# -*- coding: utf-8 -*-
# t07-extract2.py — 提取 A1X 批注区（标题行 ± 邻行全文）
import io, sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

base = '.scratch/opportunity-bugfix/lanhu-pages/'
files = [
    'A1X-1_工作计划_工作日历.md',
    'A1X-2_工作计划_计划管理.md',
    'A1X-3_工作计划_出差与拜访.md',
    'A1X-1-2_填写今日工作.md',
    'A1X-1-3_工作计划详情.md',
]
for fn in files:
    lines = open(base + fn, 'r', encoding='utf-8').read().splitlines()
    print(f'\n===== {fn} ({len(lines)} 行) =====')
    idx = [i for i, ln in enumerate(lines) if '、开发说明' in ln or '、页面说明' in ln]
    seen = set()
    for i in idx:
        for j in range(i, min(i + 4, len(lines))):
            if j in seen:
                continue
            seen.add(j)
            ln = lines[j]
            if len(ln) > 300:  # 大单元格=批注内容行
                print(ln[:5000])
                break
    if not idx:
        print('（无批注标题行）')
print('\ndone')