marcel 0.3.2 → 1.0.2

Sign up to get free protection for your applications and to get access to all the features.
Files changed (117) hide show
  1. checksums.yaml +4 -4
  2. data/APACHE-LICENSE +202 -0
  3. data/README.md +39 -21
  4. data/lib/marcel/magic.rb +147 -0
  5. data/lib/marcel/mime_type/definitions.rb +30 -3
  6. data/lib/marcel/mime_type.rb +68 -67
  7. data/lib/marcel/tables.rb +2525 -0
  8. data/lib/marcel/version.rb +1 -1
  9. data/lib/marcel.rb +3 -2
  10. metadata +39 -230
  11. data/.gitignore +0 -1
  12. data/.travis.yml +0 -7
  13. data/Gemfile +0 -4
  14. data/Gemfile.lock +0 -26
  15. data/Rakefile +0 -33
  16. data/marcel.gemspec +0 -28
  17. data/test/declared_type_test.rb +0 -17
  18. data/test/extension_test.rb +0 -25
  19. data/test/fixtures/image.gif +0 -0
  20. data/test/fixtures/magic/application/msword/msword.doc +0 -0
  21. data/test/fixtures/magic/application/pdf/illustrator-seen-as-pdf.ai +22 -6302
  22. data/test/fixtures/magic/application/pdf/pdf.pdf +0 -0
  23. data/test/fixtures/magic/application/rtf/rtf.rtf +0 -1
  24. data/test/fixtures/magic/application/vnd.adobe.flash.movie/flash.swf +0 -0
  25. data/test/fixtures/magic/application/vnd.openxmlformats-officedocument.presentationml.presentation/vnd.openxmlformats-officedocument.presentationml.presentation.pptx +0 -0
  26. data/test/fixtures/magic/application/vnd.openxmlformats-officedocument.spreadsheetml.sheet/vnd.openxmlformats-officedocument.spreadsheetml.sheet.xlsx +0 -0
  27. data/test/fixtures/magic/application/vnd.openxmlformats-officedocument.wordprocessingml.document/vnd.openxmlformats-officedocument.wordprocessingml.document.docx +0 -0
  28. data/test/fixtures/magic/application/x-font-ttf.ttf +0 -0
  29. data/test/fixtures/magic/application/xml/xml.xml +0 -1
  30. data/test/fixtures/magic/application/zip/sketch.sketch +0 -0
  31. data/test/fixtures/magic/application/zip/zip.zip +0 -0
  32. data/test/fixtures/magic/audio/flac/flac.flac +0 -0
  33. data/test/fixtures/magic/audio/mp4/m4a.m4a +0 -0
  34. data/test/fixtures/magic/audio/mp4/mp4.m4a +0 -0
  35. data/test/fixtures/magic/audio/mpeg/mpeg.mp3 +0 -0
  36. data/test/fixtures/magic/audio/x-wav/wav.wav +0 -0
  37. data/test/fixtures/magic/audio/x-wav/x-wav.wav +0 -0
  38. data/test/fixtures/magic/image/bmp/bmp.bmp +0 -0
  39. data/test/fixtures/magic/image/gif/gif.gif +0 -0
  40. data/test/fixtures/magic/image/jpeg/jpeg.jpg +0 -0
  41. data/test/fixtures/magic/image/png/png.png +0 -0
  42. data/test/fixtures/magic/image/svg+xml/svg.svg +0 -1
  43. data/test/fixtures/magic/image/tiff/tiff.tif +0 -0
  44. data/test/fixtures/magic/image/vnd.adobe.photoshop/photoshop-large-document-format.psb +0 -0
  45. data/test/fixtures/magic/image/vnd.adobe.photoshop/vnd.adobe.photoshop.psd +0 -0
  46. data/test/fixtures/magic/image/vnd.dwg/x-dwg.dwg +0 -0
  47. data/test/fixtures/magic/image/vnd.microsoft.icon/ico.ico +0 -0
  48. data/test/fixtures/magic/image/webp/webp.webp +0 -0
  49. data/test/fixtures/magic/image/x-eps/postscript/postscript.eps +0 -0
  50. data/test/fixtures/magic/image/x-eps/x-eps.eps +0 -0
  51. data/test/fixtures/magic/text/html/html.html +0 -3
  52. data/test/fixtures/magic/video/mp4/m4v.m4v +0 -0
  53. data/test/fixtures/magic/video/mp4/mp4.mp4 +0 -0
  54. data/test/fixtures/magic/video/quicktime/quicktime.mov +0 -0
  55. data/test/fixtures/magic/video/webm/webm.mkv +0 -0
  56. data/test/fixtures/name/application/illustrator/illustrator.ai +27 -6301
  57. data/test/fixtures/name/application/javascript/javascript.js +0 -3
  58. data/test/fixtures/name/application/json/json.json +0 -3
  59. data/test/fixtures/name/application/msword/msword.doc +0 -0
  60. data/test/fixtures/name/application/pdf/pdf.pdf +0 -0
  61. data/test/fixtures/name/application/rtf/rtf.rtf +0 -1
  62. data/test/fixtures/name/application/sql/sql.sql +0 -0
  63. data/test/fixtures/name/application/vnd.adobe.flash.movie/flash.swf +0 -0
  64. data/test/fixtures/name/application/vnd.android.package-archive/vnd.android.package-archive.apk +0 -0
  65. data/test/fixtures/name/application/vnd.apple.keynote/vnd.apple.keynote.key +0 -0
  66. data/test/fixtures/name/application/vnd.apple.numbers/vnd.apple.numbers.numbers +0 -0
  67. data/test/fixtures/name/application/vnd.apple.pages/vnd.apple.pages.pages +0 -0
  68. data/test/fixtures/name/application/vnd.ms-excel/vnd.ms-excel.xls +0 -0
  69. data/test/fixtures/name/application/vnd.ms-excel.sheet.binary.macroenabled.12/vnd.ms-excel.sheet.binary.macroenabled.12.xlsb +0 -0
  70. data/test/fixtures/name/application/vnd.ms-excel.sheet.macroenabled.12/vnd.ms-excel.sheet.macroenabled.12.xlsm +0 -0
  71. data/test/fixtures/name/application/vnd.ms-excel.template.macroenabled.12/vnd.ms-excel.template.macroenabled.12.xltm +0 -0
  72. data/test/fixtures/name/application/vnd.ms-powerpoint/vnd.ms-powerpoint.ppt +0 -0
  73. data/test/fixtures/name/application/vnd.ms-powerpoint.presentation.macroenabled.12/vnd.ms-powerpoint.presentation.macroenabled.12.pptm +0 -0
  74. data/test/fixtures/name/application/vnd.ms-powerpoint.slideshow.macroenabled.12/vnd.ms-powerpoint.slideshow.macroenabled.12.ppsm +0 -0
  75. data/test/fixtures/name/application/vnd.ms-powerpoint.template.macroenabled.12/vnd.ms-powerpoint.template.macroenabled.12.potm +0 -0
  76. data/test/fixtures/name/application/vnd.ms-word.document.macroenabled.12/vnd.ms-word.document.macroenabled.12.docm +0 -0
  77. data/test/fixtures/name/application/vnd.ms-word.template.macroenabled.12/vnd.ms-word.template.macroenabled.12.dotm +0 -0
  78. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.presentationml.presentation/vnd.openxmlformats-officedocument.presentationml.presentation.pptx +0 -0
  79. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.presentationml.slideshow/vnd.openxmlformats-officedocument.presentationml.slideshow.ppsx +0 -0
  80. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.presentationml.template/vnd.openxmlformats-officedocument.presentationml.template.potx +0 -0
  81. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.spreadsheetml.sheet/downloaded-from-google-docs.xlsx +0 -0
  82. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.spreadsheetml.sheet/vnd.openxmlformats-officedocument.spreadsheetml.sheet.xlsx +0 -0
  83. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.wordprocessingml.document/vnd.openxmlformats-officedocument.wordprocessingml.document.docx +0 -0
  84. data/test/fixtures/name/application/vnd.openxmlformats-officedocument.wordprocessingml.template/vnd.openxmlformats-officedocument.wordprocessingml.template.dotx +0 -0
  85. data/test/fixtures/name/application/x-font-ttf.ttf +0 -0
  86. data/test/fixtures/name/application/zip/zip.zip +0 -0
  87. data/test/fixtures/name/audio/flac/flac.flac +0 -0
  88. data/test/fixtures/name/audio/mp4/mp4.m4a +0 -0
  89. data/test/fixtures/name/audio/mpeg/mpeg.mp3 +0 -0
  90. data/test/fixtures/name/audio/x-wav/x-wav.wav +0 -0
  91. data/test/fixtures/name/image/bmp/bmp.bmp +0 -0
  92. data/test/fixtures/name/image/gif/gif.gif +0 -0
  93. data/test/fixtures/name/image/heic.heic +0 -0
  94. data/test/fixtures/name/image/heif.heif +0 -0
  95. data/test/fixtures/name/image/jpeg/jpeg.jpg +0 -0
  96. data/test/fixtures/name/image/png/png.png +0 -0
  97. data/test/fixtures/name/image/svg+xml/svg.svg +0 -1
  98. data/test/fixtures/name/image/tiff/tiff.tif +0 -0
  99. data/test/fixtures/name/image/tiff/tiff.tiff +0 -0
  100. data/test/fixtures/name/image/vnd.adobe.photoshop/saved-as-large-document-format.psb +0 -0
  101. data/test/fixtures/name/image/vnd.adobe.photoshop/vnd.adobe.photoshop.psd +0 -0
  102. data/test/fixtures/name/image/x-eps/postscript/postscript.eps +0 -0
  103. data/test/fixtures/name/image/x-eps/x-eps.eps +0 -0
  104. data/test/fixtures/name/message/rfc822/rfc822.eml +0 -34
  105. data/test/fixtures/name/text/csv/csv.csv +0 -2
  106. data/test/fixtures/name/text/html/html.html +0 -3
  107. data/test/fixtures/name/text/plain/plain.asc +0 -1
  108. data/test/fixtures/name/text/plain/plain.txt +0 -1
  109. data/test/fixtures/name/text/x-log/x-log.log +0 -1
  110. data/test/fixtures/name/video/mp4/mp4.mp4 +0 -0
  111. data/test/fixtures/name/video/quicktime/quicktime.mov +0 -0
  112. data/test/magic_and_declared_type_test.rb +0 -10
  113. data/test/magic_and_name_test.rb +0 -13
  114. data/test/magic_test.rb +0 -13
  115. data/test/mime_type_test.rb +0 -47
  116. data/test/name_test.rb +0 -10
  117. data/test/test_helper.rb +0 -49
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 57f17eae54469b574b2c7ce541bf2c6cf82f180456f6d1f133dd99c13585fbb0
4
- data.tar.gz: b73e492f9d3b2b58abc751ea29a9c5da7fe5c7ef372da6c472c16c3708edd579
3
+ metadata.gz: 35fe8aac124b049b86f375622d6255bb549fa4c972db38f27328472c96a74497
4
+ data.tar.gz: 9b4800e39fa6c1506acb964730567f4457a2b5e89be6c0fc271144f2dc5b34f8
5
5
  SHA512:
6
- metadata.gz: 140466ed263e260c2936d619d27b584af4b377f02c05acb508a0246cc55730a371023ebc93a183152b593529aac6071a374def41b686d523b85f37818c26b6b9
7
- data.tar.gz: 95f8f724211e266bf3a3ccedfed7c78fd7e35376d74d28e63ceabf538a5945fc01319115391f060bc84cd91ec18e7ed64aa0f607edff83a1026c2fe48a5bfbb5
6
+ metadata.gz: cbf93f7d5b30bcb3927c49fe3cbcc238f040689178a810892be64095908112dbe27381a438bb7d6cf89980af14e82b52d46263f9df8577d2836c5dbd9858771b
7
+ data.tar.gz: 787c8be7892b97d02b96edf1340656d43c98829a187f7d90d7b720b188d793e26c8c34f55f1e7529ed646f0e7cb6d8ed8fd87c7b4299510ffed89f7d03cc23b5
data/APACHE-LICENSE ADDED
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
data/README.md CHANGED
@@ -4,47 +4,65 @@ Marcel attempts to choose the most appropriate content type for a given file by
4
4
 
5
5
  It's used like this:
6
6
 
7
- Marcel::MimeType.for Pathname.new("example.gif")
8
- => "image/gif"
7
+ ```ruby
8
+ Marcel::MimeType.for Pathname.new("example.gif")
9
+ # => "image/gif"
9
10
 
10
- File.open "example.gif" do |file|
11
- Marcel::MimeType.for file
12
- end
13
- => "image/gif"
11
+ File.open "example.gif" do |file|
12
+ Marcel::MimeType.for file
13
+ end
14
+ # => "image/gif"
14
15
 
15
- Marcel::MimeType.for Pathname.new("unrecognisable-data"), name: "example.pdf"
16
- => "application/pdf"
16
+ Marcel::MimeType.for Pathname.new("unrecognisable-data"), name: "example.pdf"
17
+ # => "application/pdf"
17
18
 
18
- Marcel::MimeType.for extension: ".pdf"
19
- => "application/pdf"
19
+ Marcel::MimeType.for extension: ".pdf"
20
+ # => "application/pdf"
20
21
 
21
- Marcel::MimeType.for Pathname.new("unrecognisable-data"), name: "example", declared_type: "image/png"
22
- => "image/png"
22
+ Marcel::MimeType.for Pathname.new("unrecognisable-data"), name: "example", declared_type: "image/png"
23
+ # => "image/png"
23
24
 
24
- Marcel::MimeType.for StringIO.new(File.read "unrecognisable-data")
25
- => "application/octet-stream"
25
+ Marcel::MimeType.for StringIO.new(File.read "unrecognisable-data")
26
+ # => "application/octet-stream"
27
+ ```
26
28
 
27
29
  By preference, the magic number data in any passed in file is used to determine the type. If this doesn't work, it uses the type gleaned from the filename, extension, and finally the declared type. If no valid type is found in any of these, "application/octet-stream" is returned.
28
30
 
29
31
  Some types aren't easily recognised solely by magic number data. For example Adobe Illustrator files have the same magic number as PDFs (and can usually even be viewed in PDF viewers!). For these types, Marcel uses both the magic number data and the file name to work out the type:
30
32
 
31
- Marcel::MimeType.for Pathname.new("example.ai"), name: "example.ai"
32
- => "application/illustrator"
33
+ ```ruby
34
+ Marcel::MimeType.for Pathname.new("example.ai"), name: "example.ai"
35
+ # => "application/illustrator"
36
+ ```
33
37
 
34
38
  This only happens when the type from the filename is a more specific type of that from the magic number. If it isn't the magic number alone is used.
35
39
 
36
- Marcel::MimeType.for Pathname.new("example.png"), name: "example.ai"
37
- => "image/png"
38
- # As "application/illustrator" is not a more specific type of "image/png", the filename is ignored
40
+ ```ruby
41
+ Marcel::MimeType.for Pathname.new("example.png"), name: "example.ai"
42
+ # => "image/png"
43
+ # As "application/illustrator" is not a more specific type of "image/png", the filename is ignored
44
+ ```
39
45
 
40
46
  ## Motivation
41
47
 
42
48
  Marcel was extracted from Basecamp 3, in order to make our file detection logic both easily reusable but more importantly, easily testable. Test fixtures have been added for all of the most common file types uploaded to Basecamp, and other common file types too. We hope to expand this test coverage with other file types as and when problems are identified.
43
49
 
44
- ## Implementation
50
+ ## Contributing
45
51
 
46
- At present, marcel is mainly a thin wrapper around the mimemagic gem. It adds priority logic (preferring magic over name when given both), some extra type definitions, and common type subclasses (including Keynote, Pages, etc).
52
+ Marcel generates MIME lookup tables with `bundle exec rake tables`. MIME types are seeded from data found in `data/*.xml`. Custom MIMEs may be added to `data/custom.xml`, while overrides to the standard MIME database may be added to `lib/marcel/mime_type/definitions.rb`.
53
+
54
+ Marcel follows the same contributing guidelines as [rails/rails](https://github.com/rails/rails#contributing).
47
55
 
48
56
  ## Testing
49
57
 
50
58
  The main test fixture files are split into two folders, those that can be recognised by magic numbers, and those that can only be recognised by name. Even though strictly unnecessary, the fixtures in both folders should all be valid files of the type they represent.
59
+
60
+ ## License
61
+
62
+ Marcel itself is released under the terms of the MIT License. See the MIT-LICENSE file for details.
63
+
64
+ Portions of Marcel are adapted from the [mimemagic] gem, released under the terms of the MIT License.
65
+
66
+ Marcel's magic signature data is adapted from [Apache Tika](https://tika.apache.org), released under the terms of the Apache License. See the APACHE-LICENSE file for details.
67
+
68
+ [mimemagic]: https://github.com/mimemagicrb/mimemagic
@@ -0,0 +1,147 @@
1
+ # frozen_string_literal: true
2
+
3
+ # Code in this file adapted from the mimemagic gem, released under the MIT License.
4
+ # Copyright (c) 2011 Daniel Mendler. Available at https://github.com/mimemagicrb/mimemagic.
5
+
6
+ require 'marcel/tables'
7
+
8
+ require 'stringio'
9
+
10
+ module Marcel
11
+ # Mime type detection
12
+ class Magic
13
+ attr_reader :type, :mediatype, :subtype
14
+
15
+ # Mime type by type string
16
+ def initialize(type)
17
+ @type = type
18
+ @mediatype, @subtype = type.split('/', 2)
19
+ end
20
+
21
+ # Add custom mime type. Arguments:
22
+ # * <i>type</i>: Mime type
23
+ # * <i>options</i>: Options hash
24
+ #
25
+ # Option keys:
26
+ # * <i>:extensions</i>: String list or single string of file extensions
27
+ # * <i>:parents</i>: String list or single string of parent mime types
28
+ # * <i>:magic</i>: Mime magic specification
29
+ # * <i>:comment</i>: Comment string
30
+ def self.add(type, options)
31
+ extensions = [options[:extensions]].flatten.compact
32
+ TYPES[type] = [extensions,
33
+ [options[:parents]].flatten.compact,
34
+ options[:comment]]
35
+ extensions.each {|ext| EXTENSIONS[ext] = type }
36
+ MAGIC.unshift [type, options[:magic]] if options[:magic]
37
+ end
38
+
39
+ # Removes a mime type from the dictionary. You might want to do this if
40
+ # you're seeing impossible conflicts (for instance, application/x-gmc-link).
41
+ # * <i>type</i>: The mime type to remove. All associated extensions and magic are removed too.
42
+ def self.remove(type)
43
+ EXTENSIONS.delete_if {|ext, t| t == type }
44
+ MAGIC.delete_if {|t, m| t == type }
45
+ TYPES.delete(type)
46
+ end
47
+
48
+ # Returns true if type is a text format
49
+ def text?; mediatype == 'text' || child_of?('text/plain'); end
50
+
51
+ # Mediatype shortcuts
52
+ def image?; mediatype == 'image'; end
53
+ def audio?; mediatype == 'audio'; end
54
+ def video?; mediatype == 'video'; end
55
+
56
+ # Returns true if type is child of parent type
57
+ def child_of?(parent)
58
+ self.class.child?(type, parent)
59
+ end
60
+
61
+ # Get string list of file extensions
62
+ def extensions
63
+ TYPES.key?(type) ? TYPES[type][0] : []
64
+ end
65
+
66
+ # Get mime comment
67
+ def comment
68
+ (TYPES.key?(type) ? TYPES[type][2] : nil).to_s
69
+ end
70
+
71
+ # Lookup mime type by file extension
72
+ def self.by_extension(ext)
73
+ ext = ext.to_s.downcase
74
+ mime = ext[0..0] == '.' ? EXTENSIONS[ext[1..-1]] : EXTENSIONS[ext]
75
+ mime && new(mime)
76
+ end
77
+
78
+ # Lookup mime type by filename
79
+ def self.by_path(path)
80
+ by_extension(File.extname(path))
81
+ end
82
+
83
+ # Lookup mime type by magic content analysis.
84
+ # This is a slow operation.
85
+ def self.by_magic(io)
86
+ mime = magic_match(io, :find)
87
+ mime && new(mime[0])
88
+ end
89
+
90
+ # Lookup all mime types by magic content analysis.
91
+ # This is a slower operation.
92
+ def self.all_by_magic(io)
93
+ magic_match(io, :select).map { |mime| new(mime[0]) }
94
+ end
95
+
96
+ # Return type as string
97
+ def to_s
98
+ type
99
+ end
100
+
101
+ # Allow comparison with string
102
+ def eql?(other)
103
+ type == other.to_s
104
+ end
105
+
106
+ def hash
107
+ type.hash
108
+ end
109
+
110
+ alias == eql?
111
+
112
+ def self.child?(child, parent)
113
+ child == parent || TYPES.key?(child) && TYPES[child][1].any? {|p| child?(p, parent) }
114
+ end
115
+
116
+ def self.magic_match(io, method)
117
+ return magic_match(StringIO.new(io.to_s), method) unless io.respond_to?(:read)
118
+
119
+ io.binmode if io.respond_to?(:binmode)
120
+ io.set_encoding(Encoding::BINARY) if io.respond_to?(:set_encoding)
121
+ buffer = "".encode(Encoding::BINARY)
122
+
123
+ MAGIC.send(method) { |type, matches| magic_match_io(io, matches, buffer) }
124
+ end
125
+
126
+ def self.magic_match_io(io, matches, buffer)
127
+ matches.any? do |offset, value, children|
128
+ match =
129
+ if value
130
+ if Range === offset
131
+ io.read(offset.begin, buffer)
132
+ x = io.read(offset.end - offset.begin + value.bytesize, buffer)
133
+ x && x.include?(value)
134
+ else
135
+ io.read(offset, buffer)
136
+ io.read(value.bytesize, buffer) == value
137
+ end
138
+ end
139
+
140
+ io.rewind
141
+ match && (!children || magic_match_io(io, children, buffer))
142
+ end
143
+ end
144
+
145
+ private_class_method :magic_match, :magic_match_io
146
+ end
147
+ end
@@ -1,6 +1,3 @@
1
- require 'mimemagic'
2
- require 'mimemagic/overlay'
3
-
4
1
  Marcel::MimeType.extend "text/plain", extensions: %w( txt asc )
5
2
 
6
3
  Marcel::MimeType.extend "application/illustrator", parents: "application/pdf"
@@ -33,7 +30,37 @@ Marcel::MimeType.extend "application/vnd.apple.pages", extensions: %w( pages ),
33
30
  Marcel::MimeType.extend "application/vnd.apple.numbers", extensions: %w( numbers ), parents: "application/zip"
34
31
  Marcel::MimeType.extend "application/vnd.apple.keynote", extensions: %w( key ), parents: "application/zip"
35
32
 
33
+ Marcel::MimeType.extend "audio/aac", extensions: %w( aac ), parents: "audio/x-aac"
34
+
35
+
36
36
  Marcel::MimeType.extend "image/vnd.dwg", magic: [[0, "AC10"]]
37
37
 
38
+ Marcel::MimeType.extend "application/x-x509-ca-cert", magic: [[0, '-----BEGIN CERTIFICATE-----']], extensions: %w( pem ), parents: "application/x-x509-cert;format=pem"
39
+
40
+ Marcel::MimeType.extend "image/avif", magic: [[4, "ftypavif"]], extensions: %w( avif )
38
41
  Marcel::MimeType.extend "image/heif", magic: [[4, "ftypmif1"]], extensions: %w( heif )
39
42
  Marcel::MimeType.extend "image/heic", magic: [[4, "ftypheic"]], extensions: %w( heic )
43
+
44
+ Marcel::MimeType.extend "video/mp4", magic: [[4, "ftypisom"], [4, "ftypM4V "]], extensions: %w( mp4 m4v )
45
+
46
+ Marcel::MimeType.extend "audio/flac", magic: [[0, 'fLaC']], extensions: %w( flac ), parents: "audio/x-flac"
47
+ Marcel::MimeType.extend "audio/x-wav", magic: [[0, 'RIFF', [[8, 'WAVE']]]], extensions: %w( wav ), parents: "audio/vnd.wav"
48
+ Marcel::MimeType.extend "audio/mpc", magic: [[0, "MPCKSH"]], extensions: %w( mpc )
49
+
50
+ Marcel::MimeType.extend "font/ttf", magic: [[0, "\x00\x01\x00\x00"]], extensions: %w( ttf ttc )
51
+ Marcel::MimeType.extend "font/otf", magic: [[0, "OTTO"]], extensions: %w( otf ), parents: "font/ttf"
52
+ Marcel::MimeType.extend "application/vnd.adobe.flash.movie", magic: [[0, "FWS"], [0, "CWS"]], extensions: %w( swf )
53
+ Marcel::MimeType.extend "application/sql", extensions: %w( sql )
54
+ Marcel::MimeType.extend "text/vcard", magic: [[0, "BEGIN:VCARD"]], extensions: %w( vcf ), parents: "text/plain"
55
+
56
+ Marcel::MimeType.extend(
57
+ "application/vnd.ms-access",
58
+ extensions: %w( mdb mde accdb accde ),
59
+ magic: [
60
+ [0, "\x00\x01\x00\x00\x53\x74\x61\x6e\x64\x61\x72\x64\x20\x4a\x65\x74\x20\x44\x42"], # \x00\x01\x00\xStandard Jet DB
61
+ [0, "\x00\x01\x00\x00\x53\x74\x61\x6e\x64\x61\x72\x64\x20\x41\x43\x45\x20\x44\x42"], # \x00\x01\x00\xStandard ACE DB
62
+ ],
63
+ parents: "application/x-msaccess"
64
+ )
65
+
66
+ Marcel::MimeType.extend "text/markdown", extensions: %w(md mdtext markdown mkd), parents: "text/x-web-markdown"
@@ -1,97 +1,98 @@
1
- class Marcel::MimeType
2
- BINARY = "application/octet-stream"
1
+ module Marcel
2
+ class MimeType
3
+ BINARY = "application/octet-stream"
3
4
 
4
- class << self
5
- def extend(type, extensions: [], parents: [], magic: nil)
6
- existing = MimeMagic::TYPES[type] || [[], [], ""]
5
+ class << self
6
+ def extend(type, extensions: [], parents: [], magic: nil)
7
+ existing = Marcel::TYPES[type] || [[], [], ""]
7
8
 
8
- extensions = (Array(extensions) + existing[0]).uniq
9
- parents = (Array(parents) + existing[1]).uniq
10
- comment = existing[2]
9
+ extensions = (Array(extensions) + existing[0]).uniq
10
+ parents = (Array(parents) + existing[1]).uniq
11
+ comment = existing[2]
11
12
 
12
- MimeMagic.add(type, extensions: extensions, magic: magic, parents: parents, comment: comment)
13
- end
13
+ Magic.add(type, extensions: extensions, magic: magic, parents: parents, comment: comment)
14
+ end
14
15
 
15
- def for(pathname_or_io = nil, name: nil, extension: nil, declared_type: nil)
16
- type_from_data = for_data(pathname_or_io)
17
- fallback_type = for_declared_type(declared_type) || for_name(name) || for_extension(extension) || BINARY
16
+ def for(pathname_or_io = nil, name: nil, extension: nil, declared_type: nil)
17
+ type_from_data = for_data(pathname_or_io)
18
+ fallback_type = for_declared_type(declared_type) || for_name(name) || for_extension(extension) || BINARY
18
19
 
19
- if type_from_data
20
- most_specific_type type_from_data, fallback_type
21
- else
22
- fallback_type
20
+ if type_from_data
21
+ most_specific_type type_from_data, fallback_type
22
+ else
23
+ fallback_type
24
+ end
23
25
  end
24
- end
25
26
 
26
- private
27
- def for_data(pathname_or_io)
28
- if pathname_or_io
29
- with_io(pathname_or_io) do |io|
30
- if magic = MimeMagic.by_magic(io)
31
- magic.type.downcase
27
+ private
28
+ def for_data(pathname_or_io)
29
+ if pathname_or_io
30
+ with_io(pathname_or_io) do |io|
31
+ if magic = Marcel::Magic.by_magic(io)
32
+ magic.type.downcase
33
+ end
32
34
  end
33
35
  end
34
36
  end
35
- end
36
37
 
37
- def for_name(name)
38
- if name
39
- if magic = MimeMagic.by_path(name)
40
- magic.type.downcase
38
+ def for_name(name)
39
+ if name
40
+ if magic = Marcel::Magic.by_path(name)
41
+ magic.type.downcase
42
+ end
41
43
  end
42
44
  end
43
- end
44
45
 
45
- def for_extension(extension)
46
- if extension
47
- if magic = MimeMagic.by_extension(extension)
48
- magic.type.downcase
46
+ def for_extension(extension)
47
+ if extension
48
+ if magic = Marcel::Magic.by_extension(extension)
49
+ magic.type.downcase
50
+ end
49
51
  end
50
52
  end
51
- end
52
53
 
53
- def for_declared_type(declared_type)
54
- type = parse_media_type(declared_type)
54
+ def for_declared_type(declared_type)
55
+ type = parse_media_type(declared_type)
55
56
 
56
- if type != BINARY && !type.nil?
57
- type.downcase
57
+ if type != BINARY && !type.nil?
58
+ type.downcase
59
+ end
58
60
  end
59
- end
60
61
 
61
- def with_io(pathname_or_io, &block)
62
- case pathname_or_io
63
- when Pathname
64
- pathname_or_io.open &block
65
- else
66
- yield pathname_or_io
62
+ def with_io(pathname_or_io, &block)
63
+ if defined?(Pathname) && pathname_or_io.is_a?(Pathname)
64
+ pathname_or_io.open(&block)
65
+ else
66
+ yield pathname_or_io
67
+ end
67
68
  end
68
- end
69
69
 
70
- def parse_media_type(content_type)
71
- if content_type
72
- result = content_type.downcase.split(/[;,\s]/, 2).first
73
- result if result && result.index("/")
70
+ def parse_media_type(content_type)
71
+ if content_type
72
+ result = content_type.downcase.split(/[;,\s]/, 2).first
73
+ result if result && result.index("/")
74
+ end
74
75
  end
75
- end
76
76
 
77
- # For some document types (notably Microsoft Office) we recognise the main content
78
- # type with magic, but not the specific subclass. In this situation, if we can get a more
79
- # specific class using either the name or declared_type, we should use that in preference
80
- def most_specific_type(from_magic_type, fallback_type)
81
- if (root_types(from_magic_type) & root_types(fallback_type)).any?
82
- fallback_type
83
- else
84
- from_magic_type
77
+ # For some document types (notably Microsoft Office) we recognise the main content
78
+ # type with magic, but not the specific subclass. In this situation, if we can get a more
79
+ # specific class using either the name or declared_type, we should use that in preference
80
+ def most_specific_type(from_magic_type, fallback_type)
81
+ if (root_types(from_magic_type) & root_types(fallback_type)).any?
82
+ fallback_type
83
+ else
84
+ from_magic_type
85
+ end
85
86
  end
86
- end
87
87
 
88
- def root_types(type)
89
- if MimeMagic::TYPES[type].nil? || MimeMagic::TYPES[type][1].empty?
90
- [ type ]
91
- else
92
- MimeMagic::TYPES[type][1].map {|t| root_types t }.flatten
88
+ def root_types(type)
89
+ if TYPES[type].nil? || TYPES[type][1].empty?
90
+ [ type ]
91
+ else
92
+ TYPES[type][1].map {|t| root_types t }.flatten
93
+ end
93
94
  end
94
- end
95
+ end
95
96
  end
96
97
  end
97
98