How to highlight text using javascript

Question

You can use the jquery highlight effect.

But if you are interested in raw javascript code, take a look at what I got Simply copy paste into an HTML, open the file and click "highlight" - this should highlight the word "fox". Performance wise I think this would do for small text and a single repetition (like you specified)

function highlight(text) {
  var inputText = document.getElementById("inputText");
  var innerHTML = inputText.innerHTML;
  var index = innerHTML.indexOf(text);
  if (index >= 0) { 
   innerHTML = innerHTML.substring(0,index) + "<span class='highlight'>" + innerHTML.substring(index,index+text.length) + "</span>" + innerHTML.substring(index + text.length);
   inputText.innerHTML = innerHTML;
  }
}

.highlight {
  background-color: yellow;
}

<button onclick="highlight('fox')">Highlight</button>

<div id="inputText">
  The fox went over the fence
</div>

Edits:

Using replace

I see this answer gained some popularity, I thought I might add on it. You can also easily use replace

"the fox jumped over the fence".replace(/fox/,"<span>fox</span>");

Or for multiple occurrences (not relevant for the question, but was asked in comments) you simply add global on the replace regular expression.

"the fox jumped over the other fox".replace(/fox/g,"<span>fox</span>");

Hope this helps to the intrigued commenters.

Replacing the HTML to the entire web-page

to replace the HTML for an entire web-page, you should refer to innerHTML of the document's body.

document.body.innerHTML

The solutions offered here are quite bad.

1. You can't use regex, because that way, you search/highlight in the html tags.
2. You can't use regex, because it doesn't work properly with UTF* (anything with non-latin/English characters).
3. You can't just do an innerHTML.replace, because this doesn't work when the characters have a special HTML notation, e.g. & for &, < for <, > for >, ä for ä, ö for ö ü for ü ß for ß, etc.

What you need to do:

Loop through the HTML document, find all text nodes, get the textContent, get the position of the highlight-text with indexOf (with an optional toLowerCase if it should be case-insensitive), append everything before indexof as textNode, append the matched Text with a highlight span, and repeat for the rest of the textnode (the highlight string might occur multiple times in the textContent string).

Here is the code for this:

var InstantSearch = {

    "highlight": function (container, highlightText)
    {
        var internalHighlighter = function (options)
        {

            var id = {
                container: "container",
                tokens: "tokens",
                all: "all",
                token: "token",
                className: "className",
                sensitiveSearch: "sensitiveSearch"
            },
            tokens = options[id.tokens],
            allClassName = options[id.all][id.className],
            allSensitiveSearch = options[id.all][id.sensitiveSearch];


            function checkAndReplace(node, tokenArr, classNameAll, sensitiveSearchAll)
            {
                var nodeVal = node.nodeValue, parentNode = node.parentNode,
                    i, j, curToken, myToken, myClassName, mySensitiveSearch,
                    finalClassName, finalSensitiveSearch,
                    foundIndex, begin, matched, end,
                    textNode, span, isFirst;

                for (i = 0, j = tokenArr.length; i < j; i++)
                {
                    curToken = tokenArr[i];
                    myToken = curToken[id.token];
                    myClassName = curToken[id.className];
                    mySensitiveSearch = curToken[id.sensitiveSearch];

                    finalClassName = (classNameAll ? myClassName + " " + classNameAll : myClassName);

                    finalSensitiveSearch = (typeof sensitiveSearchAll !== "undefined" ? sensitiveSearchAll : mySensitiveSearch);

                    isFirst = true;
                    while (true)
                    {
                        if (finalSensitiveSearch)
                            foundIndex = nodeVal.indexOf(myToken);
                        else
                            foundIndex = nodeVal.toLowerCase().indexOf(myToken.toLowerCase());

                        if (foundIndex < 0)
                        {
                            if (isFirst)
                                break;

                            if (nodeVal)
                            {
                                textNode = document.createTextNode(nodeVal);
                                parentNode.insertBefore(textNode, node);
                            } // End if (nodeVal)

                            parentNode.removeChild(node);
                            break;
                        } // End if (foundIndex < 0)

                        isFirst = false;


                        begin = nodeVal.substring(0, foundIndex);
                        matched = nodeVal.substr(foundIndex, myToken.length);

                        if (begin)
                        {
                            textNode = document.createTextNode(begin);
                            parentNode.insertBefore(textNode, node);
                        } // End if (begin)

                        span = document.createElement("span");
                        span.className += finalClassName;
                        span.appendChild(document.createTextNode(matched));
                        parentNode.insertBefore(span, node);

                        nodeVal = nodeVal.substring(foundIndex + myToken.length);
                    } // Whend

                } // Next i 
            }; // End Function checkAndReplace 

            function iterator(p)
            {
                if (p === null) return;

                var children = Array.prototype.slice.call(p.childNodes), i, cur;

                if (children.length)
                {
                    for (i = 0; i < children.length; i++)
                    {
                        cur = children[i];
                        if (cur.nodeType === 3)
                        {
                            checkAndReplace(cur, tokens, allClassName, allSensitiveSearch);
                        }
                        else if (cur.nodeType === 1)
                        {
                            iterator(cur);
                        }
                    }
                }
            }; // End Function iterator

            iterator(options[id.container]);
        } // End Function highlighter
        ;


        internalHighlighter(
            {
                container: container
                , all:
                    {
                        className: "highlighter"
                    }
                , tokens: [
                    {
                        token: highlightText
                        , className: "highlight"
                        , sensitiveSearch: false
                    }
                ]
            }
        ); // End Call internalHighlighter 

    } // End Function highlight

};

Then you can use it like this:

function TestTextHighlighting(highlightText)
{
    var container = document.getElementById("testDocument");
    InstantSearch.highlight(container, highlightText);
}

Here's an example HTML document

<!DOCTYPE html>
<html>
    <head>
        <title>Example of Text Highlight</title>
        <style type="text/css" media="screen">
            .highlight{ background: #D3E18A;}
            .light{ background-color: yellow;}
        </style>
    </head>
    <body>
        <div id="testDocument">
            This is a test
            <span> This is another test</span>
            äöüÄÖÜäöüÄÖÜ
            <span>Test123&auml;&ouml;&uuml;&Auml;&Ouml;&Uuml;</span>
        </div>
    </body>
</html>

By the way, if you search in a database with LIKE,
e.g. WHERE textField LIKE CONCAT('%', @query, '%') [which you shouldn't do, you should use fulltext-search or Lucene], then you can escape every character with \ and add an SQL-escape-statement, that way you'll find special characters that are LIKE-expressions.

e.g.

WHERE textField LIKE CONCAT('%', @query, '%') ESCAPE '\'

and the value of @query is not '%completed%' but '%\c\o\m\p\l\e\t\e\d%'

(tested, works with SQL-Server and PostgreSQL, and every other RDBMS system that supports ESCAPE)

---

A revised typescript-version:

namespace SearchTools 
{


    export interface IToken
    {
        token: string;
        className: string;
        sensitiveSearch: boolean;
    }


    export class InstantSearch 
    {

        protected m_container: Node;
        protected m_defaultClassName: string;
        protected m_defaultCaseSensitivity: boolean;
        protected m_highlightTokens: IToken[];


        constructor(container: Node, tokens: IToken[], defaultClassName?: string, defaultCaseSensitivity?: boolean)
        {
            this.iterator = this.iterator.bind(this);
            this.checkAndReplace = this.checkAndReplace.bind(this);
            this.highlight = this.highlight.bind(this);
            this.highlightNode = this.highlightNode.bind(this);    

            this.m_container = container;
            this.m_defaultClassName = defaultClassName || "highlight";
            this.m_defaultCaseSensitivity = defaultCaseSensitivity || false;
            this.m_highlightTokens = tokens || [{
                token: "test",
                className: this.m_defaultClassName,
                sensitiveSearch: this.m_defaultCaseSensitivity
            }];
        }


        protected checkAndReplace(node: Node)
        {
            let nodeVal: string = node.nodeValue;
            let parentNode: Node = node.parentNode;
            let textNode: Text = null;

            for (let i = 0, j = this.m_highlightTokens.length; i < j; i++)
            {
                let curToken: IToken = this.m_highlightTokens[i];
                let textToHighlight: string = curToken.token;
                let highlightClassName: string = curToken.className || this.m_defaultClassName;
                let caseSensitive: boolean = curToken.sensitiveSearch || this.m_defaultCaseSensitivity;

                let isFirst: boolean = true;
                while (true)
                {
                    let foundIndex: number = caseSensitive ?
                        nodeVal.indexOf(textToHighlight)
                        : nodeVal.toLowerCase().indexOf(textToHighlight.toLowerCase());

                    if (foundIndex < 0)
                    {
                        if (isFirst)
                            break;

                        if (nodeVal)
                        {
                            textNode = document.createTextNode(nodeVal);
                            parentNode.insertBefore(textNode, node);
                        } // End if (nodeVal)

                        parentNode.removeChild(node);
                        break;
                    } // End if (foundIndex < 0)

                    isFirst = false;


                    let begin: string = nodeVal.substring(0, foundIndex);
                    let matched: string = nodeVal.substr(foundIndex, textToHighlight.length);

                    if (begin)
                    {
                        textNode = document.createTextNode(begin);
                        parentNode.insertBefore(textNode, node);
                    } // End if (begin)

                    let span: HTMLSpanElement = document.createElement("span");

                    if (!span.classList.contains(highlightClassName))
                        span.classList.add(highlightClassName);

                    span.appendChild(document.createTextNode(matched));
                    parentNode.insertBefore(span, node);

                    nodeVal = nodeVal.substring(foundIndex + textToHighlight.length);
                } // Whend

            } // Next i 

        } // End Sub checkAndReplace 


        protected iterator(p: Node)
        {
            if (p == null)
                return;

            let children: Node[] = Array.prototype.slice.call(p.childNodes);

            if (children.length)
            {
                for (let i = 0; i < children.length; i++)
                {
                    let cur: Node = children[i];

                    // https://developer.mozilla.org/en-US/docs/Web/API/Node/nodeType
                    if (cur.nodeType === Node.TEXT_NODE) 
                    {
                        this.checkAndReplace(cur);
                    }
                    else if (cur.nodeType === Node.ELEMENT_NODE) 
                    {
                        this.iterator(cur);
                    }
                } // Next i 

            } // End if (children.length) 

        } // End Sub iterator


        public highlightNode(n:Node)
        {
            this.iterator(n);
        } // End Sub highlight 


        public highlight()
        {
            this.iterator(this.m_container);
        } // End Sub highlight 


    } // End Class InstantSearch 


} // End Namespace SearchTools 

Usage:

let searchText = document.getElementById("txtSearchText");
let searchContainer = document.body; // document.getElementById("someTable");
let highlighter = new SearchTools.InstantSearch(searchContainer, [
    {
        token: "this is the text to highlight" // searchText.value,
        className: "highlight", // this is the individual highlight class
        sensitiveSearch: false
    }
]);


// highlighter.highlight(); // this would highlight in the entire table
// foreach tr - for each td2 
highlighter.highlightNode(td2); // this highlights in the second column of table

Why using a selfmade highlighting function is a bad idea

The reason why it's probably a bad idea to start building your own highlighting function from scratch is because you will certainly run into issues that others have already solved. Challenges:

• You would need to remove text nodes with HTML elements to highlight your matches without destroying DOM events and triggering DOM regeneration over and over again (which would be the case with e.g. innerHTML)
• If you want to remove highlighted elements you would have to remove HTML elements with their content and also have to combine the splitted text-nodes for further searches. This is necessary because every highlighter plugin searches inside text nodes for matches and if your keywords will be splitted into several text nodes they will not being found.
• You would also need to build tests to make sure your plugin works in situations which you have not thought about. And I'm talking about cross-browser tests!

Sounds complicated? If you want some features like ignoring some elements from highlighting, diacritics mapping, synonyms mapping, search inside iframes, separated word search, etc. this becomes more and more complicated.

Use an existing plugin

When using an existing, well implemented plugin, you don't have to worry about above named things. The article 10 jQuery text highlighter plugins on Sitepoint compares popular highlighter plugins.

Have a look at mark.js

mark.js is such a plugin that is written in pure JavaScript, but is also available as jQuery plugin. It was developed to offer more opportunities than the other plugins with options to:

• search for keywords separately instead of the complete term
• map diacritics (For example if "justo" should also match "justò")
• ignore matches inside custom elements
• use custom highlighting element
• use custom highlighting class
• map custom synonyms
• search also inside iframes
• receive not found terms

DEMO

Alternatively you can see this fiddle.

Usage example:

// Highlight "keyword" in the specified context
$(".context").mark("keyword");

// Highlight the custom regular expression in the specified context
$(".context").markRegExp(/Lorem/gmi);

It's free and developed open-source on GitHub (project reference).

function stylizeHighlightedString() {

    var text = window.getSelection();

    // For diagnostics
    var start = text.anchorOffset;
    var end = text.focusOffset - text.anchorOffset;

    range = window.getSelection().getRangeAt(0);

    var selectionContents = range.extractContents();
    var span = document.createElement("span");

    span.appendChild(selectionContents);

    span.style.backgroundColor = "yellow";
    span.style.color = "black";

    range.insertNode(span);
}

Here's my regexp pure JavaScript solution:

function highlight(text) {
    document.body.innerHTML = document.body.innerHTML.replace(
        new RegExp(text + '(?!([^<]+)?<)', 'gi'),
        '<b style="background-color:#ff0;font-size:100%">$&</b>'
    );
}