Only process 500 lines/row at a time createReadStream - node.js

Question

I have to read a really large CSV file so search through the google and get to know about createReadStream. I am using a program that read the csv file data and insert it into the mongoDB.
process I am following
process the data using createReadStream (I think it read the file line by line).
Storing data into an array.
Insert the data into mongoDB using insertMany
Now the problem is whole file is first get stored into an array and then I insert into the database.
But what I think is the better approach would be I only store first 500 line/rows into an array insert it into the DB and again follow the same step for the next 500 records
Is it possible to achieve this ?
and also is it the right way to do this ?
my program
const test = async () => {
const stream = fs.createReadStream(workerData)
.pipe(parse())
.on('data', async function(csvrow) {
try{
stream.pause()
if(!authorName.includes(csvrow.author)) {
const author = new Author({author: csvrow.author})
authorId = author._id
authorName.push(author.author)
authorData.push(author)
}
if(!companyName.includes(csvrow.company_name)) {
const company = new Company({companyName: csvrow.company_name})
companyID = company._id
companyName.push(company.companyName)
companyData.push(company)
}
users = new User({
name: csvrow.firstname,
dob: csvrow.dob,
address: csvrow.address,
phone: csvrow.phone,
state: csvrow.state,
zip: csvrow.zip,
email: csvrow.email,
gender: csvrow.gender,
userType: csvrow.userType
})
userData.push(users)
book = new Book({
book_number: csvrow.book_number,
book_name: csvrow.book_name,
book_desc: csvrow.book_desc,
user_id: users._id,
author_id: authorId
})
bookData.push(book)
relationalData.push({
username: users.name,
author_id: authorId,
book_id: book._id,
company_id: companyID
})
}finally {
stream.resume()
}
})
.on('end', async function() {
try {
Author.insertMany(authorData)
User.insertMany(userData)
Book.insertMany(bookData)
Company.insertMany(companyData)
await Relational.insertMany(relationalData)
parentPort.postMessage("true")
}catch(e){
console.log(e)
parentPort.postMessage("false")
}
})
}
test()
This program is working fine also inserting the data into the DB, But I am looking for something like this:
const stream = fs.createReadStream(workerData)
.pipe(parse())
.on('data', async function(csvrow, maxLineToRead: 500) {
// whole code/logic of insert data into DB
})
so maxLineToRead is my imaginary term.
basically my point is I want to process 500 data at a time and insert it into the DB and want to repeat this process till the end.

Answer 1

You can create a higher scoped array variable where you accumulate rows of data as they arrive on the data event. When you get to 500 rows, fire off your database operation to insert them. If not yet at 500 rows, then just add the next one to the array and wait for more data events to come.
Then, in the end event insert any remaining rows still in the higher scoped array.
In this way, you will insert 500 at a time and then however many are left at the end. This has an advantage vs. inserting them all at the end that you spread out the database load over the time you are parsing.
Here's an attempt to implement that type of processing. There are some unknowns (documented with comments) based on an incomplete description of exactly what you're trying to accomplish in some circumstances):
const test = () => {
return new Promise((resolve, reject) => {
const accumulatedRows = [];
async function processRows(rows) {
// initialize data arrays that we will insert
const authorData = [],
companyData = [],
userData = [],
bookData = [],
relationalData = [];
// this code still has a problem that I don't have enough context
// to know how to solve
// If authorName contains csvrow.author, then the variable
// authorId is not initialized, but is used later in the code
// This is a problem that needs to be fixed.
// The same issue occurs for companyID
for (let csvrow of rows) {
let authorId, companyID;
if (!authorName.includes(csvrow.author)) {
const author = new Author({ author: csvrow.author })
authorId = author._id
authorName.push(author.author)
authorData.push(author)
}
if (!companyName.includes(csvrow.company_name)) {
const company = new Company({ companyName: csvrow.company_name })
companyID = company._id
companyName.push(company.companyName)
companyData.push(company)
}
let users = new User({
name: csvrow.firstname,
dob: csvrow.dob,
address: csvrow.address,
phone: csvrow.phone,
state: csvrow.state,
zip: csvrow.zip,
email: csvrow.email,
gender: csvrow.gender,
userType: csvrow.userType
});
userData.push(users)
let book = new Book({
book_number: csvrow.book_number,
book_name: csvrow.book_name,
book_desc: csvrow.book_desc,
user_id: users._id,
author_id: authorId
});
bookData.push(book)
relationalData.push({
username: users.name,
author_id: authorId,
book_id: book._id,
company_id: companyID
});
}
// all local arrays of data are populated now for this batch
// so add this data to the database
await Author.insertMany(authorData);
await User.insertMany(userData);
await Book.insertMany(bookData);
await Company.insertMany(companyData);
await Relational.insertMany(relationalData);
}
const batchSize = 50;
const stream = fs.createReadStream(workerData)
.pipe(parse())
.on('data', async function(csvrow) {
try {
accumulatedRows.push(csvRow);
if (accumulatedRows.length >= batchSize) {
stream.pause();
await processRows(accumulatedRows);
// clear out the rows we just processed
acculatedRows.length = 0;
stream.resume();
}
} catch (e) {
// calling destroy(e) will prevent leaking a stream
// and will trigger the error event to be called with that error
stream.destroy(e);
}
}).on('end', async function() {
try {
await processRows(accumulatedRows);
resolve();
} catch (e) {
reject(e);
}
}).on('error', (e) => {
reject(e);
});
});
}
test().then(() => {
parentPort.postMessage("true");
}).catch(err => {
console.log(err);
parentPort.postMessage("false");
});