import pandas as pd

file_l2 = r'/root/.openclaw/workspace-xiaoyan/business_knowledge/L2单词表/L2新版独有单词.xlsx'
file_kb = r'/root/.openclaw/workspace-xiaoyan/business_knowledge/L2单词表/L2知识库-三级+A2.xlsx'

df_l2 = pd.read_excel(file_l2)
df_kb = pd.read_excel(file_kb)

available = df_l2[df_l2['可用'] == 1].copy()

new_rows = []
for _, row in available.iterrows():
    new_rows.append({
        '单词': row['单词'],
        '词性': row['词性'],
        '中文释义': row['词义'],
        'KET/三级重合': '',
        '分类': '',
        'Unnamed: 5': '',
        '与L1重复': row['是否为L1单词'],
        'L1词性': row['L1词性'] if pd.notna(row['L1词性']) else '',
        'L1词义': row['L1词义'] if pd.notna(row['L1词义']) else '',
        '在L1中的行数': row['L1行数'] if pd.notna(row['L1行数']) else '',
        '删除': ''
    })

df_new = pd.DataFrame(new_rows)

df_kb = pd.concat([df_kb, df_new], ignore_index=True)

df_kb = df_kb.sort_values(by='单词', key=lambda x: x.str.lower(), ignore_index=True)

output_path = r'/root/.openclaw/workspace-xiaoyan/business_knowledge/L2单词表/L2知识库-三级+A2.xlsx'
df_kb.to_excel(output_path, index=False)

print(f"已添加 {len(new_rows)} 个单词")
print(f"L2知识库总单词数: {len(df_kb)}")
print(f"\n已保存至: {output_path}")
print("\n添加的单词（按字母顺序）:")
for i, row in df_new.sort_values(by='单词', key=lambda x: x.str.lower()).iterrows():
    print(f"  {row['单词']:<15} {str(row['词性']):<10} {row['中文释义']:<25} L1:{row['与L1重复']} L1词性:{row['L1词性']} L1词义:{row['L1词义']}")