import re
from collections import defaultdict
<h1>模拟文档库</h1><p>documents = {
1: "python programming language",
2: "python data science",
3: "web development with python",
4: "machine learning in python"
}</p><h1>构建倒排索引</h1><p>index = defaultdict(set)
for doc_id, text in documents.items():
words = re.findall(r'\b\w+\b', text.lower())
for word in words:
index[word].add(doc_id)</p>

def search(query):
    words = re.findall(r'\b\w+\b', query.lower())
    results = None
    for word in words:
        if word in index:
            if results is None:
                results = index[word]
            else:
                results = results & index[word]  # 取交集（AND 查询）
        else:
            return set()  # 任一词不存在则无结果
    return results or set()

def search_ranked(query):
    words = re.findall(r'\b\w+\b', query.lower())
    scores = defaultdict(int)
    for word in words:
        if word in index:
            for doc_id in index[word]:
                scores[doc_id] += 1
    # 按得分降序排列
    return sorted(scores.items(), key=lambda x: x[1], reverse=True)

from whoosh.index import create_in
from whoosh.fields import Schema, TEXT, ID
import os
<p>schema = Schema(title=TEXT(stored=True), content=TEXT)
if not os.path.exists("indexdir"):
os.mkdir("indexdir")
ix = create_in("indexdir", schema)</p><p>writer = ix.writer()
writer.add_document(title="Python Intro", content="Learn python programming")
writer.commit()</p><p>with ix.searcher() as searcher:
from whoosh.query import *
query = Term("content", "python")
results = searcher.search(query)
for r in results:
print(r["title"])</p>