#!/usr/bin/env python3
"""模拟翻译流程，检查 _build_prompt 使用的数据"""
import sys
sys.path.insert(0, '.')

from src.manifest_manager import ManifestManager
from src.text_processor import TextProcessor

# 加载 manifest
manifest = ManifestManager("cache/manifests/Empire of AI Dreams and Nightmares in Sam Altmans OpenAI (Karen Hao)_chinese_manifest.json")
manifest.load()

# 创建 chunks (模拟 create_chunks_from_manifest)
processor = TextProcessor({})
chunks = processor.create_chunks_from_manifest(manifest, mode="chinese")

print(f"Total chunks: {len(chunks)}")

if chunks:
    # 取第一个 chunk 的前几个 item
    first_chunk = chunks[0]
    print(f"First chunk has {len(first_chunk)} items")
    
    for item in first_chunk[:5]:
        print(f"\n=== ITEM {item.global_id} ===")
        print(f"  type(item): {type(item)}")
        print(f"  clean_text: '{item.clean_text[:50]}...'")
        print(f"  text_with_placeholders: '{item.text_with_placeholders[:50] if item.text_with_placeholders else 'EMPTY'}...'")
        print(f"  has φ in twp: {'φ' in (item.text_with_placeholders or '')}")
        print(f"  placeholder_map: {item.placeholder_map}")
        
        # 模拟 _build_prompt 的逻辑
        if item.text_with_placeholders:
            text = item.text_with_placeholders
        else:
            text = item.clean_text
        prompt_line = f"{item.global_id} [BODY] {text}"
        print(f"  -> Will send to LLM: '{prompt_line[:80]}...'")
        print(f"  -> Prompt contains φ: {'φ' in prompt_line}")