Text block in PDF-to-text conversion being broken up into multiple lines

[idea-launch-lab]

Hi,
I am trying to recover text from reference section from a pdf article, but the text block sometimes break up into multiple lines. A somewhat related issue might be #4629

Incorrect text splitting:

Correct text splitting:

I would like to recover text without extra line delimiters. Below is code I use to get text from pdf:

// PDFJS.version = '1.0.85';
// PDFJS.build = '094d0e2';

context.getPDFText = function pico_getPDFText() {

    // Variable to hold PDF text data
    var pdfTextContent = '';

    // pdfObj: global reference to PDF file object

    // Get each page and extract text content of the page
    for (var p = 1; p <= context.pdfObj.numPages; p++) {

        // Asynchronous processing
        context.pdfObj.getPage(p).then(function(res) {

            var content = res.getTextContent().then(function(textContent) {
                var promise = new Promise(function(resolve, reject) {

                    for (var i = 0; i < textContent.items.length; i++) {
                        var line = textContent.items[i].str.trim().toLowerCase();

                        if ((line.indexOf('reference') > -1 || line.indexOf('bibliograph') > -1) &&
                            (line === 'references' || line === 'bibliography')) {
                            // print references / bibliographic citations
                            console.log(line);
                        }
                    }

                });

            });
        });
    }
}

Thank you.
Sid

[Snuffleupagus]

Closing as incomplete, please provide a link to the PDF file (or attach it to the issue, since GitHub now supports that) in order to re-open the issue.