summaryrefslogtreecommitdiff
path: root/src/pkg/mime/mediatype.go
blob: 608f759da8f315795310291f25fbc9a92c2c5a29 (plain)
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
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
// Copyright 2010 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"
	"errors"
	"fmt"
	"strings"
	"unicode"
)

// FormatMediaType serializes mediatype t and the parameters
// param as a media type conforming to RFC 2045 and RFC 2616.
// The type and parameter names are written in lower-case.
// When any of the arguments result in a standard violation then
// FormatMediaType returns the empty string.
func FormatMediaType(t string, param map[string]string) string {
	slash := strings.Index(t, "/")
	if slash == -1 {
		return ""
	}
	major, sub := t[:slash], t[slash+1:]
	if !isToken(major) || !isToken(sub) {
		return ""
	}
	var b bytes.Buffer
	b.WriteString(strings.ToLower(major))
	b.WriteByte('/')
	b.WriteString(strings.ToLower(sub))

	for attribute, value := range param {
		b.WriteByte(';')
		b.WriteByte(' ')
		if !isToken(attribute) {
			return ""
		}
		b.WriteString(strings.ToLower(attribute))
		b.WriteByte('=')
		if isToken(value) {
			b.WriteString(value)
			continue
		}

		b.WriteByte('"')
		offset := 0
		for index, character := range value {
			if character == '"' || character == '\\' {
				b.WriteString(value[offset:index])
				offset = index
				b.WriteByte('\\')
			}
			if character&0x80 != 0 {
				return ""
			}
		}
		b.WriteString(value[offset:])
		b.WriteByte('"')
	}
	return b.String()
}

func checkMediaTypeDisposition(s string) error {
	typ, rest := consumeToken(s)
	if typ == "" {
		return errors.New("mime: no media type")
	}
	if rest == "" {
		return nil
	}
	if !strings.HasPrefix(rest, "/") {
		return errors.New("mime: expected slash after first token")
	}
	subtype, rest := consumeToken(rest[1:])
	if subtype == "" {
		return errors.New("mime: expected token after slash")
	}
	if rest != "" {
		return errors.New("mime: unexpected content after media subtype")
	}
	return nil
}

// ParseMediaType parses a media type value and any optional
// parameters, per RFC 1521.  Media types are the values in
// Content-Type and Content-Disposition headers (RFC 2183).
// On success, ParseMediaType returns the media type converted
// to lowercase and trimmed of white space and a non-nil map.
// The returned map, params, maps from the lowercase
// attribute to the attribute value with its case preserved.
func ParseMediaType(v string) (mediatype string, params map[string]string, err error) {
	i := strings.Index(v, ";")
	if i == -1 {
		i = len(v)
	}
	mediatype = strings.TrimSpace(strings.ToLower(v[0:i]))

	err = checkMediaTypeDisposition(mediatype)
	if err != nil {
		return "", nil, err
	}

	params = make(map[string]string)

	// Map of base parameter name -> parameter name -> value
	// for parameters containing a '*' character.
	// Lazily initialized.
	var continuation map[string]map[string]string

	v = v[i:]
	for len(v) > 0 {
		v = strings.TrimLeftFunc(v, unicode.IsSpace)
		if len(v) == 0 {
			break
		}
		key, value, rest := consumeMediaParam(v)
		if key == "" {
			if strings.TrimSpace(rest) == ";" {
				// Ignore trailing semicolons.
				// Not an error.
				return
			}
			// Parse error.
			return "", nil, errors.New("mime: invalid media parameter")
		}

		pmap := params
		if idx := strings.Index(key, "*"); idx != -1 {
			baseName := key[:idx]
			if continuation == nil {
				continuation = make(map[string]map[string]string)
			}
			var ok bool
			if pmap, ok = continuation[baseName]; !ok {
				continuation[baseName] = make(map[string]string)
				pmap = continuation[baseName]
			}
		}
		if _, exists := pmap[key]; exists {
			// Duplicate parameter name is bogus.
			return "", nil, errors.New("mime: duplicate parameter name")
		}
		pmap[key] = value
		v = rest
	}

	// Stitch together any continuations or things with stars
	// (i.e. RFC 2231 things with stars: "foo*0" or "foo*")
	var buf bytes.Buffer
	for key, pieceMap := range continuation {
		singlePartKey := key + "*"
		if v, ok := pieceMap[singlePartKey]; ok {
			decv := decode2231Enc(v)
			params[key] = decv
			continue
		}

		buf.Reset()
		valid := false
		for n := 0; ; n++ {
			simplePart := fmt.Sprintf("%s*%d", key, n)
			if v, ok := pieceMap[simplePart]; ok {
				valid = true
				buf.WriteString(v)
				continue
			}
			encodedPart := simplePart + "*"
			if v, ok := pieceMap[encodedPart]; ok {
				valid = true
				if n == 0 {
					buf.WriteString(decode2231Enc(v))
				} else {
					decv, _ := percentHexUnescape(v)
					buf.WriteString(decv)
				}
			} else {
				break
			}
		}
		if valid {
			params[key] = buf.String()
		}
	}

	return
}

func decode2231Enc(v string) string {
	sv := strings.SplitN(v, "'", 3)
	if len(sv) != 3 {
		return ""
	}
	// TODO: ignoring lang in sv[1] for now. If anybody needs it we'll
	// need to decide how to expose it in the API. But I'm not sure
	// anybody uses it in practice.
	charset := strings.ToLower(sv[0])
	if charset != "us-ascii" && charset != "utf-8" {
		// TODO: unsupported encoding
		return ""
	}
	encv, _ := percentHexUnescape(sv[2])
	return encv
}

func isNotTokenChar(r rune) bool {
	return !isTokenChar(r)
}

// consumeToken consumes a token from the beginning of provided
// string, per RFC 2045 section 5.1 (referenced from 2183), and return
// the token consumed and the rest of the string.  Returns ("", v) on
// failure to consume at least one character.
func consumeToken(v string) (token, rest string) {
	notPos := strings.IndexFunc(v, isNotTokenChar)
	if notPos == -1 {
		return v, ""
	}
	if notPos == 0 {
		return "", v
	}
	return v[0:notPos], v[notPos:]
}

// consumeValue consumes a "value" per RFC 2045, where a value is
// either a 'token' or a 'quoted-string'.  On success, consumeValue
// returns the value consumed (and de-quoted/escaped, if a
// quoted-string) and the rest of the string.  On failure, returns
// ("", v).
func consumeValue(v string) (value, rest string) {
	if !strings.HasPrefix(v, `"`) && !strings.HasPrefix(v, `'`) {
		return consumeToken(v)
	}

	leadQuote := rune(v[0])

	// parse a quoted-string
	rest = v[1:] // consume the leading quote
	buffer := new(bytes.Buffer)
	var idx int
	var r rune
	var nextIsLiteral bool
	for idx, r = range rest {
		switch {
		case nextIsLiteral:
			buffer.WriteRune(r)
			nextIsLiteral = false
		case r == leadQuote:
			return buffer.String(), rest[idx+1:]
		case r == '\\':
			nextIsLiteral = true
		case r != '\r' && r != '\n':
			buffer.WriteRune(r)
		default:
			return "", v
		}
	}
	return "", v
}

func consumeMediaParam(v string) (param, value, rest string) {
	rest = strings.TrimLeftFunc(v, unicode.IsSpace)
	if !strings.HasPrefix(rest, ";") {
		return "", "", v
	}

	rest = rest[1:] // consume semicolon
	rest = strings.TrimLeftFunc(rest, unicode.IsSpace)
	param, rest = consumeToken(rest)
	param = strings.ToLower(param)
	if param == "" {
		return "", "", v
	}

	rest = strings.TrimLeftFunc(rest, unicode.IsSpace)
	if !strings.HasPrefix(rest, "=") {
		return "", "", v
	}
	rest = rest[1:] // consume equals sign
	rest = strings.TrimLeftFunc(rest, unicode.IsSpace)
	value, rest = consumeValue(rest)
	if value == "" {
		return "", "", v
	}
	return param, value, rest
}

func percentHexUnescape(s string) (string, error) {
	// Count %, check that they're well-formed.
	percents := 0
	for i := 0; i < len(s); {
		if s[i] != '%' {
			i++
			continue
		}
		percents++
		if i+2 >= len(s) || !ishex(s[i+1]) || !ishex(s[i+2]) {
			s = s[i:]
			if len(s) > 3 {
				s = s[0:3]
			}
			return "", fmt.Errorf("mime: bogus characters after %%: %q", s)
		}
		i += 3
	}
	if percents == 0 {
		return s, nil
	}

	t := make([]byte, len(s)-2*percents)
	j := 0
	for i := 0; i < len(s); {
		switch s[i] {
		case '%':
			t[j] = unhex(s[i+1])<<4 | unhex(s[i+2])
			j++
			i += 3
		default:
			t[j] = s[i]
			j++
			i++
		}
	}
	return string(t), nil
}

func ishex(c byte) bool {
	switch {
	case '0' <= c && c <= '9':
		return true
	case 'a' <= c && c <= 'f':
		return true
	case 'A' <= c && c <= 'F':
		return true
	}
	return false
}

func unhex(c byte) byte {
	switch {
	case '0' <= c && c <= '9':
		return c - '0'
	case 'a' <= c && c <= 'f':
		return c - 'a' + 10
	case 'A' <= c && c <= 'F':
		return c - 'A' + 10
	}
	return 0
}