在线时间:8:00-16:00
迪恩网络APP
随时随地掌握行业动态
扫描二维码
关注迪恩网络微信公众号
开源软件名称:yanyiwu/gojieba开源软件地址:https://github.com/yanyiwu/gojieba开源编程语言:Go 71.6%开源软件介绍:EnglishGoJiebaGoJieba是"结巴"中文分词的Golang语言版本。 简介
用法go get github.com/yanyiwu/gojieba 分词示例 package main
import (
"fmt"
"strings"
"github.com/yanyiwu/gojieba"
)
func main() {
var s string
var words []string
use_hmm := true
x := gojieba.NewJieba()
defer x.Free()
s = "我来到北京清华大学"
words = x.CutAll(s)
fmt.Println(s)
fmt.Println("全模式:", strings.Join(words, "/"))
words = x.Cut(s, use_hmm)
fmt.Println(s)
fmt.Println("精确模式:", strings.Join(words, "/"))
s = "比特币"
words = x.Cut(s, use_hmm)
fmt.Println(s)
fmt.Println("精确模式:", strings.Join(words, "/"))
x.AddWord("比特币")
s = "比特币"
words = x.Cut(s, use_hmm)
fmt.Println(s)
fmt.Println("添加词典后,精确模式:", strings.Join(words, "/"))
s = "他来到了网易杭研大厦"
words = x.Cut(s, use_hmm)
fmt.Println(s)
fmt.Println("新词识别:", strings.Join(words, "/"))
s = "小明硕士毕业于中国科学院计算所,后在日本京都大学深造"
words = x.CutForSearch(s, use_hmm)
fmt.Println(s)
fmt.Println("搜索引擎模式:", strings.Join(words, "/"))
s = "长春市长春药店"
words = x.Tag(s)
fmt.Println(s)
fmt.Println("词性标注:", strings.Join(words, ","))
s = "区块链"
words = x.Tag(s)
fmt.Println(s)
fmt.Println("词性标注:", strings.Join(words, ","))
s = "长江大桥"
words = x.CutForSearch(s, !use_hmm)
fmt.Println(s)
fmt.Println("搜索引擎模式:", strings.Join(words, "/"))
wordinfos := x.Tokenize(s, gojieba.SearchMode, !use_hmm)
fmt.Println(s)
fmt.Println("Tokenize:(搜索引擎模式)", wordinfos)
wordinfos = x.Tokenize(s, gojieba.DefaultMode, !use_hmm)
fmt.Println(s)
fmt.Println("Tokenize:(默认模式)", wordinfos)
keywords := x.ExtractWithWeight(s, 5)
fmt.Println("Extract:", keywords)
}
See example in jieba_test, extractor_test BenchmarkUnittest go test ./... Benchmark go test -bench "Jieba" -test.benchtime 10s
go test -bench "Extractor" -test.benchtime 10s ContributorsCode ContributorsThis project exists thanks to all the people who contribute. Contact
|
2023-10-27
2022-08-15
2022-08-17
2022-09-23
2022-08-13
请发表评论