pdfh 3.0.2 → 3.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 800f047d683e60b4fafca9fc762c7df699194c916822221754de2383078e0da3
-  data.tar.gz: 6d10a59cdeb87d5127ff624ffad4c4fc644872ab91c8df50cd97db40f4fff0a2
+  metadata.gz: ecddee5472149aa038427798c482557111e62070ebed5558fdffcde55417b325
+  data.tar.gz: 75ff53bc3429bc5303411a81d3922e3f0b6f4249bf66bae396e867cd0b4615a9
 SHA512:
-  metadata.gz: b0caadec708ec57951c5e40192ccb84c735d652420d4bd1f0398fe3f4dc6758e3acf3ae1121459aa219275f7ef66084412cf8d7c8b07eb254f93c827513a4b9e
-  data.tar.gz: 125c1aebc9023315fa4355f880c25090c2f13aa34ebeadbcbcfc1481a49bb39d0112350fcd50b01844b278c45c9fa96842869ae969b8343fc600b6f4ee7740dd
+  metadata.gz: 4c51ac8db9d6f9b56c1608289c7d7694b21af6856eb69e06b4fd203ff2824ed3884a1ef1c64cefea37ff1358614e41e3c55264134d9616d9d14819d36ed7241a
+  data.tar.gz: b3d382767616e4008997ce8050691c1e578b8a181ee2a36a4fb4f6a8ed912e93f65511967db2990efbbcd33d73ffdc21535a5163ad9e248225e5e0054548b570

data/.rubocop.yml

@@ -26,3 +26,6 @@ Style/StringLiterals:
 Style/StringLiteralsInInterpolation:
   Enabled: true
   EnforcedStyle: double_quotes
+
+Layout/HashAlignment:
+  EnforcedHashRocketStyle: table

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2024-01-10 03:23:37 UTC using RuboCop version 1.59.0.
+# on 2024-03-13 18:36:20 UTC using RuboCop version 1.62.1.
 # 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
@@ -21,12 +21,7 @@ RSpec/AnyInstance:
   Exclude:
     - 'spec/pdfh/main_spec.rb'
 
-# Offense count: 1
-# Configuration parameters: CountAsOne.
-RSpec/ExampleLength:
-  Max: 6
-
-# Offense count: 7
+# Offense count: 8
 # Configuration parameters: Include, CustomTransform, IgnoreMethods, SpecSuffixOnly.
 # Include: **/*_spec*rb*, **/spec/**/*
 RSpec/FilePath:
@@ -37,9 +32,10 @@ RSpec/FilePath:
     - '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'
 
-# Offense count: 7
+# Offense count: 8
 # Configuration parameters: Include, CustomTransform, IgnoreMethods, IgnoreMetadata.
 # Include: **/*_spec.rb
 RSpec/SpecFilePathFormat:
@@ -51,6 +47,7 @@ RSpec/SpecFilePathFormat:
     - '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'
 
 # Offense count: 3

data/Gemfile

@@ -7,6 +7,7 @@ gemspec
 
 gem "bundler", "~> 2.0"
 gem "code-scanning-rubocop", "~> 0.5"
+gem "debug", "~> 1.8"
 gem "factory_bot", "~> 6.2"
 gem "pry", "~> 0.14"
 gem "rake", "~> 13.0"

data/Gemfile.lock

@@ -1,13 +1,13 @@
 PATH
   remote: .
   specs:
-    pdfh (3.0.2)
+    pdfh (3.1.0)
       colorize (~> 1.1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (7.1.2)
+    activesupport (7.1.3.2)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.0.2)
@@ -20,82 +20,96 @@ GEM
     ansi (1.5.0)
     ast (2.4.2)
     base64 (0.2.0)
-    bigdecimal (3.1.5)
+    bigdecimal (3.1.7)
     blockenspiel (0.5.0)
     code-scanning-rubocop (0.6.1)
       rubocop (~> 1.0)
     coderay (1.1.3)
     colorize (1.1.0)
-    concurrent-ruby (1.2.2)
+    concurrent-ruby (1.2.3)
     connection_pool (2.4.1)
-    diff-lcs (1.5.0)
+    debug (1.9.2)
+      irb (~> 1.10)
+      reline (>= 0.3.8)
+    diff-lcs (1.5.1)
     docile (1.4.0)
-    drb (2.2.0)
-      ruby2_keywords
-    factory_bot (6.4.5)
+    drb (2.2.1)
+    factory_bot (6.4.6)
       activesupport (>= 5.0.0)
-    i18n (1.14.1)
+    i18n (1.14.4)
       concurrent-ruby (~> 1.0)
-    json (2.7.1)
+    io-console (0.7.2)
+    irb (1.13.0)
+      rdoc (>= 4.0.0)
+      reline (>= 0.4.2)
+    json (2.7.2)
     language_server-protocol (3.17.0.3)
-    method_source (1.0.0)
-    minitest (5.20.0)
+    method_source (1.1.0)
+    minitest (5.22.3)
     mutex_m (0.2.0)
     parallel (1.24.0)
-    parser (3.3.0.2)
+    parser (3.3.1.0)
       ast (~> 2.4.1)
       racc
     pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
+    psych (5.1.2)
+      stringio
     racc (1.7.3)
     rainbow (3.1.1)
-    rake (13.1.0)
+    rake (13.2.1)
+    rdoc (6.6.3.1)
+      psych (>= 4.0.0)
     regexp_parser (2.9.0)
+    reline (0.5.5)
+      io-console (~> 0.5)
     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)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.0)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-mocks (3.12.6)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-support (3.12.1)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.1)
     rspec_junit_formatter (0.6.0)
       rspec-core (>= 2, < 4, != 2.12.0)
-    rubocop (1.59.0)
+    rubocop (1.63.4)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.2.2.4)
+      parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.30.0, < 2.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.30.0)
-      parser (>= 3.2.1.0)
+    rubocop-ast (1.31.3)
+      parser (>= 3.3.1.0)
     rubocop-capybara (2.20.0)
       rubocop (~> 1.41)
     rubocop-factory_bot (2.25.1)
       rubocop (~> 1.41)
-    rubocop-performance (1.20.2)
+    rubocop-performance (1.21.0)
       rubocop (>= 1.48.1, < 2.0)
-      rubocop-ast (>= 1.30.0, < 2.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
     rubocop-rake (0.6.0)
       rubocop (~> 1.0)
-    rubocop-rspec (2.26.1)
+    rubocop-rspec (2.29.2)
       rubocop (~> 1.40)
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)
+      rubocop-rspec_rails (~> 2.28)
+    rubocop-rspec_rails (2.28.3)
+      rubocop (~> 1.40)
     ruby-progressbar (1.13.0)
-    ruby2_keywords (0.0.5)
     simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
@@ -106,6 +120,7 @@ GEM
       terminal-table
     simplecov-html (0.12.3)
     simplecov_json_formatter (0.1.4)
+    stringio (3.1.0)
     terminal-table (3.0.2)
       unicode-display_width (>= 1.1.1, < 3)
     tzinfo (2.0.6)
@@ -120,6 +135,7 @@ PLATFORMS
 DEPENDENCIES
   bundler (~> 2.0)
   code-scanning-rubocop (~> 0.5)
+  debug (~> 1.8)
   factory_bot (~> 6.2)
   pdfh!
   pry (~> 0.14)
@@ -135,4 +151,4 @@ DEPENDENCIES
   versionomy (~> 0.5)
 
 BUNDLED WITH
-   2.5.4
+   2.5.10

data/README.md

@@ -18,20 +18,22 @@ gem install pdfh
 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
 ```
 
 #### Fedora
+
 ```bash
 sudo dnf install -y qpdf poppler-utils
 ```
 
 ## Usage
 
-After installing this gem you need to create your configuration file on your home folder.
-`pdfh.yml`
+After installing this gem you need to create your configuration file on your home folder. `pdfh.yml`
+
 ```yaml
 ---
 lookup_dirs:       # Directories where all pdf's are going to be analyzed
@@ -42,25 +44,22 @@ document_types:
     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
-    store_path: "{YEAR}/bank_docs"        # Relative path to copy this document
+    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
         month_offset: -1                     # [OPTIONAL] Integer (signed) value to adjust month
 ```
 
-Store Path supported placeholders:
-* `{YEAR}` 2022
+**Store Path** and **Name Template** supported placeholders:
 
-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
+- `{original}` Original filename
+- `{period}` 2022-01
+- `{year}` 2022
+- `{month}` 01
+- `{type}` document_type.name
+- `{subtype}` subtype.name if matched
+- `{extra}` day if provided/matched
 
 ## Development
 
@@ -77,6 +76,7 @@ gem install pdfh-*
 ```
 
 ### Conventional Commits
+
 ```bash
 npm install -g @commitlint/cli @commitlint/config-conventional
 commitlint --from origin --to @
@@ -97,7 +97,7 @@ Everyone interacting in the Pdfh project’s codebases, issue trackers, chat roo
 <!-- Links -->
 [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-img]: https://img.shields.io/badge/ruby-3.3-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

data/bin/run

@@ -2,6 +2,7 @@
 # frozen_string_literal: true
 
 require "bundler/setup"
+require "debug"
 require "pdfh"
 require "pry"
 

data/lib/pdfh/models/document.rb

@@ -3,8 +3,6 @@
 module Pdfh
   # Handles the PDF detected by the rules
   class Document
-    IDENT = 12
-
     attr_reader :text, :type, :file, :extra, :period
 
     # @param file [String]
@@ -40,12 +38,17 @@ module Pdfh
 
     # @return [void]
     def print_info_line(property, info)
-      Pdfh.ident_print property, info.to_s, color: :light_blue, width: IDENT
+      Pdfh.ident_print property, info.to_s, color: :light_blue, width: 12
     end
 
     # @return [String]
     def file_name_only
-      File.basename(@file, File.extname(@file))
+      File.basename(@file, file_extension)
+    end
+
+    # @return [String]
+    def file_extension
+      File.extname(@file)
     end
 
     # @return [String]
@@ -60,7 +63,7 @@ module Pdfh
 
     # @return [String]
     def type_name
-      @type&.name&.titleize || "N/A"
+      type&.name&.titleize || "N/A"
     end
 
     # @return [String]
@@ -68,23 +71,28 @@ module Pdfh
       @sub_type&.name&.titleize || "N/A"
     end
 
+    # @return [Hash{Symbol->String}]
+    def rename_data
+      {
+        original: file_name_only,
+        period: period.to_s,
+        year: period.year.to_s,
+        month: period.month.to_s,
+        type: type_name,
+        subtype: sub_type,
+        extra: extra || ""
+      }.freeze
+    end
+
     # @return [String]
     def new_name
-      template = @type.name_template
-      new_name = template
-                 .sub("{original}", file_name_only)
-                 .sub("{period}", period.to_s)
-                 .sub("{year}", period.year.to_s)
-                 .sub("{month}", period.month.to_s)
-                 .sub("{type}", type_name)
-                 .sub("{subtype}", sub_type)
-                 .sub("{extra}", extra || "")
-      "#{new_name}.pdf"
+      new_name = type.generate_new_name(rename_data)
+      "#{new_name}#{file_extension}"
     end
 
     # @return [String]
     def store_path
-      @type.store_path.gsub("{YEAR}", period.year.to_s)
+      type.generate_path(rename_data)
     end
 
     # @return [String]
@@ -95,6 +103,7 @@ module Pdfh
       "#{type.print_cmd} #{relative_path}"
     end
 
+    # @return [String (frozen)]
     def companion_files(join: false)
       return @companion unless join
 

data/lib/pdfh/models/document_type.rb

@@ -11,6 +11,11 @@ module Pdfh
       self.re_file = Regexp.new(re_file)
       self.re_date = Regexp.new(re_date)
       self.sub_types = extract_subtype(sub_types) if sub_types
+      @path_validator = RenameValidator.new(store_path)
+      @name_validator = RenameValidator.new(name_template)
+      return if @path_validator.valid? && @name_validator.valid?
+
+      raise_validators_error
     end
 
     # removes special characters from string and replaces spaces with dashes
@@ -35,6 +40,18 @@ module Pdfh
       pwd
     end
 
+    # @param values [Hash{Symbol->String}
+    # @return [String]
+    def generate_new_name(values)
+      @name_validator.gsub(values)
+    end
+
+    # @param values [Hash{Symbol->String}
+    # @return [String]
+    def generate_path(values)
+      @path_validator.gsub(values)
+    end
+
     private
 
     # @return [boolean]
@@ -51,5 +68,14 @@ module Pdfh
         DocumentSubType.new(name: name, month_offset: offset)
       end
     end
+
+    # @raise [ArgumentError] when called
+    # @return [void]
+    def raise_validators_error
+      template = "has invalid %<1>s. Unknown tokens: %<2>s"
+      path_errors = format(template, :store_path, @path_validator.unknown_list) unless @path_validator.valid?
+      name_errors = format(template, :name_template, @name_validator.unknown_list) unless @name_validator.valid?
+      raise ArgumentError, "Document type #{name.inspect} #{path_errors} #{name_errors}"
+    end
   end
 end

data/lib/pdfh/models/settings.rb

@@ -55,6 +55,8 @@ module Pdfh
       @document_types = doc_types.each_with_object({}) do |data, result|
         doc_type = DocumentType.new(data)
         result.store(doc_type.gid, doc_type)
+      rescue ArgumentError => e
+        Pdfh.error_print e.message, exit_app: false
       end
     end
   end

data/lib/pdfh/utils/opt_parser.rb

@@ -49,12 +49,12 @@ module Pdfh
       # @return [nil]
       def list_types
         settings = SettingsBuilder.build
-        ident = 4
+        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.inspect}"
+          puts "#{" " * ident}#{type.gid.ljust(max_width).yellow}  #{type.name}"
         end
         nil
       end

data/lib/pdfh/utils/rename_validator.rb

@@ -0,0 +1,50 @@
+# frozen_string_literal: true
+
+module Pdfh
+  # Validates the rename template, and generate new name
+  class RenameValidator
+    RENAME_TYPES = {
+      "original" => "No name change",
+      "period"   => "Year-Month",
+      "year"     => "Year",
+      "month"    => "Month",
+      "type"     => "Document Type name",
+      "subtype"  => "Document Subtype name",
+      "extra"    => "Extra data extracted from date_re"
+    }.freeze
+
+    attr_reader :template, :all, :unknown, :valid
+
+    # @param template [String]
+    # @return [self]
+    def initialize(template)
+      @template = template
+      @all = template.scan(/{([^}]+)}/).flatten.map(&:downcase)
+      @unknown = all - types
+      @valid = all - unknown
+    end
+
+    # @return [Array<String>]
+    def types
+      RENAME_TYPES.keys
+    end
+
+    # @return [Boolean]
+    def valid?
+      unknown.empty?
+    end
+
+    # @return [String]
+    def unknown_list
+      unknown.join(", ")
+    end
+
+    # @param values [Hash{Symbol->String}]
+    # @return [String (frozen)]
+    def gsub(values)
+      template
+        .gsub(/\{([^}]+)}/, &:downcase) # convert all text between {} to lowercase
+        .gsub("{", "%{") % values
+    end
+  end
+end

data/lib/pdfh/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pdfh
-  VERSION = "3.0.2"
+  VERSION = "3.1.0"
 end

data/lib/pdfh.rb

@@ -22,6 +22,7 @@ require_relative "pdfh/utils/month"
 require_relative "pdfh/utils/opt_parser"
 require_relative "pdfh/utils/options"
 require_relative "pdfh/utils/pdf_file_handler"
+require_relative "pdfh/utils/rename_validator"
 require_relative "pdfh/utils/settings_builder"
 
 require_relative "pdfh/main"

data/pdfh.gemspec

@@ -20,7 +20,7 @@ Gem::Specification.new do |spec|
 
   spec.metadata["homepage_uri"] = spec.homepage
   spec.metadata["source_code_uri"] = spec.homepage
-  spec.metadata["changelog_uri"] = URI.join(spec.homepage, "CHANGELOG.md").to_s
+  spec.metadata["changelog_uri"] = URI.join(spec.homepage, "/blob/master/CHANGELOG.md").to_s
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdfh
 version: !ruby/object:Gem::Version
-  version: 3.0.2
+  version: 3.1.0
 platform: ruby
 authors:
 - Isaias Piña
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-01-10 00:00:00.000000000 Z
+date: 2024-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: colorize
@@ -64,6 +64,7 @@ files:
 - lib/pdfh/utils/opt_parser.rb
 - lib/pdfh/utils/options.rb
 - lib/pdfh/utils/pdf_file_handler.rb
+- lib/pdfh/utils/rename_validator.rb
 - lib/pdfh/utils/settings_builder.rb
 - lib/pdfh/version.rb
 - pdfh.gemspec
@@ -74,7 +75,7 @@ metadata:
   allowed_push_host: https://rubygems.org
   homepage_uri: https://github.com/iax7/pdfh
   source_code_uri: https://github.com/iax7/pdfh
-  changelog_uri: https://github.com/iax7/CHANGELOG.md
+  changelog_uri: https://github.com/blob/master/CHANGELOG.md
   rubygems_mfa_required: 'true'
 post_install_message:
 rdoc_options: []
@@ -91,7 +92,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.3
+rubygems_version: 3.5.7
 signing_key:
 specification_version: 4
 summary: Organize PDF files