From 07fdf64cbcd515f2e3a63563939e7c98461148c7 Mon Sep 17 00:00:00 2001
From: Winni Neessen <wn@neessen.net>
Date: Fri, 11 Mar 2022 10:29:44 +0100
Subject: [PATCH] Started work on charset and encoding handling

---
 .idea/workspace.xml |   9 ++--
 cmd/main.go         |   8 +++-
 encoding.go         | 105 +++++++++++++++++++++++++++++++++++++++++++-
 header.go           |  24 +++++++---
 mailmsg.go          |  84 ++++++++++++++++++++++++++++++++---
 5 files changed, 210 insertions(+), 20 deletions(-)

diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index ba493d0..f982bb6 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -4,12 +4,12 @@
     <option name="autoReloadType" value="ALL" />
   </component>
   <component name="ChangeListManager">
-    <list default="true" id="b79e8e7a-d892-4ce4-8bf4-f9e45415b803" name="Changes" comment="Lots of cleanups and refactoring">
+    <list default="true" id="b79e8e7a-d892-4ce4-8bf4-f9e45415b803" name="Changes" comment="Calling it a day...">
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/client.go" beforeDir="false" afterPath="$PROJECT_DIR$/client.go" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/cmd/main.go" beforeDir="false" afterPath="$PROJECT_DIR$/cmd/main.go" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/encoding.go" beforeDir="false" afterPath="$PROJECT_DIR$/encoding.go" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/header.go" beforeDir="false" afterPath="$PROJECT_DIR$/header.go" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/mailmsg.go" beforeDir="false" afterPath="$PROJECT_DIR$/mailmsg.go" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -97,7 +97,8 @@
     <MESSAGE value="Implemented SMTP AUTH" />
     <MESSAGE value="Better context and connection handling" />
     <MESSAGE value="Lots of cleanups and refactoring" />
-    <option name="LAST_COMMIT_MESSAGE" value="Lots of cleanups and refactoring" />
+    <MESSAGE value="Calling it a day..." />
+    <option name="LAST_COMMIT_MESSAGE" value="Calling it a day..." />
   </component>
   <component name="VgoProject">
     <integration-enabled>true</integration-enabled>
diff --git a/cmd/main.go b/cmd/main.go
index 3ab1202..897ae16 100644
--- a/cmd/main.go
+++ b/cmd/main.go
@@ -21,10 +21,14 @@ func main() {
 		fmt.Printf("failed to set FROM addres: %s", err)
 		os.Exit(1)
 	}
-	m.ToIgnoreInvalid("test@test.de", "foo@bar.de", "blubb@blah.com")
+	if err := m.To("t1+2941@test.de", "foo@bar.de", "blubb@blah.com"); err != nil {
+		fmt.Printf("failed to set TO address: %s", err)
+		os.Exit(1)
+	}
 	m.CcIgnoreInvalid("cc@test.de", "bar.de", "cc@blah.com")
 	m.BccIgnoreInvalid("bcc@test.de", "bcc@blah.com")
-	m.SetHeader("Foo", "bar")
+	m.Subject("This is the Subject with Umlauts: üöäß")
+	m.SetHeader(mail.HeaderContentLang, "en")
 	m.SetMessageID()
 	m.SetDate()
 	m.SetBulk()
diff --git a/encoding.go b/encoding.go
index c82d37e..44e333b 100644
--- a/encoding.go
+++ b/encoding.go
@@ -1,8 +1,12 @@
 package mail
 
-// Encoding represents a MIME encoding scheme like quoted-printable or base64.
+// Encoding represents a MIME encoding scheme like quoted-printable or Base64.
 type Encoding string
 
+// Charset represents a character set for the encodingA
+type Charset string
+
+// List of supported encodings
 const (
 	// EncodingB64 represents the Base64 encoding as specified in RFC 2045.
 	EncodingB64 Encoding = "base64"
@@ -13,3 +17,102 @@ const (
 	// NoEncoding avoids any character encoding (except of the mail headers)
 	NoEncoding Encoding = "8bit"
 )
+
+// List of common charsets
+const (
+	// CharsetUTF7 represents the "UTF-7" charset
+	CharsetUTF7 Charset = "UTF-7"
+
+	// CharsetUTF8 represents the "UTF-8" charset
+	CharsetUTF8 Charset = "UTF-8"
+
+	// CharsetASCII represents the "US-ASCII" charset
+	CharsetASCII Charset = "US-ASCII"
+
+	// CharsetISO88591 represents the "ISO-8859-1" charset
+	CharsetISO88591 Charset = "ISO-8859-1"
+
+	// CharsetISO88592 represents the "ISO-8859-2" charset
+	CharsetISO88592 Charset = "ISO-8859-2"
+
+	// CharsetISO88593 represents the "ISO-8859-3" charset
+	CharsetISO88593 Charset = "ISO-8859-3"
+
+	// CharsetISO88594 represents the "ISO-8859-4" charset
+	CharsetISO88594 Charset = "ISO-8859-4"
+
+	// CharsetISO88595 represents the "ISO-8859-5" charset
+	CharsetISO88595 Charset = "ISO-8859-5"
+
+	// CharsetISO88596 represents the "ISO-8859-6" charset
+	CharsetISO88596 Charset = "ISO-8859-6"
+
+	// CharsetISO88597 represents the "ISO-8859-7" charset
+	CharsetISO88597 Charset = "ISO-8859-7"
+
+	// CharsetISO88599 represents the "ISO-8859-9" charset
+	CharsetISO88599 Charset = "ISO-8859-9"
+
+	// CharsetISO885913 represents the "ISO-8859-13" charset
+	CharsetISO885913 Charset = "ISO-8859-13"
+
+	// CharsetISO885914 represents the "ISO-8859-14" charset
+	CharsetISO885914 Charset = "ISO-8859-14"
+
+	// CharsetISO885915 represents the "ISO-8859-15" charset
+	CharsetISO885915 Charset = "ISO-8859-15"
+
+	// CharsetISO885916 represents the "ISO-8859-16" charset
+	CharsetISO885916 Charset = "ISO-8859-16"
+
+	// CharsetISO2022JP represents the "ISO-2022-JP" charset
+	CharsetISO2022JP Charset = "ISO-2022-JP"
+
+	// CharsetISO2022KR represents the "ISO-2022-KR" charset
+	CharsetISO2022KR Charset = "ISO-2022-KR"
+
+	// CharsetWindows1250 represents the "windows-1250" charset
+	CharsetWindows1250 Charset = "windows-1250"
+
+	// CharsetWindows1251 represents the "windows-1251" charset
+	CharsetWindows1251 Charset = "windows-1251"
+
+	// CharsetWindows1252 represents the "windows-1252" charset
+	CharsetWindows1252 Charset = "windows-1252"
+
+	// CharsetWindows1255 represents the "windows-1255" charset
+	CharsetWindows1255 Charset = "windows-1255"
+
+	// CharsetWindows1256 represents the "windows-1256" charset
+	CharsetWindows1256 Charset = "windows-1256"
+
+	// CharsetKOI8R represents the "KOI8-R" charset
+	CharsetKOI8R Charset = "KOI8-R"
+
+	// CharsetKOI8U represents the "KOI8-U" charset
+	CharsetKOI8U Charset = "KOI8-U"
+
+	// CharsetBig5 represents the "Big5" charset
+	CharsetBig5 Charset = "Big5"
+
+	// CharsetGB18030 represents the "GB18030" charset
+	CharsetGB18030 Charset = "GB18030"
+
+	// CharsetGB2312 represents the "GB2312" charset
+	CharsetGB2312 Charset = "GB2312"
+
+	// CharsetTIS620 represents the "TIS-620" charset
+	CharsetTIS620 Charset = "TIS-620"
+
+	// CharsetEUCKR represents the "EUC-KR" charset
+	CharsetEUCKR Charset = "EUC-KR"
+
+	// CharsetShiftJIS represents the "Shift_JIS" charset
+	CharsetShiftJIS Charset = "Shift_JIS"
+
+	// CharsetUnknown represents the "Unknown" charset
+	CharsetUnknown Charset = "Unknown"
+
+	// CharsetGBK represents the "GBK" charset
+	CharsetGBK Charset = "GBK"
+)
diff --git a/header.go b/header.go
index a642e5a..af8d300 100644
--- a/header.go
+++ b/header.go
@@ -18,6 +18,15 @@ const (
 	// See: https://www.rfc-editor.org/rfc/rfc822#section-5.1
 	HeaderDate Header = "Date"
 
+	// HeaderInReplyTo represents the "In-Reply-To" field
+	HeaderInReplyTo Header = "In-Reply-To"
+
+	// HeaderListUnsubscribe is the "List-Unsubscribe" header field
+	HeaderListUnsubscribe Header = "List-Unsubscribe"
+
+	// HeaderListUnsubscribePost is the "List-Unsubscribe-Post" header field
+	HeaderListUnsubscribePost Header = "List-Unsubscribe-Post"
+
 	// HeaderMessageID represents the "Message-ID" field for message identification
 	// See: https://www.rfc-editor.org/rfc/rfc1036#section-2.1.5
 	HeaderMessageID Header = "Message-ID"
@@ -26,24 +35,27 @@ const (
 	// See: https://datatracker.ietf.org/doc/html/rfc2045#section-4
 	HeaderMIMEVersion Header = "MIME-Version"
 
-	// HeaderPrecedence is the "Precedence" genHeader field
+	// HeaderPrecedence is the "Precedence" header field
 	HeaderPrecedence Header = "Precedence"
 
-	// HeaderSubject is the "Subject" genHeader field
+	// HeaderReplyTo is the "Reply-To" header field
+	HeaderReplyTo Header = "Reply-To"
+
+	// HeaderSubject is the "Subject" header field
 	HeaderSubject Header = "Subject"
 )
 
 // List of common generic header field names
 const (
-	// HeaderBcc is the "Blind Carbon Copy" genHeader field
+	// HeaderBcc is the "Blind Carbon Copy" header field
 	HeaderBcc AddrHeader = "Bcc"
 
-	// HeaderCc is the "Carbon Copy" genHeader field
+	// HeaderCc is the "Carbon Copy" header field
 	HeaderCc AddrHeader = "Cc"
 
-	// HeaderFrom is the "From" genHeader field
+	// HeaderFrom is the "From" header field
 	HeaderFrom AddrHeader = "From"
 
-	// HeaderTo is the "Receipient" genHeader field
+	// HeaderTo is the "Receipient" header field
 	HeaderTo AddrHeader = "To"
 )
diff --git a/mailmsg.go b/mailmsg.go
index 19b7009..675f193 100644
--- a/mailmsg.go
+++ b/mailmsg.go
@@ -3,6 +3,7 @@ package mail
 import (
 	"fmt"
 	"math/rand"
+	"mime"
 	"net/mail"
 	"os"
 	"time"
@@ -11,10 +12,13 @@ import (
 // Msg is the mail message struct
 type Msg struct {
 	// charset represents the charset of the mail (defaults to UTF-8)
-	charset string
+	charset Charset
+
+	// encoding represents the message encoding (the encoder will be a corresponding WordEncoder)
+	encoding Encoding
 
 	// encoder represents a mime.WordEncoder from the std lib
-	//encoder mime.WordEncoder
+	encoder mime.WordEncoder
 
 	// genHeader is a slice of strings that the different generic mail Header fields
 	genHeader map[Header][]string
@@ -23,18 +27,61 @@ type Msg struct {
 	addrHeader map[AddrHeader][]*mail.Address
 }
 
+// MsgOption returns a function that can be used for grouping Msg options
+type MsgOption func(*Msg)
+
 // NewMsg returns a new Msg pointer
-func NewMsg() *Msg {
+func NewMsg(o ...MsgOption) *Msg {
 	m := &Msg{
-		charset:    "UTF-8",
+		encoding:   EncodingQP,
+		charset:    CharsetUTF8,
 		genHeader:  make(map[Header][]string),
 		addrHeader: make(map[AddrHeader][]*mail.Address),
 	}
+
+	// Override defaults with optionally provided MsgOption functions
+	for _, co := range o {
+		if co == nil {
+			continue
+		}
+		co(m)
+	}
+
+	// Set the matcing mime.WordEncoder for the Msg
+	m.setEncoder()
+
 	return m
 }
 
+// WithCharset overrides the default message charset
+func WithCharset(c Charset) MsgOption {
+	return func(m *Msg) {
+		m.charset = c
+	}
+}
+
+// WithEncoding overrides the default message encoding
+func WithEncoding(e Encoding) MsgOption {
+	return func(m *Msg) {
+		m.encoding = e
+	}
+}
+
+// SetCharset sets the encoding charset of the Msg
+func (m *Msg) SetCharset(c Charset) {
+	m.charset = c
+}
+
+// SetEncoding sets the encoding of the Msg
+func (m *Msg) SetEncoding(e Encoding) {
+	m.encoding = e
+}
+
 // SetHeader sets a generic header field of the Msg
 func (m *Msg) SetHeader(h Header, v ...string) {
+	for i, hv := range v {
+		v[i] = m.encodeString(hv)
+	}
 	m.genHeader[h] = v
 }
 
@@ -42,7 +89,7 @@ func (m *Msg) SetHeader(h Header, v ...string) {
 func (m *Msg) SetAddrHeader(h AddrHeader, v ...string) error {
 	var al []*mail.Address
 	for _, av := range v {
-		a, err := mail.ParseAddress(av)
+		a, err := mail.ParseAddress(m.encodeString(av))
 		if err != nil {
 			return fmt.Errorf("failed to parse mail address header %q: %w", av, err)
 		}
@@ -62,7 +109,7 @@ func (m *Msg) SetAddrHeader(h AddrHeader, v ...string) error {
 func (m *Msg) SetAddrHeaderIgnoreInvalid(h AddrHeader, v ...string) {
 	var al []*mail.Address
 	for _, av := range v {
-		a, err := mail.ParseAddress(av)
+		a, err := mail.ParseAddress(m.encodeString(av))
 		if err != nil {
 			continue
 		}
@@ -81,6 +128,11 @@ func (m *Msg) To(t ...string) error {
 	return m.SetAddrHeader(HeaderTo, t...)
 }
 
+// Subject sets the "Subject" header field of the Msg
+func (m *Msg) Subject(s string) {
+	m.SetHeader(HeaderSubject, s)
+}
+
 // ToIgnoreInvalid takes and validates a given mail address list sets the To: addresses of the Msg
 // Any provided address that is not RFC5322 compliant, will be ignored
 func (m *Msg) ToIgnoreInvalid(t ...string) {
@@ -126,7 +178,7 @@ func (m *Msg) SetMessageID() {
 
 // SetMessageIDWithValue sets the message id for the mail
 func (m *Msg) SetMessageIDWithValue(v string) {
-	m.SetHeader(HeaderMessageID, v)
+	m.SetHeader(HeaderMessageID, fmt.Sprintf("<%s>", v))
 }
 
 // SetBulk sets the "Precedence: bulk" genHeader which is recommended for
@@ -149,3 +201,21 @@ func (m *Msg) Header() {
 	fmt.Printf("Generic header: %+v\n", m.genHeader)
 
 }
+
+// setEncoder creates a new mime.WordEncoder based on the encoding setting of the message
+func (m *Msg) setEncoder() {
+	switch m.encoding {
+	case EncodingQP:
+		m.encoder = mime.QEncoding
+	case EncodingB64:
+		m.encoder = mime.BEncoding
+	default:
+		m.encoder = mime.QEncoding
+	}
+}
+
+// encodeString encodes a string based on the configured message encoder and the corresponding
+// charset for the Msg
+func (m *Msg) encodeString(s string) string {
+	return m.encoder.Encode(string(m.charset), s)
+}