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_l1 = r'/root/.openclaw/workspace-xiaoyan/business_knowledge/L2单词表/L1完整.xlsx'

df_l2 = pd.read_excel(file_l2)
df_l1 = pd.read_excel(file_l1)

l1_words = {}
for idx, row in df_l1.iterrows():
    word = str(row['单词']).strip().lower()
    if word not in l1_words:
        l1_words[word] = []
    l1_words[word].append({
        'row': idx + 2,
        '词性': row['词性'],
        '词义': row['词义']
    })

is_l1_list = []
l1_row_list = []
l1_pos_list = []
l1_meaning_list = []

for idx, row in df_l2.iterrows():
    word = str(row['单词']).strip().lower()
    if word in l1_words:
        is_l1_list.append('是')
        matches = l1_words[word]
        l1_row_list.append(', '.join(str(m['row']) for m in matches))
        l1_pos_list.append(', '.join(str(m['词性']) for m in matches))
        l1_meaning_list.append(', '.join(str(m['词义']) for m in matches))
    else:
        is_l1_list.append('否')
        l1_row_list.append('')
        l1_pos_list.append('')
        l1_meaning_list.append('')

df_l2['是否为L1单词'] = is_l1_list
df_l2['L1行数'] = l1_row_list
df_l2['L1词性'] = l1_pos_list
df_l2['L1词义'] = l1_meaning_list

output_path = r'/root/.openclaw/workspace-xiaoyan/business_knowledge/L2单词表/L2新版独有单词.xlsx'
df_l2.to_excel(output_path, index=False)

count_yes = sum(1 for v in is_l1_list if v == '是')
count_no = sum(1 for v in is_l1_list if v == '否')

print(f"L2新版独有单词总数: {len(df_l2)}")
print(f"在L1中存在的: {count_yes} 个")
print(f"不在L1中的: {count_no} 个")
print(f"\n已保存至: {output_path}")