filereader api on big files

Question

My file reader api code has been working good so far until one day I got a 280MB txt file from one of my client. Page just crashes straight up in Chrome and in Firefox nothing happens.

// create new reader object 
var fileReader = new FileReader(); 

// read the file as text 
fileReader.readAsText( $files[i] );  
fileReader.onload = function(e) 
{   // read all the information about the file 
    // do sanity checks here etc... 
    $timeout( function() 
    {    
        // var fileContent = e.target.result;
        // get the first line 
        var firstLine = e.target.result.slice(0, e.target.result.indexOf("\n") ); }}

What I am trying to do above is that get the first line break so that I can get the column length of the file. Should I not read it as text ? How can I get the column length of the file without breaking the page on big files?

Answer 1

Your application is failing for big files because you're reading the full file into memory before processing it. This inefficiency can be solved by streaming the file (reading chunks of a small size), so you only need to hold a part of the file in memory.

A File objects is also an instance of a Blob, which offers the .slice method to create a smaller view of the file.

Here is an example that assumes that the input is ASCII (demo: http://jsfiddle.net/mw99v8d4/).

function findColumnLength(file, callback) {
    // 1 KB at a time, because we expect that the column will probably small.
    var CHUNK_SIZE = 1024;
    var offset = 0;
    var fr = new FileReader();
    fr.onload = function() {
        var view = new Uint8Array(fr.result);
        for (var i = 0; i < view.length; ++i) {
            if (view[i] === 10 || view[i] === 13) {
                // \n = 10 and \r = 13
                // column length = offset + position of \r or \n
                callback(offset + i);
                return;
            }
        }
        // \r or \n not found, continue seeking.
        offset += CHUNK_SIZE;
        seek();
    };
    fr.onerror = function() {
        // Cannot read file... Do something, e.g. assume column size = 0.
        callback(0);
    };
    seek();

    function seek() {
        if (offset >= file.size) {
            // No \r or \n found. The column size is equal to the full
            // file size
            callback(file.size);
            return;
        }
        var slice = file.slice(offset, offset + CHUNK_SIZE);
        fr.readAsArrayBuffer(slice);
    }
}

The previous snippet counts the number of bytes before a line break. Counting the number of characters in a text consisting of multibyte characters is slightly more difficult, because you have to account for the possibility that the last byte in the chunk could be a part of a multibyte character.