pdf_paradise 0.1.66

data/lib/pdf_paradise/utility_scripts/delete_last_page_of_this_pdf_file.rb

@@ -0,0 +1,180 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::DeleteLastPageOfThisPdfFile
+#
+# This class will accept one (or several) .pdf files and then proceed
+# to remove the very last .pdf page in that file. So if that pdf-file
+# has had 100 pages, we will end up with 99 pages.
+#
+# By default, the class here will create a new output file and leave
+# the original file untouched.
+#
+# Note that this functionality depends on either "qpdf" or "pdftk".
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/delete_last_page_of_this_pdf_file.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+require 'pdf_paradise/pdf_file_n_total_pages.rb'
+
+module PdfParadise
+
+class DeleteLastPageOfThisPdfFile < Base 
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === OVERWRITE_THE_OLD_PDF_FILE
+  #
+  # If the following constant is set to true then the given input
+  # file will be overwritten.
+  # ========================================================================= #
+  OVERWRITE_THE_OLD_PDF_FILE = true
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      input_files = ARGV,
+      run_already = true
+    )
+    reset
+    set_input_files(input_files)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+    # ======================================================================= #
+    # === @overwrite_the_old_pdf_file
+    # ======================================================================= #
+    @overwrite_the_old_pdf_file = OVERWRITE_THE_OLD_PDF_FILE
+  end
+
+  # ========================================================================= #
+  # === set_input_files
+  # ========================================================================= #
+  def set_input_files(i)
+    i = [i] unless i.is_a? Array
+    if i.empty? and is_on_roebe?
+      # ===================================================================== #
+      # In this case we will use the main-pdf file, if it exists.
+      # ===================================================================== #
+      if ENV.has_key?('MAIN_BOOK') and
+        File.exist?(ENV['MAIN_BOOK'])
+        i << ENV['MAIN_BOOK'].dup
+      end
+    end
+    @input_files = i
+    sanitize_input_files
+  end
+
+  # ========================================================================= #
+  # === sanitize_input_files
+  # ========================================================================= #
+  def sanitize_input_files
+    unless @input_files.empty?
+      # ===================================================================== #
+      # Select only .pdf files next.
+      # ===================================================================== #
+      @input_files.select! {|entry|
+        entry.end_with? '.pdf'
+      }
+    end
+  end
+
+  # ========================================================================= #
+  # === process_each_pdf
+  # ========================================================================= #
+  def process_each_pdf
+    @input_files.each {|this_pdf_file|
+      # ===================================================================== #
+      # First, we must find out how many pdf pages are in the given
+      # pdf file at hand.
+      # ===================================================================== #
+      if File.exist? this_pdf_file
+        opnn; e 'Now working on the .pdf file '+sfancy(this_pdf_file)
+        has_n_pages = PdfParadise.n_pages_in_this_pdf_file?(this_pdf_file) # This is also the last page.
+        if use_pdftk?
+          _ = 'pdftk '+this_pdf_file+' cat 1-'+(has_n_pages.to_i - 1).to_s+' '+
+               has_n_pages.to_s+'-end output '+
+               name_of_the_output_file?(this_pdf_file)
+        else # else we use qpdf
+          _ = 'qpdf'.dup
+          if @overwrite_the_old_pdf_file
+            _ << ' --replace-input'
+          end
+          if @overwrite_the_old_pdf_file
+            _ << ' --pages '+this_pdf_file+' 1-'+(has_n_pages.to_i - 1).to_s+' -- '+
+                 this_pdf_file
+          else
+            _ << ' --pages '+this_pdf_file+' 1-'+(has_n_pages.to_i - 1).to_s+' -- '+
+                 this_pdf_file+' '+name_of_the_output_file?(this_pdf_file)
+          end
+        end
+        esystem _
+      else
+        opnn; e 'No file exists at `'+sfile(this_pdf_file)+'`.'
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === name_of_the_output_file?
+  # ========================================================================= #
+  def name_of_the_output_file?(i)
+    if @overwrite_the_old_pdf_file
+      i.sub(/\.pdf$/,'')+'.pdf'
+    else
+      i.sub(/\.pdf$/,'')+'_output_file.pdf'
+    end
+  end; alias output? name_of_the_output_file? # === output?
+
+  # ========================================================================= #
+  # === use_pdftk?
+  # ========================================================================= #
+  def use_pdftk?
+    false
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input_files
+  end
+
+  # ========================================================================= #
+  # === run
+  # ========================================================================= #
+  def run
+    process_each_pdf
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.delete_last_page_of_this_pdf_file
+#
+# Easier method-way to invoke the above class.
+# =========================================================================== #
+def self.delete_last_page_of_this_pdf_file(i = ARGV)
+  PdfParadise::DeleteLastPageOfThisPdfFile.new(i)
+end; self.instance_eval { alias remove_the_last_page_of_this_pdf_file delete_last_page_of_this_pdf_file } # === PdfParadise.remove_the_last_page_of_this_pdf_file
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::DeleteLastPageOfThisPdfFile.new(ARGV)
+end # delete_last_page_of_this_pdf_file

data/lib/pdf_paradise/utility_scripts/delete_this_page_of_this_pdf_file.rb

@@ -0,0 +1,329 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::DeleteThisPageOfThisPdfFile
+#
+# This class will accept one (or several) .pdf files and then proceed
+# to remove the specified .pdf page in that file.
+#
+# By default, the class here will honour the constant called
+# OVERWRITE_THE_OLD_PDF_FILE in order to determine whether a new
+# .pdf file is to be created, or whether to modify the original
+# .pdf file as-is. 
+#
+# Note that this functionality "contained" in this .rb file depends
+# on either "qpdf" or "pdftk" - personally I much prefer qpdf these
+# days.
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/delete_this_page_of_this_pdf_file.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+ 
+module PdfParadise
+
+class DeleteThisPageOfThisPdfFile < Base 
+
+  require 'pdf_paradise/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === OVERWRITE_THE_OLD_PDF_FILE
+  #
+  # If the following constant is set to true then the given input
+  # file will be overwritten. I prefer this on my home system, so
+  # the default is true for now.
+  # ========================================================================= #
+  OVERWRITE_THE_OLD_PDF_FILE = true
+
+  # ========================================================================= #
+  # === DEFAULT_REMOVE_THIS_PDF_PAGE
+  #
+  # If you don't feel like manually passing data to the .rb file, use
+  # the hardcoded value here.
+  # ========================================================================= #
+  DEFAULT_REMOVE_THIS_PDF_PAGE = 126
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      input_files = ARGV,
+      run_already = true
+    )
+    reset
+    set_commandline_arguments(
+      input_files
+    )
+    set_input_files(
+      input_files
+    )
+    # ======================================================================= #
+    # === Handle Blocks next
+    # ======================================================================= #
+    if block_given?
+      yielded = yield
+      case yielded
+      when :do_not_run_yet
+        run_already = false
+      end
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+    # ======================================================================= #
+    # === @overwrite_the_old_pdf_file
+    #
+    # This determines whether the old .pdf file will be overwritten.
+    # ======================================================================= #
+    @overwrite_the_old_pdf_file = OVERWRITE_THE_OLD_PDF_FILE
+    # ======================================================================= #
+    # === @remove_this_pdf_page
+    #
+    # This variable keeps track as to which particular page we wish
+    # to remove from our .pdf file. By default we will set to one
+    # as is anyway.
+    # ======================================================================= #
+    @remove_this_pdf_page = DEFAULT_REMOVE_THIS_PDF_PAGE
+    # ======================================================================= #
+    # === @use_this_program
+    # ======================================================================= #
+    @use_this_program = 'hexapdf' # qpdf'
+  end
+
+  # ========================================================================= #
+  # === show_help
+  # ========================================================================= #
+  def show_help
+    e
+    e 'The first argument should be the .pdf file.'
+    e 'The second argument should be the page number.'
+    e
+  end
+
+  # ========================================================================= #
+  # === set_input_files
+  # ========================================================================= #
+  def set_input_files(i)
+    i = [i] unless i.is_a? Array
+    @input_files = i
+    sanitize_input_files
+  end; alias set_pdf_file  set_input_files # === set_pdf_file
+       alias set_pdf_files set_input_files # === set_pdf_files
+
+  # ========================================================================= #
+  # === sanitize_input_files
+  # ========================================================================= #
+  def sanitize_input_files
+    unless @input_files.empty?
+      set_page_number(
+        @input_files.select {|entry|
+          # ================================================================= #
+          # Get numbers.
+          # ================================================================= #
+          entry =~ /^\d+$/
+        }
+      )
+      # ===================================================================== #
+      # Select only .pdf files next.
+      # ===================================================================== #
+      @input_files.select! {|entry|
+        entry.end_with? '.pdf'
+      }
+    end
+  end
+
+  # ========================================================================= #
+  # === return_the_proper_range
+  #
+  # This method will return the proper range, such as:
+  #
+  #   1-9,11-z
+  #
+  # The ',' will be included in the return value by this method.
+  # ========================================================================= #
+  def return_the_proper_range
+    before_part = "1-#{(@remove_this_pdf_page - 1).to_s}"
+    after_part  = (@remove_this_pdf_page + 1).to_s+'-z'
+    "#{before_part},#{after_part}"
+  end
+
+  # ========================================================================= #
+  # === name_of_the_output_file?
+  # ========================================================================= #
+  def name_of_the_output_file?(i)
+    if @overwrite_the_old_pdf_file
+      i.sub(/\.pdf$/,'')+'.pdf'
+    else
+      i.sub(/\.pdf$/,'')+'_output_file.pdf'
+    end
+  end; alias output? name_of_the_output_file? # === output?
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input_files
+  end
+
+  # ========================================================================= #
+  # === process_each_pdf
+  # ========================================================================= #
+  def process_each_pdf
+    @input_files.each {|this_pdf_file|
+      # ===================================================================== #
+      # The command should be something like this:
+      #
+      #   qpdf input.pdf --pages input.pdf 1-9,26-z -- outputfile.pdf 
+      #
+      # See: https://superuser.com/a/1297395
+      # ===================================================================== #
+      if File.exist? this_pdf_file
+        opnn; e 'Now working on the .pdf file '+sfancy(this_pdf_file)+
+                ', containing '+n_pages?(this_pdf_file).to_s+' pages.'
+        opnn; e 'The page that will be removed is: '+
+                steelblue(@remove_this_pdf_page.to_s)
+        case @use_this_program
+        when /qpdf/
+          _ = @use_this_program.dup
+          _ << " #{this_pdf_file}"
+          _ << " --pages #{this_pdf_file} "+return_the_proper_range
+          _ << " -- output.pdf"
+        when /hexapdf/
+          _ = @use_this_program.dup
+          _ << ' modify'
+          _ << " #{this_pdf_file}"
+          _ << ' -i '+return_the_proper_range.tr('z','e')
+          _ << " output.pdf"
+        end
+        e
+        esystem _
+        e
+        if @overwrite_the_old_pdf_file
+          output_file = 'output.pdf'
+          if File.exist? output_file
+            File.delete(this_pdf_file) if File.exist? this_pdf_file
+            move_file(output_file, this_pdf_file)
+          end
+        end
+        opnn; e 'The .pdf file at '+sfancy(this_pdf_file)+
+                ' now contains '+n_pages?(this_pdf_file).to_s+' pages.'
+      else
+        opnn; e "No file exists at `#{sfile(this_pdf_file)}`."
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === remove_this_pdf_page?
+  # ========================================================================= #
+  def remove_this_pdf_page?
+    @remove_this_pdf_page
+  end; alias page_number? remove_this_pdf_page? # === page_number?
+
+  # ========================================================================= #
+  # === set_remove_this_pdf_page
+  # ========================================================================= #
+  def set_remove_this_pdf_page(
+      i = nil
+    )
+    if i
+      if i.is_a? Array
+        i = i.first
+      end
+      if i.nil?
+        # In this case use the default value.
+        i = DEFAULT_REMOVE_THIS_PDF_PAGE
+      end
+      @remove_this_pdf_page = i.to_i
+    end
+  end; alias set_page_number set_remove_this_pdf_page # === set_page_number
+
+  # ========================================================================= #
+  # === menu                                                       (menu tag)
+  # ========================================================================= #
+  def menu(
+      i = return_commandline_arguments_starting_with_hyphens
+    )
+    if i.is_a? Array
+      i.each {|entry| menu(entry) }
+    else
+      case i
+      # ===================================================================== #
+      # === deletethispageofthispdffile DONE*pdf --remove-this-page-number=430
+      #
+      # Remove specific pages from a given .pdf file.
+      #
+      # Usage example:
+      #
+      #   pagegone DONE*pdf --remove-this-page-number=360
+      #   pagegone DONE*pdf --remove=94
+      #   pagegone DONE*pdf --remove=162
+      #   pagegone DONE*pdf --remove=307
+      #
+      # ===================================================================== #
+      when /^-?-?remove(-|_)?this(-|_)?page(-|_)?number=(.+)$/i, # === $4
+           /^-?-?remove=(.+)$/i # === $1
+        _ = $1.to_s.dup
+        _ = $4.to_s.dup if $4
+        set_remove_this_pdf_page(_)
+      # ===================================================================== #
+      # === --help
+      # ===================================================================== #
+      when /help/
+        show_help
+        exit
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === run
+  # ========================================================================= #
+  def run
+    menu
+    process_each_pdf
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.remove_this_page_of_that_pdf_file
+# =========================================================================== #
+def self.remove_this_page_of_that_pdf_file(
+    this_page,
+    that_pdf_file
+  )
+  _ = PdfParadise::DeleteThisPageOfThisPdfFile.new { :do_not_run_yet } 
+  _.set_pdf_file(that_pdf_file)
+  _.set_remove_this_pdf_page(this_page)
+  _.run
+end
+
+# =========================================================================== #
+# === PdfParadise.delete_last_page_of_this_pdf_file
+#
+# Easier method-way to invoke the above class.
+# =========================================================================== #
+def self.delete_last_page_of_this_pdf_file(i = ARGV)
+  PdfParadise::DeleteThisPageOfThisPdfFile.new(i)
+end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::DeleteThisPageOfThisPdfFile.new(ARGV)
+end # deletethispageofthispdffile

data/lib/pdf_paradise/utility_scripts/extract_all_images_from_this_pdf_file.rb

@@ -0,0 +1,129 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::ExtractAllImagesFromThisPdfFile
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/extract_all_images_from_this_pdf_file.rb'
+# PdfParadise::ExtractAllImagesFromThisPdfFile.new
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class ExtractAllImagesFromThisPdfFile < PdfParadise::Base # === PdfParadise::ExtractAllImagesFromThisPdfFile
+
+  require 'pdf_paradise/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      commandline_arguments = ARGV,
+      run_already           = true
+    )
+    reset
+    set_commandline_arguments(
+      commandline_arguments
+    )
+    case run_already
+    # ======================================================================= #
+    # === :do_not_run_yet
+    # ======================================================================= #
+    when :do_not_run_yet
+      run_already = false
+    end
+    make_sure_that_the_first_argument_is_not_a_symbol
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === make_sure_that_the_first_argument_is_not_a_symbol
+  # ========================================================================= #
+  def make_sure_that_the_first_argument_is_not_a_symbol
+    if @commandline_arguments
+      if @commandline_arguments.is_a? Symbol
+        @commandline_arguments = []
+      elsif @commandline_arguments.first.is_a? Symbol
+        @commandline_arguments.shift
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === determine_the_raw_name
+  #
+  # This method will determine the raw filename.
+  # ========================================================================= #
+  def determine_the_raw_name(
+      _ = first_argument?
+    )
+    if _ and _.is_a?(Array)
+      _ = _.first
+    end
+    if _
+      _ = _.dup # Work on a copy.
+      _.delete_suffix!('.pdf')
+      _ = File.basename(_) if _.include? '/'
+    end
+    # ======================================================================= #
+    # === @raw_name
+    # ======================================================================= #
+    @raw_name = _
+  end
+
+  # ========================================================================= #
+  # === do_extract_the_pdf_file
+  # ========================================================================= #
+  def do_extract_the_pdf_file(
+      i = first_argument?
+    )
+    if @raw_name.nil?
+      determine_the_raw_name(i) if i
+    end
+    if i and File.exist?(i)
+      cmd = "pdfimages -j #{i} #{@raw_name}"
+      e
+      esystem cmd
+      e
+    else
+      e "No file exists at `#{i}`."
+      false 
+    end
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    _ = first_argument?
+    determine_the_raw_name(_)
+    if _ and File.exist?(_)
+      do_extract_the_pdf_file(_)
+    end
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::ExtractAllImagesFromThisPdfFile.new(ARGV)
+end # eimages