photoprism/pkg/txt/separator.go

30 lines
626 B
Go

package txt
import (
"unicode"
)
// isSeparator reports whether the rune could mark a word boundary.
func isSeparator(r rune) bool {
// ASCII alphanumerics and underscore are not separators
if r <= 0x7F {
switch {
case '0' <= r && r <= '9':
return false
case 'a' <= r && r <= 'z':
return false
case 'A' <= r && r <= 'Z':
return false
case r == '_', r == '\'':
return false
}
return true
}
// Letters and digits are not separators
if unicode.IsLetter(r) || unicode.IsDigit(r) {
return false
}
// Otherwise, all we can do for now is treat spaces as separators.
return unicode.IsSpace(r)
}