MongoDB 全文索引 与 展示查询数据的一部分，提高性能

test_search_db> db.articles.drop();
true
test_search_db> 

test_search_db> print("开始生成 10 万条数据，请稍候...");
| 
| const totalRecords = 100000;
| const batchSize = 5000; // 每 5000 条数据批量提交一次
| let bulk = db.articles.initializeUnorderedBulkOp();
| 
| // 词库：用于随机组合生成文本
| const keywords = ["MongoDB", "Database", "AI", "Cloud", "Performance", "Index", "Query", "Optimization", "Full-text Search", "Developer", "Java", "Python", "Node.js", "Cluster", "Scaling", "Big Data", "Analytics"];
| const verbs = ["improves", "accelerates", "transforms", "simplifies", "manages", "secures", "analyzes", "powers"];
| const readyText = ["This article explores the advanced features of modern technologies.", "A deep dive into indexing strategies and best practices.", "How to build scalable applications with high availability.", "An introductory guide for developers and architects."];
| 
| function getRandomElement(arr) {
|     return arr[Math.floor(Math.random() * arr.length)];
| }
| 
| function generateRandomString(wordCount) {
|     let sentence = [];
|     for (let i = 0; i < wordCount; i++) {
|         sentence.push(getRandomElement(keywords));
|         if (i % 3 === 0 && i > 0) sentence.push(getRandomElement(verbs));
|     }
|     return sentence.join(" ") + ". " + getRandomElement(readyText);
| }
| 
| // 3. 循环生成并分批插入
| for (let i = 1; i <= totalRecords; i++) {
|     // 随机生成标题、摘要和正文，确保里面包含我们要搜索的关键词
|     let title = `${getRandomElement(keywords)}${getRandomElement(verbs)}${getRandomElement(keywords)}`;
|     let summary = generateRandomString(8);
|     let content = generateRandomString(30); // 正文较长
| 
|     bulk.insert({
|         article_id: i,
|         title: title,
|         summary: summary,
|         content: content,
|         views: Math.floor(Math.random() * 10000),
|         createdAt: new Date(Date.now() - Math.floor(Math.random() * 10000000000))
|     });
| 
|     // 达到批次大小，执行写入并重置 bulk
|     if (i % batchSize === 0) {
|         bulk.execute();
|         bulk = db.articles.initializeUnorderedBulkOp();
|         print(`已写入 ${i} 条数据...`);
|     }
| }
| 
| // 检查是否有剩余未提交的数据
| if (totalRecords % batchSize !== 0) {
|     bulk.execute();
| }
| 
| print("数据填充完毕！当前总数据量：", db.articles.countDocuments());
开始生成 10 万条数据，请稍候...
已写入 5000 条数据...
已写入 10000 条数据...
已写入 15000 条数据...
已写入 20000 条数据...
已写入 25000 条数据...
已写入 30000 条数据...
已写入 35000 条数据...
已写入 40000 条数据...
已写入 45000 条数据...
已写入 50000 条数据...
已写入 55000 条数据...
已写入 60000 条数据...
已写入 65000 条数据...
已写入 70000 条数据...
已写入 75000 条数据...
已写入 80000 条数据...
已写入 85000 条数据...
已写入 90000 条数据...
已写入 95000 条数据...
已写入 100000 条数据...
数据填充完毕！当前总数据量： 100000

test_search_db> show collections;
articles
test_search_db> db.articles.find().limit(1);
[
  {
    _id: ObjectId('69fe22f484970425839df8a3'),
    article_id: 1,
    title: 'Analytics manages Index',
    summary: 'Java Node.js Optimization Index transforms Database Cloud Performance manages Python. An introductory guide for developers and architects.',
    content: 'Database Python Query Cloud simplifies Java Python AI analyzes Scaling AI Analytics improves Python Database Developer powers Performance Node.js Database improves Java Full-text Search Java improves Index Scaling Performance transforms Node.js Analytics Cloud improves Full-text Search Query Cluster simplifies Index Node.js. A deep dive into indexing strategies and best practices.',
    views: 5895,
    createdAt: ISODate('2026-02-11T17:30:28.608Z')
  }
]

test_search_db> db.articles.createIndex({ content: "text" });
content_text
test_search_db> db.articles.find(
|   { $text: { $search: "Database" } }
| ).limit(10);
[
  {
    _id: ObjectId('69fe231e84970425839ec463'),
    article_id: 52161,
    title: 'Performance analyzes Cloud',
    summary: 'AI Analytics Index Optimization analyzes Query Query Developer simplifies Index. An introductory guide for developers and architects.',
    content: 'Query Python Database Full-text Search accelerates Query Cluster Cluster manages Performance Developer Developer simplifies Database Database Full-text Search transforms Database Developer Query accelerates Database Analytics Index powers Java Database Python powers Database Database Database transforms Developer Performance Database improves Database Index. How to build scalable applications with high availability.',
    views: 4930,
    createdAt: ISODate('2026-05-01T16:06:04.940Z')
  },

db.articles.createIndex({
  title: "text",
  summary: "text",
  content: "text"
}, {
  weights: {
    title: 10,
    summary: 3,
    content: 1
  },
  name: "ArticleTextIndex"
})

db.articles.find(
  { $text: { $search: searchKeyword } },
  {
    title: 1,
    summary: 1,
    preview: { $substrCP: ["$content", 0, 20] },
    score: { $meta: "textScore" },
    _id: 0
  }
)
.sort({ score: { $meta: "textScore" } })
.limit(10);