From: Joe Tsai <joetsai@digital-static.net>
Date: Thu, 16 Jun 2022 00:29:25 +0000 (-0700)
Subject: fmt: rely on utf8.AppendRune
X-Git-Tag: go1.20rc1~971
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=9c916c79011f3af98b5670eb2ba55349ba904522;p=gostls13.git

fmt: rely on utf8.AppendRune

This is both simpler and more performant.
The need for fmt.fmtC to manually check for utf8.MaxRune
is subtle to avoid overflow when converting uint64 to rune,
so a test case was added to exercise this edge case.

Change-Id: I0f2e6cce91dcd4cc6b88190c29807ca1c58e999d
Reviewed-on: https://go-review.googlesource.com/c/go/+/412335
Auto-Submit: Joseph Tsai <joetsai@digital-static.net>
Auto-Submit: Robert Griesemer <gri@google.com>
Run-TryBot: Joseph Tsai <joetsai@digital-static.net>
Reviewed-by: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Robert Griesemer <gri@google.com>
Run-TryBot: Robert Griesemer <gri@google.com>
---

diff --git a/src/fmt/fmt_test.go b/src/fmt/fmt_test.go
index d2fa81a7b3..37d82acbf4 100644
--- a/src/fmt/fmt_test.go
+++ b/src/fmt/fmt_test.go
@@ -249,6 +249,7 @@ var fmtTests = []struct {
 	{"%.0c", '⌘', "⌘"}, // Specifying precision should have no effect.
 	{"%3c", '⌘', "  ⌘"},
 	{"%-3c", '⌘', "⌘  "},
+	{"%c", uint64(0x100000000), "\ufffd"},
 	// Runes that are not printable.
 	{"%c", '\U00000e00', "\u0e00"},
 	{"%c", '\U0010ffff', "\U0010ffff"},
diff --git a/src/fmt/format.go b/src/fmt/format.go
index bd00e5a5e0..617f78f15e 100644
--- a/src/fmt/format.go
+++ b/src/fmt/format.go
@@ -461,13 +461,14 @@ func (f *fmt) fmtQ(s string) {
 // fmtC formats an integer as a Unicode character.
 // If the character is not valid Unicode, it will print '\ufffd'.
 func (f *fmt) fmtC(c uint64) {
+	// Explicitly check whether c exceeds utf8.MaxRune since the conversion
+	// of a uint64 to a rune may lose precision that indicates an overflow.
 	r := rune(c)
 	if c > utf8.MaxRune {
 		r = utf8.RuneError
 	}
 	buf := f.intbuf[:0]
-	w := utf8.EncodeRune(buf[:utf8.UTFMax], r)
-	f.pad(buf[:w])
+	f.pad(utf8.AppendRune(buf, r))
 }
 
 // fmtQc formats an integer as a single-quoted, escaped Go character constant.
diff --git a/src/fmt/print.go b/src/fmt/print.go
index 8082d13874..4eabda1ce8 100644
--- a/src/fmt/print.go
+++ b/src/fmt/print.go
@@ -113,18 +113,7 @@ func (b *buffer) writeByte(c byte) {
 }
 
 func (bp *buffer) writeRune(r rune) {
-	if r < utf8.RuneSelf {
-		*bp = append(*bp, byte(r))
-		return
-	}
-
-	b := *bp
-	n := len(b)
-	for n+utf8.UTFMax > cap(b) {
-		b = append(b, 0)
-	}
-	w := utf8.EncodeRune(b[n:n+utf8.UTFMax], r)
-	*bp = b[:n+w]
+	*bp = utf8.AppendRune(*bp, r)
 }
 
 // pp is used to store a printer's state and is reused with sync.Pool to avoid allocations.