canonicalize 2

dkim.go

@@ -2,7 +2,7 @@ package dkim
 
 import (
 	"bytes"
-	//"fmt"
+	"container/list"
 	"io/ioutil"
 	"regexp"
 	"strings"
@@ -155,6 +155,98 @@ func canonicalize(emailReader *bytes.Reader, options sigOptions) (headers, body
 	}
 
 	canonicalizations := strings.Split(options.Canonicalization, "/")
+
+	// canonicalyze header
+	//var headersMap [][]byte
+	//headersMap := [][]byte{}
+	headersList := list.New()
+	currentHeader := []byte{}
+	for _, line := range bytes.SplitAfter(parts[0], []byte{10}) {
+		if line[0] == 32 || line[0] == 9 {
+			if len(currentHeader) == 0 {
+				return headers, body, ErrBadMailFormatHeaders
+			}
+			currentHeader = append(currentHeader, line...)
+		} else {
+			// New header, save current if exists
+			if len(currentHeader) != 0 {
+				//headersMap = append(headersMap, currentHeader)
+				headersList.PushBack(string(currentHeader))
+				currentHeader = []byte{}
+
+			}
+			currentHeader = append(currentHeader, line...)
+		}
+	}
+
+	// pour chaque header a conserver on traverse tous les headers dispo
+	// If multi instance of a field we must keep it from the bottom to the top
+	var match *list.Element
+	headersToKeepList := list.New()
+
+	for _, headerToKeep := range options.Headers {
+		match = nil
+		headerToKeepToLower := strings.ToLower(headerToKeep)
+		for e := headersList.Front(); e != nil; e = e.Next() {
+			t := strings.Split(e.Value.(string), ":")
+			if strings.ToLower(t[0]) == headerToKeepToLower {
+				match = e
+			}
+		}
+		if match != nil {
+			headersToKeepList.PushBack(match.Value.(string))
+			headersList.Remove(match)
+		} else {
+			headersToKeepList.PushBack(headerToKeep + ":\r\n")
+		}
+	}
+
+	if canonicalizations[0] == "simple" {
+		// The "simple" header canonicalization algorithm does not change header
+		// fields in any way.  Header fields MUST be presented to the signing or
+		// verification algorithm exactly as they are in the message being
+		// signed or verified.  In particular, header field names MUST NOT be
+		// case folded and whitespace MUST NOT be changed.
+		for e := headersToKeepList.Front(); e != nil; e = e.Next() {
+			headers = append(headers, []byte(e.Value.(string))...)
+		}
+	} else {
+		// The "relaxed" header canonicalization algorithm MUST apply the
+		// following steps in order:
+
+		// Convert all header field names (not the header field values) to
+		// lowercase.  For example, convert "SUBJect: AbC" to "subject: AbC".
+
+		// Unfold all header field continuation lines as described in
+		// [RFC5322]; in particular, lines with terminators embedded in
+		// continued header field values (that is, CRLF sequences followed by
+		// WSP) MUST be interpreted without the CRLF.  Implementations MUST
+		// NOT remove the CRLF at the end of the header field value.
+
+		// Convert all sequences of one or more WSP characters to a single SP
+		// character.  WSP characters here include those before and after a
+		// line folding boundary.
+
+		// Delete all WSP characters at the end of each unfolded header field
+		// value.
+
+		// Delete any WSP characters remaining before and after the colon
+		// separating the header field name from the header field value.  The
+		// colon separator MUST be retained.
+		for e := headersToKeepList.Front(); e != nil; e = e.Next() {
+			kv := strings.SplitN(e.Value.(string), ":", 2)
+			if len(kv) != 2 {
+				return []byte{}, []byte{}, ErrBadMailFormatHeaders
+			}
+			k := strings.ToLower(kv[0])
+			k = strings.TrimSpace(k)
+			v := strings.Replace(kv[1], "\n", "", -1)
+			v = strings.Replace(v, "\r", "", -1)
+			v = rxReduceWS.ReplaceAllString(v, " ")
+			v = strings.TrimSpace(v)
+			headers = append(headers, []byte(k+":"+v+CRLF)...)
+		}
+	}
 	// canonicalyze body
 	if canonicalizations[1] == "simple" {
 		// simple

dkim_test.go

@@ -33,6 +33,9 @@ kS5vLkzRI84eiJrm3+IieUqIIicsO+WYxQs+JgVx5XhpPjX4SQjHtwEC2xKkWnEv
 
 var email = "Received: (qmail 28277 invoked from network); 1 May 2015 09:43:37 -0000" + CRLF +
 	"Received: (qmail 21323 invoked from network); 1 May 2015 09:48:39 -0000" + CRLF +
+	"Received: from mail483.ha.ovh.net (b6.ovh.net [213.186.33.56])" + CRLF +
+	" by mo51.mail-out.ovh.net (Postfix) with SMTP id A6E22FF8934" + CRLF +
+	" for <toorop@toorop.fr>; Mon,  4 May 2015 14:00:47 +0200 (CEST)" + CRLF +
 	"MIME-Version: 1.0" + CRLF +
 	"Date: Fri, 1 May 2015 11:48:37 +0200" + CRLF +
 	"Message-ID: <CADu37kTXBeNkJdXc4bSF8DbJnXmNjkLbnswK6GzG_2yn7U7P6w@tmail.io>" + CRLF +
@@ -46,6 +49,22 @@ var email = "Received: (qmail 28277 invoked from network); 1 May 2015 09:43:37 -
 	"-- " + CRLF +
 	"Toorop  " + CRLF + CRLF + CRLF + CRLF + CRLF + CRLF
 
+var headerSimple = "From: =?UTF-8?Q?St=C3=A9phane_Depierrepont?= <toorop@tmail.io>" + CRLF +
+	"Date: Fri, 1 May 2015 11:48:37 +0200" + CRLF +
+	"MIME-Version: 1.0" + CRLF +
+	"Received: from mail483.ha.ovh.net (b6.ovh.net [213.186.33.56])" + CRLF +
+	" by mo51.mail-out.ovh.net (Postfix) with SMTP id A6E22FF8934" + CRLF +
+	" for <toorop@toorop.fr>; Mon,  4 May 2015 14:00:47 +0200 (CEST)" + CRLF +
+	"Received: (qmail 21323 invoked from network); 1 May 2015 09:48:39 -0000" + CRLF +
+	"In-Reply-To:" + CRLF
+
+var headerRelaxed = "from:=?UTF-8?Q?St=C3=A9phane_Depierrepont?= <toorop@tmail.io>" + CRLF +
+	"date:Fri, 1 May 2015 11:48:37 +0200" + CRLF +
+	"mime-version:1.0" + CRLF +
+	"received:from mail483.ha.ovh.net (b6.ovh.net [213.186.33.56]) by mo51.mail-out.ovh.net (Postfix) with SMTP id A6E22FF8934 for <toorop@toorop.fr>; Mon, 4 May 2015 14:00:47 +0200 (CEST)" + CRLF +
+	"received:(qmail 21323 invoked from network); 1 May 2015 09:48:39 -0000" + CRLF +
+	"in-reply-to:" + CRLF
+
 var bodySimple = "Hello world" + CRLF +
 	"line with trailing space         " + CRLF +
 	"line with           space         " + CRLF +
@@ -112,6 +131,26 @@ func Test_SignConfig(t *testing.T) {
 	assert.NoError(t, err)
 }
 
+func Test_canonicalize(t *testing.T) {
+	emailReader := bytes.NewReader([]byte(email))
+	options := NewSigOptions()
+	options.Headers = []string{"from", "date", "mime-version", "received", "received", "In-Reply-To"}
+	// simple/simple
+	options.Canonicalization = "simple/simple"
+	header, body, err := canonicalize(emailReader, options)
+	assert.NoError(t, err)
+	assert.Equal(t, []byte(headerSimple), header)
+	assert.Equal(t, []byte(bodySimple), body)
+
+	// relaxed/relaxed
+	options.Canonicalization = "relaxed/relaxed"
+	header, body, err = canonicalize(emailReader, options)
+	assert.NoError(t, err)
+	assert.Equal(t, []byte(headerRelaxed), header)
+	assert.Equal(t, []byte(bodyRelaxed), body)
+
+}
+
 func Test_Sign(t *testing.T) {
 	emailReader := bytes.NewReader([]byte(email))
 	options := NewSigOptions()
@@ -122,20 +161,3 @@ func Test_Sign(t *testing.T) {
 	emailReader, err := Sign(emailReader, options)
 	assert.NoError(t, err)
 }
-
-func Test_canonicalize(t *testing.T) {
-	emailReader := bytes.NewReader([]byte(email))
-	options := NewSigOptions()
-	// simple/simple
-	options.Canonicalization = "simple/simple"
-	_, body, err := canonicalize(emailReader, options)
-	assert.NoError(t, err)
-	assert.Equal(t, []byte(bodySimple), body)
-
-	// relaxed/relaxed
-	options.Canonicalization = "relaxed/relaxed"
-	_, body, err = canonicalize(emailReader, options)
-	assert.NoError(t, err)
-	assert.Equal(t, []byte(bodyRelaxed), body)
-
-}

errors.go

@@ -24,5 +24,8 @@ var (
 	ErrSignBadAlgo = errors.New("bad algorithm. Only rsa-sha1 or rsa-sha256 are permitted")
 
 	// ErrBadMailFormat
-	ErrBadMailFormat = errors.New("bad mail formart")
+	ErrBadMailFormat = errors.New("bad mail format")
+
+	// ErrBadMailFormatHeaders
+	ErrBadMailFormatHeaders = errors.New("bad mail format found in headers")
 )