unvis_go: leave unicode unchanged with Unvis()

Because the original code for vis() was ported to Go using the []byte{}
notion, this causes issues for multi-rune bytes (which were not
correctly treated -- and caused loss of information).

Fix this by dealing with []rune instead, which better conveys the
concept at hand. In addition, add tests to ensure that this does not
happen again.

Though, we _really_ should move this code into a library which has a
better test suite -- and the parser itself should be reimplemented to be
less ... 80s.

Fixes: #118
Signed-off-by: Aleksa Sarai <asarai@suse.de>
This commit is contained in:
Aleksa Sarai 2017-02-10 23:08:00 +11:00
parent 0185fe9b62
commit f6dd726b66
No known key found for this signature in database
GPG key ID: 9E18AA267DDB8DB4
2 changed files with 74 additions and 21 deletions

View file

@ -43,3 +43,51 @@ func TestUnvisHelpers(t *testing.T) {
}
}
}
func TestUnvisUnicode(t *testing.T) {
// Ensure that unicode strings are not messed up by Unvis.
for _, test := range []string{
"",
"this.is.a.normal_string",
"AC_Raíz_Certicámara_S.A..pem",
"NetLock_Arany_=Class_Gold=_Főtanúsítvány.pem",
"TÜBİTAK_UEKAE_Kök_Sertifika_Hizmet_Sağlayıcısı_-_Sürüm_3.pem",
} {
got, err := Unvis(test)
if err != nil {
t.Errorf("unexpected error doing unvis(%q): %s", test, err)
continue
}
if got != test {
t.Errorf("expected %q to be unchanged, got %q", test, got)
}
}
}
func TestVisUnvis(t *testing.T) {
// Round-trip testing.
for _, test := range []string{
"",
"this.is.a.normal_string",
"AC_Raíz_Certicámara_S.A..pem",
"NetLock_Arany_=Class_Gold=_Főtanúsítvány.pem",
"TÜBİTAK_UEKAE_Kök_Sertifika_Hizmet_Sağlayıcısı_-_Sürüm_3.pem",
"hello world [ this string needs=enco ding! ]",
"even \n more encoding necessary\a\a ",
"\024 <-- some more weird characters --> 你好,世界",
} {
enc, err := Vis(test, DefaultVisFlags)
if err != nil {
t.Errorf("unexpected error doing vis(%q): %s", test, err)
continue
}
dec, err := Unvis(enc)
if err != nil {
t.Errorf("unexpected error doing unvis(%q): %s", enc, err)
continue
}
if dec != test {
t.Errorf("roundtrip failed: unvis(vis(%q) = %q) = %q", test, enc, dec)
}
}
}