pdfh 0.2.1 → 3.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a3761420b1befc7788493ed341094bffcf3b6f86bc2f6685f7b4de0a8201752b
-  data.tar.gz: 9da09a68dff012c3e22e67581c73b1bf874ed3abd0f9d58be8c760fa37ca6561
+  metadata.gz: e56c6dcb8915785a475e34a5120d44556fd6630d3738849161697b76ded58fa6
+  data.tar.gz: 335b684595f23f61607d3ff3e0c6ed106da1e52842090c4ddc89381252f5771a
 SHA512:
-  metadata.gz: 5a9ba91f43fcb3e96469bf1d4499ab9e857211553bebe4732e0d3d287e4fe7946fe635b7f6e345576d69da6b07573acce2794619098d62ae40309c7f3d170f2d
-  data.tar.gz: 80a52f67d7c47159918b5cff641f5744022d1400bf71ac9fe6247814a0369e0a2ec8e2915b791a5e85e1107a28d9c64777471aa1ec448aa1ad093ecf83805287
+  metadata.gz: 45bbfee057aeda92595c687b67a3e2f34c8ed4f36f28dbc5b3880fafb05f7a9e170b70e1ec61bc21709ba7ed3a1401667fca03cadf35593fb8843b93ee7fdfdb
+  data.tar.gz: 930644f381d3e338ec3161d8346179f3268c336bf3407ae64ed256eb9c30b0bd2b0d0bcf6c0ab31c2d0a57a25d56f05fd0f99bf89f7978be77a0d78f985da101

data/.rspec

@@ -1,3 +1,3 @@
---format documentation
+--format progress
 --color
 --require spec_helper

data/.rubocop.yml

@@ -7,7 +7,7 @@ require:
 
 AllCops:
   NewCops: enable
-  TargetRubyVersion: 2.5
+  TargetRubyVersion: 3.0
   Exclude:
     - doc/**/*
     - pkg/**/*
@@ -16,7 +16,7 @@ AllCops:
 
 Layout/LineLength:
   Max: 120
-  IgnoredPatterns: ['^\s*#']
+  AllowedPatterns: ['^\s*#']
 
 Style/StringLiterals:
   Enabled: true

data/.rubocop_todo.yml

@@ -1,36 +1,31 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2021-05-15 01:26:47 UTC using RuboCop version 1.14.0.
+# on 2023-07-13 05:43:39 UTC using RuboCop version 1.54.1.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 5
-# Configuration parameters: IgnoredMethods, CountRepeatedAttributes.
+# Offense count: 7
+# Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes.
 Metrics/AbcSize:
-  Max: 24
-
-# Offense count: 6
-# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
-# IgnoredMethods: refine
-Metrics/BlockLength:
-  Max: 87
+  Max: 25
 
 # Offense count: 1
-# Configuration parameters: CountComments, CountAsOne.
-Metrics/ClassLength:
-  Max: 121
+# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns, inherit_mode.
+# AllowedMethods: refine
+Metrics/BlockLength:
+  Max: 26
 
 # Offense count: 6
-# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
+# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 17
 
 # Offense count: 2
 RSpec/AnyInstance:
   Exclude:
-    - 'spec/pdfh/document_processor_spec.rb'
+    - 'spec/pdfh/main_spec.rb'
 
 # Offense count: 1
 # Configuration parameters: CountAsOne.
@@ -41,7 +36,20 @@ RSpec/ExampleLength:
 RSpec/MultipleExpectations:
   Max: 2
 
+# Offense count: 1
+# Configuration parameters: AllowedPatterns.
+# AllowedPatterns: ^expect_, ^assert_
+RSpec/NoExpectationExample:
+  Exclude:
+    - 'spec/pdfh/pdf_handler_spec.rb'
+
 # Offense count: 1
 RSpec/SubjectStub:
   Exclude:
-    - 'spec/pdfh/document_processor_spec.rb'
+    - 'spec/pdfh/main_spec.rb'
+
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+Style/RedundantStringEscape:
+  Exclude:
+    - 'lib/pdfh/settings_template.rb'

data/.tool-versions

@@ -0,0 +1 @@
+ruby 3.3.0

data/CHANGELOG.md

@@ -1,26 +1,31 @@
+## v3.0.0
+  * Migrate to `asdf` from `rvm`
+  * Upgrade old gems
+  * Bump to v3 (as this is project's third iteration)
+
 ## v0.2.0
-* Major gem refactoring
-* Changed setting `base_path` to `destination_base_path`
-* Add DocumentType listing option on executable file
-* Add process individual documents providing type and files
-  ```bash
-  pdfh -t document_type_id path/to_files.pdf
-  ```
-* Add settings.yml template in order to create a sample file
+  * Major gem refactoring
+  * Change setting `base_path` to `destination_base_path`
+  * Add DocumentType listing option on executable file
+  * Add process individual documents providing type and files
+    ```bash
+    pdfh -t document_type_id path/to_files.pdf
+    ```
+  * Add `settings.yml` template in order to create a sample file
 
 ## v0.1.9
-* Add dependencies validation at run
+  * Add dependencies validation at run
 
 ## v0.1.5
-* Add print_cmd field in config file for information purposes
-* Settings now validates a no existing directory
-* Refactor for easier maintenance
+  * Add `print_cmd` field in config file for information purposes
+  * Settings now validates an unexisting directory
+  * Refactor for easier maintenance
 
 ## v0.1.4
-* Add titleize format when writing new file
+  * Add titleize format when writing new file
 
 ## v0.1.3
-* Fixed copy companion files, which was not copying the files.
+  * Fixed copy companion files, which was not copying the files.
 
 ## v0.1.2
-* Initial Release
+  * Initial Release

data/Gemfile

@@ -7,14 +7,15 @@ gemspec
 
 gem "bundler", "~> 2.0"
 gem "code-scanning-rubocop", "~> 0.5"
+gem "factory_bot", "~> 6.2"
 gem "pry", "~> 0.14"
 gem "rake", "~> 13.0"
-gem "rspec", "~> 3.9"
+gem "rspec", "~> 3.12"
 gem "rspec_junit_formatter", "~> 0.4"
-gem "rubocop", "~> 1.0"
-gem "rubocop-performance", "~> 1.9"
+gem "rubocop", "~> 1.50"
+gem "rubocop-performance", "~> 1.18"
 gem "rubocop-rake", "~> 0.5"
 gem "rubocop-rspec", "~> 2.2"
-gem "simplecov", "~> 0.21"
+gem "simplecov", "~> 0.22"
 gem "simplecov-console", "~> 0.9"
 gem "versionomy", "~> 0.5"

data/Gemfile.lock

@@ -1,67 +1,102 @@
 PATH
   remote: .
   specs:
-    pdfh (0.2.1)
+    pdfh (3.0.1)
       colorize (~> 0.8.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    activesupport (7.1.2)
+      base64
+      bigdecimal
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      connection_pool (>= 2.2.5)
+      drb
+      i18n (>= 1.6, < 2)
+      minitest (>= 5.1)
+      mutex_m
+      tzinfo (~> 2.0)
     ansi (1.5.0)
     ast (2.4.2)
+    base64 (0.2.0)
+    bigdecimal (3.1.5)
     blockenspiel (0.5.0)
-    code-scanning-rubocop (0.5.0)
+    code-scanning-rubocop (0.6.1)
       rubocop (~> 1.0)
     coderay (1.1.3)
     colorize (0.8.1)
+    concurrent-ruby (1.2.2)
+    connection_pool (2.4.1)
     diff-lcs (1.5.0)
     docile (1.4.0)
+    drb (2.2.0)
+      ruby2_keywords
+    factory_bot (6.4.5)
+      activesupport (>= 5.0.0)
+    i18n (1.14.1)
+      concurrent-ruby (~> 1.0)
+    json (2.7.1)
+    language_server-protocol (3.17.0.3)
     method_source (1.0.0)
-    parallel (1.21.0)
-    parser (3.1.0.0)
+    minitest (5.20.0)
+    mutex_m (0.2.0)
+    parallel (1.24.0)
+    parser (3.3.0.2)
       ast (~> 2.4.1)
-    pry (0.14.1)
+      racc
+    pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    rainbow (3.0.0)
-    rake (13.0.6)
-    regexp_parser (2.2.0)
-    rexml (3.2.5)
-    rspec (3.10.0)
-      rspec-core (~> 3.10.0)
-      rspec-expectations (~> 3.10.0)
-      rspec-mocks (~> 3.10.0)
-    rspec-core (3.10.1)
-      rspec-support (~> 3.10.0)
-    rspec-expectations (3.10.1)
+    racc (1.7.3)
+    rainbow (3.1.1)
+    rake (13.1.0)
+    regexp_parser (2.9.0)
+    rexml (3.2.6)
+    rspec (3.12.0)
+      rspec-core (~> 3.12.0)
+      rspec-expectations (~> 3.12.0)
+      rspec-mocks (~> 3.12.0)
+    rspec-core (3.12.2)
+      rspec-support (~> 3.12.0)
+    rspec-expectations (3.12.3)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.10.0)
-    rspec-mocks (3.10.2)
+      rspec-support (~> 3.12.0)
+    rspec-mocks (3.12.6)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.10.0)
-    rspec-support (3.10.3)
-    rspec_junit_formatter (0.5.1)
+      rspec-support (~> 3.12.0)
+    rspec-support (3.12.1)
+    rspec_junit_formatter (0.6.0)
       rspec-core (>= 2, < 4, != 2.12.0)
-    rubocop (1.24.1)
+    rubocop (1.59.0)
+      json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.0.0.0)
+      parser (>= 3.2.2.4)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.15.1, < 2.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.30.0, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.15.1)
-      parser (>= 3.0.1.1)
-    rubocop-performance (1.13.1)
-      rubocop (>= 1.7.0, < 2.0)
-      rubocop-ast (>= 0.4.0)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.30.0)
+      parser (>= 3.2.1.0)
+    rubocop-capybara (2.20.0)
+      rubocop (~> 1.41)
+    rubocop-factory_bot (2.25.1)
+      rubocop (~> 1.41)
+    rubocop-performance (1.20.2)
+      rubocop (>= 1.48.1, < 2.0)
+      rubocop-ast (>= 1.30.0, < 2.0)
     rubocop-rake (0.6.0)
       rubocop (~> 1.0)
-    rubocop-rspec (2.7.0)
-      rubocop (~> 1.19)
-    ruby-progressbar (1.11.0)
-    simplecov (0.21.2)
+    rubocop-rspec (2.26.1)
+      rubocop (~> 1.40)
+      rubocop-capybara (~> 2.17)
+      rubocop-factory_bot (~> 2.22)
+    ruby-progressbar (1.13.0)
+    ruby2_keywords (0.0.5)
+    simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
@@ -70,10 +105,12 @@ GEM
       simplecov
       terminal-table
     simplecov-html (0.12.3)
-    simplecov_json_formatter (0.1.3)
+    simplecov_json_formatter (0.1.4)
     terminal-table (3.0.2)
       unicode-display_width (>= 1.1.1, < 3)
-    unicode-display_width (2.1.0)
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
+    unicode-display_width (2.5.0)
     versionomy (0.5.0)
       blockenspiel (~> 0.5)
 
@@ -83,18 +120,19 @@ PLATFORMS
 DEPENDENCIES
   bundler (~> 2.0)
   code-scanning-rubocop (~> 0.5)
+  factory_bot (~> 6.2)
   pdfh!
   pry (~> 0.14)
   rake (~> 13.0)
-  rspec (~> 3.9)
+  rspec (~> 3.12)
   rspec_junit_formatter (~> 0.4)
-  rubocop (~> 1.0)
-  rubocop-performance (~> 1.9)
+  rubocop (~> 1.50)
+  rubocop-performance (~> 1.18)
   rubocop-rake (~> 0.5)
   rubocop-rspec (~> 2.2)
-  simplecov (~> 0.21)
+  simplecov (~> 0.22)
   simplecov-console (~> 0.9)
   versionomy (~> 0.5)
 
 BUNDLED WITH
-   2.2.17
+   2.5.4

data/README.md

@@ -1,9 +1,11 @@
 # PDF Handler (pdfh)
 
-[![Rubocop](https://github.com/iax7/pdfh/actions/workflows/rubocop-analysis.yml/badge.svg)](https://github.com/iax7/pdfh/actions/workflows/rubocop-analysis.yml)
-[![Ruby][ruby-badge]][ruby-url]
+[![Rubocop][rubocop-img]][rubocop-url]
+[![Ruby][ruby-img]][ruby-url]
+[![Conventional Commits][cc-img]][cc-url]
+[![Current version][gem-img]][gem-url]
 
-Examine all PDF files in Look up directories, remove password (if has one), rename and copy to a new directory using regular expresions.
+Examine all PDF files in Look up directories, remove password (if has one), rename and copy to a new directory using regular expressions.
 
 ## Installation
 
@@ -13,11 +15,17 @@ gem install pdfh
 
 ### Dependencies
 
-You need to install pdf handling dependencies in order to use this gem. (I have only tested it on macOS)
+You need to install pdf handling dependencies in order to use this gem.
 
+#### macOS
 ```bash
-brew install qpdf
-brew install xpdf
+brew install qpdf # for qpdf
+brew install xpdf # for pdftotext
+```
+
+#### Fedora
+```bash
+sudo dnf install -y qpdf poppler-utils
 ```
 
 ## Usage
@@ -81,5 +89,11 @@ The gem is available as open source under the terms of the [MIT License](https:/
 Everyone interacting in the Pdfh project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/iax7/pdfh/blob/master/CODE_OF_CONDUCT.md).
 
 <!-- Links -->
-[ruby-badge]: https://img.shields.io/badge/ruby-3.1.0-blue?style=flat&logo=ruby&logoColor=CC342D&labelColor=white
+[rubocop-img]: https://github.com/iax7/pdfh/actions/workflows/rubocop-analysis.yml/badge.svg
+[rubocop-url]: https://github.com/iax7/pdfh/actions/workflows/rubocop-analysis.yml
+[ruby-img]: https://img.shields.io/badge/ruby-3.1-blue?style=flat&logo=ruby&logoColor=CC342D&labelColor=white
 [ruby-url]: https://www.ruby-lang.org/en/
+[cc-img]: https://img.shields.io/badge/Conventional%20Commits-1.0.0-%23FE5196?logo=conventionalcommits&logoColor=00&labelColor=fff
+[cc-url]: https://conventionalcommits.org
+[gem-img]: https://img.shields.io/gem/v/pdfh?labelColor=fff&label=version
+[gem-url]: https://rubygems.org/gems/pdfh

data/bin/console

@@ -10,7 +10,7 @@ require "pdfh"
 # (If you use this, don't forget to add pry to your Gemfile!)
 require "pry"
 
-p Pdfh.parse_argv
+p Pdfh::OptParser.parse_argv
 
 Pry.start
 

data/bin/run

@@ -5,4 +5,4 @@ require "bundler/setup"
 require "pdfh"
 require "pry"
 
-Pdfh::DocumentProcessor.new.start
+Pdfh::Main.start

data/exe/pdfh

@@ -20,7 +20,7 @@ end
 exit(1) unless validate_installed("qpdf", "pdftotext")
 
 begin
-  Pdfh::DocumentProcessor.new.start
+  Pdfh::Main.start
 rescue StandardError => e
   Pdfh.error_print e.message
 end

data/lib/pdfh/main.rb

@@ -0,0 +1,93 @@
+# frozen_string_literal: true
+
+module Pdfh
+  # Main functionality. This class is intended to manage the pdf documents
+  class Main
+    class << self
+      # @return [void]
+      def start
+        arg_options = Pdfh::OptParser.parse_argv
+        @options = Options.new(arg_options)
+
+        Pdfh.instance_variable_set(:@options, options)
+        Pdfh.instance_variable_set(:@console, Console.new(options.verbose?))
+        Pdfh.print_options(arg_options)
+
+        @settings = SettingsBuilder.build
+        Pdfh.debug "Destination path: #{settings.base_path.colorize(:light_blue)}"
+
+        options.file_mode? ? process_provided_files : process_lookup_dirs
+      rescue SettingsIOError => e
+        Pdfh.error_print(e.message, exit_app: false)
+        Pdfh.create_settings_file
+        exit(1)
+      rescue StandardError => e
+        Pdfh.error_print(e.message)
+      end
+
+      private
+
+      attr_reader :options, :settings
+
+      # @param [String] file_name
+      # @return [DocumentType]
+      def match_doc_type(file_name)
+        settings.document_types.each do |type|
+          match = type.re_file.match(file_name)
+          return type if match
+        end
+        nil
+      end
+
+      # @return [void]
+      def process_provided_files
+        type_id = options.type
+        raise ArgumentError, "No files provided to process #{type_id.inspect} type." unless options.files?
+
+        type = settings.document_type(type_id)
+        Pdfh.error_print "Type #{type_id.inspect} was not found." if type.nil?
+        options.files.each do |file|
+          next Pdfh.warn_print "File #{file.inspect} does not exist." unless File.exist?(file)
+          next Pdfh.warn_print "File #{file.inspect} is not a pdf." unless File.extname(file) == ".pdf"
+
+          PdfFileHandler.new(file, type).process_document(settings.base_path)
+        end
+      end
+
+      # @return [void]
+      def process_lookup_dirs
+        settings.lookup_dirs.each do |work_directory|
+          process_directory(work_directory)
+        end
+      end
+
+      # @param [String] work_directory
+      # @return [void]
+      def process_directory(work_directory)
+        Pdfh.headline(work_directory)
+        processed_count = 0
+        ignored_files = []
+        files = Dir["#{work_directory}/*.pdf"]
+        files.each do |pdf_file|
+          type = match_doc_type(pdf_file)
+          if type
+            processed_count += 1
+            PdfFileHandler.new(pdf_file, type).process_document(settings.base_path)
+          else
+            ignored_files << base_name_no_ext(pdf_file)
+          end
+        end
+        puts "  (No files processed)".colorize(:light_black) if processed_count.zero?
+        return unless Pdfh.verbose?
+
+        puts "\n  No document type found for these PDF files:" if ignored_files.any?
+        ignored_files.each.with_index(1) { |file, index| Pdfh.ident_print index, file, color: :magenta }
+      end
+
+      # @return [String]
+      def base_name_no_ext(file)
+        File.basename(file, File.extname(file))
+      end
+    end
+  end
+end

data/lib/pdfh/{document.rb → models/document.rb}

@@ -3,27 +3,44 @@
 module Pdfh
   # Handles the PDF detected by the rules
   class Document
-    attr_reader :text, :type, :file, :extra, :pdf_doc, :period
+    IDENT = 12
+
+    attr_reader :text, :type, :file, :extra, :period
 
     # @param file [String]
     # @param type [DocumentType]
+    # @param text [String]
     # @return [self]
-    def initialize(file, type)
-      raise IOError, "File #{file} not found" unless File.exist?(file)
-
+    def initialize(file, type, text)
       @file = file
       @type = type
-      Pdfh.verbose_print "=== Document Type: #{type.name} =============================="
-      @pdf_doc = PdfHandler.new(file, type.pwd)
-      @text = @pdf_doc.extract_text
-      Pdfh.verbose_print "~~~~~~~~~~~~~~~~~~ Finding a subtype"
+      Pdfh.debug "=== Document Type: #{type.name} =============================="
+      @text = text
+      Pdfh.debug "~~~~~~~~~~~~~~~~~~ Finding a subtype"
       @sub_type = type.sub_type(@text)
-      Pdfh.verbose_print "  SubType: #{@sub_type}"
+      Pdfh.debug "  SubType: #{@sub_type}"
       @companion = search_companion_files
 
       month, year, @extra = match_data
       @period = DocumentPeriod.new(day: extra, month: month, month_offset: @sub_type&.month_offset, year: year)
-      Pdfh.verbose_print "  Period: #{@period.inspect}"
+      Pdfh.debug "  Period: #{@period.inspect}"
+    end
+
+    # @return [void]
+    def print_info
+      print_info_line "Type", type.name
+      print_info_line "Sub-Type", sub_type
+      print_info_line "Period", period
+      print_info_line "New Name", new_name
+      print_info_line "Store Path", store_path
+      print_info_line "Extra files", companion_files(join: true)
+      print_info_line "Print CMD", print_cmd
+      print_info_line "Processed?", "No (in Dry mode)" if Pdfh.dry?
+    end
+
+    # @return [void]
+    def print_info_line(property, info)
+      Pdfh.ident_print property, info.to_s, color: :light_blue, width: IDENT
     end
 
     # @return [String]
@@ -100,13 +117,13 @@ module Pdfh
     # unnamed matches needs to be in order month, year
     # @return [Array] - format [month, year, day]
     def match_data
-      Pdfh.verbose_print "~~~~~~~~~~~~~~~~~~ Match Data RegEx"
-      Pdfh.verbose_print "  Using regex: #{@type.re_date}"
-      Pdfh.verbose_print "        named:   #{@type.re_date.named_captures}"
+      Pdfh.debug "~~~~~~~~~~~~~~~~~~ Match Data RegEx"
+      Pdfh.debug "  Using regex: #{@type.re_date}"
+      Pdfh.debug "        named:   #{@type.re_date.named_captures}"
       matched = @type.re_date.match(@text)
       raise ReDateError unless matched
 
-      Pdfh.verbose_print "     captured: #{matched.captures}"
+      Pdfh.debug "     captured: #{matched.captures}"
 
       return matched.captures.map(&:downcase) if @type.re_date.named_captures.empty?
 
@@ -116,12 +133,12 @@ module Pdfh
 
     # @return [Array]
     def search_companion_files
-      Pdfh.verbose_print "~~~~~~~~~~~~~~~~~~ Searching Companion files"
-      Pdfh.verbose_print "  Searching on: #{home_dir.inspect}"
+      Pdfh.debug "~~~~~~~~~~~~~~~~~~ Searching Companion files"
+      Pdfh.debug "  Searching on: #{home_dir.inspect}"
       Dir.chdir(home_dir) do
         files_matching = Dir["#{file_name_only}.*"]
         companion = files_matching.reject { |file| file.include? ".pdf" }
-        Pdfh.verbose_print "    Found: #{companion.inspect}"
+        Pdfh.debug "    Found: #{companion.inspect}"
 
         companion
       end

data/lib/pdfh/{document_type.rb → models/document_type.rb}

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require "base64"
-
 module Pdfh
   DocumentSubType = Struct.new(:name, :month_offset, keyword_init: true)
 
@@ -13,10 +11,13 @@ module Pdfh
       self.name_template ||= "{original}"
       self.re_file = Regexp.new(re_file)
       self.re_date = Regexp.new(re_date)
-      self.pwd = Base64.decode64(pwd) if pwd
       self.sub_types = extract_subtype(sub_types) if sub_types
     end
 
+    # removes special characters from string and replaces spaces with dashes
+    # @example usage
+    #   "Test This?%&".gid
+    #   # => "test-this"
     # @return [String]
     def gid
       name.downcase.gsub(/[^0-9A-Za-z\s]/, "").tr(" ", "-")
@@ -28,14 +29,26 @@ module Pdfh
       sub_types&.find { |st| /#{st.name}/i.match?(text) }
     end
 
+    # @return [String]
+    def password
+      return Base64.decode64(pwd) if base64?
+
+      pwd
+    end
+
     private
 
+    # @return [boolean]
+    def base64?
+      pwd.is_a?(String) && Base64.strict_encode64(Base64.decode64(pwd)) == pwd
+    end
+
     # @param sub_types [Array]
     # @return [DocumentSubType]
     def extract_subtype(sub_types)
       sub_types.map do |st|
-        name = st["name"]
-        offset = st["month_offset"].to_i
+        name = st[:name]
+        offset = st[:month_offset].to_i
         DocumentSubType.new(name: name, month_offset: offset)
       end
     end