Add sentiment_engine with CryptoSentimentCalibrator fixes - improved keyword lists, lowered FinBERT threshold, added neutral handling

sentiment_engine/tests/unit/test_schemas_payload.py

@@ -0,0 +1,92 @@
+"""Tests for payload schemas"""
+
+import pytest
+from datetime import datetime
+from sentiment_engine.schemas.payload import NormalizedPayload, SourceType, AssetMention, EngagementMetrics
+
+
+class TestNormalizedPayload:
+    """Tests for NormalizedPayload schema"""
+
+    def test_valid_payload(self):
+        payload = NormalizedPayload(
+            source_id="test_source",
+            source_type=SourceType.NEWS,
+            source_credibility_base=0.8,
+            ingest_ts=datetime.now().timestamp(),
+            publish_ts=datetime.now().timestamp(),
+            asset_mentions=[AssetMention(asset_id="BTC", mention_span=(0, 3), confidence=0.9, source_text="BTC", mention_type="ticker")],
+            raw_text="BTC surges to new highs",
+            title="BTC Surges",
+            url="https://test.com",
+            author="Test Author",
+            content_length=100,
+            language="en"
+        )
+        assert payload.source_id == "test_source"
+        assert payload.has_assets is True
+        assert payload.get_assets() == ["BTC"]
+
+    def test_empty_text_raises(self):
+        with pytest.raises(ValueError, match="raw_text cannot be empty"):
+            NormalizedPayload(
+                source_id="test",
+                source_type=SourceType.NEWS,
+                source_credibility_base=0.5,
+                ingest_ts=1234567890.0,
+                raw_text="",
+                content_length=0,
+                language="en"
+            )
+
+    def test_whitespace_text_raises(self):
+        with pytest.raises(ValueError, match="raw_text cannot be empty"):
+            NormalizedPayload(
+                source_id="test",
+                source_type=SourceType.NEWS,
+                source_credibility_base=0.5,
+                ingest_ts=1234567890.0,
+                raw_text="   ",
+                content_length=0,
+                language="en"
+            )
+
+
+class TestAssetMention:
+    """Tests for AssetMention schema"""
+
+    def test_valid_mention(self):
+        mention = AssetMention(
+            asset_id="BTC",
+            mention_span=(0, 3),
+            confidence=0.9,
+            source_text="BTC",
+            mention_type="ticker"
+        )
+        assert mention.asset_id == "BTC"
+        assert mention.confidence == 0.9
+
+
+class TestEngagementMetrics:
+    """Tests for EngagementMetrics"""
+
+    def test_total_engagement(self):
+        metrics = EngagementMetrics(retweets=10, likes=50, replies=5, upvotes=100, comments=20)
+        assert metrics.total_engagement() == 185
+
+    def test_default_zero(self):
+        metrics = EngagementMetrics()
+        assert metrics.total_engagement() == 0
+
+
+class TestSourceType:
+    """Tests for SourceType enum"""
+
+    def test_all_values(self):
+        assert SourceType.NEWS == "news"
+        assert SourceType.SOCIAL == "social"
+        assert SourceType.EXCHANGE_ANN == "exchange_ann"
+        assert SourceType.REGULATORY == "regulatory"
+        assert SourceType.CORPORATE == "corporate"
+        assert SourceType.FORUM == "forum"
+        assert SourceType.ON_CHAIN == "on_chain"