pdf_paradise 0.3.20

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/utility_scripts/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_file_n_total_pages.rb

@@ -0,0 +1,348 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::PdfFileNTotalPages
+#
+# This class can report how many pages are in a given .pdf file.
+#
+# Also note that an alternative exists:
+#
+#   https://github.com/prawnpdf/pdf-inspector
+#
+# The code would be like this here:
+#
+#   page_analysis = PDF::Inspector::Page.analyze(pdf)
+#   page_analysis.pages.size # <-- like 50 pages
+#
+# Usage example:
+#
+#   PdfParadise::PdfFileNTotalPages.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/pdf_file_n_total_pages.rb'
+# PdfParadise::PdfFileNTotalPages.new(ARGV) 
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class PdfFileNTotalPages < Base # === PdfParadise::PdfFileNTotalPages
+
+  # ========================================================================= #
+  # === MATCH_AGAINST_THIS_REGEX
+  # ========================================================================= #
+  MATCH_AGAINST_THIS_REGEX = /Count (\d+)/
+
+  # ========================================================================= #
+  # === USE_THIS_PROGRAM_TO_DETERMINE_HOW_MANY_PAGES_ARE_PART_OF_THE_PDF_FILE
+  #
+  # This can be :pdfinfo or :qpdf or similar.
+  # ========================================================================= #
+  USE_THIS_PROGRAM_TO_DETERMINE_HOW_MANY_PAGES_ARE_PART_OF_THE_PDF_FILE = :hexapdf # :qpdf # :pdfinfo
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true,
+      &block
+    )
+    reset
+    # ======================================================================= #
+    # === @be_verbose
+    #
+    # Must be defined here, as reset() may be called from another method.
+    # ======================================================================= #
+    @be_verbose = true
+    set_commandline_arguments(i)
+    # ======================================================================= #
+    # === Handle blocks next
+    # ======================================================================= #
+    if block_given?
+      yielded = yield
+      case yielded
+      # ===================================================================== #
+      # === :be_quiet
+      # ===================================================================== #
+      when :be_quiet,
+           :be_silent
+        @be_verbose = false
+        run_already = false
+      end
+    end
+    case run_already
+    # ======================================================================= #
+    # === :be_silent
+    # ======================================================================= #
+    when :be_silent
+      @be_verbose = false
+      run_already = false
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    infer_the_namespace
+    reset_the_internal_variables
+  end
+
+  # ========================================================================= #
+  # === reset_the_internal_variables
+  # ========================================================================= #
+  def reset_the_internal_variables
+    # ======================================================================= #
+    # === @n_pages
+    #
+    # This variable will keep track as to how many pages the given .pdf
+    # page has.
+    # ======================================================================= #
+    @n_pages = 0
+    # ======================================================================= #
+    # === @use_this_program_to_determine_how_many_pages_are_part_of_the_pdf_file
+    # ======================================================================= #
+    @use_this_program_to_determine_how_many_pages_are_part_of_the_pdf_file =
+      USE_THIS_PROGRAM_TO_DETERMINE_HOW_MANY_PAGES_ARE_PART_OF_THE_PDF_FILE
+  end
+
+  # ========================================================================= #
+  # === n_pages
+  # ========================================================================= #
+  def n_pages?
+    @n_pages
+  end; alias n_pages n_pages? # === n_pages
+       alias result? n_pages? # === result?
+  
+  # ========================================================================= #
+  # === set_n_pages
+  #
+  # Since as of December 2021 this method will do a tiny bit of
+  # sanitizing the given input. 
+  # ========================================================================= #
+  def set_n_pages(i)
+    i = i.strip if i.is_a? String
+    i = i.to_i
+    @n_pages = i
+  end
+
+  # ========================================================================= #
+  # === determine_dataset
+  # ========================================================================= #
+  def determine_dataset(
+      of_this_pdf_file = @this_pdf_file
+    )
+    @dataset = File.binread(of_this_pdf_file)
+  end
+
+  # ========================================================================= #
+  # === this_pdf_file?
+  # ========================================================================= #
+  def this_pdf_file?
+    @this_pdf_file
+  end
+
+  # ========================================================================= #
+  # === set_this_pdf_file
+  # ========================================================================= #
+  def set_this_pdf_file(i)
+    @this_pdf_file = i
+  end
+
+  # ========================================================================= #
+  # === check_whether_qpdf_exists_and_if_not_then_exit
+  # ========================================================================= #
+  def check_whether_qpdf_exists_and_if_not_then_exit
+    does_qpdf_exist = false 
+    result = `qpdf 2>&1`
+    unless result.include? 'No such file or directory'
+      does_qpdf_exist = true
+    end
+    if does_qpdf_exist == false
+      opnn; e 'qpdf is not installed, can not continue.'
+      exit
+    end
+  end
+
+  # ========================================================================= #
+  # === ensure_that_hexapdf_exists
+  #
+  # This method will try to determine whether hexapdf exists on the
+  # given computer system or whether it does not.
+  # ========================================================================= #
+  def ensure_that_hexapdf_exists
+    result = `hexapdf --version 2>&1`
+    if result.include?('command not found')
+      false
+    else
+      true
+    end
+  end
+
+  # ========================================================================= #
+  # === determine_n_pages
+  # ========================================================================= #
+  def determine_n_pages(
+      use_this_program = @use_this_program_to_determine_how_many_pages_are_part_of_the_pdf_file
+    )
+    this_pdf_file = @this_pdf_file
+    _ = @dataset
+    if be_verbose?
+      opne 'Using `'+use_this_program.to_s+'` to determine how many '\
+           'pages are in the given .pdf file.'
+    end
+    case use_this_program
+    # ======================================================================= #
+    # === :hexapdf
+    # ======================================================================= #
+    when :hexapdf
+      if ensure_that_hexapdf_exists
+        result = `hexapdf info #{this_pdf_file}`
+        if result
+          use_this_regex = /Pages:(\s*)(\d{1,6})\s*$/ # See: https://rubular.com/r/QZ7JB6c0O22vta
+          result =~ use_this_regex
+          set_n_pages($2.to_s.dup.to_i)
+        end
+      else
+        opne 'hexapdf appears to not have been installed, or it could'
+        opne 'not be found.' 
+      end 
+    # ======================================================================= #
+    # === :qpdf
+    # ======================================================================= #
+    when :qpdf
+      check_whether_qpdf_exists_and_if_not_then_exit
+      result = `qpdf #{this_pdf_file} --show-npages`
+      set_n_pages(result)
+    # ======================================================================= #
+    # === :pdfinfo
+    # ======================================================================= #
+    when :pdfinfo
+      result = `pdfinfo #{this_pdf_file}`
+      determine_n_pages_via_pdfinfo(result)
+    else # else tag
+      # ===================================================================== #
+      # This here has the advantage (in theory) that we can just use
+      # a Regex and obtain the number of pages in the .pdf file. This
+      # works ok for many .pdf files, but not for all of them. This
+      # is also the reason why I switched to pdfinfo in March 2020 -
+      # it seems to be more reliable than the regex I am using.
+      # ===================================================================== #
+      scanned = _.scan(MATCH_AGAINST_THIS_REGEX)
+      # ===================================================================== #
+      # Note that the following may still return the wrong entry.
+      # I had this problem in March 2020.
+      # ===================================================================== #
+      max_value = scanned.map {|entry|
+        entry.first.to_i
+      }.max
+      set_n_pages(max_value)
+    end
+  end
+
+  # ========================================================================= #
+  # === determine_n_pages_via_pdfinfo
+  #
+  # We have to find an entry such as the following one:
+  #
+  #   Pages:          35
+  #
+  # ========================================================================= #
+  def determine_n_pages_via_pdfinfo(
+      i              = @this_pdf_file,
+      use_this_regex = Regexp.new(/Pages: (.+)/)
+    )
+    if i.include? 'Pages:'
+      i = i.scan(use_this_regex).flatten.first.strip
+    end
+    set_n_pages(i)
+  end
+
+  # ========================================================================= #
+  # === report_how_many_pages_were_found
+  # ========================================================================= #
+  def report_how_many_pages_were_found
+    if be_verbose?
+      e "#{rev}The pdf-file #{sfile(@this_pdf_file)} has exactly "\
+        "#{simp(n_pages?.to_s)} pages."
+    end
+  end
+
+  # ========================================================================= #
+  # === be_verbose?
+  # ========================================================================= #
+  def be_verbose?
+    @be_verbose
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    return_files_from_the_commandline_arguments.each {|this_pdf_file|
+      reset_the_internal_variables
+      set_this_pdf_file(this_pdf_file)
+      determine_dataset
+      determine_n_pages # Determine how many pages are in that .pdf file.
+      report_how_many_pages_were_found if be_verbose?
+    }
+  end
+
+  # ========================================================================= #
+  # === PdfFileNTotalPages.return_n_pages
+  #
+  # This method is silent by default.
+  # ========================================================================= #
+  def self.return_n_pages(
+      of_this_pdf_file,
+      &block
+    )
+    _ = PdfFileNTotalPages.new(of_this_pdf_file, &block)
+    _.run
+    return _.n_pages.to_i # Ought to return a number, as an integer.
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::PdfFileNTotalPages[]
+  # ========================================================================= #
+  def self.[](i)
+    new(i).result?
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.n_pdf_pages?
+#
+# This is the top-level method to find out how many pdf pages are
+# part of the given .pdf file at hand.
+#
+# The first argument to this method is simply the name of the .pdf file
+# or, rather, the path to it.
+#
+# Usage examples:
+#
+#   PdfParadise.n_pdf_pages?("/home/x/studium/UNI_WIEN/300260_Immunologie_und_zellul�re_Mikrobiologie_Teil_A/XIV-XVII_combined.pdf")
+#   PdfParadise.n_pdf_pages?("/Depot/j/hello-world.pdf")
+#
+# =========================================================================== #
+def self.n_pdf_pages?(of_this_pdf_file)
+  PdfFileNTotalPages.return_n_pages(of_this_pdf_file) { :be_quiet }.to_i
+end; self.instance_eval { alias n_pages?                      n_pdf_pages? } # === PdfParadise.n_pages?
+     self.instance_eval { alias n_pages                       n_pdf_pages? } # === PdfParadise.n_pages
+     self.instance_eval { alias n_pdf_pages                   n_pdf_pages? } # === PdfParadise.n_pdf_pages
+     self.instance_eval { alias n_pages_in_this_pdf_file?     n_pdf_pages? } # === PdfParadise.n_pages_in_this_pdf_file?
+     self.instance_eval { alias n_pages_in_this_pdf_file      n_pdf_pages? } # === PdfParadise.n_pages_in_this_pdf_file
+     self.instance_eval { alias has_n_pages?                  n_pdf_pages? } # === PdfParadise.has_n_pages?
+     self.instance_eval { alias n_pdf_pages_in_this_pdf_file  n_pdf_pages? } # === PdfParadise.n_pdf_pages_in_this_pdf_file
+     self.instance_eval { alias n_pdf_pages_in_this_pdf_file? n_pdf_pages? } # === PdfParadise.n_pdf_pages_in_this_pdf_file?
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::PdfFileNTotalPages.new(ARGV)
+end # n_pages $UNI_WIEN/300609_Molekulare_Entwicklungsbiologie/Entwicklungsbiologie7.pdf