2012-03-27 23:13:14 +00:00
|
|
|
// 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
|
|
|
|
}
|
|
|
|
|
2017-04-10 11:32:00 +00:00
|
|
|
// explode splits s into a slice of UTF-8 sequences, one per Unicode code point (still slices of bytes),
|
2014-09-21 17:33:12 +00:00
|
|
|
// up to a maximum of n byte slices. Invalid UTF-8 sequences are chopped into individual bytes.
|
2012-03-27 23:13:14 +00:00
|
|
|
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)
|
2018-12-28 15:30:48 +00:00
|
|
|
a[na] = s[0:size:size]
|
2012-03-27 23:13:14 +00:00
|
|
|
s = s[size:]
|
|
|
|
na++
|
|
|
|
}
|
|
|
|
return a[0:na]
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// countGeneric actually implements Count
|
|
|
|
func countGeneric(s, sep []byte) int {
|
|
|
|
// special case
|
|
|
|
if len(sep) == 0 {
|
2012-03-27 23:13:14 +00:00
|
|
|
return utf8.RuneCount(s) + 1
|
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
n := 0
|
|
|
|
for {
|
|
|
|
i := Index(s, sep)
|
|
|
|
if i == -1 {
|
|
|
|
return n
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
n++
|
|
|
|
s = s[i+len(sep):]
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-09-21 17:33:12 +00:00
|
|
|
// Contains reports whether subslice is within b.
|
2012-03-27 23:13:14 +00:00
|
|
|
func Contains(b, subslice []byte) bool {
|
|
|
|
return Index(b, subslice) != -1
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ContainsAny reports whether any of the UTF-8-encoded code points in chars are within b.
|
2017-10-07 00:16:47 +00:00
|
|
|
func ContainsAny(b []byte, chars string) bool {
|
|
|
|
return IndexAny(b, chars) >= 0
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ContainsRune reports whether the rune is contained in the UTF-8-encoded byte slice b.
|
2017-10-07 00:16:47 +00:00
|
|
|
func ContainsRune(b []byte, r rune) bool {
|
|
|
|
return IndexRune(b, r) >= 0
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
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
|
|
|
|
}
|
|
|
|
|
2017-04-10 11:32:00 +00:00
|
|
|
// 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
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// IndexRune interprets s as a sequence of UTF-8-encoded code points.
|
2012-03-27 23:13:14 +00:00
|
|
|
// 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.
|
2017-10-07 00:16:47 +00:00
|
|
|
// If r is utf8.RuneError, it returns the first instance of any
|
|
|
|
// invalid UTF-8 byte sequence.
|
2012-03-27 23:13:14 +00:00
|
|
|
func IndexRune(s []byte, r rune) int {
|
2017-10-07 00:16:47 +00:00
|
|
|
switch {
|
|
|
|
case 0 <= r && r < utf8.RuneSelf:
|
|
|
|
return IndexByte(s, byte(r))
|
|
|
|
case r == utf8.RuneError:
|
|
|
|
for i := 0; i < len(s); {
|
|
|
|
r1, n := utf8.DecodeRune(s[i:])
|
|
|
|
if r1 == utf8.RuneError {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
i += n
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2017-10-07 00:16:47 +00:00
|
|
|
return -1
|
|
|
|
case !utf8.ValidRune(r):
|
|
|
|
return -1
|
|
|
|
default:
|
|
|
|
var b [utf8.UTFMax]byte
|
|
|
|
n := utf8.EncodeRune(b[:], r)
|
|
|
|
return Index(s, b[:n])
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// 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
|
2017-10-07 00:16:47 +00:00
|
|
|
// code points in chars. It returns -1 if chars is empty or if there is no code
|
2012-03-27 23:13:14 +00:00
|
|
|
// point in common.
|
|
|
|
func IndexAny(s []byte, chars string) int {
|
2018-12-28 15:30:48 +00:00
|
|
|
if chars == "" {
|
|
|
|
// Avoid scanning all of s.
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
if len(s) > 8 {
|
|
|
|
if as, isASCII := makeASCIISet(chars); isASCII {
|
|
|
|
for i, c := range s {
|
|
|
|
if as.contains(c) {
|
|
|
|
return i
|
2017-10-07 00:16:47 +00:00
|
|
|
}
|
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
return -1
|
2017-10-07 00:16:47 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
}
|
|
|
|
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
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
|
|
|
// LastIndexAny interprets s as a sequence of UTF-8-encoded Unicode code
|
2017-10-07 00:16:47 +00:00
|
|
|
// 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
|
2012-03-27 23:13:14 +00:00
|
|
|
// there is no code point in common.
|
|
|
|
func LastIndexAny(s []byte, chars string) int {
|
2018-12-28 15:30:48 +00:00
|
|
|
if chars == "" {
|
|
|
|
// Avoid scanning all of s.
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
if len(s) > 8 {
|
|
|
|
if as, isASCII := makeASCIISet(chars); isASCII {
|
|
|
|
for i := len(s) - 1; i >= 0; i-- {
|
|
|
|
if as.contains(s[i]) {
|
|
|
|
return i
|
2017-10-07 00:16:47 +00:00
|
|
|
}
|
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
return -1
|
2017-10-07 00:16:47 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
}
|
|
|
|
for i := len(s); i > 0; {
|
|
|
|
r, size := utf8.DecodeLastRune(s[:i])
|
|
|
|
i -= size
|
|
|
|
for _, c := range chars {
|
|
|
|
if r == c {
|
|
|
|
return i
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
|
|
|
// Generic split: splits after each instance of sep,
|
2014-09-21 17:33:12 +00:00
|
|
|
// including sepSave bytes of sep in the subslices.
|
2012-03-27 23:13:14 +00:00
|
|
|
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
|
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
|
2012-03-27 23:13:14 +00:00
|
|
|
a := make([][]byte, n)
|
2018-12-28 15:30:48 +00:00
|
|
|
n--
|
|
|
|
i := 0
|
|
|
|
for i < n {
|
|
|
|
m := Index(s, sep)
|
|
|
|
if m < 0 {
|
|
|
|
break
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
a[i] = s[: m+sepSave : m+sepSave]
|
|
|
|
s = s[m+len(sep):]
|
|
|
|
i++
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
a[i] = s
|
|
|
|
return a[:i+1]
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
// 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 subslices
|
|
|
|
func 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 subslices
|
|
|
|
func 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)
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
var asciiSpace = [256]uint8{'\t': 1, '\n': 1, '\v': 1, '\f': 1, '\r': 1, ' ': 1}
|
|
|
|
|
|
|
|
// Fields interprets s as a sequence of UTF-8-encoded code points.
|
|
|
|
// It splits the slice s around each instance of one or more consecutive white space
|
|
|
|
// characters, as defined by unicode.IsSpace, returning a slice of subslices of s or an
|
|
|
|
// empty slice if s contains only white space.
|
2012-03-27 23:13:14 +00:00
|
|
|
func Fields(s []byte) [][]byte {
|
2018-12-28 15:30:48 +00:00
|
|
|
// First count the fields.
|
|
|
|
// This is an exact count if s is ASCII, otherwise it is an approximation.
|
|
|
|
n := 0
|
|
|
|
wasSpace := 1
|
|
|
|
// setBits is used to track which bits are set in the bytes of s.
|
|
|
|
setBits := uint8(0)
|
|
|
|
for i := 0; i < len(s); i++ {
|
|
|
|
r := s[i]
|
|
|
|
setBits |= r
|
|
|
|
isSpace := int(asciiSpace[r])
|
|
|
|
n += wasSpace & ^isSpace
|
|
|
|
wasSpace = isSpace
|
|
|
|
}
|
|
|
|
|
|
|
|
if setBits >= utf8.RuneSelf {
|
|
|
|
// Some runes in the input slice are not ASCII.
|
|
|
|
return FieldsFunc(s, unicode.IsSpace)
|
|
|
|
}
|
|
|
|
|
|
|
|
// ASCII fast path
|
|
|
|
a := make([][]byte, n)
|
|
|
|
na := 0
|
|
|
|
fieldStart := 0
|
|
|
|
i := 0
|
|
|
|
// Skip spaces in the front of the input.
|
|
|
|
for i < len(s) && asciiSpace[s[i]] != 0 {
|
|
|
|
i++
|
|
|
|
}
|
|
|
|
fieldStart = i
|
|
|
|
for i < len(s) {
|
|
|
|
if asciiSpace[s[i]] == 0 {
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
a[na] = s[fieldStart:i:i]
|
|
|
|
na++
|
|
|
|
i++
|
|
|
|
// Skip spaces in between fields.
|
|
|
|
for i < len(s) && asciiSpace[s[i]] != 0 {
|
|
|
|
i++
|
|
|
|
}
|
|
|
|
fieldStart = i
|
|
|
|
}
|
|
|
|
if fieldStart < len(s) { // Last field might end at EOF.
|
|
|
|
a[na] = s[fieldStart:len(s):len(s)]
|
|
|
|
}
|
|
|
|
return a
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// FieldsFunc interprets s as a sequence of UTF-8-encoded code points.
|
2014-09-21 17:33:12 +00:00
|
|
|
// It splits the slice s at each run of code points c satisfying f(c) and
|
2017-10-07 00:16:47 +00:00
|
|
|
// returns a slice of subslices of s. If all code points in s satisfy f(c), or
|
2015-08-28 15:33:40 +00:00
|
|
|
// 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.
|
2012-03-27 23:13:14 +00:00
|
|
|
func FieldsFunc(s []byte, f func(rune) bool) [][]byte {
|
2018-12-28 15:30:48 +00:00
|
|
|
// A span is used to record a slice of s of the form s[start:end].
|
|
|
|
// The start index is inclusive and the end index is exclusive.
|
|
|
|
type span struct {
|
|
|
|
start int
|
|
|
|
end int
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
spans := make([]span, 0, 32)
|
2012-03-27 23:13:14 +00:00
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// Find the field start and end indices.
|
|
|
|
wasField := false
|
|
|
|
fromIndex := 0
|
|
|
|
for i := 0; i < len(s); {
|
|
|
|
size := 1
|
|
|
|
r := rune(s[i])
|
|
|
|
if r >= utf8.RuneSelf {
|
|
|
|
r, size = utf8.DecodeRune(s[i:])
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
if f(r) {
|
|
|
|
if wasField {
|
|
|
|
spans = append(spans, span{start: fromIndex, end: i})
|
|
|
|
wasField = false
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if !wasField {
|
|
|
|
fromIndex = i
|
|
|
|
wasField = true
|
|
|
|
}
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
i += size
|
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
|
|
|
|
// Last field might end at EOF.
|
|
|
|
if wasField {
|
|
|
|
spans = append(spans, span{fromIndex, len(s)})
|
|
|
|
}
|
|
|
|
|
|
|
|
// Create subslices from recorded field indices.
|
|
|
|
a := make([][]byte, len(spans))
|
|
|
|
for i, span := range spans {
|
|
|
|
a[i] = s[span.start:span.end:span.end]
|
|
|
|
}
|
|
|
|
|
|
|
|
return a
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
2014-09-21 17:33:12 +00:00
|
|
|
// 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 {
|
2012-03-27 23:13:14 +00:00
|
|
|
return []byte{}
|
|
|
|
}
|
2014-09-21 17:33:12 +00:00
|
|
|
if len(s) == 1 {
|
|
|
|
// Just return a copy.
|
|
|
|
return append([]byte(nil), s[0]...)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
2014-09-21 17:33:12 +00:00
|
|
|
n := len(sep) * (len(s) - 1)
|
|
|
|
for _, v := range s {
|
|
|
|
n += len(v)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
b := make([]byte, n)
|
2014-09-21 17:33:12 +00:00
|
|
|
bp := copy(b, s[0])
|
|
|
|
for _, v := range s[1:] {
|
2012-03-27 23:13:14 +00:00
|
|
|
bp += copy(b[bp:], sep)
|
2014-09-21 17:33:12 +00:00
|
|
|
bp += copy(b[bp:], v)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
return b
|
|
|
|
}
|
|
|
|
|
2014-09-21 17:33:12 +00:00
|
|
|
// HasPrefix tests whether the byte slice s begins with prefix.
|
2012-03-27 23:13:14 +00:00
|
|
|
func HasPrefix(s, prefix []byte) bool {
|
|
|
|
return len(s) >= len(prefix) && Equal(s[0:len(prefix)], prefix)
|
|
|
|
}
|
|
|
|
|
2014-09-21 17:33:12 +00:00
|
|
|
// HasSuffix tests whether the byte slice s ends with suffix.
|
2012-03-27 23:13:14 +00:00
|
|
|
func HasSuffix(s, suffix []byte) bool {
|
|
|
|
return len(s) >= len(suffix) && Equal(s[len(s)-len(suffix):], suffix)
|
|
|
|
}
|
|
|
|
|
2014-09-21 17:33:12 +00:00
|
|
|
// Map returns a copy of the byte slice s with all its characters modified
|
2012-03-27 23:13:14 +00:00
|
|
|
// according to the mapping function. If mapping returns a negative value, the character is
|
2018-12-28 15:30:48 +00:00
|
|
|
// dropped from the byte slice with no replacement. The characters in s and the
|
|
|
|
// output are interpreted as UTF-8-encoded code points.
|
2012-03-27 23:13:14 +00:00
|
|
|
func Map(mapping func(r rune) rune, s []byte) []byte {
|
2014-09-21 17:33:12 +00:00
|
|
|
// In the worst case, the slice can grow when mapped, making
|
2017-10-07 00:16:47 +00:00
|
|
|
// things unpleasant. But it's so rare we barge in assuming it's
|
|
|
|
// fine. It could also shrink but that falls out naturally.
|
2012-03-27 23:13:14 +00:00
|
|
|
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 {
|
2015-08-28 15:33:40 +00:00
|
|
|
rl := utf8.RuneLen(r)
|
|
|
|
if rl < 0 {
|
|
|
|
rl = len(string(utf8.RuneError))
|
|
|
|
}
|
|
|
|
if nbytes+rl > maxbytes {
|
2012-03-27 23:13:14 +00:00
|
|
|
// 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.
|
2017-10-07 00:16:47 +00:00
|
|
|
//
|
|
|
|
// It panics if count is negative or if
|
|
|
|
// the result of (len(b) * count) overflows.
|
2012-03-27 23:13:14 +00:00
|
|
|
func Repeat(b []byte, count int) []byte {
|
2017-10-07 00:16:47 +00:00
|
|
|
// Since we cannot return an error on overflow,
|
|
|
|
// we should panic if the repeat will generate
|
|
|
|
// an overflow.
|
|
|
|
// See Issue golang.org/issue/16237.
|
|
|
|
if count < 0 {
|
|
|
|
panic("bytes: negative Repeat count")
|
|
|
|
} else if count > 0 && len(b)*count/count != len(b) {
|
|
|
|
panic("bytes: Repeat count causes overflow")
|
|
|
|
}
|
|
|
|
|
2012-03-27 23:13:14 +00:00
|
|
|
nb := make([]byte, len(b)*count)
|
2015-08-28 15:33:40 +00:00
|
|
|
bp := copy(nb, b)
|
|
|
|
for bp < len(nb) {
|
|
|
|
copy(nb[bp:], nb[:bp])
|
|
|
|
bp *= 2
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
return nb
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ToUpper treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters within it mapped to their upper case.
|
2012-03-27 23:13:14 +00:00
|
|
|
func ToUpper(s []byte) []byte { return Map(unicode.ToUpper, s) }
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ToLower treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their lower case.
|
2012-03-27 23:13:14 +00:00
|
|
|
func ToLower(s []byte) []byte { return Map(unicode.ToLower, s) }
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ToTitle treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their title case.
|
2012-03-27 23:13:14 +00:00
|
|
|
func ToTitle(s []byte) []byte { return Map(unicode.ToTitle, s) }
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ToUpperSpecial treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their
|
2012-03-27 23:13:14 +00:00
|
|
|
// upper case, giving priority to the special casing rules.
|
2017-10-07 00:16:47 +00:00
|
|
|
func ToUpperSpecial(c unicode.SpecialCase, s []byte) []byte {
|
|
|
|
return Map(func(r rune) rune { return c.ToUpper(r) }, s)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ToLowerSpecial treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their
|
2012-03-27 23:13:14 +00:00
|
|
|
// lower case, giving priority to the special casing rules.
|
2017-10-07 00:16:47 +00:00
|
|
|
func ToLowerSpecial(c unicode.SpecialCase, s []byte) []byte {
|
|
|
|
return Map(func(r rune) rune { return c.ToLower(r) }, s)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// ToTitleSpecial treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their
|
2012-03-27 23:13:14 +00:00
|
|
|
// title case, giving priority to the special casing rules.
|
2017-10-07 00:16:47 +00:00
|
|
|
func ToTitleSpecial(c unicode.SpecialCase, s []byte) []byte {
|
|
|
|
return Map(func(r rune) rune { return c.ToTitle(r) }, s)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
// 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)
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// Title treats s as UTF-8-encoded bytes and returns a copy with all Unicode letters that begin
|
|
|
|
// words mapped to their title case.
|
2014-09-21 17:33:12 +00:00
|
|
|
//
|
2017-04-10 11:32:00 +00:00
|
|
|
// BUG(rsc): The rule Title uses for word boundaries does not handle Unicode punctuation properly.
|
2012-03-27 23:13:14 +00:00
|
|
|
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)
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// TrimLeftFunc treats s as UTF-8-encoded bytes and returns a subslice of s by slicing off
|
|
|
|
// all leading UTF-8-encoded code points c that satisfy f(c).
|
2012-03-27 23:13:14 +00:00
|
|
|
func TrimLeftFunc(s []byte, f func(r rune) bool) []byte {
|
|
|
|
i := indexFunc(s, f, false)
|
|
|
|
if i == -1 {
|
|
|
|
return nil
|
|
|
|
}
|
|
|
|
return s[i:]
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// TrimRightFunc returns a subslice of s by slicing off all trailing
|
|
|
|
// UTF-8-encoded code points c that satisfy f(c).
|
2012-03-27 23:13:14 +00:00
|
|
|
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
|
2018-12-28 15:30:48 +00:00
|
|
|
// UTF-8-encoded code points c that satisfy f(c).
|
2012-03-27 23:13:14 +00:00
|
|
|
func TrimFunc(s []byte, f func(r rune) bool) []byte {
|
|
|
|
return TrimRightFunc(TrimLeftFunc(s, f), f)
|
|
|
|
}
|
|
|
|
|
2014-09-21 17:33:12 +00:00
|
|
|
// TrimPrefix returns s without the provided leading prefix string.
|
|
|
|
// If s doesn't start with prefix, s is returned unchanged.
|
|
|
|
func TrimPrefix(s, prefix []byte) []byte {
|
|
|
|
if HasPrefix(s, prefix) {
|
|
|
|
return s[len(prefix):]
|
|
|
|
}
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
|
|
|
|
// TrimSuffix returns s without the provided trailing suffix string.
|
|
|
|
// If s doesn't end with suffix, s is returned unchanged.
|
|
|
|
func TrimSuffix(s, suffix []byte) []byte {
|
|
|
|
if HasSuffix(s, suffix) {
|
|
|
|
return s[:len(s)-len(suffix)]
|
|
|
|
}
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// IndexFunc interprets s as a sequence of UTF-8-encoded code points.
|
2012-03-27 23:13:14 +00:00
|
|
|
// It returns the byte index in s of the first Unicode
|
|
|
|
// code point satisfying f(c), or -1 if none do.
|
|
|
|
func IndexFunc(s []byte, f func(r rune) bool) int {
|
|
|
|
return indexFunc(s, f, true)
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// LastIndexFunc interprets s as a sequence of UTF-8-encoded code points.
|
2012-03-27 23:13:14 +00:00
|
|
|
// It returns the byte index in s of the last Unicode
|
|
|
|
// code point satisfying f(c), or -1 if none do.
|
|
|
|
func LastIndexFunc(s []byte, f func(r rune) bool) int {
|
|
|
|
return lastIndexFunc(s, f, true)
|
|
|
|
}
|
|
|
|
|
|
|
|
// indexFunc is the same as IndexFunc except that if
|
|
|
|
// truth==false, the sense of the predicate function is
|
|
|
|
// inverted.
|
|
|
|
func indexFunc(s []byte, f func(r rune) bool, truth bool) int {
|
|
|
|
start := 0
|
|
|
|
for start < len(s) {
|
|
|
|
wid := 1
|
|
|
|
r := rune(s[start])
|
|
|
|
if r >= utf8.RuneSelf {
|
|
|
|
r, wid = utf8.DecodeRune(s[start:])
|
|
|
|
}
|
|
|
|
if f(r) == truth {
|
|
|
|
return start
|
|
|
|
}
|
|
|
|
start += wid
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
|
|
|
// lastIndexFunc is the same as LastIndexFunc except that if
|
|
|
|
// truth==false, the sense of the predicate function is
|
|
|
|
// inverted.
|
|
|
|
func lastIndexFunc(s []byte, f func(r rune) bool, truth bool) int {
|
|
|
|
for i := len(s); i > 0; {
|
2014-09-21 17:33:12 +00:00
|
|
|
r, size := rune(s[i-1]), 1
|
|
|
|
if r >= utf8.RuneSelf {
|
|
|
|
r, size = utf8.DecodeLastRune(s[0:i])
|
|
|
|
}
|
2012-03-27 23:13:14 +00:00
|
|
|
i -= size
|
|
|
|
if f(r) == truth {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
2017-10-07 00:16:47 +00:00
|
|
|
// asciiSet is a 32-byte value, where each bit represents the presence of a
|
|
|
|
// given ASCII character in the set. The 128-bits of the lower 16 bytes,
|
|
|
|
// starting with the least-significant bit of the lowest word to the
|
|
|
|
// most-significant bit of the highest word, map to the full range of all
|
|
|
|
// 128 ASCII characters. The 128-bits of the upper 16 bytes will be zeroed,
|
|
|
|
// ensuring that any non-ASCII character will be reported as not in the set.
|
|
|
|
type asciiSet [8]uint32
|
|
|
|
|
|
|
|
// makeASCIISet creates a set of ASCII characters and reports whether all
|
|
|
|
// characters in chars are ASCII.
|
|
|
|
func makeASCIISet(chars string) (as asciiSet, ok bool) {
|
|
|
|
for i := 0; i < len(chars); i++ {
|
|
|
|
c := chars[i]
|
|
|
|
if c >= utf8.RuneSelf {
|
|
|
|
return as, false
|
|
|
|
}
|
|
|
|
as[c>>5] |= 1 << uint(c&31)
|
|
|
|
}
|
|
|
|
return as, true
|
|
|
|
}
|
|
|
|
|
|
|
|
// contains reports whether c is inside the set.
|
|
|
|
func (as *asciiSet) contains(c byte) bool {
|
|
|
|
return (as[c>>5] & (1 << uint(c&31))) != 0
|
|
|
|
}
|
|
|
|
|
2012-03-27 23:13:14 +00:00
|
|
|
func makeCutsetFunc(cutset string) func(r rune) bool {
|
2017-10-07 00:16:47 +00:00
|
|
|
if len(cutset) == 1 && cutset[0] < utf8.RuneSelf {
|
|
|
|
return func(r rune) bool {
|
|
|
|
return r == rune(cutset[0])
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if as, isASCII := makeASCIISet(cutset); isASCII {
|
|
|
|
return func(r rune) bool {
|
|
|
|
return r < utf8.RuneSelf && as.contains(byte(r))
|
|
|
|
}
|
|
|
|
}
|
2012-03-27 23:13:14 +00:00
|
|
|
return func(r rune) bool {
|
|
|
|
for _, c := range cutset {
|
|
|
|
if c == r {
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Trim returns a subslice of s by slicing off all leading and
|
2018-12-28 15:30:48 +00:00
|
|
|
// trailing UTF-8-encoded code points contained in cutset.
|
2012-03-27 23:13:14 +00:00
|
|
|
func Trim(s []byte, cutset string) []byte {
|
|
|
|
return TrimFunc(s, makeCutsetFunc(cutset))
|
|
|
|
}
|
|
|
|
|
|
|
|
// TrimLeft returns a subslice of s by slicing off all leading
|
2018-12-28 15:30:48 +00:00
|
|
|
// UTF-8-encoded code points contained in cutset.
|
2012-03-27 23:13:14 +00:00
|
|
|
func TrimLeft(s []byte, cutset string) []byte {
|
|
|
|
return TrimLeftFunc(s, makeCutsetFunc(cutset))
|
|
|
|
}
|
|
|
|
|
|
|
|
// TrimRight returns a subslice of s by slicing off all trailing
|
2018-12-28 15:30:48 +00:00
|
|
|
// UTF-8-encoded code points that are contained in cutset.
|
2012-03-27 23:13:14 +00:00
|
|
|
func TrimRight(s []byte, cutset string) []byte {
|
|
|
|
return TrimRightFunc(s, makeCutsetFunc(cutset))
|
|
|
|
}
|
|
|
|
|
|
|
|
// TrimSpace returns a subslice of s by slicing off all leading and
|
|
|
|
// trailing white space, as defined by Unicode.
|
|
|
|
func TrimSpace(s []byte) []byte {
|
|
|
|
return TrimFunc(s, unicode.IsSpace)
|
|
|
|
}
|
|
|
|
|
2018-12-28 15:30:48 +00:00
|
|
|
// Runes interprets s as a sequence of UTF-8-encoded code points.
|
|
|
|
// It returns a slice of runes (Unicode code points) equivalent to s.
|
2012-03-27 23:13:14 +00:00
|
|
|
func Runes(s []byte) []rune {
|
|
|
|
t := make([]rune, utf8.RuneCount(s))
|
|
|
|
i := 0
|
|
|
|
for len(s) > 0 {
|
|
|
|
r, l := utf8.DecodeRune(s)
|
|
|
|
t[i] = r
|
|
|
|
i++
|
|
|
|
s = s[l:]
|
|
|
|
}
|
|
|
|
return t
|
|
|
|
}
|
|
|
|
|
|
|
|
// Replace returns a copy of the slice s with the first n
|
|
|
|
// non-overlapping instances of old replaced by new.
|
2015-08-28 15:33:40 +00:00
|
|
|
// If old is empty, it matches at the beginning of the slice
|
|
|
|
// and after each UTF-8 sequence, yielding up to k+1 replacements
|
|
|
|
// for a k-rune slice.
|
2012-03-27 23:13:14 +00:00
|
|
|
// If n < 0, there is no limit on the number of replacements.
|
|
|
|
func Replace(s, old, new []byte, n int) []byte {
|
|
|
|
m := 0
|
|
|
|
if n != 0 {
|
|
|
|
// Compute number of replacements.
|
|
|
|
m = Count(s, old)
|
|
|
|
}
|
|
|
|
if m == 0 {
|
2014-09-21 17:33:12 +00:00
|
|
|
// Just return a copy.
|
|
|
|
return append([]byte(nil), s...)
|
2012-03-27 23:13:14 +00:00
|
|
|
}
|
|
|
|
if n < 0 || m < n {
|
|
|
|
n = m
|
|
|
|
}
|
|
|
|
|
|
|
|
// Apply replacements to buffer.
|
|
|
|
t := make([]byte, len(s)+n*(len(new)-len(old)))
|
|
|
|
w := 0
|
|
|
|
start := 0
|
|
|
|
for i := 0; i < n; i++ {
|
|
|
|
j := start
|
|
|
|
if len(old) == 0 {
|
|
|
|
if i > 0 {
|
|
|
|
_, wid := utf8.DecodeRune(s[start:])
|
|
|
|
j += wid
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
j += Index(s[start:], old)
|
|
|
|
}
|
|
|
|
w += copy(t[w:], s[start:j])
|
|
|
|
w += copy(t[w:], new)
|
|
|
|
start = j + len(old)
|
|
|
|
}
|
|
|
|
w += copy(t[w:], s[start:])
|
|
|
|
return t[0:w]
|
|
|
|
}
|
|
|
|
|
|
|
|
// EqualFold reports whether s and t, interpreted as UTF-8 strings,
|
|
|
|
// are equal under Unicode case-folding.
|
|
|
|
func EqualFold(s, t []byte) bool {
|
|
|
|
for len(s) != 0 && len(t) != 0 {
|
|
|
|
// Extract first rune from each.
|
|
|
|
var sr, tr rune
|
|
|
|
if s[0] < utf8.RuneSelf {
|
|
|
|
sr, s = rune(s[0]), s[1:]
|
|
|
|
} else {
|
|
|
|
r, size := utf8.DecodeRune(s)
|
|
|
|
sr, s = r, s[size:]
|
|
|
|
}
|
|
|
|
if t[0] < utf8.RuneSelf {
|
|
|
|
tr, t = rune(t[0]), t[1:]
|
|
|
|
} else {
|
|
|
|
r, size := utf8.DecodeRune(t)
|
|
|
|
tr, t = r, t[size:]
|
|
|
|
}
|
|
|
|
|
|
|
|
// If they match, keep going; if not, return false.
|
|
|
|
|
|
|
|
// Easy case.
|
|
|
|
if tr == sr {
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// Make sr < tr to simplify what follows.
|
|
|
|
if tr < sr {
|
|
|
|
tr, sr = sr, tr
|
|
|
|
}
|
|
|
|
// Fast check for ASCII.
|
|
|
|
if tr < utf8.RuneSelf && 'A' <= sr && sr <= 'Z' {
|
|
|
|
// ASCII, and sr is upper case. tr must be lower case.
|
|
|
|
if tr == sr+'a'-'A' {
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
2017-10-07 00:16:47 +00:00
|
|
|
// General case. SimpleFold(x) returns the next equivalent rune > x
|
2012-03-27 23:13:14 +00:00
|
|
|
// or wraps around to smaller values.
|
|
|
|
r := unicode.SimpleFold(sr)
|
|
|
|
for r != sr && r < tr {
|
|
|
|
r = unicode.SimpleFold(r)
|
|
|
|
}
|
|
|
|
if r == tr {
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
2017-10-07 00:16:47 +00:00
|
|
|
// One string is empty. Are both?
|
2012-03-27 23:13:14 +00:00
|
|
|
return len(s) == len(t)
|
|
|
|
}
|
2018-12-28 15:30:48 +00:00
|
|
|
|
|
|
|
func indexRabinKarp(s, sep []byte) int {
|
|
|
|
// Rabin-Karp search
|
|
|
|
hashsep, pow := hashStr(sep)
|
|
|
|
n := len(sep)
|
|
|
|
var h uint32
|
|
|
|
for i := 0; i < n; i++ {
|
|
|
|
h = h*primeRK + uint32(s[i])
|
|
|
|
}
|
|
|
|
if h == hashsep && Equal(s[:n], sep) {
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
for i := n; i < len(s); {
|
|
|
|
h *= primeRK
|
|
|
|
h += uint32(s[i])
|
|
|
|
h -= pow * uint32(s[i-n])
|
|
|
|
i++
|
|
|
|
if h == hashsep && Equal(s[i-n:i], sep) {
|
|
|
|
return i - n
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
|
|
|
// primeRK is the prime base used in Rabin-Karp algorithm.
|
|
|
|
const primeRK = 16777619
|
|
|
|
|
|
|
|
// hashStr returns the hash and the appropriate multiplicative
|
|
|
|
// factor for use in Rabin-Karp algorithm.
|
|
|
|
func hashStr(sep []byte) (uint32, uint32) {
|
|
|
|
hash := uint32(0)
|
|
|
|
for i := 0; i < len(sep); i++ {
|
|
|
|
hash = hash*primeRK + uint32(sep[i])
|
|
|
|
}
|
|
|
|
var pow, sq uint32 = 1, primeRK
|
|
|
|
for i := len(sep); i > 0; i >>= 1 {
|
|
|
|
if i&1 != 0 {
|
|
|
|
pow *= sq
|
|
|
|
}
|
|
|
|
sq *= sq
|
|
|
|
}
|
|
|
|
return hash, pow
|
|
|
|
}
|