2009-06-04 15:41:31 -06:00
|
|
|
// 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.
|
|
|
|
|
2009-11-10 11:55:53 -07:00
|
|
|
// The bytes package implements functions for the manipulation of byte slices.
|
2009-06-04 15:41:31 -06:00
|
|
|
// Analagous to the facilities of the strings package.
|
|
|
|
package bytes
|
|
|
|
|
2009-09-01 14:46:59 -06:00
|
|
|
import (
|
|
|
|
"unicode";
|
|
|
|
"utf8";
|
|
|
|
)
|
2009-06-04 15:41:31 -06:00
|
|
|
|
|
|
|
// 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 {
|
|
|
|
for i := 0; i < len(a) && i < len(b); i++ {
|
|
|
|
switch {
|
|
|
|
case a[i] > b[i]:
|
2009-11-09 13:07:39 -07:00
|
|
|
return 1
|
2009-06-04 15:41:31 -06:00
|
|
|
case a[i] < b[i]:
|
2009-11-09 13:07:39 -07:00
|
|
|
return -1
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
switch {
|
|
|
|
case len(a) < len(b):
|
2009-11-09 13:07:39 -07:00
|
|
|
return -1
|
2009-06-04 15:41:31 -06:00
|
|
|
case len(a) > len(b):
|
2009-11-09 13:07:39 -07:00
|
|
|
return 1
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
return 0;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
// Equal returns a boolean reporting whether a == b.
|
|
|
|
func Equal(a, b []byte) bool {
|
|
|
|
if len(a) != len(b) {
|
2009-11-09 13:07:39 -07:00
|
|
|
return false
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
for i := 0; i < len(a); i++ {
|
|
|
|
if a[i] != b[i] {
|
2009-11-09 13:07:39 -07:00
|
|
|
return false
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
return true;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
2009-06-24 20:02:29 -06:00
|
|
|
// 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 {
|
2009-11-09 13:07:39 -07:00
|
|
|
n = len(s)
|
2009-06-24 20:02:29 -06:00
|
|
|
}
|
|
|
|
a := make([][]byte, n);
|
2009-09-14 18:20:29 -06:00
|
|
|
var size int;
|
2009-06-24 20:02:29 -06:00
|
|
|
na := 0;
|
2009-06-04 15:41:31 -06:00
|
|
|
for len(s) > 0 {
|
2009-06-24 20:02:29 -06:00
|
|
|
if na+1 >= n {
|
|
|
|
a[na] = s;
|
|
|
|
na++;
|
2009-10-06 15:55:39 -06:00
|
|
|
break;
|
2009-06-24 20:02:29 -06:00
|
|
|
}
|
2009-09-14 18:20:29 -06:00
|
|
|
_, size = utf8.DecodeRune(s);
|
2009-06-24 20:02:29 -06:00
|
|
|
a[na] = s[0:size];
|
2009-11-20 12:45:05 -07:00
|
|
|
s = s[size:];
|
2009-06-24 20:02:29 -06:00
|
|
|
na++;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
return a[0:na];
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
// Count counts the number of non-overlapping instances of sep in s.
|
|
|
|
func Count(s, sep []byte) int {
|
|
|
|
if len(sep) == 0 {
|
2009-11-09 13:07:39 -07:00
|
|
|
return utf8.RuneCount(s) + 1
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
c := sep[0];
|
|
|
|
n := 0;
|
|
|
|
for i := 0; i+len(sep) <= len(s); i++ {
|
2009-11-09 22:09:34 -07:00
|
|
|
if s[i] == c && (len(sep) == 1 || Equal(s[i:i+len(sep)], sep)) {
|
2009-06-04 15:41:31 -06:00
|
|
|
n++;
|
2009-11-09 22:09:34 -07:00
|
|
|
i += len(sep) - 1;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
return n;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
// 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 {
|
2009-11-09 13:07:39 -07:00
|
|
|
return 0
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
c := sep[0];
|
|
|
|
for i := 0; i+n <= len(s); i++ {
|
2009-11-09 22:09:34 -07:00
|
|
|
if s[i] == c && (n == 1 || Equal(s[i:i+n], sep)) {
|
2009-11-09 13:07:39 -07:00
|
|
|
return i
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
return -1;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
2009-11-18 20:23:08 -07:00
|
|
|
// IndexByte returns the index of the first instance of c in s, or -1 if c is not present in s.
|
2009-12-04 11:23:43 -07:00
|
|
|
func IndexByte(s []byte, c byte) int // asm_$GOARCH.s
|
|
|
|
|
|
|
|
func indexBytePortable(s []byte, c byte) int {
|
2009-11-18 20:23:08 -07:00
|
|
|
for i, b := range s {
|
|
|
|
if b == c {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2009-10-12 11:09:35 -06:00
|
|
|
// 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 {
|
2009-11-09 13:07:39 -07:00
|
|
|
return len(s)
|
2009-10-12 11:09:35 -06:00
|
|
|
}
|
|
|
|
c := sep[0];
|
2009-11-09 22:09:34 -07:00
|
|
|
for i := len(s) - n; i >= 0; i-- {
|
|
|
|
if s[i] == c && (n == 1 || Equal(s[i:i+n], sep)) {
|
2009-11-09 13:07:39 -07:00
|
|
|
return i
|
2009-10-12 11:09:35 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2009-11-04 16:19:30 -07:00
|
|
|
// 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 {
|
2009-06-04 15:41:31 -06:00
|
|
|
if len(sep) == 0 {
|
2009-11-09 13:07:39 -07:00
|
|
|
return explode(s, n)
|
2009-06-24 20:02:29 -06:00
|
|
|
}
|
|
|
|
if n <= 0 {
|
2009-11-09 13:07:39 -07:00
|
|
|
n = Count(s, sep) + 1
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
c := sep[0];
|
|
|
|
start := 0;
|
|
|
|
a := make([][]byte, n);
|
|
|
|
na := 0;
|
2009-06-24 20:02:29 -06:00
|
|
|
for i := 0; i+len(sep) <= len(s) && na+1 < n; i++ {
|
2009-11-09 22:09:34 -07:00
|
|
|
if s[i] == c && (len(sep) == 1 || Equal(s[i:i+len(sep)], sep)) {
|
2009-11-04 17:49:28 -07:00
|
|
|
a[na] = s[start : i+sepSave];
|
2009-06-04 15:41:31 -06:00
|
|
|
na++;
|
2009-11-09 22:09:34 -07:00
|
|
|
start = i + len(sep);
|
|
|
|
i += len(sep) - 1;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
}
|
2009-11-20 12:45:05 -07:00
|
|
|
a[na] = s[start:];
|
2009-10-06 15:55:39 -06:00
|
|
|
return a[0 : na+1];
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
2009-11-04 16:19:30 -07:00
|
|
|
// Split splits the array s around each instance of sep, returning an array of subarrays of s.
|
|
|
|
// If sep is empty, Split splits s after each UTF-8 sequence.
|
|
|
|
// If n > 0, Split splits s into at most n subarrays; the last subarray will contain an unsplit remainder.
|
2009-11-06 15:24:38 -07:00
|
|
|
func Split(s, sep []byte, n int) [][]byte { return genSplit(s, sep, 0, n) }
|
2009-11-04 16:19:30 -07:00
|
|
|
|
|
|
|
// SplitAfter splits the array s after each instance of sep, returning an array of subarrays of s.
|
|
|
|
// If sep is empty, SplitAfter splits s after each UTF-8 sequence.
|
|
|
|
// If n > 0, SplitAfter splits s into at most n subarrays; the last subarray will contain an
|
|
|
|
// unsplit remainder.
|
|
|
|
func SplitAfter(s, sep []byte, n int) [][]byte {
|
2009-11-09 13:07:39 -07:00
|
|
|
return genSplit(s, sep, len(sep), n)
|
2009-11-04 16:19:30 -07:00
|
|
|
}
|
|
|
|
|
2009-06-04 15:41:31 -06:00
|
|
|
// 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 {
|
2009-11-09 13:07:39 -07:00
|
|
|
return []byte{}
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
if len(a) == 1 {
|
2009-11-09 13:07:39 -07:00
|
|
|
return a[0]
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
2009-11-09 22:09:34 -07:00
|
|
|
n := len(sep) * (len(a) - 1);
|
2009-06-04 15:41:31 -06:00
|
|
|
for i := 0; i < len(a); i++ {
|
2009-11-09 13:07:39 -07:00
|
|
|
n += len(a[i])
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
b := make([]byte, n);
|
|
|
|
bp := 0;
|
|
|
|
for i := 0; i < len(a); i++ {
|
|
|
|
s := a[i];
|
|
|
|
for j := 0; j < len(s); j++ {
|
|
|
|
b[bp] = s[j];
|
2009-10-06 15:55:39 -06:00
|
|
|
bp++;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
if i+1 < len(a) {
|
2009-06-04 15:41:31 -06:00
|
|
|
s = sep;
|
|
|
|
for j := 0; j < len(s); j++ {
|
|
|
|
b[bp] = s[j];
|
2009-10-06 15:55:39 -06:00
|
|
|
bp++;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
return b;
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
// HasPrefix tests whether the byte array s begins with prefix.
|
|
|
|
func HasPrefix(s, prefix []byte) bool {
|
2009-11-09 13:07:39 -07:00
|
|
|
return len(s) >= len(prefix) && Equal(s[0:len(prefix)], prefix)
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
// HasSuffix tests whether the byte array s ends with suffix.
|
|
|
|
func HasSuffix(s, suffix []byte) bool {
|
2009-11-20 12:45:05 -07:00
|
|
|
return len(s) >= len(suffix) && Equal(s[len(s)-len(suffix):], suffix)
|
2009-06-04 15:41:31 -06:00
|
|
|
}
|
2009-09-01 14:46:59 -06:00
|
|
|
|
|
|
|
// Map returns a copy of the byte array s with all its characters modified
|
|
|
|
// according to the mapping function.
|
|
|
|
func Map(mapping func(rune int) int, 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
|
2009-10-06 15:55:39 -06:00
|
|
|
nbytes := 0; // number of bytes encoded in b
|
2009-09-01 14:46:59 -06:00
|
|
|
b := make([]byte, maxbytes);
|
2009-09-15 10:41:59 -06:00
|
|
|
for i := 0; i < len(s); {
|
|
|
|
wid := 1;
|
2009-09-01 14:46:59 -06:00
|
|
|
rune := int(s[i]);
|
2009-11-15 13:07:27 -07:00
|
|
|
if rune >= utf8.RuneSelf {
|
2009-11-20 12:45:05 -07:00
|
|
|
rune, wid = utf8.DecodeRune(s[i:])
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
|
|
|
rune = mapping(rune);
|
2009-11-09 22:09:34 -07:00
|
|
|
if nbytes+utf8.RuneLen(rune) > maxbytes {
|
2009-09-01 14:46:59 -06:00
|
|
|
// Grow the buffer.
|
|
|
|
maxbytes = maxbytes*2 + utf8.UTFMax;
|
|
|
|
nb := make([]byte, maxbytes);
|
|
|
|
for i, c := range b[0:nbytes] {
|
2009-11-09 13:07:39 -07:00
|
|
|
nb[i] = c
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
|
|
|
b = nb;
|
|
|
|
}
|
|
|
|
nbytes += utf8.EncodeRune(rune, b[nbytes:maxbytes]);
|
2009-09-15 10:41:59 -06:00
|
|
|
i += wid;
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
|
|
|
return b[0:nbytes];
|
|
|
|
}
|
|
|
|
|
2009-11-16 13:40:01 -07:00
|
|
|
// Repeat returns a new byte array 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;
|
|
|
|
}
|
|
|
|
|
2009-09-01 14:46:59 -06:00
|
|
|
// ToUpper returns a copy of the byte array s with all Unicode letters mapped to their upper case.
|
2009-11-06 15:24:38 -07:00
|
|
|
func ToUpper(s []byte) []byte { return Map(unicode.ToUpper, s) }
|
2009-09-01 14:46:59 -06:00
|
|
|
|
|
|
|
// ToUpper returns a copy of the byte array s with all Unicode letters mapped to their lower case.
|
2009-11-06 15:24:38 -07:00
|
|
|
func ToLower(s []byte) []byte { return Map(unicode.ToLower, s) }
|
2009-09-01 14:46:59 -06:00
|
|
|
|
|
|
|
// ToTitle returns a copy of the byte array s with all Unicode letters mapped to their title case.
|
2009-11-06 15:24:38 -07:00
|
|
|
func ToTitle(s []byte) []byte { return Map(unicode.ToTitle, s) }
|
2009-09-01 14:46:59 -06:00
|
|
|
|
|
|
|
// Trim returns a slice of the string s, with all leading and trailing white space
|
|
|
|
// removed, as defined by Unicode.
|
|
|
|
func TrimSpace(s []byte) []byte {
|
|
|
|
start, end := 0, len(s);
|
2009-09-15 10:41:59 -06:00
|
|
|
for start < end {
|
|
|
|
wid := 1;
|
2009-09-01 14:46:59 -06:00
|
|
|
rune := int(s[start]);
|
|
|
|
if rune >= utf8.RuneSelf {
|
2009-11-09 13:07:39 -07:00
|
|
|
rune, wid = utf8.DecodeRune(s[start:end])
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
|
|
|
if !unicode.IsSpace(rune) {
|
2009-11-09 13:07:39 -07:00
|
|
|
break
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
2009-09-15 10:41:59 -06:00
|
|
|
start += wid;
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
2009-09-15 10:41:59 -06:00
|
|
|
for start < end {
|
|
|
|
wid := 1;
|
2009-09-01 14:46:59 -06:00
|
|
|
rune := int(s[end-1]);
|
|
|
|
if rune >= utf8.RuneSelf {
|
|
|
|
// Back up carefully looking for beginning of rune. Mustn't pass start.
|
2009-11-04 17:49:28 -07:00
|
|
|
for wid = 2; start <= end-wid && !utf8.RuneStart(s[end-wid]); wid++ {
|
|
|
|
}
|
2009-09-01 14:46:59 -06:00
|
|
|
if start > end-wid { // invalid UTF-8 sequence; stop processing
|
2009-11-09 13:07:39 -07:00
|
|
|
return s[start:end]
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
2009-10-06 15:55:39 -06:00
|
|
|
rune, wid = utf8.DecodeRune(s[end-wid : end]);
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
|
|
|
if !unicode.IsSpace(rune) {
|
2009-11-09 13:07:39 -07:00
|
|
|
break
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
2009-09-15 10:41:59 -06:00
|
|
|
end -= wid;
|
2009-09-01 14:46:59 -06:00
|
|
|
}
|
|
|
|
return s[start:end];
|
|
|
|
}
|
2009-09-13 22:35:18 -06:00
|
|
|
|
|
|
|
// How big to make a byte array when growing.
|
|
|
|
// Heuristic: Scale by 50% to give n log n time.
|
|
|
|
func resize(n int) int {
|
|
|
|
if n < 16 {
|
2009-11-09 13:07:39 -07:00
|
|
|
n = 16
|
2009-09-13 22:35:18 -06:00
|
|
|
}
|
|
|
|
return n + n/2;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Add appends the contents of t to the end of s and returns the result.
|
|
|
|
// If s has enough capacity, it is extended in place; otherwise a
|
|
|
|
// new array is allocated and returned.
|
|
|
|
func Add(s, t []byte) []byte {
|
|
|
|
lens := len(s);
|
|
|
|
lent := len(t);
|
2009-10-06 15:55:39 -06:00
|
|
|
if lens+lent <= cap(s) {
|
2009-11-09 13:07:39 -07:00
|
|
|
s = s[0 : lens+lent]
|
2009-09-13 22:35:18 -06:00
|
|
|
} else {
|
|
|
|
news := make([]byte, lens+lent, resize(lens+lent));
|
2009-11-18 16:24:24 -07:00
|
|
|
copy(news, s);
|
2009-09-13 22:35:18 -06:00
|
|
|
s = news;
|
|
|
|
}
|
2009-11-18 16:24:24 -07:00
|
|
|
copy(s[lens:lens+lent], t);
|
2009-09-13 22:35:18 -06:00
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
// AddByte appends byte b to the end of s and returns the result.
|
|
|
|
// If s has enough capacity, it is extended in place; otherwise a
|
|
|
|
// new array is allocated and returned.
|
|
|
|
func AddByte(s []byte, t byte) []byte {
|
|
|
|
lens := len(s);
|
2009-10-06 15:55:39 -06:00
|
|
|
if lens+1 <= cap(s) {
|
2009-11-09 13:07:39 -07:00
|
|
|
s = s[0 : lens+1]
|
2009-09-13 22:35:18 -06:00
|
|
|
} else {
|
|
|
|
news := make([]byte, lens+1, resize(lens+1));
|
2009-11-18 16:24:24 -07:00
|
|
|
copy(news, s);
|
2009-09-13 22:35:18 -06:00
|
|
|
s = news;
|
|
|
|
}
|
|
|
|
s[lens] = t;
|
|
|
|
return s;
|
|
|
|
}
|
2009-12-02 21:47:38 -07:00
|
|
|
|
|
|
|
// Runes returns a slice of runes (Unicode code points) equivalent to s.
|
|
|
|
func Runes(s []byte) []int {
|
|
|
|
t := make([]int, utf8.RuneCount(s));
|
|
|
|
i := 0;
|
|
|
|
for len(s) > 0 {
|
|
|
|
r, l := utf8.DecodeRune(s);
|
|
|
|
t[i] = r;
|
|
|
|
i++;
|
|
|
|
s = s[l:];
|
|
|
|
}
|
|
|
|
return t;
|
|
|
|
}
|