File: encodedword.go

package info (click to toggle)
golang-gopkg-alexcesaro-quotedprintable.v3 0.0~git20150716.0.2caba25-4
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, sid
  • size: 116 kB
  • sloc: makefile: 2
file content (279 lines) | stat: -rw-r--r-- 6,317 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
package quotedprintable

import (
	"bytes"
	"encoding/base64"
	"errors"
	"fmt"
	"io"
	"strings"
	"unicode"
	"unicode/utf8"
)

// A WordEncoder is a RFC 2047 encoded-word encoder.
type WordEncoder byte

const (
	// BEncoding represents Base64 encoding scheme as defined by RFC 2045.
	BEncoding = WordEncoder('b')
	// QEncoding represents the Q-encoding scheme as defined by RFC 2047.
	QEncoding = WordEncoder('q')
)

var (
	errInvalidWord = errors.New("mime: invalid RFC 2047 encoded-word")
)

// Encode returns the encoded-word form of s. If s is ASCII without special
// characters, it is returned unchanged. The provided charset is the IANA
// charset name of s. It is case insensitive.
func (e WordEncoder) Encode(charset, s string) string {
	if !needsEncoding(s) {
		return s
	}
	return e.encodeWord(charset, s)
}

func needsEncoding(s string) bool {
	for _, b := range s {
		if (b < ' ' || b > '~') && b != '\t' {
			return true
		}
	}
	return false
}

// encodeWord encodes a string into an encoded-word.
func (e WordEncoder) encodeWord(charset, s string) string {
	buf := getBuffer()
	defer putBuffer(buf)

	buf.WriteString("=?")
	buf.WriteString(charset)
	buf.WriteByte('?')
	buf.WriteByte(byte(e))
	buf.WriteByte('?')

	if e == BEncoding {
		w := base64.NewEncoder(base64.StdEncoding, buf)
		io.WriteString(w, s)
		w.Close()
	} else {
		enc := make([]byte, 3)
		for i := 0; i < len(s); i++ {
			b := s[i]
			switch {
			case b == ' ':
				buf.WriteByte('_')
			case b <= '~' && b >= '!' && b != '=' && b != '?' && b != '_':
				buf.WriteByte(b)
			default:
				enc[0] = '='
				enc[1] = upperhex[b>>4]
				enc[2] = upperhex[b&0x0f]
				buf.Write(enc)
			}
		}
	}
	buf.WriteString("?=")
	return buf.String()
}

const upperhex = "0123456789ABCDEF"

// A WordDecoder decodes MIME headers containing RFC 2047 encoded-words.
type WordDecoder struct {
	// CharsetReader, if non-nil, defines a function to generate
	// charset-conversion readers, converting from the provided
	// charset into UTF-8.
	// Charsets are always lower-case. utf-8, iso-8859-1 and us-ascii charsets
	// are handled by default.
	// One of the the CharsetReader's result values must be non-nil.
	CharsetReader func(charset string, input io.Reader) (io.Reader, error)
}

// Decode decodes an encoded-word. If word is not a valid RFC 2047 encoded-word,
// word is returned unchanged.
func (d *WordDecoder) Decode(word string) (string, error) {
	fields := strings.Split(word, "?") // TODO: remove allocation?
	if len(fields) != 5 || fields[0] != "=" || fields[4] != "=" || len(fields[2]) != 1 {
		return "", errInvalidWord
	}

	content, err := decode(fields[2][0], fields[3])
	if err != nil {
		return "", err
	}

	buf := getBuffer()
	defer putBuffer(buf)

	if err := d.convert(buf, fields[1], content); err != nil {
		return "", err
	}

	return buf.String(), nil
}

// DecodeHeader decodes all encoded-words of the given string. It returns an
// error if and only if CharsetReader of d returns an error.
func (d *WordDecoder) DecodeHeader(header string) (string, error) {
	// If there is no encoded-word, returns before creating a buffer.
	i := strings.Index(header, "=?")
	if i == -1 {
		return header, nil
	}

	buf := getBuffer()
	defer putBuffer(buf)

	buf.WriteString(header[:i])
	header = header[i:]

	betweenWords := false
	for {
		start := strings.Index(header, "=?")
		if start == -1 {
			break
		}
		cur := start + len("=?")

		i := strings.Index(header[cur:], "?")
		if i == -1 {
			break
		}
		charset := header[cur : cur+i]
		cur += i + len("?")

		if len(header) < cur+len("Q??=") {
			break
		}
		encoding := header[cur]
		cur++

		if header[cur] != '?' {
			break
		}
		cur++

		j := strings.Index(header[cur:], "?=")
		if j == -1 {
			break
		}
		text := header[cur : cur+j]
		end := cur + j + len("?=")

		content, err := decode(encoding, text)
		if err != nil {
			betweenWords = false
			buf.WriteString(header[:start+2])
			header = header[start+2:]
			continue
		}

		// Write characters before the encoded-word. White-space and newline
		// characters separating two encoded-words must be deleted.
		if start > 0 && (!betweenWords || hasNonWhitespace(header[:start])) {
			buf.WriteString(header[:start])
		}

		if err := d.convert(buf, charset, content); err != nil {
			return "", err
		}

		header = header[end:]
		betweenWords = true
	}

	if len(header) > 0 {
		buf.WriteString(header)
	}

	return buf.String(), nil
}

func decode(encoding byte, text string) ([]byte, error) {
	switch encoding {
	case 'B', 'b':
		return base64.StdEncoding.DecodeString(text)
	case 'Q', 'q':
		return qDecode(text)
	}
	return nil, errInvalidWord
}

func (d *WordDecoder) convert(buf *bytes.Buffer, charset string, content []byte) error {
	switch {
	case strings.EqualFold("utf-8", charset):
		buf.Write(content)
	case strings.EqualFold("iso-8859-1", charset):
		for _, c := range content {
			buf.WriteRune(rune(c))
		}
	case strings.EqualFold("us-ascii", charset):
		for _, c := range content {
			if c >= utf8.RuneSelf {
				buf.WriteRune(unicode.ReplacementChar)
			} else {
				buf.WriteByte(c)
			}
		}
	default:
		if d.CharsetReader == nil {
			return fmt.Errorf("mime: unhandled charset %q", charset)
		}
		r, err := d.CharsetReader(strings.ToLower(charset), bytes.NewReader(content))
		if err != nil {
			return err
		}
		if _, err = buf.ReadFrom(r); err != nil {
			return err
		}
	}
	return nil
}

// hasNonWhitespace reports whether s (assumed to be ASCII) contains at least
// one byte of non-whitespace.
func hasNonWhitespace(s string) bool {
	for _, b := range s {
		switch b {
		// Encoded-words can only be separated by linear white spaces which does
		// not include vertical tabs (\v).
		case ' ', '\t', '\n', '\r':
		default:
			return true
		}
	}
	return false
}

// qDecode decodes a Q encoded string.
func qDecode(s string) ([]byte, error) {
	dec := make([]byte, len(s))
	n := 0
	for i := 0; i < len(s); i++ {
		switch c := s[i]; {
		case c == '_':
			dec[n] = ' '
		case c == '=':
			if i+2 >= len(s) {
				return nil, errInvalidWord
			}
			b, err := readHexByte(s[i+1], s[i+2])
			if err != nil {
				return nil, err
			}
			dec[n] = b
			i += 2
		case (c <= '~' && c >= ' ') || c == '\n' || c == '\r' || c == '\t':
			dec[n] = c
		default:
			return nil, errInvalidWord
		}
		n++
	}

	return dec[:n], nil
}