how can i parse a csv with javascript for a non-web application?

Question

I am trying to write a script that will dynamically generate some InDesign templates using values contained within various columns of a local csv file.

There seems to be a number of ways to approach this for a browser application, however, I can't find anything for non-web applications and all attempts thus far have failed.

nb: data created on windows, using excel. I'm editing on my linux box, and running the script on a mac so I need a solution that takes all this into account.

This is what i have so far, incorporating some helpful code found here: http://www.bennadel.com/blog/1504-ask-ben-parsing-csv-strings-with-javascript-exec-regular-expression-command.htm

// target the latest version of InDesign
#target "InDesign-10"

// This will parse a delimited string into an array of
// arrays. The default delimiter is the comma, but this
// can be overriden in the second argument.
// http://www.bennadel.com/blog/1504-ask-ben-parsing-csv-strings-with-javascript-exec-regular-expression-command.htm

function CSVToArray( strData, strDelimiter ){
    // Check to see if the delimiter is defined. If not,
    // then default to comma.
    strDelimiter = (strDelimiter || ",");
    // Create a regular expression to parse the CSV values.
    var objPattern = new RegExp(
        (
            // Delimiters.
            "(\\" + strDelimiter + "|\\r?\\n|\\r|^)" +
                // Quoted fields.
                "(?:\"([^\"]*(?:\"\"[^\"]*)*)\"|" +
                // Standard fields.
                "([^\"\\" + strDelimiter + "\\r\\n]*))"
        ),
        "gi"
    );
    // Create an array to hold our data. Give the array
    // a default empty first row.
    var arrData = [[]];
    // Create an array to hold our individual pattern
    // matching groups.
    var arrMatches = null;
    // Keep looping over the regular expression matches
    // until we can no longer find a match.
    while (arrMatches = objPattern.exec( strData )){
        // Get the delimiter that was found.
        var strMatchedDelimiter = arrMatches[ 1 ];
        // Check to see if the given delimiter has a length
        // (is not the start of string) and if it matches
        // field delimiter. If id does not, then we know
        // that this delimiter is a row delimiter.
        if (
            strMatchedDelimiter.length &&
                (strMatchedDelimiter != strDelimiter)
        ){
            // Since we have reached a new row of data,
            // add an empty row to our data array.
            arrData.push( [] );
        }
        // Now that we have our delimiter out of the way,
        // let's check to see which kind of value we
        // captured (quoted or unquoted).
        if (arrMatches[ 2 ]){
            // We found a quoted value. When we capture
            // this value, unescape any double quotes.
            var strMatchedValue = arrMatches[ 2 ].replace(
                new RegExp( "\"\"", "g" ),
                "\""
            );
        } else {
            // We found a non-quoted value.
            var strMatchedValue = arrMatches[ 3 ];
        }
        // Now that we have our value string, let's add
        // it to the data array.
        arrData[ arrData.length - 1 ].push( strMatchedValue );
    }
    // Return the parsed data.
    return( arrData );
} 

var csv = CSVToArray(File("source.csv"), ",");

// create new document using specified presets
var myDocument              = app.documents.add();
var myTextFrame             = myDocument.pages.item(0).textFrames.add();
myTextFrame.geometricBounds =  ["6p", "6p", "24p", "24p"];
myTextFrame.contents        = csv[0];

no worky, advice appreciated

Answer 1

For the simplest case it's indeed trivial:

function parseCSV(text) {
    return text.split('\n').map(function(row) {
        var r = [];
        row.replace(/""/g, "\x01").replace(/"(.*?)"|([^\s,]+)/g, function(_, $1, $2) {
            r.push(($1 || $2).replace(/\x01/g, '"'));
        });
        return r;
    });
}

// example:

var t =
    '   "lorem ipsum",  dolor,                      sit\n' +
        ' consectetur, "adipiscing ""elit"" sed",   eiusmod';

csv = parseCSV(t);
document.write(JSON.stringify(csv));

However, if your csvs are non-standard, it will be a bit harder. I don't know if you can use node modules like csv in Adobe scripting, if not, you can at least look at their sources.