interscript 0.1.1 → 0.1.2

data/maps/un-jpn-Hrkt-Latn-kunrei.yaml

@@ -0,0 +1,354 @@
+---
+authority_id: un
+id: kunrei
+language: jpn
+source_script: Hrkt
+destination_script: Latn
+name: Romanization of Japanese, Kunrei-siki
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/9th-uncsgn-docs/econf/9th_UNCSGN_e-conf-98-47-add1.pdf
+creation_date: 2007
+adoption_date: 2007-06-29
+description: |
+  The official romanization system for Japanese is the Kunrei-siki.
+  It was officially adopted on 9 December, 1954 (Cabinet Notification No. 1, table 1).
+
+notes:
+  - A small-script tu/tsu form (ッ / っ) is inserted between kana symbols to indicate a double consonant (kk, ss, tt, pp in Kunrei-siki).
+  - ン / ん is romanized always n in Kunrei-siki; when it is necessary to separate the sound n from the vowel or y to follow, the apostrophe is added after the n.
+  - Long vowels are expressed in Kunrei-siki by placing a circumflex (^) over a vowel.
+  - The combination in parentheses is used to denote the word meaning ’big, great’.
+
+tests:
+  - source: かんおう
+    expected: kanô #kan'ô
+  - source: かのう
+    expected: kanô
+  - source: きんゆう
+    expected: kinyû # kin'yû
+  - source: きにゅう
+    expected: kinyû
+  - source: とうきょう
+    expected: tôkyô
+
+map:
+  characters:
+    "あ": "a"
+    "い": "i"
+    "う": "u"
+    "え": "e"
+    "お": "o"
+
+    "か": "ka"
+    "き": "ki"
+    "く": "ku"
+    "け": "ke"
+    "こ": "ko"
+
+    "さ": "sa"
+    "し": "si"
+    "す": "su"
+    "せ": "se"
+    "そ": "so"
+
+    "た": "ta"
+    "ち": "ti"
+    "つ": "tu" # See note 1
+    "て": "te"
+    "と": "to"
+
+    "な": "na"
+    "に": "ni"
+    "ぬ": "nu"
+    "ね": "ne"
+    "の": "no"
+
+    "は": "ha"
+    "ひ": "hi"
+    "ふ": "hu"
+    "へ": "he"
+    "ほ": "ho"
+
+    "ま": "ma"
+    "み": "mi"
+    "む": "mu"
+    "め": "me"
+    "も": "mo"
+
+    "ら": "ra"
+    "り": "ri"
+    "る": "ru"
+    "れ": "re"
+    "ろ": "ro"
+
+    "わ": "wa"
+    "を": "o"
+
+    "ん": "n" # See note 2
+
+    "が": "ga"
+    "ぎ": "gi"
+    "ぐ": "gu"
+    "げ": "ge"
+    "ご": "go"
+
+    "ざ": "za"
+    "じ": "zi"
+    "ず": "zu"
+    "ぜ": "ze"
+    "ぞ": "zo"
+
+    "だ": "da"
+    "ぢ": "di"
+    "づ": "du"
+    "で": "de"
+    "ど": "do"
+
+    "ば": "ba"
+    "び": "bi"
+    "ぶ": "bu"
+    "べ": "be"
+    "ぼ": "bo"
+
+    "ぱ": "pa"
+    "ぴ": "pi"
+    "ぷ": "pu"
+    "ぺ": "pe"
+    "ぽ": "po"
+
+    "おぅ": "ô"
+    "おお": "ô" # See note 4
+
+    # Officially only kya kyu kyo??
+    "きゃ": "kya"
+    "きゅ": "kyu"
+    "きゅぅ": "kyû"
+    "きょ": "kyo"
+    "きょぅ": "kyô"
+
+    # Officially not exists?
+    "こぅ": "kô"
+
+    # Officially only sya syu syo??
+    "しゃ": "sya"
+    "しゅ": "syu"
+    "しゅぅ": "syû"
+    "しょ": "syo"
+    "しょぅ": "syô"
+
+    # Supplementary
+    "ゃ": "ya"
+    "ゅ": "yu"
+    "ょ": "yo"
+    "ぅ": "u"
+    "ょぅ": "yô"
+    "ゅぅ": "yû"
+
+    # Officially not exists?
+    "そぅ": "sô"
+
+    # Officially only tya tyu tyo??
+    "ちゃ": "tya"
+    "ちゅ": "tyu"
+    "ちゅぅ": "tyû"
+    "ちょ": "tyo"
+    "ちょぅ": "tyô"
+
+    # Officially not exists?
+    "とぅ": "tô"
+
+    # Officially only nya nyu nyo??
+    "にゃ": "nya"
+    "にゅ": "nyu"
+    "にゅぅ": "nyû"
+    "にょ": "nyo"
+    "にょぅ": "nyô"
+
+    # Officially not exists?
+    "のぅ": "nô"
+
+    "ひゃ": "hya"
+    "ひゅ": "hyu"
+    "ひゅぅ": "hyû"
+    "ひょ": "hyo"
+    "ひょぅ": "hyô"
+    "ほぅ": "hô"
+    "みゃ": "mya"
+    "みゅ": "myu"
+    "みゅぅ": "myû"
+    "みょ": "myo"
+    "みょぅ": "myô"
+    "もぅ": "mô"
+    "よぅ": "yô"
+    "りゃ": "rya"
+    "りゅ": "ryu"
+    "りゅぅ": "ryû"
+    "りょ": "ryo"
+    "りょぅ": "ryô"
+    "ろぅ": "rô"
+    "ぎゃ": "gya"
+    "ぎゅ": "gyu"
+    "ぎゅぅ": "gyû"
+    "ぎょ": "gyo"
+    "ぎょぅ": "gyô"
+    "ごぅ": "gô"
+    "じゃ": "zya"
+    "じゅ": "zyu"
+    "じゅぅ": "zyû"
+    "じょ": "zyo"
+    "じょぅ": "zyô"
+    "ぞぅ": "zô"
+    "どぅ": "dô"
+    "びゃ": "bya"
+    "びゅ": "byu"
+    "びゅぅ": "byû"
+    "びょ": "byo"
+    "びょぅ": "byô"
+    "ぼぅ": "bô"
+    "ぴゃ": "pya"
+    "ぴゅ": "pyu"
+    "ぴゅぅ": "pyû"
+    "ぴょ": "pyo"
+    "ぴょぅ": "pyô"
+    "ぽぅ": "pô"
+
+
+    "ア": "a"
+    "イ": "i"
+    "ウ": "u"
+    "エ": "e"
+    "オ": "o"
+    "カ": "ka"
+    "キ": "ki"
+    "ク": "ku"
+    "ケ": "ke"
+    "コ": "ko"
+    "サ": "sa"
+    "シ": "si"
+    "ス": "su"
+    "セ": "se"
+    "ソ": "so"
+    "タ": "ta"
+    "チ": "ti"
+    "ツ": "tu" # See note 1
+    "テ": "te"
+    "ト": "to"
+    "ナ": "na"
+    "ニ": "ni"
+    "ヌ": "nu"
+    "ネ": "ne"
+    "ノ": "no"
+    "ハ": "ha"
+    "ヒ": "hi"
+    "フ": "hu"
+    "ヘ": "he"
+    "ホ": "ho"
+    "マ": "ma"
+    "ミ": "mi"
+    "ム": "mu"
+    "メ": "me"
+    "モ": "mo"
+    "ヤ": "ya"
+    "ユ": "yu"
+    "ヨ": "yo"
+    "ラ": "ra"
+    "リ": "ri"
+    "ル": "ru"
+    "レ": "re"
+    "ロ": "ro"
+    "ワ": "wa"
+    "ン": "n" # See note 2
+    "ガ": "ga"
+    "ギ": "gi"
+    "グ": "gu"
+    "ゲ": "ge"
+    "ゴ": "go"
+    "ザ": "za"
+    "ジ": "zi"
+    "ズ": "zu"
+    "ゼ": "ze"
+    "ゾ": "zo"
+    "ダ": "da"
+    "ヂ": "di"
+    "ヅ": "du"
+    "デ": "de"
+    "ド": "do"
+    "バ": "ba"
+    "ビ": "bi"
+    "ブ": "bu"
+    "ベ": "be"
+    "ボ": "bo"
+    "パ": "pa"
+    "ピ": "pi"
+    "プ": "pu"
+    "ペ": "pe"
+    "ポ": "po"
+    "オゥ": "ô"
+    "オオ": "ô" # See note 4
+    "キャ": "kya"
+    "キュ": "kyu"
+    "キュゥ": "kyû"
+    "キョ": "kyo"
+    "キョゥ": "kyô"
+    "コゥ": "kô"
+    "シャ": "sya"
+    "シュ": "syu"
+    "シュゥ": "syû"
+    "ショ": "syo"
+    "ショゥ": "syô"
+    "ソゥ": "sô"
+    "チャ": "tya"
+    "チュ": "tyu"
+    "チュゥ": "tyû"
+    "チョ": "tyo"
+    "チョゥ": "tyô"
+    "トゥ": "tô"
+    "ニャ": "nya"
+    "ニュ": "nyu"
+    "ニュゥ": "nyû"
+    "ニョ": "nyo"
+    "ニョゥ": "nyô"
+    "ノゥ": "nô"
+    "ヒャ": "hya"
+    "ヒュ": "hyu"
+    "ヒュゥ": "hyû"
+    "ヒョ": "hyo"
+    "ヒョゥ": "hyô"
+    "ホゥ": "hô"
+    "ミャ": "mya"
+    "ミュ": "myu"
+    "ミュゥ": "myû"
+    "ミョ": "myo"
+    "ミョゥ": "myô"
+    "モゥ": "mô"
+    "ヨゥ": "yô"
+    "リャ": "rya"
+    "リュ": "ryu"
+    "リュゥ": "ryû"
+    "リョ": "ryo"
+    "リョゥ": "ryô"
+    "ロゥ": "rô"
+    "ギャ": "gya"
+    "ギュ": "gyu"
+    "ギュゥ": "gyû"
+    "ギョ": "gyo"
+    "ギョゥ": "gyô"
+    "ゴゥ": "gô"
+    "ジャ": "zya"
+    "ジュ": "zyu"
+    "ジュゥ": "zyû"
+    "ジョ": "zyo"
+    "ジョゥ": "zyô"
+    "ゾゥ": "zô"
+    "ドゥ": "dô"
+    "ビャ": "bya"
+    "ビュ": "byu"
+    "ビュゥ": "byû"
+    "ビョ": "byo"
+    "ビョゥ": "byô"
+    "ボゥ": "bô"
+    "ピャ": "pya"
+    "ピュ": "pyu"
+    "ピュゥ": "pyû"
+    "ピョ": "pyo"
+    "ピョゥ": "pyô"
+    "ポゥ": "pô"

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

@@ -0,0 +1,80 @@
+---
+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:
+  characters:
+    "ᠠ": "a"
+    "ᠪ": "b"
+    "ᠼ": "c"
+    "ᠲ": "d"
+    "ᠳ": "d"
+    "ᠡ": "e"
+    "ᠹ": "f"
+    "ᠭ": "g"
+    "ᠺ": "g"
+    "ᠬ": "h"
+    "ᠾ": "h"
+    "ᠢ": "i"
+    "ᠵ": "j"
+    "ᠺ": "k"
+    "ᠯ": "l"
+    "ᠮ": "m"
+    "ᠨ": "n"
+    "ᠥ": "o"
+    "ᠫ": "p"
+    "ᠴ": "q"
+    "ᠷ": "r"
+    "ᠰ": "s"
+    "ᠲ": "t"
+    "ᠦ": "u"
+    "ᠸ": "w"
+    "ᠱ": "x"
+    "ᠶ": "y"
+    "ᠽ": "z"
+    "ᠣ":
+      - "o" # General use
+      - "ô" # For place names
+    "ᠤ":
+      - "u" # General use
+      - "û" # For place names

data/spec/interscript_spec.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+RSpec.describe Interscript do
+  it "converts rus using bgnpcgn-rus-Cyrl-Latn-1947" do
+    system = YAML.load_file "maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml"
+    system["tests"].each do |test|
+      result = Interscript.transliterate "bgnpcgn-rus-Cyrl-Latn-1947", test["source"]
+      expect(result).to eq test["expected"]
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1 @@
+require 'interscript'