Package utf8 implements functions and constants to support text encoded in UTF-8. It includes functions to translate between runes and UTF-8 byte sequences. See https://en.wikipedia.org/wiki/UTF-8
Numbers fundamental to the encoding.
const (
RuneError = '\uFFFD' // the "error" Rune or "Unicode replacement character"
RuneSelf = 0x80 // characters below RuneSelf are represented as themselves in a single byte.
MaxRune = '\U0010FFFF' // Maximum valid Unicode code point.
UTFMax = 4 // maximum number of bytes of a UTF-8 encoded Unicode character.
) func DecodeLastRune(p []byte) (r rune, size int)
DecodeLastRune unpacks the last UTF-8 encoding in p and returns the rune and its width in bytes. If p is empty it returns (RuneError, 0). Otherwise, if the encoding is invalid, it returns (RuneError, 1). Both are impossible results for correct, non-empty UTF-8.
An encoding is invalid if it is incorrect UTF-8, encodes a rune that is out of range, or is not the shortest possible UTF-8 encoding for the value. No other validation is performed.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
b := []byte("Hello, 世界")
for len(b) > 0 {
r, size := utf8.DecodeLastRune(b)
fmt.Printf("%c %v\n", r, size)
b = b[:len(b)-size]
}
}
func DecodeLastRuneInString(s string) (r rune, size int)
DecodeLastRuneInString is like DecodeLastRune but its input is a string. If s is empty it returns (RuneError, 0). Otherwise, if the encoding is invalid, it returns (RuneError, 1). Both are impossible results for correct, non-empty UTF-8.
An encoding is invalid if it is incorrect UTF-8, encodes a rune that is out of range, or is not the shortest possible UTF-8 encoding for the value. No other validation is performed.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
str := "Hello, 世界"
for len(str) > 0 {
r, size := utf8.DecodeLastRuneInString(str)
fmt.Printf("%c %v\n", r, size)
str = str[:len(str)-size]
}
}
func DecodeRune(p []byte) (r rune, size int)
DecodeRune unpacks the first UTF-8 encoding in p and returns the rune and its width in bytes. If p is empty it returns (RuneError, 0). Otherwise, if the encoding is invalid, it returns (RuneError, 1). Both are impossible results for correct, non-empty UTF-8.
An encoding is invalid if it is incorrect UTF-8, encodes a rune that is out of range, or is not the shortest possible UTF-8 encoding for the value. No other validation is performed.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
b := []byte("Hello, 世界")
for len(b) > 0 {
r, size := utf8.DecodeRune(b)
fmt.Printf("%c %v\n", r, size)
b = b[size:]
}
}
func DecodeRuneInString(s string) (r rune, size int)
DecodeRuneInString is like DecodeRune but its input is a string. If s is empty it returns (RuneError, 0). Otherwise, if the encoding is invalid, it returns (RuneError, 1). Both are impossible results for correct, non-empty UTF-8.
An encoding is invalid if it is incorrect UTF-8, encodes a rune that is out of range, or is not the shortest possible UTF-8 encoding for the value. No other validation is performed.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
str := "Hello, 世界"
for len(str) > 0 {
r, size := utf8.DecodeRuneInString(str)
fmt.Printf("%c %v\n", r, size)
str = str[size:]
}
}
func EncodeRune(p []byte, r rune) int
EncodeRune writes into p (which must be large enough) the UTF-8 encoding of the rune. It returns the number of bytes written.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
r := '世'
buf := make([]byte, 3)
n := utf8.EncodeRune(buf, r)
fmt.Println(buf)
fmt.Println(n)
}
func FullRune(p []byte) bool
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.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
buf := []byte{228, 184, 150} // 世
fmt.Println(utf8.FullRune(buf))
fmt.Println(utf8.FullRune(buf[:2]))
}
func FullRuneInString(s string) bool
FullRuneInString is like FullRune but its input is a string.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
str := "世"
fmt.Println(utf8.FullRuneInString(str))
fmt.Println(utf8.FullRuneInString(str[:2]))
}
func RuneCount(p []byte) int
RuneCount returns the number of runes in p. Erroneous and short encodings are treated as single runes of width 1 byte.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
buf := []byte("Hello, 世界")
fmt.Println("bytes =", len(buf))
fmt.Println("runes =", utf8.RuneCount(buf))
}
func RuneCountInString(s string) (n int)
RuneCountInString is like RuneCount but its input is a string.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
str := "Hello, 世界"
fmt.Println("bytes =", len(str))
fmt.Println("runes =", utf8.RuneCountInString(str))
}
func RuneLen(r rune) int
RuneLen returns the number of bytes required to encode the rune. It returns -1 if the rune is not a valid value to encode in UTF-8.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
fmt.Println(utf8.RuneLen('a'))
fmt.Println(utf8.RuneLen('界'))
}
func RuneStart(b byte) bool
RuneStart reports whether the byte could be the first byte of an encoded, possibly invalid rune. Second and subsequent bytes always have the top two bits set to 10.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
buf := []byte("a界")
fmt.Println(utf8.RuneStart(buf[0]))
fmt.Println(utf8.RuneStart(buf[1]))
fmt.Println(utf8.RuneStart(buf[2]))
}
func Valid(p []byte) bool
Valid reports whether p consists entirely of valid UTF-8-encoded runes.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
valid := []byte("Hello, 世界")
invalid := []byte{0xff, 0xfe, 0xfd}
fmt.Println(utf8.Valid(valid))
fmt.Println(utf8.Valid(invalid))
}
func ValidRune(r rune) bool
ValidRune reports whether r can be legally encoded as UTF-8. Code points that are out of range or a surrogate half are illegal.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
valid := 'a'
invalid := rune(0xfffffff)
fmt.Println(utf8.ValidRune(valid))
fmt.Println(utf8.ValidRune(invalid))
}
func ValidString(s string) bool
ValidString reports whether s consists entirely of valid UTF-8-encoded runes.
package main
import (
"fmt"
"unicode/utf8"
)
func main() {
valid := "Hello, 世界"
invalid := string([]byte{0xff, 0xfe, 0xfd})
fmt.Println(utf8.ValidString(valid))
fmt.Println(utf8.ValidString(invalid))
}
© Google, Inc.
Licensed under the Creative Commons Attribution License 3.0.
https://golang.org/pkg/unicode/utf8/