pdf_paradise 0.3.20

data/lib/pdf_paradise/utility_scripts/pdf_optimizer.rb

@@ -0,0 +1,111 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: false
+# =========================================================================== #
+# === PdfParadise::PdfOptimizer
+#
+#   /screen   selects low-resolution output similar to the Acrobat Distiller
+#             "Screen Optimized" setting.
+#   /ebook    selects medium-resolution output similar to the Acrobat Distiller
+#             "eBook" setting.
+#   /printer  selects output similar to the Acrobat Distiller "Print Optimized"
+#             setting.
+#   /prepress selects output similar to Acrobat Distiller "Prepress Optimized"
+#             setting.
+#   /default  selects output intended to be useful across a wide variety of
+#             uses, possibly at the expense of a larger output file.
+# 
+# Usage example:
+#
+#   PdfParadise::PdfOptimizer.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/pdf_optimizer.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class PdfOptimizer < ::PdfParadise::Base # === PdfParadise::PdfOptimizer
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    set_input(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+  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
+       alias input_file? input? # === input_file?
+
+  # ========================================================================= #
+  # === output_file?
+  # ========================================================================= #
+  def output_file?
+    'output.pdf'
+  end; alias output_pdf? output_file? # === output_pdf?
+
+  # ========================================================================= #
+  # === use_ghostscript?
+  # ========================================================================= #
+  def use_ghostscript?
+    true # For now this is hardcoded.
+  end
+
+  # ========================================================================= #
+  # === output_ps
+  # ========================================================================= #
+  def output_ps
+    'output.ps'
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    # ======================================================================= #
+    # We have two different solutions.
+    # ======================================================================= #
+    if use_ghostscript?
+      _ = 'gs -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 -dPDFSETTINGS=/screen '\
+          '-dNOPAUSE -dQUIET -dBATCH -sOutputFile='+
+          output_file?+' '+
+          input_file?
+    else
+      _ = 'pdf2ps '+input?+' '+output_ps
+      esystem _
+      _ = 'ps2pdf '+output_ps+' '+output_pdf?
+    end
+    esystem _
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::PdfOptimizer.new(ARGV)
+end # pdfoptimizer

data/lib/pdf_paradise/utility_scripts/pdf_statistics.rb

@@ -0,0 +1,148 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::PdfStatistics
+#
+# This class will make use of PDF::Reader to provide us with some
+# statistical information about a given .pdf file.
+#
+# You can also ouput information from a specific page.
+#
+# PDF is a page based file format, so most visible information
+# is available via page-based iteration
+# 
+#   reader = PDF::Reader.new("somefile.pdf")
+# 
+#   reader.pages.each { |page|
+#     puts page.fonts
+#     puts page.text
+#     puts page.raw_content
+#   }
+#
+# Usage example:
+#
+#   PdfParadise::PdfStatistics.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/pdf_statistics.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class PdfStatistics < ::PdfParadise::Base # === PdfParadise::PdfStatistics
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    require_pdf_reader
+    reset
+    set_input(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+  end
+
+  # ========================================================================= #
+  # === require_pdf_reader
+  # ========================================================================= #
+  def require_pdf_reader
+    old_verbose = $VERBOSE
+    $VERBOSE = nil
+    require 'pdf-reader'
+    $VERBOSE = old_verbose # Restore it again here.
+  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
+
+  # ========================================================================= #
+  # === instantiate_reader_object
+  # ========================================================================= #
+  def instantiate_reader_object
+    @reader = PDF::Reader.new(input?)
+  end
+
+  # ========================================================================= #
+  # === show_extended_info
+  #
+  # This will tap into the .info method.
+  # ========================================================================= #
+  def show_extended_info
+    hash = @reader.info
+    ljust = 32
+    if hash.has_key? :Title
+      e 'The title of this .pdf is: '.ljust(ljust)+simp(hash[:Title])
+    end
+    if hash.has_key? :CreationDate
+      e 'This .pdf was created at: '.ljust(ljust)+simp(hash[:CreationDate])
+    end
+    if hash.has_key? :Author
+      e 'The author of this .pdf is: '.ljust(ljust)+simp(hash[:Author])
+    end
+    if hash.has_key? :Producer
+      e 'It was produced via: '.ljust(ljust)+simp(hash[:Producer])
+    end
+    if hash.has_key? :ModDate
+      e 'It was last modified at: '.ljust(ljust)+simp(hash[:ModDate])
+    end
+    if hash.has_key? :Creator
+      e 'It was created via: '.ljust(ljust)+simp(hash[:Creator])
+    end
+  end
+ 
+  # ========================================================================= #
+  # === report_n_pages_in_the_pdf_document
+  # ========================================================================= #
+  def report_n_pages_in_the_pdf_document
+    e 'n pages in this .pdf document:  '+simp(@reader.page_count)
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    instantiate_reader_object
+    cliner
+    e rev+
+      'The PDF version for this .pdf file was: '+simp(@reader.pdf_version)
+    show_extended_info
+    # e @reader.metadata # <- This is how to obtain the metadata information.
+    report_n_pages_in_the_pdf_document
+    cliner
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::PdfStatistics[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::PdfStatistics.new(ARGV)
+end # pdfstatistics /Depot/PDF/foobar.pdf

data/lib/pdf_paradise/utility_scripts/pdf_to_html.rb

@@ -0,0 +1,75 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::PdfToHtml
+#
+# This class will convert a .pdf file to .html, based on pdftohtml from
+# poppler.
+#
+# Usage examples:
+#
+#   PdfParadise::PdfToHtml.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/pdf_to_html.rb'
+# PdfParadise::PdfToHtml.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class PdfToHtml < ::PdfParadise::Base # === PdfParadise::PdfToHtml
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = ARGV,
+      run_already = true
+    )
+    reset
+    set_commandline_arguments(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    commandline_arguments?.each {|entry|
+      # ===================================================================== #
+      # The -s option is used to "generate single HTML that includes all
+      # pages".
+      # ===================================================================== #
+      _ = 'pdftohtml -s '+entry+' '+
+          File.basename(entry+'_to_html')+
+          '.html'
+      esystem _
+    }
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::PdfToHtml.new(ARGV)
+end # pdf_to_html foobar.pdf

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