SanitizeHTML

sanitize.go

// SanitizeHTML strips html tags, replace common entities
func SanitizeHTML(s string) string {

	output := ""

	// Shortcut strings with no tags in them
	if !strings.ContainsAny(s, "<>") {
		output = s
	} else {

		// First remove line breaks etc as these have no meaning outside html tags
		s = strings.Replace(s, "\n", "", -1)
		s = strings.Replace(s, "\r", "", -1)

		// Then replace line breaks with newlines, to preserve that formatting
		s = strings.Replace(s, "</p>", "\n", -1)
		s = strings.Replace(s, "<br>", "\n", -1)
		s = strings.Replace(s, "</br>", "\n", -1)
		s = strings.Replace(s, "<br/>", "\n", -1)

		// Walk through the string removing all tags
		b := bytes.NewBufferString("")
		inTag := false
		for _, r := range s {
			switch r {
			case '<':
				inTag = true
			case '>':
				inTag = false
			default:
				if !inTag {
					b.WriteRune(r)
				}
			}
		}
		output = b.String()
	}

	// Remove a few common harmless entities, to arrive at something more like plain text
	output = strings.Replace(output, "&#8216;", "'", -1)
	output = strings.Replace(output, "&#8217;", "'", -1)
	output = strings.Replace(output, "&#8220;", "\"", -1)
	output = strings.Replace(output, "&#8221;", "\"", -1)
	output = strings.Replace(output, "&nbsp;", " ", -1)
	output = strings.Replace(output, "&quot;", "\"", -1)
	output = strings.Replace(output, "&apos;", "'", -1)

	// Translate some entities into their plain text equivalent (for example accents, if encoded as entities)
	output = html.UnescapeString(output)

	return output
}