interscript-maps 2.0.5

data/maps/alalc-pli-Deva-Latn-2012.imp

@@ -0,0 +1,140 @@
+metadata {
+  authority_id: alalc
+  id: 2012
+  language: iso-639-2:pli
+  source_script: Deva
+  destination_script: Latn
+  name: Pali Romanization, 2012
+  url: https://www.loc.gov/catdir/cpso/romanization/pali.pdf
+  creation_date: 2012
+  description: |
+    ALA-LC Romanization table for Pali
+
+  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: Niggahīta combinations representing nasals are romanized by ṅ
+      before gutturals, ñ before palatals, ṇ before cerebrals, n before dentals, and m before
+      labials.
+}
+
+tests {
+  test "तेन खो पन समयेन वेसालिया अविदूरे कलन्दगामो नाम अत्थि", "taena khao pana samayaena vaesaālaiyaā avaidaūrae kalanadagaāmao naāma atathai"
+  test "तत्थ सुदिन्‍नो नाम कलन्दपुत्तो सेट्ठिपुत्तो होति", "tatatha saudainanao naāma kalanadapautatao saeṭaṭhaipautatao haotai"
+  test "अथ खो सुदिन्‍नो कलन्दपुत्तो सम्बहुलेहि", "atha khao saudainanao kalanadapautatao samabahaulaehai"
+  test "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा", "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+  test "अथ खो सुदिन्‍नो कलन्दपुत्तो अचिरवुट्ठिताय परिसाय येन भगवा तेनुपसङ्कमि; उपसङ्कमित्वा भगवन्तं अभिवादेत्वा एकमन्तं निसीदि", "atha khao saudainanao kalanadapautatao acairavauṭaṭhaitaāya paraisaāya yaena bhagavaā taenaupasaṅakamai; upasaṅakamaitavaā bhagavanataṃ abhaivaādaetavaā ekamanataṃ naisaīdai"
+  test "अथ खो सुदिन्‍नस्स कलन्दपुत्तस्स मातापितरो सुदिन्‍नं कलन्दपुत्तं एतदवोचुं", "atha khao saudainanasasa kalanadapautatasasa maātaāpaitarao saudainanaṃ kalanadapautataṃ etadavaocauṃ"
+  test "त्वं खोसि, तात सुदिन्‍न, अम्हाकं एकपुत्तको पियो मनापो सुखेधितो सुखपरिहतो", "tavaṃ khaosai, taāta saudainana, amahaākaṃ ekapautatakao paiyao manaāpao saukhaedhaitao saukhaparaihatao"
+  test "न त्वं, तात सुदिन्‍न, किञ्‍चि दुक्खस्स जानासि", "na tavaṃ, taāta saudainana, kaiñacai daukakhasasa jaānaāsai"
+  test "अनुञ्‍ञातोम्हि किर मातापितूहि अगारस्मा अनगारियं पब्बज्‍जाया’’ति, हट्ठो उदग्गो पाणिना गत्तानि परिपुञ्छन्तो वुट्ठासि", "anauñañaātaomahai kaira maātaāpaitaūhai agaārasamaā anagaāraiyaṃ pababajajaāyaā’’tai, haṭaṭhao udagagao paāṇainaā gatataānai paraipauñachanatao vauṭaṭhaāsai"
+}
+
+stage {
+
+  # RULES
+  # note[3]
+  sub "\u0902", "ṅ", after: any("कखगघङ")
+  sub "\u0902", "ñ", after: any("चछजझञ")
+  sub "\u0902", "ṇ", after: any("टठडढण")
+  sub "\u0902", "n", after: any("तथदधन")
+  # Those aren't tested...
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    sub "अ", "a"
+    sub "आ", "ā"
+    sub "इ", "i"
+    sub "ई", "ī"
+    sub "उ", "u"
+    sub "ऊ", "ū"
+    sub "ए", "e"
+    sub "ओ", "o"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "क", "ka"
+    sub "ख", "kha"
+    sub "ग", "ga"
+    sub "घ", "gha"
+    sub "ङ", "ṅa"
+
+    # Palatals
+    sub "च", "ca"
+    sub "छ", "cha"
+    sub "ज", "ja"
+    sub "झ", "jha"
+    sub "ञ", "ña"
+
+    # Cerebrals
+    sub "ट", "ṭa"
+    sub "ठ", "ṭha"
+    sub "ड", "ḍa"
+    sub "ढ", "ḍha"
+    sub "ण", "ṇa"
+
+    # Dentals
+    sub "त", "ta"
+    sub "थ", "tha"
+    sub "द", "da"
+    sub "ध", "dha"
+    sub "न", "na"
+
+    # Labials
+    sub "प", "pa"
+    sub "फ", "pha"
+    sub "ब", "ba"
+    sub "भ", "bha"
+    sub "म", "ma"
+
+    # Semivowels
+    sub "य", "ya"
+    sub "र", "ra"
+    sub "ल", "la"
+    sub "ळ", "ḻa"
+    sub "व", "va"
+
+    # Sibilants
+    sub "श", "śa"
+    sub "ष", "ṣa"
+    sub "स", "sa"
+
+    # Aspirate
+    sub "ह", "ha"
+
+    # Visagga
+    sub "ः", "ḥ"
+
+    # Niggahīta/Anusvāra
+    sub "ं", "ṃ"
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "े", "e"
+    sub "ो", "o"
+    sub "्", ""
+    sub "‍", "" # Used for joining
+  }
+
+  compose
+}

data/maps/alalc-pra-Deva-Latn-2012.imp

@@ -0,0 +1,52 @@
+metadata {
+  authority_id: alalc
+  id: 2012
+  language: iso-639-2:pra
+  source_script: Deva
+  destination_script: Latn
+  name: Prakrit Romanization, 2012
+  url: https://www.loc.gov/catdir/cpso/romanization/sanskrit.pdf
+  creation_date: 2012
+  description: |
+    ALA-LC Romanization table for Prakrit
+
+  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.
+      In other circumstances it is transliterated by a tilde (~) over the vowel.
+
+    - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+}
+
+tests {
+  test "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि", "sṛṣṭisthitivināśānāṃ śaktibhūte sanātani"
+  test "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते", "guṇāśraye guṇamaye nārāyaṇi namo’stu te"
+}
+
+dependency "alalc-san-Deva-Latn-2012", as: devalatn
+
+stage {
+
+  run map.devalatn.stage.main
+
+}
+

data/maps/alalc-rus-Cyrl-Latn-1997.imp

@@ -0,0 +1,165 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:rus
+  source_script: Cyrl
+  destination_script: Latn
+  name: ALA-LC Romanization System 1997
+  url: https://en.wikipedia.org/wiki/ALA-LC_romanization_for_Russian
+  creation_date: 1997
+  description: |
+    The ALA-LC Romanization tables for Slavic alphabets is a set of standards for romanization of texts
+    in various writing systems used in North American libraries and publications.
+    This version was published by the American Library Association and the Library of Congress in 1997.
+    This article is about the ALA-LC method of transliteration of Russian-language text from Cyrillic script to Latin script.
+
+    The formal, unambiguous version of the system requires some diacritics and two-letter tie characters which are often omitted in practice.
+
+  notes:
+    - Pre-1918 letters skipped
+    - Pre-18th century letters skipped
+}
+
+tests {
+  test "Азов", "Azov"
+  test "Тамбов", "Tambov"
+  test "Барнаул", "Barnaul"
+  test "Кубань", "Kubanʹ"
+  test "Владимир", "Vladimir"
+  test "Ульяновск", "Ulʹi͡anovsk"
+  test "Грозный", "Groznyǐ"
+  test "Волгодонск", "Volgodonsk"
+  test "Дзержинский", "Dzerzhinskiǐ"
+  test "Нелидово", "Nelidovo"
+  test "Елизово", "Elizovo"
+  test "Чебоксары", "Cheboksary"
+  test "Ёлкин", "Ëlkin"
+  test "Озёрный", "Ozërnyǐ"
+  test "Жуков", "Zhukov"
+  test "Лужники", "Luzhniki"
+  test "Звенигород", "Zvenigorod"
+  test "Вязьма", "Vi͡azʹma"
+  test "Иркутск", "Irkutsk"
+  test "Апатиты", "Apatity"
+  test "Йошкар-Ола", "Ǐoshkar-Ola"
+  test "Бийск", "Biǐsk"
+  test "Киров", "Kirov"
+  test "Енисейск", "Eniseǐsk"
+  test "Ломоносов", "Lomonosov"
+  test "Нелидово", "Nelidovo"
+  test "Менделеев", "Mendeleev"
+  test "Каменка", "Kamenka"
+  test "Новосибирск", "Novosibirsk"
+  test "Кандалакша", "Kandalaksha"
+  test "Омск", "Omsk"
+  test "Красноярск", "Krasnoi͡arsk"
+  test "Петрозаводск", "Petrozavodsk"
+  test "Серпухов", "Serpukhov"
+  test "Ростов", "Rostov"
+  test "Северобайкальск", "Severobaǐkalʹsk"
+  test "Сковородино", "Skovorodino"
+  test "Чайковский", "Chaǐkovskiǐ"
+  test "Тамбов", "Tambov"
+  test "Мытищи", "Mytishchi"
+  test "Углич", "Uglich"
+  test "Дудинка", "Dudinka"
+  test "Фурманов", "Furmanov"
+  test "Уфа", "Ufa"
+  test "Хабаровск", "Khabarovsk"
+  test "Прохладный", "Prokhladnyǐ"
+  test "Цимлянск", "T͡Simli͡ansk"
+  test "Ельцин", "Elʹt͡sin"
+  test "Чебоксары", "Cheboksary"
+  test "Печора", "Pechora"
+  test "Шахтёрск", "Shakhtërsk"
+  test "Мышкин", "Myshkin"
+  test "Щёлково", "Shchëlkovo"
+  test "Ртищево", "Rtishchevo"
+  test "Подъездной", "Podʺezdnoǐ"
+  test "Ыттык-Кёль", "Yttyk-Këlʹ"
+  test "Тында", "Tynda"
+  test "Тюмень", "Ti͡umenʹ"
+  test "Электрогорск", "Ėlektrogorsk"
+  test "Радиоэлектроника", "Radioėlektronika"
+  test "Юбилейный", "I͡Ubileǐnyǐ"
+  test "Ключевская", "Kli͡uchevskai͡a"
+  test "Якутск", "I͡Akutsk"
+  test "Брянск", "Bri͡ansk"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "'", "" # '
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "В", "V" # В
+    sub "Г", "G" # Г
+    sub "Д", "D" # Д
+    sub "Е", "E" # Е
+    sub "Ё", "Ë" # Ё
+    sub "Ж", "Zh" # Ж
+    sub "З", "Z" # З
+    sub "И", "I" # И
+    sub "Й", "Ǐ" # Й
+    sub "К", "K" # К
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "Ф", "F" # Ф
+    sub "Х", "Kh" # Х
+    sub "Ц", "T͡S" # Ц
+    sub "Ч", "Ch" # Ч
+    sub "Ш", "Sh" # Ш
+    sub "Щ", "Shch" # Щ
+    sub "Ъ", "ʺ" # Ъ
+    sub "Ы", "Y" # Ы
+    sub "Ь", "ʹ" # Ь
+    sub "Э", "Ė" # Э
+    sub "Ю", "I͡U" # Ю
+    sub "Я", "I͡A" # Я
+
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "в", "v" # в
+    sub "г", "g" # г
+    sub "д", "d" # д
+    sub "е", "e" # e
+    sub "ё", "ë" # ё
+    sub "ж", "zh" # ж
+    sub "з", "z" # з
+    sub "и", "i" # и
+    sub "й", "ǐ" # й
+    sub "к", "k" # к
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "u" # у
+    sub "ф", "f" # ф
+    sub "х", "kh" # х
+    sub "ц", "t͡s" # ц
+    sub "ч", "ch" # ч
+    sub "ш", "sh" # ш
+    sub "щ", "shch" # щ
+    sub "ъ", "ʺ" # ъ
+    sub "ы", "y" # ы
+    sub "ь", "ʹ" # ь
+    sub "э", "ė" # э
+    sub "ю", "i͡u" # ю
+    sub "я", "i͡a" # я
+  }
+
+  compose
+}

data/maps/alalc-rus-Cyrl-Latn-2012.imp

@@ -0,0 +1,107 @@
+metadata {
+  authority_id: alalc
+  id: 2012
+  language: iso-639-2:rus
+  source_script: Cyrl
+  destination_script: Latn
+  name: ALA-LC Romanization System 2012
+  url: https://www.loc.gov/catdir/cpso/romanization/russian.pdf
+  creation_date: 2012
+  description: |
+    The ALA-LC Romanization tables for Slavic alphabets is a set of standards for romanization of texts
+    in various writing systems used in North American libraries and publications.
+    The latest version was published by the American Library Association and the Library of Congress in 2012.
+
+  notes:
+    - The letters І, Ѣ, Ѳ and Ѵ were eliminated in the orthographic reform of 1918. For other obsolete letters appearing in Russian texts, consult the Church Slavic table.
+}
+
+tests {
+  test "Азов", "Azov"
+  test "Тамбов", "Tambov"
+  test "Барнаул", "Barnaul"
+  test "Кубань", "Kubanʹ"
+  test "Владимир", "Vladimir"
+  test "Ульяновск", "Ulʹi͡anovsk"
+  test "Грозный", "Groznyǐ"
+  test "Волгодонск", "Volgodonsk"
+  test "Дзержинский", "Dzerzhinskiǐ"
+  test "Нелидово", "Nelidovo"
+  test "Елизово", "Elizovo"
+  test "Чебоксары", "Cheboksary"
+  test "Ёлкин", "Ëlkin"
+  test "Озёрный", "Ozërnyǐ"
+  test "Жуков", "Zhukov"
+  test "Лужники", "Luzhniki"
+  test "Звенигород", "Zvenigorod"
+  test "Вязьма", "Vi͡azʹma"
+  test "Иркутск", "Irkutsk"
+  test "Апатиты", "Apatity"
+  test "Йошкар-Ола", "Ǐoshkar-Ola"
+  test "Бийск", "Biǐsk"
+  test "Киров", "Kirov"
+  test "Енисейск", "Eniseǐsk"
+  test "Ломоносов", "Lomonosov"
+  test "Нелидово", "Nelidovo"
+  test "Менделеев", "Mendeleev"
+  test "Каменка", "Kamenka"
+  test "Новосибирск", "Novosibirsk"
+  test "Кандалакша", "Kandalaksha"
+  test "Омск", "Omsk"
+  test "Красноярск", "Krasnoi͡arsk"
+  test "Петрозаводск", "Petrozavodsk"
+  test "Серпухов", "Serpukhov"
+  test "Ростов", "Rostov"
+  test "Северобайкальск", "Severobaǐkalʹsk"
+  test "Сковородино", "Skovorodino"
+  test "Чайковский", "Chaǐkovskiǐ"
+  test "Тамбов", "Tambov"
+  test "Мытищи", "Mytishchi"
+  test "Углич", "Uglich"
+  test "Дудинка", "Dudinka"
+  test "Фурманов", "Furmanov"
+  test "Уфа", "Ufa"
+  test "Хабаровск", "Khabarovsk"
+  test "Прохладный", "Prokhladnyǐ"
+  test "Цимлянск", "T͡Simli͡ansk"
+  test "Ельцин", "Elʹt͡sin"
+  test "Чебоксары", "Cheboksary"
+  test "Печора", "Pechora"
+  test "Шахтёрск", "Shakhtërsk"
+  test "Мышкин", "Myshkin"
+  test "Щёлково", "Shchëlkovo"
+  test "Ртищево", "Rtishchevo"
+  test "Подъездной", "Podʺezdnoǐ"
+  test "Ыттык-Кёль", "Yttyk-Këlʹ"
+  test "Тында", "Tynda"
+  test "Тюмень", "Ti͡umenʹ"
+  test "Электрогорск", "Ėlektrogorsk"
+  test "Радиоэлектроника", "Radioėlektronika"
+  test "Юбилейный", "I͡Ubileǐnyǐ"
+  test "Ключевская", "Kli͡uchevskai͡a"
+  test "Якутск", "I͡Akutsk"
+  test "Брянск", "Bri͡ansk"
+}
+
+dependency "alalc-rus-Cyrl-Latn-1997", as: cyrllatn
+
+
+stage {
+
+  run map.cyrllatn.stage.main
+
+  # CHARACTERS
+  parallel {
+    sub "\u0406", "Ī"
+    sub "\u0456", "ī"
+
+    sub "\u0462", "I͡E" # Ѣ
+    sub "\u0463", "i͡e" # ѣ
+
+    sub "\u0472", "Ḟ" # Ѳ
+    sub "\u0473", "ḟ" # ѳ
+
+    sub "\u0474", "Ẏ" # Ѵ
+    sub "\u0475", "ẏ" # ѵ
+  }
+}