interscript 0.1.3 → 0.1.9

data/maps/alalc-mar-Deva-Latn-1997.yaml

@@ -0,0 +1,189 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:mar
+source_script: Deva
+destination_script: Latn
+name: Marathi Romanization, 1997
+alias:
+  ogc11122:
+    code: mar_Deva2Latn_ALA_1997
+    description: Marathi ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/marathi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Marathi
+
+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:
+  - source: "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद"
+    expected: "ṭhaāṇae - jailahayaāta baudhavaāraī eka hajaāra raugaṇaāñcaī vaāḍha, tara jaṇaāñcayaā maṛitayaūcaī naonda"
+  - source: "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक"
+    expected: "ekataā kapaūra paunahaā aḍakalaī vaādaāta, vaebasaīraijamadhalayaā 'tayaā' saīnamaulae jamaāvaācaī gharaāvara dagaḍaphaeka"
+  - source: "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं"
+    expected: "jaāṇaūna ghayaā, baīemasaīcayaā adhaikaāऱyaānnaī kaṅganaā raāṇaautacayaā ôphaisamadhalae nakakaī kaāya- kaāya taoḍalam"
+  - source: "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश"
+    expected: "kaṅganaā maumbaīta daākhala haoṇayaāpaūravaī 'maātaośaraī'varaūna pharamaāna sauṭalae; paravakatayaānnaā sakata ādaeśa"
+  - source: "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय"
+    expected: "maraāṭhaā ārakashaṇaāsa taātapaurataī sathagaitaī; saravaocaca nayaāyaālayaācaā nairaṇaya"
+  - source: "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात"
+    expected: "bhaārataācayaā tainahaī laśaīñcaā pahailaā ṭapapaā yaśasavaī, vaācaā kadhaī yaeṇaāra baājaāraāta"
+  - source: "रुग्णवाढीमुळे खाटांची चणचण"
+    expected: "raugaṇavaāḍhaīmaulae khaāṭaāñcaī caṇacaṇa"
+  - source: "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद"
+    expected: "paīema savanaidhaī karaja yaojanaelaā maumbaītaūna alapa parataisaāda"
+  - source: "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती"
+    expected: "saāntaākaraūjha-caembaūra laiṅka raoḍavaraīla unanata maāragaālaā sathagaitaī"
+  - source: "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार"
+    expected: "sampaādaka araṇaba gaosavaāmaī yaāñcayaāvairaūdadha khaḍaka paolaisa ṭhaāṇayaāta takaraāra"
+  - source: "२५६८७५४४६४४६१६११"
+    expected: "2568754464461611"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0902(?=[कखगघङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजझञ])
+      result: ñ
+    - pattern: \u0902(?=[टठडढण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+
+  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
+    # 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'
+    'ळ': 'la'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'sha'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Anusvāra
+    'ं': 'm'
+
+    # Bisarga
+    'ः ': 'ḥ'
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛi"
+    'ॄ': "rī"
+    'े': "e"
+    'ो': "o"
+    'ौ': "au"
+    '्': ''
+
+    # digits
+
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'

data/maps/alalc-mar-Deva-Latn-2011.yaml

@@ -0,0 +1,45 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:mar
+source_script: Deva
+destination_script: Latn
+name: Marathi Romanization, 2011
+url: https://loc.gov/catdir/cpso/romanization/marathi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Marathi
+
+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:
+  - source: "कोरोनाच्या लढाईत पोलीस थकलेत, पण हिंमत हरलेले नाहीत; गृहमंत्र्यांकडून कौतुक"
+    expected: "kaoraonaācayaā laḍhaāīta paolaīsa thakalaeta, paṇa haimmata haralaelae naāhaīta; gaṛihamantarayaāṅkaḍaūna kaautauka"
+
+map:
+
+  inherit: "alalc-mar-Deva-Latn-1997"

data/maps/{alalc-mkd-cyrl-latn-1997.yaml → alalc-mkd-Cyrl-Latn-1997.yaml}

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 1997
-language: mkd
+language: iso-639-2:mkd
 source_script: Cyrl
 destination_script: Latn
 name: Serbian and Makedonian Romanization, ALA-LC 1997 System

data/maps/alalc-mkd-Cyrl-Latn-2013.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 2013
-language: mkd
+language: iso-639-2:mkd
 source_script: Cyrl
 destination_script: Latn
 name: Makedonian Romanization, ALA-LC 2013 System

data/maps/alalc-mon-Cyrl-Latn-1997.yaml

@@ -0,0 +1,220 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:mon
+source_script: Cyrl
+destination_script: Latn
+name: Transliteration of Cyrillic Khalkha
+alias:
+  ogc11122:
+    code: mon_Cyrl2Latn_ALA_1997
+    description: Mongolian ALA-Library of Congress 1997 System
+url: https://collab.its.virginia.edu/wiki/tibetan-script/Transliteration%20Schemes%20Mongolian%20Cyrillic%20Script.html
+creation_date:
+confirmation_date:
+description: |
+  In Mongolia, the Khalkha dialect, currently written in both Cyrillic and traditional Mongolian script
+  (and at times in Latin for social networking), is predominant, while in Inner Mongolia, the language
+  is dialectally more diverse and is written in the traditional Mongolian script.
+
+tests:
+  - source: Эрдэнэт Сум
+    expected: Êrdênêt Sum
+  - source: Эрдэнэт
+    expected: Êrdênêt
+  - source: Эрдэнэ
+    expected: Êrdênê
+  - source: Шивээговь Сум
+    expected: Shivêêgovi Sum
+  - source: Шивээговь
+    expected: Shivêêgovi
+  - source: Шарынгол Сум
+    expected: Sharyngol Sum
+  - source: Шарынгол
+    expected: Sharyngol
+  - source: Цагааннуур
+    expected: Tsagaannuur
+  - source: Хонгор Сум
+    expected: Khongor Sum
+  - source: Хонгор
+    expected: Khongor
+  - source: Хайлаастай
+    expected: Khaĭlaastaĭ
+  - source: Түнэл Сум
+    expected: Tünêl Sum
+  - source: Түнэл
+    expected: Tünêl
+  - source: Сүхбаатар
+    expected: Sükhbaatar
+  - source: Сүмбэр Сум
+    expected: Sümbêr Sum
+  - source: Сүмбэр
+    expected: Sümbêr
+  - source: Сайншанд Сум
+    expected: Saĭnshand Sum
+  - source: Сайншанд
+    expected: Saĭnshand
+  - source: Орхон Сум
+    expected: Orkhon Sum
+  - source: Орхон
+    expected: Orkhon
+  - source: Нарст
+    expected: Narst
+  - source: Мөрөн Сум
+    expected: Mörön Sum
+  - source: Мөрөн
+    expected: Mörön
+  - source: Зүүнхөвөө
+    expected: Züünkhövöö
+  - source: Жаргалант Сум
+    expected: Zhargalant Sum
+  - source: Жаргалант
+    expected: Zhargalant
+  - source: Дархан Сум
+    expected: Darkhan Sum
+  - source: Даланзадгад Сум
+    expected: Dalanzadgad Sum
+  - source: Даланзадгад
+    expected: Dalanzadgad
+  - source: Давст Сум
+    expected: Davst Sum
+  - source: Давст
+    expected: Davst
+  - source: Говьсүмбэр Сум
+    expected: Govisümbêr Sum
+  - source: Говь
+    expected: Govi
+  - source: Буга
+    expected: Buga
+  - source: Бор-Өндөр Сум
+    expected: Bor-Öndör Sum
+  - source: Бор-Өндөр
+    expected: Bor-Öndör
+  - source: Баянхонгор
+    expected: Baiankhongor
+  - source: Баянтал
+    expected: Baiantal
+  - source: Баяндэлгэр Сум
+    expected: Baiandêlgêr Sum
+  - source: Баяндэлгэр
+    expected: Baiandêlgêr
+  - source: Баян-Өндөр Сум
+    expected: Baian-Öndör Sum
+  - source: Баруун-Урт Сум
+    expected: Baruun-Urt Sum
+  - source: Баруун-Урт
+    expected: Baruun-Urt
+  - source: Архуст
+    expected: Arkhust
+  - source: Арвайхээр Сум
+    expected: Arvaĭkhêêr Sum
+  - source: Арвайхээр
+    expected: Arvaĭkhêêr
+  - source: Есөнбулаг Сум
+    expected: Esönbulag Sum
+  - source: Ерөө Сум
+    expected: Eröö Sum
+  - source: Есөнзүйл Сум
+    expected: Esönzüĭl Sum
+  - source: Ноён Сум
+    expected: Noën Sum
+  - source: Родник Балянгийн-Булак
+    expected: Rodnik Baliangiĭn-Bulak
+  - source: Замын-Үүд Сум
+    expected: Zamyn-Üüd Sum
+  - source: Адаацаг Сум
+    expected: Adaatsag Sum
+  - source: Чандмань Сум
+    expected: Chandmani Sum
+  - source: Хяргас Сум
+    expected: Khiargas Sum
+  - source: Еэвэн, ерөөл
+    expected: Eêvên, erööl
+  - source: Ёроол, оёдол
+    expected: Ërool, oëdol
+  - source: Пуужин, апарат
+    expected: Puuzhin, aparat
+  - source: Фото, фонд
+    expected: Foto, fond
+  - source: Щедрин, щорс
+    expected: Shchedrin, shchors
+  - source: Оръё, суръя, гаръя
+    expected: Or“ë, sur“ia, gar“ia
+  - source: Юм, юүдэн
+    expected: Ium, iuüdên
+  - source: Ямар, ядуу, ая
+    expected: Iamar, iaduu, aia
+
+map:
+
+  characters:
+    "А": "A"      # \u0410
+    "Б": "B"      # \u0411
+    "В": "V"      # \u0412
+    "Г": "G"      # \u0413
+    "Д": "D"      # \u0414
+    "Е": "E"      # \u0415
+    "Ё": "Ë"      # \u0401
+    "Ж": "Zh"     # \u0416
+    "З": "Z"      # \u0417
+    "И": "I"      # \u0418
+    "Й": "Ĭ"      # \u0419
+    "К": "K"      # \u041a
+    "Л": "L"      # \u041b
+    "М": "M"      # \u041c
+    "Н": "N"      # \u041d
+    "О": "O"      # \u041e
+    "Ө": "Ö"      # \u04e8
+    "П": "P"      # \u041f
+    "Р": "R"      # \u0420
+    "С": "S"      # \u0421
+    "Т": "T"      # \u0422
+    "У": "U"      # \u0423
+    "Ү": "Ü"      # \u04ae
+    "Ф": "F"      # \u0424
+    "Х": "Kh"     # \u0425
+    "Ц": "Ts"     # \u0426
+    "Ч": "Ch"     # \u0427
+    "Ш": "Sh"     # \u0428
+    "Щ": "Shch"   # \u0429
+    "Ъ": "“"      # \u042a
+    "Ы": "Y"      # \u042b
+    "Ь": "I"      # \u042c
+    "Э": "Ê"      # \u042d
+    "Ю": "Iu"     # \u042e
+    "Я": "Ia"     # \u042f
+    "а": "a"      # \u0430
+    "б": "b"      # \u0431
+    "в": "v"      # \u0432
+    "г": "g"      # \u0433
+    "д": "d"      # \u0434
+    "е": "e"      # \u0435
+    "ё": "ë"      # \u0451
+    "ж": "zh"     # \u0436
+    "з": "z"      # \u0437
+    "и": "i"      # \u0438
+    "й": "ĭ"      # \u0439
+    "к": "k"      # \u043a
+    "л": "l"      # \u043b
+    "м": "m"      # \u043c
+    "н": "n"      # \u043d
+    "о": "o"      # \u043e
+    "ө": "ö"      # \u04e9
+    "п": "p"      # \u043f
+    "р": "r"      # \u0440
+    "с": "s"      # \u0441
+    "т": "t"      # \u0442
+    "у": "u"      # \u0443
+    "ү": "ü"      # \u04af
+    "ф": "f"      # \u0444
+    "х": "kh"     # \u0445
+    "ц": "ts"     # \u0446
+    "ч": "ch"     # \u0447
+    "ш": "sh"     # \u0448
+    "щ": "shch"   # \u0449
+    "ъ": "“"      # \u044a
+    "ы": "y"      # \u044b
+    "ь": "i"      # \u044c
+    "э": "ê"      # \u044d
+    "ю": "iu"     # \u044e
+    "я": "ia"     # \u044f