Golang : Format strings to SEO friendly URL example

Problem:

You want to take a string and format it to SEO friendly URL. SEO friendly means no uppercase, underscore and characters deemed not suitable for search engine crawlers. How to do that?

NOTES: This example can be used in sanitazing and cleaning up input strings as well.

Solution:

Ported this PHP function to Golang

 function SEOfriendlyURL($string)
 {
 $string = strtolower($string);
 $string = str_replace(" ", "-", $string);
 $string = str_replace("/", "-", $string);

 $string = preg_replace('/\s+/', '-', $string);
 $string = preg_replace("`\[.*\]`U", "", $string);
 $string = preg_replace('`&(amp;)?#?[a-z0-9]+;`i', '-', $string);
 $string = preg_replace("/[^\x9\xA\xD\x20-\x7F]/", "", $string);
 $string = htmlentities($string, ENT_COMPAT, 'utf-8');
 $string = preg_replace("`&([a-z])(acute|uml|circ|grave|ring|cedil|slash|tilde|caron|lig|quot|rsquo);`i", "\\1", $string);
 $string = preg_replace(array("`[^a-z0-9]`i", "`[-]+`"), "-", $string);
 return strtolower(trim($string, '-'));
 }

and added some improvements to normalize unicode strings and remove all diacritical/accents marks.

Here you go!

 package main

 import (
 "fmt"
 "golang.org/x/text/transform"
 "golang.org/x/text/unicode/norm"
 "regexp"
 "strings"
 "unicode"
 )

 func isMn(r rune) bool {
 return unicode.Is(unicode.Mn, r) // Mn: nonspacing marks
 }

 func SEOURL(s string) string {
 seoStr := strings.ToLower(s)
 //seoStr = strings.Replace(seoStr, "/", "-", -1)

 //regE := regexp.MustCompile("/s+/")
 //seoStrByte := regE.ReplaceAll([]byte(seoStr), []byte("-"))
 //seoStr = string(seoStrByte) // convert []byte to string

 // convert all spaces to dash
 regE := regexp.MustCompile("[[:space:]]")
 seoStrByte := regE.ReplaceAll([]byte(seoStr), []byte("-"))
 seoStr = string(seoStrByte) // convert []byte to string

 // remove all blanks such as tab
 regE = regexp.MustCompile("[[:blank:]]")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte(""))
 seoStr = string(seoStrByte) // convert []byte to string

 // remove all punctuations with the exception of dash
 //regE = regexp.MustCompile("[[:punct:]]")

 regE = regexp.MustCompile("[!/:-@[-`{-~]")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte(""))
 seoStr = string(seoStrByte) // convert []byte to string

 // \x9\xA\xD will cause non-hex character in escape sequence error
 // regE = regexp.MustCompile("/[^\x9\xA\xD\x20-\x7F]/")

 //regE = regexp.MustCompile("[[:xdigit:]]") -- will remove some alphabet. Bug?

 regE = regexp.MustCompile("/[^\x20-\x7F]/")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte(""))
 seoStr = string(seoStrByte) // convert []byte to string

 regE = regexp.MustCompile("`&(amp;)?#?[a-z0-9]+;`i")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte("-"))
 seoStr = string(seoStrByte) // convert []byte to string

 regE = regexp.MustCompile("`&([a-z])(acute|uml|circ|grave|ring|cedil|slash|tilde|caron|lig|quot|rsquo);`i")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte("\\1"))
 seoStr = string(seoStrByte) // convert []byte to string

 regE = regexp.MustCompile("`[^a-z0-9]`i")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte("-"))
 seoStr = string(seoStrByte) // convert []byte to string

 regE = regexp.MustCompile("`[-]+`")
 seoStrByte = regE.ReplaceAll([]byte(seoStr), []byte("-"))
 seoStr = string(seoStrByte) // convert []byte to string

 // normalize unicode strings and remove all diacritical/accents marks
 // see https://www.socketloop.com/tutorials/golang-normalize-unicode-strings-for-comparison-purpose

 t := transform.Chain(norm.NFD, transform.RemoveFunc(isMn), norm.NFC)
 seoStr, _, _ = transform.String(t, seoStr)

 return strings.TrimSpace(seoStr)
 }

 func main() {

 NonSEOString := "@<ElNi\u00f1o coming?  > #% sooner this year!"

 fmt.Println("BEFORE : ", NonSEOString)

 SEOedString := SEOURL(NonSEOString)

 fmt.Println("AFTER : ", SEOedString)
 }

Output:

BEFORE : @<ElNiño coming? > #% sooner this year!

AFTER : elnino-coming--#%-sooner-this-year

NOTES: This example is not perfect as regular expression is not exactly my forte. Also, the conversion from byte to string can be optimized instead of converting in and out. Will leave it as an exercise for you. ;-)

References:

https://golang.org/pkg/regexp/#Regexp.ReplaceAll

https://golang.org/pkg/regexp/syntax/#pkg-overview

https://www.socketloop.com/tutorials/golang-normalize-unicode-strings-for-comparison-purpose

https://www.socketloop.com/tutorials/trim-white-spaces-string-golang