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
|
// Copyright 2015 Huan Du. All rights reserved.
// Licensed under the MIT license that can be found in the LICENSE file.
package xstrings
import (
"strings"
"unicode/utf8"
)
// Reverse a utf8 encoded string.
func Reverse(str string) string {
var size int
tail := len(str)
buf := make([]byte, tail)
s := buf
for len(str) > 0 {
_, size = utf8.DecodeRuneInString(str)
tail -= size
s = append(s[:tail], []byte(str[:size])...)
str = str[size:]
}
return string(buf)
}
// Slice a string by rune.
//
// Start must satisfy 0 <= start <= rune length.
//
// End can be positive, zero or negative.
// If end >= 0, start and end must satisfy start <= end <= rune length.
// If end < 0, it means slice to the end of string.
//
// Otherwise, Slice will panic as out of range.
func Slice(str string, start, end int) string {
var size, startPos, endPos int
origin := str
if start < 0 || end > len(str) || (end >= 0 && start > end) {
panic("out of range")
}
if end >= 0 {
end -= start
}
for start > 0 && len(str) > 0 {
_, size = utf8.DecodeRuneInString(str)
start--
startPos += size
str = str[size:]
}
if end < 0 {
return origin[startPos:]
}
endPos = startPos
for end > 0 && len(str) > 0 {
_, size = utf8.DecodeRuneInString(str)
end--
endPos += size
str = str[size:]
}
if len(str) == 0 && (start > 0 || end > 0) {
panic("out of range")
}
return origin[startPos:endPos]
}
// Partition splits a string by sep into three parts.
// The return value is a slice of strings with head, match and tail.
//
// If str contains sep, for example "hello" and "l", Partition returns
// "he", "l", "lo"
//
// If str doesn't contain sep, for example "hello" and "x", Partition returns
// "hello", "", ""
func Partition(str, sep string) (head, match, tail string) {
index := strings.Index(str, sep)
if index == -1 {
head = str
return
}
head = str[:index]
match = str[index : index+len(sep)]
tail = str[index+len(sep):]
return
}
// LastPartition splits a string by last instance of sep into three parts.
// The return value is a slice of strings with head, match and tail.
//
// If str contains sep, for example "hello" and "l", LastPartition returns
// "hel", "l", "o"
//
// If str doesn't contain sep, for example "hello" and "x", LastPartition returns
// "", "", "hello"
func LastPartition(str, sep string) (head, match, tail string) {
index := strings.LastIndex(str, sep)
if index == -1 {
tail = str
return
}
head = str[:index]
match = str[index : index+len(sep)]
tail = str[index+len(sep):]
return
}
// Insert src into dst at given rune index.
// Index is counted by runes instead of bytes.
//
// If index is out of range of dst, panic with out of range.
func Insert(dst, src string, index int) string {
return Slice(dst, 0, index) + src + Slice(dst, index, -1)
}
// Scrub scrubs invalid utf8 bytes with repl string.
// Adjacent invalid bytes are replaced only once.
func Scrub(str, repl string) string {
var buf *stringBuilder
var r rune
var size, pos int
var hasError bool
origin := str
for len(str) > 0 {
r, size = utf8.DecodeRuneInString(str)
if r == utf8.RuneError {
if !hasError {
if buf == nil {
buf = &stringBuilder{}
}
buf.WriteString(origin[:pos])
hasError = true
}
} else if hasError {
hasError = false
buf.WriteString(repl)
origin = origin[pos:]
pos = 0
}
pos += size
str = str[size:]
}
if buf != nil {
buf.WriteString(origin)
return buf.String()
}
// No invalid byte.
return origin
}
// WordSplit splits a string into words. Returns a slice of words.
// If there is no word in a string, return nil.
//
// Word is defined as a locale dependent string containing alphabetic characters,
// which may also contain but not start with `'` and `-` characters.
func WordSplit(str string) []string {
var word string
var words []string
var r rune
var size, pos int
inWord := false
for len(str) > 0 {
r, size = utf8.DecodeRuneInString(str)
switch {
case isAlphabet(r):
if !inWord {
inWord = true
word = str
pos = 0
}
case inWord && (r == '\'' || r == '-'):
// Still in word.
default:
if inWord {
inWord = false
words = append(words, word[:pos])
}
}
pos += size
str = str[size:]
}
if inWord {
words = append(words, word[:pos])
}
return words
}
|
