49 lines
988 B
Go
49 lines
988 B
Go
package topdata
|
||
|
||
import (
|
||
"html"
|
||
"strings"
|
||
"unicode"
|
||
|
||
"golang.org/x/text/unicode/norm"
|
||
)
|
||
|
||
func slugifyWikiText(value string, fallback string) string {
|
||
value = html.UnescapeString(strings.TrimSpace(value))
|
||
var b strings.Builder
|
||
lastDash := false
|
||
for _, r := range norm.NFKD.String(strings.ToLower(value)) {
|
||
switch {
|
||
case r >= 'a' && r <= 'z':
|
||
b.WriteRune(r)
|
||
lastDash = false
|
||
case r >= '0' && r <= '9':
|
||
b.WriteRune(r)
|
||
lastDash = false
|
||
case unicode.Is(unicode.Mn, r):
|
||
continue
|
||
case isWikiSlugJoinerPunctuation(r):
|
||
continue
|
||
default:
|
||
if b.Len() > 0 && !lastDash {
|
||
b.WriteByte('-')
|
||
lastDash = true
|
||
}
|
||
}
|
||
}
|
||
slug := strings.Trim(b.String(), "-")
|
||
if slug == "" {
|
||
return fallback
|
||
}
|
||
return slug
|
||
}
|
||
|
||
func isWikiSlugJoinerPunctuation(r rune) bool {
|
||
switch r {
|
||
case '\'', '"', '`', '´', '‘', '’', '‚', '‛', '“', '”', '„', '‟', '‹', '›', '«', '»', '′', '″', ''', '"':
|
||
return true
|
||
default:
|
||
return false
|
||
}
|
||
}
|