encoding/japanese: make iso2022jp replace with FFFD on error
This CL also fixes a bug in the JIS 212 mode.
Updates golang/go#18898
Change-Id: Idb10e375bbc5d278db4e8550f26986a5d2bb6caa
Reviewed-on: https://go-review.googlesource.com/37595
Run-TryBot: Marcel van Lohuizen <mpvl@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Nigel Tao <nigeltao@golang.org>
diff --git a/encoding/japanese/all_test.go b/encoding/japanese/all_test.go
index a3def34..9cffe10 100644
--- a/encoding/japanese/all_test.go
+++ b/encoding/japanese/all_test.go
@@ -5,6 +5,7 @@
package japanese
import (
+ "fmt"
"strings"
"testing"
@@ -23,16 +24,13 @@
func TestNonRepertoire(t *testing.T) {
// Pick n to cause the destination buffer in transform.String to overflow.
- const n = 10000
+ const n = 100
+ long := strings.Repeat(".", n)
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$B\x7e\x7e", "\ufffd"},
- {dec, ShiftJIS, "\xef\xfc", "\ufffd"},
-
{enc, EUCJP, "갂", ""},
{enc, EUCJP, "a갂", "a"},
{enc, EUCJP, "丌갂", "\x8f\xb0\xa4"},
@@ -51,12 +49,13 @@
{dec, EUCJP, "\x8e\xff", "\ufffd\ufffd"},
{dec, EUCJP, "\x8ea", "\ufffda"},
{dec, EUCJP, "\x8f\xa0", "\ufffd\ufffd"},
- {dec, EUCJP, "\x8f\xa1a", "\ufffda"},
- {dec, EUCJP, "\x8f\xa1a", "\ufffda"},
{dec, EUCJP, "\x8f\xa1\xa0", "\ufffd\ufffd"},
{dec, EUCJP, "\x8f\xa1a", "\ufffda"},
+ {dec, EUCJP, "\x8f\xa1a", "\ufffda"},
+ {dec, EUCJP, "\x8f\xa1a", "\ufffda"},
{dec, EUCJP, "\x8f\xa2\xa2", "\ufffd"},
{dec, EUCJP, "\xfe", "\ufffd"},
+ {dec, EUCJP, "\xfe\xfc", "\ufffd"},
{dec, EUCJP, "\xfe\xff", "\ufffd\ufffd"},
// Correct handling of end of source
{dec, EUCJP, strings.Repeat("\x8e", n), strings.Repeat("\ufffd", n)},
@@ -68,11 +67,12 @@
// Continue correctly after errors
{dec, ShiftJIS, "\x80", "\u0080"}, // It's what the spec says.
{dec, ShiftJIS, "\x81", "\ufffd"},
+ {dec, ShiftJIS, "\x81\x7f", "\ufffd\u007f"},
{dec, ShiftJIS, "\xe0", "\ufffd"},
{dec, ShiftJIS, "\xe0\x39", "\ufffd\u0039"},
- {dec, ShiftJIS, "\x81\x7f", "\ufffd\u007f"},
- {dec, ShiftJIS, "\xe0\xfd", "\ufffd"},
{dec, ShiftJIS, "\xe0\x9f", "燹"},
+ {dec, ShiftJIS, "\xe0\xfd", "\ufffd"},
+ {dec, ShiftJIS, "\xef\xfc", "\ufffd"},
{dec, ShiftJIS, "\xfc\xfc", "\ufffd"},
{dec, ShiftJIS, "\xfc\xfd", "\ufffd"},
{dec, ShiftJIS, "\xfdaa", "\ufffdaa"},
@@ -80,17 +80,70 @@
{dec, ShiftJIS, strings.Repeat("\x81\x81", n), strings.Repeat("=", n)},
{dec, ShiftJIS, strings.Repeat("\xe0\xfd", n), strings.Repeat("\ufffd", n)},
{dec, ShiftJIS, "a" + strings.Repeat("\xe0\xfd", n), "a" + strings.Repeat("\ufffd", n)},
+
+ {dec, ISO2022JP, "\x1b$", "\ufffd$"},
+ {dec, ISO2022JP, "\x1b(", "\ufffd("},
+ {dec, ISO2022JP, "\x1b@", "\ufffd@"},
+ {dec, ISO2022JP, "\x1bZ", "\ufffdZ"},
+ // incomplete escapes
+ {dec, ISO2022JP, "\x1b$", "\ufffd$"},
+ {dec, ISO2022JP, "\x1b$J.", "\ufffd$J."}, // illegal
+ {dec, ISO2022JP, "\x1b$B.", "\ufffd"}, // JIS208
+ {dec, ISO2022JP, "\x1b$(", "\ufffd$("}, // JIS212
+ {dec, ISO2022JP, "\x1b$(..", "\ufffd$(.."}, // JIS212
+ {dec, ISO2022JP, "\x1b$(" + long, "\ufffd$(" + long}, // JIS212
+ {dec, ISO2022JP, "\x1b$(D.", "\ufffd"}, // JIS212
+ {dec, ISO2022JP, "\x1b$(D..", "\ufffd"}, // JIS212
+ {dec, ISO2022JP, "\x1b$(D...", "\ufffd\ufffd"}, // JIS212
+ {dec, ISO2022JP, "\x1b(B.", "."}, // ascii
+ {dec, ISO2022JP, "\x1b(B..", ".."}, // ascii
+ {dec, ISO2022JP, "\x1b(J.", "."}, // roman
+ {dec, ISO2022JP, "\x1b(J..", ".."}, // roman
+ {dec, ISO2022JP, "\x1b(I\x20", "\ufffd"}, // katakana
+ {dec, ISO2022JP, "\x1b(I\x20\x20", "\ufffd\ufffd"}, // katakana
+ // recover to same state
+ {dec, ISO2022JP, "\x1b(B\x1b.", "\ufffd."},
+ {dec, ISO2022JP, "\x1b(I\x1b.", "\ufffdョ"},
+ {dec, ISO2022JP, "\x1b(I\x1b$.", "\ufffd、ョ"},
+ {dec, ISO2022JP, "\x1b(I\x1b(.", "\ufffdィョ"},
+ {dec, ISO2022JP, "\x1b$B\x7e\x7e", "\ufffd"},
+ {dec, ISO2022JP, "\x1b$@\x0a.", "\x0a."},
+ {dec, ISO2022JP, "\x1b$B\x0a.", "\x0a."},
+ {dec, ISO2022JP, "\x1b$(D\x0a.", "\x0a."},
+ {dec, ISO2022JP, "\x1b$(D\x7e\x7e", "\ufffd"},
+ {dec, ISO2022JP, "\x80", "\ufffd"},
+
+ // TODO: according to https://encoding.spec.whatwg.org/#iso-2022-jp,
+ // these should all be correct.
+ // {dec, ISO2022JP, "\x1b(B\x0E", "\ufffd"},
+ // {dec, ISO2022JP, "\x1b(B\x0F", "\ufffd"},
+ {dec, ISO2022JP, "\x1b(B\x5C", "\u005C"},
+ {dec, ISO2022JP, "\x1b(B\x7E", "\u007E"},
+ // {dec, ISO2022JP, "\x1b(J\x0E", "\ufffd"},
+ // {dec, ISO2022JP, "\x1b(J\x0F", "\ufffd"},
+ // {dec, ISO2022JP, "\x1b(J\x5C", "\u00A5"},
+ // {dec, ISO2022JP, "\x1b(J\x7E", "\u203E"},
}
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)
- }
+ t.Run(fmt.Sprintf("%s/%v/%q", dir, tc.e, tc.src), func(t *testing.T) {
+ dst := make([]byte, 100000)
+ src := []byte(tc.src)
+ for i := 0; i <= len(tc.src); i++ {
+ nDst, nSrc, err := tr.Transform(dst, src[:i], false)
+ if err != nil && err != transform.ErrShortSrc && err != wantErr {
+ t.Fatalf("error on first call to Transform: %v", err)
+ }
+ n, _, err := tr.Transform(dst[nDst:], src[nSrc:], true)
+ nDst += n
+ if err != wantErr {
+ t.Fatalf("(%q|%q): got %v; want %v", tc.src[:i], tc.src[i:], err, wantErr)
+ }
+ if got := string(dst[:nDst]); got != tc.want {
+ t.Errorf("(%q|%q):\ngot %q\nwant %q", tc.src[:i], tc.src[i:], got, tc.want)
+ }
+ }
+ })
}
}
diff --git a/encoding/japanese/iso2022jp.go b/encoding/japanese/iso2022jp.go
index b63e7d5..613226d 100644
--- a/encoding/japanese/iso2022jp.go
+++ b/encoding/japanese/iso2022jp.go
@@ -5,7 +5,6 @@
package japanese
import (
- "errors"
"unicode/utf8"
"golang.org/x/text/encoding"
@@ -31,8 +30,6 @@
return new(iso2022JPEncoder)
}
-var errInvalidISO2022JP = errors.New("japanese: invalid ISO-2022-JP encoding")
-
const (
asciiState = iota
katakanaState
@@ -50,45 +47,51 @@
func (d *iso2022JPDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
r, size := rune(0), 0
-loop:
for ; nSrc < len(src); nSrc += size {
c0 := src[nSrc]
if c0 >= utf8.RuneSelf {
- err = errInvalidISO2022JP
- break loop
+ r, size = '\ufffd', 1
+ goto write
}
if c0 == asciiEsc {
if nSrc+2 >= len(src) {
- err = transform.ErrShortSrc
- break loop
+ if !atEOF {
+ return nDst, nSrc, transform.ErrShortSrc
+ }
+ // TODO: is it correct to only skip 1??
+ r, size = '\ufffd', 1
+ goto write
}
size = 3
c1 := src[nSrc+1]
c2 := src[nSrc+2]
switch {
- case c1 == '$' && (c2 == '@' || c2 == 'B'):
+ case c1 == '$' && (c2 == '@' || c2 == 'B'): // 0x24 {0x40, 0x42}
*d = jis0208State
continue
- case c1 == '$' && c2 == '(':
+ case c1 == '$' && c2 == '(': // 0x24 0x28
if nSrc+3 >= len(src) {
- err = transform.ErrShortSrc
- break loop
+ if !atEOF {
+ return nDst, nSrc, transform.ErrShortSrc
+ }
+ r, size = '\ufffd', 1
+ goto write
}
size = 4
- if src[nSrc]+3 == 'D' {
+ if src[nSrc+3] == 'D' {
*d = jis0212State
continue
}
- case c1 == '(' && (c2 == 'B' || c2 == 'J'):
+ case c1 == '(' && (c2 == 'B' || c2 == 'J'): // 0x28 {0x42, 0x4A}
*d = asciiState
continue
- case c1 == '(' && c2 == 'I':
+ case c1 == '(' && c2 == 'I': // 0x28 0x49
*d = katakanaState
continue
}
- err = errInvalidISO2022JP
- break loop
+ r, size = '\ufffd', 1
+ goto write
}
switch *d {
@@ -97,8 +100,8 @@
case katakanaState:
if c0 < 0x21 || 0x60 <= c0 {
- err = errInvalidISO2022JP
- break loop
+ r, size = '\ufffd', 1
+ goto write
}
r, size = rune(c0)+(0xff61-0x21), 1
@@ -106,11 +109,14 @@
if c0 == 0x0a {
*d = asciiState
r, size = rune(c0), 1
- break
+ goto write
}
if nSrc+1 >= len(src) {
- err = transform.ErrShortSrc
- break loop
+ if !atEOF {
+ return nDst, nSrc, transform.ErrShortSrc
+ }
+ r, size = '\ufffd', 1
+ goto write
}
size = 2
c1 := src[nSrc+1]
@@ -121,22 +127,19 @@
r = rune(jis0212Decode[i])
} else {
r = '\ufffd'
- break
+ goto write
}
if r == 0 {
r = '\ufffd'
}
}
+ write:
if nDst+utf8.RuneLen(r) > len(dst) {
- err = transform.ErrShortDst
- break loop
+ return nDst, nSrc, transform.ErrShortDst
}
nDst += utf8.EncodeRune(dst[nDst:], r)
}
- if atEOF && err == transform.ErrShortSrc {
- err = errInvalidISO2022JP
- }
return nDst, nSrc, err
}
diff --git a/encoding/japanese/shiftjis.go b/encoding/japanese/shiftjis.go
index 9667b1f..16fd8a6 100644
--- a/encoding/japanese/shiftjis.go
+++ b/encoding/japanese/shiftjis.go
@@ -45,8 +45,8 @@
c0 = 2*c0 - 0x21
if nSrc+1 >= len(src) {
- err = transform.ErrShortSrc
if !atEOF {
+ err = transform.ErrShortSrc
break loop
}
r, size = '\ufffd', 1