How to wrap part of a text in a node with JavaScript

function parseText( element ){
  var stack = [ element ];
  var group = false;
  var re = /(?!\s|$).*?(\.|$)/;
  while ( stack.length > 0 ){
    var node = stack.shift();
    if ( node.nodeType === Node.TEXT_NODE )
    {
      if ( node.textContent.trim() != "" )
      {
        var match;
        while( node && (match = re.exec( node.textContent )) )
        {
          var start  = group ? 0 : match.index;
          var length = match[0].length + match.index - start;
          if ( start > 0 )
          {
            node = node.splitText( start );
          }
          var wrapper = document.createElement( 'span' );
          var next    = null;
          if ( match[1].length > 0 ){
            if ( node.textContent.length > length )
              next = node.splitText( length );
            group = false;
            wrapper.className = "sentence sentence-end";
          }
          else
          {
            wrapper.className = "sentence";
            group = true;
          }
          var parent  = node.parentNode;
          var sibling = node.nextSibling;
          wrapper.appendChild( node );
          if ( sibling )
            parent.insertBefore( wrapper, sibling );
          else
            parent.appendChild( wrapper );
          node = next;
        }
      }
    }
    else if ( node.nodeType === Node.ELEMENT_NODE || node.nodeType === Node.DOCUMENT_NODE )
    {
      stack.unshift.apply( stack, node.childNodes );
    }
  }
}

parseText( document.body );
.sentence {
  text-decoration: underline wavy red;
}

.sentence-end {
  border-right: 1px solid red;
}
<p>This is a sentence. This is another sentence.</p>
<p>This sentence has <strong>emphasis</strong> inside it.</p>
<p><span>This sentence spans</span><span> two elements.</span></p>

I would use "flat DOM" representation for such task.

In flat DOM this paragraph

<p>abc <a href="beta.html">def. ghij.</p>

will be represented by two vectors:

chars: "abc def. ghij.",
props:  ....aaaaaaaaaa, 

You will use normal regexp on chars to mark span areas on props vector:

chars: "abc def. ghij."
props:  ssssaaaaaaaaaa  
            ssss sssss

I am using schematic representation here, it's real structure is an array of arrays:

props: [
  [s],
  [s],
  [s],
  [s],
  [a,s],
  [a,s],
  ...
]

conversion tree-DOM <-> flat-DOM can use simple state automata.

At the end you will convert flat DOM to tree DOM that will look like:

<p><s>abc </s><a href="beta.html"><s>def.</s> <s>ghij.</s></p>

Just in case: I am using this approach in my HTML WYSIWYG editors.


Here are two ways to deal with this.

I don't know if the following will exactly match your needs. It's a simple enough solution to the problem, but at least it doesn't use RegEx to manipulate HTML tags. It performs pattern matching against the raw text and then uses the DOM to manipulate the content.


First approach

This approach creates only one <span> tag per match, leveraging some less common browser APIs.
(See the main problem of this approach below the demo, and if not sure, use the second approach).

The Range class represents a text fragment. It has a surroundContents function that lets you wrap a range in an element. Except it has a caveat:

This method is nearly equivalent to newNode.appendChild(range.extractContents()); range.insertNode(newNode). After surrounding, the boundary points of the range include newNode.

An exception will be thrown, however, if the Range splits a non-Text node with only one of its boundary points. That is, unlike the alternative above, if there are partially selected nodes, they will not be cloned and instead the operation will fail.

Well, the workaround is provided in the MDN, so all's good.

So here's an algorithm:

  • Make a list of Text nodes and keep their start indices in the text
  • Concatenate these nodes' values to get the text
  • Find matches over the text, and for each match:

    • Find the start and end nodes of the match, comparing the the nodes' start indices to the match position
    • Create a Range over the match
    • Let the browser do the dirty work using the trick above
    • Rebuild the node list since the last action changed the DOM

Here's my implementation with a demo:

function highlight(element, regex) {
    var document = element.ownerDocument;
    
    var getNodes = function() {
        var nodes = [],
            offset = 0,
            node,
            nodeIterator = document.createNodeIterator(element, NodeFilter.SHOW_TEXT, null, false);
            
        while (node = nodeIterator.nextNode()) {
            nodes.push({
                textNode: node,
                start: offset,
                length: node.nodeValue.length
            });
            offset += node.nodeValue.length
        }
        return nodes;
    }
    
    var nodes = getNodes(nodes);
    if (!nodes.length)
        return;
    
    var text = "";
    for (var i = 0; i < nodes.length; ++i)
        text += nodes[i].textNode.nodeValue;

    var match;
    while (match = regex.exec(text)) {
        // Prevent empty matches causing infinite loops        
        if (!match[0].length)
        {
            regex.lastIndex++;
            continue;
        }
        
        // Find the start and end text node
        var startNode = null, endNode = null;
        for (i = 0; i < nodes.length; ++i) {
            var node = nodes[i];
            
            if (node.start + node.length <= match.index)
                continue;
            
            if (!startNode)
                startNode = node;
            
            if (node.start + node.length >= match.index + match[0].length)
            {
                endNode = node;
                break;
            }
        }
        
        var range = document.createRange();
        range.setStart(startNode.textNode, match.index - startNode.start);
        range.setEnd(endNode.textNode, match.index + match[0].length - endNode.start);
        
        var spanNode = document.createElement("span");
        spanNode.className = "highlight";

        spanNode.appendChild(range.extractContents());
        range.insertNode(spanNode);
        
        nodes = getNodes();
    }
}

// Test code
var testDiv = document.getElementById("test-cases");
var originalHtml = testDiv.innerHTML;
function test() {
    testDiv.innerHTML = originalHtml;
    try {
        var regex = new RegExp(document.getElementById("regex").value, "g");
        highlight(testDiv, regex);
    }
    catch(e) {
        testDiv.innerText = e;
    }
}
document.getElementById("runBtn").onclick = test;
test();
.highlight {
  background-color: yellow;
  border: 1px solid orange;
  border-radius: 5px;
}

.section {
  border: 1px solid gray;
  padding: 10px;
  margin: 10px;
}
<form class="section">
  RegEx: <input id="regex" type="text" value="[A-Z].*?\." /> <button id="runBtn">Highlight</button>
</form>

<div id="test-cases" class="section">
  <div>foo bar baz</div>
  <p>
    <b>HTML</b> is a language used to make <b>websites.</b>
	It was developed by <i>CERN</i> employees in the early 90s.
  <p>
  <p>
    This program is <a href="beta.html">not stable yet. Do not use this in production yet.</a>
  </p>
  <div>foo bar baz</div>
</div>

Ok, that was the lazy approach which, unfortunately doesn't work for some cases. It works well if you only highlight across inline elements, but breaks when there are block elements along the way because of the following property of the extractContents function:

Partially selected nodes are cloned to include the parent tags necessary to make the document fragment valid.

That's bad. It'll just duplicate block-level nodes. Try the previous demo with the baz\s+HTML regex if you want to see how it breaks.


Second approach

This approach iterates over the matching nodes, creating <span> tags along the way.

The overall algorithm is straightforward as it just wraps each matching node in its own <span>. But this means we have to deal with partially matching text nodes, which requires some more effort.

If a text node matches partially, it's split with the splitText function:

After the split, the current node contains all the content up to the specified offset point, and a newly created node of the same type contains the remaining text. The newly created node is returned to the caller.

function highlight(element, regex) {
    var document = element.ownerDocument;
    
    var nodes = [],
        text = "",
        node,
        nodeIterator = document.createNodeIterator(element, NodeFilter.SHOW_TEXT, null, false);
        
    while (node = nodeIterator.nextNode()) {
        nodes.push({
            textNode: node,
            start: text.length
        });
        text += node.nodeValue
    }
    
    if (!nodes.length)
        return;

    var match;
    while (match = regex.exec(text)) {
        var matchLength = match[0].length;
        
        // Prevent empty matches causing infinite loops        
        if (!matchLength)
        {
            regex.lastIndex++;
            continue;
        }
        
        for (var i = 0; i < nodes.length; ++i) {
            node = nodes[i];
            var nodeLength = node.textNode.nodeValue.length;
            
            // Skip nodes before the match
            if (node.start + nodeLength <= match.index)
                continue;
        
            // Break after the match
            if (node.start >= match.index + matchLength)
                break;
            
            // Split the start node if required
            if (node.start < match.index) {
                nodes.splice(i + 1, 0, {
                    textNode: node.textNode.splitText(match.index - node.start),
                    start: match.index
                });
                continue;
            }
            
            // Split the end node if required
            if (node.start + nodeLength > match.index + matchLength) {
                nodes.splice(i + 1, 0, {
                    textNode: node.textNode.splitText(match.index + matchLength - node.start),
                    start: match.index + matchLength
                });
            }
            
            // Highlight the current node
            var spanNode = document.createElement("span");
            spanNode.className = "highlight";
            
            node.textNode.parentNode.replaceChild(spanNode, node.textNode);
            spanNode.appendChild(node.textNode);
        }
    }
}

// Test code
var testDiv = document.getElementById("test-cases");
var originalHtml = testDiv.innerHTML;
function test() {
    testDiv.innerHTML = originalHtml;
    try {
        var regex = new RegExp(document.getElementById("regex").value, "g");
        highlight(testDiv, regex);
    }
    catch(e) {
        testDiv.innerText = e;
    }
}
document.getElementById("runBtn").onclick = test;
test();
.highlight {
  background-color: yellow;
}

.section {
  border: 1px solid gray;
  padding: 10px;
  margin: 10px;
}
<form class="section">
  RegEx: <input id="regex" type="text" value="[A-Z].*?\." /> <button id="runBtn">Highlight</button>
</form>

<div id="test-cases" class="section">
  <div>foo bar baz</div>
  <p>
    <b>HTML</b> is a language used to make <b>websites.</b>
	It was developed by <i>CERN</i> employees in the early 90s.
  <p>
  <p>
    This program is <a href="beta.html">not stable yet. Do not use this in production yet.</a>
  </p>
  <div>foo bar baz</div>
</div>

This should be good enough for most cases I hope. If you need to minimize the number of <span> tags it can be done by extending this function, but I wanted to keep it simple for now.