apacify 0.2.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0ff691ed803af1a67b7223e0f6c056a00852b57b9ab6030a9fb5fac548bd1a07
-  data.tar.gz: e6522ee720d3fe658f2b80b45042c8f44e97651cafde412cf7ad9cf1f58a5c5c
+  metadata.gz: 7d47b70beff46216daa1ff9aef7c7fe770368089d28b79bc0dc094ab4091252f
+  data.tar.gz: 862dae468db6d27bbd09e05056c4861950d8ce5629f27cc5c41cdc6eed336559
 SHA512:
-  metadata.gz: f485f2c6d7d2a416815b695ff76e264e572c6fc6fc0c2f0c3e8b0957d949869bd01b0365e03a3e34a19aa539d102bc6c9bd791beb68fb094eeb3b4d6ed4ef873
-  data.tar.gz: '0228bcd7a24f7d27cd84c1108c63897070d132a3d09e2312d0d974ed18602cb3674f0b8e12c5699c02fa5f548e984c248cb84cfbd67c7e7ec7feb1eddf1c1681'
+  metadata.gz: f3a52d9a875a59bd0d642aa9f57703a017ddd6f2fe39c30942bd674c24af783ecba4c84f7f09f74751b6b451cf6078c518f71b71c8fac97bdace5931be7afb40
+  data.tar.gz: 9244be4b802c94724b124cfc32c08bbc3ad7ac3f679db0b855a13174376fa3041587d60143985c3772996e26a2b1c2e8f58ebbd32d18218a8cef856229279fef

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## [0.4.0] - 2026-03-01
+
+- Lowercase second element after hyphenated prefixes per APA 7th ed (e.g., Mid-century, Pre-war)
+- Preserve proper nouns after prefixes when input is already capitalized (e.g., Pre-Christian)
+
+## [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

data/CLAUDE.md

@@ -0,0 +1,36 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project
+
+Apacify is a Ruby gem that converts strings to APA-style title case. It extends `String` with `.apacify(ignore: [])`.
+
+## Commands
+
+```bash
+rake              # Run tests + linter (default)
+rake test         # Tests only (minitest)
+rake standard     # Lint only (Standard/RuboCop)
+ruby -Ilib test/test_apacify.rb                          # Run test file directly
+ruby -Ilib test/test_apacify.rb -n test_method_name      # Single test
+bin/console       # IRB with gem loaded
+```
+
+## Architecture
+
+Entry point: `lib/apacify.rb` — loads `config/minor.yml`, defines `Apacify.titleize`, patches `String#apacify`.
+
+Pipeline: **input string → Tokenizer → Token[] → Titleizer → output string**
+
+- `Tokenizer` splits on word boundaries (spaces + punctuation), implements `Enumerable`
+- `Token` represents a single unit; knows if it's a minor word, punctuation, first/last, Roman numeral, hyphenated
+- `Titleizer` walks tokens and applies capitalization rules via `should_capitalize?`
+
+## APA Title Case Rules
+
+1. Always capitalize first word and words after sentence-ending punctuation (`:`, `.`, `!`, `?`, `—`)
+2. Capitalize all major words (4+ letters always qualify)
+3. Minor words (≤3 letters, listed in `config/minor.yml`) stay lowercase unless rule 1 applies
+4. Hyphenated parts each get capitalized independently
+5. `ignore:` parameter preserves original case (case-sensitive matching)

data/lib/apacify/titleizer.rb

@@ -1,5 +1,3 @@
-require "yaml"
-
 module Apacify
   class Titleizer
     attr_reader :tokens, :ignore
@@ -27,7 +25,7 @@ module Apacify
       return false if ignored_word?(token)
 
       token.first? ||
-        tokens.previous(token).sentence_ending_punctuation? ||
+        tokens.previous_punctuation(token)&.sentence_ending_punctuation? ||
         !token.minor_word? ||
         token.long?
     end
@@ -39,12 +37,8 @@ module Apacify
       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
+        return true if token_string == ignore_word
 
-        # 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

data/lib/apacify/token.rb

@@ -1,20 +1,40 @@
-require "forwardable"
-
 module Apacify
   class Token
-    extend Forwardable
-
     attr_reader :string, :index
 
-    def_delegator :string, :downcase
-
     def initialize(string, index)
       @string = string
       @index = index
     end
 
     def capitalize_word_parts
-      string.downcase.gsub(/(^|-)(\w)/) { |match| $1 + $2.upcase }
+      parts = string.split("-", -1)
+      after_prefix = false
+      parts.map! do |part|
+        word = part[/\w+/]
+        unless word
+          after_prefix = false
+          next part
+        end
+
+        prefix = part[0, part.index(word)]
+        suffix = part[(prefix.length + word.length)..]
+
+        capitalized = if all_caps?(word)
+          word
+        elsif roman_numeral?(word)
+          word.upcase
+        elsif after_prefix
+          capitalized?(word) ? word : word.downcase
+        else
+          word.downcase.capitalize
+        end
+
+        after_prefix ||= PREFIXES.include?(word.downcase)
+
+        "#{prefix}#{capitalized}#{suffix}"
+      end
+      parts.join("-")
     end
 
     def first?
@@ -38,7 +58,7 @@ module Apacify
     end
 
     def sentence_ending_punctuation?
-      string.match?(/[.!?:—()]+\s*/)
+      string.match?(PUNCTUATION_PATTERN)
     end
 
     def to_s
@@ -46,7 +66,21 @@ module Apacify
     end
 
     def whitespace_or_punctuation?
-      string.match?(/\s+|[.!?:—()]+\s*/)
+      string.match?(/\A(?:\s|#{PUNCTUATION_CHARS})+\s*\z/o)
+    end
+
+    private
+
+    def all_caps?(word)
+      word.match?(/\A[A-Z]+\z/)
+    end
+
+    def capitalized?(word)
+      word[0] == word[0].upcase
+    end
+
+    def roman_numeral?(word)
+      word.match?(/\A(?:M{0,4}(?:CM|CD|D?C{0,3})(?:XC|XL|L?X{0,3})(?:IX|IV|V?I{0,3}))\z/i)
     end
   end
 end

data/lib/apacify/tokenizer.rb

@@ -2,13 +2,13 @@ module Apacify
   class Tokenizer
     include Enumerable
 
-    attr_reader :tokens, :ignore
+    attr_reader :tokens
 
     def initialize(string)
       @tokens = string
         .split(word_boundary_pattern)
         .map
-        .with_index(&instantiate)
+        .with_index { |token, index| Token.new(token, index) }
     end
 
     def [](index)
@@ -21,18 +21,21 @@ module Apacify
       tokens.each(&block)
     end
 
-    def previous(token)
-      tokens[token.index - 1]
+    def previous_punctuation(token)
+      index = token.index - 1
+      while index >= 0
+        prev_token = tokens[index]
+        return prev_token if prev_token.sentence_ending_punctuation?
+        break unless prev_token.whitespace_or_punctuation?
+        index -= 1
+      end
+      nil
     end
 
     private
 
-    def instantiate
-      ->(token, index) { Token.new(token, index) }
-    end
-
     def word_boundary_pattern
-      /(\s+|[.!?:—()]+\s*)/
+      WORD_BOUNDARY_PATTERN
     end
   end
 end

data/lib/apacify/version.rb

@@ -1,3 +1,3 @@
 module Apacify
-  VERSION = "0.2.0"
+  VERSION = "0.4.0"
 end

data/lib/apacify.rb

@@ -1,13 +1,25 @@
-require_relative "apacify/error"
 require_relative "apacify/titleizer"
 require_relative "apacify/token"
 require_relative "apacify/tokenizer"
 require_relative "apacify/version"
 
 module Apacify
-  MINOR_WORDS = YAML.safe_load_file(
-    File.join(__dir__, "..", "config", "minor.yml")
-  ).freeze
+  MINOR_WORDS = %w[
+    a an and as at but by de for from
+    if in nor of off on or out pas per
+    so the to up via with yet
+  ].freeze
+
+  PREFIXES = %w[
+    anti co counter ex extra infra inter intra
+    macro mega meta micro mid mini multi neo
+    non over post pre pro proto pseudo quasi
+    re semi sub super supra trans ultra un under
+  ].to_set.freeze
+
+  PUNCTUATION_CHARS = '[.!?:—()\[\]]'
+  PUNCTUATION_PATTERN = /#{PUNCTUATION_CHARS}+\s*/
+  WORD_BOUNDARY_PATTERN = /(\s+|#{PUNCTUATION_CHARS}+\s*)/
 
   def self.titleize(string, ignore: [])
     Titleizer.new(string, ignore:).titleize

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: apacify
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Ariel Rzezak
@@ -19,13 +19,12 @@ extra_rdoc_files: []
 files:
 - ".standard.yml"
 - CHANGELOG.md
+- CLAUDE.md
 - CODE_OF_CONDUCT.md
 - LICENSE.txt
 - README.md
 - Rakefile
-- config/minor.yml
 - lib/apacify.rb
-- lib/apacify/error.rb
 - lib/apacify/titleizer.rb
 - lib/apacify/token.rb
 - lib/apacify/tokenizer.rb
@@ -51,7 +50,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.7.0
+rubygems_version: 4.0.3
 specification_version: 4
 summary: Convert strings to title case following APA style guidelines.
 test_files: []

data/config/minor.yml

@@ -1,28 +0,0 @@
-- "a"
-- "an"
-- "and"
-- "as"
-- "at"
-- "but"
-- "by"
-- "de"
-- "for"
-- "for"
-- "from"
-- "if"
-- "in"
-- "nor"
-- "of"
-- "off"
-- "on"
-- "or"
-- "out"
-- "pas"
-- "per"
-- "so"
-- "the"
-- "to"
-- "up"
-- "via"
-- "with"
-- "yet"

data/lib/apacify/error.rb

@@ -1,4 +0,0 @@
-module Apacify
-  class Error < StandardError
-  end
-end