summaryrefslogtreecommitdiff
path: root/libgo/go/utf16
diff options
context:
space:
mode:
Diffstat (limited to 'libgo/go/utf16')
-rw-r--r--libgo/go/utf16/utf16.go101
-rw-r--r--libgo/go/utf16/utf16_test.go118
2 files changed, 219 insertions, 0 deletions
diff --git a/libgo/go/utf16/utf16.go b/libgo/go/utf16/utf16.go
new file mode 100644
index 000000000..372e38a71
--- /dev/null
+++ b/libgo/go/utf16/utf16.go
@@ -0,0 +1,101 @@
+// 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
+
+import "unicode"
+
+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 returns true if the specified Unicode code point
+// can appear in a surrogate pair.
+func IsSurrogate(rune int) bool {
+ return surr1 <= rune && rune < 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 int) int {
+ if surr1 <= r1 && r1 < surr2 && surr2 <= r2 && r2 < surr3 {
+ return (int(r1)-surr1)<<10 | (int(r2) - surr2) + 0x10000
+ }
+ return unicode.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(rune int) (r1, r2 int) {
+ if rune < surrSelf || rune > unicode.MaxRune || IsSurrogate(rune) {
+ return unicode.ReplacementChar, unicode.ReplacementChar
+ }
+ rune -= surrSelf
+ return surr1 + (rune>>10)&0x3ff, surr2 + rune&0x3ff
+}
+
+// Encode returns the UTF-16 encoding of the Unicode code point sequence s.
+func Encode(s []int) []uint16 {
+ n := len(s)
+ for _, v := range s {
+ if v >= surrSelf {
+ n++
+ }
+ }
+
+ a := make([]uint16, n)
+ n = 0
+ for _, v := range s {
+ switch {
+ case v < 0, surr1 <= v && v < surr3, v > unicode.MaxRune:
+ v = unicode.ReplacementChar
+ fallthrough
+ case v < surrSelf:
+ a[n] = uint16(v)
+ n++
+ default:
+ r1, r2 := EncodeRune(v)
+ a[n] = uint16(r1)
+ a[n+1] = uint16(r2)
+ n += 2
+ }
+ }
+ return a[0:n]
+}
+
+// Decode returns the Unicode code point sequence represented
+// by the UTF-16 encoding s.
+func Decode(s []uint16) []int {
+ a := make([]int, len(s))
+ n := 0
+ for i := 0; i < len(s); i++ {
+ switch r := s[i]; {
+ case surr1 <= r && r < surr2 && i+1 < len(s) &&
+ surr2 <= s[i+1] && s[i+1] < surr3:
+ // valid surrogate sequence
+ a[n] = DecodeRune(int(r), int(s[i+1]))
+ i++
+ n++
+ case surr1 <= r && r < surr3:
+ // invalid surrogate sequence
+ a[n] = unicode.ReplacementChar
+ n++
+ default:
+ // normal rune
+ a[n] = int(r)
+ n++
+ }
+ }
+ return a[0:n]
+}
diff --git a/libgo/go/utf16/utf16_test.go b/libgo/go/utf16/utf16_test.go
new file mode 100644
index 000000000..2b9fb3d87
--- /dev/null
+++ b/libgo/go/utf16/utf16_test.go
@@ -0,0 +1,118 @@
+// 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_test
+
+import (
+ "fmt"
+ "reflect"
+ "testing"
+ "unicode"
+ . "utf16"
+)
+
+type encodeTest struct {
+ in []int
+ out []uint16
+}
+
+var encodeTests = []encodeTest{
+ {[]int{1, 2, 3, 4}, []uint16{1, 2, 3, 4}},
+ {[]int{0xffff, 0x10000, 0x10001, 0x12345, 0x10ffff},
+ []uint16{0xffff, 0xd800, 0xdc00, 0xd800, 0xdc01, 0xd808, 0xdf45, 0xdbff, 0xdfff}},
+ {[]int{'a', 'b', 0xd7ff, 0xd800, 0xdfff, 0xe000, 0x110000, -1},
+ []uint16{'a', 'b', 0xd7ff, 0xfffd, 0xfffd, 0xe000, 0xfffd, 0xfffd}},
+}
+
+func TestEncode(t *testing.T) {
+ for _, tt := range encodeTests {
+ out := Encode(tt.in)
+ if !reflect.DeepEqual(out, tt.out) {
+ t.Errorf("Encode(%v) = %v; want %v", hex(tt.in), hex16(out), hex16(tt.out))
+ }
+ }
+}
+
+func TestEncodeRune(t *testing.T) {
+ for i, tt := range encodeTests {
+ j := 0
+ for _, r := range tt.in {
+ r1, r2 := EncodeRune(r)
+ if r < 0x10000 || r > unicode.MaxRune {
+ if j >= len(tt.out) {
+ t.Errorf("#%d: ran out of tt.out", i)
+ break
+ }
+ if r1 != unicode.ReplacementChar || r2 != unicode.ReplacementChar {
+ t.Errorf("EncodeRune(%#x) = %#x, %#x; want 0xfffd, 0xfffd", r, r1, r2)
+ }
+ j++
+ } else {
+ if j+1 >= len(tt.out) {
+ t.Errorf("#%d: ran out of tt.out", i)
+ break
+ }
+ if r1 != int(tt.out[j]) || r2 != int(tt.out[j+1]) {
+ t.Errorf("EncodeRune(%#x) = %#x, %#x; want %#x, %#x", r, r1, r2, tt.out[j], tt.out[j+1])
+ }
+ j += 2
+ dec := DecodeRune(r1, r2)
+ if dec != r {
+ t.Errorf("DecodeRune(%#x, %#x) = %#x; want %#x", r1, r2, dec, r)
+ }
+ }
+ }
+ if j != len(tt.out) {
+ t.Errorf("#%d: EncodeRune didn't generate enough output", i)
+ }
+ }
+}
+
+type decodeTest struct {
+ in []uint16
+ out []int
+}
+
+var decodeTests = []decodeTest{
+ {[]uint16{1, 2, 3, 4}, []int{1, 2, 3, 4}},
+ {[]uint16{0xffff, 0xd800, 0xdc00, 0xd800, 0xdc01, 0xd808, 0xdf45, 0xdbff, 0xdfff},
+ []int{0xffff, 0x10000, 0x10001, 0x12345, 0x10ffff}},
+ {[]uint16{0xd800, 'a'}, []int{0xfffd, 'a'}},
+ {[]uint16{0xdfff}, []int{0xfffd}},
+}
+
+func TestDecode(t *testing.T) {
+ for _, tt := range decodeTests {
+ out := Decode(tt.in)
+ if !reflect.DeepEqual(out, tt.out) {
+ t.Errorf("Decode(%v) = %v; want %v", hex16(tt.in), hex(out), hex(tt.out))
+ }
+ }
+}
+
+type hex []int
+
+func (h hex) Format(f fmt.State, c int) {
+ fmt.Fprint(f, "[")
+ for i, v := range h {
+ if i > 0 {
+ fmt.Fprint(f, " ")
+ }
+ fmt.Fprintf(f, "%x", v)
+ }
+ fmt.Fprint(f, "]")
+}
+
+type hex16 []uint16
+
+func (h hex16) Format(f fmt.State, c int) {
+ fmt.Fprint(f, "[")
+ for i, v := range h {
+ if i > 0 {
+ fmt.Fprint(f, " ")
+ }
+ fmt.Fprintf(f, "%x", v)
+ }
+ fmt.Fprint(f, "]")
+}