有效地搜索大量关键字的正文(1000个)

import re
from collections import defaultdict

def build_inverted_index(documents):
    index = defaultdict(list)
    for doc_id, doc_text in documents.items():
        words = re.findall(r'\w+', doc_text.lower())
        for word in set(words):
            index[word].append(doc_id)
    return index

def search(query, index, documents):
    query_words = re.findall(r'\w+', query.lower())
    results = set(index[query_words[0]])
    for word in query_words[1:]:
        results &= set(index[word])
    return [documents[doc_id] for doc_id in results]

# 示例文档
documents = {
    1: "This is a sample document.",
    2: "Another document with sample text.",
    3: "Yet another document for testing."
}

# 构建倒排索引
index = build_inverted_index(documents)

# 搜索示例
query = "sample document"
results = search(query, index, documents)
print(results)