interscript 0.1.3 → 0.1.9

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

@@ -0,0 +1,145 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:aze
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization Table -- Azerbaijani (1997)
+alias:
+  ogc11122:
+    code: aze_Cyrl2Latn_ALA_1997
+    description: Azerbaijani ALA-Library of Congress 1997 System
+url: https://transliteration.eki.ee/pdf/Azerbaijani.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization Tables: Transliteration Schemes for Non-Roman Scripts. Randal K. Berry (ed.). Library of Congress, 1997.
+
+notes:
+  - "Ј ј replaced Й й in 1959 (Roman: y; ISO 9: j; ALA-LC: ĭ)."
+
+tests: # from internet
+  - source: Азәрбајҹан дили
+    expected: Azărbaı̐jan dili
+  - source: |
+      Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад вә бәрабәр доғулурлар.
+      Онларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар.
+    expected: |
+      Bu̇tu̇n insanlar lăı̐agăt vă ḣu̇guglaryna ġȯră azad vă bărabăr doghulurlar.
+      Onlaryn shu̇urlary vă vijdanlary var vă bir-birlărină mu̇nasibătdă gardashlyg ruḣunda davranmalydyrlar.
+  - source: |
+      Азәрбајҹан! Азәрбајҹан!
+      Еј гәһрәман өвладын шанлы Вәтәни!
+      Сәндән өтрү ҹан вермәјә ҹүмлә һазырыз!
+      Сәндән өтрү ган төкмәјә ҹүмлә гадириз!
+      Үчрәнҝли бајрағынла мәсуд јаша!
+      Үчрәнҝли бајрағынла мәсуд јаша!
+      Минләрлә ҹан гурбан олду,
+      Синән һәрбә мејдан олду!
+      Һүгугундан кечән әсҝәр,
+      Һәрә бир гәһрәман олду!
+      Сән оласан ҝүлүстан,
+      Сәнә һәр ан ҹан гурбан!
+      Сәнә мин бир мәһәббәт
+      Синәмдә тутмуш мәкан!
+      Намусуну һифз етмәјә,
+      Бајрағыны јүксәлтмәјә
+      Намусуну һифз етмәјә,
+      Ҹүмлә ҝәнҹләр мүштагдыр!
+      Шанлы Вәтән! Шанлы Вәтән!
+      Азәрбајҹан! Азәрбајҹан!
+      Азәрбајҹан! Азәрбајҹан!
+    expected: |
+      Azărbaı̐jan! Azărbaı̐jan!
+      Eı̐ găḣrăman ȯvladyn shanly Vătăni!
+      Săndăn ȯtru̇ jan vermăı̐ă ju̇mlă ḣazyryz!
+      Săndăn ȯtru̇ gan tȯkmăı̐ă ju̇mlă gadiriz!
+      U̇chrănġli baı̐raghynla măsud ı̐asha!
+      U̇chrănġli baı̐raghynla măsud ı̐asha!
+      Minlărlă jan gurban oldu,
+      Sinăn ḣărbă meı̐dan oldu!
+      Ḣu̇gugundan kechăn ăsġăr,
+      Ḣără bir găḣrăman oldu!
+      Săn olasan ġu̇lu̇stan,
+      Sănă ḣăr an jan gurban!
+      Sănă min bir măḣăbbăt
+      Sinămdă tutmush măkan!
+      Namusunu ḣifz etmăı̐ă,
+      Baı̐raghyny ı̐u̇ksăltmăı̐ă
+      Namusunu ḣifz etmăı̐ă,
+      Ju̇mlă ġănjlăr mu̇shtagdyr!
+      Shanly Vătăn! Shanly Vătăn!
+      Azărbaı̐jan! Azărbaı̐jan!
+      Azărbaı̐jan! Azărbaı̐jan!
+
+map:
+  characters:
+    '\u0410': 'A'       # А
+    '\u0411': 'B'       # Б
+    '\u0412': 'V'       # В
+    '\u0413': 'G'       # Г
+    '\u0492': 'Gh'      # Ғ
+    '\u0414': 'D'       # Д
+    '\u0415': 'E'       # Е
+    '\u04D8': "A\u0306" # Ә
+    '\u0416': 'Zh'      # Ж
+    '\u0417': 'Z'       # З
+    '\u0418': 'I'       # И
+    '\u042B': 'Y'       # Ы
+    '\u0408': "I\u0310" # Ј
+    '\u0419': 'Y'       # Й note[1]
+    '\u0419': 'Y'       # Й
+    '\u041A': 'K'       # К
+    '\u049C': "G\u0307" # Ҝ
+    '\u041B': 'L'       # Л
+    '\u041C': 'M'       # М
+    '\u041D': 'N'       # Н
+    '\u041E': 'O'       # О
+    '\u04E8': "O\u0307" # Ө
+    '\u041F': 'P'       # П
+    '\u0420': 'R'       # Р
+    '\u0421': 'S'       # С
+    '\u0422': 'T'       # Т
+    '\u0423': 'U'       # У
+    '\u04AE': "U\u0307" # Ү
+    '\u0424': 'F'       # Ф
+    '\u0425': 'Kh'      # Х
+    '\u04BA': "H\u0307" # Һ
+    '\u0427': 'Ch'      # Ч
+    '\u04B8': 'J'       # Ҹ
+    '\u0428': 'Sh'      # Ш
+
+    '\u0430': 'a'       # а
+    '\u0431': 'b'       # б
+    '\u0432': 'v'       # в
+    '\u0433': 'g'       # г
+    '\u0493': 'gh'      # ғ
+    '\u0434': 'd'       # д
+    '\u0435': 'e'       # e
+    '\u04D9': "a\u0306" # ә
+    '\u0436': 'zh'      # ж
+    '\u0437': 'z'       # з
+    '\u0438': 'i'       # и
+    '\u044B': 'y'       # ы
+    '\u0458': "\u0131\u0310" # ј
+    '\u0439': 'y'       # й note[1]
+    '\u043A': 'k'       # к
+    '\u049D': "g\u0307" # ҝ
+    '\u043B': 'l'       # л
+    '\u043C': 'm'       # м
+    '\u043D': 'n'       # н
+    '\u043E': 'o'       # о
+    '\u04E9': "o\u0307" # ө
+    '\u043F': 'p'       # п
+    '\u0440': 'r'       # р
+    '\u0441': 's'       # с
+    '\u0442': 't'       # т
+    '\u0443': 'u'       # у
+    '\u04AF': "u\u0307" # ү
+    '\u0444': 'f'       # ф
+    '\u0445': 'kh'      # х
+    '\u04BB': "h\u0307" # һ
+    '\u0447': 'ch'      # ч
+    '\u04B9': 'j'       # ҹ
+    '\u0448': 'sh'      # ш
+
+    '\u2019': '\u2019'

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

@@ -1,16 +1,20 @@
 ---
 authority_id: alalc
 id: 1997
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: ALA-LC Romanization Table -- Byelorussian (1997)
+alias:
+  ogc11122:
+    code: bel_Cyrl2Latn_ALA_1997
+    description: Byelorussian ALA-Library of Congress 1997 System
 url: http://catdir.loc.gov/catdir/cpso/romanization/beloruss.pdf
 creation_date: 1997
 
 notes:
-  - Ґ letter found in Old Belarusian and in modern publications in Tarashkevitsa orthography. 
-  - Do not confuse with the digraph кг (also romanized as “kh”). Manual review may be needed when transcribing data in vernacular characters in order to distinguish х from кг. 
+  - Ґ letter found in Old Belarusian and in modern publications in Tarashkevitsa orthography.
+  - Do not confuse with the digraph кг (also romanized as “kh”). Manual review may be needed when transcribing data in vernacular characters in order to distinguish х from кг.
   - The apostrophe (´) is not transliterated.
   - Soft sign (prime) is USMARC hexadecimal code A7 ~ U+02B9 Unicode character
 

data/maps/alalc-ben-Beng-Latn-1997.yaml

@@ -0,0 +1,291 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:ben
+source_script: Beng
+destination_script: Latn
+name: Bengali Romanization, 1997
+alias:
+  ogc11122:
+    code: ben_Beng2Latn_ALA_1997
+    description: Bengali ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/bengali.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Bengali
+
+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 symbol ( ্ )
+      called hasanta or birāma.
+
+  - ব is used both as a labial and as a semivowel. When it occurs as the
+    second or subsequent consonant of a consonant cluster, it is
+    transliterated va. When ব is doubled, it is transliterated bba.
+
+  - Candrabindu before guttural, palatal, cerebral, and dental occlusives
+    is transliterated n̐. Before labials, sibilants, semivowels, the
+    aspirate, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, abagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - 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॥
+
+    expected: |
+      āmāra sonāra bāṃlā, āmi tomāẏa bhālobāsi।
+      ciradina tomāra ākāśa, tomāra bātāsa, āmāra prāṇe bājāẏa bān̐śi॥
+      o mā, phāgune tora āmera bane ghrāṇe pāgala kare, mari hāẏa, hāẏa re—
+      o mā, aghrāṇe tora bharā kshete āmi kī dekhechi madhura hāsi॥
+
+      kī śobhā, kī chāyaṛā go, kī sneha, kī māyaṛā go—
+      kī ām̐cala bichāyaṛecha baṭera mūle, nadīra kūle kūle।
+      mā, tora mukhera bāṇī āmāra kāne lāge sudhāra mato,
+      mari hāẏa, hāẏa re—
+      mā, tora badanakhāni malina hale, o mā, āmi naẏanajale bhāsi॥
+  - source: "ট্রাম্প-বাইডেন মহারণ: জয় দাবি দুজনেরই"
+    expected: "ṭrāmpa-bāiḍena mahāraṇa: jaẏa dābi dujanerai"
+  - source: "রিপাবলিকান গভর্নর ডগ ডসি বলেছেন, ফলাফল নিয়ে এখনই কথা বলার সময় আসেনি।"
+    expected: "ripābalikāna gabharnara ḍaga ḍasi balechena, phalāphala niẏe ekhanai kathā balāra samaẏa āseni।"
+  - source: "অনেক আগে থেকেই ট্রাম্প ফ্লোরিডায় জিতে গেছেন বলে গণমাধ্যমগুলোতে তুলে ধরা হচ্ছে"
+    expected: "aneka āge thekei ṭrāmpa phloriḍāẏa jite gechena bale gaṇamādhyamagulote tule dharā hacche"
+  - source: "করোনায় আরও ২১ মৃত্যু, নতুন শনাক্ত ১৫১৭"
+    expected: "karonāẏa ārao 21 mṛtyu, natuna śanākta 1517"
+  - source: "শালিক পাখিকে পোষ মানানোর মতো কঠিন কাজ করা কিশোর রোহানের বাড়ি কুষ্টিয়া শহরের পিটিআই সড়কে।"
+    expected: "śālika pākhike posha mānānora mato kaṭhina kāja karā kiśora rohānera bāṛi kushṭiẏā śaharera piṭiāi saṛake।"
+  - source: "সুইং স্টেটের সর্বশেষ অবস্থা দেখে মনে হচ্ছে, দুজনের ভাগ্য দুলছে পেন্ডুলামে।"
+    expected: "suiṃ sṭeṭera sarbaśesha abasthā dekhe mane hacche, dujanera bhāgya dulache penḍulāme।"
+  - source: "২০১৬ সালের নির্বাচনে বহিরাগত হিসেবেই ডোনাল্ড ট্রাম্পের রাজনীতিতে আগমন"
+    expected: "2016 sālera nirbācane bahirāgata hisebei ḍonālḍa ṭrāmpera rājanītite āgamana"
+  - source: "কই সঙ্গে রাজনীতির পাদপ্রদীপ থেকে সম্পূর্ণ বাইরে থাকা তাঁর পরিবারও চলে আসে রাজনীতির আলোচনায়"
+    expected: "kai saṅge rājanītira pādapradīpa theke sampūrṇa bāire thākā tān̐ra paribārao cale āse rājanītira ālocanāẏa"
+  - source: "নির্বাচনী প্রচারের সময় প্রেসিডেন্ট ডোনাল্ড ট্রাম্পের পরিবারের সদস্যরা মাঠে নেমেছেন"
+    expected: "nirbācanī pracārera samaẏa presiḍenṭa ḍonālḍa ṭrāmpera paribārera sadasyarā māṭhe nemechena"
+  - source: "তাঁরা সমর্থকদের উদ্দেশ্যে বলেছেন, এ নির্বাচন শুধু প্রেসিডেন্ট ডোনাল্ড ট্রাম্পের প্রতি নয়"
+    expected: "tān̐rā samarthakadera uddeśye balechena, e nirbācana śudhu presiḍenṭa ḍonālḍa ṭrāmpera prati naẏa"
+  - source: "স্মার্টফোন কিনতে ৮ হাজার করে ঋণ পাবেন ৪১৫০১ শিক্ষার্থী"
+    expected: "smārṭaphona kinate 8 hājāra kare ṛṇa pābena 41501 śikshārthī"
+  - source: "বার্সা সমর্থকদের নিয়ে উদ্‌যাপনের কথা গিলতে হলো ভিদালকে"
+    expected: "bārsā samarthakadera niẏe ud‌yāpanera kathā gilate halo bhidālake"
+
+map:
+
+  rules:
+    #rule II
+    - 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: 'c'
+    - pattern: ([ছ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ch'
+    - 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: ([ড়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ṛ'
+    - pattern: ([ড়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ṛ'
+    - pattern: ([ঢ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ḍh'
+    - pattern: ([ঢ়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ṛh'
+    - 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: ([ৎ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ṯ'
+    - 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: 'y'
+    - pattern: ([য়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ẏ'
+    - pattern: ([য়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ẏ'
+    - pattern: ([র]=?)(?=[\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: ([শ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'ś'
+    - pattern: ([ষ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result: 'sh'
+    - 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'
+
+    # Rule III
+    - pattern: ([ବ]=?)(?=[\u09AC])
+      result:  'bba'
+    # Rule V
+    - pattern: \u0981(?=[কখগঘঙচছজঝঞটঠডডঢঢণতৎথদধন])
+      result: "m̐"
+    - pattern: (?<=)\u0b01(?=\b)
+      result: "m̐"
+
+  characters:
+
+    # Vowels and Diphthongs
+
+    'অ': 'a'
+    'আ': 'ā'
+    'ই': 'i'
+    'ঈ': 'ī'
+    'উ': 'u'
+    'ঊ': 'ū'
+    'এ': 'e'
+    'ঐ': 'ai'
+    'ও': 'o'
+    'ঔ': 'au'
+    'ঋ': 'ṛ'
+    'ৠ': 'ṝ'
+    'ঌ': 'ḹ'
+
+    # Consonants
+    # Gutturals
+    'ক': 'ka'
+    'খ': 'kha'
+    'গ': 'ga'
+    'ঘ': 'gha'
+    'ঙ': 'ṅa'
+
+    # Palatals
+    'চ': 'ca'
+    'ছ': 'cha'
+    'জ': 'ja'
+    'ঝ': 'jha'
+    'ঞ': 'ña'
+
+    # Cerebrals
+    'ট': 'ṭa'
+    'ঠ': 'ṭha'
+    'ড': 'ḍa'
+    'ড়': 'ṛa'
+    'ড়': 'ṛa'
+    'ঢ': 'ḍha'
+    'ঢ়': 'ṛha'
+    'ণ': 'ṇa'
+
+    # Dentals
+    'ত': 'ta'
+    'ৎ': 'ṯa'
+    'থ': 'tha'
+    'দ': 'da'
+    'ধ': 'dha'
+    'ন': 'na'
+
+    # Labials
+    'প': 'pa'
+    'ফ': 'pha'
+    'ব': 'ba' # see Note 3
+    'ভ': 'bha'
+    'ম': 'ma'
+
+    # Semivowels
+    'য': 'ya'
+    'য়': 'ẏa'
+    'য়': 'ẏa'
+    'র': 'ra'
+    'ল': 'la'
+
+    # Sibilants
+    'শ': 'śa'
+    'ষ': 'sha'
+    'স': 'sa'
+
+    # Aspirate
+    'হ': 'ha'
+
+    # Anusvāra
+    'ং': 'ṃ'
+
+    # Bisarga
+    'ঃ': 'ḥ'
+
+    # Candrabindu (anunāsika)
+    '\u0981': 'n̐'
+
+    # Abagraha (see Note 5)
+    'ऽ': '’' # (apostrophe)
+
+
+    # Medials # Needed for connecting constants
+
+    '\u09be': 'ā'
+    '\u09bf': 'i'
+    '\u09c0': 'ī'
+    '\u09c1': 'u'
+    '\u09c2': 'ū'
+    '\u09c3': 'ṛ'
+    '\u09c7': 'e'
+    '\u09c8': 'ai'
+    '\u09cb': 'o'
+    '\u09cc': 'au'
+    '\u09cd': ''
+
+    #Numbers
+
+    '০': '0'
+    '১': '1'
+    '২': '2'
+    '৩': '3'
+    '৪': '4'
+    '৫': '5'
+    '৬': '6'
+    '৭': '7'
+    '৮': '8'
+    '৯': '9'