go/src/unicode/utf8/utf8.go

const RuneError …

const RuneSelf …

const MaxRune …

const UTFMax …

const surrogateMin …

const surrogateMax …

const t1 …

const tx …

const t2 …

const t3 …

const t4 …

const t5 …

const maskx …

const mask2 …

const mask3 …

const mask4 …

const rune1Max …

const rune2Max …

const rune3Max …

const locb …

const hicb …

const xx …

const as …

const s1 …

const s2 …

const s3 …

const s4 …

const s5 …

const s6 …

const s7 …

const runeErrorByte0 …

const runeErrorByte1 …

const runeErrorByte2 …

var first …

type acceptRange …

var acceptRanges …

// 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 { … }

// FullRuneInString is like FullRune but its input is a string.
func FullRuneInString(s string) bool { … }

// 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.
func DecodeRune(p []byte) (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.
func DecodeRuneInString(s string) (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.
func DecodeLastRune(p []byte) (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.
func DecodeLastRuneInString(s string) (r rune, size int) { … }

// 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.
func RuneLen(r rune) int { … }

// 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.
func EncodeRune(p []byte, r rune) int { … }

func encodeRuneNonASCII(p []byte, r rune) int { … }

// 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].
func AppendRune(p []byte, r rune) []byte { … }

func appendRuneNonASCII(p []byte, r rune) []byte { … }

// 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 { … }

// RuneCountInString is like [RuneCount] but its input is a string.
func RuneCountInString(s string) (n int) { … }

// 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.
func RuneStart(b byte) bool { … }

// Valid reports whether p consists entirely of valid UTF-8-encoded runes.
func Valid(p []byte) bool { … }

// ValidString reports whether s consists entirely of valid UTF-8-encoded runes.
func ValidString(s string) 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.
func ValidRune(r rune) bool { … }