Implement tokenize().

This commit is contained in:
Gea-Suan Lin
2024-02-09 11:46:19 +08:00
parent b133273065
commit ce79d2b245
3 changed files with 21 additions and 3 deletions

View File

@@ -4,15 +4,15 @@ import (
"fmt"
"github.com/gslin/go-ir-playground/internal/artifact"
"github.com/gslin/go-ir-playground/internal/ngram"
"github.com/gslin/go-ir-playground/internal/tokenize"
)
func main() {
articles := artifact.Read("data/articles.json")
for _, article := range articles {
title_bag := ngram.Bigram(article.Title)
body_bag := ngram.Bigram(article.Body)
title_bag := tokenize.Tokenize(article.Title)
body_bag := tokenize.Tokenize(article.Body)
fmt.Printf("title_bag = %v\n", title_bag)
fmt.Printf("body_bag = %v\n", body_bag)