gcc/libgo/go/bytes/bytes.go
Ian Lance Taylor 9a0e3259f4 libgo: Update to weekly.2011-12-14.
From-SVN: r183118
2012-01-12 01:31:45 +00:00

705 lines
18 KiB
Go

// 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"
)
// Compare returns an integer comparing the two byte arrays lexicographically.
// The result will be 0 if a==b, -1 if a < b, and +1 if a > b
func Compare(a, b []byte) int {
m := len(a)
if m > len(b) {
m = len(b)
}
for i, ac := range a[0:m] {
bc := b[i]
switch {
case ac > bc:
return 1
case ac < bc:
return -1
}
}
switch {
case len(a) < len(b):
return -1
case len(a) > len(b):
return 1
}
return 0
}
// Equal returns a boolean reporting whether a == b.
func Equal(a, b []byte) bool
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 an array of UTF-8 sequences, one per Unicode character (still arrays of bytes),
// up to a maximum of n byte arrays. 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.
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 returns 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
}
// 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 subarrays.
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 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)
}
// Fields splits the array s around each instance of one or more consecutive white space
// characters, returning a slice of subarrays 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 array s at each run of code points c satisfying f(c) and
// returns a slice of subarrays of s. If no code points in s satisfy f(c), an
// empty slice is returned.
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 a to create a single byte array. The separator
// sep is placed between elements in the resulting array.
func Join(a [][]byte, sep []byte) []byte {
if len(a) == 0 {
return []byte{}
}
if len(a) == 1 {
return a[0]
}
n := len(sep) * (len(a) - 1)
for i := 0; i < len(a); i++ {
n += len(a[i])
}
b := make([]byte, n)
bp := copy(b, a[0])
for _, s := range a[1:] {
bp += copy(b[bp:], sep)
bp += copy(b[bp:], s)
}
return b
}
// HasPrefix tests whether the byte array 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 array 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 array 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 array 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 {
if nbytes+utf8.RuneLen(r) > 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 := 0
for i := 0; i < count; i++ {
for j := 0; j < len(b); j++ {
nb[bp] = b[j]
bp++
}
}
return nb
}
// ToUpper returns a copy of the byte array s with all Unicode letters mapped to their upper case.
func ToUpper(s []byte) []byte { return Map(unicode.ToUpper, s) }
// ToUpper returns a copy of the byte array 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 array 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 array 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 array 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 array 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)
}
// BUG(r): The rule Title uses for word boundaries does not handle Unicode punctuation properly.
// Title returns a copy of s with all Unicode letters that begin words
// mapped to their title case.
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)
}
// IndexFunc interprets s as a sequence of UTF-8-encoded Unicode code points.
// 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)
}
// LastIndexFunc interprets s as a sequence of UTF-8-encoded Unicode code points.
// 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; {
r, size := utf8.DecodeLastRune(s[0:i])
i -= size
if f(r) == truth {
return i
}
}
return -1
}
func makeCutsetFunc(cutset string) func(r rune) bool {
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
// trailing UTF-8-encoded Unicode code points contained in cutset.
func Trim(s []byte, cutset string) []byte {
return TrimFunc(s, makeCutsetFunc(cutset))
}
// TrimLeft returns a subslice of s by slicing off all leading
// UTF-8-encoded Unicode code points contained in cutset.
func TrimLeft(s []byte, cutset string) []byte {
return TrimLeftFunc(s, makeCutsetFunc(cutset))
}
// TrimRight returns a subslice of s by slicing off all trailing
// UTF-8-encoded Unicode code points that are contained in cutset.
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)
}
// Runes returns a slice of runes (Unicode code points) equivalent to s.
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.
// 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 {
// Nothing to do. Just copy.
t := make([]byte, len(s))
copy(t, s)
return t
}
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
}
// General case. SimpleFold(x) returns the next equivalent rune > x
// 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
}
// One string is empty. Are both?
return len(s) == len(t)
}