369 lines
13 KiB
Python
369 lines
13 KiB
Python
|
"""
|
||
|
|
Comprehensive tests for NLPProcessingPipeline integration.
|
||
|
|
"""
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
import asyncio
|
||
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
||
|
|
|
||
|
|
from sentiment_engine.nlp.pipeline import NLPProcessingPipeline
|
||
|
|
from sentiment_engine.nlp.entity_extraction import EntityExtractor, AssetMapper
|
||
|
|
from sentiment_engine.nlp.sentiment_emotion import SentimentEmotionAnalyzer
|
||
|
|
from sentiment_engine.nlp.event_classification import EventClassifier
|
||
|
|
from sentiment_engine.nlp.temporal import TemporalAnchorer
|
||
|
|
from sentiment_engine.nlp.credibility import CredibilityScorer
|
||
|
|
from sentiment_engine.schemas.payload import NormalizedPayload, SourceType, AssetMention, EngagementMetrics
|
||
|
|
from sentiment_engine.schemas.processed import ProcessedItem, EntityExtraction, SentimentScores, EmotionScores, EventClassification, TemporalAnchor, CredibilityScore
|
||
|
|
|
||
|
|
|
||
|
|
class TestNLPProcessingPipeline:
|
||
|
|
"""Tests for NLPProcessingPipeline"""
|
||
|
|
|
||
|
|
@pytest.fixture
|
||
|
|
def pipeline(self):
|
||
|
|
return NLPProcessingPipeline()
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_initialize_all_components(self, pipeline):
|
||
|
|
"""Should initialize all components"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
assert pipeline._initialized is True
|
||
|
|
assert pipeline.entity_extractor is not None
|
||
|
|
assert pipeline.sentiment_analyzer is not None
|
||
|
|
assert pipeline.event_classifier is not None
|
||
|
|
assert pipeline.temporal_anchorer is not None
|
||
|
|
assert pipeline.credibility_scorer is not None
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_returns_processed_item(self, pipeline):
|
||
|
|
"""Process should return complete ProcessedItem"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test_source",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=100,
|
||
|
|
raw_text="Bitcoin surges to $100k as institutional inflows surge!",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
|
||
|
|
assert isinstance(result, ProcessedItem)
|
||
|
|
assert result.payload_id is not None
|
||
|
|
assert result.source_id == "test_source"
|
||
|
|
assert len(result.entities) >= 0
|
||
|
|
assert isinstance(result.sentiment_per_asset, dict)
|
||
|
|
assert isinstance(result.emotions_per_asset, dict)
|
||
|
|
assert isinstance(result.events, list)
|
||
|
|
assert result.temporal is not None
|
||
|
|
assert result.credibility is not None
|
||
|
|
assert result.processing_latency_ms > 0
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_with_asset_mentions(self, pipeline):
|
||
|
|
"""Process should use asset mentions from payload"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test_source",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=100,
|
||
|
|
raw_text="BTC surges to new high!",
|
||
|
|
asset_mentions=[
|
||
|
|
AssetMention(
|
||
|
|
asset_id="BTC",
|
||
|
|
mention_span=(0, 3),
|
||
|
|
confidence=0.9,
|
||
|
|
source_text="BTC",
|
||
|
|
mention_type="ticker"
|
||
|
|
)
|
||
|
|
],
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
|
||
|
|
# Should have sentiment for BTC
|
||
|
|
assert "BTC" in result.sentiment_per_asset
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_batch(self, pipeline):
|
||
|
|
"""Process batch should handle multiple payloads"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payloads = [
|
||
|
|
NormalizedPayload(
|
||
|
|
source_id=f"source_{i}",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=100,
|
||
|
|
raw_text=f"Bitcoin news {i}",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
for i in range(5)
|
||
|
|
]
|
||
|
|
|
||
|
|
results = await pipeline.process_batch(payloads)
|
||
|
|
|
||
|
|
assert len(results) == 5
|
||
|
|
assert all(isinstance(r, ProcessedItem) for r in results)
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_batch_concurrency_limit(self, pipeline):
|
||
|
|
"""Process batch should respect semaphore limit"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payloads = [
|
||
|
|
NormalizedPayload(
|
||
|
|
source_id=f"source_{i}",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=100,
|
||
|
|
raw_text=f"Bitcoin news {i}",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
for i in range(20)
|
||
|
|
]
|
||
|
|
|
||
|
|
# Should complete without errors
|
||
|
|
results = await pipeline.process_batch(payloads)
|
||
|
|
assert len(results) == 20
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_handles_errors_gracefully(self, pipeline):
|
||
|
|
"""Process should handle component errors gracefully"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
# Create a payload that might cause issues
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test_source",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=0,
|
||
|
|
raw_text="",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
# Should not crash even with empty text
|
||
|
|
try:
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
assert isinstance(result, ProcessedItem)
|
||
|
|
except Exception:
|
||
|
|
# If it raises, that's also acceptable behavior
|
||
|
|
pass
|
||
|
|
|
||
|
|
def test_get_model_versions(self, pipeline):
|
||
|
|
"""Should return model versions"""
|
||
|
|
versions = pipeline.get_model_versions()
|
||
|
|
assert isinstance(versions, dict)
|
||
|
|
|
||
|
|
|
||
|
|
class TestPipelineComponentInteraction:
|
||
|
|
"""Tests for component interactions within pipeline"""
|
||
|
|
|
||
|
|
@pytest.fixture
|
||
|
|
def pipeline(self):
|
||
|
|
return NLPProcessingPipeline()
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_entity_extraction_feeds_sentiment(self, pipeline):
|
||
|
|
"""Entities extracted should feed into sentiment analysis"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=50,
|
||
|
|
raw_text="BTC and ETH both surge",
|
||
|
|
asset_mentions=[
|
||
|
|
AssetMention(asset_id="BTC", mention_span=(0, 3), confidence=0.9, source_text="BTC", mention_type="ticker"),
|
||
|
|
AssetMention(asset_id="ETH", mention_span=(8, 11), confidence=0.9, source_text="ETH", mention_type="ticker"),
|
||
|
|
],
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
|
||
|
|
# Both assets should have sentiment
|
||
|
|
assert "BTC" in result.sentiment_per_asset
|
||
|
|
assert "ETH" in result.sentiment_per_asset
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_event_classification_uses_entities(self, pipeline):
|
||
|
|
"""Event classification should use extracted entities"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=50,
|
||
|
|
raw_text="SEC approves Bitcoin ETF for trading",
|
||
|
|
asset_mentions=[
|
||
|
|
AssetMention(asset_id="BTC", mention_span=(20, 23), confidence=0.9, source_text="BTC", mention_type="ticker"),
|
||
|
|
],
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
|
||
|
|
# Should detect regulatory event involving BTC
|
||
|
|
regulatory_events = [e for e in result.events if e.event_type.value == "regulatory"]
|
||
|
|
assert len(regulatory_events) >= 1
|
||
|
|
assert "BTC" in regulatory_events[0].assets_involved
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_temporal_anchoring_uses_publish_ts(self, pipeline):
|
||
|
|
"""Temporal anchoring should use publish timestamp"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
publish_ts = 1700000000.0
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.8,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=publish_ts,
|
||
|
|
content_length=50,
|
||
|
|
raw_text="Breaking: BTC crashes now!",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
|
||
|
|
assert result.temporal.time_horizon == "immediate"
|
||
|
|
assert result.temporal.is_breaking is True
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_credibility_scoring_uses_all_factors(self, pipeline):
|
||
|
|
"""Credibility should combine all factors"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="high_cred_source",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.9,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=200,
|
||
|
|
raw_text="Bitcoin surges to $100k as institutional inflows surge. BlackRock IBIT sees record inflows.",
|
||
|
|
metadata={
|
||
|
|
"author": "analyst",
|
||
|
|
"engagement_metrics": {"likes": 1000, "retweets": 100, "replies": 50, "views": 10000}
|
||
|
|
}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
|
||
|
|
# High credibility source + good content + good engagement = high composite
|
||
|
|
assert result.credibility.composite > 0.5
|
||
|
|
|
||
|
|
|
||
|
|
class TestPipelineEdgeCases:
|
||
|
|
"""Edge case tests for pipeline"""
|
||
|
|
|
||
|
|
@pytest.fixture
|
||
|
|
def pipeline(self):
|
||
|
|
return NLPProcessingPipeline()
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_empty_text(self, pipeline):
|
||
|
|
"""Should handle empty text"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.5,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=0,
|
||
|
|
raw_text="",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
assert isinstance(result, ProcessedItem)
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_very_long_text(self, pipeline):
|
||
|
|
"""Should handle very long text"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
long_text = "Bitcoin surges. " * 1000
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.5,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=len(long_text),
|
||
|
|
raw_text=long_text,
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
assert isinstance(result, ProcessedItem)
|
||
|
|
assert result.processing_latency_ms < 30000 # Should complete within 30s
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_unicode(self, pipeline):
|
||
|
|
"""Should handle unicode text"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.5,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=50,
|
||
|
|
raw_text="Bitcoin 🚀 surges to $100k 💎",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
assert isinstance(result, ProcessedItem)
|
||
|
|
|
||
|
|
@pytest.mark.asyncio
|
||
|
|
async def test_process_special_characters(self, pipeline):
|
||
|
|
"""Should handle special characters"""
|
||
|
|
await pipeline.initialize()
|
||
|
|
|
||
|
|
payload = NormalizedPayload(
|
||
|
|
source_id="test",
|
||
|
|
source_type=SourceType.NEWS,
|
||
|
|
source_credibility_base=0.5,
|
||
|
|
ingest_ts=1700000000.0,
|
||
|
|
publish_ts=1700000000.0,
|
||
|
|
content_length=50,
|
||
|
|
raw_text="BTC/USD: $50,000.00 (24h: +5.2%)",
|
||
|
|
metadata={}
|
||
|
|
)
|
||
|
|
|
||
|
|
result = await pipeline.process(payload)
|
||
|
|
assert isinstance(result, ProcessedItem)
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
pytest.main([__file__, "-v"])
|