summaryrefslogtreecommitdiffstats
path: root/media/mediaType.go
blob: 367c8ecc96ee7b7b24863f52187503efe1e94811 (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
// Copyright 2019 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

// Package media contains Media Type (MIME type) related types and functions.
package media

import (
	"encoding/json"
	"fmt"
	"net/http"
	"strings"
)

var zero Type

const (
	DefaultDelimiter = "."
)

// MediaType (also known as MIME type and content type) is a two-part identifier for
// file formats and format contents transmitted on the Internet.
// For Hugo's use case, we use the top-level type name / subtype name + suffix.
// One example would be application/svg+xml
// If suffix is not provided, the sub type will be used.
// <docsmeta>{ "name": "MediaType" }</docsmeta>
type Type struct {
	// The full MIME type string, e.g. "application/rss+xml".
	Type string `json:"-"`

	// The top-level type name, e.g. "application".
	MainType string `json:"mainType"`
	// The subtype name, e.g. "rss".
	SubType string `json:"subType"`
	// The delimiter before the suffix, e.g. ".".
	Delimiter string `json:"delimiter"`

	// FirstSuffix holds the first suffix defined for this MediaType.
	FirstSuffix SuffixInfo `json:"-"`

	// This is the optional suffix after the "+" in the MIME type,
	//  e.g. "xml" in "application/rss+xml".
	mimeSuffix string

	// E.g. "jpg,jpeg"
	// Stored as a string to make Type comparable.
	// For internal use only.
	SuffixesCSV string `json:"-"`
}

// SuffixInfo holds information about a Media Type's suffix.
type SuffixInfo struct {
	// Suffix is the suffix without the delimiter, e.g. "xml".
	Suffix string `json:"suffix"`

	// FullSuffix is the suffix with the delimiter, e.g. ".xml".
	FullSuffix string `json:"fullSuffix"`
}

// FromContent resolve the Type primarily using http.DetectContentType.
// If http.DetectContentType resolves to application/octet-stream, a zero Type is returned.
// If http.DetectContentType  resolves to text/plain or application/xml, we try to get more specific using types and ext.
func FromContent(types Types, extensionHints []string, content []byte) Type {
	t := strings.Split(http.DetectContentType(content), ";")[0]
	if t == "application/octet-stream" {
		return zero
	}

	var found bool
	m, found := types.GetByType(t)
	if !found {
		if t == "text/xml" {
			// This is how it's configured in Hugo by default.
			m, found = types.GetByType("application/xml")
		}
	}

	if !found {
		return zero
	}

	var mm Type

	for _, extension := range extensionHints {
		extension = strings.TrimPrefix(extension, ".")
		mm, _, found = types.GetFirstBySuffix(extension)
		if found {
			break
		}
	}

	if found {
		if m == mm {
			return m
		}

		if m.IsText() && mm.IsText() {
			// http.DetectContentType isn't brilliant when it comes to common text formats, so we need to do better.
			// For now we say that if it's detected to be a text format and the extension/content type in header reports
			// it to be a text format, then we use that.
			return mm
		}

		// E.g. an image with a *.js extension.
		return zero
	}

	return m
}

// FromStringAndExt creates a Type from a MIME string and a given extension.
func FromStringAndExt(t, ext string) (Type, error) {
	tp, err := FromString(t)
	if err != nil {
		return tp, err
	}
	tp.SuffixesCSV = strings.TrimPrefix(ext, ".")
	tp.Delimiter = DefaultDelimiter
	tp.init()
	return tp, nil
}

// FromString creates a new Type given a type string on the form MainType/SubType and
// an optional suffix, e.g. "text/html" or "text/html+html".
func FromString(t string) (Type, error) {
	t = strings.ToLower(t)
	parts := strings.Split(t, "/")
	if len(parts) != 2 {
		return Type{}, fmt.Errorf("cannot parse %q as a media type", t)
	}
	mainType := parts[0]
	subParts := strings.Split(parts[1], "+")

	subType := strings.Split(subParts[0], ";")[0]

	var suffix string

	if len(subParts) > 1 {
		suffix = subParts[1]
	}

	var typ string
	if suffix != "" {
		typ = mainType + "/" + subType + "+" + suffix
	} else {
		typ = mainType + "/" + subType
	}

	return Type{Type: typ, MainType: mainType, SubType: subType, mimeSuffix: suffix}, nil
}

// For internal use.
func (m Type) String() string {
	return m.Type
}

// Suffixes returns all valid file suffixes for this type.
func (m Type) Suffixes() []string {
	if m.SuffixesCSV == "" {
		return nil
	}

	return strings.Split(m.SuffixesCSV, ",")
}

// IsText returns whether this Type is a text format.
// Note that this may currently return false negatives.
// TODO(bep) improve
// For internal use.
func (m Type) IsText() bool {
	if m.MainType == "text" {
		return true
	}
	switch m.SubType {
	case "javascript", "json", "rss", "xml", "svg", "toml", "yml", "yaml":
		return true
	}
	return false
}

func InitMediaType(m *Type) {
	m.init()
}

func (m *Type) init() {
	m.FirstSuffix.FullSuffix = ""
	m.FirstSuffix.Suffix = ""
	if suffixes := m.Suffixes(); suffixes != nil {
		m.FirstSuffix.Suffix = suffixes[0]
		m.FirstSuffix.FullSuffix = m.Delimiter + m.FirstSuffix.Suffix
	}
}

func newMediaType(main, sub string, suffixes []string) Type {
	t := Type{MainType: main, SubType: sub, SuffixesCSV: strings.Join(suffixes, ","), Delimiter: DefaultDelimiter}
	t.init()
	return t
}

func newMediaTypeWithMimeSuffix(main, sub, mimeSuffix string, suffixes []string) Type {
	mt := newMediaType(main, sub, suffixes)
	mt.mimeSuffix = mimeSuffix
	mt.init()
	return mt
}

// Types is a slice of media types.
// <docsmeta>{ "name": "MediaTypes" }</docsmeta>
type Types []Type

func (t Types) Len() int           { return len(t) }
func (t Types) Swap(i, j int)      { t[i], t[j] = t[j], t[i] }
func (t Types) Less(i, j int) bool { return t[i].Type < t[j].Type }

// GetByType returns a media type for tp.
func (t Types) GetByType(tp string) (Type, bool) {
	for _, tt := range t {
		if strings.EqualFold(tt.Type, tp) {