pdf_paradise 0.3.20

data/lib/pdf_paradise/toplevel_methods/query_pdf_title.rb

@@ -0,0 +1,201 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::QueryPdfTitle
+#
+# This class will simply report the title of a .pdf file (or more accurately,
+# all .pdf files that were passed to this class).
+#
+# Presently this depends on exiftool, but there are other ways how to
+# query the title of a .pdf file, such as via prawn.
+#
+# However had, for the time being, we will depend on exiftool.
+#
+# The shell-invocation command for this would be:
+#
+#   exiftool *.pdf | grep Title
+#
+# Usage example:
+#
+#   PdfParadise::QueryPdfTitle.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/query_pdf_title.rb'
+# PdfParadise::QueryPdfTitle.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class QueryPdfTitle < Base # === PdfParadise::QueryPdfTitle
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    set_input(i)
+    if block_given?
+      yielded = yield
+      case yielded
+      when :be_verbose
+        @be_verbose = true
+      when :be_quiet
+        @be_verbose = false
+      end
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @be_verbose
+    # ======================================================================= #
+    @be_verbose = true
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+  end
+
+  # ========================================================================= #
+  # === set_input
+  # ========================================================================= #
+  def set_input(i = '')
+    i = [i] unless i.is_a? Array
+    @input = i
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input
+  end; alias pdf_files? input? # === pdf_files?
+
+  # ========================================================================= #
+  # === iterate_over_the_input_files
+  # ========================================================================= #
+  def iterate_over_the_input_files
+    use_this_regex = /^Title\s*: (.+)$/
+    pdf_files?.each {|this_pdf_file|
+      if File.exist? this_pdf_file
+        sys_cmd = `exiftool #{this_pdf_file}`
+        begin
+          @title = sys_cmd.scan(use_this_regex).flatten.first
+        rescue ArgumentError => error
+          e 'An error happened for '+sfile(this_pdf_file)+'.'
+          pp error
+          pp error.class
+          exit
+        end
+        if @be_verbose
+          e "#{rev}The title for `#{sfile(this_pdf_file)}#{rev}` is:"
+          e
+          e "  #{sfancy(@title)}"
+          e
+        end
+      else
+        opnn(namespace: @namespace); e "No file exists at `#{sfile(this_pdf_file)}`."
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === title?
+  # ========================================================================= #
+  def title?
+    @title
+  end
+
+  # ========================================================================= #
+  # === string?
+  #
+  # This variant will always return a String - an empty String if the .pdf
+  # file has no title set.
+  # ========================================================================= #
+  def string?
+    title?.to_s
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    iterate_over_the_input_files
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::QueryPdfTitle[]
+  # ========================================================================= #
+  def self.[](i = '')
+    self.new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.does_this_pdf_file_have_a_title?
+#
+# This method can be used to query whether a given .pdf file has a title
+# or whether it does not.
+#
+# Usage examples:
+#
+#   PdfParadise.does_this_pdf_file_have_a_title? "foobar.pdf" # => true
+#   PdfParadise.has_title? "foobar.pdf" # => true
+#
+# =========================================================================== #
+def self.does_this_pdf_file_have_a_title?(i)
+  !query_pdf_title(i).empty?
+end; self.instance_eval { alias has_title? does_this_pdf_file_have_a_title? } # === PdfParadise.has_title?
+
+# =========================================================================== #
+# === PdfParadise.pdf_has_no_title?
+# =========================================================================== #
+def self.pdf_has_no_title?(i)
+  !does_this_pdf_file_have_a_title?(i)
+end
+
+# =========================================================================== #
+# === PdfParadise.query_pdf_title
+#
+# The input to this method should be an existing .pdf file.
+#
+# It will call class QueryPdfTitle to determine the title of the .pdf
+# file at hand.
+#
+# This method will return a String if a title can be found in the
+# .pdf file at hand.
+#
+# Usage example:
+#
+#   title = PdfParadise.query_pdf_title('/foobar.pdf') # => "Lecture 2 - Scaling"
+#   title = PdfParadise.return_title_of_this_pdf_file('')
+#
+# =========================================================================== #
+def self.query_pdf_title(i)
+  PdfParadise::QueryPdfTitle.new(i) { :be_quiet }.string?
+end; self.instance_eval { alias return_pdf_title_of           query_pdf_title } # === PdfParadise.return_pdf_title
+     self.instance_eval { alias return_title_of_this_pdf_file query_pdf_title } # === PdfParadise.return_title_of_this_pdf_file
+     self.instance_eval { alias title?                        query_pdf_title } # === PdfParadise.title?
+     self.instance_eval { alias return_title_of_this_pdf_file query_pdf_title } # === PdfParadise.return_title_of_this_pdf_file
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::QueryPdfTitle.new(ARGV)
+end # querypdftitle

data/lib/pdf_paradise/toplevel_methods/reduce_size_of_this_pdf_file.rb

@@ -0,0 +1,46 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/reduce_size_of_this_pdf_file.rb'
+# =========================================================================== #
+module PdfParadise
+
+  require 'pdf_paradise/toplevel_methods/e.rb'
+
+  begin
+    require 'esystem'
+  rescue LoadError; end
+
+  # ========================================================================= #
+  # === 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 +1,12 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/to_pdf.rb'
+# PdfParadise.to_pdf
+# =========================================================================== #
+require 'pdf_paradise/utility_scripts/to_pdf.rb'
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise.to_pdf(ARGV)  
+end # topdf

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/automatic_pdf_title.rb

@@ -0,0 +1,104 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::AutomaticPdfTitle
+#
+# This class can automatically set the title of a .pdf file.
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/automatic_pdf_title.rb'
+# PdfParadise.autotitle(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+ 
+module PdfParadise
+
+class AutomaticPdfTitle < Base # === PdfParadise::AutomaticPdfTitle 
+
+  require 'pdf_paradise/set_pdf_title.rb'
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      input_files = ARGV,
+      run_already = true
+    )
+    reset
+    set_commandline_arguments(
+      input_files
+    )
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+    infer_the_namespace
+  end
+
+  # ========================================================================= #
+  # === automatic_pdf_title
+  # ========================================================================= #
+  def automatic_pdf_title(
+      i = commandline_arguments?
+    )
+    i.each {|this_pdf_file|
+      if File.exist? this_pdf_file
+        new_pdf_title = File.basename(this_pdf_file).
+                        sub(/#{File.extname(this_pdf_file)}$/,'').
+                        tr('_',' ')
+        # =================================================================== #
+        # Remove leading 'DONE_' substrings:
+        # =================================================================== #
+        if new_pdf_title.start_with? 'DONE'
+          new_pdf_title.sub!(/^DONE_/,'') if new_pdf_title.include? 'DONE_'
+          new_pdf_title.sub!(/^DONE /,'') if new_pdf_title.include? 'DONE '
+        end
+        e "#{rev}Setting the title of the .pdf file "\
+          "#{sfile(this_pdf_file)} #{rev}to:"
+        e
+        e "  #{PdfParadise.darkolivegreen(new_pdf_title)}"
+        e
+        PdfParadise.set_pdf_title(
+          this_pdf_file,
+          new_pdf_title # First comes the file, then the title.
+        )
+      else
+        e "#{rev}No .pdf file exists at `#{sfile(this_pdf_file)}#{rev}`."
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    automatic_pdf_title(commandline_arguments?)
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.automatic_pdf_title
+#
+# This method will automatically set the title of a .pdf file to its
+# filename, with all '_' tokens replaced by ' ' tokens.
+#
+# The input to this method should be .pdf files that are existing locally.
+# =========================================================================== #
+def self.automatic_pdf_title(
+    of_this_pdf_file = ARGV
+  )
+  [of_this_pdf_file].flatten.compact.each {|this_pdf_file|
+    PdfParadise::AutomaticPdfTitle.new(this_pdf_file)
+  }
+end; self.instance_eval { alias autotitle automatic_pdf_title } # === PdfParadise.autotitle
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise.automatic_pdf_title(ARGV)
+end # apdf

data/lib/pdf_paradise/utility_scripts/check_syntax_of_pdf_files.rb

@@ -0,0 +1,106 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::CheckSyntaxOfPdfFiles
+#
+# This class will check for the syntax of .pdf files.
+#
+# Usage example:
+#
+#   PdfParadise::CheckSyntaxOfPdfFiles.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/check_syntax_of_pdf_files.rb'
+# PdfParadise::CheckSyntaxOfPdfFiles.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class CheckSyntaxOfPdfFiles < ::PdfParadise::Base # === PdfParadise::CheckSyntaxOfPdfFiles
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = ARGV,
+      run_already = true
+    )
+    reset
+    set_commandline_arguments(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    _ = commandline_arguments?
+    work_on_these_files(_)
+  end
+
+  # ========================================================================= #
+  # === work_on_these_files
+  # ========================================================================= #
+  def work_on_these_files(i)
+    if i.is_a?(Array) and (i.first == :work_on_every_pdf_file_in_the_current_working_directory)
+      i = Dir['*.pdf']
+    end
+    i.each {|entry|
+      if File.file?(entry)
+        check_this_pdf_file(entry)
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === check_this_pdf_file
+  #
+  # This is the method that does the syntax-check, via qpdf.
+  #
+  # The specific commandline that will be invoked is:
+  #
+  #   qpdf --check 09.11.2009_Scan_Dr_Kirchmayer_Statik_und_Edbebensicherheit.pdf
+  #
+  # ========================================================================= #
+  def check_this_pdf_file(
+      i
+    )
+    # ======================================================================= #
+    # Always work on an Array:
+    # ======================================================================= #
+    [i].flatten.compact.each {|this_pdf_file|
+      cmd_to_run = "qpdf --check #{this_pdf_file}"
+      e
+      e cmd_to_run
+      e
+      result = `#{cmd_to_run}`
+      if result.include? 'No syntax or stream encoding errors found'
+        e sfile(this_pdf_file)+rev+': all is fine with this .pdf file.'
+      else
+        e swarn('Some problem exists for ')+sfile(this_pdf_file)+rev
+        pp result
+      end
+    }
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::CheckSyntaxOfPdfFiles[]
+  # ========================================================================= #
+  def self.[](i = ARGV)
+    new(i)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::CheckSyntaxOfPdfFiles.new(ARGV)
+end # CheckSyntaxOfPdfFiles

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