pdf_paradise 0.1.43

data/lib/pdf_paradise/pdf_file_n_total_pages.rb

@@ -0,0 +1,227 @@
+#!/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/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+)/
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    set_commandline_arguments(i)
+    case run_already
+    when :be_silent
+      @be_verbose = false
+      run_already = false
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @n_pages
+    #
+    # This variable will keep track as to how many pages the given .pdf
+    # page has.
+    # ======================================================================= #
+    @n_pages    = 0
+    # ======================================================================= #
+    # === @be_verbose
+    # ======================================================================= #
+    @be_verbose = true
+    # ======================================================================= #
+    # === @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 = :pdfinfo 
+  end
+
+  # ========================================================================= #
+  # === n_pages
+  # ========================================================================= #
+  def n_pages?
+    @n_pages
+  end; alias n_pages n_pages? # === n_pages
+       alias result? n_pages? # === result?
+  
+  # ========================================================================= #
+  # === set_n_pages
+  # ========================================================================= #
+  def set_n_pages(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
+
+  # ========================================================================= #
+  # === be_verbose?
+  # ========================================================================= #
+  def be_verbose?
+    @be_verbose
+  end
+
+  # ========================================================================= #
+  # === report_how_many_pages_were_found
+  # ========================================================================= #
+  def report_how_many_pages_were_found
+    e "#{rev}The pdf-file #{sfile(@this_pdf_file)} has exactly "\
+      "#{simp(n_pages?.to_s)} pages."
+  end
+
+  # ========================================================================= #
+  # === set_this_pdf_file
+  # ========================================================================= #
+  def set_this_pdf_file(i)
+    @this_pdf_file = i
+  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
+    )
+    if i.include? 'Pages:'
+      i = i.scan(/Pages: (.+)/).flatten.first.strip
+    end
+    set_n_pages(i)
+  end
+
+  # ========================================================================= #
+  # === determine_n_pages
+  # ========================================================================= #
+  def determine_n_pages
+    _ = @dataset
+    case @use_this_program_to_determine_how_many_pages_are_part_of_the_pdf_file
+    # ======================================================================= #
+    # === :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
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    return_files_from_the_commandline_arguments.each {|this_pdf_file|
+      reset
+      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)
+    _ = PdfFileNTotalPages.new(of_this_pdf_file, :be_silent)
+    _.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 example:
+#
+#   PdfParadise.n_pdf_pages?("/home/x/STUDIUM/UNI_WIEN/300260_Immunologie_und_zellul�re_Mikrobiologie_Teil_A/XIV-XVII_combined.pdf")
+#
+# =========================================================================== #
+def self.n_pdf_pages?(of_this_pdf_file)
+  PdfFileNTotalPages.return_n_pages(of_this_pdf_file).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?
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::PdfFileNTotalPages.new(ARGV)
+end # n_pages $UNI_WIEN/300609_Molekulare_Entwicklungsbiologie/Entwicklungsbiologie7.pdf

data/lib/pdf_paradise/project/project_base_directory.rb

@@ -0,0 +1,22 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# require 'pdf_paradise/project/project_base_directory.rb'
+# =========================================================================== #
+module PdfParadise
+
+  # ========================================================================= #
+  # === PdfParadise::PROJECT_BASE_DIRECTORY
+  # ========================================================================= #
+  PROJECT_BASE_DIRECTORY =
+    File.absolute_path("#{__dir__}/..")+'/'
+
+  # ========================================================================= #
+  # === PdfParadise.project_base_dir?
+  # ========================================================================= #
+  def self.project_base_dir?
+    PROJECT_BASE_DIRECTORY
+  end
+
+end

data/lib/pdf_paradise/remove_pdf_password.rb

@@ -0,0 +1,392 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: false
+# =========================================================================== #
+# === PdfParadise::RemovePdfPassword
+#
+# Use this class to remove a password from a .pdf file.
+#
+# We can either use "qpdf" or "pdftk".
+#
+# We could also fetch the password from ENV['PASSWORD'].
+#
+# Usage example:
+#
+#   PdfParadise::RemovePdfPassword.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/remove_pdf_password.rb'
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class RemovePdfPassword < ::PdfParadise::Base # === PdfParadise::RemovePdfPassword
+
+  include SaveFile
+  include FileUtils::Verbose
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === PASSWORD
+  #
+  # The password in use can be hardcoded here.
+  # ========================================================================= #
+  PASSWORD = 'Quellbrunn' # AGLMT15'
+
+  # ========================================================================= #
+  # === ARRAY_ALLOWED_PASSWORD_FILES
+  #
+  # A directory may include a PASSWORD.md file. In this case, we will use
+  # that particular file as the new password.
+  # ========================================================================= #
+  ARRAY_ALLOWED_PASSWORD_FILES = %w(
+    PASSWORD.md
+    PASSWORT.md
+  )
+
+  # ========================================================================= #
+  # === REGEX_FOR_PASSWORD
+  # ========================================================================= #
+  REGEX_FOR_PASSWORD = /--password(=| )(.+) ?/
+
+  # ========================================================================= #
+  # === AUTOMATICALLY_REPLACE
+  #
+  # If this constant is set to true then we will automatically
+  # replace the old, existing .pdf file with the newly generated
+  # file.
+  # ========================================================================= #
+  AUTOMATICALLY_REPLACE = false
+
+  # ========================================================================= #
+  # === COMMAND_NOT_FOUND
+  # ========================================================================= #
+  COMMAND_NOT_FOUND = "command not found\n"
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    set_input(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    set_password # Reset it here.
+    @output_file = nil
+    # ======================================================================= #
+    # === @automatically_replace
+    # ======================================================================= #
+    @automatically_replace = AUTOMATICALLY_REPLACE
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input
+  end
+
+  # ========================================================================= #
+  # === run_sys_command
+  # ========================================================================= #
+  def run_sys_command(i = string?)
+    esystem i
+  end
+
+  # ========================================================================= #
+  # === string?
+  # ========================================================================= #
+  def string?
+    @string
+  end
+
+  # ========================================================================= #
+  # === set_password
+  # ========================================================================= #
+  def set_password(i = PASSWORD)
+    @password = i
+  end
+
+  # ========================================================================= #
+  # === mv
+  # ========================================================================= #
+  def mv(old, new)
+    new = new.strip # We don't want any newlines.
+    if File.exist? old
+      opnn; e "Now replacing `#{sfancy(old)}` with `#{simp(new)}`."
+      FileUtils.mv(old, new)
+    else
+      opnn; e "No file exists at `#{sfile(old)}`, thus can not rename/replace."
+    end
+  end
+
+  # ========================================================================= #
+  # === password?
+  # ========================================================================= #
+  def password?
+    @password
+  end
+
+  # ========================================================================= #
+  # === tell_the_user_that_we_will_remove_the_password_next
+  # ========================================================================= #
+  def tell_the_user_that_we_will_remove_the_password_next(this_file = input?)
+    opnn; e 'Now removing the password ('+orange(password?.to_s)+') '\
+            'from the file `'+sfile(this_file)+'`.'
+  end
+
+  # ========================================================================= #
+  # === check_commandline                                          (menu tag)
+  #
+  # Pass the commandline arguments through this method.
+  # ========================================================================= #
+  def check_commandline(i)
+    if i.is_a? Array
+      i.each {|entry|
+        check_commandline(entry)
+      }
+    else
+      case i.to_s # case tag
+      # ===================================================================== #
+      # === remove_password --batch
+      # ===================================================================== #
+      when /-?-?batch/
+        @input = Dir['*.pdf']
+      # ===================================================================== #
+      # === remove_password --password?
+      # ===================================================================== #
+      when '--password?',
+           'password?',
+           'password'
+        e password?
+        exit
+      # ===================================================================== #
+      # === remove_password --help
+      # ===================================================================== #
+      when 'HELP',
+           '--help',
+           'help'
+        show_help
+        exit
+      else
+        if i.include? '--'
+          if i.include?('--password ') or i.include?('--password')
+            i =~ REGEX_FOR_PASSWORD # See here for the test: http://rubular.com/r/P6LScCOVYZ
+            set_password($2.to_s.dup) # The second capture group holds our result.
+            i.gsub!(REGEX_FOR_PASSWORD, '')
+          end
+        end unless i.is_a? Symbol
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === show_help                                                  (help tag)
+  #
+  # Show some instructions in how to use this class.
+  #
+  # Invocation example:
+  #
+  #   nopassword --help
+  #
+  # ========================================================================= #
+  def show_help
+    e
+    e 'You can set a different password via:'
+    e
+    e sfancy('  --password NEW_PASSWORD_HERE')
+    e
+    e 'nopdf *.pdf --password '+password?
+    e
+    e 'If you want to batch-process all .pdf files in the '\
+      'current directory,'
+    e 'and subsequently remove all password-protection '\
+      'from these files, do:'
+    e
+    e sfancy('  --batch')
+    e
+  end
+
+  # ========================================================================= #
+  # === remove_password_through_qpdf
+  #
+  # Here we make use of qpdf.
+  # ========================================================================= #
+  def remove_password_through_qpdf(
+      work_on_this_file = input?
+    )
+    if qpdf_exists?
+      set_output_file(work_on_this_file)
+      @string = 'qpdf --password='+password?+' --decrypt '+
+                 work_on_this_file+' '+output_file?
+    else
+      e 'qpdf does not exist. Please install it. Exiting now.'
+      exit
+    end
+  end
+
+  # ========================================================================= #
+  # === set_output_file
+  # ========================================================================= #
+  def set_output_file(i)
+    i = file_name_without_extension?(i)
+    i = "no_password_#{i}.pdf"
+    @output_file = i
+  end
+
+  # ========================================================================= #
+  # === file_name_without_extension?
+  # ========================================================================= #
+  def file_name_without_extension?(i = input?)
+    i.strip.sub(/\.pdf$/,'') # Chop off trailing extension name.
+  end
+
+  # ========================================================================= #
+  # === output_file?
+  # ========================================================================= #
+  def output_file?
+    @output_file
+  end; alias output? output_file? # === output?
+
+  # ========================================================================= #
+  # === opnn
+  # ========================================================================= #
+  def opnn
+    super(NAMESPACE)
+  end
+
+  # ========================================================================= #
+  # === qpdf_exists?
+  #
+  # Query method to try to find out whether qpdf is installed.
+  # ========================================================================= #
+  def qpdf_exists?
+    result = `qpdf 2>&1`
+    ! result.include?(COMMAND_NOT_FOUND)
+  end
+
+  # ========================================================================= #
+  # === remove_password_through_pdftk
+  # ========================================================================= #
+  def remove_password_through_pdftk(this_file)
+    # ======================================================================= #
+    # Decrypt a PDF called input.pdf with YOURPASSWORD-HERE password
+    # and create unencrypted output.pdf, enter:
+    # ======================================================================= #
+    @string = 'pdftk '+this_file+' output no_password_output.pdf user_pw '+password?
+  end
+
+  # ========================================================================= #
+  # === consider_replacing_the_old_file
+  # ========================================================================= #
+  def consider_replacing_the_old_file(
+      old_file    = input?,
+      output_file = @output_file
+    )
+    if @automatically_replace
+      opnn; e 'The constant '+swarn('AUTOMATICALLY_REPLACE')+' is set to true.'
+      opnn; e 'This means that we will automatically try to replace '\
+              'the old .pdf with the new .pdf'
+      mv(output_file, old_file)
+    end
+  end
+
+  # ========================================================================= #
+  # === set_input
+  #
+  # Since as of Jul 2016, the input given to this class must always
+  # be ketp as an Array.
+  # ========================================================================= #
+  def set_input(
+      i = '', do_check_the_commandline = true
+    )
+    case do_check_the_commandline
+    when :do_not_check_the_commandline
+      do_check_the_commandline = false
+    end
+    # ======================================================================= #
+    # Next we will have special symbol-instructions here, in
+    # particular :all_pdf_files
+    # ======================================================================= #
+    if i.is_a? Symbol
+      case i
+      when :all_pdf_files
+        i = Dir['*.pdf']
+      end
+    end
+    if i.is_a? Array
+      i.flatten!
+    else
+      i = [i]
+    end
+    @input = i # This is guaranteed to be an Array.
+    check_commandline(i) if do_check_the_commandline
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    check_for_a_password_file_in_the_current_directory
+    # ======================================================================= #
+    # Iterate over the given input-files.
+    # ======================================================================= #
+    input?.each {|file|
+      remove_password_through_qpdf(file)
+      # remove_password_through_pdftk(file) # Pick this, or the other one.
+      tell_the_user_that_we_will_remove_the_password_next(file)
+      run_sys_command
+      consider_replacing_the_old_file(file)
+    }
+  end
+
+  # ========================================================================= #
+  # === check_for_a_password_file_in_the_current_directory     (password tag)
+  #
+  # We can check for several password files.
+  # ========================================================================= #
+  def check_for_a_password_file_in_the_current_directory
+    _ = ARRAY_ALLOWED_PASSWORD_FILES
+    does_any_file_exist = _.select {|entry|
+      File.exist?(entry)
+    }
+    does_a_password_file_exist = !does_any_file_exist.empty?
+    if does_a_password_file_exist
+      this_selection = does_any_file_exist.first
+      opnn; e 'A file called `'+sfile(this_selection)+'` was found in the current directory.'
+      if File.zero? this_selection # Check whether it is empty.
+        opnn; e 'As it is, however had, empty, we will not change the '\
+                "password to the file's content."
+      else
+        # =================================================================== #
+        # Read in the new password from the existing file.
+        # =================================================================== #
+        use_this_dataset = File.readlines(this_selection).map(&:chomp)
+        set_password(
+          use_this_dataset.first # <- We will only honour the first line of this file.
+        )
+        opnn; e 'We will use the content of this file as the new password '\
+                '(Password thus being: '+orange(password?)+').'
+      end 
+    end
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::RemovePdfPassword.new(ARGV)
+end # no_password