1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
|
// 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.
// A package of simple functions to manipulate arrays of bytes.
// Analagous to the facilities of the strings package.
package bytes
import (
"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 {
for i := 0; i < len(a) && i < len(b); i++ {
switch {
case a[i] > b[i]:
return 1
case a[i] < b[i]:
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 {
if len(a) != len(b) {
return false
}
for i := 0; i < len(a); i++ {
if a[i] != b[i] {
return false
}
}
return true
}
// Copy copies bytes from src to dst,
// stopping when either all of src has been copied
// or all of dst has been filled.
// It returns the number of bytes copied.
func Copy(dst, src []byte) int {
if len(src) > len(dst) {
src = src[0:len(dst)];
}
for i, x := range src {
dst[i] = x
}
return len(src)
}
// 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:len(s)];
na++;
}
return a[0:na]
}
// Count counts the number of non-overlapping instances of sep in s.
func Count(s, sep []byte) int {
if len(sep) == 0 {
return utf8.RuneCount(s)+1
}
c := sep[0];
n := 0;
for i := 0; i+len(sep) <= len(s); i++ {
if s[i] == c && (len(sep) == 1 || Equal(s[i:i+len(sep)], sep)) {
n++;
i += len(sep)-1
}
}
return n
}
// 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
}
c := sep[0];
for i := 0; i+n <= len(s); i++ {
if s[i] == c && (n == 1 || Equal(s[i:i+n], sep)) {
return i
}
}
return -1
}
// 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.
func Split(s, sep []byte, n int) [][]byte {
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];
na++;
start = i+len(sep);
i += len(sep)-1;
}
}
a[na] = s[start:len(s)];
return a[0:na+1]
}
// 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 := 0;
for i := 0; i < len(a); i++ {
s := a[i];
for j := 0; j < len(s); j++ {
b[bp] = s[j];
bp++
}
if i + 1 < len(a) {
s = sep;
for j := 0; j < len(s); j++ {
b[bp] = s[j];
bp++
}
}
}
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):len(s)], suffix)
}
// 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
nbytes := 0; // number of bytes encoded in b
b := make([]byte, maxbytes);
for i := 0; i < len(s); {
wid := 1;
rune := int(s[i]);
if rune < utf8.RuneSelf {
rune = mapping(rune);
} else {
rune, wid = utf8.DecodeRune(s[i:len(s)]);
}
rune = mapping(rune);
if nbytes + utf8.RuneLen(rune) > maxbytes {
// Grow the buffer.
maxbytes = maxbytes*2 + utf8.UTFMax;
nb := make([]byte, maxbytes);
for i, c := range b[0:nbytes] {
nb[i] = c
}
b = nb;
}
nbytes += utf8.EncodeRune(rune, b[nbytes:maxbytes]);
i += wid;
}
return b[0:nbytes];
}
// 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 Title(s []byte) []byte {
return Map(unicode.ToTitle, s)
}
// 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);
for start < end {
wid := 1;
rune := int(s[start]);
if rune >= utf8.RuneSelf {
rune, wid = utf8.DecodeRune(s[start:end])
}
if !unicode.IsSpace(rune) {
break;
}
start += wid;
}
for start < end {
wid := 1;
rune := int(s[end-1]);
if rune >= utf8.RuneSelf {
// Back up carefully looking for beginning of rune. Mustn't pass start.
for wid = 2; start <= end-wid && !utf8.RuneStart(s[end-wid]); wid++ {
}
if start > end-wid { // invalid UTF-8 sequence; stop processing
return s[start:end]
}
rune, wid = utf8.DecodeRune(s[end-wid:end]);
}
if !unicode.IsSpace(rune) {
break;
}
end -= wid;
}
return s[start:end];
}
// 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 {
n = 16
}
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);
if lens + lent <= cap(s) {
s = s[0:lens+lent];
} else {
news := make([]byte, lens+lent, resize(lens+lent));
Copy(news, s);
s = news;
}
Copy(s[lens:lens+lent], t);
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);
if lens + 1 <= cap(s) {
s = s[0:lens+1];
} else {
news := make([]byte, lens+1, resize(lens+1));
Copy(news, s);
s = news;
}
s[lens] = t;
return s;
}
|