golang remove html tag from string

remove_html_tag.go

package utils

import (
	"regexp"
	"sort"
	"strings"
)

// match html tag and replace it with ""
func RemoveHtmlTag(in string) string {
	// regex to match html tag
	const pattern = `(<\/?[a-zA-A]+?[^>]*\/?>)*`
	r := regexp.MustCompile(pattern)
	groups := r.FindAllString(in, -1)
	// should replace long string first
	sort.Slice(groups, func(i, j int) bool {
		return len(groups[i]) > len(groups[j])
	})
	for _, group := range groups {
		if strings.TrimSpace(group) != "" {
			in = strings.ReplaceAll(in, group, "")
		}
	}
	return in
}

your method for removing HTM tags is not very optimized. A simple regex or the bluemonday lib is much faster for the same result.

see bench and method comparaison here : https://go.dev/play/p/7fkN9Vp-86U