Class: PdfParadise::SplitPdf

Inherits:
Base
  • Object
show all
Defined in:
lib/pdf_paradise/utility_scripts/split_pdf.rb

Overview

PdfParadise::SplitPdf

Constant Summary collapse

SPLIT_UP_INTO_N_CHUNKS =
#

SPLIT_UP_INTO_N_CHUNKS

Split up the .pdf file at hand into n chunks. This constant used to be set to 10 rather than 2.

#
1

Constants inherited from Base

Base::NAMESPACE

Instance Method Summary collapse

Methods inherited from Base

#basename, #be_verbose?, #change_directory, #commandline_arguments?, #copy_file, #delete_file, #e, #ecomment, #esystem, #first_argument?, #gold, #infer_the_namespace, #input_without_leading_hyphens?, #internal_hash?, #is_an_image_file?, #is_on_roebe?, #lightsteelblue, #log_dir?, #mkdir, #mv, #n_pages?, #namespace?, #no_file_at, #opne, #opnn, #orange, #reset_the_internal_hash, #return_commandline_arguments_starting_with_hyphens, #return_files_from_the_commandline_arguments, #return_pwd, #rev, #set_be_quiet, #set_commandline_arguments, #steelblue, #try_to_ensure_that_this_directory_exists, #write_what_into

Constructor Details

#initialize(optional_arguments = nil, run_already = true, &block) ⇒ SplitPdf

#

initialize

#


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
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 30

def initialize(
    optional_arguments = nil,
    run_already        = true,
    &block
  )
  reset
  set_commandline_arguments(
    optional_arguments
  )
  # ======================================================================= #
  # === Hande blocks passed to this method next
  # ======================================================================= #
  if block_given?
    yielded = yield
    if yielded.is_a? Hash
      if yielded.has_key? :split_into_n_pages
        set_n_pages(
          yielded.delete(:split_into_n_pages)
        )
      end
      if yielded.has_key? :store_in_this_directory
        set_store_here(
          yielded.delete(:store_in_this_directory)
        )
      end
    end
  end
  run if run_already
end

Instance Method Details

#array_these_files_were_created_anew? ⇒ Boolean

#

array_these_files_were_created_anew?

#

Returns:

  • (Boolean) 


225
226
227
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 225

def array_these_files_were_created_anew?
  @array_these_files_were_created_anew
end

#do_convert_this_file_via_hexapdf(i) ⇒ Object

#

do_convert_this_file_via_hexapdf

This can be done via “hexapdf split foobar.pdf”.

The argument to this method should be the existing .pdf file, such as “foobar.pdf”.

#


210
211
212
213
214
215
216
217
218
219
220
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 210

def do_convert_this_file_via_hexapdf(i)
  cmd_to_use = "hexapdf split #{i}"
  e
  e(cmd_to_use)
  e
  `#{cmd_to_use}`
  array_new_files = Dir[i.delete_suffix('.pdf')+'*']
  @array_these_files_were_created_anew.clear
  @array_these_files_were_created_anew << array_new_files
  return array_new_files # Perhaps we may need this at a later time.
end

#ensure_that_the_directory_exists(this_directory = nil) ⇒ Object

#

ensure_that_the_directory_exists

#


108
109
110
111
112
113
114
115
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 108

def ensure_that_the_directory_exists(this_directory = nil)
  if this_directory
    unless File.directory? this_directory
      require 'fileutils'
      FileUtils.mkdir_p(this_directory)
    end
  end
end

#menu(i = @commandline_arguments) ⇒ Object

#

menu (menu tag)

#


120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 120

def menu(
    i = @commandline_arguments
  )
  if i.is_a? Array
    i.each {|entry| menu(entry) }
  else
    case i
    # ===================================================================== #
    # === splitpdf --n-pages=1
    # ===================================================================== #
    when /^-?-?n(_|-)?pages=(.+)$/i # $2
      _ = $2.to_s.dup
      opnn; e 'We will split the .pdf file into '+sfancy(_.to_s)+' pages each.'
      set_split_n_pages(_)
    end
  end
end

#n_chunks? ⇒ Boolean

#

n_chunks?

#

Returns:

  • (Boolean) 


176
177
178
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 176

def n_chunks?
  @split_up_into_chunks_of_n_pages
end

#path? ⇒ Boolean

#

path?

#

Returns:

  • (Boolean) 


303
304
305
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 303

def path?
  @path
end

#report_the_output_file_will_be_at(output_file) ⇒ Object

#

report_the_output_file_will_be_at

#


183
184
185
186
187
188
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 183

def report_the_output_file_will_be_at(output_file)
  opnn; e 'The output file will be at:'
  e
  e "  #{sfile(output_file)}"
  e
end

#reset ⇒ Object

#

reset

#


63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 63

def reset
  super()
  set_split_up_into_chunks_of_n_pages
  set_store_in_this_directory
  infer_the_namespace
  # ======================================================================= #
  # === @path
  # ======================================================================= #
  @path = nil
  # ======================================================================= #
  # === @use_convert_or_hexapdf
  #
  # Since as of February 2023 the default is now hexapdf.
  # ======================================================================= #
  @use_convert_or_hexapdf = :hexapdf # or :convert
  # ======================================================================= #
  # === @array_these_files_were_created_anew
  # ======================================================================= #
  @array_these_files_were_created_anew = []
end

#return_n_pages(i = input?) ) ⇒ Object

#

return_n_pages

This will return the amount of pages in the given .pdf file.

#


169
170
171
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 169

def return_n_pages(i = input?)
  ::PdfParadise.n_pages?(i).to_i # We need an integer here.
end

#return_name_of_the_output_file_based_on_this_filename(filename, index) ⇒ Object

#

return_name_of_the_output_file_based_on_this_filename

#


193
194
195
196
197
198
199
200
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 193

def return_name_of_the_output_file_based_on_this_filename(
    filename, index
  )
  return @store_in_this_directory+
         File.basename(filename).delete_suffix('.pdf')+
         '_page'+(index.to_i+1).to_s+
         '.pdf'
end

#run ⇒ Object

#

run

#


310
311
312
313
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 310

def run
  menu
  try_to_split_up_the_pdf
end

#set_split_up_into_chunks_of_n_pages(i = SPLIT_UP_INTO_N_CHUNKS) ⇒ Object Also known as: set_split_n_pages, set_n_pages

#

set_split_up_into_chunks_of_n_pages

#


141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 141

def set_split_up_into_chunks_of_n_pages(
    i = SPLIT_UP_INTO_N_CHUNKS
  )
  if i.is_a? Array
    i = i.first
  end
  case i
  when :max
    i = 1
    set_split_n_pages(
      PdfParadise.n_pdf_pages?(
        return_n_pages - 1
      )
    )
  when nil,
       :default
    i = SPLIT_UP_INTO_N_CHUNKS
  end
  i = i.to_i # We need to keep this variable as Integer value.
  @split_up_into_chunks_of_n_pages = i
end

#set_store_in_this_directory(i = return_pwd) ⇒ Object Also known as: set_store_here

#

set_store_in_this_directory

By default we will store into the current working directory.

#


89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 89

def set_store_in_this_directory(
    i = return_pwd
  )
  case i
  when :default
    i = return_pwd
  end
  i = i.dup if i.frozen?
  # ======================================================================= #
  # We require a String.
  # ======================================================================= #
  i << '/' unless i.end_with? '/'
  @store_in_this_directory = i
  ensure_that_the_directory_exists(i)
end

#try_to_split_up_the_pdf(i = input_without_leading_hyphens? ) ⇒ Object

#

try_to_split_up_the_pdf

#


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
 
# File 'lib/pdf_paradise/utility_scripts/split_pdf.rb', line 232

def try_to_split_up_the_pdf(
    i = input_without_leading_hyphens?
  )
  i = i.first if i.is_a? Array
  filename = i
  if File.exist? i
    n_pages = return_n_pages(i)
    opnn; e "The file at `#{sfile(i)}` exists. We will next split"
    opnn; e 'it up into chunks of '+simp(n_chunks?.to_s)+' pages.'
    # ===================================================================== #
    # We currently depend on "bin/convert" from ImageMagick. We
    # will also try to preserve as much quality as possible.
    # Unfortunately convert really has a lousy quality, so as
    # of May 2022 we add hexapdf as option too.
    # ===================================================================== #
    # cmd_to_use = 'convert '.dup
    case @use_convert_or_hexapdf
    # ===================================================================== #
    # === :convert
    # ===================================================================== #
    when :convert
      cmd_to_use = 'convert -quality 98 '.dup
    # ===================================================================== #
    # === :hexapdf
    # ===================================================================== #
    when :hexapdf
      do_convert_this_file_via_hexapdf(i)
      exit
    end

    old_index = 0
    n_chunks?.step(n_pages+1, n_chunks?) {|entry|
      range = old_index.to_s+'-'+(entry - 1).to_s
      _ = filename+'['+range+']'
      # =================================================================== #
      # Keep track of the name of the output file at hand.
      # =================================================================== #
      output_file = return_name_of_the_output_file_based_on_this_filename(filename, old_index+1)
      report_the_output_file_will_be_at(output_file)
      esystem(
        "#{cmd_to_use}#{_} #{output_file}"
      )
      old_index = entry
    }
    # ===================================================================== #
    # We may have to correct the command a bit to account for the
    # very last .pdf pages.
    # ===================================================================== #
    n_possible_remaining_pages = n_pages % n_chunks?
    if n_possible_remaining_pages > 0
      # =================================================================== #
      # Ok, now we know that we must do a modification because we know
      # that there are n remaining pages left.
      # =================================================================== #
      range = old_index.to_s+'-'+((old_index+n_possible_remaining_pages)- 1).to_s
      _ = filename+'['+range+']'+' '
      output_file = @store_in_this_directory+'OUTPUT_PDF_FILE_'+range.tr('-','_')+'_'+File.basename(filename)
      @path = output_file
      opnn; e 'The output file will be at `'+sfile(output_file)+'`.'
      esystem(
        cmd_to_use+_+' '+output_file
      )
    end
  else
    opnn; no_file_at(i)
  end
end