Go语言 中文分词技术使用技巧（一）

?

package main

import (
	"fmt"
	"github.com/yanyiwu/gojieba"
	"strings"
)

func main() {

	var seg = gojieba.NewJieba()
	defer seg.Free()
	var useHmm = true
	var separator = "|"

	var resWords []string
	var sentence = "万里长城万里长"

	resWords = seg.CutAll(sentence)
	fmt.Printf("%s\t全模式：%s \n", sentence, strings.Join(resWords, separator))

	resWords = seg.Cut(sentence, useHmm)
	fmt.Printf("%s\t精确模式：%s \n", sentence, strings.Join(resWords, separator))

	var addWord = "万里长"
	seg.AddWord(addWord)
	fmt.Printf("添加新词：%s\n", addWord)

	resWords = seg.Cut(sentence, useHmm)
	fmt.Printf("%s\t精确模式：%s \n", sentence, strings.Join(resWords, separator))

	sentence = "北京鲜花速递"
	resWords = seg.Cut(sentence, useHmm)
	fmt.Printf("%s\t新词识别：%s \n", sentence, strings.Join(resWords, separator))

	sentence = "北京鲜花速递"
	resWords = seg.CutForSearch(sentence, useHmm)
	fmt.Println(sentence, "\t搜索引擎模式：", strings.Join(resWords, separator))

	sentence = "北京市朝阳公园"
	resWords = seg.Tag(sentence)
	fmt.Println(sentence, "\t词性标注：", strings.Join(resWords, separator))

	sentence = "鲁迅先生"
	resWords = seg.CutForSearch(sentence, !useHmm)
	fmt.Println(sentence, "\t搜索引擎模式：", strings.Join(resWords, separator))

	words := seg.Tokenize(sentence, gojieba.SearchMode, !useHmm)
	fmt.Println(sentence, "\tTokenize Search Mode 搜索引擎模式：", words)

	words = seg.Tokenize(sentence, gojieba.DefaultMode, !useHmm)
	fmt.Println(sentence, "\tTokenize Default Mode搜索引擎模式：", words)

	word2 := seg.ExtractWithWeight(sentence, 5)
	fmt.Println(sentence, "\tExtract：", word2)

	return
}

go build -o gojieba 

time ./gojieba 

万里长城万里长  全模式：万里|万里长城|里长|长城|万里|里长 
万里长城万里长  精确模式：万里长城|万里|长 
添加新词：万里长
万里长城万里长  精确模式：万里长城|万里长 
北京鲜花速递    新词识别：北京|鲜花|速递 
北京鲜花速递    搜索引擎模式： 北京|鲜花|速递
北京市朝阳公园  词性标注： 北京市/ns|朝阳/ns|公园/n
鲁迅先生        搜索引擎模式： 鲁迅|先生
鲁迅先生        Tokenize Search Mode 搜索引擎模式： [{鲁迅 0 6} {先生 6 12}]
鲁迅先生        Tokenize Default Mode搜索引擎模式： [{鲁迅 0 6} {先生 6 12}]
鲁迅先生        Extract： [{鲁迅 8.20023407859} {先生 5.56404756434}]

real    0m1.746s
user    0m1.622s
sys     0m0.124s