net/mail: move RFC 2047 code to internal/mime

The code concerning quoted-printable encoding (RFC 2045) and its
variant for MIME headers (RFC 2047) is currently spread in
mime/multipart and net/mail. It is also not exported.

This commit is the second step to fix that issue. It moves the
RFC 2047 encoding and decoding functions from net/mail to
internal/mime. The exported API is unchanged.

Updates #4943

Change-Id: I5f58aa58e74bbe4ec91b2e9b8c81921338053b00
Reviewed-on: https://go-review.googlesource.com/2101Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

src/go/build/deps_test.go

@@ -252,7 +252,7 @@ var pkgDeps = map[string][]string{
 
 	// Uses of networking.
 	"log/syslog":    {"L4", "OS", "net"},
-	"net/mail":      {"L4", "NET", "OS"},
+	"net/mail":      {"L4", "NET", "OS", "internal/mime"},
 	"net/textproto": {"L4", "OS", "net"},
 
 	// Core crypto.

src/internal/mime/header.go

+// Copyright 2015 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package mime
+
+import (
+	"bytes"
+	"encoding/base64"
+	"errors"
+	"fmt"
+	"io"
+	"io/ioutil"
+	"strconv"
+	"strings"
+	"unicode"
+)
+
+// EncodeWord encodes a string into an RFC 2047 encoded-word.
+func EncodeWord(s string) string {
+	// UTF-8 "Q" encoding
+	b := bytes.NewBufferString("=?utf-8?q?")
+	for i := 0; i < len(s); i++ {
+		switch c := s[i]; {
+		case c == ' ':
+			b.WriteByte('_')
+		case isVchar(c) && c != '=' && c != '?' && c != '_':
+			b.WriteByte(c)
+		default:
+			fmt.Fprintf(b, "=%02X", c)
+		}
+	}
+	b.WriteString("?=")
+	return b.String()
+}
+
+// DecodeWord decodes an RFC 2047 encoded-word.
+func DecodeWord(s string) (string, error) {
+	fields := strings.Split(s, "?")
+	if len(fields) != 5 || fields[0] != "=" || fields[4] != "=" {
+		return "", errors.New("address not RFC 2047 encoded")
+	}
+	charset, enc := strings.ToLower(fields[1]), strings.ToLower(fields[2])
+	if charset != "us-ascii" && charset != "iso-8859-1" && charset != "utf-8" {
+		return "", fmt.Errorf("charset not supported: %q", charset)
+	}
+
+	in := bytes.NewBufferString(fields[3])
+	var r io.Reader
+	switch enc {
+	case "b":
+		r = base64.NewDecoder(base64.StdEncoding, in)
+	case "q":
+		r = qDecoder{r: in}
+	default:
+		return "", fmt.Errorf("RFC 2047 encoding not supported: %q", enc)
+	}
+
+	dec, err := ioutil.ReadAll(r)
+	if err != nil {
+		return "", err
+	}
+
+	switch charset {
+	case "us-ascii":
+		b := new(bytes.Buffer)
+		for _, c := range dec {
+			if c >= 0x80 {
+				b.WriteRune(unicode.ReplacementChar)
+			} else {
+				b.WriteRune(rune(c))
+			}
+		}
+		return b.String(), nil
+	case "iso-8859-1":
+		b := new(bytes.Buffer)
+		for _, c := range dec {
+			b.WriteRune(rune(c))
+		}
+		return b.String(), nil
+	case "utf-8":
+		return string(dec), nil
+	}
+	panic("unreachable")
+}
+
+type qDecoder struct {
+	r       io.Reader
+	scratch [2]byte
+}
+
+func (qd qDecoder) Read(p []byte) (n int, err error) {
+	// This method writes at most one byte into p.
+	if len(p) == 0 {
+		return 0, nil
+	}
+	if _, err := qd.r.Read(qd.scratch[:1]); err != nil {
+		return 0, err
+	}
+	switch c := qd.scratch[0]; {
+	case c == '=':
+		if _, err := io.ReadFull(qd.r, qd.scratch[:2]); err != nil {
+			return 0, err
+		}
+		x, err := strconv.ParseInt(string(qd.scratch[:2]), 16, 64)
+		if err != nil {
+			return 0, fmt.Errorf("mime: invalid RFC 2047 encoding: %q", qd.scratch[:2])
+		}
+		p[0] = byte(x)
+	case c == '_':
+		p[0] = ' '
+	default:
+		p[0] = c
+	}
+	return 1, nil
+}
+
+// isVchar returns true if c is an RFC 5322 VCHAR character.
+func isVchar(c byte) bool {
+	// Visible (printing) characters.
+	return '!' <= c && c <= '~'
+}

src/net/mail/message.go

@@ -18,17 +18,14 @@ package mail
 import (
 	"bufio"
 	"bytes"
-	"encoding/base64"
 	"errors"
 	"fmt"
+	"internal/mime"
 	"io"
-	"io/ioutil"
 	"log"
 	"net/textproto"
-	"strconv"
 	"strings"
 	"time"
-	"unicode"
 )
 
 var debug = debugT(false)
@@ -180,21 +177,7 @@ func (a *Address) String() string {
 		return b.String()
 	}
 
-	// UTF-8 "Q" encoding
-	b := bytes.NewBufferString("=?utf-8?q?")
-	for i := 0; i < len(a.Name); i++ {
-		switch c := a.Name[i]; {
-		case c == ' ':
-			b.WriteByte('_')
-		case isVchar(c) && c != '=' && c != '?' && c != '_':
-			b.WriteByte(c)
-		default:
-			fmt.Fprintf(b, "=%02X", c)
-		}
-	}
-	b.WriteString("?= ")
-	b.WriteString(s)
-	return b.String()
+	return mime.EncodeWord(a.Name) + " " + s
 }
 
 type addrParser []byte
@@ -352,7 +335,7 @@ func (p *addrParser) consumePhrase() (phrase string, err error) {
 
 		// RFC 2047 encoded-word starts with =?, ends with ?=, and has two other ?s.
 		if err == nil && strings.HasPrefix(word, "=?") && strings.HasSuffix(word, "?=") && strings.Count(word, "?") == 4 {
-			word, err = decodeRFC2047Word(word)
+			word, err = mime.DecodeWord(word)
 		}
 
 		if err != nil {
@@ -440,86 +423,6 @@ func (p *addrParser) len() int {
 	return len(*p)
 }
 
-func decodeRFC2047Word(s string) (string, error) {
-	fields := strings.Split(s, "?")
-	if len(fields) != 5 || fields[0] != "=" || fields[4] != "=" {
-		return "", errors.New("address not RFC 2047 encoded")
-	}
-	charset, enc := strings.ToLower(fields[1]), strings.ToLower(fields[2])
-	if charset != "us-ascii" && charset != "iso-8859-1" && charset != "utf-8" {
-		return "", fmt.Errorf("charset not supported: %q", charset)
-	}
-
-	in := bytes.NewBufferString(fields[3])
-	var r io.Reader
-	switch enc {
-	case "b":
-		r = base64.NewDecoder(base64.StdEncoding, in)
-	case "q":
-		r = qDecoder{r: in}
-	default:
-		return "", fmt.Errorf("RFC 2047 encoding not supported: %q", enc)
-	}
-
-	dec, err := ioutil.ReadAll(r)
-	if err != nil {
-		return "", err
-	}
-
-	switch charset {
-	case "us-ascii":
-		b := new(bytes.Buffer)
-		for _, c := range dec {
-			if c >= 0x80 {
-				b.WriteRune(unicode.ReplacementChar)
-			} else {
-				b.WriteRune(rune(c))
-			}
-		}
-		return b.String(), nil
-	case "iso-8859-1":
-		b := new(bytes.Buffer)
-		for _, c := range dec {
-			b.WriteRune(rune(c))
-		}
-		return b.String(), nil
-	case "utf-8":
-		return string(dec), nil
-	}
-	panic("unreachable")
-}
-
-type qDecoder struct {
-	r       io.Reader
-	scratch [2]byte
-}
-
-func (qd qDecoder) Read(p []byte) (n int, err error) {
-	// This method writes at most one byte into p.
-	if len(p) == 0 {
-		return 0, nil
-	}
-	if _, err := qd.r.Read(qd.scratch[:1]); err != nil {
-		return 0, err
-	}
-	switch c := qd.scratch[0]; {
-	case c == '=':
-		if _, err := io.ReadFull(qd.r, qd.scratch[:2]); err != nil {
-			return 0, err
-		}
-		x, err := strconv.ParseInt(string(qd.scratch[:2]), 16, 64)
-		if err != nil {
-			return 0, fmt.Errorf("mail: invalid RFC 2047 encoding: %q", qd.scratch[:2])
-		}
-		p[0] = byte(x)
-	case c == '_':
-		p[0] = ' '
-	default:
-		p[0] = c
-	}
-	return 1, nil
-}
-
 var atextChars = []byte("ABCDEFGHIJKLMNOPQRSTUVWXYZ" +
 	"abcdefghijklmnopqrstuvwxyz" +
 	"0123456789" +