diff options
author | Joe Tsai <joetsai@digital-static.net> | 2022-06-22 20:57:50 -0700 |
---|---|---|
committer | Joseph Tsai <joetsai@digital-static.net> | 2022-08-08 20:44:51 +0000 |
commit | 9a4685f22036b4e2577bb79dbfabd7c4e48146e3 (patch) | |
tree | 835c8522189cbf231780f450fb7b9dbb7e3431dd /src/strings | |
parent | ced4d6fd2d415d43c0f26e01fe332e4afa80114a (diff) | |
download | go-9a4685f22036b4e2577bb79dbfabd7c4e48146e3.tar.gz go-9a4685f22036b4e2577bb79dbfabd7c4e48146e3.zip |
strings: avoid utf8.RuneError mangling in Split
Split should only split strings and not perform mangling
of invalid UTF-8 into ut8.RuneError.
The prior behavior is clearly a bug since mangling is not
performed in all other situations (e.g., separator is non-empty).
Fixes #53511
Change-Id: I112a2ef15ee46ddecda015ee14bca04cd76adfbf
Reviewed-on: https://go-review.googlesource.com/c/go/+/413715
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: Ian Lance Taylor <iant@google.com>
Run-TryBot: Ian Lance Taylor <iant@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Diffstat (limited to 'src/strings')
-rw-r--r-- | src/strings/strings.go | 7 | ||||
-rw-r--r-- | src/strings/strings_test.go | 2 |
2 files changed, 4 insertions, 5 deletions
diff --git a/src/strings/strings.go b/src/strings/strings.go index 1dc4238522..013d718426 100644 --- a/src/strings/strings.go +++ b/src/strings/strings.go @@ -15,7 +15,7 @@ import ( // explode splits s into a slice of UTF-8 strings, // one string per Unicode character up to a maximum of n (n < 0 means no limit). -// Invalid UTF-8 sequences become correct encodings of U+FFFD. +// Invalid UTF-8 bytes are sliced individually. func explode(s string, n int) []string { l := utf8.RuneCountInString(s) if n < 0 || n > l { @@ -23,12 +23,9 @@ func explode(s string, n int) []string { } a := make([]string, n) for i := 0; i < n-1; i++ { - ch, size := utf8.DecodeRuneInString(s) + _, size := utf8.DecodeRuneInString(s) a[i] = s[:size] s = s[size:] - if ch == utf8.RuneError { - a[i] = string(utf8.RuneError) - } } if n > 0 { a[n-1] = s diff --git a/src/strings/strings_test.go b/src/strings/strings_test.go index 9e7fb85ddf..a1604c2c47 100644 --- a/src/strings/strings_test.go +++ b/src/strings/strings_test.go @@ -406,6 +406,8 @@ var splittests = []SplitTest{ {"1 2 3 4", " ", 3, []string{"1", "2", "3 4"}}, {"1 2", " ", 3, []string{"1", "2"}}, {"", "T", math.MaxInt / 4, []string{""}}, + {"\xff-\xff", "", -1, []string{"\xff", "-", "\xff"}}, + {"\xff-\xff", "-", -1, []string{"\xff", "\xff"}}, } func TestSplit(t *testing.T) { |