pdf_paradise 0.1.66

data/lib/pdf_paradise/toplevel_methods/rotate_pdf_file.rb

@@ -0,0 +1,143 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::RotatePdfFile
+#
+# Usage example:
+#
+#   PdfParadise::RotatePdfFile.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/rotate_pdf_file.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class RotatePdfFile < Base # === PdfParadise::RotatePdfFile
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === ROTATE_BY_N_DEGREES
+  # ========================================================================= #
+  ROTATE_BY_N_DEGREES = 90
+
+  # ========================================================================= #
+  # === ROTATE_REGEX
+  # ========================================================================= #
+  ROTATE_REGEX = /(--rotate (\d+))/ # URL: http://rubular.com/r/ds3tk7DPPw
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i = nil,
+      run_already = true
+    )
+    reset
+    set_input(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    set_rotate
+  end
+
+  # ========================================================================= #
+  # === set_rotate
+  # ========================================================================= #
+  def set_rotate(i = ROTATE_BY_N_DEGREES)
+    @rotate_by_n_degrees = i.to_s
+  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
+    # ========================================================================= #
+    # === --help
+    # ========================================================================= #
+    when 'HELP',/-?-?help$/,'' # '' means empty.
+      opnn; e 'The available options are:'
+      opnn; eparse '  --rotate N # rotate by n degrees (into '\
+                   'clockwise direction. Example: rotatepdf --rotate 90 foo.pdf)'
+      exit
+    # ======================================================================= #
+    # 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!(/#{$1.to_s}/, '')
+    end unless File.exist? i
+    i = i.to_s.strip
+    @input = i
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input
+  end
+
+  # ========================================================================= #
+  # === output_file?
+  # ========================================================================= #
+  def output_file?
+    _ = File.basename(input?).gsub(/\.pdf$/,'')
+    _.tr(' ','') if _.include? ' '
+    '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
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    _ = 'convert '+input?+' -rotate '+rotate_by_n_degrees?+' '+add_quality+output_file?
+    esystem _
+    e 'Finished converting! The file should now reside at:'
+    e sfile('  '+output_file?)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::RotatePdfFile.new(ARGV)
+end # rotatepdf

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/combine_these_pdf_pages.rb

@@ -0,0 +1,118 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::CombineThesePdfPages
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/combine_these_pdf_pages.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class CombineThesePdfPages < PdfParadise::Base # === PdfParadise::CombineThesePdfPages
+
+  require 'pdf_paradise/utility_scripts/split_pdf.rb'
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      commandline_arguments = ARGV,
+      run_already           = true
+    )
+    reset
+    set_commandline_arguments(
+      commandline_arguments
+    )
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    name_of_the_pdf_file = File.absolute_path(first_argument?)
+    unless File.exist? name_of_the_pdf_file
+      e 'Please provide a path to an existing .pdf file.'
+      return
+    end
+    _ = log_dir?
+    mkdir(_) unless File.directory? _
+    cd _
+    if File.exist? name_of_the_pdf_file
+      unless File.exist? File.absolute_path(File.basename(name_of_the_pdf_file))
+        e 'Copying the file '+name_of_the_pdf_file+'.'
+        copy_file(name_of_the_pdf_file)
+      end
+      if File.exist? File.basename(name_of_the_pdf_file)
+        name_of_the_pdf_file = File.absolute_path(File.basename(name_of_the_pdf_file))
+      end
+    end
+    these_pages_must_be_kept = commandline_arguments?[1]
+    # Must be converted into an array.
+    if these_pages_must_be_kept.include? ','
+      these_pages_must_be_kept = these_pages_must_be_kept.split(',')
+    else
+      these_pages_must_be_kept = [these_pages_must_be_kept]
+    end
+    these_pages_must_be_kept.map! {|entry| entry.to_i }
+    begin
+      require 'hexapdf'
+      pdf = HexaPDF::Document.open(name_of_the_pdf_file)
+      new_pdf = HexaPDF::Document.new
+      pdf.pages.each_with_index { |page, index| index += 1
+        if these_pages_must_be_kept.include? index
+          e 'Copying page page number: '+
+             steelblue(index.to_s)
+          new_pdf.pages << new_pdf.import(page)
+        end
+      }
+      @output_file_to_use = 'output.pdf'
+      @output_file_to_use = File.absolute_path(@output_file_to_use)
+      delete_file(@output_file_to_use) if File.exist? @output_file_to_use
+      e 'Storing into `'+@output_file_to_use+'`.'
+      new_pdf.write(
+        @output_file_to_use,
+        validate: false,
+        optimize: true
+      )
+    rescue LoadError
+      e 'HexaPDF is not available. Please install it via:'
+      e
+      e '  gem install hexapdf'
+      e
+    end
+  end
+
+  # ========================================================================= #
+  # === stored_where?
+  # ========================================================================= #
+  def stored_where?
+    @output_file_to_use
+  end; alias output_file_to_use? stored_where? # === output_file_to_use?
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::CombineThesePdfPages.new(ARGV)
+end # combinethesepdfpages

data/lib/pdf_paradise/utility_scripts/convert_pdf_to_text.rb

@@ -0,0 +1,175 @@
+#!/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
+
+# =========================================================================== #
+# === PdfParadise.pdf_to_text
+# =========================================================================== #
+def self.pdf_to_text(i = ARGV)
+  PdfParadise::ConvertPdfToText.new(i)
+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 +1,221 @@
+#!/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'
+# PdfParadise::DeleteFirstPageOfThisPdfFile.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class DeleteFirstPageOfThisPdfFile < Base 
+
+  require 'pdf_paradise/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === 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
+    # ======================================================================= #
+    # === @use_this_pdf_application
+    #
+    # The following variable may be :hexapdf, :pdftk or :qpdf.
+    #
+    # It specifies which application can be used for deleting .pdf pages.
+    # ======================================================================= #
+    @use_this_pdf_application = :qpdf # :hexapdf # :pdftk
+  end
+
+  # ========================================================================= #
+  # === use_hexapdf?
+  # ========================================================================= #
+  def use_hexapdf?
+    @use_this_pdf_application == :hexapdf
+  end
+
+  # ========================================================================= #
+  # === set_input_files
+  # ========================================================================= #
+  def set_input_files(i)
+    i = [i] unless i.is_a? Array
+    i.map! {|entry|
+      if entry.include? '*'
+        entry = Dir[entry]
+      end
+      entry
+    }
+    i.flatten!
+    # ======================================================================= #
+    # 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
+        # ===================================================================== #
+        # Store how many pages this .pdf file has.
+        # ===================================================================== #
+        has_n_pages = PdfParadise.n_pages_in_this_pdf_file?(this_pdf_file)
+        if this_pdf_file.include? ' '
+          this_pdf_file = '"'+this_pdf_file+'"'
+        end
+        opnn; e 'Now working on the .pdf file '+sfancy(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)
+        elsif use_hexapdf?
+          _ = 'hexapdf modify '+this_pdf_file+' -i 2-e '+
+               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?
+    @use_this_pdf_application == :pdftk
+  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
+    self.instance_eval {
+  alias remove_first_page_of_this_pdf_file delete_first_page_of_this_pdf_file
+} # === PdfParadise.remove_first_page_of_this_pdf_file
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::DeleteFirstPageOfThisPdfFile.new(ARGV)
+end # delete_first_page_of_this_pdf_file