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
|
// 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 "utf8"
// Explode splits s into an array of UTF-8 sequences, one per Unicode character (still strings).
// Invalid UTF-8 sequences become correct encodings of U+FFF8.
func Explode(s string) []string {
a := make([]string, utf8.RuneCountInString(s));
var size, rune int;
i := 0;
for len(s) > 0 {
rune, size = utf8.DecodeRuneInString(s);
s = s[size:len(s)];
a[i] = string(rune);
i++;
}
return a
}
// 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];
for i := 0; i+n <= len(s); i++ {
if s[i] == c && (n == 1 || s[i:i+n] == sep) {
return i
}
}
return -1
}
// Split returns the array representing the substrings of s separated by string sep. Adjacent
// occurrences of sep produce empty substrings. If sep is empty, it is the same as Explode.
func Split(s, sep string) []string {
if sep == "" {
return Explode(s)
}
c := sep[0];
start := 0;
n := Count(s, sep)+1;
a := make([]string, n);
na := 0;
for i := 0; i+len(sep) <= len(s); i++ {
if s[i] == c && (len(sep) == 1 || 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
}
// 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):len(s)] == suffix
}
// Upper returns a copy of the string s, with all low ASCII lowercase letters
// converted to uppercase.
// TODO: full Unicode support
func UpperASCII(s string) string {
// Note, we can work byte-by-byte because UTF-8 multibyte characters
// don't use any low ASCII byte values.
b := make([]byte, len(s));
for i := 0; i < len(s); i++ {
c := s[i];
if 'a' <= c && c <= 'z' {
c -= 'a' - 'A';
}
b[i] = c;
}
return string(b);
}
// Upper returns a copy of the string s, with all low ASCII lowercase letters
// converted to lowercase.
// TODO: full Unicode support
func LowerASCII(s string) string {
// Note, we can work byte-by-byte because UTF-8 multibyte characters
// don't use any low ASCII byte values.
b := make([]byte, len(s));
for i := 0; i < len(s); i++ {
c := s[i];
if 'A' <= c && c <= 'Z' {
c += 'a' - 'A';
}
b[i] = c;
}
return string(b);
}
func isWhitespaceASCII(c byte) bool {
switch int(c) {
case ' ', '\t', '\r', '\n':
return true;
}
return false;
}
// Trim returns a slice of the string s, with all leading and trailing whitespace
// removed. "Whitespace" for now defined as space, tab, CR, or LF.
// TODO: full Unicode whitespace support (need a unicode.IsWhitespace method)
func TrimSpaceASCII(s string) string {
// Note, we can work byte-by-byte because UTF-8 multibyte characters
// don't use any low ASCII byte values.
start, end := 0, len(s);
for start < end && isWhitespaceASCII(s[start]) {
start++;
}
for start < end && isWhitespaceASCII(s[end-1]) {
end--;
}
return s[start:end];
}
|
