分词计算频次代码-GO

package main

import (
	"fmt"
	"github.com/huichen/sego"
	"os"
	"path/filepath"
	"sort"
	"strings"
	"unicode/utf8"
)

type Pair struct {
	Key   string
	Value int
}

// PariList实现了sort接口，可以使用sort.Sort对其排序

type PairList []Pair

func (p PairList) Swap(i, j int)      { p[i], p[j] = p[j], p[i] }
func (p PairList) Len() int           { return len(p) }
func (p PairList) Less(i, j int) bool { return p[j].Value < p[i].Value } // 逆序

func main() {

	if len(os.Args) == 1 || os.Args[1] == "-h" || os.Args[1] == "--help" {
		fmt.Printf("usage: %s <file1> [<file2> [... <fileN>]]\n",
			filepath.Base(os.Args[0]))
		os.Exit(1)
	}

	// 载入词典
	var segmenter sego.Segmenter
	segmenter.LoadDictionary("../github.com/huichen/sego/data/dictionary.txt")

	//读取文件内容到buf中
	//filename := "./test2.txt"
	filenameArray := os.Args[1:]
	filename := filenameArray[0]
	fp, err := os.Open(filename)
	defer fp.Close()
	if err != nil {
		fmt.Println(filename, err)
		return
	}
	buf := make([]byte, 409600)
	n, _ := fp.Read(buf)

	if n == 0 {
		return
	}

	// 分词
	segments := segmenter.Segment(buf)
	// 处理分词结果
	// 支持普通模式和搜索模式两种分词，见utils.go代码中SegmentsToString函数的注释。
	// 如果需要词性标注，用SegmentsToString(segments, false)，更多参考utils.go文件
	output := sego.SegmentsToSlice(segments, false)
	//fmt.Println(len(output))
	var memory map[string]int
	memory = make(map[string]int, 10000)
	//输出分词后的成语
	for _, s := range output {
		/*if len(s) > 0 && fmt.Sprintf("%#v", s) != "\"\\x00\"" && fmt.Sprintf("%#v", s) != "\" \"" && fmt.Sprintf("%#v", s) != "\"\\n\"" {
			fmt.Println(s)
			//按照分词顺序重新排列文章，改为换行
		}*/

		if len(s) > utf8.UTFMax ||
			utf8.RuneCountInString(s) > 1 {
			//fmt.Println(s)
			memory[strings.ToLower(s)] += 1
		}

	}
	//fmt.Println(memory)
	//统计排序
	p := make(PairList, len(memory))
	i := 0
	for k, v := range memory { // 将wordcount map转换成PairList
		p[i] = Pair{k, v}
		i++
	}

	sort.Sort(p) // 因为PairList实现了排序接口，所以可以使用sort.Sort()对其排序

	wordWidth, frequencyWidth := 0, 0
	for _, pair := range p {
		word, frequency := pair.Key, pair.Value
		if width := utf8.RuneCountInString(word); width > wordWidth {
			wordWidth = width
		}
		if width := len(fmt.Sprint(frequency)); width > frequencyWidth {
			frequencyWidth = width
		}
	}
	gap := wordWidth + frequencyWidth - len("Word") - len("Frequency")
	fmt.Printf("Word %*s%s\n", gap, " ", "Frequency")

	for _, pair := range p {
		fmt.Printf("%-*s %*d\n", wordWidth, pair.Key, frequencyWidth,
			pair.Value)
	}
}

执行命令

go build main.go

./main text.txt | head -n 10

标签：fmt,PairList,len,频次,width,memory,GO,os,分词
来源： https://blog.csdn.net/aichojie/article/details/123129955