Converting Office Docs to PDF with AWS Lambda

js

const https = require('https');
const path = require('path');
const fs = require('fs');
var async = require('async');
const {writeFileSync} = require('fs');
const lambdafs = require('lambdafs');
const {execSync} = require('child_process');
var AWS = require('aws-sdk');

const inputPath = path.join( '/opt', 'lo.tar.br'); 
const outputPath = '/tmp/';
const bucketName = 'doc-conversion-test';

module.exports.handler = async (event, context) => {
  console.log(execSync('ls -alh /opt').toString('utf8'));

  try {
    // Decompressing
    let decompressed = {
      file: await lambdafs.inflate(inputPath)
    };
 
    console.log('output brotli de:----', decompressed); 
  } catch (error) {
    console.log('Error brotli de:----', error);
  }
 
  try {
    console.log(execSync('ls -alh /opt').toString('utf8')); 
  } catch (e) {
    console.log(e);
  }

  var body = "";
  //S3 put event
  body = event.Records[0].body;
  console.log('s3 bucket file name from event:', body);

  // get file from s3 bucket
  var s3fileName = body;
  var newFileName = Date.now()+'.pdf';
  var s3 = new AWS.S3({apiVersion: '2006-03-01'});
  var fileStream = fs.createWriteStream('/tmp/'+s3fileName);

  var getObject = function(keyFile) {
      return new Promise(function(success, reject) {
          s3.getObject(
              { Bucket: bucketName, Key: keyFile },
              function (error, data) {
                  if(error) {
                      reject(error);
                  } else {
                      success(data);
                  }
              }
          );
      });
  }

  let fileData = await getObject(s3fileName);
    try{  
      fs.writeFileSync('/tmp/'+s3fileName, fileData.Body);
    } catch(err) {
      // An error occurred
      console.error('file write:', err);
    }

    const convertCommand = `export HOME=/tmp && /tmp/lo/instdir/program/soffice.bin --headless --norestore --invisible --nodefault --nofirststartwizard --nolockcheck --nologo --convert-to "pdf:writer_pdf_Export" --outdir /tmp /tmp/${s3fileName}`;
    try {
      console.log(execSync(convertCommand).toString('utf8'));
    } catch (e) {
      console.log(execSync(convertCommand).toString('utf8'));
    }
    console.log(execSync('ls -alh /tmp').toString('utf8'));

    function uploadFile(buffer, fileName) {
     return new Promise((resolve, reject) => {
      s3.putObject({
       Body: buffer,
       Key: fileName,
       Bucket: bucketName,
      }, (error) => {
       if (error) {
        reject(error);
       } else {

        resolve(fileName);
       }
      });
     });
    }


    let fileParts = s3fileName.substr(0, s3fileName.lastIndexOf(".")) + ".pdf";
    let fileB64data = fs.readFileSync('/tmp/'+fileParts);
    await uploadFile(fileB64data, 'pdf/'+fileParts);
    console.log('new pdf converted and uploaded!!!');
};

I have tried a few different AWS Lambda OpenOffice PDF generators over the past weeks and this is the only one that has worked with current Amazon Linux 2/Lambda constraints for a wide variety of files.

yes, it works fine for 99%

I used this code to convert from docx to html -- worked perfectly with a few tweaks..
i also need it to convert it to pdf -- but the pdf which is getting generated is empty, not sure whats wrong.

import {execSync} from "child_process";

export class WordToHtmlConvertor {
/**

• This function handles the s3 upload event and converts the file to the specified format ,and uploads it to S3 again
• @param {any} event - The uploaded s3 objects bucket and key
  */
  static convertWordToHtml = async (bucketName: String, key: String) => {
  const fs = require("fs");

const params = {
	Bucket: bucketName,
	Key: key,
};
const AWS = require("aws-sdk");
const s3 = new AWS.S3();
await s3.getObject(params, function(err, data){
	if (err) {
		console.error(err.code, "-", err.message);
	}
	/*fs.writeFile('/tmp/' + key, data.Body, function(err){
		if(err) {
			console.log(err.code, "-", err.message);
		}
	});*/
	fs.writeFileSync('/tmp/'+ key, data.Body);
});
try {
	const path = require('path');
	const inputPath = path.join( '/opt', 'lo.tar.br');
	const lambdafs = require('lambdafs');

	// Decompressing
	let decompressed = {
		file: await lambdafs.inflate(inputPath)
	};
	console.log('Libre Office Brotli layer decompressed', decompressed);
} catch (error) {
	console.log('Error decompressing', error);
}

//let newFile = key.substr(0, key.lastIndexOf(".")) + ".html";
let newFile = key.substr(0, key.lastIndexOf(".")) + ".pdf";
console.log(newFile);
try {
	//console.log( execSync(`export HOME=/tmp && /tmp/lo/instdir/program/soffice.bin --headless --norestore --invisible --nodefault --nofirststartwizard --nolockcheck --nologo --convert-to html:HTML --outdir /tmp /tmp/TEst.docx`));
	console.log( execSync(`export HOME=/tmp && /tmp/lo/instdir/program/soffice.bin --headless --norestore --invisible --nodefault --nofirststartwizard --nolockcheck --nologo --convert-to "pdf:writer_pdf_Export" --outdir /tmp /tmp/TEst.docx`));
} catch (e) {
	//console.log( execSync(`export HOME=/tmp && /tmp/lo/instdir/program/soffice.bin --headless --norestore --invisible --nodefault --nofirststartwizard --nolockcheck --nologo --convert-to html:HTML --outdir /tmp /tmp/TEst.docx`));
	console.log( execSync(`export HOME=/tmp && /tmp/lo/instdir/program/soffice.bin --headless --norestore --invisible --nodefault --nofirststartwizard --nolockcheck --nologo --convert-to "pdf:writer_pdf_Export" --outdir /tmp /tmp/TEst.docx`));
}

console.log(execSync('cat /tmp/TEst.docx').toString('utf8'));
console.log(execSync('cat /tmp/TEst.pdf').toString('utf8'));
let fileData = fs.readFileSync('/tmp/' + newFile, {encoding: 'binary'});
await uploadFile(fileData, newFile).then(function (result) {
console.log("Uploaded to s3:", result);
}).catch(function (err) {
console.error("Error uploading file to S3:", err.toString());
});

console.log('New Document converted and uploaded');

function uploadFile(buffer, fileName) {
console.log("Inside upload File "+ buffer.toString() + fileName);
	return new Promise(function(resolve, reject) {
		s3.putObject(
			{
				Bucket: bucketName,
				Key: fileName,
				Body: buffer,
				//ContentType: 'text/html',
				ContentType: 'application/pdf',
			}
		).promise().then(resolve, reject);
	});
}

}
};

can you please help ?

this worked with some editing:

• had to give s3 bucket read and write access for my lambda function in IAM
• "body = event.Records[0].body;" returns undefined -> I just manually changed it to my filename (ex. file.docx)
  the pdf looks great, thank you!

working with a little modification for amplify
https://gist.github.com/diveshqss/1fc4a81a47db2e24f1401e50984dc075

I have been using this blog (https://madhavpalshikar.medium.com/converting-office-docs-to-pdf-with-aws-lambda-372c5ac918f1) for my conversion project. I have followed all steps in this blog, up till step 6 - of uploading code.. bt i don't know how to test this now. I'm not able to upload doc and then see if it converts...Im a novice to AWS and im experimeting. so if you could help me with that, i will be beyond gratefull. Plz reach out to me at - priyanshikathuria@gmail.com

Thanks @madhavpalshikar for sharing this. You just saved my day.

Kudos!!

Hi

I have tried to follow the instructions on your post but every time I test the Lambda Function I get the below error from Lambda:

{
"errorType": "TypeError",
"errorMessage": "Cannot read properties of undefined (reading '0')",
"trace": [
"TypeError: Cannot read properties of undefined (reading '0')",
" at Runtime.module.exports.handler (/var/task/index/index.js:36:26)",
" at runMicrotasks ()",
" at processTicksAndRejections (node:internal/process/task_queues:96:5)"
]
}

I'm pretty sure it is causing a loop @ line 36

body = event.Records[0].body;

Does anyone have any ideas how to fix this issue please?

Thanks

M