interscript 0.1.9 → 2.0.5

data/maps/un-asm-Beng-Latn-1972.yaml

@@ -1,223 +0,0 @@
----
-authority_id: un
-id: 1972
-language: iso-639-2:ben
-source_script: Beng
-destination_script: Latn
-name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Assamese Romanization, Version 4.0
-url: https://www.eki.ee/wgrs/rom1_as.htm
-creation_date: 1972
-confirmation_date: 2016
-description: |
-  The United Nations recommended system was approved in 1972 (II/11) and amended in 1977 (III/12),
-  based on a report prepared by D. N. Sharma. The tables and their corrections were published in
-  volume II of the conference reports.
-
-  There is no evidence of the use of the system either in India or in international cartographic products.
-
-  Assamese (Asamīyā) uses an alphasyllabic script whereby each character represents a syllable rather
-  than one sound. Vowels and diphthongs are marked in two ways: as independent characters (used syllable-initially)
-  and in an abbreviated form, to denote vowels after consonants. The romanization table is unambiguous but the user
-  would have to recognize many ligatures not given in the original table. The system is mostly reversible but there
-  exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters) and consonants
-  (ligatures vs. character sequences).
-
-  References
-
-  Second United Nations Conference on the Standardization of Geographical Names.
-  London, 10–31 May 1972. Vol. II. Technical papers. United Nations. New York 1974, pp. 141–142.
-
-  Third United Nations Conference on the Standardization of Geographical Names. Athens,
-  17 August – 7 September 1977. Vol. II, Technical papers, pp. 393 etc.
-
-notes:
-   - |
-     ু Exceptions: গু gu; রু ru; শু shu; হু hu; ন্তু ntu; স্তু stu.
-   - |
-     ূ Exceptions: রূ rū.
-   - |
-     ৃ Exceptions: হৃ hṛ.
-   - |
-     ্‌  Pronunciation without a vowel; special form: ৎ t.
-   - |
-     Dotted variants of the characters: ড় ṙa; ঢ় ṙha; য় ya.
-
-tests:
-  - source: "অসমীয়া কবিতা"
-    expected: "asamīyā kabitā"
-  - source: "কবিৰ আজি জন্মদিন"
-    expected: "kabira āji janmadina"
-  - source: "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড"
-    expected: "beruṭata emāhara pāchhate punara bhayaṁkara agnikāṇḍa"
-  - source: "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ"
-    expected: "bhaṅāra biruddhe āvedana dākhila kaṁganāra"
-  - source: "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি"
-    expected: "āpuni paṙhi bhāla pāba parā bātari"
-  - source: "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক"
-    expected: "shrīrāmapurata garubharti ṭrāka jabda, dujanaka āṭaka"
-  - source: "কেনে আছে প্ৰাক্তন"
-    expected: "kene āchhe prāktana"
-  - source: "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ"
-    expected: "kamumbāira meyarara dehata kobhiḍa pajiṭibha"
-  - source: "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা"
-    expected: "ṭuiṭāraj̱oge khoda sadarī kare ei kathā"
-  - source: "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়"
-    expected: "lakhimapura jilāra nārāyaṇapurara barapathārata āji prashānti dhāma nāmere ekhana bṛddhāshramara shubhārambha karā haya"
-
-map:
-  rules:
-    - pattern: ([ক]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'k'
-    - pattern: ([খ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'kh'
-    - pattern: ([গ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'g'
-    - pattern: ([ঘ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'gh'
-    - pattern: ([ঙ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṅ'
-    - pattern: ([চ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ch'
-    - pattern: ([ছ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'chh'
-    - pattern: ([জ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'j'
-    - pattern: ([ঝ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'jh'
-    - pattern: ([ঞ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ñ'
-    - pattern: ([ট]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṭ'
-    - pattern: ([ঠ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṭh'
-    - pattern: ([ড]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ḍ'
-    - pattern: ([ঢ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ḍh'
-    - pattern: ([ণ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṇ'
-    - pattern: ([ত]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   't'
-    - pattern: ([থ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'th'
-    - pattern: ([দ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'd'
-    - pattern: ([ধ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'dh'
-    - pattern: ([ন]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'n'
-    - pattern: ([প]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'p'
-    - pattern: ([ফ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ph'
-    - pattern: ([ব]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'b'
-    - pattern: ([ভ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'bh'
-    - pattern: ([ম]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'm'
-    - pattern: ([য]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'j̱'
-    - pattern: ([ৰ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'r'
-    - pattern: ([ল]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'l'
-    - pattern: ([ৱ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'v'
-    - pattern: ([শ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'sh'
-    - pattern: ([ষ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṣh'
-    - pattern: ([স]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   's'
-    - pattern: ([হ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'h'
-    - pattern: ([ড়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṙ'
-    - pattern: ([ঢ়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṙh'
-    - pattern: ([য়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'y'
-    - pattern: ([ড়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṙ'
-    - pattern: ([ঢ়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'ṙh'
-    - pattern: ([য়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
-      result:   'y'
-
-  characters:
-
-    # I. Independent vowel characters
-    'অ': 'a'
-    'আ': 'ā'
-    'ই': 'i'
-    'ঈ': 'ī'
-    'উ': 'u'
-    'ঊ': 'ū'
-    'ঋ': 'ṛ'
-    'এ': 'e'
-    'ঐ': 'ai'
-    'ও': 'o'
-    'ঔ': 'au'
-
-    # II. Abbreviated vowel characters
-    '\u09be': 'ā'
-    '\u09bf': 'i'
-    '\u09c0': 'ī'
-    '\u09c1': 'u'
-    '\u09c2': 'ū'
-    '\u09c3': 'ṛ'
-    '\u09c7': 'e'
-    '\u09c8': 'ai'
-    '\u09cb': 'o'
-    '\u09cc': 'au'
-
-    # III. Other symbols
-    '\u0982':	'ṁ'
-    '\u0981':	'm̐'
-    '\u0983':	'ḥ'
-    '\u09cd': ''
-
-    # IV. Consonant characters
-    'ক': 'ka'
-    'খ': 'kha'
-    'গ': 'ga'
-    'ঘ': 'gha'
-    'ঙ': 'ṅa'
-    'চ': 'cha'
-    'ছ': 'chha'
-    'জ': 'ja'
-    'ঝ': 'jha'
-    'ঞ': 'ña'
-    'ট': 'ṭa'
-    'ঠ': 'ṭha'
-    'ড': 'ḍa'
-    'ঢ': 'ḍha'
-    'ণ': 'ṇa'
-    'ত': 'ta'
-    'থ': 'tha'
-    'দ': 'da'
-    'ধ': 'dha'
-    'ন': 'na'
-    'প': 'pa'
-    'ফ': 'pha'
-    'ব': 'ba'
-    'ভ': 'bha'
-    'ম': 'ma'
-    'য': 'j̱a'
-    'ৰ': 'ra'
-    'ল': 'la'
-    'ৱ': 'va'
-    'শ': 'sha'
-    'ষ': 'ṣha'
-    'স': 'sa'
-    'হ': 'ha'
-    'ৎ': 't'
-
-    # Note V Dotted variants
-    'ড়': 'ṙa'
-    'ঢ়': 'ṙha'
-    'য়': 'ya'
-    'য়': 'ya'
-    'ড়': 'ṙa'
-    'ঢ়': 'ya'

data/maps/un-bel-Cyrl-Latn-2007.yaml

@@ -1,114 +0,0 @@
----
-authority_id: un
-id: 2007
-language: iso-639-2:bel
-source_script: Cyrl
-destination_script: Latn
-name: National System of Geographic Names Transmission into Roman Alphabet in Belarus
-url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/9th-uncsgn-docs/crp/9th_UNCSGN_e-conf-98-crp-21.pdf
-creation_date: 2007
-description: |
-  RESOLUTION OF THE STATE COMMITTEE
-  ON PROPERTY OF THE REPUBLIC OF BELARUS June 11, 2007 No. 38
-
-  8/16668 (06/18/2007) On amendments and additions to the Instructions
-  for the transliteration of geographical names of the
-  Republic of Belarus in letters of the Latin alphabet
-
-  Based on the Regulation on the State Property Committee of the Republic of Belarus,
-  approved by the Decree of the Council of Ministers of the Republic of Belarusdated July 29, 2006
-  No. 958 "Issues of the State Committee on Property of the Republic of Belarus"
-tests: # the same as "by-bel-cyrl-Latn-2007"
-  - source: Аршанскi
-    expected: Aršanski
-  - source: Бешанковічы
-    expected: Biešankovičy
-  - source: Віцебск
-    expected: Viciebsk
-  - source: Гомель
-    expected: Homieĺ
-  - source: Гаўя
-    expected: Haŭja
-  - source: Добруш
-    expected: Dobruš
-  - source: Ельск
-    expected: Jeĺsk
-  - source: Бабаедава
-    expected: Babajedava
-  - source: Венцавічы
-    expected: Viencavičy
-  - source: Ёды
-    expected: Jody
-  - source: Вераб'ёвічы
-    expected: Vierabjovičy
-  - source: Мёры
-    expected: Miory
-  - source: Зэльва
-    expected: Zeĺva
-  - source: Iванава
-    expected: Ivanava
-  - source: Iўе
-    expected: Iŭje
-  - source: Лагойск
-    expected: Lahojsk
-  - source: Круглае
-    expected: Kruhlaje
-  - source: Лошыца
-    expected: Lošyca
-  - source: Любань
-    expected: Liubań
-  - source: Магілёў
-    expected: Mahilioŭ
-  - source: Нясвіж
-    expected: Niasviž
-  - source: Орша
-    expected: Orša
-  - source: Паставы
-    expected: Pastavy
-  - source: Рагачоў
-    expected: Rahačoŭ
-  - source: Смаргонь
-    expected: Smarhoń
-  - source: Талачын
-    expected: Talačyn
-  - source: Узда
-    expected: Uzda
-  - source: Шаркаўшчына
-    expected: Šarkaŭščyna
-  - source: Фаніпаль
-    expected: Fanipaĺ
-  - source: Хоцімск
-    expected: Chocimsk
-  - source: Цёмны Лес
-    expected: Ciomny Lies
-  - source: Чавусы
-    expected: Čavusy
-  - source: Шумілiна
-    expected: Šumilina
-  - source: Чыгірынка
-    expected: Čyhirynka
-  - source: Чэрвень
-    expected: Červień
-  - source: Друць
-    expected: Druć
-  - source: Чачэрск
-    expected: Čačersk
-  - source: Юхнаўка
-    expected: Juchnaŭka
-  - source: Гаюціна
-    expected: Hajucina
-  - source: Цюрлi
-    expected: Ciurli
-  - source: Любонічы
-    expected: Liuboničy
-  - source: Ямнае
-    expected: Jamnaje
-  - source: Баяры
-    expected: Bajary
-  - source: Валяр'яны
-    expected: Valiarjany
-  - source: Вязынка
-    expected: Viazynka
-
-map:
-  inherit: "by-bel-Cyrl-Latn-2007"

data/maps/un-ben-Beng-Latn-2016.yaml

@@ -1,534 +0,0 @@
----
-authority_id: un
-id: 2016
-language: iso-639-2:ben
-source_script: Beng
-destination_script: Latn
-name: Bengali Romanization, Version 4.0
-url: http://www.eki.ee/wgrs/rom1_bn.htm
-creation_date: 2016
-description: |
-  The United Nations recommended system was approved in 1972 (II/11)
-  and amended in 1977 (III/12), based on a report prepared by D. N.
-  Sharma. The tables and their corrections were published in volume II of
-  the conference reports1,2.
-
-  There is no evidence of the use of the system either in Bangladesh,
-  in India or in international cartographic products. The resolution
-  IV/17 (1982) recommended association, inter alia, with Bangladesh, in
-  carrying out further studies on the system.
-
-  Bengali (Bānglā) uses an alphasyllabic script whereby each character
-  represents a syllable rather than one sound. Vowels and diphthongs are
-  marked in two ways: as independent characters (used syllable-initially)
-  and in an abbreviated form, to denote vowels after consonants. The
-  romanization table is unambiguous but the user would have to recognize
-  many ligatures not given in the original table. The system is mostly
-  reversible but there exist some ambiguities in the romanization of
-  vowels (independent vs. abbreviated characters) and consonants
-  (ligatures vs. character sequences).
-
-  Other systems of romanization
-
-  For differences between the UN system and the ISO transliteration
-  standard ISO 15919: 2001 see the section on the romanization of Hindi.
-
-  References
-
-  Second United Nations Conference on the Standardization of
-  Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers.
-  United Nations. New York 1974, pp. 139–140.
-
-  Third United Nations Conference on the Standardization of
-  Geographical Names. Athens, 17 August – 7 September 1977. Vol. II,
-  Technical papers, pp. 393 etc.
-
-notes:
-  - |
-    In the romanization system below character variations and the table of ligatures have been added.
-
-    I. Independent vowel characters
-
-    1	অ	a
-    2	আ	ā
-    3	ই	i
-    4	ঈ	ī
-    5	উ	u
-    6	ঊ	ū
-    7	ঋ	ṛ
-    8	এ	e
-    9	ঐ	ai
-    10	ও	o
-    11	ঔ	au
-
-
-
-
-  - Where two Roman equivalents are given, the second (in brackets) is
-    used for recording the pronunciation of place-names while the first
-    form is for general use.
-  - In the table only word-initial character variants are shown.
-    Depending on the position in the word many variants of the characters
-    are used as well as some ligatures. These features are not covered here.
-  - For technical reasons the characters of the Mongolian script are
-    turned 90˚ anti-clockwise.
-
-tests:
-  - source: "র্ক"
-    expected: "rka"
-  - source: "গ্র"
-    expected: "gra"
-  - source: "ত্য"
-    expected: "tya"
-
-  - source: |
-      আমার সোনার বাংলা, আমি তোমায় ভালোবাসি।
-      চিরদিন তোমার আকাশ, তোমার বাতাস, আমার প্রাণে বাজায় বাঁশি॥
-      ও মা, ফাগুনে তোর আমের বনে ঘ্রাণে পাগল করে, মরি হায়, হায় রে—
-      ও মা, অঘ্রাণে তোর ভরা ক্ষেতে আমি কী দেখেছি মধুর হাসি॥
-
-      কী শোভা, কী ছায়া গো, কী স্নেহ, কী মায়া গো—
-      কী আঁচল বিছায়েছ বটের মূলে, নদীর কূলে কূলে।
-      মা, তোর মুখের বাণী আমার কানে লাগে সুধার মতো,
-      মরি হায়, হায় রে—
-      মা, তোর বদনখানি মলিন হলে, ও মা, আমি নয়নজলে ভাসি॥
-
-    # Note: There are still couple of improvements we can do in the
-    # transilation system, but for now this could work
-    #
-    # But please revisit this - specially the use case of `য়`, it's adding
-    # some mixed character in the text.
-    #
-    expected: |
-      āmaāra saonaāra baāṁlaā, āmai taomaāj̱aA় bhaālaobaāsai।
-      chairadaina taomaāra ākaāsha, taomaāra baātaāsa, āmaāra praāṇae baājaāj̱aA় baām̐shai॥
-      o maā, phaāgaunae taora āmaera banae ghraāṇae paāgala karae, marai haāj̱aA়, haāj̱aA় rae—
-      o maā, aghraāṇae taora bharaā kṣhaetae āmai kaī daekhaechhai madhaura haāsai॥
-
-      kaī shaobhaā, kaī chhaāj̱aA়ā gao, kaī snaeha, kaī maāj̱aA়ā gao—
-      kaī ām̐chala baichhaāj̱aA়echha baṭaera maūlae, nadaīra kaūlae kaūlae।
-      maā, taora maukhaera baāṇaī āmaāra kaānae laāgae saudhaāra matao,
-      marai haāj̱aA়, haāj̱aA় rae—
-      maā, taora badanakhaānai malaina halae, o maā, āmai naj̱aA়najalae bhaāsai॥
-
-map:
-  characters:
-
-    # I. Independent vowel characters
-
-    'অ': 'a'	 # 1
-    'আ': 'ā'	# 2
-    'ই': 'i'	 # 3
-    'ঈ': 'ī'	 # 4
-    'উ': 'u'	 # 5
-    'ঊ': 'ū'	 # 6
-    'ঋ': 'ṛ'	 # 7
-    'এ': 'e'	 # 8
-    'ঐ': 'ai'	# 9
-    'ও': 'o'	 # 10
-    'ঔ': 'au'	# 11
-
-    # II. Abbreviated vowel characters (ক stands for any consonant character)
-
-    # 'ক': 'a'   # 1
-    '\u09be': 'ā'	  # 2 কা
-    '\u09bf': 'i'	  # 3 কি
-    '\u09c0': 'ī'	  # 4 কী
-    '\u09c1': 'u'   # 5 কু Exceptions: গু gu; রু ru; শু shu; হু hu; ন্তু ntu; স্তু stu.
-    '\u09c2': 'ū'   # 6 কূ Exception: রূ rū.
-    '\u09c3': 'ṛ'   # 7 কৃ Exception: হৃ hṛ.
-    '\u09c7': 'e'	  # 8 কে
-    '\u09c8': 'ai'	# 9 কৈ
-    '\u09cb': 'o'	  # 10 কো
-    '\u09cc': 'au'	# 11 কৌ
-
-    # II 5 Exceptions
-    'গু': 'gu'
-    'রু': 'ru'
-    'শু': 'shu'
-    'হু': 'hu'
-    'ন্তু': 'ntu'
-    'স্তু': 'stu'
-    # II 6 Exceptions
-    'রূ': 'rū'
-    # II 7 Exceptions
-    'হৃ': 'hṛ'
-
-    # III. Other symbols (ক stands for any consonant character)
-
-    '\u0982':	'ṁ'	  # 1 কং
-    '\u0981':	'm̐'	  # 2 কঁ
-    '\u0983':	'ḥ'	  # 3 কঃ
-    '\u09cd\u200c': ''	 # 4 ক্‌ Pronunciation without a vowel; special form: ৎ t.
-
-    # III 4 special form
-    'ৎ': 't'
-
-    # IV. Consonant characters
-
-    'ক': 'ka'		# 1
-    'খ': 'kha'	# 2
-    'গ': 'ga'		# 3
-    'ঘ': 'gha'	# 4
-    'ঙ': 'ṅa'		# 5
-    'চ': 'cha'	# 6
-    'ছ': 'chha' # 7
-    'জ': 'ja'		# 8
-    'ঝ': 'jha'	# 9
-    'ঞ': 'ña'	# 10
-    'ট': 'ṭa'	  # 11
-    'ঠ': 'ṭha' 	# 12
-    'ড': 'ḍa'	# 13 A Dotted variants of the characters: ড় ṙa; ঢ় ṙha; য় ya.
-    'ঢ': 'ḍha'	# 14 A Dotted variants of the characters: ড় ṙa; ঢ় ṙha; য় ya.
-    'ণ': 'ṇa'		# 15
-    'ত': 'ta'		# 16
-    'থ': 'tha'	# 17
-    'দ': 'da'		# 18
-    'ধ': 'dha'	# 19
-    'ন': 'na'		# 20
-    'প': 'pa'		# 21
-    'ফ': 'pha'	# 22
-    'ব': 'ba'		# 23
-    'ভ': 'bha'	# 24
-    'ম': 'ma'		# 25
-    'য': 'j̱aA'	# 26
-    'র': 'ra'		# 27
-    'ল': 'la'		# 28
-    'শ': 'sha'	# 29
-    'ষ': 'ṣha'	# 30
-    'স': 'sa'		# 31
-    'হ': 'ha'		# 32
-
-    # IV 13, 14
-    'ড়': 'ṙa'
-    'ঢ়': 'ṙha'
-    'য়': 'ya'
-
-
-    # V. Ligatures
-    # Adscript forms of some consonants
-    #
-    # We already implemented one to one mapping for most commonly used
-    # combined letters - (Zuktabarna), so we can ignore this custom rules
-    # fro now.
-    #
-    # 'র্‍':	'r-:'
-    # '‍্র':	'-r:'
-    # '‍্য':	'-y:'
-
-
-    # Other ligatures (the list is not complete)
-
-    'ক্ক': 'kka'
-    'ক্ট': 'kṭa'
-    'ক্ত': 'kta'
-    'ক্ন': 'kna'
-    'ক্ম': 'kma'
-    'ক্র': 'kra'
-    'ক্ল': 'kla'
-    'ক্ব': 'kva'
-    'ক্ষ': 'kṣha'
-    'ক্ষ্ন': 'kṣhna'
-    'ক্ষ্ম': 'kṣhma'
-    'ক্ষ্ব': 'kṣhva'
-
-    'ক্স': 'ksa'
-    'গ্গ': 'gga'
-    'গ্দ': 'gda'
-    'গ্ধ': 'gdha'
-    'গ্ন': 'gna'
-    'গ্ম': 'gma'
-    'গ্র': 'gra'
-    'গ্ল': 'gla'
-    'ঘ্র': 'ghra'
-    'ঙ্ক': 'ṅka'
-    'ঙ্গ': 'ṅga'
-    'চ্চ': 'chcha'
-
-    'চ্ছ': 'chchha'
-    'চ্ছ্ব': 'chchhva'
-    'চ্ঞ': 'chña'
-    'জ্জ': 'jja'
-    'জ্জ্ব': 'jjva'
-    'জ্ঝ': 'jjha'
-    'জ্ঞ': 'jña'
-    'জ্ব': 'jva'
-    'ঞ্চ': 'ñcha'
-    'ঞ্ছ': 'ñchha'
-    'ঞ্জ': 'ñja'
-    'ঞ্ঝ': 'ñjha'
-
-    'ট্ট': 'ṭṭa'
-    'ড্ড': 'ḍḍa'
-    'ণ্ট': 'ṇṭa'
-    'ণ্ঠ': 'ṇṭha'
-    'ণ্ড': 'ṇḍa'
-    'ত্ত': 'tta'
-    'ত্ত্ব': 'ttva'
-    'ত্থ': 'ttha'
-    'ত্ন': 'tna'
-    'ত্ম': 'tma'
-    'ত্র': 'tra'
-    'ত্ল': 'tla'
-
-    'ত্ব': 'tva'
-    'দ্দ': 'dda'
-    'দ্দ্ব': 'ddva'
-    'দ্ধ': 'ddha'
-    'দ্ধ্ব': 'ddhva'
-    'দ্ন': 'dna'
-    'দ্ব': 'dva'
-    'দ্ভ': 'dbha'
-    'দ্ম': 'dma'
-    'দ্র': 'dra'
-    'দ্ল': 'dla'
-    'ধ্র': 'dhra'
-
-    'ন্ঠ': 'nṭha'
-    'ন্ড': 'nḍa'
-    'ন্ক': 'nka'
-    'ন্ত': 'nta'
-    'ন্ত্র': 'ntra'
-    'ন্থ': 'ntha'
-    'ন্দ': 'nda'
-    'ন্দ্র': 'ndra'
-    'ন্ধ': 'ndha'
-    'ন্ন': 'nna'
-    'ন্ম': 'nma'
-    'ন্ব': 'nva'
-
-    'প্ন': 'pna'
-    'প্ত': 'pta'
-    'প্প': 'ppa'
-    'প্র': 'pra'
-    'প্ল': 'pla'
-    'ফ্র': 'phra'
-    'ব্জ': 'bja'
-    'ব্দ': 'bda'
-    'ব্ধ': 'bdha'
-    'ব্ব': 'bba'
-    'ব্র': 'bra'
-    'ভ্র': 'bhra'
-    'ম্প': 'mpa'
-    'ম্ব': 'mba'
-    'ম্ভ': 'mbha'
-    'ম্ভ্র': 'mbhra'
-    'ম্ম': 'mma'
-    'ম্র': 'mra'
-    'ম্ল': 'mla'
-    'ল্ক': 'lka'
-    'ল্ট': 'lṭa'
-    'ল্ড': 'lḍa'
-    'ল্ম': 'lma'
-    'ল্ল': 'lla'
-
-    'শ্চ': 'shcha'
-    'শ্ছ': 'shchha'
-    'শ্ত': 'shta'
-    'শ্ন': 'shna'
-    'শ্ম': 'shma'
-    'শ্র': 'shra'
-    'শ্ল': 'shla'
-    'শ্ব': 'shva'
-    'ষ্ক': 'ṣhka'
-    'ষ্ট': 'ṣhṭa'
-    'ষ্ট্র': 'ṣhṭra'
-    'ষ্ঠ': 'ṣhṭha'
-
-    'ষ্ঞ': 'ṣhña'
-    'ষ্প': 'ṣhpa'
-    'ষ্ফ': 'ṣhpha'
-    'স্ক': 'ska'
-    'স্ক্র': 'skra'
-    'স্খ': 'skha'
-    'স্ত': 'sta'
-    'স্ন': 'sna'
-    'স্ম': 'sma'
-    'স্র': 'sra'
-    'স্ব': 'sva'
-    'হ্ন': 'hna'
-
-    'হ্ম': 'hma'
-    'হ্র': 'hra'
-    'হ্ল': 'hla'
-
-    # Zuktabarna - combined letters
-    #
-    # The followings are not the official list, but this has been
-    # collected and varified from some reliable source.
-    # Source: https://www.somewhereinblog.net/blog/trivuzblog/28849694
-    #
-    'ক্ট্র': 'kṭra'
-    'ক্ত্র': 'ktra'
-    'ক্য': 'kya'
-    'ক্ষ্ণ': 'kṣṇa'
-    'ক্ষ্ম': 'kṣma'
-    'খ্য': 'khaj̱a'
-    'খ্র': 'khra'
-    'গ্ন': 'gna'
-    'গ্‌ণ': 'gṇa'
-    'গ্ধ্য': 'gdhya'
-    'গ্ধ্র': 'gdhra'
-    'গ্ন্য': 'gnya'
-    'গ্ব': 'gva'
-    'গ্য': 'gya'
-    'গ্র্য': 'grya'
-    'ঘ্ন': 'ghna'
-    'ঘ্য': 'ghya'
-    'ঙ্‌ক্ত': 'ṅkata'
-    'ঙ্ক্য': 'ṅkaya'
-    'ঙ্ক্ষ': 'ṅkṣa'
-    'ঙ্খ': 'ṅkha'
-    'ঙ্গ্য': 'ṅgaya'
-    'ঙ্ঘ': 'ṅgha'
-    'ঙ্ঘ্য': 'ṅghya'
-    'ঙ্ঘ্র': 'ṅghra'
-    'ঙ্ম': 'ṅma'
-    'চ্ছ্র': 'cchra'
-    'চ্ব': 'cva'
-    'চ্য': 'cya'
-    'জ্য': 'jya'
-    'জ্র': 'jra'
-    'ট্ব': 'ṭva'
-    'ট্ম': 'ṭma'
-    'ট্য': 'ṭya'
-    'ট্র': 'ṭra'
-    'ড্ব': 'ḍva'
-    'ড্য': 'ḍya'
-    'ড্র': 'ḍra'
-    'ড়্গ': 'ḍga'
-    'ঢ্য': 'ḍhya'
-    'ঢ্র': 'ḍhra'
-    'ণ্ঠ্য': 'ṇṭhya'
-    'ণ্ড্য': 'ṇḍya'
-    'ণ্ড্র': 'ṇḍra'
-    'ণ্ঢ': 'ṇḍha'
-    'ণ্ণ': 'ṇṇa'
-    'ণ্ব': 'ṇva'
-    'ণ্ম': 'ṇma'
-    'ণ্য': 'ṇya'
-    'ৎক': 'tka'
-    'ত্ত্য': 'ttya'
-    'ত্ম্য': 'tmya'
-    'ত্য': 'tya'
-    'ত্র্য': 'trya'
-    'ৎল': 'tla'
-    'ৎস': 'tsa'
-    'থ্ব': 'thva'
-    'থ্য': 'thya'
-    'থ্র': 'thra'
-    'দ্গ': 'dga'
-    'দ্ঘ': 'dgha'
-    'দ্ভ্র': 'dbhra'
-    'দ্য': 'dya'
-    'দ্র্য': 'draya'
-    'ধ্ন': 'dhna'
-    'ধ্ব': 'dhva'
-    'ধ্ম': 'dhma'
-    'ধ্য': 'dya'
-    'ন্ট': 'nṭa'
-    'ন্ট্র': 'nṭra'
-    'ন্ড্র': 'nḍra'
-    'ন্ত্ব': 'ntva'
-    'ন্ত্য': 'ntaya'
-    'ন্ত্র্য': 'ntraya'
-    'ন্থ্র': 'nthra'
-    'ন্দ্য': 'ndya'
-    'ন্দ্ব': 'ndva'
-    'ন্ধ্য': 'ndhya'
-    'ন্ধ্র': 'ndhra'
-    'ন্য': 'nya'
-    'প্ট': 'pṭa'
-    'প্য': 'pya'
-    'প্র্য': 'praya'
-    'প্স': 'psa'
-    'ফ্ল': 'phla'
-    'ব্য': 'bya'
-    'ব্ল': 'bla'
-    'ভ্ব': 'bhva'
-    'ভ্য': 'bhya'
-    'ম্ন': 'mna'
-    'ম্প্র': 'mpra'
-    'ম্ফ': 'mpha'
-    'ম্ব্র': 'mvra'
-    'ম্য': 'mya'
-    'য্য': 'j̱aya'
-    'র্ক': 'rka'
-    'র্ক্য': 'rkya'
-    'র্গ্য': 'rgya'
-    'র্ঘ্য': 'rghya'
-    'র্চ্য': 'rchya'
-    'র্জ্য': 'rjya'
-    'র্ণ্য': 'rṇya'
-    'র্ত্য': 'rtya'
-    'র্থ্য': 'rthya'
-    'র্ব্য': 'rvya'
-    'র্ম্য': 'rmya'
-    'র্শ্য': 'rshya'
-    'র্ষ্য': 'rṣhya'
-    'র্হ্য': 'rhya'
-    'র্খ': 'rkha'
-    'র্গ': 'rga'
-    'র্গ্র': 'rgra'
-    'র্ঘ': 'rgha'
-    'র্চ': 'rcha'
-    'র্ছ': 'rchha'
-    'র্জ': 'rja'
-    'র্ঝ': 'rjha'
-    'র্ট': 'rṭa'
-    'র্ড': 'rḍa'
-    'র্ণ': 'rṇa'
-    'র্ত': 'rta'
-    'র্ত্র': 'rtra'
-    'র্থ': 'rtha'
-    'র্দ': 'rda'
-    'র্দ্ব': 'rdva'
-    'র্দ্র': 'rdra'
-    'র্ধ': 'rdha'
-    'র্ধ্ব': 'rdhba'
-    'র্ন': 'rna'
-    'র্প': 'rpa'
-    'র্ফ': 'rpha'
-    'র্ভ': 'rbha'
-    'র্ম': 'rma'
-    'র্য': 'rya'
-    'র্ল': 'rla'
-    'র্শ': 'rsha'
-    'র্শ্ব': 'rshba'
-    'র্ষ': 'rṣha'
-    'র্স': 'rsa'
-    'র্হ': 'rha'
-    'র্ঢ্য': 'rḍhya'
-    'ল্ক্য': 'lkaya'
-    'ল্গ': 'lga'
-    'ল্প': 'lpa'
-    'ল্‌ফ': 'lpha'
-    'ল্ফ': 'lpha'
-    'ল্ব': 'lba'
-    'ল্‌ভ': 'lbha'
-    'ল্য': 'lya'
-    'শ্য': 'sya'
-    'ষ্ক্র': 'ṣkra'
-    'ষ্ট্য': 'ṣṭya'
-    'ষ্ঠ্য': 'ṣṭhya'
-    'ষ্ণ': 'ṣṇa'
-    'ষ্প্র': 'ṣpra'
-    'ষ্ব': 'ṣva'
-    'ষ্ম': 'ṣma'
-    'ষ্য': 'ṣya'
-    'স্ট': 'sṭa'
-    'স্ট্র': 'sṭra'
-    'স্ত্ব': 'stva'
-    'স্ত্য': 'stṣya'
-    'স্ত্র': 'stra'
-    'স্থ': 'stha'
-    'স্থ্য': 'sthya'
-    'স্প': 'spa'
-    'স্প্র': 'spra'
-    'স্প্‌ল': 'spala'
-    'স্ফ': 'spha'
-    'স্য': 'sya'
-    'স্ল': 'sla'
-    'হ্ণ': 'hṇa'
-    'হ্ব': 'hva'
-    'হ্য': 'hya'