interscript 0.1.6 → 0.1.7

data/bin/interscript

@@ -1,41 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'rubygems'
-
-# resolve bin path, ignoring symlinks
-require 'pathname'
-bin_file = Pathname.new(__FILE__).realpath
-
-# add self to libpath
-$LOAD_PATH.unshift File.expand_path("../../lib", bin_file)
-
-# Fixes https://github.com/rubygems/rubygems/issues/1420
-require 'rubygems/specification'
-
-class Gem::Specification
-  def this; self; end
-end
-
-require 'interscript/command'
-
-if ARGV.any? && !Interscript::Command.all_tasks.key?(ARGV.first)
-  ARGV.unshift :translit
-end
-Interscript::Command.start ARGV
-
-# if ARGV.empty?
-#   puts "write source file, source format, and output file"
-# else
-#   args = Hash[ARGV.flat_map { |s| s.scan(/--?([^=\s]+)(?:=(\S+))?/) }]
-#   input = ARGV[0]
-#   system_code = args["system"]
-#   output_file = args["output"]
-
-#   raise "Please enter the system code with --system={system_code}" unless system_code
-
-#   if output_file
-#     Interscript.transliterate_file(system_code, input, output_file)
-#   else
-#     puts Interscript.transliterate(system_code, IO.read(input))
-#   end
-# end

data/bin/rspec

@@ -1,29 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-#
-# This file was generated by Bundler.
-#
-# The application 'rspec' is installed as part of a gem, and
-# this file is here to facilitate running it.
-#
-
-require "pathname"
-ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
-  Pathname.new(__FILE__).realpath)
-
-bundle_binstub = File.expand_path("../bundle", __FILE__)
-
-if File.file?(bundle_binstub)
-  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
-    load(bundle_binstub)
-  else
-    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
-Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
-  end
-end
-
-require "rubygems"
-require "bundler/setup"
-
-load Gem.bin_path("rspec-core", "rspec")

data/bin/setup

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-IFS=$'\n\t'
-set -vx
-
-bundle install
-
-# Do any other automated setup that you need to do here

data/lib/interscript-opal.rb

@@ -1,2 +0,0 @@
-require "opal"
-require "interscript"

data/lib/interscript/opal_map_translate.rb

@@ -1,12 +0,0 @@
-module Interscript
-  module OpalMapTranslate
-    def self.translate_regexp(src)
-      src.
-        gsub('[:upper:]', '\\\\\\\\p{Lu}').
-        gsub('[:lower:]', '\\\\\\\\p{Ll}').
-        gsub('[:alpha:]', '\\\\\\\\p{L}').
-        gsub('(?<=[\\\\p{Lu}])?', '(?<=[\\\\\\\\p{Lu}]?)').
-        gsub('(?=[\\\\p{Lu}])?', '(?=[\\\\\\\\p{Lu}]?)')
-    end
-  end
-end

data/maps/alalc-hin-Deva-Latn-2020.yaml

@@ -1,159 +0,0 @@
----
-authority_id: alalc
-id: 2020
-language: hin
-source_script: Deva
-destination_script: Latn
-name: Hindi Romanization, 2020
-url: https://www.loc.gov/catdir/cpso/romanization/hindi.pdf
-creation_date: 2020
-description: |
-  ALA-LC Romanization table for Hindi
-
-notes:
-
-  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
-    vowels following a consonant can be found in grammars; no distinction between the two is
-    made in transliteration.
-
-  - |
-    The vowel a is implicit after all consonants and consonant clusters and is supplied in
-    transliteration, with the following exceptions:
-
-    a) when another vowel is indicated by its appropriate sign; and
-    b) when the absence of any vowel is indicated by the subscript sign ( ◌् ) called halanta or
-       virāma.
-
-  - |
-    Exception: Anusvāra is transliterated by:
-
-    a) ṅ before gutturals,
-    b) ñ before palatals,
-    c) ṇ before cerebrals,
-    d) n before dentals, and
-    e) m before labials.
-
-  - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
-    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
-
-  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
-
-tests:
-  - source: "हम"
-    expected: "hama"
-  - source: "मीन"
-    expected: "maīna"
-  - source: "औसत"
-    expected: "ăusata"
-  - source: "माँऽऽऽ!"
-    expected: "maān̐’’’!"
-  - source: "माँ"
-    expected: "maām̐"
-
-
-
-map:
-
-  rules:
-    # note[4]
-    - pattern: (?<=)\u0901(?=\b)
-      result: "m̐"
-
-  characters:
-
-    # I. Vowels and Diphthongs (see Note 1)
-
-    'अ': 'a'
-    'आ': 'ā'
-    'इ': 'i'
-    'ई': 'ī'
-    'उ': 'u'
-    'ऊ': 'ū'
-    'ऋ': 'ṛ'
-    'ॠ': 'ṝ'
-    'ऌ': 'ḹ'
-    'ॳ': 'ĕ'
-    'ए': 'e'
-    'ॲ': 'ê'
-    'अै': 'ai'
-    'ऐ': 'ai'
-    'ऒ': 'ŏ'
-    'ओ': 'o'
-    'ऑ': 'ô'
-    'औ': 'ău'
-
-    # II. Consonants (see Note 2)
-    # Gutturals
-    'क': 'ka'
-    'ख': 'kha'
-    'ग': 'ga'
-    'घ': 'gha'
-    'ङ': 'ṅa'
-
-    # Palatals
-    'च': 'ca'
-    'छ': 'cha'
-    'ज': 'ja'
-    'झ': 'jha'
-    'ञ': 'ña'
-
-    # Cerebrals
-    'ट': 'ṭa'
-    'ठ': 'ṭha'
-    'ड': 'ḍa'
-    'ड़': 'ṛa'
-    'ढ': 'ḍha'
-    'ढ़': 'ṛha'
-    'ण': 'ṇa'
-
-    # Dentals
-    'त': 'ta'
-    'थ': 'tha'
-    'द': 'da'
-    'ध': 'dha'
-    'न': 'na'
-
-    # Labials
-    'प': 'pa'
-    'फ': 'pha'
-    'ब': 'ba'
-    'भ': 'bha'
-    'म': 'ma'
-
-    # Semivowels
-    'य': 'ya'
-    'र': 'ra'
-    'ल': 'la'
-    'व': 'ba'
-
-    # Sibilants
-    'श': 'śa'
-    'ष': 'sha'
-    'स': 'sa'
-
-    # Aspirate
-    'ह': 'ha'
-
-    # Anusvāra
-    'ं': 'ṃ'
-
-    # Bisarga
-    'ः ': 'ḥ'
-
-    # Anunāsika
-    'ँ': 'n̐' # ঁ : n̐, m̐
-
-    # Abagraha
-    'ऽ': '’' # (apostrophe)
-
-    # Medials # Needed for connecting constants
-    'ा': "ā"
-    'ि': "i"
-    'ी': "ī"
-    'ु': "u"
-    'ू': "ū"
-    'ृ': "ṛi"
-    'ॄ': "rī"
-    'े': "e"
-    'ॊ': "o"
-    'ौ': "au"

data/maps/un-mon-Mong-Latn-2013.yaml

@@ -1,99 +0,0 @@
----
-authority_id: un
-id: 2013
-language: mon
-source_script: Mong
-destination_script: Latn
-name: Mongolian Romanization in China, Version 4.0
-url: http://www.eki.ee/wgrs/rom1_mnc.htm
-creation_date: 2013-09
-description: |
-  The United Nations resolution III/8 in 1977 recognized the Scheme for
-  a Chinese Phonetic Alphabet (Pinyin) as China’s official Roman alphabet
-  scheme and recommended the alphabet as the international system for the
-  romanization of Chinese geographical names. In China Mongolian
-  geographical names are transcribed directly from the Mongolian script
-  into Pinyin. The scheme was published in Toponymic Guidelines for Map
-  and Other Editors: China, 19821.
-
-  The system is used in China and in international cartographic
-  products.
-
-  Mongolian uses a vertical script. Transcription of Mongolian names is
-  made from their proper pronunciation based on the written form of the
-  Mongolian language and Qahar vernacular, with Zhenglan as its
-  representative pronunciation. Due to the complex nature of the script
-  the romanization scheme is not reversible, e.g. the name of the city
-  Hohhot is written ᠬᠥᠬᠡᠬᠣᠲᠠ but may be transliterated as kökeqota.
-
-notes:
-  - The long and short Mongolian vowels are not distinguished in the
-    spelling for general use, but in recording the pronunciation of
-    place-names, the long vowel is represented by duplication.
-  - Where two Roman equivalents are given, the second (in brackets) is
-    used for recording the pronunciation of place-names while the first
-    form is for general use.
-  - In the table only word-initial character variants are shown.
-    Depending on the position in the word many variants of the characters
-    are used as well as some ligatures. These features are not covered here.
-  - For technical reasons the characters of the Mongolian script are
-    turned 90˚ anti-clockwise.
-
-tests:
-  - source: "ᠬᠥᠬᠡᠬᠣᠲᠠ"
-    expected: "kökeqota"
-map:
-  rules:
-    - pattern: \u182c(\u1821|\u1825|\u1826)
-      result: "k\\1"
-    - pattern: \u182d(\u1821|\u1825|\u1826)
-      result: "g\\1"
-
-  characters:
-    "ᠠ": "a"
-    "ᠪ": "b"
-    "ᠼ": "c"
-    "ᠲ": "d"
-    "ᠳ": "d"
-    "ᠡ": "e"
-    "ᠹ": "f"
-    "ᠭ": "ġ"
-    "ᠺ": "g"
-    "ᠬ": "q"
-    "ᠾ": "h"
-    "ᠢ": "i"
-    "ᠵ": "j"
-    "ᠺ": "k"
-    "ᠯ": "l"
-    "ᠮ": "m"
-    "ᠨ": "n"
-    "ᠥ": "ö"
-    "ᠫ": "p"
-    "ᠴ": "q"
-    "ᠷ": "r"
-    "ᠰ": "s"
-    "ᠲ": "t"
-    "ᠦ": "u"
-    "ᠸ": "w"
-    "ᠱ": "x"
-    "ᠶ": "y"
-    "ᠽ": "z"
-    "ᠣ": "o"
-      # - "o" # General use
-      # - "ô" # For place names
-    "ᠤ": "u"
-      # - "u" # General use
-      # - "û" # For place names
-
-
-    # @TODO Exceptional
-    #
-    # This is failing the whole test suite, but as far as I understood
-    # from the comment, this city name is exceptional, so we are temporarliy
-    # adding it as execeptional rules for now.
-    #
-    # But, we will need some natives attension to help us out here, and maybe
-    # come up with some basic rules for this exceptional pattern.
-    #
-
-    "ᠬᠥᠬᠡᠬᠣᠲᠠ": "kökeqota"