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
|
// 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 strings.
package strings
import (
"unicode"
"utf8"
)
// explode splits s into an array of UTF-8 sequences, one per Unicode character (still strings) up to a maximum of n (n <= 0 means no limit).
// Invalid UTF-8 sequences become correct encodings of U+FFF8.
func explode(s string, n int) []string {
if n <= 0 {
n = len(s)
}
a := make([]string, n)
var size, rune int
na := 0
for len(s) > 0 {
if na+1 >= n {
a[na] = s
na++
break
}
rune, size = utf8.DecodeRuneInString(s)
s = s[size:]
a[na] = string(rune)
na++
}
return a[0:na]
}
// Count counts the number of non-overlapping instances of sep in s.
func Count(s, sep string) int {
if sep == "" {
return utf8.RuneCountInString(s) + 1
}
c := sep[0]
n := 0
for i := 0; i+len(sep) <= len(s); i++ {
if s[i] == c && (len(sep) == 1 || 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 string) int {
n := len(sep)
if n == 0 {
return 0
}
c := sep[0]
if n == 1 {
// special case worth making fast
for i := 0; i < len(s); i++ {
if s[i] == c {
return i
}
}
return -1
}
// n > 1
for i := 0; i+n <= len(s); i++ {
if s[i] == c && s[i:i+n] == sep {
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 string) int {
n := len(sep)
if n == 0 {
return len(s)
}
c := sep[0]
if n == 1 {
// special case worth making fast
for i := len(s) - 1; i >= 0; i-- {
if s[i] == c {
return i
}
}
return -1
}
// n > 1
for i := len(s) - n; i >= 0; i-- {
if s[i] == c && s[i:i+n] == sep {
return i
}
}
return -1
}
// Generic split: splits after each instance of sep,
// including sepSave bytes of sep in the subarrays.
func genSplit(s, sep string, sepSave, n int) []string {
if sep == "" {
return explode(s, n)
}
if n <= 0 {
n = Count(s, sep) + 1
}
c := sep[0]
start := 0
a := make([]string, n)
na := 0
for i := 0; i+len(sep) <= len(s) && na+1 < n; i++ {
if s[i] == c && (len(sep) == 1 || 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]
}
// Split splits the string s around each instance of sep, returning an array of substrings of s.
// If sep is empty, Split splits s after each UTF-8 sequence.
// If n > 0, Split splits s into at most n substrings; the last substring will be the unsplit remainder.
func Split(s, sep string, n int) []string { return genSplit(s, sep, 0, n) }
// SplitAfter splits the string s after each instance of sep, returning an array of substrings of s.
// If sep is empty, SplitAfter splits s after each UTF-8 sequence.
// If n > 0, SplitAfter splits s into at most n substrings; the last substring will be the unsplit remainder.
func SplitAfter(s, sep string, n int) []string {
return genSplit(s, sep, len(sep), n)
}
// Fields splits the string s around each instance of one or more consecutive white space
// characters, returning an array of substrings of s or an empty list if s contains only white space.
func Fields(s string) []string {
n := 0
inField := false
for _, rune := range s {
wasInField := inField
inField = !unicode.IsSpace(rune)
if inField && !wasInField {
n++
}
}
a := make([]string, n)
na := 0
fieldStart := -1
for i, rune := range s {
if unicode.IsSpace(rune) {
if fieldStart >= 0 {
a[na] = s[fieldStart:i]
na++
fieldStart = -1
}
} else if fieldStart == -1 {
fieldStart = i
}
}
if fieldStart != -1 {
a[na] = s[fieldStart:]
na++
}
return a[0:na]
}
// Join concatenates the elements of a to create a single string. The separator string
// sep is placed between elements in the resulting string.
func Join(a []string, sep string) string {
if len(a) == 0 {
return ""
}
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 string(b)
}
// HasPrefix tests whether the string s begins with prefix.
func HasPrefix(s, prefix string) bool {
return len(s) >= len(prefix) && s[0:len(prefix)] == prefix
}
// HasSuffix tests whether the string s ends with suffix.
func HasSuffix(s, suffix string) bool {
return len(s) >= len(suffix) && s[len(s)-len(suffix):] == suffix
}
// Map returns a copy of the string 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.
func Map(mapping func(rune int) int, s string) string {
// In the worst case, the string 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 _, c := range s {
rune := mapping(c)
if rune >= 0 {
wid := 1
if rune >= utf8.RuneSelf {
wid = utf8.RuneLen(rune)
}
if nbytes+wid > 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])
}
}
return string(b[0:nbytes])
}
// Repeat returns a new string consisting of count copies of the string s.
func Repeat(s string, count int) string {
b := make([]byte, len(s)*count)
bp := 0
for i := 0; i < count; i++ {
for j := 0; j < len(s); j++ {
b[bp] = s[j]
bp++
}
}
return string(b)
}
// ToUpper returns a copy of the string s with all Unicode letters mapped to their upper case.
func ToUpper(s string) string { return Map(unicode.ToUpper, s) }
// ToLower returns a copy of the string s with all Unicode letters mapped to their lower case.
func ToLower(s string) string { return Map(unicode.ToLower, s) }
// ToTitle returns a copy of the string s with all Unicode letters mapped to their title case.
func ToTitle(s string) string { 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 string) string {
start, end := 0, len(s)
for start < end {
wid := 1
rune := int(s[start])
if rune >= utf8.RuneSelf {
rune, wid = utf8.DecodeRuneInString(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.DecodeRuneInString(s[end-wid : end])
}
if !unicode.IsSpace(rune) {
break
}
end -= wid
}
return s[start:end]
}
|