libis-format 1.3.4 → 2.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (78) hide show
  1. checksums.yaml +4 -4
  2. data/.coveralls.yml +2 -0
  3. data/.gitignore +20 -0
  4. data/.travis.yml +70 -0
  5. data/Gemfile +0 -12
  6. data/README.md +2 -2
  7. data/Rakefile +8 -0
  8. data/base/Dockerfile +35 -0
  9. data/base/Dockerfile.alpine +20 -0
  10. data/base/Dockerfile.rvm +56 -0
  11. data/base/rework_path +20 -0
  12. data/bin/{pdf_tool → pdf_copy} +2 -3
  13. data/data/PDFA_def.ps +3 -3
  14. data/data/eciRGB_v2.icc +0 -0
  15. data/data/types.yml +4 -17
  16. data/docker_cfg.yml +1 -0
  17. data/lib/libis/format/cli/convert.rb +4 -4
  18. data/lib/libis/format/cli/prompt_helper.rb +24 -32
  19. data/lib/libis/format/command_line.rb +3 -2
  20. data/lib/libis/format/config.rb +23 -19
  21. data/lib/libis/format/converter/audio_converter.rb +31 -56
  22. data/lib/libis/format/converter/base.rb +36 -16
  23. data/lib/libis/format/converter/chain.rb +32 -52
  24. data/lib/libis/format/converter/fop_pdf_converter.rb +8 -4
  25. data/lib/libis/format/converter/image_assembler.rb +82 -0
  26. data/lib/libis/format/converter/image_converter.rb +45 -250
  27. data/lib/libis/format/converter/image_splitter.rb +80 -0
  28. data/lib/libis/format/converter/image_watermarker.rb +261 -0
  29. data/lib/libis/format/converter/jp2_converter.rb +38 -36
  30. data/lib/libis/format/converter/office_converter.rb +28 -22
  31. data/lib/libis/format/converter/pdf_assembler.rb +66 -0
  32. data/lib/libis/format/converter/pdf_converter.rb +52 -200
  33. data/lib/libis/format/converter/pdf_optimizer.rb +70 -0
  34. data/lib/libis/format/converter/pdf_splitter.rb +65 -0
  35. data/lib/libis/format/converter/pdf_watermarker.rb +110 -0
  36. data/lib/libis/format/converter/repository.rb +13 -7
  37. data/lib/libis/format/converter/spreadsheet_converter.rb +16 -10
  38. data/lib/libis/format/converter/video_converter.rb +58 -47
  39. data/lib/libis/format/converter/xslt_converter.rb +11 -13
  40. data/lib/libis/format/converter.rb +1 -1
  41. data/lib/libis/format/identifier.rb +46 -44
  42. data/lib/libis/format/info.rb +27 -0
  43. data/lib/libis/format/library.rb +147 -0
  44. data/lib/libis/format/tool/droid.rb +30 -29
  45. data/lib/libis/format/tool/extension_identification.rb +26 -24
  46. data/lib/libis/format/tool/{ff_mpeg.rb → ffmpeg.rb} +10 -17
  47. data/lib/libis/format/tool/fido.rb +27 -22
  48. data/lib/libis/format/tool/file_tool.rb +24 -11
  49. data/lib/libis/format/tool/fop_pdf.rb +14 -25
  50. data/lib/libis/format/tool/identification_tool.rb +40 -38
  51. data/lib/libis/format/tool/office_to_pdf.rb +18 -30
  52. data/lib/libis/format/tool/pdf_copy.rb +47 -0
  53. data/lib/libis/format/tool/pdf_merge.rb +19 -25
  54. data/lib/libis/format/tool/pdf_optimizer.rb +19 -22
  55. data/lib/libis/format/tool/pdf_split.rb +33 -6
  56. data/lib/libis/format/tool/pdf_to_pdfa.rb +31 -45
  57. data/lib/libis/format/tool/pdfa_validator.rb +30 -24
  58. data/lib/libis/format/tool/spreadsheet_to_ods.rb +18 -29
  59. data/lib/libis/format/tool.rb +3 -4
  60. data/lib/libis/format/version.rb +1 -3
  61. data/lib/libis/format/yaml_loader.rb +71 -0
  62. data/lib/libis/format.rb +7 -5
  63. data/lib/libis-format.rb +0 -2
  64. data/libis-format.gemspec +18 -24
  65. data/tools/PdfTool.jar +0 -0
  66. data/tools/pdfbox/pdfbox-app-2.0.13.jar +0 -0
  67. data/tools/pdfbox/{preflight-app-3.0.3.jar → preflight-app-2.0.13.jar} +0 -0
  68. metadata +86 -128
  69. data/data/AdobeRGB1998.icc +0 -0
  70. data/lib/libis/format/converter/email_converter.rb +0 -35
  71. data/lib/libis/format/tool/msg_to_pdf.rb +0 -270
  72. data/lib/libis/format/tool/pdf_tool.rb +0 -52
  73. data/lib/libis/format/type_database.rb +0 -156
  74. data/lib/libis/format/type_database_impl.rb +0 -153
  75. data/tools/pdf2pdfa +0 -395
  76. data/tools/pdfbox/pdfbox-app-3.0.3.jar +0 -0
  77. /data/bin/{droid_tool → droid} +0 -0
  78. /data/bin/{fido_tool → fido} +0 -0
@@ -0,0 +1,261 @@
1
+ # encoding: utf-8
2
+
3
+ require_relative 'base'
4
+ require 'libis/format/identifier'
5
+
6
+ require 'mini_magick'
7
+ # noinspection RubyResolve
8
+ require 'fileutils'
9
+
10
+ MiniMagick.logger.level = ::Logger::UNKNOWN
11
+
12
+ MiniMagick.configure do |config|
13
+ # config.cli = :graphicsmagick
14
+ config.validate_on_create = false
15
+ config.validate_on_write = false
16
+ config.whiny = false
17
+ end
18
+
19
+ module Libis
20
+ module Format
21
+ module Converter
22
+
23
+ # noinspection RubyTooManyInstanceVariablesInspection
24
+ class ImageWatermarker < Libis::Format::Converter::Base
25
+
26
+ def self.input_types
27
+ [:TIFF, :JPG, :PNG, :BMP, :GIF, :PDF, :JP2]
28
+ end
29
+
30
+ def self.output_types(format = nil)
31
+ return [] unless input_types.include?(format) if format
32
+ [format]
33
+ end
34
+
35
+ def self.multipage?(format)
36
+ [:PDF, :TIFF, :GIF, :PBM, :PGM, :PPM].include?(format)
37
+ end
38
+
39
+ def initialize
40
+ super
41
+ @quiet = true
42
+ @wm_image = nil
43
+ @wm_file = nil
44
+ @wm_text = '© LIBIS'
45
+ @wm_tiles = 4
46
+ @wm_resize = nil
47
+ @wm_gap = 20
48
+ @wm_gravity = 'Center'
49
+ @wm_rotation = 30
50
+ @wm_composition ='modulate'
51
+ @wm_composition_args = '10'
52
+ end
53
+
54
+ def image_watermark(_)
55
+ #force usage of this converter
56
+ self
57
+ end
58
+
59
+ def quiet(v)
60
+ @quiet = !!v
61
+ self
62
+ end
63
+
64
+ def page(v)
65
+ @page = v.to_i
66
+ self
67
+ end
68
+
69
+ # watermark image to use
70
+ def file(v)
71
+ @wm_file = v.blank? ? nil : v
72
+ self
73
+ end
74
+
75
+ # text to create a watermark from
76
+ def text(v)
77
+ @wm_text = v.blank? ? nil : v
78
+ self
79
+ end
80
+
81
+ # rotation of the watermark text (counter clockwise in degrees; integer number)
82
+ # default 30
83
+ def rotation(v)
84
+ @wm_rotation = v.to_i
85
+ self
86
+ end
87
+
88
+ # number of tiles of the watermark
89
+ # default 4
90
+ # 0: no tiling, so only 1 watermark will be placed with the original size
91
+ # 1: 1 tile, so the watermark will be scaled up to fill the image
92
+ # n > 1: minimum n tiles in both directions
93
+ # n < 0: tile without scaling the watermark
94
+ def tiles(v)
95
+ @wm_tiles = v.to_i
96
+ self
97
+ end
98
+
99
+ # fraction 0.0 - 1.0
100
+ def resize(v)
101
+ @wm_resize = (v.to_f * 100).to_i
102
+ self
103
+ end
104
+
105
+ # size of the gap between watermark instances. Fractions as percentage of widht/height
106
+ # default 0.2
107
+ def gap(v)
108
+ @wm_gap = (v.to_f * 100).to_i
109
+ self
110
+ end
111
+
112
+ # center point for the watermark overlay
113
+ # default 'center'
114
+ def gravity(v)
115
+ @wm_gravity = v.blank? ? nil : v
116
+ self
117
+ end
118
+
119
+ # the image composition method for merging the watermark image
120
+ # default 'modulate'
121
+ # See https://imagemagick.org/script/compose.php for more information
122
+ def composition(v)
123
+ @wm_composition = v.blank? ? nil : v
124
+ self
125
+ end
126
+
127
+ # arguments for the composition method
128
+ # default '10'
129
+ # See https://imagemagick.org/script/compose.php for more information
130
+ def composition_args(v)
131
+ @wm_composition_args = v.blank? ? nil : v
132
+ self
133
+ end
134
+
135
+
136
+ def convert(source, target, format, opts = {})
137
+ super
138
+
139
+ FileUtils.mkpath(File.dirname(target))
140
+
141
+ if source.is_a?(Array) || File.directory?(source)
142
+ error 'Only a single image file is allowed for input'
143
+ else
144
+ image = MiniMagick::Image.open(source) { |b| b.quiet }
145
+
146
+ if image.pages.size > 1
147
+ if @page
148
+ convert_image(image.pages[@page].path, target, format)
149
+ else
150
+ error 'multipage input file detecte; you need to supply a page number'
151
+ end
152
+ else
153
+ convert_image(source, target, format)
154
+ end
155
+ end
156
+
157
+ target
158
+
159
+ end
160
+
161
+ protected
162
+
163
+ # noinspection DuplicatedCode
164
+ def convert_image(source, target, format)
165
+
166
+ wm_image = watermark_image
167
+ return nil unless wm_image
168
+ image_info = MiniMagick::Image::Info.new(source) {|b| b.quiet}
169
+
170
+ MiniMagick::Tool::Convert.new do |convert|
171
+ convert.quiet if @quiet
172
+
173
+ # adapt watermark image to tile size and apply gap and resize if necessary
174
+ convert << @wm_image.path
175
+ # noinspection RubyResolve
176
+ convert.bordercolor('transparent').border("#{@wm_gap}%") if @wm_gap > 0
177
+ convert.filter('Lagrange')
178
+ convert.resize("#{image_info['width'] / @wm_tiles}x#{image_info['height'] / @wm_tiles}") if @wm_tiles > 0
179
+ convert.resize("#{@wm_resize}%") if @wm_resize
180
+ convert.write('mpr:watermark').delete.+
181
+
182
+ # convert the source image
183
+ convert << source
184
+ if @wm_tiles >= 0 and @wm_tiles <= 1
185
+ # only 1 watermark required (tiles = 0/1 => scaled no/yes)
186
+ convert << 'mpr:watermark'
187
+ else
188
+ # fill the image size with a pattern of the watermark image
189
+ convert.stack do |stack|
190
+ stack.size("#{image_info['width']}x#{image_info['height']}")
191
+ stack << 'xc:transparent'
192
+ # noinspection RubyResolve
193
+ stack.tile('mpr:watermark')
194
+ # noinspection RubyResolve
195
+ stack.draw "rectangle 0,0,#{image_info['width']},#{image_info['height']}"
196
+ end
197
+ end
198
+ # perform the blending operation
199
+ convert.compose(@wm_composition).gravity(@wm_gravity).define("compose:args=#{@wm_composition_args}").composite
200
+
201
+ convert.format(format)
202
+ convert << target
203
+
204
+ debug "ImageMagick command: '#{convert.command.join(' ')}'"
205
+ end
206
+
207
+ target
208
+
209
+ end
210
+
211
+ private
212
+
213
+ # Create or use a watermark image.
214
+ #
215
+ # If both text and image are set, the file will be used as-is if it exists and is a valid image file. Otherwise the
216
+ # file will be created or overwritten with a newly created watermark image.
217
+ #
218
+ # The created watermark file will be a 2000x2000 pixels PNG image with transparent background
219
+ #
220
+ # The text will be slanted by given rotation degrees counter-clockwise
221
+ def watermark_image
222
+ rotation = 360 - @wm_rotation
223
+ @wm_image = MiniMagick::Image.new(@wm_file) if @wm_file
224
+ # only create image if file is not an image
225
+ unless @wm_image&.valid?
226
+ # noinspection RubyResolve
227
+ # Create image file (as given or temp file)
228
+ image = @wm_file || (Dir::Tmpname.create(%w(wm_image .png)) {|_|})
229
+ # noinspection RubyResolve
230
+ MiniMagick::Tool::Convert.new do |convert|
231
+ convert.quiet # allways quiet
232
+ convert.background 'transparent'
233
+ convert.size('2000x2000')
234
+ convert.gravity 'Center'
235
+ convert.font('Helvetica').fill('black').pointsize(72) #.stroke('black').strokewidth(1)
236
+ convert << "label:#{@wm_text}"
237
+ convert.rotate rotation
238
+ convert.trim.repage.+
239
+ convert << image
240
+ end
241
+ if @wm_file
242
+ @wm_image = MiniMagick::Image.new(image)
243
+ else # delete temp file
244
+ @wm_image = MiniMagick::Image.open(image)
245
+ File.delete(image)
246
+ end
247
+ # noinspection RubyResolve
248
+ unless @wm_image.valid?
249
+ error "Problem creating watermark image '#{image}'."
250
+ @wm_image = nil
251
+ end
252
+ @wm_image
253
+ end
254
+ end
255
+
256
+
257
+ end
258
+
259
+ end
260
+ end
261
+ end
@@ -1,5 +1,4 @@
1
- # frozen_string_literal: true
2
-
1
+ # encoding: utf-8
3
2
  require 'libis-tools'
4
3
  require 'fileutils'
5
4
  require 'libis/format/config'
@@ -8,31 +7,32 @@ require_relative 'base'
8
7
  module Libis
9
8
  module Format
10
9
  module Converter
10
+
11
11
  class Jp2Converter < Libis::Format::Converter::Base
12
+
12
13
  def self.input_types
13
- %i[TIFF JPG PNG BMP GIF PDF]
14
+ [:TIFF, :JPG, :PNG, :BMP, :GIF, :PDF]
14
15
  end
15
16
 
16
17
  def self.output_types(format = nil)
17
- return [] unless input_types.include?(format)
18
-
18
+ return [] unless input_types.include?(format) if format
19
19
  [:JP2]
20
20
  end
21
21
 
22
22
  def initialize
23
23
  super
24
24
  @options = {
25
- color_xform: false,
26
- error_resilience: :ALL,
27
- lossless: true,
28
- progression_order: 'RLCP',
29
- tile_size: [1024, 1024],
30
- codeblock_size: [6, 6]
25
+ color_xform: false,
26
+ error_resilience: :ALL,
27
+ lossless: true,
28
+ progression_order: 'RLCP',
29
+ tile_size: [1024, 1024],
30
+ codeblock_size: [6, 6],
31
31
  }
32
32
  end
33
33
 
34
34
  def j2kdriver(_)
35
- # force usage of this converter
35
+ #force usage of this converter
36
36
  end
37
37
 
38
38
  def color_xform(flag = true)
@@ -68,36 +68,38 @@ module Libis
68
68
 
69
69
  @options.each do |key, value|
70
70
  case key
71
- when :color_xform
72
- options << '--set-output-j2k-color-xform' << (value ? 'YES' : 'NO')
73
- when :error_resilience
74
- options << '--set-output-j2k-error-resilience' << value.to_s
75
- when :lossless
76
- if value
77
- options << '--set-output-j2k-xform' << 'R53' << '5' << '--set-output-j2k-ratio' << '0'
71
+ when :color_xform
72
+ options << '--set-output-j2k-color-xform' << (value ? 'YES' : 'NO')
73
+ when :error_resilience
74
+ options << '--set-output-j2k-error-resilience' << value.to_s
75
+ when :lossless
76
+ if value
77
+ options << '--set-output-j2k-xform' << 'R53' << '5' << '--set-output-j2k-ratio' << '0'
78
+ else
79
+ options << '--set-output-j2k-xform' << 'I97' << '--set-output-j2k-psnr' << '46'
80
+ end
81
+ when :progression_order
82
+ options << '--set-output-j2k-progression-order' << value.to_s
83
+ when :tile_size
84
+ options << '--set-output-j2k-tile-size' << value[0].to_s << value[1].to_s
85
+ when :codeblock_size
86
+ options << '--set-output-j2k-codeblock-size' << value[0].to_s << value[1].to_s
78
87
  else
79
- options << '--set-output-j2k-xform' << 'I97' << '--set-output-j2k-psnr' << '46'
80
- end
81
- when :progression_order
82
- options << '--set-output-j2k-progression-order' << value.to_s
83
- when :tile_size
84
- options << '--set-output-j2k-tile-size' << value[0].to_s << value[1].to_s
85
- when :codeblock_size
86
- options << '--set-output-j2k-codeblock-size' << value[0].to_s << value[1].to_s
87
- else # rubocop:disable Style/EmptyElse
88
- # do nothing
88
+ #do nothing
89
89
  end
90
90
  end
91
91
 
92
- result = Libis::Tools::Command.run(
93
- Libis::Format::Config[:j2k_cmd],
94
- '--input-file-name', source,
95
- '--set-output-type', 'JP2',
96
- *options,
97
- '--output-file-name', target
92
+
93
+ Libis::Tools::Command.run(
94
+ Libis::Format::Config[:j2k_cmd],
95
+ '--input-file-name', source,
96
+ '--set-output-type', 'JP2',
97
+ *options,
98
+ '--output-file-name', target,
99
+
98
100
  )
99
101
 
100
- result.merge(files: [target], converter: self.class.name)
102
+ target
101
103
  end
102
104
  end
103
105
  end
@@ -1,50 +1,56 @@
1
- # frozen_string_literal: true
1
+ # encoding: utf-8
2
2
 
3
3
  require_relative 'base'
4
4
 
5
5
  require 'libis/format/tool/office_to_pdf'
6
- require 'libis/format/type_database'
6
+ require 'libis/format/library'
7
7
 
8
8
  module Libis
9
9
  module Format
10
10
  module Converter
11
+
11
12
  class OfficeConverter < Libis::Format::Converter::Base
13
+
12
14
  def self.input_types
13
- %i[
14
- TXT
15
- RTF
16
- HTML
17
- MSDOC
18
- MSDOT
19
- MSXLS
20
- MSPPT
21
- MSDOCX
22
- MSDOTX
23
- MSXLSX
24
- MSPPTX
25
- WORDPERFECT
26
- OO_WRITER
27
- OO_IMPRESS
28
- OO_CALC
15
+ [
16
+ :TXT,
17
+ :RTF,
18
+ :HTML,
19
+ :MSDOC,
20
+ :MSDOT,
21
+ :MSXLS,
22
+ :MSPPT,
23
+ :MSDOCX,
24
+ :MSDOTX,
25
+ :MSXLSX,
26
+ :MSPPTX,
27
+ :WORDPERFECT,
28
+ :OO_WRITER,
29
+ :OO_IMPRESS,
30
+ :OO_CALC
29
31
  ]
30
32
  end
31
33
 
32
34
  def self.output_types(format = nil)
33
- return [] unless input_types.include?(format)
34
-
35
+ return [] unless input_types.include?(format) if format
35
36
  [:PDF]
36
37
  end
37
38
 
38
39
  def office_convert(_)
39
- # force usage of this converter
40
+ #force usage of this converter
40
41
  end
41
42
 
42
43
  def convert(source, target, format, opts = {})
43
44
  super
44
45
 
45
- Format::Tool::OfficeToPdf.run(source, target)
46
+ return nil unless Format::Tool::OfficeToPdf.run(source, target)
47
+
48
+ target
49
+
46
50
  end
51
+
47
52
  end
53
+
48
54
  end
49
55
  end
50
56
  end
@@ -0,0 +1,66 @@
1
+ # encoding: utf-8
2
+
3
+ require_relative 'base'
4
+
5
+ require 'libis/format/tool/pdf_merge'
6
+
7
+ module Libis
8
+ module Format
9
+ module Converter
10
+
11
+ # noinspection DuplicatedCode
12
+ class PdfAssembler < Libis::Format::Converter::Base
13
+
14
+ def self.input_types
15
+ [:PDF]
16
+ end
17
+
18
+ def self.output_types(format = nil)
19
+ return [] unless input_types.include?(format) if format
20
+ [:PDF]
21
+ end
22
+
23
+ def self.category
24
+ :assembler
25
+ end
26
+
27
+ def pdf_assemnble(_)
28
+ #force usage of this converter
29
+ end
30
+
31
+ def convert(source, target, format, opts = {})
32
+ super
33
+
34
+ result = if source.is_a? Array
35
+ assemble(source, target)
36
+ elsif File.directory?(source)
37
+ source_list = Dir[File.join(source, '**', '*')].reject {|p| File.directory? p}
38
+ assemble(source_list, target)
39
+ else
40
+ assemble([source], target)
41
+ end
42
+ return nil unless result
43
+
44
+ result
45
+ end
46
+
47
+ private
48
+
49
+ def assemble(source, target)
50
+
51
+ result = Libis::Format::Tool::PdfMerge.run(source, target)
52
+
53
+ unless result[:err].empty?
54
+ error("PdfMerge encountered errors:\n%s", result[:err].join(join("\n")))
55
+ return nil
56
+ end
57
+
58
+ target
59
+ end
60
+
61
+ end
62
+
63
+ end
64
+
65
+ end
66
+ end