tests/test_real_data.py

import requests
import time
import os

BACKEND_URL = os.getenv("BACKEND_URL", "http://localhost:8000")

def test_real_data():
    # Real data: A short news paragraph about Uganda
    real_text = (
        "Uganda, famously known as the Pearl of Africa, is a landlocked country in East Africa. "
        "It is bordered to the east by Kenya, to the north by South Sudan, to the west by the Democratic Republic of the Congo, "
        "to the south-west by Rwanda, and to the south by Tanzania. The southern part of the country includes a substantial portion of Lake Victoria, "
        "shared with Kenya and Tanzania. Uganda takes its name from the Buganda kingdom, which encompasses a large portion of the south of the country, "
        "including the capital Kampala."
    )
    
    target_language = "Luganda"
    
    print("Submitting real data for translation to:", target_language)
    
    # 1. Submit text
    resp = requests.post(
        f"{BACKEND_URL}/pipeline/submit",
        json={"text": real_text, "target_language": target_language},
        timeout=15
    )
    resp.raise_for_status()
    job_id = resp.json()["request_id"]
    print(f"Job submitted. ID: {job_id}")
    
    # 2. Poll for completion
    start = time.time()
    while True:
        status_resp = requests.get(f"{BACKEND_URL}/pipeline/status/{job_id}", timeout=10)
        status_resp.raise_for_status()
        data = status_resp.json()
        
        if data["status"] == "completed":
            print(f"\n✅ Job completed in {time.time() - start:.2f} seconds!")
            result = data["result"]
            print("\n--- SUMMARY ---")
            print(result["summary"])
            print("\n--- TRANSLATION (Luganda) ---")
            print(result["translated_summary"])
            break
        elif data["status"] == "failed":
            print(f"\n❌ Job failed: {data.get('error')}")
            return
            
        print(".", end="", flush=True)
        time.sleep(2)
        
    # 3. Download Audio
    print(f"\nDownloading audio for job {job_id}...")
    audio_resp = requests.get(f"{BACKEND_URL}/pipeline/audio/{job_id}", timeout=10)
    
    if audio_resp.status_code == 200:
        audio_file = "real_data_audio.wav"
        with open(audio_file, "wb") as f:
            f.write(audio_resp.content)
        print(f"✅ Audio downloaded successfully: {audio_file} ({len(audio_resp.content)} bytes)")
    else:
        print(f"❌ Failed to download audio. Status: {audio_resp.status_code}, Detail: {audio_resp.text}")

if __name__ == "__main__":
    test_real_data()