如何在弹性搜索中插入多个 JSON 文档

Question

输入数据

[{
"_index": "abc",
"_type": "_doc",
"_id": "QAE",
"_score": 6.514091,
"_source": {
    "category": "fruits",
    "action": "eating",
    "metainfo": {
        "hash": "nzUZ1ONm0e167p"
    },
    "createddate": "2019-10-03T12:37:45.297Z" 
}},
{

 "_index": "abc",
"_type": "_doc",
"_id": "PQR",
"_score": 6.514091,
"_source": {
    "category": "Vegetables",
    "action": "eating",
    "metainfo": {
        "hash": "nzUZ1ONm0e167p"
    },
    "createddate": "2019-10-03T12:37:45.297Z"
  }
 }-----------------

----------------] 我有大约 30,000 条记录作为输入数据。如何在单个查询中插入此数据。我试过了

var elasticsearch = require('elasticsearch');
var client = new elasticsearch.Client({
    host: '********',
    log: 'trace'
}); 
  client.index({
     index: "abc",
     body: ****input data*****
}).then((res) => {
     console.log(res);
}, (err) => {
         console.log("err", err);
  });

在此代码中，在正文中发送输入数据。但它返回一个错误。请给我建议。

Answer 1

这似乎是你在寻找什么：

'use strict'

require('array.prototype.flatmap').shim()
const { Client } = require('@elastic/elasticsearch')
const client = new Client({
  node: 'http://localhost:9200'
})

async function run () {
  await client.indices.create({
    index: 'tweets',
    body: {
      mappings: {
        properties: {
          id: { type: 'integer' },
          text: { type: 'text' },
          user: { type: 'keyword' },
          time: { type: 'date' }
        }
      }
    }
  }, { ignore: [400] })

  const dataset = [{
    id: 1,
    text: 'If I fall, don\'t bring me back.',
    user: 'jon',
    date: new Date()
  }, {
    id: 2,
    text: 'Winter is coming',
    user: 'ned',
    date: new Date()
  }, {
    id: 3,
    text: 'A Lannister always pays his debts.',
    user: 'tyrion',
    date: new Date()
  }, {
    id: 4,
    text: 'I am the blood of the dragon.',
    user: 'daenerys',
    date: new Date()
  }, {
    id: 5, // change this value to a string to see the bulk response with errors
    text: 'A girl is Arya Stark of Winterfell. And I\'m going home.',
    user: 'arya',
    date: new Date()
  }]


// The major part is below:

  const body = dataset.flatMap(doc => [{ index: { _index: 'tweets' } }, doc])
  const { body: bulkResponse } = await client.bulk({ refresh: true, body })

//

  if (bulkResponse.errors) {
    const erroredDocuments = []
    // The items array has the same order of the dataset we just indexed.
    // The presence of the `error` key indicates that the operation
    // that we did for the document has failed.
    bulkResponse.items.forEach((action, i) => {
      const operation = Object.keys(action)[0]
      if (action[operation].error) {
        erroredDocuments.push({
          // If the status is 429 it means that you can retry the document,
          // otherwise it's very likely a mapping error, and you should
          // fix the document before to try it again.
          status: action[operation].status,
          error: action[operation].error,
          operation: body[i * 2],
          document: body[i * 2 + 1]
        })
      }
    })
    console.log(erroredDocuments)
  }

  const { body: count } = await client.count({ index: 'tweets' })
  console.log(count)
}

run().catch(console.log)

参考链接：https://www.elastic.co/guide/en/elasticsearch/client/javascript-api/current/bulk_examples.html