-
-
Notifications
You must be signed in to change notification settings - Fork 14
/
Copy pathstringsx.go
68 lines (60 loc) · 1.5 KB
/
stringsx.go
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
package stringsx
import (
"strings"
"unicode"
"unicode/utf8"
)
// Clean removes non-graphic characters from the given string.
// Removable characters are the ones for which [unicode.IsGraphic] returns false.
//
// For details, see https://stackoverflow.com/a/58994297/1705598
func Clean(s string) string {
return strings.Map(func(r rune) rune {
if unicode.IsGraphic(r) {
return r
}
return -1
}, s)
}
// LimitRunes returns a slice of s that contains at most the given number of runes.
// If n is 0 or negative, the empty string is returned.
// If s has less runes than n, s is returned.
//
// Each byte of invalid UTF-8 sequences count as one when counting the limit, e.g.
//
// LimitRunes("\xff\xffab", 3) // returns "\xff\xffa"
func LimitRunes(s string, n int) string {
if n <= 0 || s == "" {
return ""
}
// Quick check: if byte-length is not greater than n, number of runes will also be not greater:
if len(s) <= n {
return s
}
for i := range s {
n--
if n == -1 {
return s[:i]
}
}
// s has n or less runes
return s
}
// SplitQuotes splits the given string by sep.
// If sep appears inside quotes, it is skipped.
// Quotes are not removed from the parts.
func SplitQuotes(s string, sep, quote rune) (parts []string) {
sepLen := utf8.RuneLen(sep)
start, inQuotes := 0, false
for i, r := range s {
if r == sep && !inQuotes {
parts = append(parts, s[start:i])
start = i + sepLen
continue
}
if r == quote {
inQuotes = !inQuotes
}
}
return append(parts, s[start:])
}