Open In App

How to validate HTML tag using Regular Expression

Improve
Improve
Like Article
Like
Save
Share
Report

Given string str, the task is to check whether it is a valid HTML tag or not by using Regular Expression.
The valid HTML tag must satisfy the following conditions: 

  1. It should start with an opening tag (<).
  2. It should be followed by a double quotes string or single quotes string.
  3. It should not allow one double quotes string, one single quotes string or a closing tag (>) without single or double quotes enclosed.
  4. It should end with a closing tag (>).

Examples: 

Input: str = “<input value = ‘>’>”; 
Output: true 
Explanation: The given string satisfies all the above mentioned conditions.
Input: str = “<br/>”; 
Output: true 
Explanation: The given string satisfies all the above mentioned conditions.
Input: str = “br/>”; 
Output: false 
Explanation: The given string doesn’t starts with an opening tag “<“. Therefore, it is not a valid HTML tag.
Input: str = “<‘br/>”; 
Output: false 
Explanation: The given string has one single quotes string that is not allowed. Therefore, it is not a valid HTML tag.
Input: str = “<input value => >”; 
Output: false 
Explanation: The given string has a closing tag (>) without single or double quotes enclosed that is not allowed. Therefore, it is not a valid HTML tag.

Approach: The idea is to use Regular Expression to solve this problem. The following steps can be followed to compute the answer. 

  • Get the String.
  • Create a regular expression to check valid HTML tag as mentioned below: 
     

regex = “<(“[^”]*”|'[^’]*’|[^'”>])*>”; 

  • Where: 
    • < represents the string should start with an opening tag (<).
    • ( represents the starting of the group.
    • “[^”]*” represents the string should allow double quotes enclosed string.
    • | represents or.
    • ‘[^’]*‘ represents the string should allow single quotes enclosed string.
    • | represents or.
    • [^'”>] represents the string should not contain one single quote, double quotes, and “>”.
    • ) represents the ending of the group.
    • * represents 0 or more.
    • > represents the string should end with a closing tag (>).
  • Match the given string with the regular expression. In Java, this can be done by using Pattern.matcher().
  • Return true if the string matches with the given regular expression, else return false.

Below is the implementation of the above approach: 
 

C++




// C++ program to validate the
// HTML tag using Regular Expression
#include <iostream>
#include <regex>
using namespace std;
 
// Function to validate the HTML tag.
bool isValidHTMLTag(string str)
{
 
  // Regex to check valid HTML tag.
  const regex pattern("<(\"[^\"]*\"|'[^']*'|[^'\">])*>");
 
  // If the HTML tag
  // is empty return false
  if (str.empty())
  {
     return false;
  }
 
  // Return true if the HTML tag
  // matched the ReGex
  if(regex_match(str, pattern))
  {
    return true;
  }
  else
  {
    return false;
  }
}
 
// Driver Code
int main()
{
   
  // Test Case 1:
  string str1 = "<input value = '>'>";
  cout << ((isValidHTMLTag(str1)) ? "true" : "false") << endl;
 
  // Test Case 2:
  string str2 = "<br/>";
  cout << ((isValidHTMLTag(str2)) ? "true" : "false") << endl;
 
  // Test Case 3:
  string str3 = "br/>";
  cout << ((isValidHTMLTag(str3)) ? "true" : "false")<< endl;
 
  // Test Case 4:
  string str4 = "<'br/>";
  cout << ((isValidHTMLTag(str4))? "true" : "false") << endl;
 
 
  return 0;
}
 
// This code is contributed by yuvraj_chandra


Java




// Java program to validate
// HTML tag using regex.
 
import java.util.regex.*;
 
class GFG {
 
    // Function to validate
    // HTML tag using regex.
    public static boolean
    isValidHTMLTag(String str)
    {
        // Regex to check valid HTML tag.
        String regex
            = "<(\"[^\"]*\"|'[^']*'|[^'\">])*>";
 
        // Compile the ReGex
        Pattern p = Pattern.compile(regex);
 
        // If the string is empty
        // return false
        if (str == null) {
            return false;
        }
 
        // Find match between given string
        // and regular expression
        // using Pattern.matcher()
        Matcher m = p.matcher(str);
 
        // Return if the string
        // matched the ReGex
        return m.matches();
    }
 
    // Driver Code.
    public static void main(String args[])
    {
 
        // Test Case 1:
        String str1 = "<input value = '>'>";
        System.out.println(isValidHTMLTag(str1));
 
        // Test Case 2:
        String str2 = "<br/>";
        System.out.println(isValidHTMLTag(str2));
 
        // Test Case 3:
        String str3 = "br/>";
        System.out.println(isValidHTMLTag(str3));
 
        // Test Case 4:
        String str4 = "<'br/>";
        System.out.println(isValidHTMLTag(str4));
 
    }
}


Python3




# Python3 program to validate
# HTML tag using regex.  
# using regular expression
import re
 
# Function to validate
# HTML tag using regex.
def isValidHTMLTag(str):
 
    # Regex to check valid
    # HTML tag using regex.
    regex = "<(\"[^\"]*\"|'[^']*'|[^'\">])*>"
     
    # Compile the ReGex
    p = re.compile(regex)
 
    # If the string is empty
    # return false
    if (str == None):
        return False
 
    # Return if the string
    # matched the ReGex
    if(re.search(p, str)):
        return True
    else:
        return False
 
# Driver code
 
# Test Case 1:
str1 = "<input value = '>'>"
print(isValidHTMLTag(str1))
 
# Test Case 2:
str2 = "<br/>"
print(isValidHTMLTag(str2))
 
# Test Case 3:
str3 = "br/>"
print(isValidHTMLTag(str3))
 
# Test Case 4:
str4 = "<'br/>"
print(isValidHTMLTag(str4))
 
# This code is contributed by avanitrachhadiya2155


C#




// C# program to validate
// HTML tag using regex.
 
using System;
using System.Text.RegularExpressions;
 
class GFG {
 
  // Function to validate
  // HTML tag using regex.
  public static bool
    isValidHTMLTag(string str)
  {
    // Regex to check valid HTML tag.
    string regex
      = "<(\"[^\"]*\"|'[^']*'|[^'\">])*>";
 
    // Compile the ReGex
    Regex p = new Regex(regex);
 
    // If the string is empty
    // return false
    if (str == null) {
      return false;
    }
 
    // Find match between given string
    // and regular expression
    // using Pattern.matcher()
    Match m = p.Match(str);
 
    // Return if the string
    // matched the ReGex
    return m.Success;
  }
 
  // Driver Code.
  public static void Main()
  {
 
    // Test Case 1:
    string str1 = "<input value = '>'>";
    Console.WriteLine(isValidHTMLTag(str1));
 
    // Test Case 2:
    string str2 = "<br/>";
    Console.WriteLine(isValidHTMLTag(str2));
 
    // Test Case 3:
    string str3 = "br/>";
    Console.WriteLine(isValidHTMLTag(str3));
 
    // Test Case 4:
    string str4 = "<'br/>";
    Console.WriteLine(isValidHTMLTag(str4));
 
  }
}
 
// This code is contributed by Aman Kumar.


Javascript




// Javascript program to validate
// HTML tag using regex.
  
    // Function to validate
    // HTML tag using regex.
    function isValidHTMLTag(str)
    {
        // Regex to check valid HTML tag.
        let regex = new RegExp(/<(\"[^\"]*\"|'[^']*'|[^'\">])*>/);
 
        // If the string is empty
        // return false
        if (str == null) {
            return "false";
        }
  
        // Find match between given string
        // and regular expression
        if (regex.test(str) == true) {
            return "true";
        }
        else {
            return "false";
        }
    }
  
    // Driver Code.
  
        // Test Case 1:
        let str1 = "<input value = '>'>";
        console.log(isValidHTMLTag(str1)+"<br>");
  
        // Test Case 2:
        let str2 = "<br/>";
        console.log(isValidHTMLTag(str2)+"<br>");
  
        // Test Case 3:
        let str3 = "br/>";
        console.log(isValidHTMLTag(str3)+"<br>");
  
        // Test Case 4:
        let str4 = "<'br/>";
        console.log(isValidHTMLTag(str4)+"<br>");
         
   // This code is contributed by Utkarsh Kumar


Output: 

true
true
false
false
false

 

Time Complexity: O(N) for each test case, where N is the length of the given string. 
Auxiliary Space: O(1)



Last Updated : 03 Feb, 2023
Like Article
Save Article
Previous
Next
Share your thoughts in the comments
Similar Reads