replace html2text package with a basic regex; reorder text/html processing to be last

This commit is contained in:
Philipp Born 2023-02-20 13:06:19 +01:00
parent 893360da28
commit 5ac44ff40f
No known key found for this signature in database
GPG key ID: 8F5874E00662B261
3 changed files with 15 additions and 19 deletions

3
go.mod
View file

@ -27,7 +27,6 @@ require github.com/pkg/errors v0.9.1 // indirect
require (
firebase.google.com/go/v4 v4.10.0
github.com/k3a/html2text v1.1.0
github.com/stripe/stripe-go/v74 v74.8.0
)
@ -41,7 +40,7 @@ require (
github.com/MicahParks/keyfunc v1.9.0 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/emersion/go-sasl v0.0.0-20220912192320-0145f2c60ead // indirect
github.com/golang-jwt/jwt/v4 v4.5.0 // indirect
github.com/golang-jwt/jwt/v4 v4.4.3 // indirect
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
github.com/golang/protobuf v1.5.2 // indirect
github.com/google/go-cmp v0.5.9 // indirect

15
go.sum
View file

@ -42,8 +42,8 @@ github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7
github.com/gabriel-vasile/mimetype v1.4.1 h1:TRWk7se+TOjCYgRth7+1/OYLNiRNIotknkFtf/dnN7Q=
github.com/gabriel-vasile/mimetype v1.4.1/go.mod h1:05Vi0w3Y9c/lNvJOdmIwvrrAhX3rYhfQQCaf9VJcv7M=
github.com/golang-jwt/jwt/v4 v4.4.2/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0=
github.com/golang-jwt/jwt/v4 v4.5.0 h1:7cYmW1XlMY7h7ii7UhUyChSgS5wUJEnm9uZVTGqOWzg=
github.com/golang-jwt/jwt/v4 v4.5.0/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0=
github.com/golang-jwt/jwt/v4 v4.4.3 h1:Hxl6lhQFj4AnOX6MLrsCb/+7tCj7DxP7VA+2rDIq5AU=
github.com/golang-jwt/jwt/v4 v4.4.3/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0=
github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
@ -79,14 +79,8 @@ github.com/googleapis/enterprise-certificate-proxy v0.2.3 h1:yk9/cqRKtT9wXZSsRH9
github.com/googleapis/enterprise-certificate-proxy v0.2.3/go.mod h1:AwSRAtLfXpU5Nm3pW+v7rGDHp09LsPtGY9MduiEsR9k=
github.com/googleapis/gax-go/v2 v2.7.0 h1:IcsPKeInNvYi7eqSaDjiZqDDKu5rsmunY0Y1YupQSSQ=
github.com/googleapis/gax-go/v2 v2.7.0/go.mod h1:TEop28CZZQ2y+c0VxMUmu1lV+fQx57QpBWsYpwqHJx8=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1 h1:EGx4pi6eqNxGaHF6qqu48+N2wcFQ5qg5FXgOdqsJ5d8=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
github.com/gorilla/websocket v1.5.0 h1:PPwGk2jz7EePpoHN/+ClbZu8SPxiqlu12wZP/3sWmnc=
github.com/gorilla/websocket v1.5.0/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
github.com/k3a/html2text v1.1.0 h1:ks4hKSTdiTRsLr0DM771mI5TvsoG6zH7m1Ulv7eJRHw=
github.com/k3a/html2text v1.1.0/go.mod h1:ieEXykM67iT8lTvEWBh6fhpH4B23kB9OMKPdIBmgUqA=
github.com/mattn/go-sqlite3 v1.14.16 h1:yOQRA0RpS5PFz/oikGwBEqvAWhWg5ufRz4ETLjwpU1Y=
github.com/mattn/go-sqlite3 v1.14.16/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
github.com/olebedev/when v0.0.0-20221205223600-4d190b02b8d8 h1:0uFGkScHef2Xd8g74BMHU1jFcnKEm0PzrPn4CluQ9FI=
@ -98,10 +92,6 @@ github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZN
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d h1:zE9ykElWQ6/NYmHa3jpm/yHnI4xSofP+UP6SpjHcSeM=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
github.com/smartystreets/goconvey v1.6.4 h1:fv0U8FUIMPNf1L9lnHLvLhgicrIVChEkdzIKYqbNC9s=
github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0 h1:1zr/of2m5FGMsad5YfcqgdqdWrIhu+EBEJRhR1U7z/c=
@ -171,7 +161,6 @@ golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGm
golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20220907171357-04be3eba64a2 h1:H2TDz8ibqkAF6YGhCdN3jS9O0/s90v0rJh3X/OLHEUk=

View file

@ -6,7 +6,6 @@ import (
"errors"
"fmt"
"github.com/emersion/go-smtp"
"github.com/k3a/html2text"
"io"
"mime"
"mime/multipart"
@ -14,6 +13,7 @@ import (
"net/http"
"net/http/httptest"
"net/mail"
"regexp"
"strings"
"sync"
)
@ -219,10 +219,10 @@ func readMailBody(body io.Reader, header mail.Header) (string, error) {
}
if strings.ToLower(contentType) == "text/plain" {
return readPlainTextMailBody(body, header.Get("Content-Transfer-Encoding"))
} else if strings.ToLower(contentType) == "text/html" {
return readHTMLMailBody(body, header.Get("Content-Transfer-Encoding"))
} else if strings.HasPrefix(strings.ToLower(contentType), "multipart/") {
return readMultipartMailBody(body, params, 0)
} else if strings.ToLower(contentType) == "text/html" {
return readHTMLMailBody(body, header.Get("Content-Transfer-Encoding"))
}
return "", errUnsupportedContentType
}
@ -269,6 +269,14 @@ func readHTMLMailBody(reader io.Reader, transferEncoding string) (string, error)
if err != nil {
return "", err
}
body := html2text.HTML2Text(string(html))
// Strip HTML
re := regexp.MustCompile("<[^>]*>")
body := re.ReplaceAllString(string(html), "")
// Cleanup potential empty lines
re2 := regexp.MustCompile("(?m)^[ \t]*\r?\n")
body = re2.ReplaceAllString(body, "")
return string(body), nil
}