feat(backend):使用gse替代gojieba进行分词

- 移除 gojieba 依赖,减少二进制文件大小
- 添加 gse 依赖,支持更高效的分词处理
- 更新 splitWords 函数,使用 gse 进行中英文分词
- 在包初始化时加载 gse 默认词典
This commit is contained in:
ArvinLovegood 2025-06-21 13:49:30 +08:00
parent a936dc6371
commit b2c12cffbb
3 changed files with 21 additions and 5 deletions

View File

@ -3,13 +3,16 @@ package data
import (
"bufio"
"fmt"
"github.com/yanyiwu/gojieba"
"github.com/go-ego/gse"
"go-stock/backend/logger"
"os"
"strings"
)
// 金融情感词典,包含股票市场相关的专业词汇
var (
seg gse.Segmenter
// 正面金融词汇及其权重
positiveFinanceWords = map[string]float64{
"上涨": 2.0, "涨停": 3.0, "牛市": 3.0, "反弹": 2.0, "新高": 2.5,
@ -50,6 +53,14 @@ var (
}
)
func init() {
// 加载默认词典
err := seg.LoadDict()
if err != nil {
logger.SugaredLogger.Error(err.Error())
}
}
// SentimentResult 情感分析结果类型
type SentimentResult struct {
Score float64 // 情感得分
@ -228,10 +239,7 @@ func calculateScore(words []string) (float64, int, int) {
// 简单的分词函数,考虑了中文和英文
func splitWords(text string) []string {
x := gojieba.NewJieba()
defer x.Free()
return x.Cut(text, true)
return seg.Cut(text, true)
}
// GetSentimentDescription 获取情感类别的文本描述

2
go.mod
View File

@ -9,6 +9,7 @@ require (
github.com/duke-git/lancet/v2 v2.3.4
github.com/energye/systray v1.0.2
github.com/glebarez/sqlite v1.11.0
github.com/go-ego/gse v0.80.3
github.com/go-resty/resty/v2 v2.16.2
github.com/go-toast/toast v0.0.0-20190211030409-01e6764cf0a4
github.com/robertkrimen/otto v0.5.1
@ -67,6 +68,7 @@ require (
github.com/tkrajina/go-reflector v0.5.8 // indirect
github.com/valyala/bytebufferpool v1.0.0 // indirect
github.com/valyala/fasttemplate v1.2.2 // indirect
github.com/vcaesar/cedar v0.20.2 // indirect
github.com/wailsapp/go-webview2 v1.0.19 // indirect
github.com/wailsapp/mimetype v1.4.1 // indirect
go.uber.org/multierr v1.10.0 // indirect

6
go.sum
View File

@ -26,6 +26,8 @@ github.com/glebarez/go-sqlite v1.21.2 h1:3a6LFC4sKahUunAmynQKLZceZCOzUthkRkEAl9g
github.com/glebarez/go-sqlite v1.21.2/go.mod h1:sfxdZyhQjTM2Wry3gVYWaW072Ri1WMdWJi0k6+3382k=
github.com/glebarez/sqlite v1.11.0 h1:wSG0irqzP6VurnMEpFGer5Li19RpIRi2qvQz++w0GMw=
github.com/glebarez/sqlite v1.11.0/go.mod h1:h8/o8j5wiAsqSPoWELDUdJXhjAhsVliSn7bWZjOhrgQ=
github.com/go-ego/gse v0.80.3 h1:YNFkjMhlhQnUeuoFcUEd1ivh6SOB764rT8GDsEbDiEg=
github.com/go-ego/gse v0.80.3/go.mod h1:Gt3A9Ry1Eso2Kza4MRaiZ7f2DTAvActmETY46Lxg0gU=
github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
github.com/go-resty/resty/v2 v2.16.2 h1:CpRqTjIzq/rweXUt9+GxzzQdlkqMdt8Lm/fuK/CAbAg=
@ -129,6 +131,10 @@ github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6Kllzaw
github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
github.com/valyala/fasttemplate v1.2.2 h1:lxLXG0uE3Qnshl9QyaK6XJxMXlQZELvChBOCmQD0Loo=
github.com/valyala/fasttemplate v1.2.2/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
github.com/vcaesar/cedar v0.20.2 h1:TDx7AdZhilKcfE1WvdToTJf5VrC/FXcUOW+KY1upLZ4=
github.com/vcaesar/cedar v0.20.2/go.mod h1:lyuGvALuZZDPNXwpzv/9LyxW+8Y6faN7zauFezNsnik=
github.com/vcaesar/tt v0.20.1 h1:D/jUeeVCNbq3ad8M7hhtB3J9x5RZ6I1n1eZ0BJp7M+4=
github.com/vcaesar/tt v0.20.1/go.mod h1:cH2+AwGAJm19Wa6xvEa+0r+sXDJBT0QgNQey6mwqLeU=
github.com/wailsapp/go-webview2 v1.0.19 h1:7U3QcDj1PrBPaxJNCui2k1SkWml+Q5kvFUFyTImA6NU=
github.com/wailsapp/go-webview2 v1.0.19/go.mod h1:qJmWAmAmaniuKGZPWwne+uor3AHMB5PFhqiK0Bbj8kc=
github.com/wailsapp/mimetype v1.4.1 h1:pQN9ycO7uo4vsUUuPeHEYoUkLVkaRntMnHJxVwYhwHs=