Sanitize email body and remove special characters

Author: Sven Liebert

service/cmd/server/main.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"github.com/emersion/go-imap"
 	"github.com/emersion/go-imap/client"
+	_ "github.com/emersion/go-message/charset"
 	"github.com/emersion/go-message/mail"
 	"github.com/microcosm-cc/bluemonday"
 	"github.com/robfig/cron/v3"
@@ -46,6 +47,13 @@ func getMailBody(p *mail.Part) string {
 	body, _ := ioutil.ReadAll(p.Body)
 	plainTextBody := strings.Replace(string(body), "\n", "\\n", -1)
 	plainTextBody = strings.Replace(plainTextBody, "\r", "\\r", -1)
+
+	regex, err := regexp.Compile(`[^\w] && [\\]`)
+	if err != nil {
+		log.Fatal(err)
+	}
+	plainTextBody = regex.ReplaceAllString(plainTextBody, " ")
+
 	return sanitizePolicy.Sanitize(plainTextBody)
 }
 

service/go.mod

@@ -5,7 +5,6 @@ go 1.14
 require (
 	github.com/emersion/go-imap v1.2.1
 	github.com/emersion/go-message v0.15.0
-	github.com/grokify/html-strip-tags-go v0.0.1
 	github.com/microcosm-cc/bluemonday v1.0.19
 	github.com/robfig/cron/v3 v3.0.1
 )

service/go.sum

@@ -10,8 +10,6 @@ github.com/emersion/go-textwrapper v0.0.0-20200911093747-65d896831594 h1:IbFBtwo
 github.com/emersion/go-textwrapper v0.0.0-20200911093747-65d896831594/go.mod h1:aqO8z8wPrjkscevZJFVE1wXJrLpC5LtJG7fqLOsPb2U=
 github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
 github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
-github.com/grokify/html-strip-tags-go v0.0.1 h1:0fThFwLbW7P/kOiTBs03FsJSV9RM2M/Q/MOnCQxKMo0=
-github.com/grokify/html-strip-tags-go v0.0.1/go.mod h1:2Su6romC5/1VXOQMaWL2yb618ARB8iVo6/DR99A6d78=
 github.com/microcosm-cc/bluemonday v1.0.19 h1:OI7hoF5FY4pFz2VA//RN8TfM0YJ2dJcl4P4APrCWy6c=
 github.com/microcosm-cc/bluemonday v1.0.19/go.mod h1:QNzV2UbLK2/53oIIwTOyLUSABMkjZ4tqiyC1g/DyqxE=
 github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=