AIyaodianzhushou/data-pipeline/test_parse.py

"""测试解析：预览前10个 DOCX 文件"""
from docx_ingest import *

files = find_docx_files('/opt/2025')[:10]
for f in files:
    e = parse_docx(f)
    if e:
        print(f'{e["name"]} | {e["category"]} | {len(e["sections"])} sections | keys: {list(e["sections"].keys())[:5]}')
    else:
        print(f'SKIP: {f}')