qbit/go
1
0
Fork 0
mirror of https://github.com/golang/go synced 2024-11-26 14:36:52 -07:00
Code Releases Activity

document utf8

Browse Source 
R=rsc
DELTA=18  (12 added, 0 deleted, 6 changed)
OCL=25807
CL=25811
This commit is contained in:
Rob Pike 2009-03-05 19:15:13 -08:00
parent 42b49b1907
commit dfe0853255
1 changed files with 18 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/lib/utf8.go
View File

@ -2,15 +2,16 @@
// Use of this source code is governed by a BSD-style // Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file. // license that can be found in the LICENSE file.
// UTF-8 support. // Functions and constants to support text encoded in UTF-8.
// This package calls a Unicode character a rune for brevity.
package utf8 package utf8
// Numbers fundamental to the encoding.
const ( const (
RuneError = 0xFFFD; RuneError = 0xFFFD; // the "error" Rune or "replacement character".
RuneSelf = 0x80; RuneSelf = 0x80; // characters below Runeself are represented as themselves in a single byte.
RuneMax = 0x10FFFF; RuneMax = 0x10FFFF; // maximum Unicode code point.
UTFMax = 4; UTFMax = 4; // maximum number of bytes of a UTF-8 encoded Unicode character.
) )
const ( const (
@ -181,28 +182,34 @@ func decodeRuneInStringInternal(s string, i int, n int) (rune, size int, short b
return RuneError, 1, false return RuneError, 1, false
} }
// FullRune reports whether the bytes in p begin with a full UTF-8 encoding of a rune.
// An invalid encoding is considered a full Rune since it will convert as a width-1 error rune.
func FullRune(p []byte) bool { func FullRune(p []byte) bool {
rune, size, short := decodeRuneInternal(p); rune, size, short := decodeRuneInternal(p);
return !short return !short
} }
// FullRuneInString is like FullRune but its input is a string.
func FullRuneInString(s string, i int) bool { func FullRuneInString(s string, i int) bool {
rune, size, short := decodeRuneInStringInternal(s, i, len(s) - i); rune, size, short := decodeRuneInStringInternal(s, i, len(s) - i);
return !short return !short
} }
// DecodeRune unpacks the first UTF-8 encoding in p and returns the rune and its width in bytes.
func DecodeRune(p []byte) (rune, size int) { func DecodeRune(p []byte) (rune, size int) {
var short bool; var short bool;
rune, size, short = decodeRuneInternal(p); rune, size, short = decodeRuneInternal(p);
return; return;
} }
// DecodeRuneInString is like DecodeRune but its input is a string.
func DecodeRuneInString(s string, i int) (rune, size int) { func DecodeRuneInString(s string, i int) (rune, size int) {
var short bool; var short bool;
rune, size, short = decodeRuneInStringInternal(s, i, len(s) - i); rune, size, short = decodeRuneInStringInternal(s, i, len(s) - i);
return; return;
} }
// RuneLen returns the number of bytes required to encode the rune.
func RuneLen(rune int) int { func RuneLen(rune int) int {
switch { switch {
case rune <= _Rune1Max: case rune <= _Rune1Max:
@ -217,6 +224,8 @@ func RuneLen(rune int) int {
return -1; return -1;
} }
// EncodeRune writes into p (which must be large enough) the UTF-8 encoding of the rune.
// It returns the number of bytes written.
func EncodeRune(rune int, p []byte) int { func EncodeRune(rune int, p []byte) int {
if rune <= _Rune1Max { if rune <= _Rune1Max {
p[0] = byte(rune); p[0] = byte(rune);
@ -247,6 +256,8 @@ func EncodeRune(rune int, p []byte) int {
return 4; return 4;
} }
// RuneCount returns the number of runes in p. Erroneous and short
// encodings are treated as single runes of width 1 byte.
func RuneCount(p []byte) int { func RuneCount(p []byte) int {
i := 0; i := 0;
var n int; var n int;
@ -261,6 +272,7 @@ func RuneCount(p []byte) int {
return n; return n;
} }
// RuneCountInString is like RuneCount but its input is a string.
func RuneCountInString(s string, i int, l int) int { func RuneCountInString(s string, i int, l int) int {
ei := i + l; ei := i + l;
n := 0; n := 0;