go/tagengine/sanitize/sanitize.go
2024-11-11 06:36:55 +01:00

92 lines
1.4 KiB
Go

package sanitize
import (
"strings"
"unicode"
)
func SpaceNumbers(s string) string {
if len(s) == 0 {
return s
}
isDigit := func(b rune) bool {
switch b {
case '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
return true
}
return false
}
b := strings.Builder{}
var first rune
for _, c := range s {
first = c
break
}
digit := isDigit(first)
// Range over runes.
for _, c := range s {
thisDigit := isDigit(c)
if thisDigit != digit {
b.WriteByte(' ')
digit = thisDigit
}
b.WriteRune(c)
}
return b.String()
}
func SpacePunctuation(s string) string {
needsSpace := func(r rune) bool {
switch r {
case '`', '~', '!', '@', '#', '%', '^', '&', '*', '(', ')',
'-', '_', '+', '=', '[', '{', ']', '}', '\\', '|',
':', ';', '"', '\'', ',', '<', '.', '>', '?', '/':
return true
}
return false
}
b := strings.Builder{}
// Range over runes.
for _, r := range s {
if needsSpace(r) {
b.WriteRune(' ')
b.WriteRune(r)
b.WriteRune(' ')
} else {
b.WriteRune(r)
}
}
return b.String()
}
func CollapseSpaces(s string) string {
// Trim leading and trailing spaces.
s = strings.TrimSpace(s)
b := strings.Builder{}
wasSpace := false
// Range over runes.
for _, c := range s {
if unicode.IsSpace(c) {
wasSpace = true
continue
} else if wasSpace {
wasSpace = false
b.WriteRune(' ')
}
b.WriteRune(c)
}
return b.String()
}