Source File
utf16.go
Belonging Package
unicode/utf16
// 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 charactermaxRune = '\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 = 0xd800surr2 = 0xdc00surr3 = 0xe000surrSelf = 0x10000)// IsSurrogate reports whether the specified Unicode code point// can appear in a surrogate pair.func ( rune) bool {return surr1 <= && < 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 (, rune) rune {if surr1 <= && < surr2 && surr2 <= && < surr3 {return (-surr1)<<10 | ( - 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 ( rune) (, rune) {if < surrSelf || > maxRune {return replacementChar, replacementChar}-= surrSelfreturn surr1 + (>>10)&0x3ff, surr2 + &0x3ff}// Encode returns the UTF-16 encoding of the Unicode code point sequence s.func ( []rune) []uint16 {:= len()for , := range {if >= surrSelf {++}}:= make([]uint16, )= 0for , := range {switch {case 0 <= && < surr1, surr3 <= && < surrSelf:// normal rune[] = uint16()++case surrSelf <= && <= maxRune:// needs surrogate sequence, := EncodeRune()[] = uint16()[+1] = uint16()+= 2default:[] = uint16(replacementChar)++}}return [:]}// Decode returns the Unicode code point sequence represented// by the UTF-16 encoding s.func ( []uint16) []rune {:= make([]rune, len()):= 0for := 0; < len(); ++ {switch := []; {case < surr1, surr3 <= :// normal rune[] = rune()case surr1 <= && < surr2 && +1 < len() &&surr2 <= [+1] && [+1] < surr3:// valid surrogate sequence[] = DecodeRune(rune(), rune([+1]))++default:// invalid surrogate sequence[] = replacementChar}++}return [:]}
The pages are generated with Golds v0.2.8-preview. (GOOS=darwin GOARCH=arm64)