JavaScript regular expression: inserting span tag for each character

I have a regular expression task at hand and can really use some help.

Say I have a text like below:

To Sherlock Holmes she is always <i>THE</i> woman.

I need to enclose each character in a span tag, with exception of HTML tags. For example, the text above would be:

<span>T</span><span>o</span><span> </span><span>S</span><span>h</span>
<span>e</span><span>r</span><span>l</span><span>o</span><span>c</span>
<span>k</span><span> </span><span>H</span><span>o</span><span>l</span>
<span>m</span><span>e</span><span>s</span><span> </span><span>s</span>
<span>h</span><span>e</span><span> </span><span>i</span><span>s</span>
<span> </span><span>a</span><span>l</span><span>w</span><span>a</span>
<span>y</span><span>s</span><span> </span><i><span>T</span><span>H<开发者_高级运维/span>
<span>E</span></i><span> </span><span>w</span><span>o</span><span>m</span>
<span>a</span><span>n</span><span>.</span>

Note that:

• each character is enclosed in a span tag, even a space
• HTML tag, <i></i> is not

Any suggestion is welcome.

Thanks!

This job is better handled by DOM interactions. The following two utility functions will work help wrapping each character in the given text with a span tag.

/**
 * recursively get all text nodes as an array for a given element
 */
function getTextNodes(node) {
    var childTextNodes = [];

    if (!node.hasChildNodes()) {
        return;
    }

    var childNodes = node.childNodes;
    for (var i = 0; i < childNodes.length; i++) {
        if (childNodes[i].nodeType == Node.TEXT_NODE) {
            childTextNodes.push(childNodes[i]);
        }
        else if (childNodes[i].nodeType == Node.ELEMENT_NODE) {
            Array.prototype.push.apply(childTextNodes, getTextNodes(childNodes[i]));
        }
    }

    return childTextNodes;
}

/**
 * given a text node, wrap each character in the
 * given tag.
 */
function wrapEachCharacter(textNode, tag) {
    var text = textNode.nodeValue;
    var parent = textNode.parentNode;

    var characters = text.split('');
    characters.forEach(function(character) {
        var element = document.createElement(tag);
        var characterNode = document.createTextNode(character);
        element.appendChild(characterNode);

        parent.insertBefore(element, textNode);
    });

    parent.removeChild(textNode);
}

Now given some piece of HTML, we will create a DOM representation of it, and then retrieve all text nodes from it using the first function - getTextNodes. Once we have all the text nodes, we can pass each one of them to the second function - wrapEachCharacter.

// create a wrapper element that will hold our HTML.
var container = document.createElement('div');
container.innerHTML = "To Sherlock Holmes she is always <i>THE</i> woman.";

// get all text nodes recursively.
var allTextNodes = getTextNodes(container);

// wrap each character in each text node thus gathered.
allTextNodes.forEach(function(textNode) {
    wrapEachCharacter(textNode, 'span');
});

An example is posted here.

Something along this line should do the trick

txt = txt.replace (/(<.*?>)|(.)/g, function (m0, tag, ch) {
   return tag || ('<span>' + ch + '</span>');
});

Don't use a regex, just loop over the string using a for loop:

var s = 'To Sherlock Holmes she is always <i>THE</i> woman.';
var out = '';
for (var z = 0; z < s.length; ++z) {
    var ch = s.charAt(z);
    if (ch == '<') {
        while (ch != '>') {
            out += ch;
            ch = s.charAt(++z);
        }
        out += ch;
        continue;
    }
    out += '<span>' + ch + '</span>';
}
alert(out);