This commit is contained in:
Gea-Suan Lin
2024-02-16 21:02:40 +08:00
parent 1de46569e8
commit 3dcd171227
2 changed files with 0 additions and 0 deletions

View File

@@ -0,0 +1,14 @@
package tokenizer
import (
"slices"
"github.com/gslin/go-ir-playground/internal/ngram"
)
func Tokenize(s string) []string {
bag := append(ngram.Unigram(s), ngram.Bigram(s)...)
slices.Sort(bag)
slices.Compact[[]string, string](bag)
return bag
}