epub_bilingual_translator/scripts/test_short_id_strategy.py

#!/usr/bin/env python3
"""
Debug script to show chunk content and test short ID strategy.
"""

import asyncio
import json
import os
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent))

from dotenv import load_dotenv
from src.manifest_manager import ManifestManager
from src.llm_client import LLMClient
from src.data_model import ManifestEntry

load_dotenv()

# Configuration
MANIFEST_PATH = Path("cache/Empire of AI Dreams and Nightmares in Sam Altmans OpenAI (Karen Hao)_manifest.json")
API_KEY = os.getenv("V3_API_KEY")
BASE_URL = "https://api.gpt.ge/v1"
MODEL = "gemini-3-flash-preview"
EXTRA_HEADERS = {"x-foo": "true"}


def show_current_chunk_format():
    """Show current chunk format (problematic)."""
    print("\n" + "="*60)
    print("当前 Chunk 格式 (有问题)")
    print("="*60)
    
    # Load manifest
    manager = ManifestManager(MANIFEST_PATH)
    manager.load()
    
    # Get sample entries with placeholders
    samples = [e for e in manager.entries if e.placeholders][:3]
    
    print("\n发送给 LLM 的格式 (当前):")
    print("-"*60)
    for item in samples:
        context = item.context or "BODY"
        print(f"{item.entry_id} [{context}] {item.original_text[:50]}...")
    
    print("\n问题分析:")
    print("  1. entry_id 太长 (包含 UUID): 容易被 LLM 截断或修改")
    print("  2. [BODY] context 没必要发送")
    print("  3. 依赖 LLM 精确复制长 ID，不可靠")


def show_proposed_chunk_format():
    """Show proposed short ID chunk format."""
    print("\n" + "="*60)
    print("建议的 Chunk 格式 (短 ID)")
    print("="*60)
    
    manager = ManifestManager(MANIFEST_PATH)
    manager.load()
    
    samples = [e for e in manager.entries if e.placeholders][:5]
    
    print("\n发送给 LLM 的格式 (建议):")
    print("-"*60)
    
    # Build with short IDs
    id_map = {}  # short_id -> entry_id
    for i, item in enumerate(samples, 1):
        short_id = f"#{i}"
        id_map[short_id] = item.entry_id
        text = item.original_text[:60]
        print(f"{short_id}: {text}...")
    
    print("\n期望 LLM 返回的格式:")
    print("-"*60)
    print("#1: φ1φpenguinrandomhouse.com（保持不翻译）")
    print("#2: 该产品在欧盟的产品安全授权代表为 φ1φPenguin Random House Irelandφ/1φ...")
    print("#3: φ1φ献辞")
    print("#4: φ1φ题记")  
    print("#5: φ1φ作者说明")
    
    print("\n优势:")
    print("  1. 短 ID (#1, #2...) 不会被 LLM 弄乱")
    print("  2. 去掉了无用的 context 标签")
    print("  3. 解析更可靠：用正则 ^#(\\d+): 匹配")
    print("  4. ID 映射表保留在代码中，用于还原")
    
    print("\n映射表 (代码内保留):")
    for short_id, full_id in id_map.items():
        print(f"  {short_id} -> {full_id[:50]}...")


async def test_short_id_translation():
    """Test translation with short ID format."""
    print("\n" + "="*60)
    print("测试短 ID 翻译")
    print("="*60)
    
    manager = ManifestManager(MANIFEST_PATH)
    manager.load()
    
    # Get 5 entries with varied content
    samples = [e for e in manager.entries if len(e.original_text) > 20][:5]
    
    # Build prompt with short IDs
    id_map = {}
    lines = []
    for i, item in enumerate(samples, 1):
        short_id = f"#{i}"
        id_map[short_id] = item.entry_id
        text = item.original_text.replace('\n', ' ').strip()
        lines.append(f"{short_id}: {text}")
    
    user_prompt = "\n".join(lines)
    
    print("\n发送给 LLM 的 Prompt:")
    print("-"*60)
    print(user_prompt)
    
    # Create client
    from openai import AsyncOpenAI
    client = AsyncOpenAI(
        base_url=BASE_URL,
        api_key=API_KEY,
        default_headers=EXTRA_HEADERS
    )
    
    system_prompt = """You are a professional English to Chinese translator.

Translate each line to Chinese. Keep the format:
- Each line starts with #N: (keep this ID exactly)
- Preserve any φXφ placeholders exactly as-is
- Only output translations, no explanations

Example input:
#1: Hello world
#2: φ1φClick hereφ/1φ to continue

Example output:
#1: 你好世界
#2: φ1φ点击这里φ/1φ 继续"""
    
    print("\n发送请求...")
    
    try:
        resp = await client.chat.completions.create(
            model=MODEL,
            messages=[
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": user_prompt}
            ],
            temperature=0.3,
        )
        raw_response = resp.choices[0].message.content.strip()
        
        print("\nLLM 返回:")
        print("-"*60)
        print(raw_response)
        
        # Parse with short ID
        print("\n解析结果:")
        print("-"*60)
        import re
        results = {}
        for line in raw_response.split("\n"):
            line = line.strip()
            match = re.match(r'^#(\d+):\s*(.+)$', line)
            if match:
                short_id = f"#{match.group(1)}"
                translation = match.group(2)
                if short_id in id_map:
                    full_id = id_map[short_id]
                    results[full_id] = translation
                    print(f"  {short_id} -> {translation[:40]}...")
        
        print(f"\n成功解析: {len(results)}/{len(samples)}")
        
    finally:
        await client.close()


async def main():
    print("="*60)
    print("Chunk ID 策略分析与测试")
    print("="*60)
    
    if not MANIFEST_PATH.exists():
        print(f"ERROR: Manifest not found at {MANIFEST_PATH}")
        return
    
    # 1. Show current format (problems)
    show_current_chunk_format()
    
    # 2. Show proposed format
    show_proposed_chunk_format()
    
    # 3. Test short ID translation
    if API_KEY:
        await test_short_id_translation()
    else:
        print("\n跳过测试 (V3_API_KEY 未设置)")
    
    print("\n" + "="*60)
    print("分析完成")
    print("="*60)


if __name__ == "__main__":
    asyncio.run(main())