Decode plain text mbox bodies

backend/06-mbox.go

@@ -2,9 +2,12 @@ package backend
 
 import (
 	"bytes"
+	"encoding/base64"
 	"fmt"
 	"io"
 	"mime"
+	"mime/multipart"
+	"mime/quotedprintable"
 	"net/mail"
 	"os"
 	"path/filepath"
@@ -162,7 +165,64 @@ func messageBody(raw []byte) string {
 	if err != nil {
 		return string(raw)
 	}
-	return string(body)
+	return extractTextBody(msg.Header, body)
+}
+
+type headerGetter interface {
+	Get(string) string
+}
+
+func extractTextBody(h headerGetter, body []byte) string {
+	mediaType, params, _ := mime.ParseMediaType(h.Get("Content-Type"))
+	decoded := decodeTransfer(body, h.Get("Content-Transfer-Encoding"))
+	if strings.HasPrefix(mediaType, "multipart/") {
+		boundary := params["boundary"]
+		if boundary == "" {
+			return string(decoded)
+		}
+		mr := multipart.NewReader(bytes.NewReader(decoded), boundary)
+		var htmlBody string
+		for {
+			part, err := mr.NextPart()
+			if err == io.EOF {
+				break
+			}
+			if err != nil {
+				break
+			}
+			partBody, _ := io.ReadAll(part)
+			text := extractTextBody(part.Header, partBody)
+			partType, _, _ := mime.ParseMediaType(part.Header.Get("Content-Type"))
+			if strings.HasPrefix(partType, "text/plain") && strings.TrimSpace(text) != "" {
+				return text
+			}
+			if strings.HasPrefix(partType, "text/html") && htmlBody == "" {
+				htmlBody = text
+			}
+		}
+		if htmlBody != "" {
+			return htmlBody
+		}
+		return ""
+	}
+	return string(decoded)
+}
+
+func decodeTransfer(body []byte, enc string) []byte {
+	switch strings.ToLower(strings.TrimSpace(enc)) {
+	case "quoted-printable":
+		b, err := io.ReadAll(quotedprintable.NewReader(bytes.NewReader(body)))
+		if err == nil {
+			return b
+		}
+	case "base64":
+		cleaned := strings.NewReplacer("\r", "", "\n", "", " ", "", "\t", "").Replace(string(body))
+		b, err := base64.StdEncoding.DecodeString(cleaned)
+		if err == nil {
+			return b
+		}
+	}
+	return body
 }
 
 func safeMboxName(folder string) string {