备份-实体-分词

udpdataclear/udpSensitiveWords/go.mod

@@ -6,11 +6,14 @@ require (
 	github.com/fortytw2/leaktest v1.3.0 // indirect
 	github.com/importcjj/sensitive v0.0.0-20200106142752-42d1c505be7b
 	github.com/mailru/easyjson v0.7.7 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/olivere/elastic v6.2.35+incompatible // indirect
 	github.com/prometheus/client_golang v1.10.0
+	github.com/spf13/pflag v1.0.3 // indirect
 	go.mongodb.org/mongo-driver v1.5.1
 	google.golang.org/grpc v1.36.1
 	google.golang.org/protobuf v1.26.0
+	gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 // indirect
 	gopkg.in/mgo.v2 v2.0.0-20190816093944-a6b53ec6cb22
 	gopkg.in/olivere/elastic.v1 v1.0.1
 )

udpdataclear/udpSensitiveWords/main.go

@@ -5,13 +5,15 @@ import (
 )
 
 func init() {
-
+	//return
 	util.InitC()
 }
 func main() {
 
-	go util.AddTaskSensitiveWordsData() //增量
+	//go util.AddTaskSensitiveWordsData() //增量
 
+	//util.TemporaryTestNewData()
+	//return
 	// 主函数中添加
 	util.ExtractUdp() //udp通知抽取
 	lock := make(chan bool)

udpdataclear/udpSensitiveWords/util/words.go

@@ -112,6 +112,10 @@ func dealWithNameScoreRules(name string) (string, bool, float64 , []map[string]i
 func dealWithWordsRules(info_name string, source_name string) (int, int) {
 	total, hit := 0, 0
 	//字符串处理，替换指定字符
+	source_name = strings.ReplaceAll(source_name, "（微型企业）", "")
+	source_name = strings.ReplaceAll(source_name, "（有限合伙）", "")
+	source_name = strings.ReplaceAll(source_name, "（普通合伙）", "")
+
 	info_name = strings.ReplaceAll(info_name, "(", "")
 	info_name = strings.ReplaceAll(info_name, ")", "")
 	info_name = strings.ReplaceAll(info_name, "（", "")