pdfh 3.2.0 → 3.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2cc0c0f6ba735b3d69c9f5bf32e6acc94b185b3606574834504634acad34f1e8
-  data.tar.gz: fd4bf05918b2631d2cb6335341704be2540d50cdcf5a395e7e85dd2206c865ca
+  metadata.gz: 29f90e2cbc737c2ea6f15b58f6a46513d90ac68053c770018a5a2549b76adcc6
+  data.tar.gz: 476440f76e4cd8eb0cdc248d9040cbf75fc510656ff1129d83d18bc1f9edf8ec
 SHA512:
-  metadata.gz: c58687eba046fb229b713a70650554a93473b22c9fe39c6d5427adde475187ec64a91031fb9b6ef6f22de9e516a5b5f75e7bdd6276657541127247395d53cec4
-  data.tar.gz: 0bc6756a6c83335f4afaad5708da797bd5d4e052542b12fa0ee030e23e66a779fe6303aa21eb6f63b6bba849291bf3a2f08a0a32ea1ea4b4f05ab14f2c3b976d
+  metadata.gz: 10672062c7041f020920bf4c51a9af88d82130d4db59f8a332a5b05df055bf6079c127b4c8d7d31fb145f9fc88b9527bc330a83f23d2f0dc69c92e843c8246ba
+  data.tar.gz: 606afc6611bb8036cd073c8a5a031dbc0812d2385de77d1b774c2c49b42673f266e4020c679a558dc3d709b3309e1e9d8708d2a8a7b6808f66b4d1ae770da780

data/.gitignore

@@ -39,4 +39,3 @@ Icon
 Network Trash Folder
 Temporary Items
 .apdisk
-

data/.pre-commit-config.yaml

@@ -0,0 +1,36 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+default_install_hook_types:
+  - pre-commit
+  - commit-msg
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+        exclude: ^.idea/
+      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      - id: mixed-line-ending
+  - repo: https://github.com/gitleaks/gitleaks
+    rev: v8.25.0
+    hooks:
+      - id: gitleaks
+  - repo: https://github.com/rubocop/rubocop
+    rev: v1.75.4
+    hooks:
+      - id: rubocop
+  - repo: https://github.com/compilerla/conventional-pre-commit
+    rev: v4.1.0
+    hooks:
+      - id: conventional-pre-commit
+        stages: [commit-msg]
+        args: []
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell

data/.rubocop.yml

@@ -1,10 +1,9 @@
 inherit_from: .rubocop_todo.yml
 
-require:
-  - rubocop-factory_bot
+plugins:
   - rubocop-performance
+  - rubocop-factory_bot
   - rubocop-rake
-  - rubocop-rspec
 
 AllCops:
   NewCops: enable
@@ -14,6 +13,8 @@ AllCops:
     - pkg/**/*
     - tmp/**/*
     - vendor/**/*
+  SuggestExtensions:
+    rubocop-rspec: false
 
 Layout/LineLength:
   Max: 120

data/.rubocop_todo.yml

@@ -1,54 +1,33 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2024-03-13 18:36:20 UTC using RuboCop version 1.62.1.
+# on 2025-04-19 20:15:39 UTC using RuboCop version 1.75.2.
 # 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: 8
+# Offense count: 10
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes.
 Metrics/AbcSize:
-  Max: 25
+  Max: 38
+
+# Offense count: 16
+# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
+# AllowedMethods: refine
+Metrics/BlockLength:
+  Max: 131
 
 # Offense count: 6
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
-  Max: 17
-
-# Offense count: 2
-RSpec/AnyInstance:
-  Exclude:
-    - 'spec/pdfh/main_spec.rb'
-
-# Offense count: 8
-# Configuration parameters: Include, CustomTransform, IgnoreMethods, SpecSuffixOnly.
-# Include: **/*_spec*rb*, **/spec/**/*
-RSpec/FilePath:
-  Exclude:
-    - 'spec/pdfh/models/document_period_spec.rb'
-    - 'spec/pdfh/models/document_spec.rb'
-    - 'spec/pdfh/utils/console_spec.rb'
-    - 'spec/pdfh/utils/month_spec.rb'
-    - 'spec/pdfh/utils/opt_parser_spec.rb'
-    - 'spec/pdfh/utils/pdf_file_handler_spec.rb'
-    - 'spec/pdfh/utils/rename_validator_spec.rb'
-    - 'spec/pdfh/utils/settings_builder_spec.rb'
+  Max: 33
 
-# Offense count: 8
-# Configuration parameters: Include, CustomTransform, IgnoreMethods, IgnoreMetadata.
-# Include: **/*_spec.rb
-RSpec/SpecFilePathFormat:
+# Offense count: 1
+# Configuration parameters: MinNameLength, AllowNamesEndingInNumbers, AllowedNames, ForbiddenNames.
+# AllowedNames: as, at, by, cc, db, id, if, in, io, ip, of, on, os, pp, to
+Naming/MethodParameterName:
   Exclude:
-    - '**/spec/routing/**/*'
-    - 'spec/pdfh/models/document_period_spec.rb'
-    - 'spec/pdfh/models/document_spec.rb'
-    - 'spec/pdfh/utils/console_spec.rb'
-    - 'spec/pdfh/utils/month_spec.rb'
-    - 'spec/pdfh/utils/opt_parser_spec.rb'
-    - 'spec/pdfh/utils/pdf_file_handler_spec.rb'
-    - 'spec/pdfh/utils/rename_validator_spec.rb'
-    - 'spec/pdfh/utils/settings_builder_spec.rb'
+    - 'lib/pdfh/utils/console.rb'
 
 # Offense count: 3
 # This cop supports safe autocorrection (--autocorrect).

data/Gemfile.lock

@@ -1,13 +1,13 @@
 PATH
   remote: .
   specs:
-    pdfh (3.2.0)
+    pdfh (3.3.0)
       colorize (~> 1.1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (8.0.1)
+    activesupport (8.0.2)
       base64
       benchmark (>= 0.3)
       bigdecimal
@@ -21,7 +21,7 @@ GEM
       tzinfo (~> 2.0, >= 2.0.5)
       uri (>= 0.13.1)
     ansi (1.5.0)
-    ast (2.4.2)
+    ast (2.4.3)
     base64 (0.2.0)
     benchmark (0.4.0)
     bigdecimal (3.1.9)
@@ -31,12 +31,12 @@ GEM
     coderay (1.1.3)
     colorize (1.1.0)
     concurrent-ruby (1.3.5)
-    connection_pool (2.5.0)
+    connection_pool (2.5.3)
     date (3.4.1)
     debug (1.10.0)
       irb (~> 1.10)
       reline (>= 0.3.8)
-    diff-lcs (1.6.0)
+    diff-lcs (1.6.1)
     docile (1.4.1)
     drb (2.2.1)
     factory_bot (6.5.1)
@@ -44,36 +44,37 @@ GEM
     i18n (1.14.7)
       concurrent-ruby (~> 1.0)
     io-console (0.8.0)
-    irb (1.15.1)
+    irb (1.15.2)
       pp (>= 0.6.0)
       rdoc (>= 4.0.0)
       reline (>= 0.4.2)
-    json (2.10.1)
+    json (2.11.3)
     language_server-protocol (3.17.0.4)
     lint_roller (1.1.0)
-    logger (1.6.6)
+    logger (1.7.0)
     method_source (1.1.0)
-    minitest (5.25.4)
-    parallel (1.26.3)
-    parser (3.3.7.1)
+    minitest (5.25.5)
+    parallel (1.27.0)
+    parser (3.3.8.0)
       ast (~> 2.4.1)
       racc
     pp (0.6.2)
       prettyprint
     prettyprint (0.2.0)
+    prism (1.4.0)
     pry (0.15.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    psych (5.2.3)
+    psych (5.2.4)
       date
       stringio
     racc (1.8.1)
     rainbow (3.1.1)
     rake (13.2.1)
-    rdoc (6.12.0)
+    rdoc (6.13.1)
       psych (>= 4.0.0)
     regexp_parser (2.10.0)
-    reline (0.6.0)
+    reline (0.6.1)
       io-console (~> 0.5)
     rspec (3.13.0)
       rspec-core (~> 3.13.0)
@@ -81,16 +82,16 @@ GEM
       rspec-mocks (~> 3.13.0)
     rspec-core (3.13.3)
       rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.3)
+    rspec-expectations (3.13.4)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.2)
+    rspec-mocks (3.13.4)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-support (3.13.2)
+    rspec-support (3.13.3)
     rspec_junit_formatter (0.6.0)
       rspec-core (>= 2, < 4, != 2.12.0)
-    rubocop (1.73.2)
+    rubocop (1.75.5)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
@@ -98,19 +99,21 @@ GEM
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 2.9.3, < 3.0)
-      rubocop-ast (>= 1.38.0, < 2.0)
+      rubocop-ast (>= 1.44.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 4.0)
-    rubocop-ast (1.38.1)
-      parser (>= 3.3.1.0)
-    rubocop-capybara (2.21.0)
-      rubocop (~> 1.41)
-    rubocop-factory_bot (2.27.0)
+    rubocop-ast (1.44.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
+    rubocop-capybara (2.22.1)
+      lint_roller (~> 1.1)
+      rubocop (~> 1.72, >= 1.72.1)
+    rubocop-factory_bot (2.27.1)
       lint_roller (~> 1.1)
       rubocop (~> 1.72, >= 1.72.1)
-    rubocop-performance (1.24.0)
+    rubocop-performance (1.25.0)
       lint_roller (~> 1.1)
-      rubocop (>= 1.72.1, < 2.0)
+      rubocop (>= 1.75.0, < 2.0)
       rubocop-ast (>= 1.38.0, < 2.0)
     rubocop-rake (0.7.1)
       lint_roller (~> 1.1)
@@ -134,7 +137,7 @@ GEM
       terminal-table
     simplecov-html (0.13.1)
     simplecov_json_formatter (0.1.4)
-    stringio (3.1.5)
+    stringio (3.1.7)
     terminal-table (4.0.0)
       unicode-display_width (>= 1.1.1, < 4)
     tzinfo (2.0.6)
@@ -168,4 +171,4 @@ DEPENDENCIES
   versionomy (~> 0.5)
 
 BUNDLED WITH
-   2.6.5
+   2.6.8

data/README.md

@@ -5,7 +5,7 @@
 [![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 expressions.
+Examine all PDF files in lookup directories, remove passwords (if present), rename them, and copy them to a new directory using regular expressions.
 
 ## Installation
 
@@ -20,8 +20,7 @@ You need to install pdf handling dependencies in order to use this gem.
 #### macOS
 
 ```bash
-brew install qpdf # for qpdf
-brew install xpdf # for pdftotext
+brew install qpdf xpdf # < for pdftotext
 ```
 
 #### Fedora
@@ -38,38 +37,58 @@ sudo pacman -S qpdf poppler
 
 ## Usage
 
-After installing this gem you need to create your configuration file on any of the following directories:
-
+After installing this gem, create your configuration file in one of the following directories:
 - `~/.config/pdfh.yml`
 - `~/pdfh.yml`
-- or configure `PDFH_CONFIG_FILE` environment variable
+- or configure the `PDFH_CONFIG_FILE` environment variable
 
+Example configuration:
 ```yaml
 ---
-lookup_dirs:       # Directories where all pdf's are going to be analyzed
+lookup_dirs:                   # Directories where all PDFs will be analyzed
   - ~/Downloads
 destination_base_path: ~/PDFs  # Directory where all matching documents will be copied (MUST exist)
 document_types:
-  - name: Document From Bank              # Description
+  - name: My Bank                         # Description (type)
     re_file: '.*MyBankReg\.pdf'           # Regular expression to match its filename
-    re_date: 'al \d{1,2} de (\w+) del? (\d+)' # Date regular expresion
-    pwd: base64string                     # [OPTIONAL] Password if the document is protected
+    re_date: '\d{1,2} de (\w+) de (\d+)'  # Date regular expression
+    pwd: base64_encoded                   # [OPTIONAL] Password if the document is protected
     store_path: "{year}/bank_docs"        # Relative path to copy this document
     name_template: '{period} {subtype}'   # Template for new filename when copied
     sub_types:                            # [OPTIONAL] In case your need an extra category
-      - name: Account1                       # Regular expresion to match this subtype
+      - name: AccountX                       # Regular expression to match this subtype
+        re_date: '\d{1,2} de (\w+)'          # [OPTIONAL] Date regular expression
         month_offset: -1                     # [OPTIONAL] Integer (signed) value to adjust month
+zip_types:                     # [OPTIONAL] Zip files to be processed BEFORE the PDFs
+  - name: My Bank 2                          # Description
+    re_file: 'Document_MR5664_\d+_\d+.zip'   # Regular expression to match its filename
+    pwd: base64_encoded                      # [OPTIONAL] Password if the document is protected
 ```
 
+> [!CAUTION]
+> `pwd` is not encrypted, so be careful with this option. It is stored as a base64 string as a very thin layer of obfuscation.
+> You can use `echo -n 'password' | base64` to encode your password.
+
 **Store Path** and **Name Template** supported placeholders:
 
-- `{original}` Original filename
-- `{period}` 2022-01
-- `{year}` 2022
-- `{month}` 01
-- `{type}` document_type.name
-- `{subtype}` subtype.name if matched
-- `{extra}` day if provided/matched
+Placeholder | Description               | Example
+--- |---------------------------| ---
+`{original}` | Original filename         | MyBankDocument2.pdf
+`{period}`   | Year-Month                | 2022-01
+`{year}`     | Year                      | 2022
+`{month}`    | Month                     | 01
+`{type}`     | Document type **name**    | My Bank
+`{subtype}`  | Sub type **name**         | AccountX
+`{extra}`    | day if captured/matched   | 01
+
+`period`, `year`, `month` and `{extra}` are calculated from the date captured by the regular expression.
+
+### Examples
+
+Date text | RegEx | Captured
+--- | --- | ---
+`01/02/2025` | `(?<d>\d{2}\/(?<m>\d{2})\/(?<y>\d{4})` | d: `01` m: `02` y: `2025`
+`072025 - ` | `(?<m>\d{2})(?<y>\d{4}) -` | m: `07` y: `2025`
 
 ## Development
 
@@ -85,6 +104,15 @@ build pdfh.gemspec
 gem install pdfh-*
 ```
 
+To release a new version, run:
+
+```bash
+rake bump
+rake release
+```
+
+This will create a git tag for the version, push git commits and tags, and upload the `.gem` file to rubygems.org.
+
 ### Conventional Commits
 
 ```bash

data/bin/run

@@ -6,4 +6,6 @@ require "debug"
 require "pdfh"
 require "pry"
 
-Pdfh::Main.start
+exit(1) if Pdfh::Utils::DependencyValidator.missing?(*Pdfh::REQUIRED_CMDS)
+
+Pdfh::Main.start(argv: ARGV)

data/exe/pdfh

@@ -1,26 +1,12 @@
 #!/usr/bin/env ruby
 # frozen_string_literal: true
 
-require "open3"
 require "pdfh"
 
-# @param apps [Array]
-# @return [Boolean]
-def validate_installed(*apps)
-  found_app = []
-  apps.each_with_object(found_app) do |app, result|
-    _stdout, _stderr, status = Open3.capture3("which #{app}")
-    puts "Missing #{app} command." unless status.success?
-    result << status.success?
-  end
-
-  found_app.all?
-end
-
-exit(1) unless validate_installed("qpdf", "pdftotext")
+exit(1) if Pdfh::Utils::DependencyValidator.missing?(*Pdfh::REQUIRED_CMDS)
 
 begin
-  Pdfh::Main.start
+  Pdfh::Main.start(argv: ARGV)
 rescue StandardError => e
   Pdfh.error_print e.message
 end

data/lib/pdfh/concerns/password_decodable.rb

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+
+module Pdfh
+  module Concerns
+    # Module that provides password handling capabilities for classes that contain
+    # password attributes. It handles Base64-encoded passwords by automatically
+    # detecting and decoding them when accessed through the password method.
+    module PasswordDecodable
+      # Returns the decoded password if it's Base64 encoded, otherwise returns it as is
+      # @return [String]
+      def password
+        return Base64.decode64(pwd) if base64?
+
+        pwd
+      end
+
+      # @return [Boolean]
+      def password?
+        base64?
+      end
+
+      private
+
+      # @return [boolean]
+      def base64?
+        pwd.is_a?(String) && pwd.size.positive? &&
+          Base64.strict_encode64(Base64.decode64(pwd)) == pwd
+      end
+    end
+  end
+end

data/lib/pdfh/main.rb

@@ -4,13 +4,12 @@ module Pdfh
   # Main functionality. This class is intended to manage the pdf documents
   class Main
     class << self
+      # @param argv [Array<String>]
       # @return [void]
-      def start
-        arg_options = Pdfh::OptParser.parse_argv
+      def start(argv:)
+        arg_options = Pdfh::OptParser.new(argv: argv).parse_argv
         @options = Options.new(arg_options)
-
-        Pdfh.instance_variable_set(:@options, options)
-        Pdfh.instance_variable_set(:@console, Console.new(options.verbose?))
+        assign_global_utils(@options)
         Pdfh.print_options(arg_options)
 
         @settings = SettingsBuilder.build
@@ -30,8 +29,15 @@ module Pdfh
 
       attr_reader :options, :settings
 
+      # @param options [Options]
+      # @return [void]
+      def assign_global_utils(options)
+        Pdfh.instance_variable_set(:@options, options)
+        Pdfh.instance_variable_set(:@console, Console.new(options.verbose?))
+      end
+
       # @param [String] file_name
-      # @return [DocumentType]
+      # @return [DocumentType, nil]
       def match_doc_type(file_name)
         settings.document_types.each do |type|
           match = type.re_file.match(file_name)
@@ -64,31 +70,74 @@ module Pdfh
 
       # @param [String] work_directory
       # @return [void]
+      def process_zip_files(work_directory)
+        @settings.zip_types&.each do |zip_type|
+          find_files(work_directory, :zip).each do |file|
+            next unless zip_type.re_file.match?(File.basename(file))
+
+            Pdfh.info " > Processing zip file: #{file.green}"
+            password_opt = "-P #{zip_type.password}" if zip_type.password?
+            `unzip -o #{password_opt} #{file} -d #{work_directory}`
+          end
+        end
+      end
+
+      # @param directory [String]
+      # @param type [String, Symbol]
+      # @return [Array<String>]
+      def find_files(directory, type)
+        glob = File.join(directory, "*.#{type}")
+        Dir.glob(glob)
+      end
+
       def process_directory(work_directory)
         Pdfh.headline(work_directory)
-        processed_count = 0
-        ignored_files = []
-        files = Dir["#{work_directory}/*.pdf"]
+        process_zip_files(work_directory) if @settings.zip_types?
+        processed_result = RunResult.new
+        files = find_files(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)
+            processed_result.add_processed(pdf_file)
           else
-            ignored_files << base_name_no_ext(pdf_file)
+            processed_result.add_ignored(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 }
+        print_processing_results(processed_result)
       end
 
       # @return [String]
       def base_name_no_ext(file)
         File.basename(file, File.extname(file))
       end
+
+      def print_processing_results(result)
+        Pdfh.info "  (No files processed)".colorize(:light_black) if result.processed.empty?
+        return unless Pdfh.verbose?
+
+        Pdfh.info "\n  No document type found for these PDF files:" if result.ignored.any?
+        result.ignored.each.with_index(1) do |file, index|
+          Pdfh.ident_print index, base_name_no_ext(file), color: :magenta
+        end
+      end
+    end
+
+    # keeps track of the processed and ignored files
+    class RunResult
+      attr_reader :processed, :ignored
+
+      # @return [self]
+      def initialize
+        @processed = []
+        @ignored = []
+      end
+
+      # @return [void]
+      def add_ignored(file) = @ignored << file
+
+      # @return [void]
+      def add_processed(file) = @processed << file
     end
   end
 end

data/lib/pdfh/models/document_type.rb

@@ -3,6 +3,22 @@
 module Pdfh
   # Represents a type of document that can be processed by pdfh
   class DocumentType
+    include Concerns::PasswordDecodable
+
+    # @!attribute [r] name
+    #   @return [String] The name of the document type.
+    # @!attribute [r] re_file
+    #   @return [Regexp] The regular expression to match file names.
+    # @!attribute [r] re_date
+    #   @return [Regexp] The regular expression to extract dates and its information.
+    # @!attribute [r] pwd
+    #   @return [String, nil] The base64 password for the document type, if any.
+    # @!attribute [r] store_path
+    #   @return [String] The path where the document will be stored.
+    # @!attribute [r] name_template
+    #   @return [String] The template for generating document names.
+    # @!attribute [r] sub_types
+    #   @return [Array<DocumentSubType>, nil] The subtypes of the document, if any.
     attr_reader :name, :re_file, :re_date, :pwd, :store_path, :name_template, :sub_types
 
     # @param args [Hash]
@@ -41,13 +57,6 @@ module Pdfh
       sub_types&.find { |st| /#{st.name}/i.match?(text) }
     end
 
-    # @return [String]
-    def password
-      return Base64.decode64(pwd) if base64?
-
-      pwd
-    end
-
     # @param values [Hash{Symbol->String}
     # @return [String]
     def generate_new_name(values)
@@ -64,11 +73,6 @@ module Pdfh
 
     attr_accessor :path_validator, :name_validator
 
-    # @return [boolean]
-    def base64?
-      pwd.is_a?(String) && Base64.strict_encode64(Base64.decode64(pwd)) == pwd
-    end
-
     # @param sub_types [Array<Hash{Symbol->String}>]
     # @return [Array<DocumentSubType>]
     def extract_subtypes(sub_types)

data/lib/pdfh/models/settings.rb

@@ -3,7 +3,13 @@
 module Pdfh
   # Handles the config yaml data mapping, and associates a file name with a doc type
   class Settings
-    attr_reader :lookup_dirs, :base_path
+    # @!attribute [r] lookup_dirs
+    #   @return [Array<String>] List of directories to look up for processing.
+    # @!attribute [r] base_path
+    #   @return [String] The base directory path for storing processed files.
+    # @!attribute [r] zip_types
+    #   @return [Array<ZipType>, nil] List of zip types to process, or nil if none.
+    attr_reader :lookup_dirs, :base_path, :zip_types
 
     # @param config_data [Hash]
     # @return [self]
@@ -15,7 +21,8 @@ module Pdfh
       lookup_dirs.each.with_index(1) { |dir, idx| Pdfh.debug "  #{idx}. #{dir}" }
       Pdfh.debug
 
-      load_doc_types(config_data[:document_types])
+      build_doc_types(config_data[:document_types])
+      build_zip_types(config_data[:zip_types]) if config_data.key?(:zip_types)
     end
 
     # @return [Array<DocumentType>]
@@ -28,8 +35,14 @@ module Pdfh
       @document_types[id]
     end
 
+    # @return [Boolean]
+    def zip_types?
+      !!zip_types&.any?
+    end
+
     private
 
+    # @param lookup_dirs_list [Array[String]]
     # @return [void]
     def process_lookup_dirs(lookup_dirs_list)
       @lookup_dirs = lookup_dirs_list.filter_map do |dir|
@@ -44,14 +57,16 @@ module Pdfh
     end
 
     # @return [void]
+    # @param dir [String]
     def process_destination_base(dir)
       @base_path = File.expand_path(dir)
       raise ArgumentError, "Destination base directory is not configured." if @base_path.nil?
       raise ArgumentError, "Destination base directory #{@base_path} does not exist." unless File.directory?(@base_path)
     end
 
-    # @return [Array<DocumentType>]
-    def load_doc_types(doc_types)
+    # @param doc_types [Array<Hash>]
+    # @return [void]
+    def build_doc_types(doc_types)
       @document_types = doc_types.each_with_object({}) do |data, result|
         doc_type = DocumentType.new(data)
         result.store(doc_type.gid, doc_type)
@@ -60,5 +75,13 @@ module Pdfh
         Pdfh.backtrace_print e if Pdfh.verbose?
       end
     end
+
+    # @param zip_types [Array<Hash>]
+    # @return [void]
+    def build_zip_types(zip_types)
+      exit(1) if Pdfh::Utils::DependencyValidator.missing?(:unzip)
+
+      @zip_types = zip_types.compact.map { ZipType.new(_1) }
+    end
   end
 end

data/lib/pdfh/models/zip_types.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module Pdfh
+  # Zip files which contains PDF files that need pre-processing
+  class ZipType
+    include Concerns::PasswordDecodable
+
+    attr_reader :name, :re_file, :pwd
+
+    # @param args [Hash]
+    # @return [self]
+    def initialize(args)
+      args.each { |k, v| instance_variable_set(:"@#{k}", v) }
+      @re_file = Regexp.new(re_file)
+    end
+  end
+end

data/lib/pdfh/utils/dependency_validator.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+require "open3"
+
+module Pdfh
+  module Utils
+    # Provides methods to validate external dependencies
+    module DependencyValidator
+      module_function
+
+      # Validates if the required command-line applications are installed
+      # @param apps [Array<String>] names of required command-line applications
+      # @return [Boolean] true if all applications are installed, false otherwise
+      def installed?(*apps)
+        missing = apps.filter_map do |app|
+          _stdout, _stderr, status = Open3.capture3("which #{app}")
+
+          app.to_s unless status.success?
+        end
+
+        if missing.any?
+          errors = missing.map(&:red)
+          puts "Required dependency #{errors.join(", ")} not found. Please install it before continuing."
+        end
+        missing.empty?
+      end
+
+      # @param apps [Array<String>]
+      # @return [Boolean] true if any application is missing, false if all are installed
+      def missing?(*apps)
+        !installed?(*apps)
+      end
+    end
+  end
+end

data/lib/pdfh/utils/opt_parser.rb

@@ -5,58 +5,73 @@ require "optparse"
 module Pdfh
   # Handles Argument options
   class OptParser
-    OPT_PARSER = OptionParser.new do |opts|
-      opts.default_argv
-      # Process ARGV
-      opts.banner = "Usage: #{opts.program_name} [options] [file1 ...]"
-      opts.separator ""
-      opts.separator "Specific options:"
-
-      opts.on("-tID", "--type=ID", "Document type id (requires a trailing file list)")
-      opts.on_tail("-T", "--list-types", "List document types in configuration") { list_types || exit }
-      opts.on_tail("-V", "--version", "Show version") { version || exit }
-      opts.on_tail("-h", "--help", "help (this dialog)") { help || exit }
-
-      opts.on("-v", "--verbose", "Show more output. Useful for debug")
-      opts.on("-d", "--dry", "Dry run, does not write new pdf")
+    # @param argv [Array<String>] command line arguments (ie. ARGV)
+    # @param console [Pdfh::Console, nil]
+    # @return [self]
+    def initialize(argv:, console: nil)
+      @argv = argv
+      @console = console || Console.new(false)
+      @options = {
+        verbose: false,
+        dry: false,
+        type: nil,
+        files: []
+      }
     end
 
-    class << self
-      # @return [Hash]
-      def parse_argv
-        Pdfh.instance_variable_set(:@console, Console.new(false))
-
-        options = { dry: false, verbose: false }
-        OPT_PARSER.parse!(into: options)
-        options[:files] = ARGV if ARGV.any?
-        options.transform_keys { |key| key.to_s.tr("-", "_").to_sym }
-      rescue OptionParser::InvalidOption => e
-        Pdfh.error_print(e.message, exit_app: false)
-        puts OPT_PARSER.help
-        exit 1
-      end
+    # @return [Hash] Parsed options including flags and file arguments
+    def parse_argv
+      option_parser = build_option_parser
+      non_option_args = option_parser.parse!(@argv)
+      @options[:files] = non_option_args
+      @options.transform_keys { |key| key.to_s.tr("-", "_").to_sym }
+    rescue OptionParser::InvalidOption => e
+      @console.error_print(e.message, exit_app: false)
+      puts option_parser.help
+      exit 1
+    end
 
-      # @return [nil]
-      def version
-        puts "#{OPT_PARSER.program_name} v#{Pdfh::VERSION}"
-      end
+    private
 
-      # @return [nil]
-      def help
-        puts OPT_PARSER
+    # @return [OptionParser] Configured OptionParser instance
+    def build_option_parser
+      OptionParser.new do |opts|
+        opts.banner = "Usage: #{opts.program_name} [options] [file1.pdf, ...]"
+        opts.separator ""
+        opts.separator "Specific options:"
+
+        opts.on("-tID", "--type=ID", "Document type id (requires a trailing file list)") { @options[:type] = _1 }
+        opts.on("-v", "--verbose", "Show more output. Useful for debug") { @options[:verbose] = true }
+        opts.on("-d", "--dry", "Dry run, does not write new pdf") { @options[:dry] = true }
+        opts.on_tail("-T", "--list-types", "List document types in configuration") { list_types && exit }
+        opts.on_tail("-V", "--version", "Show version") { version || exit }
+        opts.on_tail("-h", "--help", "help (this dialog)") { help || exit }
       end
+    end
+
+    # @return [nil]
+    def version
+      @console.info "#{build_option_parser.program_name} v#{Pdfh::VERSION}"
+    end
+
+    # @return [nil]
+    def help
+      @console.info build_option_parser
+    end
+
+    # Lists the available document types
+    # @return [nil]
+    def list_types
+      Pdfh.instance_variable_set(:@options, Options.new(@options))
+      Pdfh.instance_variable_set(:@console, @console)
 
-      # @return [nil]
-      def list_types
-        settings = SettingsBuilder.build
-        ident = 2
-        max_width = settings.document_types.map { |t| t.gid.size }.max
-        puts "#{" " * ident}#{"ID".ljust(max_width)}  Type Name"
-        puts "#{" " * ident}#{"—" * max_width}  #{"—" * 23}"
-        settings.document_types.each do |type|
-          puts "#{" " * ident}#{type.gid.ljust(max_width).yellow}  #{type.name}"
-        end
-        nil
+      settings = SettingsBuilder.build
+      spacing = " " * 2
+      max_width = settings.document_types.map { |t| t.gid.size }.max
+      @console.info "#{spacing}#{"ID".ljust(max_width)}  Type Name"
+      @console.info "#{spacing}#{"—" * max_width}  #{"—" * 23}"
+      settings.document_types.each do |type|
+        @console.info "#{spacing}#{type.gid.ljust(max_width).yellow}  #{type.name}"
       end
     end
   end

data/lib/pdfh/utils/pdf_file_handler.rb

@@ -87,7 +87,7 @@ module Pdfh
     end
 
     # Gets the text from the pdf in order to execute
-    # the regular expresion matches
+    # the regular expression matches
     # @return [String]
     def extract_text
       temp = Tempfile.new("pdfh")

data/lib/pdfh/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pdfh
-  VERSION = "3.2.0"
+  VERSION = "3.3.0"
 end

data/lib/pdfh.rb

@@ -9,15 +9,20 @@ require "yaml"
 
 require_relative "ext/string"
 
+# Concerns
+require_relative "pdfh/concerns/password_decodable"
+
 # Models
 require_relative "pdfh/models/document"
 require_relative "pdfh/models/document_period"
 require_relative "pdfh/models/document_sub_type"
 require_relative "pdfh/models/document_type"
 require_relative "pdfh/models/settings"
+require_relative "pdfh/models/zip_types"
 
 # Utils
 require_relative "pdfh/utils/console"
+require_relative "pdfh/utils/dependency_validator"
 require_relative "pdfh/utils/month"
 require_relative "pdfh/utils/opt_parser"
 require_relative "pdfh/utils/options"
@@ -31,6 +36,8 @@ require_relative "pdfh/version"
 
 # Gem entry point
 module Pdfh
+  REQUIRED_CMDS = %i[qpdf pdftotext].freeze
+
   # Settings not found
   class SettingsIOError < StandardError; end
 
@@ -45,6 +52,7 @@ module Pdfh
   class << self
     extend Forwardable
     def_delegators :@options, :verbose?, :dry?, :file_mode?
-    def_delegators :@console, :ident_print, :warn_print, :error_print, :backtrace_print, :headline, :debug, :info, :print_options
+    def_delegators :@console, :ident_print, :warn_print, :error_print, :backtrace_print, :headline, :debug, :info,
+                   :print_options
   end
 end

data/mise.toml

@@ -1,2 +1,2 @@
 [tools]
-ruby = "3.4.2"
+ruby = "3.4.3"

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: pdfh
 version: !ruby/object:Gem::Version
-  version: 3.2.0
+  version: 3.3.0
 platform: ruby
 authors:
 - Isaias Piña
 bindir: exe
 cert_chain: []
-date: 2025-04-01 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: colorize
@@ -33,6 +33,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".pre-commit-config.yaml"
 - ".rspec"
 - ".rubocop.yml"
 - ".rubocop_todo.yml"
@@ -50,14 +51,17 @@ files:
 - exe/pdfh
 - lib/ext/string.rb
 - lib/pdfh.rb
+- lib/pdfh/concerns/password_decodable.rb
 - lib/pdfh/main.rb
 - lib/pdfh/models/document.rb
 - lib/pdfh/models/document_period.rb
 - lib/pdfh/models/document_sub_type.rb
 - lib/pdfh/models/document_type.rb
 - lib/pdfh/models/settings.rb
+- lib/pdfh/models/zip_types.rb
 - lib/pdfh/settings_template.rb
 - lib/pdfh/utils/console.rb
+- lib/pdfh/utils/dependency_validator.rb
 - lib/pdfh/utils/month.rb
 - lib/pdfh/utils/opt_parser.rb
 - lib/pdfh/utils/options.rb
@@ -90,7 +94,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.6
+rubygems_version: 3.6.8
 specification_version: 4
 summary: Organize PDF files
 test_files: []