pdf_paradise 0.1.66

data/lib/pdf_paradise/utility_scripts/extract_pdf_page.rb

@@ -0,0 +1,283 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::ExtractPdfPage
+#
+# Use this class to extract one or more pdf pages from a given .pdf file.
+#
+# Three arguments can be passed to this class:
+#
+#   The first argument  is the first page of the range to extract
+#   The second argument is the last page of the range to extract
+#   The third argument  is the given input file (the .pdf file)
+#
+# Specific invocation examples:
+#
+#   pdfpextr START_PAGE.pdf  5  19
+#   pdfpextr inputfile.pdf  22  36
+#   ext_pdf  foo.pdf         1 100
+#
+# Usage examples:
+#   require 'extract_pdf_page'
+#   ExtractPdfPage.new
+#   ExtractPdfPage.new :save_here => '/Depot/Temp/test.pdf'
+#
+# Usage examples from the commandline:
+#   epdf foo.pdf 5
+#   epdf foo.pdf 5 10
+# =========================================================================== #
+# require 'extract_pdf_page.rb'
+# =========================================================================== #
+require 'pdf_paradise/requires/esystem_and_opn_and_colours.rb'
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class ExtractPdfPage < PdfParadise::Base # === PdfParadise::ExtractPdfPage
+
+  require 'pdf_paradise/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === DEFAULT_START_PAGE
+  # ========================================================================= #
+  DEFAULT_START_PAGE =  '1'
+
+  # ========================================================================= #
+  # === DEFAULT_END_PAGE
+  #
+  # This number can be modified automatically during runtime.
+  # ========================================================================= #
+  DEFAULT_END_PAGE   = '10'
+
+  # ========================================================================= #
+  # === DEFAULT_EXTRACT_N_PDF_FILES
+  # ========================================================================= #
+  DEFAULT_EXTRACT_N_PDF_FILES = 1
+
+  # ========================================================================= #
+  # === initialize
+  #
+  # We accept three arguments:
+  #
+  #   (1) the name of the .pdf file
+  #   (2) the start page
+  #   (3) the end page
+  #
+  # ========================================================================= #
+  def initialize(
+      mandatory_name_of_pdf_file = nil,
+      optional_start_page = DEFAULT_START_PAGE, 
+      extract_n_pdf_files = DEFAULT_EXTRACT_N_PDF_FILES,
+      run_already         = true
+    )
+    reset
+    check_against_menu(mandatory_name_of_pdf_file)
+    if mandatory_name_of_pdf_file.is_a? Hash
+      if mandatory_name_of_pdf_file.has_key? :dont_run_yet 
+        run_already = !mandatory_name_of_pdf_file.delete(:dont_run_yet)
+      end
+    end
+    set_name_of_pdf_file(mandatory_name_of_pdf_file) # Must come before set_extract_n_pdf_files()
+    unless mandatory_name_of_pdf_file.is_a? Hash
+      set_start_page(optional_start_page)
+      set_extract_n_pdf_files(extract_n_pdf_files)
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === set_name_of_pdf_file
+  #
+  # The input can also be a Hash.
+  # ========================================================================= #
+  def set_name_of_pdf_file(i)
+    if i.is_a? Hash
+      if i.has_key? :start_page
+        set_start_page(i.delete(:start_page))
+      end
+      if i.has_key? :end_page
+        set_end_page(i.delete(:end_page))
+      end
+      if i.has_key? :pdf_file_to_use
+        i = i.delete(:pdf_file_to_use)
+      end
+    else
+      i = i.to_s
+    end
+    unless File.exist? i
+      opnn; e 'Warning - no file at `'+sfile(i.to_s)+'` could be found.'
+      opnn; e 'Thus we can not extract anything. Exiting now'
+      exit
+    end
+    @name_of_pdf_file = i
+  end; alias use_this_input_file set_name_of_pdf_file # === use_this_input_file
+
+  # ========================================================================= #
+  # === set_start_page
+  # ========================================================================= #
+  def set_start_page(
+      i = DEFAULT_START_PAGE
+    )
+    i = DEFAULT_START_PAGE if i.nil?
+    if i.is_a? Hash
+      if i.has_key? :save_here
+        set_save_here(i.delete(:save_here))
+      end
+    end
+    i = i.to_s
+    if File.exist?(i) and i.include? '.pdf'
+      use_this_input_file(i)
+      i = DEFAULT_START_PAGE
+    end
+    i = i.to_i
+    @start_page = i
+  end
+
+  # ========================================================================= #
+  # === report_to_the_user_where_we_stored_the_new_pdf_file
+  # ========================================================================= #
+  def report_to_the_user_where_we_stored_the_new_pdf_file
+    _ = output_file?
+    if File.exist? _
+      opnn; e 'Finished storing at `'+sfile(_)+'`.'
+    end
+  end
+
+  # ========================================================================= #
+  # === check_against_menu                                         (menu tag)
+  # ========================================================================= #
+  def check_against_menu(i = nil)
+    case i
+    when '--help','HELP'
+      e 'Usage example:'
+      e '  ext_pdf foo.pdf 1 100'
+      exit
+    end
+  end
+
+  # ========================================================================= #
+  # === start_page?
+  # ========================================================================= #
+  def start_page?
+    @start_page.to_s
+  end; alias which_page? start_page? # === which_page?
+
+  # ========================================================================= #
+  # === calculate_last_page
+  #
+  # This will calculate which page must be the last.
+  # ========================================================================= #
+  def calculate_last_page
+    return start_page?.to_i + (@extract_n_pdf_files.to_i - 1)
+  end
+
+  # ========================================================================= #
+  # === difference?
+  # ========================================================================= #
+  def difference?
+    return (calculate_last_page - start_page?.to_i) 
+  end; alias n_times difference? # === n_times
+
+  # ========================================================================= #
+  # === output_file?
+  # ========================================================================= #
+  def output_file?
+    @output_file
+  end
+
+  # ========================================================================= #
+  # === report_to_the_user_how_many_pages_we_extracted
+  # ========================================================================= #
+  def report_to_the_user_how_many_pages_we_extracted
+    n_pdf_pages = @extract_n_pdf_files.to_i
+    if File.exist? input_file?
+      opnn; e 'We extracted '+sfancy(n_pdf_pages.to_s)+' pdf pages.'
+    end
+  end
+
+  # ========================================================================= #
+  # === report_to_the_user
+  # ========================================================================= #
+  def report_to_the_user
+    report_to_the_user_how_many_pages_we_extracted
+    report_to_the_user_where_we_stored_the_new_pdf_file
+  end
+
+  # ========================================================================= #
+  # === name_of_pdf_file?
+  # ========================================================================= #
+  def name_of_pdf_file?
+    @name_of_pdf_file
+  end; alias input_file?           name_of_pdf_file? # === input_file?
+       alias name_of_the_pdf_file? name_of_pdf_file? # === name_of_the_pdf_file?
+
+  # ========================================================================= #
+  # === run_verbose_system_command
+  # ========================================================================= #
+  def run_verbose_system_command
+    n_times.times.each {|index|
+      start = start_page?.to_i+index.to_i
+      _ = ''.dup
+      _ << 'gs -sDEVICE=pdfwrite -dNOPAUSE -dBATCH -dSAFER'
+      _ << ' -dFirstPage='+start.to_s
+      _ << ' -dLastPage='+( start.to_i ).to_s
+      _ << ' -sOutputFile='+start.to_s+'_'+output_file?
+      _ << ' '+name_of_pdf_file?.to_s
+      esystem _
+    }
+  end
+
+  # ========================================================================= #
+  # === determine_output_file
+  # ========================================================================= #
+  def determine_output_file
+    # @output_file = 'extracted_page_'+which_page?+'_from_file_'+name_of_pdf_file?
+    @output_file = 'extracted_page_from_file_'+name_of_pdf_file?
+  end
+
+  # ========================================================================= #
+  # === set_end_page
+  # ========================================================================= #
+  def set_extract_n_pdf_files(i = DEFAULT_EXTRACT_N_PDF_FILES)
+    i = DEFAULT_EXTRACT_N_PDF_FILES if i.nil?
+    i = i.to_i
+    if i > ::PdfParadise.n_pdf_pages?(name_of_the_pdf_file?)
+      i = ::PdfParadise.n_pdf_pages?(name_of_the_pdf_file?)
+    end
+    @extract_n_pdf_files = i
+  end; alias set_end_page set_extract_n_pdf_files # === set_end_page
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    determine_output_file
+    run_verbose_system_command
+    report_to_the_user
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::ExtractPdfPage.new(ARGV[0], ARGV[1], ARGV[2])
+end # epdf

data/lib/pdf_paradise/utility_scripts/pdf_optimizer.rb

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

data/lib/pdf_paradise/utility_scripts/pdf_statistics.rb

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

data/lib/pdf_paradise/utility_scripts/pdf_to_html.rb

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