import pandas as pd

# 文件路径
table1_path = "/root/.openclaw/media/inbound/é_¾åº_æ_æ_å_è_ç³_æ_1.0---4d1d9fe3-1e36-4df1-baf6-d826fcf7a05e.xlsx"
table3_path = "/root/.openclaw/media/inbound/â_¼ï_LV1-å_ç_å_è_åº_-ç¼_å_é_è_ç_è_é---e503b23c-829e-4367-b819-762856bd50b5.xlsx"
output_path = "/root/.openclaw/workspace-xiaoban/匹配完成的LV1词汇表.xlsx"

# 读取两个表格
df1 = pd.read_excel(table1_path)
df3 = pd.read_excel(table3_path)

print(f"表一总条数：{len(df1)}")
print(f"表三总条数：{len(df3)}")
print(f"表一列名：{list(df1.columns)}")
print(f"表三列名：{list(df3.columns)}")

# 创建映射：统一将单词转为字符串作为key，匹配三个字段
word_map = {}
for _, row in df1.iterrows():
    word = str(row['单词']).strip()
    word_map[word] = {
        '难度（D）': row['难度（D）'],
        '实现成本(T)': row['实现成本(T)'],
        '单词系数': row['单词系数']
    }

# 给表三添加三列
def get_value(word, col):
    key = str(word).strip()
    return word_map.get(key, {}).get(col, None)

df3['难度（D）'] = df3['单词'].apply(lambda x: get_value(x, '难度（D）'))
df3['实现成本(T)'] = df3['单词'].apply(lambda x: get_value(x, '实现成本(T)'))
df3['单词系数'] = df3['单词'].apply(lambda x: get_value(x, '单词系数'))

# 保存结果
df3.to_excel(output_path, index=False)

# 统计匹配情况
match_count = df3['难度（D）'].notna().sum()
print(f"\n匹配完成！结果已保存到：{output_path}")
print(f"成功匹配条数：{match_count}")
print(f"未匹配条数：{len(df3) - match_count}")