interscript 0.1.2 → 0.1.7

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

data/maps/alalc-pan-Guru-Latn-1997.yaml

@@ -0,0 +1,256 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:pan
+source_script: Guru
+destination_script: Latn
+name: Panjabi Romanization, 1997
+alias:
+  ogc11122:
+    code: pan_Deva2Latn_ALA_1997
+    description: Panjabi ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/panjabi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Panjabi
+
+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 consonant clusters and may be implicit after consonants except
+    when they are final or when another vowel is indicated by its appropriate sign. The cases in
+    which the vowel a is implicit, however, can be determined only from a knowledge of the
+    language or from suitable reference sources. In such cases the a is supplied in transliteration.
+
+  - The dotted letters (ਸ਼ ਖ਼ ਗ਼ ਜ਼ ਫ਼ ਲ਼) are used in Urdu words.
+
+  - |
+    Exception: Bindī is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - |
+    Exception: Ṭippī is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - |
+    Exception: When adhik implies the combination of a non-aspirated and an aspirated
+    consonant, the combination is transliterated as a non-aspirated, followed by an aspirated
+    consonant.
+
+tests:
+  - source: "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ"
+    expected: "pañjaāba 'ca wadha raihaā khaudakaushaīāṃ daā raujhaāna"
+  - source: "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ"
+    expected: "lakkha taoṃ paāra paujjaā saragarama kaesaāṃ daā aṅkaṛaā, daillaī 'ca dao lakkha taoṃ paāra inaphaaikaṭaiḍa"
+  - source: "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ"
+    expected: "paraiwaāraka samassaiāwaāṃ atae waiāha waī haai haora ahaima kaārana"
+  - source: "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ"
+    expected: "maradaāṃ 'ca aurataāṃ naālaoṃ waddha haai khaudakaushaī daā raujhaāna"
+  - source: "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ"
+    expected: "raāshaṭaraī paddhara 'tae pañjaāba daī sathaitaī kaāfaī saūbaiāṃ taoṃ baihatara"
+  - source: "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ"
+    expected: "caīnaī saainaā nae laāpataā arauṇaācala dae 5 naaujawaānaāṃ baārae dassaiā"
+  - source: "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ"
+    expected: "saākharataā dae maāmalae 'ca daesha 'ca 7waeṃ nam̆̐bara 'tae pañjaāba"
+  - source: "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ"
+    expected: "daillaī kamaeṭaī dae maaiṃbara shaṇṭaī nae akaālaī dala taoṃ daittaā asataīfaā"
+  - source: "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ"
+    expected: "102 haora kaoraonaā paāzaīṭaiwa maraīzaāṃ daī paushaṭaī, ika daī maauta"
+  - source: "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ"
+    expected: "saṛaka haādasae daauraāna ika daī maauta"
+
+map:
+
+  rules:
+    # note[4]
+    - pattern: \u0A02(?=[ਕਖਖ਼ਗਗ਼ਘਙ])    # ਂ  before gutturals
+      result: ṅ
+    - pattern: \u0A02(?=[ਚਛਜਜ਼ਝਞ])    # ਂ   before palatals
+      result: ñ
+    - pattern: \u0A02(?=[ਟਠਡਢਣ])    # ਂ   before cerebrals
+      result: ṇ
+    - pattern: \u0A02(?=[ਤਥਦਧਨ])    # ਂ   before dentals
+      result: n
+
+    # note[5]
+    - pattern: \u0A70(?=[ਕਖਖ਼ਗਗ਼ਘਙ])    # ੰ  before gutturals
+      result: ṅ
+    - pattern: \u0A70(?=[ਚਛਜਜ਼ਝਞ])    # ੰ  before palatals
+      result: ñ
+    - pattern: \u0A70(?=[ਟਠਡਢਣ])    # ੰ  before cerebrals
+      result: ṇ
+    - pattern: \u0A70(?=[ਤਥਦਧਨ])    # ੰ  before dentals
+      result: n
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'ਅ': 'a'
+    'ਆ': 'ā'
+    'ਇ': 'i'
+    'ਈ': 'ī'
+    'ਉ': 'u'
+    'ਊ': 'ū'
+    'ਏ': 'e'
+    'ਐ': 'ai'
+    'ਓ': 'o'
+    'ਔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ਕ': 'ka'
+    'ਖ': 'kha'
+    'ਖ਼': 'kha'
+    'ਗ': 'ga'
+    'ਗ਼': 'gha'
+    'ਘ': 'gha'
+    'ਙ': 'ṅa'
+
+    # Palatals
+    'ਚ': 'ca'
+    'ਛ': 'cha'
+    'ਜ਼': 'za'
+    'ਜ': 'ja'
+    'ਝ': 'jha'
+    'ਞ': 'ña'
+
+    # Cerebrals
+    'ਟ': 'ṭa'
+    'ਠ': 'ṭha'
+    'ਡ': 'ḍa'
+    'ਢ': 'ḍha'
+    'ਣ': 'ṇa'
+
+    # Dentals
+    'ਤ': 'ta'
+    'ਥ': 'tha'
+    'ਦ': 'da'
+    'ਧ': 'dha'
+    'ਨ': 'na'
+
+    # Labials
+    'ਪ': 'pa'
+    'ਫ': 'pha'
+    'ਫ਼': 'fa'
+    'ਬ': 'ba'
+    'ਭ': 'bha'
+    'ਮ': 'ma'
+
+    # Semivowels
+    'ਯ': 'ya'
+    'ਰ': 'ra'
+    'ਲ': 'la'
+    'ਲੵ': 'ḷa'
+    'ਲ਼': 'ḷa'
+    'ਵ': 'wa'
+    'ੜ': 'ṛa'
+
+    # Sibilants
+    'ਸ': 'sa'
+    'ਸ਼': 'sha'
+
+    # Aspirate
+    'ਹ': 'ha'
+
+    # Bindī (see Note 4)
+    'ਂ': 'ṃ'
+
+    # Ṭippī (see Note 5)
+    'ੰ': 'm̆̐'
+
+    # Medials # Needed for connecting constants
+    'ਾ': "ā"
+    'ਿ': "i"
+    'ੀ': "ī"
+    'ੁ': "u"
+    'ੂ': "ū"
+    'ੇ': "e"
+    'ੈ': "ai"
+    'ੋ': "o"
+    'ੌ': "au"
+
+    # For adhik character[Note 6]
+
+    # Gutturals
+    'ੱਕ': 'kka'
+    'ੱਖ': 'kkha'
+    'ੱਖ਼': 'kkha'
+    'ੱਗ': 'gga'
+    'ੱਗ਼': 'ggha'
+    'ੱਘ': 'ggha'
+    'ੱਙ': 'ṅṅa'
+
+    # Palatals
+    'ੱਚ': 'cca'
+    'ੱਛ': 'ccha'
+    'ੱਜ': 'jja'
+    'ੱਜ਼': 'zza'
+    'ੱਝ': 'jjha'
+    'ੱਞ': 'ñña'
+
+    # Cerebrals
+    'ੱਟ': 'ṭṭa'
+    'ੱਠ': 'ṭṭha'
+    'ੱਡ': 'ḍḍa'
+    'ੱਢ': 'ḍḍha'
+    'ੱਣ': 'ṇṇa'
+
+    # Dentals
+    'ੱਤ': 'tta'
+    'ੱਥ': 'ttha'
+    'ੱਦ': 'dda'
+    'ੱਧ': 'ddha'
+    'ੱਨ': 'nna'
+
+    # Labials
+    'ੱਪ': 'ppa'
+    'ੱਫ': 'ppha'
+    'ੱਫ਼': 'ffa'
+    'ੱਬ': 'bba'
+    'ੱਭ': 'bbha'
+    'ੱਮ': 'mma'
+
+    # Semivowels
+    'ੱਯ': 'yya'
+    'ੱਰ': 'rra'
+    'ੱਲ': 'lla'
+    'ੱਲੵ': 'ḷḷa'
+    'ੱਵ': 'wwa'
+    'ੱੜ': 'ṛṛa'
+
+    # Sibilants
+    'ੱਸ': 'ssa'
+    'ੱਸ਼': 'ssha'
+
+    # Aspirate
+    'ੱਹ': 'hha'
+
+
+    # digits
+
+    '੦': '0'
+    '੧': '1'
+    '੨': '2'
+    '੩': '3'
+    '੪': '4'
+    '੫': '5'
+    '੬': '6'
+    '੭': '7'
+    '੮': '8'
+    '੯': '9'
+