Make encoding tests independent of LOCALE settings (#8018)
* Make encoding tests independent of LOCALE settings * Fix fmt * Force CI to restart
This commit is contained in:
parent
032c90e7c5
commit
6097ff68e7
1 changed files with 26 additions and 12 deletions
|
@ -62,19 +62,24 @@ func TestToUTF8WithErr(t *testing.T) {
|
||||||
}
|
}
|
||||||
|
|
||||||
func TestToUTF8WithFallback(t *testing.T) {
|
func TestToUTF8WithFallback(t *testing.T) {
|
||||||
|
// "ABC"
|
||||||
res := ToUTF8WithFallback([]byte{0x41, 0x42, 0x43})
|
res := ToUTF8WithFallback([]byte{0x41, 0x42, 0x43})
|
||||||
assert.Equal(t, []byte("ABC"), res)
|
assert.Equal(t, []byte{0x41, 0x42, 0x43}, res)
|
||||||
|
|
||||||
|
// "áéíóú"
|
||||||
res = ToUTF8WithFallback([]byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
res = ToUTF8WithFallback([]byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
||||||
assert.Equal(t, []byte("áéíóú"), res)
|
assert.Equal(t, []byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba}, res)
|
||||||
|
|
||||||
|
// UTF8 BOM + "áéíóú"
|
||||||
res = ToUTF8WithFallback([]byte{0xef, 0xbb, 0xbf, 0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
res = ToUTF8WithFallback([]byte{0xef, 0xbb, 0xbf, 0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
||||||
assert.Equal(t, []byte("áéíóú"), res)
|
assert.Equal(t, []byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba}, res)
|
||||||
|
|
||||||
|
// "Hola, así cómo ños"
|
||||||
res = ToUTF8WithFallback([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0xF1, 0x6F, 0x73})
|
res = ToUTF8WithFallback([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0xF1, 0x6F, 0x73})
|
||||||
assert.Equal(t, []byte("Hola, así cómo ños"), res)
|
assert.Equal(t, []byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xC3, 0xAD, 0x20, 0x63, 0xC3, 0xB3, 0x6D, 0x6F, 0x20, 0xC3, 0xB1, 0x6F, 0x73}, res)
|
||||||
|
|
||||||
minmatch := []byte("Hola, así cómo ")
|
// "Hola, así cómo "
|
||||||
|
minmatch := []byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xC3, 0xAD, 0x20, 0x63, 0xC3, 0xB3, 0x6D, 0x6F, 0x20}
|
||||||
|
|
||||||
res = ToUTF8WithFallback([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0x07, 0xA4, 0x6F, 0x73})
|
res = ToUTF8WithFallback([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0x07, 0xA4, 0x6F, 0x73})
|
||||||
// Do not fail for differences in invalid cases, as the library might change the conversion criteria for those
|
// Do not fail for differences in invalid cases, as the library might change the conversion criteria for those
|
||||||
|
@ -85,8 +90,10 @@ func TestToUTF8WithFallback(t *testing.T) {
|
||||||
assert.Equal(t, minmatch, res[0:len(minmatch)])
|
assert.Equal(t, minmatch, res[0:len(minmatch)])
|
||||||
|
|
||||||
// Japanese (Shift-JIS)
|
// Japanese (Shift-JIS)
|
||||||
|
// "日属秘ぞしちゅ。"
|
||||||
res = ToUTF8WithFallback([]byte{0x93, 0xFA, 0x91, 0xAE, 0x94, 0xE9, 0x82, 0xBC, 0x82, 0xB5, 0x82, 0xBF, 0x82, 0xE3, 0x81, 0x42})
|
res = ToUTF8WithFallback([]byte{0x93, 0xFA, 0x91, 0xAE, 0x94, 0xE9, 0x82, 0xBC, 0x82, 0xB5, 0x82, 0xBF, 0x82, 0xE3, 0x81, 0x42})
|
||||||
assert.Equal(t, []byte("日属秘ぞしちゅ。"), res)
|
assert.Equal(t, []byte{0xE6, 0x97, 0xA5, 0xE5, 0xB1, 0x9E, 0xE7, 0xA7, 0x98, 0xE3,
|
||||||
|
0x81, 0x9E, 0xE3, 0x81, 0x97, 0xE3, 0x81, 0xA1, 0xE3, 0x82, 0x85, 0xE3, 0x80, 0x82}, res)
|
||||||
|
|
||||||
res = ToUTF8WithFallback([]byte{0x00, 0x00, 0x00, 0x00})
|
res = ToUTF8WithFallback([]byte{0x00, 0x00, 0x00, 0x00})
|
||||||
assert.Equal(t, []byte{0x00, 0x00, 0x00, 0x00}, res)
|
assert.Equal(t, []byte{0x00, 0x00, 0x00, 0x00}, res)
|
||||||
|
@ -124,19 +131,24 @@ func TestToUTF8(t *testing.T) {
|
||||||
}
|
}
|
||||||
|
|
||||||
func TestToUTF8DropErrors(t *testing.T) {
|
func TestToUTF8DropErrors(t *testing.T) {
|
||||||
|
// "ABC"
|
||||||
res := ToUTF8DropErrors([]byte{0x41, 0x42, 0x43})
|
res := ToUTF8DropErrors([]byte{0x41, 0x42, 0x43})
|
||||||
assert.Equal(t, []byte("ABC"), res)
|
assert.Equal(t, []byte{0x41, 0x42, 0x43}, res)
|
||||||
|
|
||||||
|
// "áéíóú"
|
||||||
res = ToUTF8DropErrors([]byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
res = ToUTF8DropErrors([]byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
||||||
assert.Equal(t, []byte("áéíóú"), res)
|
assert.Equal(t, []byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba}, res)
|
||||||
|
|
||||||
|
// UTF8 BOM + "áéíóú"
|
||||||
res = ToUTF8DropErrors([]byte{0xef, 0xbb, 0xbf, 0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
res = ToUTF8DropErrors([]byte{0xef, 0xbb, 0xbf, 0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba})
|
||||||
assert.Equal(t, []byte("áéíóú"), res)
|
assert.Equal(t, []byte{0xc3, 0xa1, 0xc3, 0xa9, 0xc3, 0xad, 0xc3, 0xb3, 0xc3, 0xba}, res)
|
||||||
|
|
||||||
|
// "Hola, así cómo ños"
|
||||||
res = ToUTF8DropErrors([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0xF1, 0x6F, 0x73})
|
res = ToUTF8DropErrors([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0xF1, 0x6F, 0x73})
|
||||||
assert.Equal(t, []byte("Hola, así cómo ños"), res)
|
assert.Equal(t, []byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xC3, 0xAD, 0x20, 0x63, 0xC3, 0xB3, 0x6D, 0x6F, 0x20, 0xC3, 0xB1, 0x6F, 0x73}, res)
|
||||||
|
|
||||||
minmatch := []byte("Hola, así cómo ")
|
// "Hola, así cómo "
|
||||||
|
minmatch := []byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xC3, 0xAD, 0x20, 0x63, 0xC3, 0xB3, 0x6D, 0x6F, 0x20}
|
||||||
|
|
||||||
res = ToUTF8DropErrors([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0x07, 0xA4, 0x6F, 0x73})
|
res = ToUTF8DropErrors([]byte{0x48, 0x6F, 0x6C, 0x61, 0x2C, 0x20, 0x61, 0x73, 0xED, 0x20, 0x63, 0xF3, 0x6D, 0x6F, 0x20, 0x07, 0xA4, 0x6F, 0x73})
|
||||||
// Do not fail for differences in invalid cases, as the library might change the conversion criteria for those
|
// Do not fail for differences in invalid cases, as the library might change the conversion criteria for those
|
||||||
|
@ -147,8 +159,10 @@ func TestToUTF8DropErrors(t *testing.T) {
|
||||||
assert.Equal(t, minmatch, res[0:len(minmatch)])
|
assert.Equal(t, minmatch, res[0:len(minmatch)])
|
||||||
|
|
||||||
// Japanese (Shift-JIS)
|
// Japanese (Shift-JIS)
|
||||||
|
// "日属秘ぞしちゅ。"
|
||||||
res = ToUTF8DropErrors([]byte{0x93, 0xFA, 0x91, 0xAE, 0x94, 0xE9, 0x82, 0xBC, 0x82, 0xB5, 0x82, 0xBF, 0x82, 0xE3, 0x81, 0x42})
|
res = ToUTF8DropErrors([]byte{0x93, 0xFA, 0x91, 0xAE, 0x94, 0xE9, 0x82, 0xBC, 0x82, 0xB5, 0x82, 0xBF, 0x82, 0xE3, 0x81, 0x42})
|
||||||
assert.Equal(t, []byte("日属秘ぞしちゅ。"), res)
|
assert.Equal(t, []byte{0xE6, 0x97, 0xA5, 0xE5, 0xB1, 0x9E, 0xE7, 0xA7, 0x98, 0xE3,
|
||||||
|
0x81, 0x9E, 0xE3, 0x81, 0x97, 0xE3, 0x81, 0xA1, 0xE3, 0x82, 0x85, 0xE3, 0x80, 0x82}, res)
|
||||||
|
|
||||||
res = ToUTF8DropErrors([]byte{0x00, 0x00, 0x00, 0x00})
|
res = ToUTF8DropErrors([]byte{0x00, 0x00, 0x00, 0x00})
|
||||||
assert.Equal(t, []byte{0x00, 0x00, 0x00, 0x00}, res)
|
assert.Equal(t, []byte{0x00, 0x00, 0x00, 0x00}, res)
|
||||||
|
|
Loading…
Reference in a new issue