interscript 0.1.1 → 0.1.2

data/maps/historic-jpn-Hrkt-Latn-hepburn.yaml

@@ -0,0 +1,336 @@
+---
+authority_id: mext
+id: hepburn
+language: jpn
+source_script: Hrkt
+destination_script: Latn
+name: Romanization of Japanese, Modified Hepburn System
+url: http://www.eki.ee/wgrs/rom2_ja.htm
+creation_date: 1954
+adoption_date: 1954-12-09
+description: |
+  Widely used Romanization system in customs, e.g. in passports. In
+  international cartographic products the Modified Hepburn System remains
+  the most used system.
+
+notes:
+  - A small-script tu/tsu form (ッ / っ) is inserted between kana symbols to indicate a double consonant (kk, ss, ssh, tt, tts, tch, pp in Hepburn).
+  - ン / ん in modified Hepburn the character is romanized n’ before y or a vowel letter, n in all other cases; earlier also m was used before b, p, or m.
+  - Long vowels are expressed in Hepburn by placing a macron (¯) over a vowel.
+  - The romanization in parentheses (in modified Hepburn) is used only in those cases where the kana symbol is known to be pronounced in the manner indicated.
+  - The combination in parentheses is used to denote the word meaning ’big, great’.
+
+tests:
+  - source: おばあさん
+    expected: obāsan
+  - source: おにいさん
+    expected: oniisan
+  - source: みずうみ
+    expected: mizuumi
+  - source: とおまわり
+    expected: tōmawari
+  - source: べんきょう
+    expected: benkyō
+  - source: じゃあく
+    expected: jaaku
+  - source: バレーボール
+    expected: barēbōru
+  - source: スーパーマン
+    expected: sūpāman
+
+map:
+  characters:
+    "あ": "a"
+    "い": "i"
+    "う": "u"
+    "え": "e"
+    "お": "o"
+    "か": "ka"
+    "き": "ki"
+    "く": "ku"
+    "け":
+      - "ke"
+      - "ga" # See note 4
+    "こ": "ko"
+    "さ": "sa"
+    "し": "shi"
+    "す": "su"
+    "せ": "se"
+    "そ": "so"
+    "た": "ta"
+    "ち": "chi"
+    "つ": "tsu" # See note 1
+    "て": "te"
+    "と": "to"
+    "な": "na"
+    "に": "ni"
+    "ぬ": "nu"
+    "ね": "ne"
+    "の": "no"
+    "は":
+      - "ha"
+      - "wa" # See note 4
+    "ひ": "hi"
+    "ふ": "fu"
+    "へ":
+      - "he"
+      - "e" # See note 4
+    "ほ": "ho"
+    "ま": "ma"
+    "み": "mi"
+    "む": "mu"
+    "め": "me"
+    "も": "mo"
+    "や": "ya"
+    "ゆ": "yu"
+    "よ": "yo"
+    "ら": "ra"
+    "り": "ri"
+    "る": "ru"
+    "れ": "re"
+    "ろ": "ro"
+    "わ": "wa"
+    "ん": "n" # See note 2
+    "が": "ga"
+    "ぎ": "gi"
+    "ぐ": "gu"
+    "げ": "ge"
+    "ご": "go"
+    "ざ": "za"
+    "じ": "ji"
+    "ず": "zu"
+    "ぜ": "ze"
+    "ぞ": "zo"
+    "だ": "da"
+    "ぢ": "ji"
+    "づ": "zu"
+    "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": "ō"
+    "おお": "ō" # See note 4
+    "きゃ": "kya"
+    "きゅ": "kyu"
+    "きゅぅ": "kyū"
+    "きょ": "kyo"
+    "きょぅ": "kyō"
+    "こぅ": "kō"
+    "しゃ": "sha"
+    "しゅ": "shu"
+    "しゅぅ": "shū"
+    "しょ": "sho"
+    "しょぅ": "shō"
+    "そぅ": "sō"
+    "ちゃ": "cha"
+    "ちゅ": "chu"
+    "ちゅぅ": "chū"
+    "ちょ": "cho"
+    "ちょぅ": "chō"
+    "とぅ": "tō"
+    "にゃ": "nya"
+    "にゅ": "nyu"
+    "にゅぅ": "nyū"
+    "にょ": "nyo"
+    "にょぅ": "nyō"
+    "のぅ": "nō"
+    "ひゃ": "hya"
+    "ひゅ": "hyu"
+    "ひゅぅ": "hyū"
+    "ひょ": "hyo"
+    "ひょぅ": "hyō"
+    "ほぅ":
+      - "hō"
+      - "ō" # See note 4
+    "みゃ": "mya"
+    "みゅ": "myu"
+    "みゅぅ": "myū"
+    "みょ": "myo"
+    "みょぅ": "myō"
+    "もぅ": "mō"
+    "よぅ": "yō"
+    "りゃ": "rya"
+    "りゅ": "ryu"
+    "りゅぅ": "ryū"
+    "りょ": "ryo"
+    "りょぅ": "ryō"
+    "ろぅ": "rō"
+    "ぎゃ": "gya"
+    "ぎゅ": "gyu"
+    "ぎゅぅ": "gyū"
+    "ぎょ": "gyo"
+    "ぎょぅ": "gyō"
+    "ごぅ": "gō"
+    "じゃ": "ja"
+    "じゅ": "ju"
+    "じゅぅ": "jū"
+    "じょ": "jo"
+    "じょぅ": "jō"
+    "ぞぅ": "zō"
+    "どぅ": "dō"
+    "びゃ": "bya"
+    "びゅ": "byu"
+    "びゅぅ": "byū"
+    "びょ": "byo"
+    "びょぅ": "byō"
+    "ぼぅ": "bō"
+    "ぴゃ": "pya"
+    "ぴゅ": "pyu"
+    "ぴゅぅ": "pyū"
+    "ぴょ": "pyo"
+    "ぴょぅ": "pyō"
+    "ぽぅ": "pō"
+    "ア": "a"
+    "イ": "i"
+    "ウ": "u"
+    "エ": "e"
+    "オ": "o"
+    "カ": "ka"
+    "キ": "ki"
+    "ク": "ku"
+    "ケ": "ke"
+    "コ": "ko"
+    "サ": "sa"
+    "シ": "shi"
+    "ス": "su"
+    "セ": "se"
+    "ソ": "so"
+    "タ": "ta"
+    "チ": "chi"
+    "ツ": "tsu" # See note 1
+    "テ": "te"
+    "ト": "to"
+    "ナ": "na"
+    "ニ": "ni"
+    "ヌ": "nu"
+    "ネ": "ne"
+    "ノ": "no"
+    "ハ":
+      - "ha"
+      - "wa" # See note 4
+    "ヒ": "hi"
+    "フ": "fu"
+    "ヘ":
+      - "he"
+      - "e" # See note 4
+    "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": "ji"
+    "ズ": "zu"
+    "ゼ": "ze"
+    "ゾ": "zo"
+    "ダ": "da"
+    "ヂ": "ji"
+    "ヅ": "zu"
+    "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": "ō"
+    "オオ": "ō" # See note 4
+    "キャ": "kya"
+    "キュ": "kyu"
+    "キュゥ": "kyū"
+    "キョ": "kyo"
+    "キョゥ": "kyō"
+    "コゥ": "kō"
+    "シャ": "sha"
+    "シュ": "shu"
+    "シュゥ": "shū"
+    "ショ": "sho"
+    "ショゥ": "shō"
+    "ソゥ": "sō"
+    "チャ": "cha"
+    "チュ": "chu"
+    "チュゥ": "chū"
+    "チョ": "cho"
+    "チョゥ": "chō"
+    "トゥ": "tō"
+    "ニャ": "nya"
+    "ニュ": "nyu"
+    "ニュゥ": "nyū"
+    "ニョ": "nyo"
+    "ニョゥ": "nyō"
+    "ノゥ": "nō"
+    "ヒャ": "hya"
+    "ヒュ": "hyu"
+    "ヒュゥ": "hyū"
+    "ヒョ": "hyo"
+    "ヒョゥ": "hyō"
+    "ホゥ":
+      - "hō"
+      - "ō" # See note 4
+    "ミャ": "mya"
+    "ミュ": "myu"
+    "ミュゥ": "myū"
+    "ミョ": "myo"
+    "ミョゥ": "myō"
+    "モゥ": "mō"
+    "ヨゥ": "yō"
+    "リャ": "rya"
+    "リュ": "ryu"
+    "リュゥ": "ryū"
+    "リョ": "ryo"
+    "リョゥ": "ryō"
+    "ロゥ": "rō"
+    "ギャ": "gya"
+    "ギュ": "gyu"
+    "ギュゥ": "gyū"
+    "ギョ": "gyo"
+    "ギョゥ": "gyō"
+    "ゴゥ": "gō"
+    "ジャ": "ja"
+    "ジュ": "ju"
+    "ジュゥ": "jū"
+    "ジョ": "jo"
+    "ジョゥ": "jō"
+    "ゾゥ": "zō"
+    "ドゥ": "dō"
+    "ビャ": "bya"
+    "ビュ": "byu"
+    "ビュゥ": "byū"
+    "ビョ": "byo"
+    "ビョゥ": "byō"
+    "ボゥ": "bō"
+    "ピャ": "pya"
+    "ピュ": "pyu"
+    "ピュゥ": "pyū"
+    "ピョ": "pyo"
+    "ピョゥ": "pyō"
+    "ポゥ": "pō"

data/maps/icao-bel-Cyrl-Latn-9303.yaml

@@ -0,0 +1,125 @@
+---
+authority_id: icao
+id: 9303
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Belorussian Cyrillic to Latin
+url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+creation_date: 2015
+description: |
+  Part 3 defines specifications that are common to TD1, TD2 and TD3
+  size machine readable travel documents (MRTDs) including those
+  necessary for global interoperability using visual inspection and
+  machine readable (optical character recognition) means.
+
+  Since only Latin-alphabet characters are allowed in the VIZ, if
+  mandatory data elements are in a national language that does not use
+  the Latin alphabet, a transcription or transliteration shall also be
+  provided.
+
+  This document defines the transliteration mappings used to produce
+  this transcription or transliteration.
+tests:
+  - source:
+    expected:
+map:
+  # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
+  characters:
+    "\u0027": "",     # '
+    "\u0410": "A",    # А
+    "\u0411": "B",    # Б
+    "\u0414": "D",    # Д
+    "\u0401": "IO",   # Ё
+    "\u0415": "E",    # Е
+    "\u042D": "E",    # Э
+    "\u0424": "F",    # Ф
+    "\u0413": "H",    # Г
+    "\u0418": "I",    # И
+    "\u0419": "I",    # Й
+    "\u041A": "K",    # К
+    "\u041B": "L",    # Л
+    "\u041C": "M",    # М
+    "\u041D": "N",    # Н
+    "\u041E": "O",    # О
+    "\u041F": "P",    # П
+    "\u0420": "R",    # Р
+    "\u0421": "S",    # С
+    "\u0422": "T",    # Т
+    "\u0423": "U",    # У
+    "\u0412": "V",    # В
+    "\u042B": "Y",    # Ы
+    "\u0417": "Z",    # З
+    "\u0427": "CH",   # Ч
+    "\u042F": "IA",   # Я
+    "\u042E": "IU",   # Ю
+    "\u0425": "KH",   # Х
+    "\u0428": "SH",   # Ш
+    "\u0429": "SHCH", # Щ
+    "\u0426": "TS",   # Ц
+    "\u0416": "ZH",   # Ж
+    "\u0490": "G",    # Ґ
+    "\u040E": "U",    # Ў
+    "\u046A": "U",    # Ѫ
+    "\u0402": "D",    # Ђ
+    "\u0405": "DZ",   # Ѕ
+    "\u0408": "J",    # Ј
+    "\u0409": "LJ",   # Љ
+    "\u040A": "NJ",   # Њ
+    "\u04BA": "C",    # Һ
+    "\u040F": "DZ",   # Џ
+    "\u0404": "IE",   # Є
+    "\u0407": "I",    # Ї
+    "\u0403": "G",    # Ѓ
+    "\u0406": "I",    # І
+
+    "\u0430": "a",    # а
+    "\u0431": "b",    # б
+    "\u0434": "d",    # д
+    "\u0451": "io",   # ё
+    "\u0435": "e",    # e
+    "\u044D": "e",    # э
+    "\u0444": "f",    # ф
+    "\u0433": "h",    # г
+    "\u0438": "i",    # и
+    "\u0439": "i",    # й
+    "\u043A": "k",    # к
+    "\u043B": "l",    # л
+    "\u043C": "m",    # м
+    "\u043D": "n",    # н
+    "\u043E": "o",    # о
+    "\u043F": "p",    # п
+    "\u0440": "r",    # р
+    "\u0441": "s",    # с
+    "\u0442": "t",    # т
+    "\u0443": "",     # у
+    "\u0432": "v",    # в
+    "\u044B": "y",    # ы
+    "\u0437": "z",    # з
+    "\u0447": "ch",   # ч
+    "\u044F": "ia",   # я
+    "\u044E": "i",    # ю
+    "\u0445": "kh",   # х
+    "\u0448": "sh",   # ш
+    "\u0449": "shch", # щ
+    "\u0446": "ts",   # ц
+    "\u0436": "zh",   # ж
+    "\u0491": "g",    # ґ
+    "\u045E": "",     # ў
+    "\u046B": "",     # ѫ
+    "\u0452": "d",    # ђ
+    "\u0455": "dz",   # ѕ
+    "\u0458": "j",    # ј
+    "\u0459": "lj",   # љ
+    "\u045A": "nj",   # њ
+    "\u04BB": "c",    # һ
+    "\u045F": "dz",   # џ
+    "\u0454": "ie",   # є
+    "\u0457": "i",    # ї
+    "\u0453": "g",    # ѓ
+    "\u0456": "i"     # і
+
+
+
+
+