interscript 0.1.6 → 0.1.7

data/maps/alalc-mal-Mlym-Latn-2012.yaml

@@ -0,0 +1,73 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:mal
+source_script: Mlym
+destination_script: Latn
+name: Malayalam Romanization, 2012
+alias:
+  ogc11122:
+    code: mal_Mlym2Latn_ALA_2012
+    description: Malayalam ALA-Library of Congress 2012 System
+url: https://www.loc.gov/catdir/cpso/romanization/malayalam.pdf
+creation_date: 2012
+description: |
+  ALA-LC Romanization table for Malayalam
+
+
+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.
+
+  - When  ് is used in combination with the vowel u (ഉ്), the combination is also transliterated ȧ.
+
+  - |
+    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
+    b) when the absence of any vowel is indicated by the superscript sign  ് (also used for the vowel ȧ); and
+    c) when the following modified consonantal forms are used:
+      ൿ  k
+      ൻ  n
+      ൾ  ḷ
+      ൺ  ṇ
+      ൽ  l
+      ർ   r
+  - When റ റ appears as a subscript in a cluster (റ്റ), it is transliterated ta.
+
+  - |
+    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.
+
+tests:
+  - source: "ബാർ കോഴ ആവിയായി; മകൻ മാണിയെ വ്യക്തിഹത്യ നടത്തിയവരുടെ കൂടാരത്തിൽ"
+    expected: "bār kōḻa āviyāyi; makan māṇiye vŭyakŭtihatŭya naṭatŭtiyavaruṭe kūṭāratŭtil"
+  - source: "മിഷൻ ശക്തി, ഓപറേഷൻ ശക്തി'; മുഖം മിനുക്കാൻ സ്ത്രീസുരക്ഷാ പദ്ധതികളുമായി"
+    expected: "miṣan śakŭti, ōpaṟēṣan śakŭti'; mukhaṃ minukŭkān sŭtŭrīsurakŭṣā padŭdhatikaḷumāyi"
+  - source: "സംസ്ഥാനത്ത് ബുധനാഴ്ച 6,244 പേര്‍ക്ക് കോവിഡ്; ൫൭൪൫ പേര്‍ക്ക് രോഗം സമ"
+    expected: "saṃsŭthānatŭtŭ budhanāḻŭca 6,244 pērŭkŭkŭ kōvid̂ŭ; 5745 pērŭkŭkŭ rēāgaṃ sama"
+  - source: "ശബരിമല തീര്‍ഥാടനം: സ്‌പെഷല്‍ കമ്മീഷ്ണറുടെ റിപ്പോര്‍ട്ട് ഹൈകോടതിയില്‍"
+    expected: "śabarimala tīrŭthāṭanaṃ: sŭpeṣalŭ kamŭmīṣŭṇaṟuṭe ṟipŭpōrŭṭŭṭŭ haikōṭatiyilŭ"
+  - source: "സജ്‌ന ഷാജിക്ക് ഐക്യദാര്‍ഢ്യവുമായി സന്തോഷ് കീഴാറ്റൂര്‍ ബിരിയാണി വില്‍ക്കും"
+    expected: "sajŭna ṣājikŭkŭ aikŭyadārŭḍhŭyavumāyi sanŭtōṣŭ kīḻāṟŭṟūrŭ biriyāṇi vilŭkŭkuṃ"
+  - source: "ആനപ്പുറത്തിരുന്ന് യോഗാഭ്യാസത്തിനിടെ ബാബ രാംദേവ് നിലത്തുവീണു"
+    expected: "ānapŭpuṟatŭtirunŭnŭ yēāgābhŭyāsatŭtiniṭe bāba rāṃdēvŭ nilatŭtuvīṇu"
+  - source: "സാധാരണക്കാരെൻറ ദീപാവലി നിങ്ങളുടെ കൈയിൽ; മൊറട്ടോറിയം കേസിൽ കേന്ദ്രത്തോട് സുപ്രീംകോടതി"
+    expected: "sādhāraṇakŭkārenṟa dīpāvali niṅŭṅaḷuṭe kaiyil; meāṟaṭŭṭēāṟiyaṃ kēsil kēnŭdŭratŭtēāṭŭ supŭrīṃkēāṭati"
+  - source: "മാണി ഉണ്ടായിരുന്നെങ്കിൽ ഇത്തരമൊരു തീരുമാനം എടുക്കില്ല, ഈ രാഷ്ട്രീയ വഞ്ചന അദ്ദേഹത്തിന്‍റെ ആത്മാവ് പൊറുക്കില്ല"
+    expected: "māṇi uṇŭṭāyirunŭneṅŭkil itŭtaramoru tīrumānaṃ eṭukŭkilŭla, ī rāṣŭṭŭrīya vañŭcana adŭdēhatŭtinŭṟe ātŭmāvŭ poṟukŭkilŭla"
+  - source: "ധാർമികത വിളമ്പണ്ട, എം.പി, എം.എൽ.എ സ്ഥാനങ്ങൾ രാജിവെക്കൂ എന്ന് ജോസ് കെ. മാണിയോട് ഷാഫി"
+    expected: "dhārmikata viḷamŭpaṇŭṭa, eṃ.pi, eṃ.el.e sŭthānaṅŭṅaḷ rājivekŭkū enŭnŭ jōsŭ ke. māṇiyōṭŭ ṣāphi"
+  - source: "ഞങ്ങൾ ബോക്സിൽ നിന്നും ഒന്നും ഒഴിവാക്കില്ല; ആപ്പിളിനെ ട്രോളി ഷവോമി"
+    expected: "ñaṅŭṅaḷ bēākŭsil ninŭnuṃ onŭnuṃ oḻivākŭkilŭla; āpŭpiḷine ṭŭrēāḷi ṣavēāmi"
+
+
+map:
+
+  inherit: 'alalc-mal-Mlym-Latn-1997'

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

@@ -1,11 +1,15 @@
 ---
 authority_id: alalc
 id: 1997
-language: hin
+language: iso-639-2:mar
 source_script: Deva
 destination_script: Latn
 name: Marathi Romanization, 1997
-url: https://www.loc.gov/catdir/cpso/romanization/marathi.pdf
+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
@@ -57,6 +61,8 @@ tests:
     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:
 
@@ -168,3 +174,16 @@ map:
     'ो': "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

@@ -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

data/maps/{alalc-pan-Deva-Latn-1997.yaml → alalc-pan-Guru-Latn-1997.yaml}

@@ -1,11 +1,15 @@
 ---
 authority_id: alalc
 id: 1997
-language: pan
-source_script: Deva
+language: iso-639-2:pan
+source_script: Guru
 destination_script: Latn
 name: Panjabi Romanization, 1997
-url: https://www.loc.gov/catdir/cpso/romanization/panjabi.pdf
+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
@@ -64,7 +68,7 @@ tests:
     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: "102 ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ"
+  - 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"
@@ -235,3 +239,18 @@ map:
 
     # Aspirate
     'ੱਹ': 'hha'
+
+
+    # digits
+
+    '੦': '0'
+    '੧': '1'
+    '੨': '2'
+    '੩': '3'
+    '੪': '4'
+    '੫': '5'
+    '੬': '6'
+    '੭': '7'
+    '੮': '8'
+    '੯': '9'
+