99 lines
3.2 KiB
Python
99 lines
3.2 KiB
Python
# coding=utf-8
|
|
"""
|
|
T3_Voice.py - 语音交互流程测试 (Voice Interaction Test)
|
|
|
|
【核心功能】
|
|
- 动态交互：执行“截图 -> 识别语音 -> 点击转文字 -> 再次截图 -> 提取内容”的完整闭环。
|
|
- 动作验证：测试长按操作、菜单识别、转文字等待逻辑。
|
|
- 异步逻辑：验证异步 OCR 任务是否能正确捕获转文字后的内容。
|
|
|
|
【使用场景】
|
|
- 验证微信版本更新后“转文字”按钮位置是否变化。
|
|
- 调试语音消息“点不开”或“转完没内容”的问题。
|
|
- 测试语音转文字的防死循环机制。
|
|
"""
|
|
import os
|
|
import sys
|
|
import logging
|
|
import asyncio
|
|
import cv2
|
|
|
|
# Add project root
|
|
project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
|
if project_root not in sys.path:
|
|
sys.path.append(project_root)
|
|
|
|
from WeiXin import WxUtil
|
|
|
|
# Setup Logger
|
|
logger = logging.getLogger("T3_Voice")
|
|
|
|
# Configure Root Logger to ensure all logs (including WxUtil) go to file
|
|
root_logger = logging.getLogger()
|
|
root_logger.setLevel(logging.INFO)
|
|
|
|
# Ensure Log Directory exists
|
|
if hasattr(WxUtil, 'LOG_DIR'):
|
|
log_dir = WxUtil.LOG_DIR
|
|
else:
|
|
log_dir = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "Logs")
|
|
|
|
if not os.path.exists(log_dir):
|
|
os.makedirs(log_dir)
|
|
|
|
# File Handler
|
|
log_file = os.path.join(log_dir, "T3_Voice.log")
|
|
fh = logging.FileHandler(log_file, mode='w', encoding='utf-8')
|
|
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
|
fh.setFormatter(formatter)
|
|
root_logger.addHandler(fh)
|
|
|
|
# Console Handler (if not already added by WxUtil)
|
|
if not any(isinstance(h, logging.StreamHandler) for h in root_logger.handlers):
|
|
ch = logging.StreamHandler()
|
|
ch.setFormatter(formatter)
|
|
root_logger.addHandler(ch)
|
|
|
|
async def main():
|
|
logger.info("--- T3: Voice Processing Test ---")
|
|
|
|
# 1. Connect
|
|
d = WxUtil.connect_device()
|
|
if not d:
|
|
logger.error("Device connection failed.")
|
|
return
|
|
|
|
# 2. Screenshot
|
|
screenshot_path = os.path.join(WxUtil.OUTPUT_DIR, "T3_Screenshot.jpg")
|
|
debug_path = os.path.join(WxUtil.OUTPUT_DIR, "T3_Debug.jpg")
|
|
|
|
logger.info("Taking screenshot...")
|
|
d.screenshot(screenshot_path)
|
|
logger.info("Initial screenshot taken.")
|
|
|
|
# 3. Use analyze_chat_image with strategy='ALL' to test conversion
|
|
# This simulates the real bot behavior for voice messages
|
|
logger.info("Running WxUtil.analyze_chat_image (Strategy=ALL)...")
|
|
|
|
# This function handles the click -> convert -> rescan loop internally
|
|
final_messages, _ = await WxUtil.analyze_chat_image(
|
|
screenshot_path,
|
|
debug_path,
|
|
device=d,
|
|
process_strategy="ALL"
|
|
)
|
|
|
|
# 4. Output Result
|
|
logger.info("--- Final Voice Results ---")
|
|
voice_msgs = [m for m in final_messages if m['type'] == 'voice']
|
|
if not voice_msgs:
|
|
logger.info("No voice messages found.")
|
|
else:
|
|
for i, msg in enumerate(voice_msgs):
|
|
content = msg.get('content')
|
|
converted_status = "YES" if msg.get('is_converted') else "NO"
|
|
logger.info(f"Voice [{i}] Sender: {msg['sender']} | Converted: {converted_status} | Content: {content}")
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|