// Copyright 2009 The Go Authors. All rights reserved.// Use of this source code is governed by a BSD-style// license that can be found in the LICENSE file. // Package bytes implements functions for the manipulation of byte slices.// It is analogous to the facilities of the strings package.package bytes import (	"unicode"	"unicode/utf8") func equalPortable(a, b []byte) bool {	if len(a) != len(b) {		return false	}	for i, c := range a {		if c != b[i] {			return false		}	}	return true} // explode splits s into a slice of UTF-8 sequences, one per Unicode code point (still slices of bytes),// up to a maximum of n byte slices. Invalid UTF-8 sequences are chopped into individual bytes.func explode(s []byte, n int) [][]byte {	if n <= 0 {		n = len(s)	}	a := make([][]byte, n)	var size int	na := 0	for len(s) > 0 {		if na+1 >= n {			a[na] = s			na++			break		}		_, size = utf8.DecodeRune(s)		a[na] = s[0:size]		s = s[size:]		na++	}	return a[0:na]} // Count counts the number of non-overlapping instances of sep in s.// If sep is an empty slice, Count returns 1 + the number of Unicode code points in s.func Count(s, sep []byte) int {	n := len(sep)	if n == 0 {		return utf8.RuneCount(s) + 1	}	if n > len(s) {		return 0	}	count := 0	c := sep[0]	i := 0	t := s[:len(s)-n+1]	for i < len(t) {		if t[i] != c {			o := IndexByte(t[i:], c)			if o < 0 {				break			}			i += o		}		if n == 1 || Equal(s[i:i+n], sep) {			count++			i += n			continue		}		i++	}	return count} // Contains reports whether subslice is within b.func Contains(b, subslice []byte) bool {	return Index(b, subslice) != -1} // Index returns the index of the first instance of sep in s, or -1 if sep is not present in s.func Index(s, sep []byte) int {	n := len(sep)	if n == 0 {		return 0	}	if n > len(s) {		return -1	}	c := sep[0]	if n == 1 {		return IndexByte(s, c)	}	i := 0	t := s[:len(s)-n+1]	for i < len(t) {		if t[i] != c {			o := IndexByte(t[i:], c)			if o < 0 {				break			}			i += o		}		if Equal(s[i:i+n], sep) {			return i		}		i++	}	return -1} func indexBytePortable(s []byte, c byte) int {	for i, b := range s {		if b == c {			return i		}	}	return -1} // LastIndex returns the index of the last instance of sep in s, or -1 if sep is not present in s.func LastIndex(s, sep []byte) int {	n := len(sep)	if n == 0 {		return len(s)	}	c := sep[0]	for i := len(s) - n; i >= 0; i-- {		if s[i] == c && (n == 1 || Equal(s[i:i+n], sep)) {			return i		}	}	return -1} // LastIndexByte returns the index of the last instance of c in s, or -1 if c is not present in s.func LastIndexByte(s []byte, c byte) int {	for i := len(s) - 1; i >= 0; i-- {		if s[i] == c {			return i		}	}	return -1} // IndexRune interprets s as a sequence of UTF-8-encoded Unicode code points.// It returns the byte index of the first occurrence in s of the given rune.// It returns -1 if rune is not present in s.func IndexRune(s []byte, r rune) int {	for i := 0; i < len(s); {		r1, size := utf8.DecodeRune(s[i:])		if r == r1 {			return i		}		i += size	}	return -1} // IndexAny interprets s as a sequence of UTF-8-encoded Unicode code points.// It returns the byte index of the first occurrence in s of any of the Unicode// code points in chars.  It returns -1 if chars is empty or if there is no code// point in common.func IndexAny(s []byte, chars string) int {	if len(chars) > 0 {		var r rune		var width int		for i := 0; i < len(s); i += width {			r = rune(s[i])			if r < utf8.RuneSelf {				width = 1			} else {				r, width = utf8.DecodeRune(s[i:])			}			for _, ch := range chars {				if r == ch {					return i				}			}		}	}	return -1} // LastIndexAny interprets s as a sequence of UTF-8-encoded Unicode code// points.  It returns the byte index of the last occurrence in s of any of// the Unicode code points in chars.  It returns -1 if chars is empty or if// there is no code point in common.func LastIndexAny(s []byte, chars string) int {	if len(chars) > 0 {		for i := len(s); i > 0; {			r, size := utf8.DecodeLastRune(s[0:i])			i -= size			for _, ch := range chars {				if r == ch {					return i				}			}		}	}	return -1} // Generic split: splits after each instance of sep,// including sepSave bytes of sep in the subslices.func genSplit(s, sep []byte, sepSave, n int) [][]byte {	if n == 0 {		return nil	}	if len(sep) == 0 {		return explode(s, n)	}	if n < 0 {		n = Count(s, sep) + 1	}	c := sep[0]	start := 0	a := make([][]byte, n)	na := 0	for i := 0; i+len(sep) <= len(s) && na+1 < n; i++ {		if s[i] == c && (len(sep) == 1 || Equal(s[i:i+len(sep)], sep)) {			a[na] = s[start : i+sepSave]			na++			start = i + len(sep)			i += len(sep) - 1		}	}	a[na] = s[start:]	return a[0 : na+1]} // SplitN slices s into subslices separated by sep and returns a slice of// the subslices between those separators.// If sep is empty, SplitN splits after each UTF-8 sequence.// The count determines the number of subslices to return://   n > 0: at most n subslices; the last subslice will be the unsplit remainder.//   n == 0: the result is nil (zero subslices)//   n < 0: all subslicesfunc SplitN(s, sep []byte, n int) [][]byte { return genSplit(s, sep, 0, n) } // SplitAfterN slices s into subslices after each instance of sep and// returns a slice of those subslices.// If sep is empty, SplitAfterN splits after each UTF-8 sequence.// The count determines the number of subslices to return://   n > 0: at most n subslices; the last subslice will be the unsplit remainder.//   n == 0: the result is nil (zero subslices)//   n < 0: all subslicesfunc SplitAfterN(s, sep []byte, n int) [][]byte {	return genSplit(s, sep, len(sep), n)} // Split slices s into all subslices separated by sep and returns a slice of// the subslices between those separators.// If sep is empty, Split splits after each UTF-8 sequence.// It is equivalent to SplitN with a count of -1.func Split(s, sep []byte) [][]byte { return genSplit(s, sep, 0, -1) } // SplitAfter slices s into all subslices after each instance of sep and// returns a slice of those subslices.// If sep is empty, SplitAfter splits after each UTF-8 sequence.// It is equivalent to SplitAfterN with a count of -1.func SplitAfter(s, sep []byte) [][]byte {	return genSplit(s, sep, len(sep), -1)} // Fields splits the slice s around each instance of one or more consecutive white space// characters, returning a slice of subslices of s or an empty list if s contains only white space.func Fields(s []byte) [][]byte {	return FieldsFunc(s, unicode.IsSpace)} // FieldsFunc interprets s as a sequence of UTF-8-encoded Unicode code points.// It splits the slice s at each run of code points c satisfying f(c) and// returns a slice of subslices of s.  If all code points in s satisfy f(c), or// len(s) == 0, an empty slice is returned.// FieldsFunc makes no guarantees about the order in which it calls f(c).// If f does not return consistent results for a given c, FieldsFunc may crash.func FieldsFunc(s []byte, f func(rune) bool) [][]byte {	n := 0	inField := false	for i := 0; i < len(s); {		r, size := utf8.DecodeRune(s[i:])		wasInField := inField		inField = !f(r)		if inField && !wasInField {			n++		}		i += size	} 	a := make([][]byte, n)	na := 0	fieldStart := -1	for i := 0; i <= len(s) && na < n; {		r, size := utf8.DecodeRune(s[i:])		if fieldStart < 0 && size > 0 && !f(r) {			fieldStart = i			i += size			continue		}		if fieldStart >= 0 && (size == 0 || f(r)) {			a[na] = s[fieldStart:i]			na++			fieldStart = -1		}		if size == 0 {			break		}		i += size	}	return a[0:na]} // Join concatenates the elements of s to create a new byte slice. The separator// sep is placed between elements in the resulting slice.func Join(s [][]byte, sep []byte) []byte {	if len(s) == 0 {		return []byte{}	}	if len(s) == 1 {		// Just return a copy.		return append([]byte(nil), s[0]...)	}	n := len(sep) * (len(s) - 1)	for _, v := range s {		n += len(v)	} 	b := make([]byte, n)	bp := copy(b, s[0])	for _, v := range s[1:] {		bp += copy(b[bp:], sep)		bp += copy(b[bp:], v)	}	return b} // HasPrefix tests whether the byte slice s begins with prefix.func HasPrefix(s, prefix []byte) bool {	return len(s) >= len(prefix) && Equal(s[0:len(prefix)], prefix)} // HasSuffix tests whether the byte slice s ends with suffix.func HasSuffix(s, suffix []byte) bool {	return len(s) >= len(suffix) && Equal(s[len(s)-len(suffix):], suffix)} // Map returns a copy of the byte slice s with all its characters modified// according to the mapping function. If mapping returns a negative value, the character is// dropped from the string with no replacement.  The characters in s and the// output are interpreted as UTF-8-encoded Unicode code points.func Map(mapping func(r rune) rune, s []byte) []byte {	// In the worst case, the slice can grow when mapped, making	// things unpleasant.  But it's so rare we barge in assuming it's	// fine.  It could also shrink but that falls out naturally.	maxbytes := len(s) // length of b	nbytes := 0        // number of bytes encoded in b	b := make([]byte, maxbytes)	for i := 0; i < len(s); {		wid := 1		r := rune(s[i])		if r >= utf8.RuneSelf {			r, wid = utf8.DecodeRune(s[i:])		}		r = mapping(r)		if r >= 0 {			rl := utf8.RuneLen(r)			if rl < 0 {				rl = len(string(utf8.RuneError))			}			if nbytes+rl > maxbytes {				// Grow the buffer.				maxbytes = maxbytes*2 + utf8.UTFMax				nb := make([]byte, maxbytes)				copy(nb, b[0:nbytes])				b = nb			}			nbytes += utf8.EncodeRune(b[nbytes:maxbytes], r)		}		i += wid	}	return b[0:nbytes]} // Repeat returns a new byte slice consisting of count copies of b.func Repeat(b []byte, count int) []byte {	nb := make([]byte, len(b)*count)	bp := copy(nb, b)	for bp < len(nb) {		copy(nb[bp:], nb[:bp])		bp *= 2	}	return nb} // ToUpper returns a copy of the byte slice s with all Unicode letters mapped to their upper case.func ToUpper(s []byte) []byte { return Map(unicode.ToUpper, s) } // ToLower returns a copy of the byte slice s with all Unicode letters mapped to their lower case.func ToLower(s []byte) []byte { return Map(unicode.ToLower, s) } // ToTitle returns a copy of the byte slice s with all Unicode letters mapped to their title case.func ToTitle(s []byte) []byte { return Map(unicode.ToTitle, s) } // ToUpperSpecial returns a copy of the byte slice s with all Unicode letters mapped to their// upper case, giving priority to the special casing rules.func ToUpperSpecial(_case unicode.SpecialCase, s []byte) []byte {	return Map(func(r rune) rune { return _case.ToUpper(r) }, s)} // ToLowerSpecial returns a copy of the byte slice s with all Unicode letters mapped to their// lower case, giving priority to the special casing rules.func ToLowerSpecial(_case unicode.SpecialCase, s []byte) []byte {	return Map(func(r rune) rune { return _case.ToLower(r) }, s)} // ToTitleSpecial returns a copy of the byte slice s with all Unicode letters mapped to their// title case, giving priority to the special casing rules.func ToTitleSpecial(_case unicode.SpecialCase, s []byte) []byte {	return Map(func(r rune) rune { return _case.ToTitle(r) }, s)} // isSeparator reports whether the rune could mark a word boundary.// TODO: update when package unicode captures more of the properties.func isSeparator(r rune) bool {	// ASCII alphanumerics and underscore are not separators	if r <= 0x7F {		switch {		case '0' <= r && r <= '9':			return false		case 'a' <= r && r <= 'z':			return false		case 'A' <= r && r <= 'Z':			return false		case r == '_':			return false		}		return true	}	// Letters and digits are not separators	if unicode.IsLetter(r) || unicode.IsDigit(r) {		return false	}	// Otherwise, all we can do for now is treat spaces as separators.	return unicode.IsSpace(r)} // Title returns a copy of s with all Unicode letters that begin words// mapped to their title case.//// BUG(rsc): The rule Title uses for word boundaries does not handle Unicode punctuation properly.func Title(s []byte) []byte {	// Use a closure here to remember state.	// Hackish but effective. Depends on Map scanning in order and calling	// the closure once per rune.	prev := ' '	return Map(		func(r rune) rune {			if isSeparator(prev) {				prev = r				return unicode.ToTitle(r)			}			prev = r			return r		},		s)} // TrimLeftFunc returns a subslice of s by slicing off all leading UTF-8-encoded// Unicode code points c that satisfy f(c).func TrimLeftFunc(s []byte, f func(r rune) bool) []byte {	i := indexFunc(s, f, false)	if i == -1 {		return nil	}	return s[i:]} // TrimRightFunc returns a subslice of s by slicing off all trailing UTF-8// encoded Unicode code points c that satisfy f(c).func TrimRightFunc(s []byte, f func(r rune) bool) []byte {	i := lastIndexFunc(s, f, false)	if i >= 0 && s[i] >= utf8.RuneSelf {		_, wid := utf8.DecodeRune(s[i:])		i += wid	} else {		i++	}	return s[0:i]} // TrimFunc returns a subslice of s by slicing off all leading and trailing// UTF-8-encoded Unicode code points c that satisfy f(c).func TrimFunc(s []byte, f func(r rune) bool) []byte {	return TrimRightFunc(TrimLeftFunc(s, f), f)

Lines 1–500 of 714. Load more