Back to godoc.org
unicode / utf8

Package utf8

go1.15.3
Latest Go to latest

The highest tagged major version is .

Published: Oct 14, 2020 | License: BSD-3-Clause | Standard library

Overview

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

Index

Examples

Constants

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.
)

Numbers fundamental to the encoding.

func DecodeLastRune

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.

Example

Code:

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]
	}
}
界 3
世 3
  1
, 1
o 1
l 1
l 1
e 1
H 1

func DecodeLastRuneInString

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.

Example

Code:

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]
	}
}
界 3
世 3
  1
, 1
o 1
l 1
l 1
e 1
H 1

func DecodeRune

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.

Example

Code:

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:]
	}
}
H 1
e 1
l 1
l 1
o 1
, 1
  1
世 3
界 3

func DecodeRuneInString

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.

Example

Code:

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:]
	}
}
H 1
e 1
l 1
l 1
o 1
, 1
  1
世 3
界 3

func EncodeRune

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.

Example

Code:

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)
}
[228 184 150]
3

func FullRune

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.

Example

Code:

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]))
}
true
false

func FullRuneInString

func FullRuneInString(s string) bool

FullRuneInString is like FullRune but its input is a string.

Example

Code:

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	str := "世"
	fmt.Println(utf8.FullRuneInString(str))
	fmt.Println(utf8.FullRuneInString(str[:2]))
}
true
false

func RuneCount

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.

Example

Code:

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	buf := []byte("Hello, 世界")
	fmt.Println("bytes =", len(buf))
	fmt.Println("runes =", utf8.RuneCount(buf))
}
bytes = 13
runes = 9

func RuneCountInString

func RuneCountInString(s string) (n int)

RuneCountInString is like RuneCount but its input is a string.

Example

Code:

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	str := "Hello, 世界"
	fmt.Println("bytes =", len(str))
	fmt.Println("runes =", utf8.RuneCountInString(str))
}
bytes = 13
runes = 9

func RuneLen

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.

Example

Code:

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	fmt.Println(utf8.RuneLen('a'))
	fmt.Println(utf8.RuneLen('界'))
}
1
3

func RuneStart

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.

Example

Code:

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]))
}
true
true
false

func Valid

func Valid(p []byte) bool

Valid reports whether p consists entirely of valid UTF-8-encoded runes.

Example

Code:

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))
}
true
false

func ValidRune

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.

Example

Code:

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	valid := 'a'
	invalid := rune(0xfffffff)

	fmt.Println(utf8.ValidRune(valid))
	fmt.Println(utf8.ValidRune(invalid))
}
true
false

func ValidString

func ValidString(s string) bool

ValidString reports whether s consists entirely of valid UTF-8-encoded runes.

Example

Code:

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))
}
true
false
Documentation was rendered with GOOS=linux and GOARCH=amd64.

Jump to identifier

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to identifier