Develop Reference

count total number of word in pdf book using node js? [duplicate]

I wonder if is possible to get the text inside of a PDF file by using only Javascript?
If yes, can anyone show me how?
I know there are some server-side java, c#, etc libraries but I would prefer not using a server.
thanks

Because pdf.js has been developing over the years, I would like to give a new answer. That is, it can be done locally without involving any server or external service. The new pdf.js has a function: page.getTextContent(). You can get the text content from that. I've done it successfully with the following code.
What you get in each step is a promise. You need to code this way: .then( function(){...}) to proceed to the next step.
PDFJS.getDocument( data ).then( function(pdf) {
pdf.getPage(i).then( function(page){
page.getTextContent().then( function(textContent){
What you finally get is an string array textContent.bidiTexts[]. You concatenate them to get the text of 1 page. Text blocks' coordinates are used to judge whether newline or space need to be inserted. (This may not be totally robust, but from my test it seems ok.)
The input parameter data needs to be either a URL or ArrayBuffer type data. I used the ReadAsArrayBuffer(file) function in FileReader API to get the data.
Note: According to some other user, the library has updated and caused the code to break. According to the comment by async5 below, you need to replace textContent.bidiTexts with textContent.items.
function Pdf2TextClass(){
var self = this;
this.complete = 0;
/**
*
* #param data ArrayBuffer of the pdf file content
* #param callbackPageDone To inform the progress each time
* when a page is finished. The callback function's input parameters are:
* 1) number of pages done;
* 2) total number of pages in file.
* #param callbackAllDone The input parameter of callback function is
* the result of extracted text from pdf file.
*
*/
this.pdfToText = function(data, callbackPageDone, callbackAllDone){
console.assert( data instanceof ArrayBuffer || typeof data == 'string' );
PDFJS.getDocument( data ).then( function(pdf) {
var div = document.getElementById('viewer');
var total = pdf.numPages;
callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++){
pdf.getPage(i).then( function(page){
var n = page.pageNumber;
page.getTextContent().then( function(textContent){
if( null != textContent.bidiTexts ){
var page_text = "";
var last_block = null;
for( var k = 0; k < textContent.bidiTexts.length; k++ ){
var block = textContent.bidiTexts[k];
if( last_block != null && last_block.str[last_block.str.length-1] != ' '){
if( block.x < last_block.x )
page_text += "\r\n";
else if ( last_block.y != block.y && ( last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null ))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++ self.complete;
callbackPageDone( self.complete, total );
if (self.complete == total){
window.setTimeout(function(){
var full_text = "";
var num_pages = Object.keys(layers).length;
for( var j = 1; j <= num_pages; j++)
full_text += layers[j] ;
callbackAllDone(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class

I couldn't get gm2008's example to work (the internal data structure on pdf.js has changed apparently), so I wrote my own fully promise-based solution that doesn't use any DOM elements, queryselectors or canvas, using the updated pdf.js from the example at mozilla
It eats a file path for the upload since i'm using it with node-webkit.
You need to make sure you have the cmaps downloaded and pointed somewhere and you nee pdf.js and pdf.worker.js to get this working.
/**
* Extract text from PDFs with PDF.js
* Uses the demo pdf.js from https://mozilla.github.io/pdf.js/getting_started/
*/
this.pdfToText = function(data) {
PDFJS.workerSrc = 'js/vendor/pdf.worker.js';
PDFJS.cMapUrl = 'js/vendor/pdfjs/cmaps/';
PDFJS.cMapPacked = true;
return PDFJS.getDocument(data).then(function(pdf) {
var pages = [];
for (var i = 0; i < pdf.numPages; i++) {
pages.push(i);
}
return Promise.all(pages.map(function(pageNumber) {
return pdf.getPage(pageNumber + 1).then(function(page) {
return page.getTextContent().then(function(textContent) {
return textContent.items.map(function(item) {
return item.str;
}).join(' ');
});
});
})).then(function(pages) {
return pages.join("\r\n");
});
});
}
usage:
self.pdfToText(files[0].path).then(function(result) {
console.log("PDF done!", result);
})

Just leaving here a full working sample.
<html>
<head>
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
</head>
<body>
<input id="pdffile" name="pdffile" type="file" />
<button id="btn" onclick="convert()">Process</button>
<div id="result"></div>
</body>
</html>
<script>
function convert() {
var fr=new FileReader();
var pdff = new Pdf2TextClass();
fr.onload=function(){
pdff.pdfToText(fr.result, null, (text) => { document.getElementById('result').innerText += text; });
}
fr.readAsDataURL(document.getElementById('pdffile').files[0])
}
function Pdf2TextClass() {
var self = this;
this.complete = 0;
this.pdfToText = function (data, callbackPageDone, callbackAllDone) {
console.assert(data instanceof ArrayBuffer || typeof data == 'string');
var loadingTask = pdfjsLib.getDocument(data);
loadingTask.promise.then(function (pdf) {
var total = pdf._pdfInfo.numPages;
//callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++) {
pdf.getPage(i).then(function (page) {
var n = page.pageNumber;
page.getTextContent().then(function (textContent) {
//console.log(textContent.items[0]);0
if (null != textContent.items) {
var page_text = "";
var last_block = null;
for (var k = 0; k < textContent.items.length; k++) {
var block = textContent.items[k];
if (last_block != null && last_block.str[last_block.str.length - 1] != ' ') {
if (block.x < last_block.x)
page_text += "\r\n";
else if (last_block.y != block.y && (last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++self.complete;
//callbackPageDone( self.complete, total );
if (self.complete == total) {
window.setTimeout(function () {
var full_text = "";
var num_pages = Object.keys(layers).length;
for (var j = 1; j <= num_pages; j++)
full_text += layers[j];
callbackAllDone(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
</script>

Here's some JavaScript code that does what you want using Pdf.js from http://hublog.hubmed.org/archives/001948.html:
var input = document.getElementById("input");
var processor = document.getElementById("processor");
var output = document.getElementById("output");
// listen for messages from the processor
window.addEventListener("message", function(event){
if (event.source != processor.contentWindow) return;
switch (event.data){
// "ready" = the processor is ready, so fetch the PDF file
case "ready":
var xhr = new XMLHttpRequest;
xhr.open('GET', input.getAttribute("src"), true);
xhr.responseType = "arraybuffer";
xhr.onload = function(event) {
processor.contentWindow.postMessage(this.response, "*");
};
xhr.send();
break;
// anything else = the processor has returned the text of the PDF
default:
output.textContent = event.data.replace(/\s+/g, " ");
break;
}
}, true);
...and here's an example:
http://git.macropus.org/2011/11/pdftotext/example/

Note: This code assumes you're using nodejs. That means you're parsing a local file instead of one from a web page since the original question doesn't explicitly ask about parsing pdfs on a web page.
#gm2008's answer was a great starting point (please read it and its comments for more info), but needed some updates (08/19) and had some unused code. I also like examples that are more full. There's more refactoring and tweaking that could be done (e.g. with await), but for now it's as close to that original answer as it could be.
As before, this uses Mozilla's PDFjs library. The npmjs package is at https://www.npmjs.com/package/pdfjs-dist.
In my experience, this doesn't do well in finding where to put spaces, but that's a problem for another time.
[Edit: I believe the update to the use of .transform has restored the whitespace as it originally behaved.]
// This file is called myPDFfileToText.js and is in the root folder
let PDFJS = require('pdfjs-dist');
let pathToPDF = 'path/to/myPDFfileToText.pdf';
let toText = Pdf2TextObj();
let onPageDone = function() {}; // don't want to do anything between pages
let onFinish = function(fullText) { console.log(fullText) };
toText.pdfToText(pathToPDF, onPageDone, onFinish);
function Pdf2TextObj() {
let self = this;
this.complete = 0;
/**
*
* #param path Path to the pdf file.
* #param callbackPageDone To inform the progress each time
* when a page is finished. The callback function's input parameters are:
* 1) number of pages done.
* 2) total number of pages in file.
* 3) the `page` object itself or null.
* #param callbackAllDone Called after all text has been collected. Input parameters:
* 1) full text of parsed pdf.
*
*/
this.pdfToText = function(path, callbackPageDone, callbackAllDone) {
// console.assert(typeof path == 'string');
PDFJS.getDocument(path).promise.then(function(pdf) {
let total = pdf.numPages;
callbackPageDone(0, total, null);
let pages = {};
// For some (pdf?) reason these don't all come in consecutive
// order. That's why they're stored as an object and then
// processed one final time at the end.
for (let pagei = 1; pagei <= total; pagei++) {
pdf.getPage(pagei).then(function(page) {
let pageNumber = page.pageNumber;
page.getTextContent().then(function(textContent) {
if (null != textContent.items) {
let page_text = "";
let last_item = null;
for (let itemsi = 0; itemsi < textContent.items.length; itemsi++) {
let item = textContent.items[itemsi];
// I think to add whitespace properly would be more complex and
// would require two loops.
if (last_item != null && last_item.str[last_item.str.length - 1] != ' ') {
let itemX = item.transform[5]
let lastItemX = last_item.transform[5]
let itemY = item.transform[4]
let lastItemY = last_item.transform[4]
if (itemX < lastItemX)
page_text += "\r\n";
else if (itemY != lastItemY && (last_item.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null))
page_text += ' ';
} // ends if may need to add whitespace
page_text += item.str;
last_item = item;
} // ends for every item of text
textContent != null && console.log("page " + pageNumber + " finished.") // " content: \n" + page_text);
pages[pageNumber] = page_text + "\n\n";
} // ends if has items
++self.complete;
callbackPageDone(self.complete, total, page);
// If all done, put pages in order and combine all
// text, then pass that to the callback
if (self.complete == total) {
// Using `setTimeout()` isn't a stable way of making sure
// the process has finished. Watch out for missed pages.
// A future version might do this with promises.
setTimeout(function() {
let full_text = "";
let num_pages = Object.keys(pages).length;
for (let pageNum = 1; pageNum <= num_pages; pageNum++)
full_text += pages[pageNum];
callbackAllDone(full_text);
}, 1000);
}
}); // ends page.getTextContent().then
}); // ends page.then
} // ends for every page
});
}; // Ends pdfToText()
return self;
}; // Ends object factory
Run in the terminal:
node myPDFfileToText.js

Updated 02/2021
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
<script>
function Pdf2TextClass(){
var self = this;
this.complete = 0;
this.pdfToText = function(data, callbackPageDone, callbackAllDone){
console.assert( data instanceof ArrayBuffer || typeof data == 'string' );
var loadingTask = pdfjsLib.getDocument(data);
loadingTask.promise.then(function(pdf) {
var total = pdf._pdfInfo.numPages;
//callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++){
pdf.getPage(i).then( function(page){
var n = page.pageNumber;
page.getTextContent().then( function(textContent){
//console.log(textContent.items[0]);0
if( null != textContent.items ){
var page_text = "";
var last_block = null;
for( var k = 0; k < textContent.items.length; k++ ){
var block = textContent.items[k];
if( last_block != null && last_block.str[last_block.str.length-1] != ' '){
if( block.x < last_block.x )
page_text += "\r\n";
else if ( last_block.y != block.y && ( last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null ))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++ self.complete;
//callbackPageDone( self.complete, total );
if (self.complete == total){
window.setTimeout(function(){
var full_text = "";
var num_pages = Object.keys(layers).length;
for( var j = 1; j <= num_pages; j++)
full_text += layers[j] ;
console.log(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
var pdff = new Pdf2TextClass();
pdff.pdfToText('PDF_URL');
</script>

For all the people who actually want to use it on a node server:
/**
* Created by velten on 25.04.16.
*/
"use strict";
let pdfUrl = "http://example.com/example.pdf";
let request = require('request');
var pdfParser = require('pdf2json');
let pdfPipe = request({url: pdfUrl, encoding:null}).pipe(pdfParser);
pdfPipe.on("pdfParser_dataError", err => console.error(err) );
pdfPipe.on("pdfParser_dataReady", pdf => {
//optionally:
//let pdf = pdfParser.getMergedTextBlocksIfNeeded();
let count1 = 0;
//get text on a particular page
for (let page of pdf.formImage.Pages) {
count1 += page.Texts.length;
}
console.log(count1);
pdfParser.destroy();
});

It is possible but:
you would have to use the server anyway, there's no way you can get content of a file on user computer without transferring it to server and back
I don't thing anyone has written such library yet
So if you have some free time you can learn pdf format and write such a library yourself, or you can just use server side library of course.

Editing PDFs with Hummus.js problem with certain pages

i am currently trying to edit a pdf with hummus.js to replace certain placeholder characters in the pdf with others.
This works perfectly fine for almost every page, but for certain pages I get the following error:
TypeError:
pageObject.getDictionary(...).toJSObject(...).Contents.getObjectID is
not a function for:
const textObjectID = pageObject.getDictionary().toJSObject().Contents.getObjectID();
Whenever that error happens and it doesnt work,
pageObject.getDictionary().toJSObject().Contents returns a PDFArray {}, while, when it works, it returns an PDFIndirectObjectReference {}
Does anybody know how I could solve this issue or any other way to edit a pdf that way (replacing certain placeholder characters with others)
UPDATE 1: I can now differentiate between IndirectObjectReferences and arrays containing IndirectObjectReferences, but for some reason it removes all text but keeps the images from pdf pages which i access through these arrays, the rest of the pdf pages still work perfectly fine
async function replacetext(filePath, callback) {
var pageCount = 0;
const modPdfWriter = hummus.createWriterToModify(filePath+'.pdf', { modifiedFilePath: `${filePath}-modified.pdf`, compress: false })
const numPages = modPdfWriter.createPDFCopyingContextForModifiedFile().getSourceDocumentParser().getPagesCount()
var log="";
for (let page = 0; page < numPages; page++) {
const copyingContext = modPdfWriter.createPDFCopyingContextForModifiedFile()
const objectsContext = modPdfWriter.getObjectsContext()
const pageObject = copyingContext.getSourceDocumentParser().parsePage(page)
pageCount = pageCount + 1;
try
{
var replaceTextRight = " " + pageCount.toString();
if(pageCount > 9 && pageCount < 100)
{
replaceTextRight = " " + pageCount.toString();
}
else if(pageCount > 99)
{
replaceTextRight = " " + pageCount.toString();
}
const textStream = copyingContext.getSourceDocumentParser().queryDictionaryObject(pageObject.getDictionary(), 'Contents')
console.log(textStream);
if(textStream.toString() == 'Array')
{
let data = []
streamArray = textStream.toJSArray();
for(var i = 0; i<streamArray.length; i++)
{
var streamo = copyingContext.getSourceDocumentParser().queryArrayObject(textStream, i);
const readStream = copyingContext.getSourceDocumentParser().startReadingFromStream(streamo)
while (readStream.notEnded()) {
const readData = readStream.read(10000)
data = data.concat(readData)
}
var redactedPdfPageAsString = new Buffer.from(data).toString();
var replacedBuffer = replace(redactedPdfPageAsString, "12345", pageCount.toString());
log = log+" \n Replaced " +page +" with " + pageCount.toString();
var replacedBuffer = replace(replacedBuffer, "67890", replaceTextRight);
log = log+" \n Replaced " +page +" with " + replaceTextRight;
var textObjectID = streamArray[i].getObjectID();
objectsContext.startModifiedIndirectObject(textObjectID)
var stream = objectsContext.startUnfilteredPDFStream();
stream.getWriteStream().write(strToByteArray(replacedBuffer));
objectsContext.endPDFStream(stream);
objectsContext.endIndirectObject();
}
}
else
{
let data = []
const readStream = copyingContext.getSourceDocumentParser().startReadingFromStream(textStream)
while (readStream.notEnded()) {
const readData = readStream.read(10000)
data = data.concat(readData)
}
var redactedPdfPageAsString = new Buffer.from(data).toString();
var replacedBuffer = replace(redactedPdfPageAsString, "12345", pageCount.toString());
log = log+" \n Replaced " +page +" with " + pageCount.toString();
var replacedBuffer = replace(replacedBuffer, "67890", replaceTextRight);
log = log+" \n Replaced " +page +" with " + replaceTextRight;
const textObjectID = pageObject.getDictionary().toJSObject().Contents.getObjectID();
var content = pageObject.getDictionary().toJSObject().Contents;
objectsContext.startModifiedIndirectObject(textObjectID)
const stream = objectsContext.startUnfilteredPDFStream();
stream.getWriteStream().write(strToByteArray(replacedBuffer));
objectsContext.endPDFStream(stream);
objectsContext.endIndirectObject();
}
}
catch(e){
console.log(e);
}
}
fs.writeFile('C:\\Users\\Administrator\\Downloads\\PDFModifyDebugging\\PDFWRITELOG.txt', log, function (err) {
if (err) return console.log(err);
console.log('written in file');
});
modPdfWriter.end()
hummus.recrypt(`${filePath}-modified.pdf`, filePath)
callback();
}

Google forms not asking for permissions Google Scripts

So I already looked at all the articles that I could find here, yet I still couldn't solve the problem. My question is how do I make Google App Scripts ask for permission to view certain files. Here's the problem in Google App Scripts:
Script:
var NamesToDelete = [""];
function moveFiles(sourceFileId, targetFolderId) {
var file = DriveApp.getFileById(sourceFileId);
var folder = DriveApp.getFolderById(targetFolderId);
file.moveTo(folder);
}
function createFolder(folderName){
var parentFolder = DriveApp.getRootFolder();
var subFolders = parentFolder.getFolders();
var doesntExists = true;
var newFolder = '';
// Check if folder already exists.
while(subFolders.hasNext()){
var folder = subFolders.next();
//If the name exists return the id of the folder
if(folder.getName() === folderName){
doesntExists = false;
newFolder = folder;
return newFolder.getId();
};
};
//If the name doesn't exists, then create a new folder
if(doesntExists == true){
//If the file doesn't exists
newFolder = parentFolder.createFolder(folderName);
return newFolder.getId();
};
};
function start(user){
var body = "Hello " + user + ",<br> Your google drive cleanup has been successfully initiated. <br> Please go to your drive and click the file named 'Delete Me.' Select everything inside (shift+select) and right click it. In the options that come up, click 'Remove.' <br> Thank you, <br> SS Tools"
body = body + "<br> Words you chose: <br>";
for (var i = 0; i<NamesToDelete.length; i++) {
body = body + NamesToDelete[i] + "<br>";
}
var NEW_FOLDER_NAME = "DELETE ME";
var myFolderID = createFolder(NEW_FOLDER_NAME);
var tutorialPicture = UrlFetchApp
.fetch("https://i.gyazo.com/f8716f9d9b0539506a78fba52e12788b.png")
.getBlob()
.setName("How to Delete");
Logger.log(myFolderID);
listFolders(myFolderID)
MailApp.sendEmail({
to: user,
subject: "SS Tools: Drive Cleanup Successfully Initiated",
htmlBody: body,
inlineImages:
{
Tutorial: tutorialPicture,
}
});
};
function FirstWord(word) {
var wordLength = word.length
var firstWord = ""
for (var i = 0; i < wordLength; i++) {
var c = word[i]
if (c == " ") {
break;
}
else if(c >= '0' && c <= '9') {
continue;
}
firstWord = firstWord + word[i]
}
return firstWord
}
function checkIfDeleteAB(One, Two) {
var theFirstWord = FirstWord(One)
if (theFirstWord == Two || theFirstWord == "") {
return true
}
return false
}
function listFolders(parentID, folder) {
folder = folder || DriveApp.getRootFolder();
var name = folder.getName();
var files = folder.getFiles();
while ( files.hasNext() ) {
var nextFile = files.next();
var nextName = nextFile.getName();
var arrayLength = NamesToDelete.length
for (var i = 0; i < arrayLength; i++) {
if (checkIfDeleteAB(nextName, NamesToDelete[i])) {
Logger.log(name + " :: " + nextName);
//nextFile.setTrashed(true);
moveFiles(nextFile.getId(), parentID);
break;
}
}
}
var subfolders = folder.getFolders();
while (subfolders.hasNext()) {
listFolders(parentID, subfolders.next());
}
}
function GetResponsesArray(form) {
var response = form.response;
var user = response.getRespondentEmail();
var item = response.getItemResponses();
var array = item[0].getResponse();
var word = "";
var c = 0;
var done = false;
Logger.log(array)
for (var i = 0; i<array.length; i++){
if(array[i] == " "){
c = 0;
NamesToDelete.push(word);
Logger.log(word)
word = "";
done = true;
}else{
word += array[i];
Logger.log("Shaping word :: " + word)
c++;
done = false;
}
}
if (done == false){
NamesToDelete.push(word);
}
Logger.log(user)
start(user);
}
If you can find the answer to my question I would be grateful!

Google gives the following explanation for the Access denied: DriveApp exception:
Administrators of G Suite domains have the ability to disable the Drive SDK for their domain, which prevents their users from installing and using Google Drive apps. This setting also prevents the users from being able to use Apps Script add-ons that use the Drive service or Advanced Drive Service (even if the script was authorized prior to the admin disabling Drive SDK).
In other words, it seems like you are not the admin of your domain and the admin had disabled the usage of Drive SDK for you / for the whole doman.
You need to contact the admin and ask him to change permissions.

class inheritance in javascript/angular

I am working on my hello world project. I have two pages let's call them "configuration" and "add configuration" *.html. Each one has its own controller like this:
angular.module('MissionControlApp').controller('ConfigController', ConfigController);
angular.module('MissionControlApp').controller('AddConfigController', AddConfigController);
Now, each controller has some properties that very much overlap:
function ConfigController($routeParams, ConfigFactory, $window){
var vm = this;
vm.status;
vm.projectId = $routeParams.projectId;
vm.selectedProject;
vm.configurations;
vm.selectedConfig;
vm.selectedRecords;
vm.filteredConfig;
vm.newFile;
vm.fileWarningMsg = '';
vm.addFile = function(){
var filePath = vm.newFile;
var encodedUri = encodeURIComponent(filePath);
vm.fileWarningMsg='';
ConfigFactory
.getByEncodedUri(encodedUri).then(function(response){
var configFound = response.data;
var configNames = '';
var configMatched = false;
if(response.status === 200 && configFound.length > 0){
//find an exact match from text search result
for(var i = 0; i < configFound.length; i++) {
var config = configFound[i];
for(var j=0; j<config.files.length; j++){
var file = config.files[j];
if(file.centralPath.toLowerCase() === filePath.toLowerCase()){
configMatched = true;
configNames += ' [' + config.name + '] ';
break;
}
}
}
}
if(configMatched){
vm.fileWarningMsg = 'Warning! File already exists in other configurations.\n' + configNames;
} else if(filePath.length > 0 && filePath.includes('.rvt')){
var file1 = { centralPath: filePath };
vm.selectedConfig.files.push(file1);
vm.newFile = '';
} else{
vm.fileWarningMsg = 'Warning! Please enter a valid file.';
}
}, function(error){
vm.status = 'Unable to get configuration data: ' + error.message;
});
};
My AddConfigController also wants to have the same functionality for addFile() so I just copy pasted the same code, but coming from C# i am sure i can do some class inheritance here, and just inherit from ConfigController and extend...right?
If this is super noob question. then apologies. js is a bit of a mystery to me.
function AddConfigController($routeParams, ConfigFactory, $window){
var vm = this;
vm.status;
vm.projectId = $routeParams.projectId;
vm.selectedProject = {};
vm.newConfig = {};
vm.newFile;
vm.fileWarningMsg = '';
vm.addFile = function(){
var filePath = vm.newFile;
var encodedUri = encodeURIComponent(filePath);
vm.fileWarningMsg='';
ConfigFactory
.getByEncodedUri(encodedUri).then(function(response){
var configFound = response.data;
var configNames = '';
var configMatched = false;
if(response.status === 200 && configFound.length > 0){
//find an exact match from text search result
for(var i = 0; i < configFound.length; i++) {
var config = configFound[i];
for(var j=0; j<config.files.length; j++){
var file = config.files[j];
if(file.centralPath.toLowerCase() === filePath.toLowerCase()){
configMatched = true;
configNames += ' [' + config.name + '] ';
break;
}
}
}
}
if(configMatched){
vm.fileWarningMsg = 'Warning! File already exists in other configurations.\n' + configNames;
} else if(filePath.length > 0 && filePath.includes('.rvt')){
var file1 = { centralPath: filePath };
vm.selectedConfig.files.push(file1);
vm.newFile = '';
} else{
vm.fileWarningMsg = 'Warning! Please enter a valid file.';
}
}, function(error){
vm.status = 'Unable to get configuration data: ' + error.message;
});
};

Since you asked about inheritance and you appear to be using ECMAScript 5, let me suggest taking a look at Object.create(). Specifically, the classical inheritance example.
That said, in AngularJS, a better solution would be to create a Service that manages files or configurations and put the addFile function in there. That way, both controllers could inject the service and call the same function when it is time to add a file. Likewise, other services and controllers that may need access to this functionality could inject it as well.

remove blank lines when uploading csv files angular

I got a csv-reader directive and let's user upload a csv file. I noticed that when I upload a file with spaces between words for example:
abc
abc
abc
abc
abc
this gets shown. I want to delete all the blank lines Not sure what to do.
var reader = new FileReader();
reader.onload = function(e) {
var contents = e.target.result;
var rows = contents.split('\n');
// Check if the last row is empty. This works
if(rows[rows.length-1] ===''){
rows.pop()
}
}
// this doesn't work for some reason. It doesn't detect the '' in the middle of the arrays.
for( var i=rows.length-1;i>0;i--){
if(rows[i] === ''){
rows.splice(i,1)
}
}

Try using Array.prototype.filter()
var rows = contents.split('\n').filter(function(str){
return str;
});

From what you have shown it looks like you want to check if each item in the csvModel is an empty string, rather than newValue
Something like:
for( var i=0 ;i< $scope.csvModel.length; i++){
if (csvModel[i] == "") {
$scope.csvModel.splice(i,1);
}
}

var text = [];
var target = $event.target || $event.srcElement;
var files = target.files;
if(Constants.validateHeaderAndRecordLengthFlag){
if(!this._fileUtil.isCSVFile(files[0])){
alert("Please import valid .csv file.");
this.fileReset();
}
}
var input = $event.target;
var reader = new FileReader();
reader.readAsText(input.files[0], 'UTF-8');
reader.onload = (data) => {
let csvData = reader.result;
let csvRecordsArray = csvData.split(/\r\n|\n/);
if (csvRecordsArray[csvRecordsArray.length - 1] === '') {
csvRecordsArray.pop();
}
var headerLength = -1;
if(Constants.isHeaderPresentFlag){
let headersRow = this._fileUtil.getHeaderArray(csvRecordsArray, Constants.tokenDelimeter);
headerLength = headersRow.length;
}
this.csvRecords = this._fileUtil.getDataRecordsArrayFromCSVFile(csvRecordsArray,
headerLength, Constants.validateHeaderAndRecordLengthFlag, Constants.tokenDelimeter);
if(this.csvRecords===null){
this.csvRecords=[];
}
else if(this.csvRecords!==null) {
if ((JSON.stringify(this.csvRecords[0])) === (JSON.stringify(this.csvFormate))) {
alert("format matches");
this.displayCsvContent = true;
for (let i = 0; i < this.csvRecords.length; i++) {
if (i !== 0) {
this.csvRecords[i].push(this.recordInsertedFlag);
}
}
}
else {
alert("format not matches");
}
}
if(this.csvRecords == null){
this.displayCsvContent=false;
//If control reached here it means csv file contains error, reset file.
this.fileReset();
}
};
reader.onerror = function () {
alert('Unable to read ' + input.files[0]);
};