From a3868028ac8470d1ab7782614707bb90925e7fe3 Mon Sep 17 00:00:00 2001 From: Ainar Garipov Date: Fri, 18 Sep 2020 21:01:34 +0300 Subject: [PATCH] unicode/utf8: document the handling of runes out of range in EncodeRune Document the way EncodeRune currently handles runes which are out of range. Also add an example showing that behaviour. Change-Id: I0f8e7645ae053474ec319085a2bb6d7f73bc137c Reviewed-on: https://go-review.googlesource.com/c/go/+/255998 Reviewed-by: Rob Pike Reviewed-by: Giovanni Bajo Trust: Giovanni Bajo Run-TryBot: Giovanni Bajo TryBot-Result: Go Bot --- src/unicode/utf8/example_test.go | 20 ++++++++++++++++++++ src/unicode/utf8/utf8.go | 1 + 2 files changed, 21 insertions(+) diff --git a/src/unicode/utf8/example_test.go b/src/unicode/utf8/example_test.go index 7b3e7ac7425..5cd931d2427 100644 --- a/src/unicode/utf8/example_test.go +++ b/src/unicode/utf8/example_test.go @@ -107,6 +107,26 @@ func ExampleEncodeRune() { // 3 } +func ExampleEncodeRune_outOfRange() { + runes := []rune{ + // Less than 0, out of range. + -1, + // Greater than 0x10FFFF, out of range. + 0x110000, + // The Unicode replacement character. + utf8.RuneError, + } + for i, c := range runes { + buf := make([]byte, 3) + size := utf8.EncodeRune(buf, c) + fmt.Printf("%d: %d %[2]s %d\n", i, buf, size) + } + // Output: + // 0: [239 191 189] � 3 + // 1: [239 191 189] � 3 + // 2: [239 191 189] � 3 +} + func ExampleFullRune() { buf := []byte{228, 184, 150} // 世 fmt.Println(utf8.FullRune(buf)) diff --git a/src/unicode/utf8/utf8.go b/src/unicode/utf8/utf8.go index ef0d7409602..557e8a7770c 100644 --- a/src/unicode/utf8/utf8.go +++ b/src/unicode/utf8/utf8.go @@ -337,6 +337,7 @@ func RuneLen(r rune) int { } // EncodeRune writes into p (which must be large enough) the UTF-8 encoding of the rune. +// If the rune is out of range, it writes the encoding of RuneError. // It returns the number of bytes written. func EncodeRune(p []byte, r rune) int { // Negative values are erroneous. Making it unsigned addresses the problem.