pdf_paradise 0.1.66

data/lib/pdf_paradise/set_pdf_title.rb

@@ -0,0 +1,220 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::SetPdfTitle
+#
+# This class can be used to set a new title to any given .pdf file.
+#
+# A module-method also exists, on module PdfParadise.
+#
+# We will make use of the excellent perl library called "exiftool"
+# for now. Perhaps at a later time, we will change to use something
+# else rather than perl. But for now, I simply wanted to have one
+# tool that works and move on. 
+#
+# A typical usage example would be like this:
+#
+#   exiftool -overwrite_original -Title="This is the Title now!" DONE_VO_06_Cell_Biology_Methods_Crystallography_How_to_make_a_car.pdf
+#
+# Usage example:
+#
+#   PdfParadise::SetPdfTitle.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/set_pdf_title.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class SetPdfTitle < Base # === PdfParadise::SetPdfTitle
+
+  # ========================================================================= #
+  # === SHALL_WE_DELETE_THE_ORIGINAL_FILE
+  # ========================================================================= #
+  SHALL_WE_DELETE_THE_ORIGINAL_FILE = true
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      name_of_the_pdf_file = nil,
+      new_title_to_use     = 'Default title',
+      run_already          = true
+    )
+    reset
+    if name_of_the_pdf_file.is_a?(Array) and (name_of_the_pdf_file.size > 1)
+      new_title_to_use     = name_of_the_pdf_file.last
+      if new_title_to_use.include? '--'
+        # =================================================================== #
+        # Assume this to be a commandline instruction then.
+        # =================================================================== #
+        case new_title_to_use # case tag
+        # =================================================================== #
+        # === --set-title=03 Stickstoff und Aminosäuren
+        # =================================================================== #
+        when /-?-?set(-|_)?title=(.+)$/
+          new_title_to_use = $2.to_s.dup
+        end
+      end
+      name_of_the_pdf_file = name_of_the_pdf_file.first
+    end
+    set_pdf_file(
+      name_of_the_pdf_file
+    )
+    set_title(new_title_to_use)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    set_title # Set a default, being nil in this case.
+    # ======================================================================= #
+    # === @commandline_to_use
+    # ======================================================================= #
+    @commandline_to_use = 'exiftool'.dup # This will be our commandline.
+    # ======================================================================= #
+    # === Designate the charset that is to be used next
+    #
+    # Next, append the charset to be used. This is usually UTF-8.
+    # exiftool claims that iso-8859-1 is an invalid encoding, but latin
+    # is valid, according to exiftool..
+    # ======================================================================= #
+    @commandline_to_use << ' -charset UTF8'
+    # @commandline_to_use << ' -charset latin' # <- It works with latin.
+  end
+
+  # ========================================================================= #
+  # === set_title                                                (title tag)
+  #
+  # Assign the title that we will use for the given .pdf file at hand.
+  # ========================================================================= #
+  def set_title(i = :default)
+    if i == :default
+      i = nil
+    else
+      i = i.to_s
+      i = i.dup if i.frozen?
+    end
+    i = "-Title=\"#{i}\"" if i
+    @title = i
+  end
+
+  # ========================================================================= #
+  # === set_pdf_file
+  # ========================================================================= #
+  def set_pdf_file(i)
+    i = i.first if i.is_a? Array
+    i = i.to_s # We need a String past this point.
+    i = i.dup if i.frozen?
+    @pdf_file = i
+  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
+
+  # ========================================================================= #
+  # === build_up_commandline_command
+  #
+  # Build up the main commandline to use here.
+  # ========================================================================= #
+  def build_up_commandline_command
+    if SHALL_WE_DELETE_THE_ORIGINAL_FILE
+      @commandline_to_use << ' -overwrite_original'
+    end
+    add_title_to_the_commandline
+    add_pdf_file_to_the_commandline
+  end
+
+  # ========================================================================= #
+  # === add_pdf_file_to_the_commandline
+  # ========================================================================= #
+  def add_pdf_file_to_the_commandline
+    @commandline_to_use << " #{@pdf_file}"
+  end
+
+  # ========================================================================= #
+  # === pdf_file?
+  # ========================================================================= #
+  def pdf_file?
+    @pdf_file
+  end; alias this_file? pdf_file? # === this_file?
+
+  # ========================================================================= #
+  # === add_title_to_the_commandline
+  # ========================================================================= #
+  def add_title_to_the_commandline
+    @commandline_to_use << " #{@title}"
+  end
+
+  # ========================================================================= #
+  # === run_commandline_command
+  # ========================================================================= #
+  def run_commandline_command
+    # The following clause can lead to an infinite loop, so it was disabled
+    # as of May 2022. It may have to be re-evaluated at a later point.
+    # if is_on_roebe? and return_pwd.include?('/home/x/books')
+    #   unless PdfParadise.respond_to? :automatic_pdf_title
+    #     require 'pdf_paradise/toplevel_methods/automatic_pdf_title.rb'
+    #   end
+    #   PdfParadise.autotitle(this_file?)
+    # end
+    esystem(@commandline_to_use)
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    build_up_commandline_command
+    run_commandline_command
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::SetPdfTitle[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.set_title_of_this_pdf_file
+#
+# You need to pass in two arguments to this module-method.
+#
+# The first argument is the path to the .pdf file in question that
+# you want to manipulate - that is, to change the title of said
+# .pdf file.
+#
+# The second argument is the new title of this .pdf file.
+# =========================================================================== #
+def self.set_title_of_this_pdf_file(
+    this_pdf_file,
+    this_title = ''
+  )
+  SetPdfTitle.new(this_pdf_file, this_title)
+end; self.instance_eval { alias set_pdf_title set_title_of_this_pdf_file } # === PdfParadise.set_pdf_title
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::SetPdfTitle.new(ARGV)
+end # pdf_title foo.pdf "This is the new title"

data/lib/pdf_paradise/sinatra/embeddable_interface.rb

@@ -0,0 +1,318 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::EmbeddableInterface
+#
+# The code in this file can be used to "embed" the functionality of
+# PdfParadise in web-applications, in particular in sinatra.
+#
+# This depends on the cyberweb project.
+# =========================================================================== #
+# require 'pdf_paradise/sinatra/embeddable_interface.rb'
+# include PdfParadise::EmbeddableInterface
+# PdfParadise::EmbeddableInterface.route_name?
+# =========================================================================== #
+module PdfParadise
+
+module EmbeddableInterface # === PdfParadise::EmbeddableInterface
+
+  require 'pdf_paradise/constants/constants.rb'
+
+  begin
+    require 'cyberweb/sinatra/custom_extensions.rb'
+    include Cyberweb::Sinatra::CustomExtensions
+  rescue LoadError; end
+
+  begin
+    require 'cyberweb/web_images/web_images.rb'
+  rescue LoadError; end
+
+  begin
+    require 'html_tags'
+    include HtmlTags::BaseModule
+  rescue LoadError; end
+
+  # ========================================================================= #
+  # Designate a uniform CSS style to use:
+  # ========================================================================= #
+  USE_THIS_UNIFORM_CSS_STYLE = 'margin-left:3.5em; font-weight: bold;'
+
+  # ========================================================================= #
+  # === RARROW
+  # ========================================================================= #
+  RARROW = '→'
+
+  # ========================================================================= #
+  # === USE_THIS_PORT
+  #
+  # Note that this constant, for the port, is only in use when we run
+  # the sinatra-specific part of PdfParadise in a standalone manner.
+  #
+  # When we run from the main controller, which is part of the Roebe
+  # project, then this port is not relevant, as that main controller
+  # already handles that case.
+  # ========================================================================= #
+  USE_THIS_PORT = '5200'
+
+  # ========================================================================= #
+  # === @route_name
+  # ========================================================================= #
+  @route_name = ''.dup
+
+  # ========================================================================= #
+  # === PdfParadise::EmbeddableInterface.set_route_name
+  # ========================================================================= #
+  def self.set_route_name(i)
+    @route_name = i
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::EmbeddableInterface.route_name?
+  # ========================================================================= #
+  def self.route_name?
+    @route_name
+  end
+
+  # ========================================================================= #
+  # === route_name?
+  # ========================================================================= #
+  def route_name?
+    ::PdfParadise::EmbeddableInterface.route_name?
+  end
+
+  # ========================================================================= #
+  # === sub_routes?
+  # ========================================================================= #
+  def sub_routes?
+    ::PdfParadise::EmbeddableInterface.sub_routes?
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::EmbeddableInterface.sub_routes?
+  #
+  # List the available sub-routes that depend on the main route_name?
+  # defined above. All sub-routes must be defined here, because we
+  # may expose this Hash to other applications. 
+  # ========================================================================= #
+  def self.sub_routes?
+    {
+      view:        route_name?+'/view',
+      n_pdf_pages: route_name?+'/n_pdf_pages'
+    }
+  end
+
+  # ========================================================================= #
+  # === input_type_user_input
+  # ========================================================================= #
+  def input_type_user_input
+    '<input type="text" name="user_input" style="border:3px solid slateblue; padding: 4px">'
+  end
+
+  # ========================================================================= #
+  # === input_type_submit
+  # ========================================================================= #
+  def input_type_submit(
+      text_to_use = 'Search'
+    )
+    '<input type="submit" name="user_input_submit" value="'+text_to_use+'" class="default_submit">'
+  end
+
+  # ========================================================================= #
+  # === html_start_then_title
+  # ========================================================================= #
+  def html_start_then_title
+    html_start+
+    default_title
+  end; alias html_then_title html_start_then_title # === html_then_title
+
+  # ========================================================================= #
+  # === open_body
+  # ========================================================================= #
+  def open_body
+    '<body style="font-size:larger">'
+  end
+
+  require 'pdf_paradise/version/version.rb'
+  # ========================================================================= #
+  # === return_paragraph_of_hyperlinks
+  # ========================================================================= #
+  def return_paragraph_of_hyperlinks
+    p(
+      'The following entry-points are available for the '\
+      '<b>PdfParadise project</b>: (Version: '+PdfParadise::VERSION+',
+      Last Update: '+PdfParadise::LAST_UPDATE+')
+      <br><br>'+
+      return_index_of_hyperlinks
+    )
+  end; alias footer return_paragraph_of_hyperlinks # === footer (footer tag)
+
+  # ========================================================================= #
+  # === return_link_to_root
+  # ========================================================================= #
+  def return_link_to_root
+    abr(
+      '/',
+      content: :self,
+      css_style: USE_THIS_UNIFORM_CSS_STYLE
+    )
+  end
+
+  # ========================================================================= #
+  # === return_view_string
+  # ========================================================================= #
+  def return_view_string
+    hash = PdfParadise::EmbeddableInterface.sub_routes?
+    h1('Pdf Options:', css_style: 'margin-left:0.25em;')+
+    p(
+      "The next link is to view all .pdf files at <b>"\
+      "#{PdfParadise.main_directory?}</b>"
+    )+
+    abr(hash[:view])
+  end; alias view? return_view_string # === view?
+
+  # ========================================================================= #
+  # === return_index_of_hyperlinks
+  #
+  # This method will bundle together the different indices containing the
+  # hyperlinks that will be shown on the root-directory.
+  # ========================================================================= #
+  def return_index_of_hyperlinks
+    # ======================================================================= #
+    # Obtain the hash that keeps track of all routes.
+    # ======================================================================= #
+    hash = PdfParadise::EmbeddableInterface.sub_routes?
+
+    if Object.const_defined? :WebObject
+      cat_image = Cyberweb.base64_image(:cat)
+    else
+      cat_image = ''
+    end
+    a('/', content: cat_image+' /',
+      css_style: USE_THIS_UNIFORM_CSS_STYLE)+
+      '<br>'+
+    a(hash[:view], content: cat_image+' /view',
+      css_style: USE_THIS_UNIFORM_CSS_STYLE)+
+      '<br>'+
+    a(hash[:n_pdf_pages], content: cat_image+' /n_pdf_pages',
+      css_style: USE_THIS_UNIFORM_CSS_STYLE)+
+      '<br>'+
+    a('/title', content: cat_image+' /title',
+      css_style: USE_THIS_UNIFORM_CSS_STYLE)+
+      '<br>'+
+    # ======================================================================= #
+    # Explain the autoconvert option a little bit:
+    # ======================================================================= #
+    p(
+      'Click on the <b>following link</b> to autoconvert all .pdf files '\
+      'in the directory called '\
+      '<b>'+PdfParadise.main_directory?.to_s+'</b>'
+    )+
+    a('/autoconvert', css_style: USE_THIS_UNIFORM_CSS_STYLE)+
+    '<br>'+
+    return_div_for_manual_pdf_conversion
+  end; alias return_the_hyperlinks return_index_of_hyperlinks # === return_the_hyperlinks
+
+  # ========================================================================= #
+  # === return_div_for_manual_pdf_conversion
+  # ========================================================================= #
+  def return_div_for_manual_pdf_conversion
+    # ======================================================================= #
+    # Determine the main route for the upcoming action:
+    # ======================================================================= #
+    route_to_this_action = '/convert_single_pdf_file/'
+    # ======================================================================= #
+    # Add the <div> that contains the manual conversion functionality:
+    # ======================================================================= #
+    # ======================================================================= #
+    # Explain how to convert just an individual file instead:
+    # ======================================================================= #
+    p('If you merely wish to convert a single .pdf file, you can use '\
+      'the following form for this:')+
+    div(css_style: 'padding: 0.2em') {
+      p(
+        '<b>Enter the name of the .pdf file that you wish to convert:</b>', css_style: 'padding:0.75em'
+      )+
+      form(action: route_to_this_action,
+           id: 'convert_single_pdf_file',
+           css_style: 'margin-left:2em; margin-top:2px') {
+        '<input type="text" name="user_input" style="border:3px solid slateblue; padding: 4px"><br>'\
+        '<b>Select a file</b>: <input type="file" name="this_file"><br>'\
+        '<input type="submit" name="user_input_submit" '\
+        'value="Click here to convert the .pdf file" style="2px dotted royalblue; '\
+        'color: white; background-color: olive; font-size: 1.50em;
+        margin:4px; padding: 4px; border: 1px solid black">'
+      }
+    }
+  end
+
+  # ========================================================================= #
+  # === close_html
+  # ========================================================================= #
+  def close_html
+    '</html>'
+  end
+
+  # ========================================================================= #
+  # === open_html
+  # ========================================================================= # 
+  def open_html
+    '<html>'
+  end; alias html_start open_html # === html_start
+
+  # ========================================================================= #
+  # === return_full_title
+  # ========================================================================= #
+  def return_full_title
+    '<title>PDF-based operations</title>'
+  end; alias default_title return_full_title # === default_title
+
+  # ========================================================================= #
+  # === close_body
+  # ========================================================================= #
+  def close_body
+    '</body>'
+  end
+
+  # ========================================================================= #
+  # === return_root_string
+  # ========================================================================= #
+  def return_root_string
+    html_then_title+
+    open_body+
+    return_paragraph_of_hyperlinks+
+    close_body+
+    close_html
+  end
+
+  # =========================================================================== #
+  # === return_n_pdf_pages
+  # =========================================================================== #
+  def return_n_pdf_pages
+    route_to_this_action = sub_routes?[:n_pdf_pages]
+    html_start_then_title+
+    p('Provide the path to a .pdf file:')+
+    form(action:    route_to_this_action,
+         id:        route_to_this_action.delete('/'),
+         css_style: 'margin-left:2em; margin-top:2px') {
+      input_type_user_input+
+      br+
+      input_type_submit('Submit')
+    }
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.embeddable_interface
+#
+# This method can be used to "embed" a fake-object that implements the
+# module defined above.
+# =========================================================================== #
+def self.embeddable_interface
+  object = Object.new
+  object.extend(PdfParadise::EmbeddableInterface)
+  return object
+end
+
+end

data/lib/pdf_paradise/toplevel_methods/automatic_pdf_title.rb

@@ -0,0 +1,55 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/automatic_pdf_title.rb'
+# PdfParadise.autotitle(ARGV)
+# =========================================================================== #
+module PdfParadise
+
+  begin
+    require 'colours'
+  rescue LoadError; end
+
+  require 'pdf_paradise/toplevel_methods/e.rb'
+  require 'pdf_paradise/set_pdf_title.rb'
+
+  # ========================================================================= #
+  # === 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(i)
+    i = [i].flatten.compact
+    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 "#{Colours.rev}Setting the title of the .pdf file "\
+          "#{Colours.sfile(this_pdf_file)} to:"
+        e
+        e "  #{new_pdf_title}"
+        e
+        set_pdf_title(
+          this_pdf_file, new_pdf_title # First comes the file, then the title.
+        )
+      else
+        e 'No .pdf file exists at `'+sfile(this_pdf_file)+'`.'
+      end
+    }
+  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/toplevel_methods/convert_epub_to_pdf.rb

@@ -0,0 +1,27 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+module PdfParadise
+
+  require 'pdf_paradise/toplevel_methods/esystem.rb'
+
+  # ========================================================================= #
+  # === PdfParadise.convert_epub_to_pdf
+  #
+  # This method allows us to convert an .epub file to .pdf format, if
+  # pandoc is available.
+  # ========================================================================= #
+  def self.convert_epub_to_pdf(i)
+    i = [i].flatten.compact
+    i.each {|entry|
+      _ = 'pandoc -s -t latex --toc --chapters --latex-engine=lualatex '+entry+' -o '+entry+'.pdf'
+      esystem _
+    }
+  end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise.convert_epub_to_pdf(ARGV)  
+end

data/lib/pdf_paradise/toplevel_methods/convert_markdown_to_pdf.rb

@@ -0,0 +1,45 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/toplevel_methods/convert_markdown_to_pdf.rb'
+# =========================================================================== #
+module PdfParadise
+
+  require 'pdf_paradise/toplevel_methods/e.rb'
+
+  # ========================================================================= #
+  # === PdfParadise.convert_markdown_to_pdf
+  #
+  # This method can be used to convert a markdown .md file into a .pdf
+  # file.
+  #
+  # This functionality depends on kramdown, and kramdown-pdf-converter.
+  # ========================================================================= #
+  def self.convert_markdown_to_pdf(
+      this_markdown_file
+    )
+    require 'kramdown'
+    require 'kramdown/converter/pdf'
+    begin
+      require 'save_file'
+    rescue LoadError; end
+    require 'colours'
+    [this_markdown_file].flatten.compact.each {|markdown_file|
+      if File.exist? markdown_file
+        text = File.read(markdown_file)
+        dataset = Kramdown::Document.new(text).to_pdf
+        target = markdown_file.sub(/#{File.extname(markdown_file)}$/,'')+'.pdf'
+        e 'Storing into the file `'+Colours.sfile(target)+'`.'
+        SaveFile.write_what_into(dataset, target)
+      else
+        e 'No file exists at '+Colours.sfile(markdown_file)+'.'
+      end
+    }
+  end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise.convert_markdown_to_pdf(ARGV)
+end # convert_markdown_to_pdf