Extract text from HTML while preserving block-level element newlines

Question

Background

Most questions about extracting text from HTML (i.e., stripping the tags) use:

jQuery( htmlString ).text();

While this

Answer 1

based on https://stackoverflow.com/a/20384452/3338098 and fixed to support TEXT1

TEXT2

=>TEXT1\nTEXT2 and allow non-DOM nodes

/**
 * Returns the style for a node.
 *
 * @param n The node to check.
 * @param p The property to retrieve (usually 'display').
 * @link http://www.quirksmode.org/dom/getstyles.html
 */
function getNodeStyle( n, p ) {
  return n.currentStyle ?
    n.currentStyle[p] :
    document.defaultView.getComputedStyle(n, null).getPropertyValue(p);
}

//IF THE NODE IS NOT ACTUALLY IN THE DOM then this won't take into account 
text
//however for simple things like `contenteditable` this is sufficient, however for arbitrary html this will not work
function isNodeBlock(node) {
  if (node.nodeType == document.TEXT_NODE) {return false;}
  var d = getNodeStyle( node, 'display' );//this is irrelevant if the node isn't currently in the current DOM.
  if (d.match( /^block/ ) || d.match( /list/ ) || d.match( /row/ ) ||
      node.tagName == 'BR' || node.tagName == 'HR' ||
      node.tagName == 'DIV' // div,p,... add as needed to support non-DOM nodes
     ) {
    return true;
  }
  return false;
}

/**
 * Converts HTML to text, preserving semantic newlines for block-level
 * elements.
 *
 * @param node - The HTML node to perform text extraction.
 */
function htmlToText( htmlOrNode, isNode ) {
  var node = htmlOrNode;
  if (!isNode) {node = jQuery(""+htmlOrNode+"")[0];}
  //TODO: inject "unsafe" HTML into current DOM while guaranteeing that it won't
  //      change the visible DOM so that `isNodeBlock` will work reliably
  var result = '';
  if( node.nodeType == document.TEXT_NODE ) {
    // Replace repeated spaces, newlines, and tabs with a single space.
    result = node.nodeValue.replace( /\s+/g, ' ' );
  } else {
    for( var i = 0, j = node.childNodes.length; i < j; i++ ) {
      result += htmlToText( node.childNodes[i], true );
      if (i < j-1) {
        if (isNodeBlock(node.childNodes[i])) {
          result += '\n';
        } else if (isNodeBlock(node.childNodes[i+1]) &&
                   node.childNodes[i+1].tagName != 'BR' &&
                   node.childNodes[i+1].tagName != 'HR') {
          result += '\n';
        }
      }
    }
  }
  return result;
}

the main change was

      if (i < j-1) {
        if (isNodeBlock(node.childNodes[i])) {
          result += '\n';
        } else if (isNodeBlock(node.childNodes[i+1]) &&
                   node.childNodes[i+1].tagName != 'BR' &&
                   node.childNodes[i+1].tagName != 'HR') {
          result += '\n';
        }
      }

to check neighboring blocks to determine the appropriateness of adding a newline.