summaryrefslogtreecommitdiffstats
path: root/src/unicode/utf16/utf16.go
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-28 13:15:26 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-28 13:15:26 +0000
commit82539ad8d59729fb45b0bb0edda8f2bddb719eb1 (patch)
tree58f0b58e6f44f0e04d4a6373132cf426fa835fa7 /src/unicode/utf16/utf16.go
parentInitial commit. (diff)
downloadgolang-1.17-upstream.tar.xz
golang-1.17-upstream.zip
Adding upstream version 1.17.13.upstream/1.17.13upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/unicode/utf16/utf16.go')
-rw-r--r--src/unicode/utf16/utf16.go108
1 files changed, 108 insertions, 0 deletions
diff --git a/src/unicode/utf16/utf16.go b/src/unicode/utf16/utf16.go
new file mode 100644
index 0000000..1a881aa
--- /dev/null
+++ b/src/unicode/utf16/utf16.go
@@ -0,0 +1,108 @@
+// Copyright 2010 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// Package utf16 implements encoding and decoding of UTF-16 sequences.
+package utf16
+
+// The conditions replacementChar==unicode.ReplacementChar and
+// maxRune==unicode.MaxRune are verified in the tests.
+// Defining them locally avoids this package depending on package unicode.
+
+const (
+ replacementChar = '\uFFFD' // Unicode replacement character
+ maxRune = '\U0010FFFF' // Maximum valid Unicode code point.
+)
+
+const (
+ // 0xd800-0xdc00 encodes the high 10 bits of a pair.
+ // 0xdc00-0xe000 encodes the low 10 bits of a pair.
+ // the value is those 20 bits plus 0x10000.
+ surr1 = 0xd800
+ surr2 = 0xdc00
+ surr3 = 0xe000
+
+ surrSelf = 0x10000
+)
+
+// IsSurrogate reports whether the specified Unicode code point
+// can appear in a surrogate pair.
+func IsSurrogate(r rune) bool {
+ return surr1 <= r && r < surr3
+}
+
+// DecodeRune returns the UTF-16 decoding of a surrogate pair.
+// If the pair is not a valid UTF-16 surrogate pair, DecodeRune returns
+// the Unicode replacement code point U+FFFD.
+func DecodeRune(r1, r2 rune) rune {
+ if surr1 <= r1 && r1 < surr2 && surr2 <= r2 && r2 < surr3 {
+ return (r1-surr1)<<10 | (r2 - surr2) + surrSelf
+ }
+ return replacementChar
+}
+
+// EncodeRune returns the UTF-16 surrogate pair r1, r2 for the given rune.
+// If the rune is not a valid Unicode code point or does not need encoding,
+// EncodeRune returns U+FFFD, U+FFFD.
+func EncodeRune(r rune) (r1, r2 rune) {
+ if r < surrSelf || r > maxRune {
+ return replacementChar, replacementChar
+ }
+ r -= surrSelf
+ return surr1 + (r>>10)&0x3ff, surr2 + r&0x3ff
+}
+
+// Encode returns the UTF-16 encoding of the Unicode code point sequence s.
+func Encode(s []rune) []uint16 {
+ n := len(s)
+ for _, v := range s {
+ if v >= surrSelf {
+ n++
+ }
+ }
+
+ a := make([]uint16, n)
+ n = 0
+ for _, v := range s {
+ switch {
+ case 0 <= v && v < surr1, surr3 <= v && v < surrSelf:
+ // normal rune
+ a[n] = uint16(v)
+ n++
+ case surrSelf <= v && v <= maxRune:
+ // needs surrogate sequence
+ r1, r2 := EncodeRune(v)
+ a[n] = uint16(r1)
+ a[n+1] = uint16(r2)
+ n += 2
+ default:
+ a[n] = uint16(replacementChar)
+ n++
+ }
+ }
+ return a[:n]
+}
+
+// Decode returns the Unicode code point sequence represented
+// by the UTF-16 encoding s.
+func Decode(s []uint16) []rune {
+ a := make([]rune, len(s))
+ n := 0
+ for i := 0; i < len(s); i++ {
+ switch r := s[i]; {
+ case r < surr1, surr3 <= r:
+ // normal rune
+ a[n] = rune(r)
+ case surr1 <= r && r < surr2 && i+1 < len(s) &&
+ surr2 <= s[i+1] && s[i+1] < surr3:
+ // valid surrogate sequence
+ a[n] = DecodeRune(rune(r), rune(s[i+1]))
+ i++
+ default:
+ // invalid surrogate sequence
+ a[n] = replacementChar
+ }
+ n++
+ }
+ return a[:n]
+}