Created
May 3, 2023 02:53
-
-
Save fujimaki-k/739ccd482da2a346285997571a0a6d77 to your computer and use it in GitHub Desktop.
Unicode string normalization example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package main | |
import ( | |
"fmt" | |
"regexp" | |
"strings" | |
"golang.org/x/text/unicode/norm" | |
) | |
var ( | |
controlCodeRegexp = regexp.MustCompile(`\{p}`) | |
lineFeedRegexp = regexp.MustCompile(`\r\n|\r`) | |
) | |
func Normalize(value string) string { | |
values := strings.Split(lineFeedRegexp.ReplaceAllString(value, "\n"), "\n") | |
lines := make([]string, len(values)) | |
for index, line := range values { | |
lines[index] = controlCodeRegexp.ReplaceAllString(line, "") | |
} | |
return strings.TrimSpace(norm.NFKC.String(strings.Join(lines, ""))) | |
} | |
func main() { | |
message := "Fight dayo!" | |
fmt.Println(message) | |
fmt.Println(Normalize(message)) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment