pdf_paradise 0.3.20

data/lib/pdf_paradise/utility_scripts/delete_the_first_page_of_this_pdf_file/delete_the_first_page_of_this_pdf_file.rb

@@ -0,0 +1,429 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === PdfParadise::DeleteTheFirstPageOfThisPdfFile
+#
+# This class can be used to delete the first page of a .pdf file.
+#
+# The user can pass one (or several) .pdf files to this class, and this
+# class will then proceed to try to remove the very first .pdf page,
+# in that given .pdf file. So, for instance, if the pdf-file at hand
+# has 100 pages, the new .pdf file should have 99 pages, and the first
+# page will be gone. That is the primary rationale this class follows.
+#
+# By default, the class will overwrite the original file; this behaviour
+# depends on the constant SHALL_WE_OVERWRITE_THE_ORIGINAL_PDF_FILE and
+# the user can toggle this to false, to NOT overwrite the original file.
+#
+# Note that the functionality made available through this class here
+# depends on external tools, such as the binary called "qpdf" or the 
+# binary called "pdftk" or "hexapdf".
+#
+# Since as of July 2023 the class will also log its action, by storing
+# the path to the last .pdf file that was modified.
+#
+# Usage example:
+#
+#   PdfParadise::DeleteTheFirstPageOfThisPdfFile.new(ARGV)
+#
+# =========================================================================== #
+# require 'pdf_paradise/utility_scripts/delete_the_first_page_of_this_pdf_file/delete_the_first_page_of_this_pdf_file.rb'
+# PdfParadise.delete_the_first_page_of_this_pdf_file('foobar.pdf')
+# PdfParadise::DeleteTheFirstPageOfThisPdfFile.new(ARGV)
+# =========================================================================== #
+require 'pdf_paradise/base/base.rb'
+
+module PdfParadise
+
+class DeleteTheFirstPageOfThisPdfFile < Base # === PdfParadise::DeleteTheFirstPageOfThisPdfFile
+
+  require 'pdf_paradise/utility_scripts/pdf_file_n_total_pages.rb'
+
+  # ========================================================================= #
+  # === SHALL_WE_OVERWRITE_THE_ORIGINAL_PDF_FILE
+  #
+  # Set this constant to false if you do not want to overwrite the
+  # original .pdf file.
+  # ========================================================================= #
+  SHALL_WE_OVERWRITE_THE_ORIGINAL_PDF_FILE = true
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      commandline_arguments = nil,
+      run_already           = true,
+      &block
+    )
+    reset
+    case commandline_arguments
+    # ======================================================================= #
+    # === :do_not_run_yet
+    # ======================================================================= #
+    when :do_not_run_yet
+      commandline_arguments = []
+      run_already = false
+    end
+    set_commandline_arguments(
+      commandline_arguments
+    )
+    # ======================================================================= #
+    # === Handle blocks next
+    # ======================================================================= #
+    if block_given?
+      yielded = yield
+      case yielded
+      # ===================================================================== #
+      # === :be_quiet
+      # ===================================================================== #
+      when :be_quiet
+        set_be_quiet
+      end
+    end
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    infer_the_namespace
+    reset_the_internal_hash
+    # ======================================================================= #
+    # === :work_on_these_files
+    # ======================================================================= #
+    @internal_hash[:work_on_these_files] = []
+    # ======================================================================= #
+    # === :array_backup_files
+    #
+    # We also keep track of backup fiels next.
+    # ======================================================================= #
+    @internal_hash[:array_backup_files] = []
+    # ======================================================================= #
+    # === :use_this_pdf_application
+    #
+    # The following variable may have any of the following values:
+    #
+    #   :hexapdf
+    #   :pdftk
+    #   :qpdf
+    #
+    # It specifies which application can be used for deleting .pdf pages.
+    # ======================================================================= #
+    @internal_hash[:use_this_pdf_application] = :hexapdf # :qpdf # :hexapdf # :pdftk
+    # ======================================================================= #
+    # === :original_pwd
+    #
+    # Keep track of the original working directory.
+    # ======================================================================= #
+    @internal_hash[:original_pwd] = return_pwd
+    # ======================================================================= #
+    # === :shall_we_overwrite_the_original_pdf_file
+    # ======================================================================= #
+    @internal_hash[:shall_we_overwrite_the_original_pdf_file] =
+      SHALL_WE_OVERWRITE_THE_ORIGINAL_PDF_FILE
+  end
+
+  # ========================================================================= #
+  # === use_this_pdf_application?
+  # ========================================================================= #
+  def use_this_pdf_application?
+    @internal_hash[:use_this_pdf_application]
+  end
+
+  # ========================================================================= #
+  # === use_pdftk?
+  # ========================================================================= #
+  def use_pdftk?
+    use_this_pdf_application? == :pdftk
+  end
+
+  # ========================================================================= #
+  # === array_backup_files?
+  # ========================================================================= #
+  def array_backup_files?
+    @internal_hash[:array_backup_files]
+  end; alias backups? array_backup_files? # === backups?
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    determine_the_input_files
+    _ = work_on_these_files?
+    if _.empty?
+      opne 'No .pdf file was assigned to this class.'
+    else
+      do_work_on_these_pdf_files(_)
+    end
+  end
+
+  # ========================================================================= #
+  # === determine_the_input_files
+  #
+  # This method will specifically select for all .pdf files.
+  # ========================================================================= #
+  def determine_the_input_files(
+      commandline_arguments = commandline_arguments?
+    )
+    # ======================================================================= #
+    # Next, if i is empty, and we are on Roebe, we will use the default
+    # book, if a certain ENV variable exists AND if the file that points
+    # to that location also exists.
+    # ======================================================================= #
+    if commandline_arguments.empty? and is_on_roebe?
+      if ENV.has_key?('MAIN_BOOK') and
+        File.exist?(ENV['MAIN_BOOK'])
+        this_file = ENV['MAIN_BOOK'].dup
+        e "#{rev}As we are on roebe, we will use this file:"
+        e
+        e sfile("  #{this_file}")
+        e
+        commandline_arguments << this_file
+      end
+    end
+    commandline_arguments.map! {|entry|
+      entry = entry.to_s unless entry.is_a?(String)
+      entry = Dir[entry] if entry.include? '*'
+      entry
+    }
+    commandline_arguments.flatten!
+    _ = commandline_arguments.select {|entry|
+      entry.end_with?('.pdf') and File.file?(entry) 
+    }
+    _.map! {|entry| File.absolute_path(entry) } if _ and !_.empty?
+    @internal_hash[:work_on_these_files] = _
+  end
+
+  # ========================================================================= #
+  # === create_a_backup_file
+  # ========================================================================= #
+  def create_a_backup_file(
+      entry,
+      temp_dir = temp_dir?
+    )
+    e "#{rev}First, #{steelblue('a backup file will be created')}#{rev}."
+    # ======================================================================= #
+    # Next ensure that the temp-dir exists.
+    # ======================================================================= #
+    try_to_ensure_that_this_directory_exists(temp_dir)
+    target = temp_dir+File.basename(entry)
+    if File.exist? target # Delete the old .pdf copy here.
+      delete_file(target)
+    end
+    copy_file(entry, target)
+    if File.exist? target
+      e "#{rev}A backup-file (a copy) now exists at `#{sfile(target)}#{rev}`."
+      @internal_hash[:array_backup_files] << File.absolute_path(target)
+    end
+  end
+
+  # ========================================================================= #
+  # === work_on_these_files?
+  # ========================================================================= #
+  def work_on_these_files?
+    @internal_hash[:work_on_these_files]
+  end; alias input?       work_on_these_files? # === input?
+       alias input_files? work_on_these_files? # === input_files?
+
+  # ========================================================================= #
+  # === do_work_on_these_pdf_files                                 (main tag)
+  #
+  # This is the method that will delete the first page of a given .pdf
+  # file.
+  # ========================================================================= #
+  def do_work_on_these_pdf_files(
+      i        = work_on_these_files?,
+      temp_dir = temp_dir?
+    )
+    i.each {|entry|
+      opnn { :no_trailing }
+      e; e
+      e "#{rev}Working on the file #{sfile(entry)} #{rev}next."
+      create_a_backup_file(entry)
+      backup_copy = backups?.last # Refer to the last entry there.
+      n_pages = PdfParadise.n_pages?(backup_copy)
+      e "#{rev}Now that a backup file has been created, it is time to "\
+        "work on that backup"
+      e "#{rev}copy. The .pdf currently has #{steelblue(n_pages)} #{rev}pages."
+      # ===================================================================== #
+      # Always cd into the target directory next - we have to remember
+      # the original working directory, though, so that we cd back
+      # into it:
+      # ===================================================================== #
+      if temp_dir and File.directory?(temp_dir)
+        @internal_hash[:original_pwd] = temp_dir
+        cd(temp_dir)
+      end
+      new_path = do_delete_the_first_page_of_this_pdf_file(backup_copy)
+      n_pages = PdfParadise.n_pages?(new_path)
+      e "#{rev}The .pdf file now has #{steelblue(n_pages)} #{rev}pages."
+      e 'It can be found at '+sfile(new_path)+'.' if File.exist?(new_path)
+      # ===================================================================== #
+      # === Keeping track of changes via a log-file
+      #
+      # Sine as of July 2023 we will also log into a .yml file. We will
+      # store the original .pdf file, though, as the modified .pdf
+      # file tends to be volatile.
+      # ===================================================================== #
+      if File.exist?(entry)
+        store_this_pdf_file_in_the_log_file(entry) # See the explanation above.
+      end
+      if @internal_hash[:shall_we_overwrite_the_original_pdf_file] and
+         File.exist?(new_path)
+        e "#{rev}The variable #{gold(':shall_we_overwrite_the_original_pdf_file')}"\
+          " #{rev}was set to"
+        e "#{rev}true, so the file at"
+        e "#{sfile(entry)}#{rev} will be overwritten now."
+        # =================================================================== #
+        # In this case we will overwrite the original .pdf file. The
+        # following call to mv() does this.
+        # =================================================================== #
+        delete_file(entry) if File.exist?(new_path)
+        mv(
+          new_path,
+          entry
+        )
+      end
+    }
+    cd(@internal_hash[:original_pwd]) # And go back to the initial working directory again.
+  end; alias process_each_pdf do_work_on_these_pdf_files # === process_each_pdf
+
+  # ========================================================================= #
+  # === shall_we_overwrite_the_original_pdf_file?
+  # ========================================================================= #
+  def shall_we_overwrite_the_original_pdf_file?
+    @internal_hash[:shall_we_overwrite_the_original_pdf_file]
+  end
+
+  # ========================================================================= #
+  # === store_this_pdf_file_in_the_log_file
+  # ========================================================================= #
+  def store_this_pdf_file_in_the_log_file(i)
+    PdfParadise.set_use_this_file(i)
+    what = YAML.dump(i)
+    # ======================================================================= #
+    # Find out the full, absolute path to the .yml file next:
+    # ======================================================================= #
+    into = File.absolute_path("#{log_directory?}last_modified_pdf_file.yml")
+    e "#{rev}Logging information into the file `#{sfile(into)}#{rev}`."
+    write_what_into(what, into)
+  end
+
+  # ========================================================================= #
+  # === use_hexapdf?
+  # ========================================================================= #
+  def use_hexapdf?
+    use_this_pdf_application? == :hexapdf
+  end
+
+  # ========================================================================= #
+  # === name_of_the_output_file?
+  #
+  # This method will determine the output file of the .pdf file.
+  # ========================================================================= #
+  def name_of_the_output_file?(i)
+    i.delete_suffix('.pdf')+'_output_file.pdf'
+  end; alias output? name_of_the_output_file? # === output?
+
+  # ========================================================================= #
+  # === do_delete_the_first_page_of_this_pdf_file
+  # ========================================================================= #
+  def do_delete_the_first_page_of_this_pdf_file(
+      i,
+      use_this_pdf_application = @internal_hash[:use_this_pdf_application],
+      be_verbose               = be_verbose?
+    )
+    use_this_pdf_application = use_this_pdf_application.to_s
+    # ======================================================================= #
+    # Determine the name of the (new) output file next:
+    # ======================================================================= #
+    name_of_the_output_file = name_of_the_output_file?(i)
+    if File.exist?(name_of_the_output_file) # Delete the output file first.
+      delete_file(name_of_the_output_file)
+    end
+    if i.include? ' '
+      i = '"'+i+'"'
+    end
+    # ======================================================================= #
+    # Store how many pages this .pdf file has.
+    # ======================================================================= #
+    has_n_pages = PdfParadise.n_pages_in_this_pdf_file?(i)
+    _ = ''.dup
+    _ << use_this_pdf_application
+    case _
+    # ======================================================================= #
+    # === Support for pdftk
+    # ======================================================================= #
+    when /pdftk/
+      _ << ' '+i+' cat 2-'+(has_n_pages.to_i).to_s+' '+
+           has_n_pages.to_s+'-end output '+
+           name_of_the_output_file
+    # ======================================================================= #
+    # === Support for hexapdf
+    # ======================================================================= #
+    when /hexapdf/
+      _ << ' modify '+i+' -i 2-e '+name_of_the_output_file
+    # ======================================================================= #
+    # === Support for qpdf
+    # ======================================================================= #
+    when /qpdf/
+      _ << ' '+'--pages '+i+' 2-'+(has_n_pages.to_i).to_s+' -- '+
+           i+' '+
+           name_of_the_output_file
+    else
+      e 'Unknown pdf handler: '+steelblue(_)
+      e 'Exiting.'
+      exit
+    end
+    e "Deleting the first page of this .pdf file next: "\
+      "#{sfile(i)}" if be_verbose
+    # ======================================================================= #
+    # Next, do the actual work as-such, via esystem() and a bit of padding:
+    # ======================================================================= #
+    e; e "  #{_}"; system(_); e
+    return name_of_the_output_file
+  end
+
+  # ========================================================================= #
+  # === PdfParadise::DeleteTheFirstPageOfThisPdfFile[]
+  # ========================================================================= #
+  def self.[](i = ARGV)
+    new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === PdfParadise.use_which_pdf_application_for_deleting_the_first_page_of_a_pdf_file?
+#
+# Usage example:
+#
+#   PdfParadise.use_which_pdf_application_for_deleting_the_first_page_of_a_pdf_file? # => :hexapdf
+#
+# =========================================================================== #
+def self.use_which_pdf_application_for_deleting_the_first_page_of_a_pdf_file?
+  _ = PdfParadise::DeleteTheFirstPageOfThisPdfFile.new(:do_not_run_yet)
+  return _.use_this_pdf_application?
+end
+
+# =========================================================================== #
+# === PdfParadise.delete_first_page_of_this_pdf_file
+#
+# Easier method-way to invoke the above class.
+# =========================================================================== #
+def self.delete_first_page_of_this_pdf_file(
+    i = ARGV, &block
+  )
+  PdfParadise::DeleteTheFirstPageOfThisPdfFile.new(i, &block)
+end; self.instance_eval { alias remove_the_first_page_of_this_pdf_file delete_first_page_of_this_pdf_file } # === PdfParadise.remove_the_first_page_of_this_pdf_file
+     self.instance_eval { alias remove_first_page_of_this_pdf_file     delete_first_page_of_this_pdf_file } # === PdfParadise.remove_first_page_of_this_pdf_file
+     self.instance_eval { alias delete_the_first_page_of_this_pdf_file delete_first_page_of_this_pdf_file } # === PdfParadise.delete_the_first_page_of_this_pdf_file
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  PdfParadise::DeleteTheFirstPageOfThisPdfFile.new(ARGV)
+end # deletethefirstpageofthispdffile