interscript 0.1.2 → 0.1.7

data/maps/var-hin-Deva-Latn-hunterian-1872.yaml

@@ -0,0 +1,221 @@
+---
+authority_id: var
+id: 1872
+language: iso-639-2:hin
+source_script: Deva
+destination_script: Latn
+name: Hindi Hunterian system
+url: https://transliteration.eki.ee/pdf/Hindi-Marathi-Nepali.pdf
+creation_date: 1872
+description:
+  The Hunterian system is the national system of romanization in India.
+
+notes:
+
+  -  a, i and u are used in word-final position. The a in gaon and the u in pur are not accented.
+  -  ज्ञ is transliterated gy.
+  -  v is used before i.
+
+tests:
+  - source: "परिपक्क"
+    expected: "paraipakka"
+  - source: "जगत्"
+    expected: "jagat"
+  - source: "संख्या"
+    expected: "sankhyaā"
+  - source: "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर"
+    expected: "ganbhaīra maraījaon kae maāmalae maen bhaārata daūsarae nanbara para"
+  - source: "कोरोना अपडेट्स"
+    expected: "kaoraonaā apadaetsa"
+  - source: "सीडीसी चीफ का बयान अहम"
+    expected: "saīdaīsaī chaīpha kaā bayaāna ahama"
+  - source: "गूगल प्ले स्टोर पर पेटीएम की वापसी"
+    expected: "gaūgala plae staora para paetaīema kaī waāpasaī"
+  - source: "भारत में गैंबलिंग की इजाजत नहीं"
+    expected: "bhaārata maen gaainbalainga kaī ijaājata nahaīn"
+  - source: "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं"
+    expected: "kaoraonaā waaiksaīna mauddae para ghairae raāshtrapatai; jao baāidaena baolae- maujhae aura daesa kao waaigyānaikaon para bharaosaā haai, daonaālda trampa para nahaīn"
+  - source: "गूगल की कार्रवाई पर पेटीएम ने कहा था कि ऐप को अस्थायी तौर पर प्ले-स्टोर से हटाया गया है, आपके पैसे सुरक्षित हैं"
+    expected: "gaūgala kaī kaārrawaāi para paetaīema nae kahaā thaā kai aipa kao asthaāyaī taaura para plae-staora sae hataāyaā gayaā haai, āpakae paaisae saurakshaita haain"
+
+map:
+
+  rules:
+    # note[1]
+    - pattern: (?<=)\u0906(?=\b)
+      result: "a"
+    - pattern: (?<=)\u0908(?=\b)
+      result: "i"
+    - pattern: (?<=)\u090A(?=\b)
+      result: "u"
+
+    # note[3]
+    - pattern: \u0935(?=[इई])
+      result: "v"
+
+
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ri'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'nga'
+
+    # Palatals
+    'च': 'cha'
+    'छ': 'chha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'nya'
+
+    # Cerebrals
+    'ट': 'ta'
+    'ठ': 'tha'
+    'ड': 'da'
+    'ढ': 'dha'
+    'ण': 'na'
+
+    # 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': 'wa'
+
+    # Sibilants
+    'श': 'sa'
+    'ष': 'sha'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+
+    # Additional consonants
+    'क़': 'qa'
+    'ख़': 'kha'
+    'ग़': 'ġa'
+    'ज़': 'za'
+    'ड़': 'ṙa'
+    'ढ़': 'ṙha'
+    'फ़': 'fa'
+    'ळ': 'la'
+
+    # Anusvāra
+    'ं': 'n'
+
+    # Bisarga
+    'ः': 'h'
+
+    # Anunāsika
+    'ँ': 'm'
+
+    # Note 2
+    'ज्ञ': 'gy'
+
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ri"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+    '‍': ''# Used for joining
+
+
+    #V. Vowelless with halanta (्)
+
+    # Gutturals
+    'क्': 'k'
+    'ख्': 'kh'
+    'ग्': 'g'
+    'घ्': 'gh'
+    'ङ्': 'ng'
+
+    # Palatals
+    'च्': 'ch'
+    'छ्': 'chh'
+    'ज्': 'j'
+    'झ्': 'jh'
+    'ञ्': 'ny'
+
+    # Cerebrals
+    'ट्': 't'
+    'ठ्': 'th'
+    'ड्': 'd'
+    'ढ्': 'dh'
+    'ण्': 'n'
+
+    # Dentals
+    'त्': 't'
+    'थ्': 'th'
+    'द्': 'd'
+    'ध्': 'dh'
+    'न्': 'n'
+
+    # Labials
+    'प्': 'p'
+    'फ्': 'ph'
+    'ब्': 'b'
+    'भ्': 'bh'
+    'म्': 'm'
+
+    # Semivowels
+    'य्': 'y'
+    'र्': 'r'
+    'ल्': 'l'
+    'व्': 'w'
+
+    # Sibilants
+    'श्': 's'
+    'ष्': 'sh'
+    'स्': 's'
+
+    # Aspirate
+    'ह्': 'h'
+
+    # Additional consonants
+    'क़्': 'q'
+    'ख़्': 'kh'
+    'ग़्': 'ġ'
+    'ज़्': 'z'
+    'ड़्': 'ṙ'
+    'ढ़्': 'ṙh'
+    'फ़्': 'f'
+    'ळ्': 'l'

data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml

@@ -0,0 +1,406 @@
+---
+authority_id: var
+id: hepburn-1886
+language: iso-639-2:jpn
+source_script: Hrkt
+destination_script: Latn
+name: Traditional Hepburn
+url: http://www.ab.cyberhome.ne.jp/~kaizu/roomazi/doc/hep3.html
+creation_date: 1886
+adoption_date:
+description:
+    This is a traditional version of Hepburn romanization.
+
+notes:
+    "
+    The book was published before the Japanese orthographic reform,
+    and this map takes the reformed orthography in Kana as the source
+    form.
+    https://en.wikipedia.org/wiki/Historical_kana_orthography
+
+    The distinction for long-vowel vs. repeating vowels has not been
+    implemented.
+    For example, the consecutive o's in these words are considered
+    a case of long vowel, and is transliterated as ō:
+
+        氷 (こおり) - kōri, 大阪（おおさか）- Ōsaka
+
+    If there are two consecutive o's in a string, but they belong to
+    different morpheme, then they should be transliterated separately.
+
+        小躍り（こおどり）- koodori
+
+    The same goes for the combinations o+u, u+u as well.
+
+    However, this cannot be easily determined from the Kana.
+    Lexical knowledge is needed, and sometimes the Kanji representation
+    will give more hints about morpheme boundary.
+
+    For now, this map will assume that all o+o, o+u, u+u combinations to
+    be instances of long vowels.
+    "
+
+tests:
+  - source: "ぐんま"
+    expected: "gumma"
+  - source: "しんよう"
+    expected: "shin-yō"
+  - source: "きんようび"
+    expected: "kin-yōbi"
+  - source: "とうきょう"
+    expected: "tōkyō"
+  - source: "しんばし"
+    expected: "shimbashi"
+
+map:
+
+  rules:
+    # Add a dash (-) between ん and a vowel sound or ya, yu, yo
+    - pattern: "([んン])(?=[あいうえおやゆよアイウエオヤユヨ])"
+      result: "\\1-"
+
+    # Convert ん into m before b, m, p
+    - pattern: "[んン](?=[ばびぶべぼまみむめもぱぴぷぺぽバビブベボマミムメモパピプペポ])"
+      result: "m"
+
+  postrules:
+    # Handling of っ/ッ
+    #
+    # The kana っ/ッ is a geminate marker.
+    # When followed by a consonant, repeat the first letter of
+    # the following syllable. Exception: the combination -cch-
+    # should be transliterated as -tch-
+    #
+    # If っ/ッ is not followed by a consonant, then it is usually
+    # phonetically realised as an abrupt stop or shorterning of
+    # the previous syllable. There is no documented or commonly
+    # accepted way to transliterate this sound.
+
+    - pattern: "[っッ]([BbDdFfGgHhJjKkLlMmNnPpQqRrSsTtVvWwXxYyZz])"
+      result: "\\1\\1"
+    - pattern: "[っッ]([Cc])" # ッ followed by ch-
+      result: "t\\1"
+    - pattern: "[っッ]" # drop all other っッ.
+      result: ""
+
+    # In Traditional Hepburn, long o (which can be o+o or o+u), and long u
+    # are transliterated as ō and ū.
+    #
+    # Macron should not be used if two repeating letters split across
+    # a morpheme boundary.
+    #
+    # Long vowels in loanwords are indicated with a macron instead
+    # of letter doubling.
+
+    - pattern: "a[ー]"
+      result: "ā"
+    - pattern: "i[ー]"
+      result: "ī"
+    - pattern: "u[ーu]"
+      result: "ū"
+    - pattern: "e[ー]"
+      result: "ē"
+    - pattern: "o[ーo]"
+      result: "ō"
+
+  characters:
+
+    # Hiragana
+
+    "あ": "a"
+    "い": "i"
+    "う": "u"
+    "え": "e"
+    "お": "o"
+    "おう": "ō"
+
+    "か": "ka"
+    "き": "ki"
+    "く": "ku"
+    "け": "ke"
+    "こ": "ko"
+    "きゃ": "kya"
+    "きゅ": "kyu"
+    "きょ": "kyo"
+    "きょう": "kyō"
+    "こう": "kō"
+
+    "さ": "sa"
+    "し": "shi"
+    "す": "su"
+    "せ": "se"
+    "そ": "so"
+    "しゃ": "sha"
+    "しゅ": "shu"
+    "しょ": "sho"
+    "しょう": "shō"
+    "そう": "sō"
+
+    "た": "ta"
+    "ち": "chi"
+    "つ": "tsu"
+    "て": "te"
+    "と": "to"
+    "ちゃ": "cha"
+    "ちゅ": "chu"
+    "ちょ": "cho"
+    "とう": "tō"
+    "ちょう": "chō"
+
+    "な": "na"
+    "に": "ni"
+    "ぬ": "nu"
+    "ね": "ne"
+    "の": "no"
+    "にゃ": "nya"
+    "にゅ": "nyu"
+    "にょ": "nyo"
+    "にょう": "nyō"
+    "のう": "nō"
+
+    "は": "ha"
+    "ひ": "hi"
+    "ふ": "fu"
+    "へ": "he"
+    "ほ": "ho"
+    "ひゃ": "hya"
+    "ひゅ": "hyu"
+    "ひょ": "hyo"
+    "ひょう": "hyō"
+    "ほう": "hō"
+
+    "ま": "ma"
+    "み": "mi"
+    "む": "mu"
+    "め": "me"
+    "も": "mo"
+    "みゃ": "mya"
+    "みゅ": "myu"
+    "みょ": "myo"
+    "みょう": "myō"
+    "もう": "mō"
+
+    "や": "ya"
+    "ゆ": "yu"
+    "よ": "yo"
+    "よう": "yō"
+
+    "ら": "ra"
+    "り": "ri"
+    "る": "ru"
+    "れ": "re"
+    "ろ": "ro"
+    "りゃ": "rya"
+    "りゅ": "ryu"
+    "りょ": "ryo"
+    "りょう": "ryō"
+    "ろう": "rō"
+
+    "わ": "wa"
+    "を": "wo"
+
+    "が": "ga"
+    "ぎ": "gi"
+    "ぐ": "gu"
+    "げ": "ge"
+    "ご": "go"
+    "ぎゃ": "gya"
+    "ぎゅ": "gyu"
+    "ぎょ": "gyo"
+    "ぎょう": "gyō"
+    "ごう": "gō"
+
+    "ざ": "za"
+    "じ": "ji"
+    "ず": "zu"
+    "ぜ": "ze"
+    "ぞ": "zo"
+    "じゃ": "ja"
+    "じゅ": "ju"
+    "じょ": "jo"
+    "じょう": "jō"
+    "ぞう": "zō"
+
+    "だ": "da"
+    "ぢ": "ji"
+    "づ": "zu"
+    "で": "de"
+    "ど": "do"
+    "ぢゃ": "ja"
+    "ぢゅ": "ju"
+    "ぢょ": "jo"
+    "どう": "dō"
+
+    "ば": "ba"
+    "び": "bi"
+    "ぶ": "bu"
+    "べ": "be"
+    "ぼ": "bo"
+    "びゃ": "bya"
+    "びゅ": "byu"
+    "びょ": "byo"
+    "びょう": "byō"
+    "ぼう": "bō"
+
+    "ぱ": "pa"
+    "ぴ": "pi"
+    "ぷ": "pu"
+    "ぺ": "pe"
+    "ぽ": "po"
+    "ぴゃ": "pya"
+    "ぴゅ": "pyu"
+    "ぴょ": "pyo"
+    "ぴょう": "pyō"
+    "ぽう": "pō"
+
+    "ん": "n"
+
+    # Katakana
+
+    "ア": "a"
+    "イ": "i"
+    "ウ": "u"
+    "エ": "e"
+    "オ": "o"
+    "オウ": "ō"
+
+    "カ": "ka"
+    "キ": "ki"
+    "ク": "ku"
+    "ケ": "ke"
+    "コ": "ko"
+    "キャ": "kya"
+    "キュ": "kyu"
+    "キョ": "kyo"
+    "キョウ": "kyō"
+    "コウ": "kō"
+
+    "サ": "sa"
+    "シ": "shi"
+    "ス": "su"
+    "セ": "se"
+    "ソ": "so"
+    "シャ": "sha"
+    "シュ": "shu"
+    "ショ": "sho"
+    "ショウ": "shō"
+    "ソウ": "sō"
+
+    "タ": "ta"
+    "チ": "chi"
+    "ツ": "tsu"
+    "テ": "te"
+    "ト": "to"
+    "チャ": "cha"
+    "チュ": "chu"
+    "チョ": "cho"
+    "チョウ": "chō"
+    "トウ": "tō"
+
+    "ナ": "na"
+    "ニ": "ni"
+    "ヌ": "nu"
+    "ネ": "ne"
+    "ノ": "no"
+    "ニャ": "nya"
+    "ニュ": "nyu"
+    "ニョ": "nyo"
+    "ニョウ": "nyō"
+    "ノウ": "nō"
+
+    "ハ": "ha"
+    "ヒ": "hi"
+    "フ": "fu"
+    "ヘ": "he"
+    "ホ": "ho"
+    "ヒャ": "hya"
+    "ヒュ": "hyu"
+    "ヒョ": "hyo"
+    "ヒョウ": "hyō"
+    "ホウ": "hō"
+
+    "マ": "ma"
+    "ミ": "mi"
+    "ム": "mu"
+    "メ": "me"
+    "モ": "mo"
+    "ミャ": "mya"
+    "ミュ": "myu"
+    "ミョ": "myo"
+    "ミョウ": "myō"
+    "モウ": "mō"
+
+    "ヤ": "ya"
+    "ユ": "yu"
+    "ヨ": "yo"
+    "ヨウ": "yō"
+
+    "ラ": "ra"
+    "リ": "ri"
+    "ル": "ru"
+    "レ": "re"
+    "ロ": "ro"
+    "リャ": "rya"
+    "リュ": "ryu"
+    "リョ": "ryo"
+    "リョウ": "ryō"
+    "ロウ": "rō"
+
+    "ワ": "wa"
+    "ヲ": "wo"
+
+    "ガ": "ga"
+    "ギ": "gi"
+    "グ": "gu"
+    "ゲ": "ge"
+    "ゴ": "go"
+    "ギャ": "gya"
+    "ギュ": "gyu"
+    "ギョ": "gyo"
+    "ギョウ": "gyō"
+    "ゴウ": "gō"
+
+    "ザ": "za"
+    "ジ": "ji"
+    "ズ": "zu"
+    "ゼ": "ze"
+    "ゾ": "zo"
+    "ジャ": "ja"
+    "ジュ": "ju"
+    "ジョ": "jo"
+    "ジョウ": "jō"
+    "ゾウ": "zō"
+
+    "ダ": "da"
+    "ヂ": "ji"
+    "ヅ": "zu"
+    "デ": "de"
+    "ド": "do"
+    "ヂャ": "ja"
+    "ヂュ": "ju"
+    "ヂョ": "jo"
+    "ドウ": "dō"
+
+    "バ": "ba"
+    "ビ": "bi"
+    "ブ": "bu"
+    "ベ": "be"
+    "ボ": "bo"
+    "ビャ": "bya"
+    "ビュ": "byu"
+    "ビョ": "byo"
+    "ビョウ": "byō"
+    "ボウ": "bō"
+
+    "パ": "pa"
+    "ピ": "pi"
+    "プ": "pu"
+    "ペ": "pe"
+    "ポ": "po"
+    "ピャ": "pya"
+    "ピュ": "pyu"
+    "ピョ": "pyo"
+    "ピョウ": "pyō"
+    "ポウ": "pō"
+
+    "ン": "n"