pdf_paradise 0.1.43

data/lib/pdf_paradise/toplevel_methods/reduce_size_of_this_pdf_file.rb

@@ -0,0 +1,43 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/reduce_size_of_this_pdf_file.rb'
+# =========================================================================== #
+require 'esystem'
+require 'pdf_paradise/toplevel_methods/e.rb'
+
+module PdfParadise
+
+  # ========================================================================= #
+  # === PdfParadise.reduce_size_of_this_pdf_file
+  #
+  # This method can be used to reduce the size of the passed .pdf file.
+  #
+  # This functionality depends on ghostscript (on the "gs" binary,
+  # specifically).
+  # ========================================================================= #
+  def self.reduce_size_of_this_pdf_file(this_pdf_file)
+    if this_pdf_file.is_a? Array
+      this_pdf_file.each {|entry|
+        reduce_size_of_this_pdf_file(entry)
+      }
+    else
+      guessed_name = File.basename(this_pdf_file).sub(/#{File.extname(this_pdf_file)}$/,'').dup
+      name_of_the_output_file = "output_#{guessed_name}".dup
+      name_of_the_output_file << '.pdf' unless name_of_the_output_file.end_with?('.pdf')
+      e
+      e 'Trying to reduce the size of the file '+this_pdf_file+' next:'
+      e
+      _ = 'gs -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 '\
+          '-dPDFSETTINGS=/screen -dNOPAUSE -dQUIET -dBATCH '\
+          '-sOutputFile='+name_of_the_output_file+' '+this_pdf_file
+      Esystem.esystem(_)
+    end
+  end; self.instance_eval { alias reduce_size reduce_size_of_this_pdf_file } # === PdfParadise.reduce_size
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise.reduce_size_of_this_pdf_file(ARGV)
+end # reduce_size_of_this_pdf_file

data/lib/pdf_paradise/toplevel_methods/roebe.rb

@@ -0,0 +1,17 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/roebe.rb'
+# PdfParadise.is_on_roebe?
+# =========================================================================== #
+module PdfParadise
+
+  # ========================================================================= #
+  # === PdfParadise.is_on_roebe?
+  # ========================================================================= #
+  def self.is_on_roebe?
+    ENV['IS_ROEBE'].to_s == '1'
+  end
+
+end

data/lib/pdf_paradise/toplevel_methods/to_pdf.rb

@@ -0,0 +1,38 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/to_pdf.rb'
+# PdfParadise.to_pdf
+# =========================================================================== #
+module PdfParadise
+
+  require 'pdf_paradise/toplevel_methods/e.rb'
+
+  # ========================================================================= #
+  # === PdfParadise.to_pdf
+  #
+  # This method can, by using soffice, convert a file such as .docx into
+  # the corresponding .pdf file - all on the commandline.
+  # ========================================================================= #
+  def self.to_pdf(
+      these_pdf_files = ARGV
+    )
+    [these_pdf_files].flatten.compact.map {|this_pdf_file|
+      if File.exist? this_pdf_file
+        _ = 'soffice --headless --invisible --convert-to pdf '+this_pdf_file
+        e _
+        system _
+        this_pdf_file # Return the path here, in case it has to be used.
+      else
+        e "No file exists at `#{this_pdf_file}.`"
+        nil
+      end
+    }
+  end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise.to_pdf(ARGV)  
+end # to_pdf

data/lib/pdf_paradise/utility_scripts/README.md

@@ -0,0 +1,3 @@
+This directory shall contain .rb files that can be used
+practically, e. g. to delete the last page of a .pdf file,
+and similar manipulations.

data/lib/pdf_paradise/utility_scripts/convert_pdf_to_text.rb

@@ -0,0 +1,166 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::ConvertPdfToText
+#
+# This file can convert one or several .pdf files to text files.
+#
+# Usage examples:
+#
+#   PdfParadise::ConvertPdfToText.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/convert_pdf_to_text.rb'
+# PdfParadise::ConvertPdfToText.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class ConvertPdfToText < ::PdfParadise::Base # === PdfParadise::ConvertPdfToText
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = ARGV,
+      run_already = true
+    )
+    reset
+    # ======================================================================= #
+    # Next designate which files are to be converted.
+    # ======================================================================= #
+    set_convert_these(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === get_all_pdf_files_from_current_directory
+  #
+  # This method will obtain all pdf files from the current directory.
+  # ========================================================================= #
+  def get_all_pdf_files_from_current_directory
+    return Dir['*.pdf']
+  end
+
+  # ========================================================================= #
+  # === set_convert_these
+  #
+  # This method will preferentially try to work on only .pdf files.
+  # ========================================================================= #
+  def set_convert_these(
+      i = return_pwd
+    )
+    i = return_pwd if i.nil?
+    if i.is_a? String
+      if i.empty?
+        i = get_all_pdf_files_from_current_directory()
+      elsif File.directory? i
+        i = get_all_pdf_files_from_current_directory()
+      end
+    elsif i.is_a? Array
+      i = get_all_pdf_files_from_current_directory() if i.empty?
+    end
+    i = [i] unless i.is_a? Array
+    @convert_these = i # This must be an Array.
+  end
+
+  # ========================================================================= #
+  # === start_conversion
+  # ========================================================================= #
+  def start_conversion
+    @convert_these.each {|pdf| convert_this_pdf(pdf) }
+  end
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === convert_this_pdf
+  #
+  # This will make use of the binary called "pdftotext".
+  # ========================================================================= #
+  def convert_this_pdf(
+      i = @convert_these
+    )
+    if i.is_a? Array
+      i.each {|entry| convert_this_pdf(entry) }
+    else
+      if File.exist? i
+        opnn; e "Now converting `#{sfile(i)}` via #{simp('pdftotext')}."
+        cmdline_to_use = 'pdftotext "'+i+'"' # We use "".
+        @output_file = i.gsub(/#{File.extname(i)}/, '')+'.txt'
+        system(cmdline_to_use)
+        opnn; e "Storing into the file `#{sfile(@output_file)}`."
+      else
+        unless i.start_with? '--'
+          opnn; e 'No file called '+sfile(i)+' could be found.'
+        end
+      end
+    end
+  end; alias do_convert convert_this_pdf # === do_convert
+
+  # ========================================================================= #
+  # === output_file?
+  # ========================================================================= #
+  def output_file?
+    @output_file
+  end
+
+  # ========================================================================= #
+  # === menu                                                       (menu tag)
+  # ========================================================================= #
+  def menu(
+      i = @convert_these
+    )
+    if i.is_a? Array
+      i.each {|entry| menu(entry) }
+    else
+      case i
+      # ===================================================================== #
+      # === cpdf --gui
+      # ===================================================================== #
+      when /^-?-?gui/i
+        do_start_the_GUI_interface
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === do_start_the_GUI_interface
+  # ========================================================================= #
+  def do_start_the_GUI_interface
+    require 'pdf_paradise/gui/gtk3/convert_pdf_to_text/convert_pdf_to_text.rb'
+    ::PdfParadise::GUI::Gtk::ConvertPdfToText.run
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    menu
+    start_conversion
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::ConvertPdfToText.new(ARGV)
+end # cpdf foobar.pdf

data/lib/pdf_paradise/utility_scripts/delete_first_page_of_this_pdf_file.rb

@@ -0,0 +1,185 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::DeleteFirstPageOfThisPdfFile
+#
+# This class will accept one (or several) .pdf files and then proceed
+# to remove the very first .pdf page in that file. So if that pdf-file
+# has had 100 pages, we will end up with 99 pages, and the first page
+# will be gone.
+#
+# By default, the class here will create a new output file and leave
+# the original file untouched.
+#
+# Note that the functionality made available through this class here
+# depends on either the binary called "qpdf" or on the binary called
+# "pdftk".
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/delete_first_page_of_this_pdf_file.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+require 'pdf_paradise/pdf_file_n_total_pages.rb'
+
+module PdfParadise
+
+class DeleteFirstPageOfThisPdfFile < Base 
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === SHALL_WE_OVERWRITE_THE_ORIGINAL_PDF_FILE
+  # ========================================================================= #
+  SHALL_WE_OVERWRITE_THE_ORIGINAL_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
+  end
+
+  # ========================================================================= #
+  # === set_input_files
+  # ========================================================================= #
+  def set_input_files(i)
+    i = [i] unless i.is_a? Array
+    # ======================================================================= #
+    # Next, if i is empty, and we are on Roebe, we will use the default
+    # book, if a certain ENV variable exists AND if the file that points
+    # to that location also exists.
+    # ======================================================================= #
+    if i.empty? and is_on_roebe?
+      if ENV.has_key?('MAIN_BOOK') and
+        File.exist?(ENV['MAIN_BOOK'])
+        this_file = ENV['MAIN_BOOK'].dup
+        e "#{rev}As we are on roebe, we will use this file:"
+        e
+        e sfile("  #{this_file}")
+        e
+        i << this_file
+      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)
+        if use_pdftk?
+          _ = 'pdftk '+this_pdf_file+' cat 2-'+(has_n_pages.to_i).to_s+' '+
+               has_n_pages.to_s+'-end output '+
+               name_of_the_output_file?(this_pdf_file)
+        else # else we use qpdf
+          _ = 'qpdf --pages '+this_pdf_file+' 2-'+(has_n_pages.to_i).to_s+' -- '+
+               this_pdf_file+' '+name_of_the_output_file?(this_pdf_file)
+        end
+        esystem _
+        if SHALL_WE_OVERWRITE_THE_ORIGINAL_PDF_FILE
+          # ================================================================= #
+          # In this case we will overwrite the original .pdf file.
+          # ================================================================= #
+          mv(
+            name_of_the_output_file?(this_pdf_file),
+            this_pdf_file
+          )
+        end
+      else
+        opnn; no_file_exists_at(this_pdf_file)
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === use_pdftk?
+  # ========================================================================= #
+  def use_pdftk?
+    false
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input_files
+  end
+
+  # ========================================================================= #
+  # === name_of_the_output_file?
+  #
+  # This method will determine the output file of the .pdf file.
+  # ========================================================================= #
+  def name_of_the_output_file?(i)
+    i.sub(/\.pdf$/,'')+'_output_file.pdf'
+  end; alias output? name_of_the_output_file? # === output?
+
+  # ========================================================================= #
+  # === run
+  # ========================================================================= #
+  def run
+    process_each_pdf
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.delete_first_page_of_this_pdf_file
+#
+# Easier method-way to invoke the above class.
+# =========================================================================== #
+def self.delete_first_page_of_this_pdf_file(i = ARGV)
+  PdfParadise::DeleteFirstPageOfThisPdfFile.new(i)
+end; self.instance_eval {
+  alias remove_the_first_page_of_this_pdf_file delete_first_page_of_this_pdf_file
+} # === PdfParadise.remove_the_first_page_of_this_pdf_file
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::DeleteFirstPageOfThisPdfFile.new(ARGV)
+end # delete_first_page_of_this_pdf_file