Files
speaking-practice/tests/subtitle_ai_test.py
T

50 lines
1.6 KiB
Python

import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from backend.subtitle_ai import process_subtitles_with_ai
class FakeClient:
def chat_json(self, system_prompt, user_payload):
assert "不要修改时间轴" in system_prompt
assert "start" not in user_payload["cues"][0]
assert "end" not in user_payload["cues"][0]
return {
"translations": [
{
"index": 1,
"start": "00:00:99.000",
"end": "00:00:99.999",
"zh": "我第一次做投资人是在 24 岁。",
}
]
}
def test_process_subtitles_with_ai_returns_clean_en_and_zh_vtt():
raw = """WEBVTT
00:00:00.872 --> 00:00:04.959
My first job as an investor was when I was 24 years old,
00:00:00.872 --> 00:00:04.959
My first job as an investor was when I was 24 years old,
"""
result = process_subtitles_with_ai(raw, FakeClient())
assert "My first job as an investor" in result["subtitle_en_content"]
assert "我第一次做投资人是在 24 岁。" in result["subtitle_zh_content"]
assert result["report"]["duplicate_count"] == 1
assert result["report"]["translation_count"] == 1
assert "00:00:00.872 --> 00:00:04.959" in result["subtitle_en_content"]
assert "00:00:00.872 --> 00:00:04.959" in result["subtitle_zh_content"]
assert "timestamp_calibrated" in result["report"]
assert result["report"]["timestamp_calibrated"] is False
if __name__ == "__main__":
test_process_subtitles_with_ai_returns_clean_en_and_zh_vtt()