utf8 package - unicode/utf8

utf8 package - unicode/utf8 - Go Packages

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

View Source

const (
	RuneError = '\uFFFD'     
	RuneSelf  = 0x80         
	MaxRune   = '\U0010FFFF' 
	UTFMax    = 4            
)

Numbers fundamental to the encoding.

This section is empty.

AppendRune appends the UTF-8 encoding of r to the end of p and returns the extended buffer. If the rune is out of range, it appends the encoding of RuneError.

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	buf1 := utf8.AppendRune(nil, 0x10000)
	buf2 := utf8.AppendRune([]byte("init"), 0x10000)
	fmt.Println(string(buf1))
	fmt.Println(string(buf2))
}

Output:

𐀀
init𐀀

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]
	}
}

Output:

界 3
世 3
  1
, 1
o 1
l 1
l 1
e 1
H 1

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]
	}
}

Output:

界 3
世 3
  1
, 1
o 1
l 1
l 1
e 1
H 1

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:]
	}
}

Output:

H 1
e 1
l 1
l 1
o 1
, 1
  1
世 3
界 3

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:]
	}
}

Output:

H 1
e 1
l 1
l 1
o 1
, 1
  1
世 3
界 3

EncodeRune writes into p (which must be large enough) the UTF-8 encoding of the rune. If the rune is out of range, it writes the encoding of RuneError. 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)
}

Output:

[228 184 150]
3

package main

import (
	"fmt"
	"unicode/utf8"
)

func main() {
	runes := []rune{
		// Less than 0, out of range.
		-1,
		// Greater than 0x10FFFF, out of range.
		0x110000,
		// The Unicode replacement character.
		utf8.RuneError,
	}
	for i, c := range runes {
		buf := make([]byte, 3)
		size := utf8.EncodeRune(buf, c)
		fmt.Printf("%d: %d %[2]s %d\n", i, buf, size)
	}
}

Output:

0: [239 191 189] � 3
1: [239 191 189] � 3
2: [239 191 189] � 3

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]))
}

Output:

true
false

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]))
}

Output:

true
false

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))
}

Output:

bytes = 13
runes = 9

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))
}

Output:

bytes = 13
runes = 9

RuneLen returns the number of bytes in the UTF-8 encoding of 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'))
}

Output:

1
3

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]))
}

Output:

true
true
false

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))
}

Output:

true
false

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))
}

Output:

true
false

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))
}

Output:

true
false

This section is empty.