pdf_paradise 0.3.20

data/lib/pdf_paradise/utility_scripts/rotate_pdf_file.rb

@@ -0,0 +1,303 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::RotatePdfFile
+#
+# This class can be used to rotate a .pdf file. By default this will rotate
+# it by 90%.
+#
+# Usage example:
+#
+#   PdfParadise::RotatePdfFile.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/rotate_pdf_file.rb'
+# PdfParadise::RotatePdfFile.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class RotatePdfFile < Base # === PdfParadise::RotatePdfFile
+
+  # ========================================================================= #
+  # === ROTATE_BY_N_DEGREES
+  # ========================================================================= #
+  ROTATE_BY_N_DEGREES = 90
+
+  # ========================================================================= #
+  # === ROTATE_REGEX
+  # ========================================================================= #
+  ROTATE_REGEX = /(--rotate (\d+))/ # URL: https://rubular.com/r/ds3tk7DPPw
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    case i
+    # ======================================================================= #
+    # === :do_not_run_yet
+    # ======================================================================= #
+    when :do_not_run_yet
+      i = nil
+      run_already = false
+    end
+    set_commandline_arguments(i)
+    set_input(
+      i.reject {|entry|
+        entry.start_with?('--')
+      }
+    )
+    case run_already
+    # ======================================================================= #
+    # === :run_already
+    # ======================================================================= #
+    when :run_already
+      run_already = true
+    # ======================================================================= #
+    # === :do_not_run_yet
+    # ======================================================================= #
+    when :do_not_run_yet
+      run_already = false
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    infer_the_namespace
+    # ======================================================================= #
+    # === @use_this_command
+    # ======================================================================= #
+    @use_this_command = :qpdf # :convert
+    set_rotate # Set the default value, after @use_this_command was set.
+    # ======================================================================= #
+    # === @overwrite_the_original_file
+    #
+    # Other users may want to set the next variable to false.
+    # ======================================================================= #
+    @overwrite_the_original_file = true
+  end
+
+  # ========================================================================= #
+  # === qpdf_was_used?
+  # ========================================================================= #
+  def qpdf_was_used?
+    @use_this_command == :qpdf
+  end
+
+  # ========================================================================= #
+  # === show_help                                                  (help tag)
+  # ========================================================================= #
+  def show_help
+    opne 'The available options are:'
+    e
+    eparse '  --rotate N # rotate by n degrees (into '\
+           'clockwise direction. Example: rotatepdf --rotate 90 foo.pdf)'
+    e
+  end
+
+  # ========================================================================= #
+  # === set_input
+  # ========================================================================= #
+  def set_input(i = '')
+    i = i.join(' ').strip if i.is_a? Array
+    i = i.to_s.dup
+    if i.start_with? 'file://'
+      i.sub!(/^file:\/\//,'')
+    end
+    case i
+    # ======================================================================= #
+    # We add support for --rotate next. When there is a match, we
+    # will get rid of that part of the input.
+    # ======================================================================= #
+    when ROTATE_REGEX, /--rotate/ # Usage: rotate --rotate 100 5-Kapitel_5_AllgMikrobiologie_SS2015_students_2S.pdf
+      i =~ ROTATE_REGEX
+      set_rotate($2.to_s.dup)
+      i.gsub!(/#{$1.to_s}/, '')
+    end unless File.exist? i
+    i = i.to_s.strip
+    @input = i
+  end
+
+  # ========================================================================= #
+  # === set_rotate
+  # ========================================================================= #
+  def set_rotate(
+      i = ROTATE_BY_N_DEGREES
+    )
+    i = i.to_i
+    case @use_this_command
+    # ======================================================================= #
+    # === :qpdf
+    # ======================================================================= #
+    when :qpdf
+      i = "+#{i}" if i > 0
+    end
+    @rotate_by_n_degrees = i.to_s.dup # Always .dup it, just in case.
+  end; alias set_rotate_level set_rotate # === set_rotate_level
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input
+  end
+
+  # ========================================================================= #
+  # === output_file?
+  # ========================================================================= #
+  def output_file?(
+      i = input?
+    )
+    return i if @overwrite_the_original_file # Early return.
+    _ = basename(i).delete_suffix('.pdf')
+    _.tr(' ','') if _.include? ' '
+    return "rotated_pdf_file_#{_}.pdf"
+  end
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    Opn.opn(namespace: namespace?)
+  end
+
+  # ========================================================================= #
+  # === rotate_by_n_degrees?
+  # ========================================================================= #
+  def rotate_by_n_degrees?
+    @rotate_by_n_degrees
+  end; alias rotate? rotate_by_n_degrees? # === rotate?
+
+  # ========================================================================= #
+  # === add_quality
+  # ========================================================================= #
+  def add_quality
+    return '-quality 100 '
+  end
+
+  # ========================================================================= #
+  # === notify_the_user_that_the_conversion_has_finished
+  # ========================================================================= #
+  def notify_the_user_that_the_conversion_has_finished
+    e 'Finished converting! The file should now reside at:'
+    e
+    e sfile("  #{output_file?}")
+    e
+  end
+
+  # ========================================================================= #
+  # === menu
+  # ========================================================================= #
+  def menu(
+      i = @commandline_arguments
+    )
+    if i.is_a? Array
+      i.each {|entry|
+        menu(entry)
+      }
+    else
+      case i
+      # ===================================================================== #
+      # === --help
+      #
+      # Since as of February 2023, empty input, aka '', will no longer call
+      # this method.
+      # ===================================================================== #
+      when /-?-?help$/i # '' means empty.
+        show_help
+        exit
+      # ===================================================================== #
+      # === --rotate=5
+      #
+      # Usage example:
+      #
+      #   rpdf 13.06.1991_Scan_EVVA_Schließplan_für_Zylinder_Schließanlagen.pdf --rotate=1
+      #
+      # ===================================================================== #
+      when /-?-?rotate=(\d{1,5})$/i
+        set_rotate_level($1.to_s)
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === do_convert_this_pdf_file
+  # ========================================================================= #
+  def do_convert_this_pdf_file(
+      i, be_verbose = true
+    )
+    i = i.to_s
+    output_file = output_file?
+    # ======================================================================= #
+    # Use convert by default.
+    # ======================================================================= #
+    _ = @use_this_command.to_s
+    _ = _.dup
+    if _.start_with? 'qpdf'
+      _ << ' --rotate='+rotate_by_n_degrees?+' '
+      if @overwrite_the_original_file
+        # =================================================================== #
+        # --replace-input may be given in place of outfile.
+        # =================================================================== #
+        _ << ' --replace-input'
+      end
+    else
+      _ << ' -rotate '+rotate_by_n_degrees?+' '
+    end
+    _ << add_quality if _.start_with? 'convert'
+    _ << " #{i}" # Here we add the input-file.
+    unless _.include? '--replace-input'
+      _ << " #{output_file}" # Add the output file here.
+    end
+    _.rstrip!
+    _.squeeze!(' ')
+    case be_verbose
+    # ======================================================================= #
+    # === :be_quiet
+    # ======================================================================= #
+    when :be_quiet
+      be_verbose = false
+    end
+    if be_verbose
+      esystem _
+    else
+      system _
+    end
+    # ======================================================================= #
+    # Do cleanup if qpdf was used.
+    # ======================================================================= #
+    if _.include?('--replace-input') and qpdf_was_used?
+      delete_these_files = Dir['*.pdf.~qpdf-orig']
+      delete_these_files.each {|this_file|
+        delete_this_file(this_file)
+      }
+    end 
+    if File.exist?(output_file) and is_on_roebe? and be_verbose
+      require 'open'
+      Open[output_file] # Open the .pdf file here on a roebe system.
+    end
+  end; alias do_rotate_the_pdf_file do_convert_this_pdf_file # === do_rotate_the_pdf_file
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    menu
+    do_convert_this_pdf_file(input?)
+    notify_the_user_that_the_conversion_has_finished
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::RotatePdfFile.new(ARGV)
+end # rotatepdf

data/lib/pdf_paradise/utility_scripts/split_pdf.rb

@@ -0,0 +1,364 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::SplitPdf
+#
+# Use this class to split up a .pdf file into several new documents.
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/split_pdf.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class SplitPdf < PdfParadise::Base # === PdfParadise::SplitPdf
+
+  require 'pdf_paradise/utility_scripts/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === 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.
+  # ========================================================================= #
+  SPLIT_UP_INTO_N_CHUNKS = 1 # 10
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === set_store_in_this_directory
+  #
+  # By default we will store into the current working directory.
+  # ========================================================================= #
+  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; alias set_store_here set_store_in_this_directory # === set_store_here
+
+  # ========================================================================= #
+  # === ensure_that_the_directory_exists
+  # ========================================================================= #
+  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                                                       (menu tag)
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === set_split_up_into_chunks_of_n_pages
+  # ========================================================================= #
+  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; alias set_split_n_pages set_split_up_into_chunks_of_n_pages # === set_split_n_pages
+       alias set_n_pages       set_split_up_into_chunks_of_n_pages # === set_n_pages
+
+  # ========================================================================= #
+  # === return_n_pages
+  #
+  # This will return the amount of pages in the given .pdf file.
+  # ========================================================================= #
+  def return_n_pages(i = input?)
+    ::PdfParadise.n_pages?(i).to_i # We need an integer here.
+  end
+
+  # ========================================================================= #
+  # === n_chunks?
+  # ========================================================================= #
+  def n_chunks?
+    @split_up_into_chunks_of_n_pages
+  end
+
+  # ========================================================================= #
+  # === report_the_output_file_will_be_at
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === return_name_of_the_output_file_based_on_this_filename
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === 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".
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === array_these_files_were_created_anew?
+  # ========================================================================= #
+  def array_these_files_were_created_anew?
+    @array_these_files_were_created_anew
+  end
+
+  # ========================================================================= #
+  # === try_to_split_up_the_pdf
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === path?
+  # ========================================================================= #
+  def path?
+    @path
+  end
+
+  # ========================================================================= #
+  # === run
+  # ========================================================================= #
+  def run
+    menu
+    try_to_split_up_the_pdf
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.split_this_pdf_file
+#
+# The first argument to this method should be the path to a locally
+# existing .pdf file.
+# =========================================================================== #
+def self.split_this_pdf_file(
+    i                       = ARGV,
+    split_into_n_pages      = 1,
+    store_in_this_directory = :default
+  )
+  _ = PdfParadise::SplitPdf.new(i) {{
+    split_into_n_pages:      split_into_n_pages,
+    store_in_this_directory: store_in_this_directory
+  }}
+  _ # Return the object here.
+end
+
+# =========================================================================== #
+# === PdfParadise.burst
+#
+# This will "burst" all pdf files out of a single .pdf file.
+# =========================================================================== #
+def self.burst(
+    i                       = ARGV,
+    split_into_n_pages      = :max,
+    store_in_this_directory = :default
+  )
+  _ = PdfParadise::SplitPdf.new(i) {{
+    split_into_n_pages:      split_into_n_pages,
+    store_in_this_directory: store_in_this_directory
+  }}
+  _ # Return the object here.
+end
+
+# =========================================================================== #
+# === PdfParadise.convert
+# =========================================================================== #
+def self.convert(pdf_files)
+  handle = PdfParadise.split_this_pdf_file(pdf_files)
+  handle.path? # Return the file path as well.
+end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::SplitPdf.new(ARGV)
+end # split_pdf XIV-XVII_combined.pdf