diff options
author | Tianon Gravi <admwiggin@gmail.com> | 2015-01-15 11:54:00 -0700 |
---|---|---|
committer | Tianon Gravi <admwiggin@gmail.com> | 2015-01-15 11:54:00 -0700 |
commit | f154da9e12608589e8d5f0508f908a0c3e88a1bb (patch) | |
tree | f8255d51e10c6f1e0ed69702200b966c9556a431 /src/unicode/utf16/utf16.go | |
parent | 8d8329ed5dfb9622c82a9fbec6fd99a580f9c9f6 (diff) | |
download | golang-upstream/1.4.tar.gz |
Imported Upstream version 1.4upstream/1.4
Diffstat (limited to 'src/unicode/utf16/utf16.go')
-rw-r--r-- | src/unicode/utf16/utf16.go | 108 |
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 000000000..c0e47c535 --- /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 returns true if 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) + 0x10000 + } + 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 || IsSurrogate(r) { + 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 v < 0, surr1 <= v && v < surr3, v > maxRune: + v = 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) []rune { + a := make([]rune, 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(rune(r), rune(s[i+1])) + i++ + n++ + case surr1 <= r && r < surr3: + // invalid surrogate sequence + a[n] = replacementChar + n++ + default: + // normal rune + a[n] = rune(r) + n++ + } + } + return a[0:n] +} |