Read data from .xlsx file on S3 using Nodejs Lambda - node.js

Question

I'm still new in NodeJs and AWS, so forgive me if this is a noob question.
I am trying to read the data from an excel file (.xlsx). The lambda function receives the extension of the file type.
Here is my code:
exports.handler = async (event, context, callback) => {
console.log('Received event:', JSON.stringify(event, null, 2));
if (event.fileExt === undefined) {
callback("400 Invalid Input");
}
let returnData = "";
const S3 = require('aws-sdk/clients/s3');
const s3 = new S3();
switch(event.fileExt)
{
case "plain":
case "txt":
// Extract text
const params = {Bucket: 'filestation', Key: 'MyTXT.'+event.fileExt};
try {
await s3.getObject(params, function(err, data) {
if (err) console.log(err, err.stack); // an error occurred
else{ // successful response
returnData = data.Body.toString('utf-8');
context.done(null, returnData);
}
}).promise();
} catch (error) {
console.log(error);
return;
}
break;
case "xls":
case "xlsx":
returnData = "Excel";
// Extract text
const params2 = {Bucket: 'filestation', Key: 'MyExcel.'+event.fileExt};
const readXlsxFile = require("read-excel-file/node");
try {
const doc = await s3.getObject(params2);
const parsedDoc = await readXlsxFile(doc);
console.log(parsedDoc)
} catch (err) {
console.log(err);
const message = `Error getting object.`;
console.log(message);
throw new Error(message);
}
break;
case "docx":
returnData = "Word doc";
// Extract text
break;
default:
callback("400 Invalid Operator");
break;
}
callback(null, returnData);
};
The textfile part works. But the xlsx part makes the function time out.
I did install the read-excel-file dependency and uploaded the zip so that I have access to it.
But the function times out with this message:
"errorMessage": "2020-11-02T13:06:50.948Z 120bfb48-f29c-4e3f-9507-fc88125515fd Task timed out after 3.01 seconds"
Any help would be appreciated! Thanks for your time.

Answer 1

using the xlsx npm library. here's how we did it.
assuming the file is under the root project path.
const xlsx = require('xlsx');
// read your excel file
let readFile = xlsx.readFile('file_example_XLSX_5000.xlsx')
// get first-sheet's name
let sheetName = readFile.SheetNames[0];
// convert sheets to JSON. Best if sheet has a headers specified.
console.log(xlsx.utils.sheet_to_json(readFile.Sheets[sheetName]));

Answer 2

You need to install xlsx (SheetJs) library into the project:
npm install xlsx
and then import the "read" function into the lambda, get the s3 object's body and send to xlsx like this:
const { read } = require('sheetjs-style');
const aws = require('aws-sdk');
const s3 = new aws.S3({ apiVersion: '2006-03-01' });
exports.handler = async (event) => {
const bucketName = 'excel-files';
const fileKey = 'Demo Data.xlsx';
// Simple GetObject
let file = await s3.getObject({Bucket: bucketName, Key: fileKey}).promise();
const wb = read(file.Body);
const response = {
statusCode: 200,
body: JSON.stringify({
read: wb.Sheets,
}),
};
return response;
};
(of course, you can receive the bucket and filekey from parameters if you send them...)
Very Important: Use the READ (not the readFile) function and send the Body property (with capital "B") as a paremeter

Answer 3

I changed the timeout to 20 seconds and it works. Only one issue remains: const parsedDoc = await readXlsxFile(doc); wants to receive a string (filepath) and not a file.

Answer 4

Solved by using xlsx NPM library. Using a stream and giving it buffers.