
patch.object(pipeline, '_get_content_dir') as mock_dir:
from kb_pipeline.link_parser import ParsedLink
mock_parse.return_value = ParsedLink(
platform="bilibili",
content_type="video",
content_id="BV1test",
original_url="https://www.bilibili.com/video/BV1test",
resolved_url="https://www.bilibili.com/video/BV1test"
)
mock_dir.return_value = tmp_path / "bilibili_BV1test"
result = await pipeline.run("https://www.bilibili.com/video/BV1test")
assert result.success is True
# Verify archive processor was called
archive_processor = next(p for p in mock_processors_with_archive if p.STEP_NAME == "archive")
archive_processor.process.assert_called_once()
class TestArchivePlatformDirectory:
"""Test that archive files go to correct platform directory"""
@pytest.mark.asyncio
async def test_archive_uses_platform_directory(self, tmp_path):
"""Test that archive files go to {archive_path}/{platform}/ directory"""
from kb_pipeline.processors.archive import ArchiveProcessor
from kb_pipeline.schemas import ArchiveInput
# Setup
archive_dir = tmp_path / "archive"
content_dir = tmp_path / "intermediate" / "bilibili_BV1test"
content_dir.mkdir(parents=True)
analysis_file = content_dir / "analysis.md"
analysis_file.write_text("# Test")
# Mock settings - patch at base module level where get_settings is called in __init__
with patch('kb_pipeline.processors.base.get_settings') as mock_get_settings:
mock_settings = MagicMock()
mock_settings.archive_path = str(archive_dir)
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(content_dir),
analysis_file=str(analysis_file),
content_type="video"
)
result = await processor.process(input_data)
assert result.success is True
# Verify platform subdirectory
archive_path = Path(result.archive_file)
assert archive_path.parent.name == "bilibili"
class TestArchiveNoDateSubdirectories:
"""Test that archive does not create date-based subdirectories"""
@pytest.mark.asyncio
async def test_archive_no_date_subdirectories(self, tmp_path):
"""Test that archive does not create date-based subdirectories"""
from kb_pipeline.processors.archive import ArchiveProcessor
from kb_pipeline.schemas import ArchiveInput
archive_dir = tmp_path / "archive"
content_dir = tmp_path / "intermediate" / "bilibili_BV1test"
content_dir.mkdir(parents=True)
analysis_file = content_dir / "analysis.md"
analysis_file.write_text("# Test")
with patch('kb_pipeline.processors.base.get_settings') as mock_get_settings:
mock_settings = MagicMock()
mock_settings.archive_path = str(archive_dir)
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(content_dir),
analysis_file=str(analysis_file),
content_type="video"
)
result = await processor.process(input_data)
# Verify no date-based subdirectories
archive_path = Path(result.archive_file)
# Parent should be platform dir, grandparent should be archive base
assert archive_path.parent.parent == archive_dir
# Check that parent is just "bilibili", not a date
assert archive_path.parent.name == "bilibili"