pdf_paradise 0.1.66

data/lib/pdf_paradise/utility_scripts/remove_images.rb

@@ -0,0 +1,110 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::RemoveImages
+#
+# This class will remove all images from a given .pdf file, by making use
+# of ghostscript.
+#
+# Usage example:
+#
+#   PdfParadise::RemoveImages.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/remove_images.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class RemoveImages < ::PdfParadise::Base # === PdfParadise::RemoveImages
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    set_input(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === set_input
+  # ========================================================================= #
+  def set_input(i = '')
+    i = i.first if i.is_a? Array
+    i = i.to_s.dup
+    @input = i
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input
+  end; alias input_file? input? # === input_file?
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    input_file = input_file?
+    this_output_file = 'only_text_is_kept_'+input_file
+    if File.exist? input_file
+      opnn; e 'Now removing all images from the file `'+sfile(input_file)+'`.'
+      opnn; e 'Will store into the file `'+sfile(this_output_file)+'`.'
+      _ = 'gs -o '+this_output_file+' -sDEVICE=pdfwrite -dFILTERVECTOR -dFILTERIMAGE '+input_file
+      esystem _
+      if File.exist? this_output_file
+        opnn; e 'The file `'+sfile(this_output_file)+'` has been created!'
+      end
+    else
+      e 'Please supply an argument to this class that should be a local'
+      e '.pdf file.'
+    end
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::RemoveImages[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.remove_image
+# =========================================================================== #
+def self.remove_image(from_this_pdf_file = ARGV)
+  RemoveImage.new(from_this_pdf_file)
+end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::RemoveImages.new(ARGV)
+end # removeimagesfromthispdffile

data/lib/pdf_paradise/utility_scripts/split_pdf.rb

@@ -0,0 +1,340 @@
+#!/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/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === 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
+    )
+    reset
+    set_commandline_arguments(
+      optional_arguments
+    )
+    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
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+    # ======================================================================= #
+    # === @path
+    # ======================================================================= #
+    @path = nil
+    # ======================================================================= #
+    # === @use_convert_or_hexapdf
+    # ======================================================================= #
+    @use_convert_or_hexapdf = :convert # :hexapdf
+  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'+(old_index.to_i+1).to_s+
+           '.pdf'
+  end
+
+  # ========================================================================= #
+  # === do_convert_this_file_via_hexapdf
+  # ========================================================================= #
+  def do_convert_this_file_via_hexapdf(i)
+    e 'This is currently unfinished.'
+  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

data/lib/pdf_paradise/utility_scripts/to_qdf.rb

@@ -0,0 +1,82 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::ToQdf
+#
+# This class will convert a .pdf file into a .qdf file.
+#
+# Usage example:
+#
+#   PdfParadise::ToQdf.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/to_qdf.rb'
+# PdfParadise::ToQdf.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class ToQdf < ::PdfParadise::Base # === PdfParadise::ToQdf
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      commandline_arguments = nil,
+      run_already           = true
+    )
+    reset
+    set_commandline_arguments(
+      commandline_arguments
+    )
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+  end
+
+  # ========================================================================= #
+  # === set_commandline_arguments
+  # ========================================================================= #
+  def set_commandline_arguments(i = '')
+    i = [i].flatten.compact
+    @commandline_arguments = i
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    @commandline_arguments.each {|entry|
+      qdf_file = entry.sub(/\.?pdf$/,)
+      esystem "qpdf -qdf #{entry} #{qdf_file}.qdf"
+    }
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::ToQdf[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::ToQdf.new(ARGV)
+end # to_qdf

data/lib/pdf_paradise/version/version.rb

@@ -0,0 +1,19 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/version/version.rb'
+# =========================================================================== #
+module PdfParadise
+
+  # ========================================================================= #
+  # === VERSION
+  # ========================================================================= #
+  VERSION = '0.1.66'
+
+  # ========================================================================= #
+  # === LAST_UPDATE
+  # ========================================================================= #
+  LAST_UPDATE = '15.09.2022'
+
+end

data/lib/pdf_paradise/www/README.md

@@ -0,0 +1,2 @@
+In this directory we will put code that can be used on
+the www.