func NormalizeTitle(title string) string {
normalizedTitle := title
normalizedTitle = strings.ToLower(normalizedTitle)
normalizedTitle = RomanizeHepburn(title)
normalizedTitle = strings.ToLower(normalizedTitle)
normalizedTitle = RemoveTrailingApostrophe(normalizedTitle)
normalizedTitle, _, _ = transform.String(transform.Chain(
norm.NFD,
transform.RemoveFunc(func(r rune) bool {
return unicode.Is(unicode.Mn, r)
}),
norm.NFC), normalizedTitle)
normalizedTitle = strings.ToLower(normalizedTitle)
normalizedTitle = regexp.MustCompile(`\(\d+\)`).ReplaceAllString(normalizedTitle, " ")
normalizedTitle = strings.Map(func(r rune) rune {
if !unicode.IsLetter(r) && !unicode.IsDigit(r) && r != '.' {
return ' '
}
return r
}, normalizedTitle)
normalizedTitle = regexp.MustCompile(`\s+`).ReplaceAllString(normalizedTitle, " ")
normalizedTitle = strings.TrimSpace(normalizedTitle)
return normalizedTitle
}
func ExampleUTF8Validator() {
for i := 0; i < 2; i++ {
transformer := charmap.Windows1252.NewEncoder()
if i == 1 {
transformer = transform.Chain(encoding.UTF8Validator, transformer)
}
dst := make([]byte, 256)
src := []byte("abc\xffxyz") // src is invalid UTF-8.
nDst, nSrc, err := transformer.Transform(dst, src, true)
fmt.Printf("i=%d: produced %q, consumed %q, error %v\n",
i, dst[:nDst], src[:nSrc], err)
}
// Output:
// i=0: produced "abc\x1axyz", consumed "abc\xffxyz", error <nil>
// i=1: produced "abc", consumed "abc", error encoding: invalid UTF-8
}
