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
34 lines
1.2 KiB
Python
34 lines
1.2 KiB
Python
#!/usr/bin/env python3
|
|
"""直接检查 manifest 中的 pending items"""
|
|
import sys
|
|
sys.path.insert(0, '.')
|
|
|
|
from src.manifest_manager import ManifestManager
|
|
|
|
# 加载 manifest
|
|
manifest = ManifestManager("cache/manifests/Empire of AI Dreams and Nightmares in Sam Altmans OpenAI (Karen Hao)_chinese_manifest.json")
|
|
manifest.load()
|
|
|
|
# 获取 pending items（这是 create_chunks_from_manifest 内部调用的）
|
|
pending_items = manifest.get_items(status="pending")
|
|
print(f"Pending items: {len(pending_items)}")
|
|
|
|
# 如果没有 pending，获取所有
|
|
if not pending_items:
|
|
print("No pending items, getting all...")
|
|
pending_items = manifest.get_items()
|
|
print(f"All items: {len(pending_items)}")
|
|
|
|
# 检查前 10 个 item
|
|
for item in pending_items[:10]:
|
|
twp = item.text_with_placeholders
|
|
has_phi = 'φ' in twp if twp else False
|
|
inner_ph = {k: v for k, v in item.placeholder_map.items() if not k.startswith('_')} if item.placeholder_map else {}
|
|
|
|
print(f"\n{item.global_id}:")
|
|
print(f" status: {item.status}")
|
|
print(f" clean_text: '{item.clean_text[:40]}...'")
|
|
print(f" text_with_placeholders: '{twp[:40] if twp else 'EMPTY'}...'")
|
|
print(f" has φ: {has_phi}")
|
|
print(f" inner_placeholders: {list(inner_ph.keys())}")
|