URL https://opencores.org/ocsvn/openrisc/openrisc/trunk

Subversion Repositories openrisc

[/] [openrisc/] [trunk/] [gnu-dev/] [or1k-gcc/] [libgo/] [go/] [unicode/] [utf16/] [utf16.go] - Blame information for rev 761

Go to most recent revision | Details | Compare with Previous | View Log


// 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(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 (rune(r1)-surr1)<<10 | (rune(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(r rune) (r1, r2 rune) {
        if r < surrSelf || r > unicode.MaxRune || IsSurrogate(r) {
                return unicode.ReplacementChar, unicode.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 > 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) []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] = unicode.ReplacementChar
                        n++
                default:
                        // normal rune
                        a[n] = rune(r)
                        n++
                }
        }
        return a[0:n]
}

Line No.	Rev	Author	Line
1	747	jeremybenn	`// Copyright 2010 The Go Authors. All rights reserved.`
2			`// Use of this source code is governed by a BSD-style`
3			`// license that can be found in the LICENSE file.`
4
5			`// Package utf16 implements encoding and decoding of UTF-16 sequences.`
6			`package utf16`
7
8			`import "unicode"`
9
10			`const (`
11			`// 0xd800-0xdc00 encodes the high 10 bits of a pair.`
12			`// 0xdc00-0xe000 encodes the low 10 bits of a pair.`
13			`// the value is those 20 bits plus 0x10000.`
14			`surr1 = 0xd800`
15			`surr2 = 0xdc00`
16			`surr3 = 0xe000`
17
18			`surrSelf = 0x10000`
19			`)`
20
21			`// IsSurrogate returns true if the specified Unicode code point`
22			`// can appear in a surrogate pair.`
23			`func IsSurrogate(r rune) bool {`
24			`return surr1 <= r && r < surr3`
25			`}`
26
27			`// DecodeRune returns the UTF-16 decoding of a surrogate pair.`
28			`// If the pair is not a valid UTF-16 surrogate pair, DecodeRune returns`
29			`// the Unicode replacement code point U+FFFD.`
30			`func DecodeRune(r1, r2 rune) rune {`
31			`if surr1 <= r1 && r1 < surr2 && surr2 <= r2 && r2 < surr3 {`
32			`return (rune(r1)-surr1)<<10 \| (rune(r2) - surr2) + 0x10000`
33			`}`
34			`return unicode.ReplacementChar`
35			`}`
36
37			`// EncodeRune returns the UTF-16 surrogate pair r1, r2 for the given rune.`
38			`// If the rune is not a valid Unicode code point or does not need encoding,`
39			`// EncodeRune returns U+FFFD, U+FFFD.`
40			`func EncodeRune(r rune) (r1, r2 rune) {`
41			`if r < surrSelf \|\| r > unicode.MaxRune \|\| IsSurrogate(r) {`
42			`return unicode.ReplacementChar, unicode.ReplacementChar`
43			`}`
44			`r -= surrSelf`
45			`return surr1 + (r>>10)&0x3ff, surr2 + r&0x3ff`
46			`}`
47
48			`// Encode returns the UTF-16 encoding of the Unicode code point sequence s.`
49			`func Encode(s []rune) []uint16 {`
50			`n := len(s)`
51			`for _, v := range s {`
52			`if v >= surrSelf {`
53			`n++`
54			`}`
55			`}`
56
57			`a := make([]uint16, n)`
58			`n = 0`
59			`for _, v := range s {`
60			`switch {`
61			`case v < 0, surr1 <= v && v < surr3, v > unicode.MaxRune:`
62			`v = unicode.ReplacementChar`
63			`fallthrough`
64			`case v < surrSelf:`
65			`a[n] = uint16(v)`
66			`n++`
67			`default:`
68			`r1, r2 := EncodeRune(v)`
69			`a[n] = uint16(r1)`
70			`a[n+1] = uint16(r2)`
71			`n += 2`
72			`}`
73			`}`
74			`return a[0:n]`
75			`}`
76
77			`// Decode returns the Unicode code point sequence represented`
78			`// by the UTF-16 encoding s.`
79			`func Decode(s []uint16) []rune {`
80			`a := make([]rune, len(s))`
81			`n := 0`
82			`for i := 0; i < len(s); i++ {`
83			`switch r := s[i]; {`
84			`case surr1 <= r && r < surr2 && i+1 < len(s) &&`
85			`surr2 <= s[i+1] && s[i+1] < surr3:`
86			`// valid surrogate sequence`
87			`a[n] = DecodeRune(rune(r), rune(s[i+1]))`
88			`i++`
89			`n++`
90			`case surr1 <= r && r < surr3:`
91			`// invalid surrogate sequence`
92			`a[n] = unicode.ReplacementChar`
93			`n++`
94			`default:`
95			`// normal rune`
96			`a[n] = rune(r)`
97			`n++`
98			`}`
99			`}`
100			`return a[0:n]`
101			`}`

Browse

Tools

Subversion Repositories openrisc

[/] [openrisc/] [trunk/] [gnu-dev/] [or1k-gcc/] [libgo/] [go/] [unicode/] [utf16/] [utf16.go] - Blame information for rev 761