# batch_test.py
from cmekg_aligner import CMeKGAligner

aligner = CMeKGAligner(
    uri="bolt://localhost:7687",
    user="neo4j",
    password="your_password"
)

# 模拟上万条数据（实际可从文件读取）
with open("input_terms.txt", "r", encoding="utf-8") as f:
    terms = [line.strip() for line in f if line.strip()]

print(f"🔍 开始批量对齐 {len(terms)} 条实体...")

results = aligner.find_entities_batch(terms)

# 输出结果
for term in terms[:10]:  # 只打印前10条示例
    res = results[term]
    if res:
        print(f"✅ '{term}' → '{res[0]}', {res[1]}")
    else:
        print(f"❌ '{term}' → 未匹配")

# 可选：保存到 CSV
import csv
with open("batch_alignment_result.csv", "w", encoding="utf-8", newline="") as f:
    writer = csv.writer(f)
    writer.writerow(["原始词", "标准名", "类型"])
    for term in terms:
        res = results[term]
        if res:
            writer.writerow([term, res[0], res[1]])
        else:
            writer.writerow([term, "", ""])