谭凯
7a93c52b42
- Refactor codebase into src/ (preprocessing, translation, assembly) - Add pipeline/ scripts for individual stages - Externalize configuration to config/config.yaml - Fix Cover Image preservation - Update documentation and manuals
125 lines
4.1 KiB
Python
125 lines
4.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
针对性测试脚本：复现用户报告的占位符丢失问题
|
|
直接读取 Manifest 中的特定失败 Item (p_00006, p_00011 等)
|
|
调用真实 LLM 进行翻译，并打印完整的 Prompt 和 Response
|
|
"""
|
|
import sys
|
|
import asyncio
|
|
import json
|
|
from pathlib import Path
|
|
from loguru import logger
|
|
|
|
# 添加 src 到路径
|
|
sys.path.insert(0, '.')
|
|
|
|
from src.manifest_manager import ManifestManager
|
|
from src.llm_client import LLMClient
|
|
from src.utils import load_config
|
|
|
|
# 配置日志
|
|
logger.remove()
|
|
logger.add(sys.stdout, level="DEBUG")
|
|
|
|
async def run_test():
|
|
print("=== 1. 加载配置 ===")
|
|
try:
|
|
config = load_config()
|
|
# 自动选择配置好的 provider
|
|
if 'v3' in config['providers'] and config['providers']['v3'].get('api_key'):
|
|
config['llm'] = config['providers']['v3']
|
|
print("Using Provider: v3")
|
|
elif 'openrouter' in config['providers']:
|
|
config['llm'] = config['providers']['openrouter']
|
|
print("Using Provider: openrouter")
|
|
else:
|
|
print("No valid provider found with API key in config!")
|
|
return
|
|
except Exception as e:
|
|
print(f"Config load failed: {e}")
|
|
return
|
|
|
|
print("\n=== 2. 加载真实 Manifest ===")
|
|
manifest_dir = Path("cache/manifests")
|
|
manifest_files = list(manifest_dir.glob("*.json"))
|
|
if not manifest_files:
|
|
print("Error: No manifest file found")
|
|
return
|
|
|
|
# 优先选择包含 "OpenAI" 的那个文件（用户截图）
|
|
target_manifest = next((f for f in manifest_files if "OpenAI" in f.name), manifest_files[0])
|
|
print(f"Loading: {target_manifest}")
|
|
|
|
manifest = ManifestManager(str(target_manifest))
|
|
if not manifest.load():
|
|
print("Failed to load manifest")
|
|
return
|
|
|
|
# 提取目标失败案例
|
|
target_ids = ["p_00006", "p_00009", "p_00011", "p_00013"]
|
|
# 也包括上下文以免错位 (p_00003 - p_00006)
|
|
context_ids = ["p_00003", "p_00004", "p_00005", "p_00006"]
|
|
|
|
items_to_test = []
|
|
|
|
# 测试组 1: 上下文错位测试
|
|
print("\n=== 准备测试组 1: 上下文错位及占位符 (p_00003-00006) ===")
|
|
group1 = []
|
|
for uid in context_ids:
|
|
item = manifest._items_by_id.get(uid)
|
|
if item:
|
|
# 强制清空旧翻译，模拟重新翻译
|
|
item.translation = None
|
|
item.translation_with_placeholders = None
|
|
group1.append(item)
|
|
print(f"Added {uid}: {item.text_with_placeholders}")
|
|
|
|
# 测试组 2: 独立行占位符丢失测试 (p_00009, p_00011)
|
|
print("\n=== 准备测试组 2: 独立行占位符 (p_00009, p_00011) ===")
|
|
group2 = []
|
|
for uid in ["p_00009", "p_00011"]:
|
|
item = manifest._items_by_id.get(uid)
|
|
if item:
|
|
item.translation = None
|
|
group2.append(item)
|
|
print(f"Added {uid}: {item.text_with_placeholders}")
|
|
|
|
client = LLMClient(config)
|
|
|
|
# 执行测试 1
|
|
if group1:
|
|
print("\n\n>>> 执行 Group 1 测试 (Context Alignment) <<<")
|
|
# 打印 Prompt 预览
|
|
prompt = client._build_prompt(group1, mode="chinese")
|
|
print("\n[PROMPT PREVIEW]:")
|
|
print("-" * 20)
|
|
print(prompt)
|
|
print("-" * 20)
|
|
|
|
# 调用 LLM
|
|
print("\n[CALLING LLM]...")
|
|
results = await client.translate_chunk(group1, mode="chinese")
|
|
|
|
print("\n[RESULTS Group 1]:")
|
|
for uid, trans in results.items():
|
|
print(f"{uid}: {trans}")
|
|
if uid == "p_00006":
|
|
print(f" > Contains φ1φ? {'φ1φ' in trans}")
|
|
|
|
# 执行测试 2
|
|
if group2:
|
|
print("\n\n>>> 执行 Group 2 测试 (Isolated Placeholders) <<<")
|
|
prompt = client._build_prompt(group2, mode="chinese")
|
|
print("\n[PROMPT PREVIEW]:")
|
|
print(prompt)
|
|
|
|
print("\n[CALLING LLM]...")
|
|
results = await client.translate_chunk(group2, mode="chinese")
|
|
|
|
print("\n[RESULTS Group 2]:")
|
|
for uid, trans in results.items():
|
|
print(f"{uid}: {trans}")
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(run_test())
|