mirror/protobuf-go
1
0
Fork 0
mirror of https://github.com/protocolbuffers/protobuf-go.git synced 2025-03-25 16:43:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

internal/encoding/text: escape Unicode control characters in strings

Browse Source 
Escape not only ASCII control characters, but Unicode as well.

Change-Id: I5f5791ae51fc5624599f66ce012ecef364e7ea97
Reviewed-on: https://go-review.googlesource.com/c/protobuf/+/262682
Trust: Damien Neil <dneil@google.com>
Run-TryBot: Damien Neil <dneil@google.com>
Reviewed-by: Joe Tsai <thebrokentoaster@gmail.com>
Reviewed-by: Joe Tsai <joetsai@google.com>
This commit is contained in:
Damien Neil 2020-10-15 14:48:42 -07:00
parent b1cd8e38bc
commit 711224230b
2 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
internal/encoding/text/encode.go
View File

@ -141,7 +141,7 @@ func appendString(out []byte, in string, outputASCII bool) []byte {
out = strconv.AppendUint(out, uint64(r), 16) out = strconv.AppendUint(out, uint64(r), 16)
} }
in = in[n:] in = in[n:]
case outputASCII && r >= utf8.RuneSelf: case r >= utf8.RuneSelf && (outputASCII || r <= 0x009f):
out = append(out, '\\') out = append(out, '\\')
if r <= math.MaxUint16 { if r <= math.MaxUint16 {
out = append(out, 'u') out = append(out, 'u')

10
internal/encoding/text/encode_test.go
View File

@ -394,17 +394,19 @@ func TestEncodeStrings(t *testing.T) {
// String that has as few escaped characters as possible. // String that has as few escaped characters as possible.
in: func() string { in: func() string {
var b []byte var b []byte
for i := 0; i < utf8.RuneSelf; i++ { for i := rune(0); i <= 0x00a0; i++ {
switch i { switch i {
case 0, '\\', '\n', '\'': // these must be escaped, so ignore them case 0, '\\', '\n', '\'': // these must be escaped, so ignore them
default: default:
b = append(b, byte(i)) var r [utf8.UTFMax]byte
n := utf8.EncodeRune(r[:], i)
b = append(b, r[:n]...)
} }
} }
return string(b) return string(b)
}(), }(),
wantOut: `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\"", wantOut: `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`" + `abcdefghijklmnopqrstuvwxyz{|}~\x7f\u0080\u0081\u0082\u0083\u0084\u0085\u0086\u0087\u0088\u0089\u008a\u008b\u008c\u008d\u008e\u008f\u0090\u0091\u0092\u0093\u0094\u0095\u0096\u0097\u0098\u0099\u009a\u009b\u009c\u009d\u009e\u009f` + "\u00a0" + `"`,
wantOutASCII: `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\"", wantOutASCII: `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`" + `abcdefghijklmnopqrstuvwxyz{|}~\x7f\u0080\u0081\u0082\u0083\u0084\u0085\u0086\u0087\u0088\u0089\u008a\u008b\u008c\u008d\u008e\u008f\u0090\u0091\u0092\u0093\u0094\u0095\u0096\u0097\u0098\u0099\u009a\u009b\u009c\u009d\u009e\u009f\u00a0"`,
}, },
{ {
// Valid UTF-8 wire encoding of the RuneError rune. // Valid UTF-8 wire encoding of the RuneError rune.