Bulk insert into Postgres with brianc/node-postgres

问题

I have the following code in nodejs that uses the pg (https://github.com/brianc/node-postgres) My code to create subscriptions for an employee is as such.

    client.query(
      'INSERT INTO subscriptions (subscription_guid, employer_guid, employee_guid) 
       values ($1,$2,$3)', [
        datasetArr[0].subscription_guid,
        datasetArr[0].employer_guid,
        datasetArr[0].employee_guid
      ],


      function(err, result) {
        done();

        if (err) {
          set_response(500, err, res);
          logger.error('error running query', err);
          return console.error('error running query', err);
        }

        logger.info('subscription with created');
        set_response(201);

      });

As you have already noticed datasetArr is an array. I would like to create mass subscriptions for more than one employee at a time. However I would not like to loop through the array. Is there a way to do it out of the box with pg?

回答1:

I did a search for the same question, but found no solution yet. With the async library it is very simple to use the query several times, and do the necessary error handling.

May be this code variant helps. (for inserting 10.000 small json objects to an empty database it took 6 sec).

Christoph

function insertData(item,callback) {
  client.query('INSERT INTO subscriptions (subscription_guid, employer_guid, employee_guid)
       values ($1,$2,$3)', [
        item.subscription_guid,
        item.employer_guid,
        item.employee_guid
       ], 
  function(err,result) {
    // return any err to async.each iterator
    callback(err);
  })
}
async.each(datasetArr,insertData,function(err) {
  // Release the client to the pg module
  done();
  if (err) {
    set_response(500, err, res);
    logger.error('error running query', err);
    return console.error('error running query', err);
  }
  logger.info('subscription with created');
  set_response(201);
})

回答2:

Create your data structure as:

[ [val1,val2],[val1,val2] ...]

Then convert it into a string:

 JSON.stringify([['a','b'],['c']]).replace(/\[/g,"(").replace(/\]/g,")").replace(/"/g,'\'').slice(1,-1)

append it to the query and you are done!

Agreed it has string parsing costs but its way cheaper than single inserts.

回答3:

To do Bulk insert into Postgresql from NodeJS, the better option would be to use 'COPY' Command provided by Postgres and pg-copy-streams.

Code snippet from : https://gist.github.com/sairamkrish/477d20980611202f46a2d44648f7b14b

/*
  Pseudo code - to serve as a help guide. 
*/
const copyFrom = require('pg-copy-streams').from;
const Readable = require('stream').Readable;
const { Pool,Client } = require('pg');
const fs = require('fs');
const path = require('path');
const datasourcesConfigFilePath = path.join(__dirname,'..','..','server','datasources.json');
const datasources = JSON.parse(fs.readFileSync(datasourcesConfigFilePath, 'utf8'));

const pool = new Pool({
    user: datasources.PG.user,
    host: datasources.PG.host,
    database: datasources.PG.database,
    password: datasources.PG.password,
    port: datasources.PG.port,
});

export const bulkInsert = (employees) => {
  pool.connect().then(client=>{
    let done = () => {
      client.release();
    }
    var stream = client.query(copyFrom('COPY employee (name,age,salary) FROM STDIN'));
    var rs = new Readable;
    let currentIndex = 0;
    rs._read = function () {
      if (currentIndex === employees.length) {
        rs.push(null);
      } else {
        let employee = employees[currentIndex];
        rs.push(employee.name + '\t' + employee.age + '\t' + employee.salary + '\n');
        currentIndex = currentIndex+1;
      }
    };
    let onError = strErr => {
      console.error('Something went wrong:', strErr);
      done();
    };
    rs.on('error', onError);
    stream.on('error', onError);
    stream.on('end',done);
    rs.pipe(stream);
  });
}

Finer details explained in this link

回答4:

It looks for me that the best way is the usage PostgreSQL json functions:

client.query('INSERT INTO table (columns) ' +
        'SELECT m.* FROM json_populate_recordset(null::your_custom_type, $1) AS m',
        [JSON.stringify(your_json_object_array)], function(err, result) {
      if(err) {
            console.log(err);
      } else {
            console.log(result);
      }
});

回答5:

Use an ORM; eg: Objection.

Also, Increase the Connection pool size based on your db server and the number of active connection you need.

someMovie
  .$relatedQuery('actors')
  .insert([
    {firstName: 'Jennifer', lastName: 'Lawrence'},
    {firstName: 'Bradley', lastName: 'Cooper'}
  ])
  .then(function (actors) {
    console.log(actors[0].firstName);
    console.log(actors[1].firstName);
  });

来源：https://stackoverflow.com/questions/24008668/bulk-insert-into-postgres-with-brianc-node-postgres

标签

node.js

postgresql

node-postgres