68 lines
1.2 KiB
Go
68 lines
1.2 KiB
Go
package util
|
|
|
|
import (
|
|
"regexp"
|
|
"strings"
|
|
"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)
|
|
}
|
|
|
|
func UcFirst(str string) string {
|
|
for i, v := range str {
|
|
return string(unicode.ToUpper(v)) + str[i+1:]
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func Title(s string) string {
|
|
prev := ' '
|
|
return strings.Map(
|
|
func(r rune) rune {
|
|
if isSeparator(prev) {
|
|
prev = r
|
|
return unicode.ToTitle(r)
|
|
}
|
|
prev = r
|
|
return r
|
|
},
|
|
s)
|
|
}
|
|
|
|
func Keywords(s string) (results []string) {
|
|
r := regexp.MustCompile("[\\p{L}\\d]{3,}")
|
|
all := r.FindAllString(s, -1)
|
|
|
|
for _, w := range all {
|
|
w = strings.ToLower(w)
|
|
|
|
if _, ok := Stopwords[w]; ok == false {
|
|
results = append(results, w)
|
|
}
|
|
}
|
|
|
|
return results
|
|
}
|