interscript 0.1.7 → 0.1.9

data/maps/odni-mkd-Cyrl-Latn-2005.yaml

@@ -0,0 +1,21 @@
+---
+authority_id: odni
+id: 2005
+language: iso-639-2:mkd
+source_script: Cyrl
+destination_script: Latn
+name: Standards for the transliteration of macedonian personal names in written reports and products
+creation_date: 2005
+confirmation_date: 2005
+description: |
+  Office of the Director Of National Intelligence Macedonian Personal Names 2004 System
+
+tests:
+  - source: Билјана
+    expected: Biljana
+  - source: Душко
+    expected: Dushko
+
+map:
+  inherit: odni-mkd-Cyrl-Latn-2015
+  rules:

data/maps/odni-prs-Arab-Latn-2004.yaml

@@ -0,0 +1,123 @@
+---
+authority_id: odni
+id: 2004
+language: iso-639-3:prs
+source_script: Arab
+destination_script: Latn
+name: Intelligence Community (IC) Standard for the Transliteration of Dari Personal Names (2004)
+url: https://github.com/interscript/interscript-private-references/blob/master/odni/Farsi_(Persian)_%26_Dari_IC_Standards.doc
+creation_date: 2004
+confirmation_date: 2004-11
+description: |
+
+notes:
+  - This standard is intended only for those Afghan names
+    that have a common bond or similarity with Iranian or
+    Arabic names.  They should not, for example, be used for
+    Pashto names, for which a separate standard should be used.
+  - Long/short vowels:- There is no distinction made in Roman
+    between long and short a:-  E.g., Farhad (first a is short,
+    second is long).
+  - Double consonants:-  Double consonants represented by the
+    tashdid are shown by doubling the Roman letter:-  Mohammad.
+    Exceptions:-  Consonants represented by Roman digraphs (
+    e.g., sh, ch) are not doubled:-  Mobasher [not:-  Mobashsher]
+    .  Double letters are only used for tashdid (thus, Hosein [
+    not Hossein]) or to reflect the ‘sun letter’ assimilation (
+    see below).
+  - Hamzeh:-  The hamzeh is represented name-internally by an
+    apostrophe, as is the ain.  Name-initially, however,
+    neither hamzeh nor ain are indicated in transliteration (
+    e.g., Abdorrahman, not 'Abdorrahman).
+  - Digraphs:-  No distinction is drawn in Roman between
+    digraphs such as sh and single contiguous letters (e.g., s
+    followed by h).
+  - Arabic definite article "al" ('the'):-  Common in many
+    names borrowed from Arabic, the transliteration should show
+    the 'sun letter' assimilation rather than the “l” for the
+    lam.  That  is:-  Abdorrahman.  Note also that the "Abdol +
+    attribute of Allah" names are written as one unanalyzed
+    word, as are other names that contain the definite
+    article:-  Shamsoddin (not Shams al-Din), Nezamoddin, etc.
+  - Diphthongs:-  Diphthongs are written ei and ow
+    respectively:-  Hosein; Khosrow.
+  - Yeh maqsura (final yeh pronounced as “a”):-  should be
+    written as “a” as in “Musa”.
+
+  - Special Rules
+
+  - Hyphens:-  A hyphen is used to indicate the ezafeh
+    construction:-  Arshad-e Ameri
+  - Borrowed names that incorporate the name of God (Allah)
+    are transliterated as one word, with the letter "o":-  E.g.,
+    Abdollah, Ayatollah, Azizollah.
+  - Foreign names borrowed or appearing in Dari are spelled
+    according to the standard Western tradition (even if there
+    is an Arabic or Dari version of the same name):-  Joseph,
+    Michael.
+  - Common suffixes, such as gol, pur, mand, yar, zadeh,
+    etc., as well as nesbeh (‘relationship’ (to place of birth,
+    etc.)) names derived with these suffixes  (e.g., abadi) are
+    written as part of the name:-
+
+    gol		Parigol, Ziagol
+    pur		Shahpur, Mehrpur
+    mand		Gulahmand
+    yar		Aminyar
+    zadeh		Ismailzadeh, Karimzadeh
+
+    abadi		Kamalabadi
+
+
+tests:
+  - source: مُوسَى
+    expected: musa
+
+  - source: مُؤمِن
+    expected: momen
+
+  - source: رِضايي
+    expected: rezai
+
+  - source: مُبَشِّر
+    expected: mobasher
+
+  - source: حَسَّان
+    expected: hassan
+
+  - source: حَسَن
+    expected: hasan
+
+  - source: صَفَّار
+    expected: saffar
+
+  - source: صَفَر
+    expected: safar
+
+map:
+  inherit: odni-fas-Arab-Latn-2004
+  characters:
+
+    '\u0626' : '' # ئ
+    '\u0624' : '' # ؤ
+
+    # shadda
+
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0648\u0651' : 'ww'  # و
+
+    '\u0621': '' # ء
+
+    # FROM NOTES
+
+    '\u064a\u064a' : 'i' # NOTE 4 (2)
+    '\u06cc\u06cc' : 'i'
+
+    '\u0627\u064a\b' : 'i' # NOTE 4 (3)
+    '\u0627\u06cc\b' : 'i'
+
+    # Farsi consonant characters
+
+    '\u0639' : ''  # ع # new
+    '\u0642' : 'q'  # ق
+    '\u0648' : 'w'  # و

data/maps/odni-srp-Cyrl-Latn-2005.yaml

@@ -0,0 +1,36 @@
+---
+authority_id: odni
+id: 2005
+language: iso-639-2:srp
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Serbian Personal Names 2004 System
+creation_date: 2005
+confirmation_date: 2005
+description: |
+  Office of the Director Of National Intelligence Serbian Personal Names 2004 System
+
+notes:
+
+tests:
+  - source: Гојко Митић
+    expected: Gojko Mitic
+  - source: Горња Ваганица
+    expected: Gornja Vaganica
+  - source: Довиђења
+    expected: Dovidjenja
+  - source: Ћао! Здраво!
+    expected: Cao! Zdravo!
+  - source: Кључ
+    expected: Kljuc
+  - source: Цигарете
+    expected: Cigarete
+  - source: Пролеће
+    expected: Prolece
+  - source: Понедељак
+    expected: Ponedeljak
+  - source: Горња Ваганица
+    expected: Gornja Vaganica
+
+map:
+  inherit: odni-srp-Cyrl-Latn-2015

data/maps/odni-tuk-Cyrl-Latn-2015.yaml

@@ -0,0 +1,170 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:tuk
+source_script: Cyrl
+destination_script: Latn
+name: Standards for the transliteration of Turkmen personal names in written reports and products
+url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20T%20-%20Turkmen_Personal_Names_FLTS%20(U).pdf
+source: ICS-630-01 Annex T
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Turkmen person
+  names that will be applied to all final written reports and products for IC consumers. It is not
+  intended to eliminate variations of a name that can contribute forensic information. Rather, it is to
+  provide an IC standard Romanized (English) transliteration from Turkmen that can then be linked
+  to forensic information in ways that will help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the first
+  usage. In addition, if the original Cyrillic-script spelling is known, that spelling should also
+  appear in parentheses following the name, if possible, following best practices of the issuing
+  organization and taking into consideration information system capabilities. For example:
+  Azat Muhadov (also seen as Azat Muhadow, Азат Мухадов). This convention is designed to
+  ensure that vital forensic information is not lost.
+
+  For names of persons who are known to not be part of the Turkmen-speaking community, use the
+  relevant IC transliteration standard for names from that language (e.g., Yitzhak). A translator’s
+  note may be used to clarify the known origin of the person. Spell names of individuals from
+  languages that are written in Roman letters as they are spelled in those languages (e.g., George
+  Clooney, Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the on-
+  line directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings
+  given in these on-line reference works should be used in place of the IC Standard. For any
+  individual who has at one time been listed in the Factbook or Chiefs of State directory but who no
+  longer appears in those resources (i.e. is no longer a government official), the IC Standard
+  spelling should appear first, with the spelling, if known, as it previously appeared in those
+  resources listed within parentheses at the first usage.
+
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+  (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
+  of diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
+  names of well-known individuals.
+
+notes:
+  - Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh
+  - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters, (e.g. 's' followed by 'h').
+  - The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration.
+
+tests:
+  - source: Акгюль
+    expected: Akgyul
+  - source: Акгыз
+    expected: Akgyz
+  - source: Арсланбек
+    expected: Arslanbek
+  - source: Берди
+    expected: Berdi
+  - source: Дидар
+    expected: Didar
+  - source: Гөзел
+    expected: Gozel
+  - source: Гуля
+    expected: Gulya
+  - source: Гюля
+    expected: Gyulya
+  - source: Мәхри
+    expected: Mahri
+  - source: Майса
+    expected: Maysa
+  - source: Мырат
+    expected: Myrat
+  - source: Өвез
+    expected: Ovez
+  - source: Рашит
+    expected: Rashit
+  - source: Сапармырат
+    expected: Saparmyrat
+
+map:
+  rules:
+    - pattern: "\u0448\u0448" # шш -> sh
+      result: sh
+    - pattern: "\u0428\u0448" # Шш -> Sh
+      result: Sh
+    - pattern: "\u0428\u0428" # ШШ -> SH
+      result: SH
+    - pattern: "\u0448\u0428" # шШ -> sH
+      result: sH
+    - pattern: "\u042C|\u044C" # remove Ь and ь
+      result: ''
+
+  characters:
+    '\u0410': 'A'      # А
+    '\u0411': 'B'      # Б
+    '\u0412': 'V'      # В
+    '\u0413': 'G'      # Г
+    '\u0414': 'D'      # Д
+    '\u0415': 'E'      # Е
+    '\u0401': 'Yo'     # Ё
+    '\u0416': 'Zh'     # Ж
+    '\u0496': 'J'      # җ
+    '\u0417': 'Z'      # З
+    '\u0418': 'I'      # И
+    '\u0419': 'Y'      # Й
+    '\u041A': 'K'      # К
+    '\u041B': 'L'      # Л
+    '\u041C': 'M'      # М
+    '\u041D': 'N'      # Н
+    '\u04A2': 'Ng'     # Ң
+    '\u041E': 'O'      # О
+    '\u04E8': 'O'      # Ө
+    '\u041F': 'P'      # П
+    '\u0420': 'R'      # Р
+    '\u0421': 'S'      # С
+    '\u0422': 'T'      # Т
+    '\u0423': 'U'      # У
+    '\u04AE': 'U'      # Ү
+    '\u0424': 'F'      # Ф
+    '\u0425': 'H'      # Х
+    '\u0426': 'Ts'     # Ц
+    '\u0427': 'Ch'     # Ч
+    '\u0428': 'Sh'     # Ш
+    '\u0429': 'Shch'   # Щ
+    '\u042B': 'Y'      # Ы
+    '\u042D': 'E'      # Э
+    '\u04D8': 'A'      # Ә
+    '\u042E': 'Yu'     # Ю
+    '\u042F': 'Ya'     # Я
+
+    '\u0430': 'a'      # а
+    '\u0431': 'b'      # б
+    '\u0432': 'v'      # в
+    '\u0433': 'g'      # г
+    '\u0434': 'd'      # д
+    '\u0435': 'e'      # е
+    '\u0451': 'yo'     # ё
+    '\u0436': 'zh'     # ж
+    '\u0497': 'j'      # җ
+    '\u0437': 'z'      # з
+    '\u0438': 'i'      # и
+    '\u0439': 'y'      # й
+    '\u043A': 'k'      # к
+    '\u043B': 'l'      # л
+    '\u043C': 'm'      # м
+    '\u043D': 'n'      # н
+    '\u04A3': 'ng'     # ң
+    '\u043E': 'o'      # о
+    '\u04E9': 'o'      # ө
+    '\u043F': 'p'      # п
+    '\u0440': 'r'      # р
+    '\u0441': 's'      # с
+    '\u0442': 't'      # т
+    '\u0443': 'u'      # у
+    '\u04AF': 'u'      # ү
+    '\u0444': 'f'      # ф
+    '\u0445': 'h'      # х
+    '\u0446': 'ts'     # ц
+    '\u0447': 'ch'     # ч
+    '\u0448': 'sh'     # ш
+    '\u0449': 'shch'   # щ
+    '\u044B': 'y'      # ы
+    '\u044D': 'e'      # э
+    '\u04D9': 'a'      # ә
+    '\u044E': 'yu'     # ю
+    '\u044F': 'ya'     # я

data/maps/odni-ukr-Cyrl-Latn-2015.yaml

@@ -82,6 +82,10 @@ tests:
     expected: Yaroshenko
   - source: Костянтин
     expected: Kostyantyn
+  - source: Новофедорівка
+    expected: Novofedorivka
+  - source: Гуляйгородок
+    expected: Hulyayhorodok
 
 map:
   rules:

data/maps/un-ara-Arab-Latn-2017.yaml

@@ -168,7 +168,7 @@ map:
       result: ' ad͟h D͟h'
     - pattern : ' Al L'  # الل
       result: ' al L'
-    - pattern : ' an n'  # الن
+    - pattern : ' An N'  # الن
       result: ' an N'
     - pattern: " Al " # ال
       result: " al "

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

@@ -0,0 +1,223 @@
+---
+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'