github/golang.go
2
0
Fork 0
mirror of https://github.com/golang/go.git synced 2026-04-01 17:07:17 +09:00
Code Issues Packages Projects Releases Wiki Activity

runtime: printquoted: preserve bytes of invalid UTF-8 encodings

Browse Source 
Previously, printquoted would render each byte of an invalid UTF-8
sequence as "\uFFFD", which was lossy.

This CL adjusts printquoted to distinguish valid encodings of U+FFFD
from invalid encodings; each byte of the latter is now printed
losslessly as "\xXX"

Updates #76349

Change-Id: If9a877f01b497763425d9d11a58eb2a6e2c816b2
Reviewed-on: https://go-review.googlesource.com/c/go/+/742305
Reviewed-by: Alan Donovan <adonovan@google.com>
Auto-Submit: Michael Pratt <mpratt@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
This commit is contained in:
David Finkel
2026-02-05 18:10:43 -05:00
committed by Gopher Robot
parent 215a070a04
commit cdf8951060
2 changed files with 15 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/runtime/print.go
View File

@@ -200,7 +200,7 @@ func printhex(v uint64) {
func printquoted(s string) {
printlock()
gwrite([]byte(`"`))
for _, r := range s {
for i, r := range s {
switch r {
case '\n':
gwrite([]byte(`\n`))
@@ -215,6 +215,14 @@ func printquoted(s string) {
case '\\', '"':
gwrite([]byte{byte('\\'), byte(r)})
continue
case runeError:
// Distinguish errors from a valid encoding of U+FFFD.
if _, j := decoderune(s, i); j == i+1 {
gwrite(bytes(`\x`))
printhexopts(false, 2, uint64(s[i]))
continue
}
// Fall through to quoting.
}
// For now, only allow basic printable ascii through unescaped
if r >= ' ' && r <= '~' {

6
src/runtime/print_quoted_test.go
View File

@@ -20,6 +20,12 @@ func TestPrintQuoted(t *testing.T) {
// make sure null and escape bytes are properly escaped
{in: "b\033it", expected: `"b\x1bit"`},
{in: "b\000ar", expected: `"b\x00ar"`},
// Make sure invalid UTF8 bytes make it through as expected
{in: "b\xfdar", expected: `"b\xfdar"`},
{in: "b\xfda", expected: `"b\xfda"`},
{in: "b\xfd\xffar", expected: `"b\xfd\xffar"`},
// make sure the unicode replacement character gets correctly escaped
{in: "\ufffd!!!!", expected: `"\ufffd!!!!"`},
// verify that simple 16-bit unicode runes are escaped with \u, including a greek upper-case sigma and an arbitrary unicode character.
{in: "\u1234Σ", expected: `"\u1234\u03a3"`},
// verify that 32-bit unicode runes are escaped with \U along with tabs