medieval_latina 3.1.1 → 3.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f38ebdf6480281f444c3142a6c0dd8ef3b805c34ab45710dd6af46b904f5bbc5
-  data.tar.gz: ec33854ab71c933af1da4fe44055ac94d0cf517894a60ebd9addbf42058ee7d5
+  metadata.gz: 47f39ae4c5ce8d0b6b624beae267c9a8e00b2ac44e6c09686e34e825d8671dcd
+  data.tar.gz: a8f8ca9f9357a0453429104a1d8e8423c63dbd3ab4360277993c29c46cb7573f
 SHA512:
-  metadata.gz: 951bb7a9259f812296866752be7ff0b1a4526bf0a7521b72c6465de4e2a922887922f443070b8b990e4a57a8a48ee8e76a0c67b78720598890ab71173379e924
-  data.tar.gz: 363b7fe7a6331397c0e11ade30f4c4ef6db456d3aac200919e308b318f08941df25c552fa095f4be6b3937c19a9ffd48e53fe1b172b83999a4b4e224506a837f
+  metadata.gz: d1e79d2981bdc926e0640de05a3d870ea907075f6c3c822be135c89f2060b1abaa386fe50fb4e61325e7d799ab7d216b33329ec58b35b6e9520bc4c1b7367300
+  data.tar.gz: 64dd8015e355efc41bdc754f3720c204dda502d64c0665dfed7830063f8ececb09f5eefefcfd9e520ee105676695f525a6fc1752e4be61e41a2e16f0c1b2eac9

data/.github/workflows/claude-code-review.yml

@@ -0,0 +1,57 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Optional: Filter by PR author
+    # if: |
+    #   github.event.pull_request.user.login == 'external-contributor' ||
+    #   github.event.pull_request.user.login == 'new-developer' ||
+    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
+    
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          prompt: |
+            REPO: ${{ github.repository }}
+            PR NUMBER: ${{ github.event.pull_request.number }}
+
+            Please review this pull request and provide feedback on:
+            - Code quality and best practices
+            - Potential bugs or issues
+            - Performance considerations
+            - Security concerns
+            - Test coverage
+            
+            Use the repository's CLAUDE.md for guidance on style and conventions. Be constructive and helpful in your feedback.
+
+            Use `gh pr comment` with your Bash tool to leave your review as a comment on the PR.
+          
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://docs.claude.com/en/docs/claude-code/sdk#command-line for available options
+          claude_args: '--allowed-tools "Bash(gh issue view:*),Bash(gh search:*),Bash(gh issue list:*),Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*),Bash(gh pr list:*)"'
+

data/.github/workflows/claude.yml

@@ -0,0 +1,50 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+      actions: read # Required for Claude to read CI results on PRs
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+
+          # Optional: Give a custom prompt to Claude. If this is not specified, Claude will perform the instructions specified in the comment that tagged it.
+          # prompt: 'Update the pull request description to include a summary of changes.'
+
+          # Optional: Add claude_args to customize behavior and configuration
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://docs.claude.com/en/docs/claude-code/sdk#command-line for available options
+          # claude_args: '--model claude-opus-4-1-20250805 --allowed-tools Bash(gh pr:*)'
+

data/.github/workflows/tests.yml

@@ -22,6 +22,7 @@ jobs:
           - '3.2'
           - '3.3'
           - '3.4'
+          - '4.0'
         allow_failures:
           - false
     env:

data/.tool-versions

@@ -1,2 +1,2 @@
 nodejs 24.2.0
-ruby 3.4.1
+ruby 4.0.5

data/AGENTS.md

@@ -0,0 +1,60 @@
+# AGENTS.md
+
+This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
+
+## Development Commands
+
+- **Setup**: `bin/setup` - Install dependencies with bundle install
+- **Tests**: `rake spec` or `bundle exec rspec` - Run the full test suite
+- **Linting**: `bin/lint` - Run StandardRB linter and jsonlint on dictionary.json
+- **Build lexicons**: `bin/build` - Regenerate PLS lexicon files from dictionary.json
+- **Console**: `bin/console` - Interactive prompt for experimentation
+- **Install gem locally**: `bundle exec rake install`
+- **Release**: `bundle exec rake release` (after updating version.rb)
+
+## Architecture Overview
+
+This is a Ruby gem that converts medieval Latin text to phonetic English for text-to-speech engines. The architecture consists of:
+
+### Core Components
+
+- **MedievalLatina class** (`lib/medieval_latina.rb`): Main interface with class methods for text conversion and linguistic analysis
+  - `MedievalLatina[text]` - Primary conversion method
+  - Part-of-speech helpers: `verb?`, `noun?`, `adjective?`, `adverb?`
+  - `pronunciations_for(words)` - Extract IPA pronunciations for lexicon building
+
+- **Dictionary system** (`data/dictionary.json`): Large JSON file containing Latin words with metadata including:
+  - IPA pronunciations
+  - Part of speech classifications
+  - Custom pronunciation overrides
+
+- **Lexicon generation** (`lib/medieval_latina/lexicon_builder.rb`, `lib/medieval_latina/lexicon.rb`): Creates PLS (Pronunciation Lexicon Specification) files for AWS Polly and other TTS engines
+
+### Phonetic Conversion Logic
+
+The main conversion algorithm handles:
+- Vowel teams: ae→ay, oe→ay, au→ou
+- Consonant transformations: c→ch/k (soft/hard), g→j/g, j→y, t→ts/t, x→ks
+- Consonant teams: gn→n-y, qu→kw
+- Text preprocessing with I18n transliteration
+
+### Data Flow
+
+1. Text input → word tokenization → dictionary lookup
+2. If word has custom pronunciation → use it
+3. Otherwise → apply phonetic transformation rules
+4. Rejoin with proper punctuation spacing
+
+## Key Files
+
+- `lib/medieval_latina.rb` - Main conversion logic and API
+- `data/dictionary.json` - Latin word database (400KB+)
+- `bin/build` - Splits dictionary into multiple PLS files in lexicons/ directory
+- `.standard.yml` - StandardRB configuration (Ruby 3.2, parallel linting)
+- `medieval_latina.gemspec` - Gem specification (requires Ruby >= 3.2.0)
+
+## Testing
+
+- RSpec test suite in `spec/`
+- Configuration in `.rspec` with documentation format
+- Run specific tests: `bundle exec rspec spec/specific_spec.rb`

data/Gemfile

@@ -2,3 +2,8 @@ source "https://rubygems.org"
 
 # Specify your gem's dependencies in medieval_latina.gemspec
 gemspec
+
+# `logger` stopped being autoloaded under Bundler once it became a bundled gem
+# (Ruby 3.4+) and is no longer in Ruby 4.0's default set. jsonlint requires it
+# without declaring the dependency, so declare it here for `bundle exec jsonlint`.
+gem "logger"

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    medieval_latina (3.1.1)
+    medieval_latina (3.2.0)
       i18n
 
 GEM
@@ -19,8 +19,9 @@ GEM
       optimist (~> 3)
     language_server-protocol (3.17.0.3)
     lint_roller (1.1.0)
+    logger (1.7.0)
     mini_portile2 (2.8.9)
-    nokogiri (1.18.9)
+    nokogiri (1.19.3)
       mini_portile2 (~> 2.8.2)
       racc (~> 1.4)
     oj (3.16.5)
@@ -88,6 +89,7 @@ PLATFORMS
 
 DEPENDENCIES
   jsonlint
+  logger
   medieval_latina!
   nokogiri
   rake (~> 12.0)

data/README.md

@@ -3,6 +3,22 @@
 There are good text-to-speech engines for English and classical Latin, but none for medieval Latin.
 `MedievalLatina` converts Latin text to a kind of phonetic spelling that can be read by English language text-to-speech engines.
 
+## Hear it
+
+A line of the Lord's Prayer — *Pater noster qui es in caelis* — spoken by Amazon Polly using this gem's IPA pronunciation lexicon, so you hear MedievalLatina's pronunciation rather than raw Latin:
+
+▶️ **[Play the sample](https://github.com/jaysonvirissimo/medieval_latina/raw/master/audio/pater-noster.mp3)** (`audio/pater-noster.mp3`)
+
+<!-- Inline player: drag-and-drop audio/pater-noster.mp3 into a GitHub PR/comment composer to
+     mint a https://github.com/user-attachments/assets/<id> URL, then paste that URL on its own
+     line directly below to render an inline audio player in the rendered README. -->
+
+- **Text:** *Pater noster qui es in caelis* — "Our Father, who art in heaven", the traditional Latin Lord's Prayer (public domain).
+- **Gem output:** `MedievalLatina["Pater noster qui es in caelis"]` → `"pah-tare nohstayr kwee es een chaylees"`.
+- **Voice:** Amazon Polly **Bianca** (Italian, `it-IT`, neural engine), driven by MedievalLatina's IPA via a PLS lexicon.
+- **Reproduce:** `ruby -Ilib bin/sample_audio Bianca` (requires AWS credentials in the environment and the `aws-sdk-polly` gem).
+- **Provenance:** audio generated with Amazon Polly on 2026-06-07; Polly output may be used and redistributed under the [AWS Service Terms](https://aws.amazon.com/service-terms/).
+
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -40,7 +56,8 @@ responsiveVoice.speak(sentence, "UK English Female");
 polly = Aws::Polly::Client.new
 s3 = Aws::S3::Client.new
 
-sentence = "PATER NOSTER qui es in caelis"
+# Lowercase so the text matches the lexicon's (case-sensitive) lowercase graphemes.
+sentence = "pater noster qui es in caelis"
 
 words = sentence.split(" ")
 pronunciations = MedievalLatina.pronunciations_for(words)

data/bin/sample_audio

@@ -0,0 +1,76 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+# Generates the README's spoken sample with Amazon Polly, using MedievalLatina's
+# IPA pronunciations via a PLS lexicon so Polly pronounces the Latin our way.
+#
+# Usage:
+#   AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY must be in the environment.
+#   aws-sdk-polly must be available, e.g. run through a bundle that provides it:
+#     BUNDLE_GEMFILE=/path/to/aws/Gemfile bundle exec ruby -Ilib bin/sample_audio Joanna
+#   Output: tmp/sample-<voice>.mp3
+#
+# Credentials are read from the AWS SDK default chain only; they are never echoed,
+# logged, or written to disk.
+
+require "medieval_latina"
+require "aws-sdk-polly"
+require "fileutils"
+
+# us-east-1 is where the voices/engines below are available; override via env if needed.
+REGION = ENV["AWS_REGION"] || ENV["AWS_DEFAULT_REGION"] || "us-east-1"
+# Polly matches lexicon graphemes case-sensitively and our graphemes are lowercase,
+# so synthesize from lowercased text (the README still shows it capitalized).
+SENTENCE = "pater noster qui es in caelis"
+
+# Polly applies a lexicon only when its xml:lang matches the voice's language, and
+# lexicons work on the standard/neural engines (not generative). Each voice below is
+# paired with the matching lexicon language and a lexicon-capable engine.
+VOICES = {
+  "Joanna" => {lang: "en-US", engine: "neural"},
+  "Matthew" => {lang: "en-US", engine: "neural"},
+  "Danielle" => {lang: "en-US", engine: "neural"},
+  "Stephen" => {lang: "en-US", engine: "neural"},
+  "Bianca" => {lang: "it-IT", engine: "neural"},
+  "Carla" => {lang: "it-IT", engine: "standard"},
+  "Giorgio" => {lang: "it-IT", engine: "standard"}
+}.freeze
+
+LEXICON_NAMES = {"en-US" => "MedievalLatinaEnUs", "it-IT" => "MedievalLatinaItIt"}.freeze
+
+abort "Usage: #{$PROGRAM_NAME} <voice>\nChoices: #{VOICES.keys.join(", ")}" if ARGV.empty?
+
+voice = ARGV[0]
+config = VOICES[voice]
+abort "Unknown voice #{voice.inspect}. Choose one of: #{VOICES.keys.join(", ")}" unless config
+
+# Build the {word => IPA} map from the gem's dictionary for every word in the sentence.
+pronunciations = MedievalLatina.pronunciations_for(SENTENCE.split)
+
+# Build a lexicon whose xml:lang matches the voice's language (Polly applies a lexicon
+# only when the languages match).
+lang = config[:lang]
+lexicon_name = LEXICON_NAMES[lang]
+lexicon = MedievalLatina::LexiconBuilder.new(pronunciations, lang: lang).call.to_s
+
+polly = Aws::Polly::Client.new(region: REGION)
+polly.put_lexicon(name: lexicon_name, content: lexicon) # idempotent; overwrites
+
+FileUtils.mkdir_p("tmp")
+output_path = "tmp/sample-#{voice}.mp3"
+
+# Always remove the lexicon from the AWS account, even if synthesis/write raises.
+begin
+  response = polly.synthesize_speech(
+    text: SENTENCE,
+    lexicon_names: [lexicon_name],
+    voice_id: voice,
+    engine: config[:engine],
+    output_format: "mp3"
+  )
+  File.binwrite(output_path, response.audio_stream.read)
+ensure
+  polly.delete_lexicon(name: lexicon_name)
+end
+
+puts "#{voice} (#{lang}, #{config[:engine]}) -> #{output_path} (#{File.size(output_path)} bytes)"