Small utility to find the relevant field in a PDF form Usage find_pdf_field myfile.pdf searchstring

find_pdf_field

#!/bin/ruby 

# Usage: ruby find_pdf_field myfile.pdf searchstring


require 'pdf_forms'
require 'pp'

pdftk = PdfForms.new("/usr/local/bin/pdftk")
pdf = ARGV[0]
fields =  pdftk.get_fields  pdf
search_string = ARGV[1]
matched_fields = []

def hit(object_to_search,string_to_search_for)
  string_to_search_for = string_to_search_for.downcase
  if (object_to_search.class == "Hash")
    search_results = object_to_search.select do  |key, val|
      val.downcase.include?(string_to_search_for) || key.downcase.include?(string_to_search_for)
    end
    return true if search_results.any
  elsif (object_to_search.class == "Array")
    return true if object_to_search.any? { |s| s.downcase.include?(string_to_search_for) }
  else
    return true if object_to_search.to_s.downcase.include?(string_to_search_for)
  end
  return false
end

def hit_in_object(obj,string_to_search_for)
  obj.instance_variables.each do |m|
    return true if hit(obj.instance_variable_get(m),string_to_search_for)
  end
  return false
end

#find hits
fields.each do |f|
  matched_fields << f if hit_in_object(f,search_string)
end

# outputs results
puts "There are #{matched_fields.length} matches"

matched_fields.each do |field|
  puts field.inspect
end
~