func TestNonRepertoire(t *testing.T) {
testCases := []struct {
init func(e encoding.Encoding) (string, transform.Transformer, error)
e encoding.Encoding
src, want string
}{
{dec, EUCKR, "\xfe\xfe", "\ufffd"},
// {dec, EUCKR, "א", "\ufffd"}, // TODO: why is this different?
{enc, EUCKR, "א", ""},
{enc, EUCKR, "aא", "a"},
{enc, EUCKR, "\uac00א", "\xb0\xa1"},
// TODO: should we also handle Jamo?
}
for _, tc := range testCases {
dir, tr, wantErr := tc.init(tc.e)
dst, _, err := transform.String(tr, tc.src)
if err != wantErr {
t.Errorf("%s %v(%q): got %v; want %v", dir, tc.e, tc.src, err, wantErr)
}
if got := string(dst); got != tc.want {
t.Errorf("%s %v(%q):\ngot %q\nwant %q", dir, tc.e, tc.src, got, tc.want)
}
}
}
func TestNonRepertoire(t *testing.T) {
testCases := []struct {
init func(e encoding.Encoding) (string, transform.Transformer, error)
e encoding.Encoding
src, want string
}{
{dec, EUCJP, "\xfe\xfc", "\ufffd"},
{dec, ISO2022JP, "\x1b$B\x7e\x7e", "\ufffd"},
{dec, ShiftJIS, "\xef\xfc", "\ufffd"},
{enc, EUCJP, "갂", ""},
{enc, EUCJP, "a갂", "a"},
{enc, EUCJP, "丌갂", "\x8f\xb0\xa4"},
{enc, ISO2022JP, "갂", ""},
{enc, ISO2022JP, "a갂", "a"},
{enc, ISO2022JP, "朗갂", "\x1b$BzF\x1b(B"}, // switch back to ASCII mode at end
{enc, ShiftJIS, "갂", ""},
{enc, ShiftJIS, "a갂", "a"},
{enc, ShiftJIS, "\u2190갂", "\x81\xa9"},
}
for _, tc := range testCases {
dir, tr, wantErr := tc.init(tc.e)
dst, _, err := transform.String(tr, tc.src)
if err != wantErr {
t.Errorf("%s %v(%q): got %v; want %v", dir, tc.e, tc.src, err, wantErr)
}
if got := string(dst); got != tc.want {
t.Errorf("%s %v(%q):\ngot %q\nwant %q", dir, tc.e, tc.src, got, tc.want)
}
}
}
func ExampleRemove() {
t := transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC)
s, _, _ := transform.String(t, "résumé")
fmt.Println(s)
// Output:
// resume
}
func ExampleIf() {
// Widen everything but ASCII.
isASCII := func(r rune) bool { return r <= unicode.MaxASCII }
t := runes.If(runes.Predicate(isASCII), nil, width.Widen)
s, _, _ := transform.String(t, "ｱﾙｱﾉﾘｳ tech / 中國 / 5₩")
fmt.Println(s)
// Output:
// アルアノリウ tech / 中國 / 5￦
}
func ExampleIn() {
// Convert Latin characters to their canonical form, while keeping other
// width distinctions.
t := runes.If(runes.In(unicode.Latin), width.Fold, nil)
s, _, _ := transform.String(t, "ｱﾙｱﾉﾘｳ tech / アルアノリウ ｔｅｃｈ")
fmt.Println(s)
// Output:
// ｱﾙｱﾉﾘｳ tech / アルアノリウ tech
}
func ExampleMap() {
replaceHyphens := runes.Map(func(r rune) rune {
if unicode.Is(unicode.Hyphen, r) {
return '|'
}
return r
})
s, _, _ := transform.String(replaceHyphens, "a-b‐c⸗d﹣e")
fmt.Println(s)
// Output:
// a|b|c|d|e
}