Spaces:
Running
Running
File size: 7,368 Bytes
08367f3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 |
"""
Unit tests for sentiment analysis API
These tests verify:
- All endpoints work correctly
- Sentiment analysis returns expected results
- Input validation catches errors
- Error handling works properly
"""
from fastapi.testclient import TestClient
from src.main import app
import pytest
# Create test client
client = TestClient(app)
# ============================================
# Health Check Tests
# ============================================
def test_root_endpoint():
"""Test the root endpoint returns health status"""
response = client.get("/")
assert response.status_code == 200
data = response.json()
assert data["status"] == "healthy"
assert data["service"] == "sentiment-api"
assert "version" in data
def test_health_endpoint():
"""Test the /health endpoint for Kubernetes"""
response = client.get("/health")
assert response.status_code == 200
assert response.json() == {"status": "ok"}
# ============================================
# Sentiment Analysis Tests
# ============================================
def test_analyze_positive_sentiment():
"""Test sentiment analysis with clearly positive text"""
response = client.post(
"/analyze",
json={"text": "I absolutely love this product! It's amazing and wonderful!"}
)
assert response.status_code == 200
data = response.json()
# Verify response structure
assert "text" in data
assert "sentiment" in data
assert "confidence" in data
assert "processing_time_ms" in data
# Verify sentiment detection
assert data["sentiment"] == "POSITIVE"
assert data["confidence"] > 0.9 # Should be very confident
assert data["processing_time_ms"] > 0 # Should take some time
def test_analyze_negative_sentiment():
"""Test sentiment analysis with clearly negative text"""
response = client.post(
"/analyze",
json={"text": "This is terrible, horrible, and awful. I hate it."}
)
assert response.status_code == 200
data = response.json()
assert data["sentiment"] == "NEGATIVE"
assert data["confidence"] > 0.9
def test_analyze_neutral_text():
"""Test sentiment analysis with neutral text"""
response = client.post(
"/analyze",
json={"text": "The item is blue."}
)
assert response.status_code == 200
data = response.json()
# Neutral text might be classified as either POSITIVE or NEGATIVE
# with lower confidence
assert data["sentiment"] in ["POSITIVE", "NEGATIVE"]
assert "confidence" in data
# ============================================
# Input Validation Tests
# ============================================
def test_empty_text_rejected():
"""Test that empty text is rejected"""
response = client.post(
"/analyze",
json={"text": ""}
)
assert response.status_code == 422 # Validation error
# FastAPI returns detailed validation errors
def test_missing_text_field():
"""Test that missing text field is rejected"""
response = client.post(
"/analyze",
json={}
)
assert response.status_code == 422
def test_text_too_long():
"""Test that text exceeding max length is rejected"""
long_text = "a" * 513 # Max is 512 characters
response = client.post(
"/analyze",
json={"text": long_text}
)
assert response.status_code == 422
def test_non_string_text():
"""Test that non-string text is rejected"""
response = client.post(
"/analyze",
json={"text": 12345} # Number instead of string
)
assert response.status_code == 422
# ============================================
# Response Format Tests
# ============================================
def test_response_contains_all_fields():
"""Test that response has all required fields"""
response = client.post(
"/analyze",
json={"text": "Great product!"}
)
assert response.status_code == 200
data = response.json()
# Check all required fields exist
required_fields = ["text", "sentiment", "confidence", "processing_time_ms"]
for field in required_fields:
assert field in data, f"Missing field: {field}"
def test_confidence_is_valid_probability():
"""Test that confidence is between 0 and 1"""
response = client.post(
"/analyze",
json={"text": "Excellent!"}
)
data = response.json()
confidence = data["confidence"]
assert 0 <= confidence <= 1, "Confidence must be between 0 and 1"
def test_sentiment_is_valid_label():
"""Test that sentiment is either POSITIVE or NEGATIVE"""
response = client.post(
"/analyze",
json={"text": "Test text"}
)
data = response.json()
sentiment = data["sentiment"]
assert sentiment in ["POSITIVE", "NEGATIVE"], "Invalid sentiment label"
# ============================================
# Edge Case Tests
# ============================================
def test_special_characters():
"""Test handling of special characters"""
response = client.post(
"/analyze",
json={"text": "Wow!!! This is #amazing 😊 @company"}
)
assert response.status_code == 200
# Should handle emojis and special chars gracefully
def test_multiple_languages_english_only():
"""Test that non-English text still gets processed"""
# Note: DistilBERT is trained on English
# This test just verifies it doesn't crash
response = client.post(
"/analyze",
json={"text": "Hola mundo"}
)
assert response.status_code == 200
# May not be accurate, but shouldn't crash
def test_very_short_text():
"""Test analysis of very short text"""
response = client.post(
"/analyze",
json={"text": "Good"}
)
assert response.status_code == 200
data = response.json()
assert data["sentiment"] == "POSITIVE"
def test_maximum_length_text():
"""Test analysis of text at maximum allowed length"""
max_text = "a" * 512 # Exactly at max
response = client.post(
"/analyze",
json={"text": max_text}
)
assert response.status_code == 200
# ============================================
# Performance Tests
# ============================================
def test_response_time_reasonable():
"""Test that response time is reasonable (< 5 seconds)"""
import time
start = time.time()
response = client.post(
"/analyze",
json={"text": "Test performance"}
)
elapsed = time.time() - start
assert response.status_code == 200
assert elapsed < 5.0, f"Response took {elapsed}s, should be < 5s"
# ============================================
# API Documentation Tests
# ============================================
def test_openapi_docs_available():
"""Test that API documentation is available"""
response = client.get("/docs")
assert response.status_code == 200
def test_openapi_json_available():
"""Test that OpenAPI JSON schema is available"""
response = client.get("/openapi.json")
assert response.status_code == 200
schema = response.json()
assert "openapi" in schema
assert "info" in schema
assert "paths" in schema |