apacify 0.1.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c55a078f06803a6268b5df123a09667dba0a6ea7ab821f31578a79e0a4d10426
-  data.tar.gz: c648ed8ae5233ee814da8c664c148ca207efabef7cfe9d8b9b4848d00b205e9a
+  metadata.gz: 1388346971f57a63a007b6e32798716f99dd1b5d2dcc1153624a495d7a6a0146
+  data.tar.gz: c58d4589773808ecb7d2af6c44322465ba1bab43f0704e9dbdbe6cb2e7fe6fa4
 SHA512:
-  metadata.gz: 3b437c269f63a8b0a6c279765a12f2d36dd7c5307431e28baba9913c2d020cf9abbc8646971f722f9da78a9115069f03d95402b343cca7e37c913214ee06be63
-  data.tar.gz: 7ec2fc67b96ad14d5f5d27eece0d42ae1e6e8db45217c64c5d9be8b5b03998f205fc6123ef64242de7957f571f8ca1135f0264a617c5a3d452364af8eeafb33b
+  metadata.gz: aea431081a8ce3ede8f03eb78b7d564f2f86f07cb86e4f695a1b1c14bc1bc44a1efbf91d00105a914dab5e7d31a3b9f0b91b0df5c0805a1978a9546821bcdd45
+  data.tar.gz: 3d4b59393c0b60b30ad0d308724fe8769cbfdfb39d3cb8c675ce3004b32419c71099f2891f69f89f2fb9d2b035ab9c41e142e9a090d8d16f31f36552add8dc0a

data/CHANGELOG.md

@@ -1,4 +1,10 @@
-## [Unreleased]
+## [0.3.0] - 2025-08-30
+
+- Support Roman numerals
+
+## [0.2.0] - 2025-08-30
+
+- Add ability to specify words to ignore during title case conversion
 
 ## [0.1.0] - 2025-07-26
 

data/README.md

@@ -2,6 +2,16 @@
 
 A Ruby gem that converts strings to proper title case following APA (American Psychological Association) style guidelines. Apacify capitalizes strings while keeping minor words (articles, prepositions, conjunctions) lowercase, except when they appear at the beginning or end of the title, or after sentence-ending punctuation.
 
+## APA's Title Case Guide
+
+1. Capitalize the first word of the title/heading and of any subtitle/subheading;
+2. Capitalize all "major" words (nouns, verbs, adjectives, adverbs, and pronouns) in the title/heading, including the second part of hyphenated major words (e.g., Self-Report not Self-report); and
+3. Capitalize all words of four letters or more.
+
+This boils down to using lowercase only for "minor" words of three letters or fewer, namely, for conjunctions (words like and, or, nor, and but), articles (the words a, an, and the), and prepositions (words like as, at, by, for, in, of, on, per, and to), as long as they aren't the first word in a title or subtitle. You can see examples of title case in our post on reference titles.
+
+[Source](https://blog.apastyle.org/apastyle/2012/03/title-case-and-sentence-case-capitalization-in-apa-style.html)
+
 ## Installation
 
 Install the gem and add to the application's Gemfile by executing:
@@ -46,7 +56,21 @@ Hyphenated words are handled properly:
 # => "Mother-In-Law"
 ```
 
-### Features
+You can specify words to ignore during title case conversion. Ignored words will preserve their original case and bypass all capitalization rules:
+
+```ruby
+"tokyo night (feat. evangeline)".apacify(ignore: "feat.")
+# => "Tokyo Night (feat. Evangeline)"
+
+"the quick brown fox".apacify(ignore: ["quick", "fox"])
+# => "The quick Brown fox"
+
+# Case-sensitive matching: "FEAT." != "feat."
+"tokyo night (FEAT. evangeline)".apacify(ignore: "feat.")
+# => "Tokyo Night (Feat. Evangeline)"  # FEAT. not ignored, gets capitalized
+```
+
+## Features
 
 - Follows APA style title case rules
 - Capitalizes first and last words regardless of length
@@ -55,6 +79,7 @@ Hyphenated words are handled properly:
 - Handles hyphenated words correctly
 - Preserves original spacing and punctuation
 - Words 4 letters or longer are always capitalized
+- Ignore specific words from capitalization rules
 
 ## Comparison with Rails' `#titleize`
 

data/lib/apacify/titleizer.rb

@@ -2,15 +2,18 @@ require "yaml"
 
 module Apacify
   class Titleizer
-    attr_reader :tokens
+    attr_reader :tokens, :ignore
 
-    def initialize(string)
+    def initialize(string, ignore: [])
       @tokens = Tokenizer.new(string)
+      @ignore = wrap(ignore).reject(&:empty?)
     end
 
     def titleize
       tokens.map do |token|
-        if should_capitalize?(token)
+        if token.in?(ignore)
+          token
+        elsif should_capitalize?(token)
           token.capitalize_word_parts
         else
           token
@@ -21,10 +24,47 @@ module Apacify
     private
 
     def should_capitalize?(token)
+      return false if ignored_word?(token)
+
       token.first? ||
         tokens.previous(token).sentence_ending_punctuation? ||
         !token.minor_word? ||
         token.long?
     end
+
+    def ignored_word?(token)
+      return false if ignore.empty?
+      return false if token.whitespace_or_punctuation?
+
+      token_string = token.string.strip
+
+      ignore.any? do |ignore_word|
+        # Case-sensitive direct match with full token string
+        if token_string == ignore_word
+          return true
+        end
+
+        # Check if ignore_word contains punctuation and token matches the word part (case-sensitive)
+        if ignore_word.match?(/[.!?:—()]/)
+          word_part = ignore_word.gsub(/[.!?:—()]+/, "")
+          if token_string == word_part
+            return true
+          end
+        end
+
+        false
+      end
+    end
+
+    def wrap(object)
+      case object
+      when nil
+        []
+      when Array
+        object.map(&:to_s)
+      else
+        [object]
+      end
+    end
   end
 end

data/lib/apacify/token.rb

@@ -14,13 +14,25 @@ module Apacify
     end
 
     def capitalize_word_parts
-      string.gsub(/(^|-)(\w)/) { |match| $1 + $2.upcase }
+      string.downcase.gsub(/(^|-)(\w+)/) do |match|
+        prefix = $1
+        word = $2
+        if roman_numeral?(word)
+          prefix + word.upcase
+        else
+          prefix + word.capitalize
+        end
+      end
     end
 
     def first?
       index == 0
     end
 
+    def in?(array)
+      array.include?(string)
+    end
+
     def letters
       string.downcase.gsub(/[^\w']/, "")
     end
@@ -44,5 +56,16 @@ module Apacify
     def whitespace_or_punctuation?
       string.match?(/\s+|[.!?:—()]+\s*/)
     end
+
+    private
+
+    def roman_numeral?(word)
+      # Only letters used in roman numerals
+      return false unless word.match?(/\A[ivxlcdm]+\z/)
+
+      # Roman numeral pattern - matches valid combinations
+      # This pattern handles: 1-3999 (I-MMMCMXCIX)
+      word.match?(/\A(?=[mdclxvi])m{0,4}(cm|cd|d?c{0,3})?(xc|xl|l?x{0,3})?(ix|iv|v?i{0,3})?\z/)
+    end
   end
 end

data/lib/apacify/tokenizer.rb

@@ -2,7 +2,7 @@ module Apacify
   class Tokenizer
     include Enumerable
 
-    attr_reader :tokens
+    attr_reader :tokens, :ignore
 
     def initialize(string)
       @tokens = string

data/lib/apacify/version.rb

@@ -1,3 +1,3 @@
 module Apacify
-  VERSION = "0.1.0"
+  VERSION = "0.3.0"
 end

data/lib/apacify.rb

@@ -9,13 +9,13 @@ module Apacify
     File.join(__dir__, "..", "config", "minor.yml")
   ).freeze
 
-  def self.titleize(string)
-    Titleizer.new(string).titleize
+  def self.titleize(string, ignore: [])
+    Titleizer.new(string, ignore:).titleize
   end
 end
 
 class String
-  def apacify
-    Apacify.titleize(self)
+  def apacify(ignore: [])
+    Apacify.titleize(self, ignore:)
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: apacify
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Ariel Rzezak