interscript 0.1.2 → 0.1.7

data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml

@@ -0,0 +1,190 @@
+---
+authority_id: bgnpcgn
+id: 2013
+language: iso-639-2:mkd
+source_script: Cyrl
+destination_script: Latn
+name: Makedonian Romanization, BGN/PCGN 2013 System
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811514/ROMANIZATION_OF_MACEDONIAN.pdf
+creation_date: 2013
+description: |
+  Macedonian was officially established as a written language in Yugoslavia during
+  World War II and is now the official language of North Macedonia.
+  This romanization system replaces the BGN/PCGN 1981 agreement and adheres
+  to the most widely-accepted standardization of Macedonian orthography.
+
+notes:
+  - The Macedonian Cyrillic lowercase italic Д may sometimes be seen as g.
+    There is no specific Unicode encoding for this variant form so a comparable character
+    has been used here for illustrative purposes.
+  - The Macedonian Cyrillic lowercase italic Ѓ may sometimes be seen as ī.
+    There is no specific Unicode encoding for this variant form so a comparable character
+    has been used here for illustrative purposes.
+  - The Macedonian Cyrillic lowercase italic П may sometimes be seen as ū.
+    There is no specific Unicode encoding for this variant form so a comparable character
+    has been used here for illustrative purposes.
+  - The Macedonian Cyrillic lowercase italic Т may sometimes be seen as w̄.
+    There is no specific Unicode encoding for this variant form so a comparable character
+    has been used here for illustrative purposes.
+  - |
+    An inventory of letter-diacritic combinations, with their Unicode encoding,
+    in addition to the unmodified letters of the basic Roman script is:
+    | Ǵ (U+01F4)   | ǵ (U+01F5)   |
+    | Ž (U+017D)   | ž (U+017E)   |
+    | Dz (U+01F2)* | dz (U+01F3)* |
+    | Lj (U+01C8)* | lj (U+01C9)* |
+    | Nj (U+01CB)* | nj(U+01CC)*  |
+    | Ḱ (U+IE30)   | ḱ (U+IE31)   |
+    | Č (U+010C)   | č (U+010D)   |
+    | Dž (U+01C5)* | dž (U+01C6)* |
+    | Š (U+0160)   | š (U+0161)   |
+    * Note that these characters can also be reproduced with individual letters (e.g. l+j).
+  - The Romanization column shows only lowercase forms but, when romanizing,
+    uppercase and lowercase Roman letters as appropriate should be used.
+
+tests:
+  - source: Ѓенови Ливаѓе
+    expected: Ǵenovi Livaǵe
+  - source: ЛУЃЕ луѓе
+    expected: LUǴE luǵe
+  - source: ЅВЕЗДА ѕвезда Ѕвезда
+    expected: DZVEZDA dzvezda Dzvezda
+  - source: Јабежица
+    expected: Jabežica
+  - source: Љиќен и Бард
+    expected: Ljiḱen i Bard
+  - source: Ќамилов Чукар
+    expected: Ḱamilov Čukar
+  - source: Џавидин Кајнак
+    expected: Džavidin Kajnak
+  - source: Џамалџи
+    expected: Džamaldži
+  - source: Џибра Гури и Зи
+    expected: Džibra Guri i Zi
+  - source: Абазова Куќарица
+    expected: Abazova Kuḱarica
+  - source: Баба Анѓина Маала
+    expected: Baba Anǵina Maala
+  - source: Ваљановец
+    expected: Valjanovec
+  - source: Галал Једи Дереш
+    expected: Galal Jedi Dereš
+  - source: Дванаесет Клајнци
+    expected: Dvanaeset Klajnci
+  - source: Електродистрибуција Струга
+    expected: Elektrodistribucija Struga
+  - source: Железничка Станица Рајко Жинзифов
+    expected: Železnička Stanica Rajko Žinzifov
+  - source: Заедничко Речиште
+    expected: Zaedničko Rečište
+  - source: Испраена Плоча
+    expected: Ispraena Ploča
+  - source: Казнено-Поправна Установа Идризово
+    expected: Kazneno-Popravna Ustanova Idrizovo
+  - source: Лази и Зејнелит
+    expected: Lazi i Zejnelit
+  - source: Мавровско Езеро
+    expected: Mavrovsko Ezero
+  - source: Национален Парк Галичица
+    expected: Nacionalen Park Galičica
+  - source: Одморалиште Свети Стефан
+    expected: Odmoralište Sveti Stefan
+  - source: Планинарски Дом Караџица
+    expected: Planinarski Dom Karadžica
+  - source: Раса е Лисењит
+    expected: Rasa e Lisenjit
+  - source: Скочивирска Клисура
+    expected: Skočivirska Klisura
+  - source: Термо-електроцентрала Неготино
+    expected: Termo-elektrocentrala Negotino
+  - source: Узуновско Бресје
+    expected: Uzunovsko Bresje
+  - source: Фабрика Југохром
+    expected: Fabrika Jugohrom
+  - source: Хидроелектрана Сапунџица
+    expected: Hidroelektrana Sapundžica
+  - source: Цветковско Рамниште
+    expected: Cvetkovsko Ramnište
+  - source: Чалтанова Пештера
+    expected: Čaltanova Peštera
+  - source: Шкемби Вишнејц
+    expected: Škembi Višnejc
+
+map:
+  postrules:
+    # DZ
+    - pattern: "((?<=[[:upper:]])Dz(?=[[:upper:]])?|(?<=[[:upper:]])?Dz(?=[[:upper:]]))"
+      result: "DZ"
+    #LJ
+    - pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
+      result: "LJ"
+    #NJ
+    - pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
+      result: "NJ"
+    #DŽ
+    - pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
+      result: "DŽ"
+
+  characters:
+    "\u0410": "A"
+    "\u0411": "B"
+    "\u0412": "V"
+    "\u0413": "G"
+    "\u0414": "D"
+    "\u0403": "\u01F4" # Ǵ
+    "\u0415": "E"
+    "\u0416": "\u005a\u030c" # Ž
+    "\u0417": "Z"
+    "\u0405": "Dz"
+    "\u0418": "I"
+    "\u0408": "J"
+    "\u041A": "K"
+    "\u041B": "L"
+    "\u0409": "Lj"
+    "\u041C": "M"
+    "\u041D": "N"
+    "\u040A": "Nj"
+    "\u041E": "O"
+    "\u041F": "P"
+    "\u0420": "R"
+    "\u0421": "S"
+    "\u0422": "T"
+    "\u040C": "\u004b\u0301" # Ḱ
+    "\u0423": "U"
+    "\u0424": "F"
+    "\u0425": "H"
+    "\u0426": "C"
+    "\u0427": "\u0043\u030c" # Č
+    "\u040F": "D\u007a\u030c" # Dž
+    "\u0428": "\u0053\u030c" # Š
+    "\u0430": "a"
+    "\u0431": "b"
+    "\u0432": "v"
+    "\u0433": "g"
+    "\u0434": "d"
+    "\u0453": "\u01F5" # ǵ
+    "\u0435": "e"
+    "\u0436": "\u007a\u030c" # ž
+    "\u0437": "z"
+    "\u0455": "dz"
+    "\u0438": "i"
+    "\u0458": "j"
+    "\u043A": "k"
+    "\u043B": "l"
+    "\u0459": "lj"
+    "\u043C": "m"
+    "\u043D": "n"
+    "\u045A": "nj"
+    "\u043E": "o"
+    "\u043F": "p"
+    "\u0440": "r"
+    "\u0441": "s"
+    "\u0442": "t"
+    "\u045C": "\u1E31" # ḱ
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š

data/maps/bgnpcgn-mon-Cyrl-Latn-1964.yaml

@@ -0,0 +1,223 @@
+---
+authority_id: bgnpcgn
+id: 1964
+language: iso-639-2:mon
+source_script: Cyrl
+destination_script: Latn
+name: BGN/PCGN 1964 System
+alias:
+  ogc11122:
+    code: mon_Cyrl2Latn_BGN_1964
+    description: Mongolian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1964 System
+url: https://github.com/interscript/interscript/files/5180767/BGN_Romanization_Guide_1964_mongolian_1964.pdf
+creation_date:
+confirmation_date:
+description: |
+  This system was originated by the PCGN in 1957 and adopted as a
+  BGN/PCGN System in 1964. It is intended for use in the romanization of
+  geographic names in the "Mongolian People's Republic" but not to romanize
+  Mongolian names in adjacent parts of China and the U.S.S.R.
+
+notes: |
+  - b occurs initially and after л, м, and б.
+  - v occurs medially in Mongolian words and initially in foreign words.
+  - y occurs only as the second element of diphthongs.
+  - k, p, f, and shch occurs foreign words only.
+  - "\u2019" occurs only in Russion words.
+  - ï occurs only in suffixes to words containing back vowels (a, o, and u).
+  - In monosyllables yu or yü depending on pronunciation; in polysyllables yu when followed by a, o, or u, but yü when followed by i, e, ö, or ü.
+
+tests:
+  - source: Эрдэнэт Сум
+    expected: Erdenet Sum
+  - source: Эрдэнэт
+    expected: Erdenet
+  - source: Эрдэнэ
+    expected: Erdene
+  - source: Шивээговь Сум
+    expected: Shiveegovĭ Sum
+  - source: Шивээговь
+    expected: Shiveegovĭ
+  - source: Шарынгол Сум
+    expected: Sharïngol Sum
+  - source: Шарынгол
+    expected: Sharïngol
+  - source: Цагааннуур
+    expected: Tsagaannuur
+  - source: Хонгор Сум
+    expected: Hongor Sum
+  - source: Хонгор
+    expected: Hongor
+  - source: Хайлаастай
+    expected: Haylaastay
+  - source: Түнэл Сум
+    expected: Tünel Sum
+  - source: Түнэл
+    expected: Tünel
+  - source: Сүхбаатар
+    expected: Sühbaatar
+  - source: Сүмбэр Сум
+    expected: Sümber Sum
+  - source: Сүмбэр
+    expected: Sümber
+  - source: Сайншанд Сум
+    expected: Saynshand Sum
+  - source: Сайншанд
+    expected: Saynshand
+  - source: Орхон Сум
+    expected: Orhon Sum
+  - source: Орхон
+    expected: Orhon
+  - source: Нарст
+    expected: Narst
+  - source: Мөрөн Сум
+    expected: Mörön Sum
+  - source: Мөрөн
+    expected: Mörön
+  - source: Зүүнхөвөө
+    expected: Dzüünhövöö
+  - source: Жаргалант Сум
+    expected: Jargalant Sum
+  - source: Жаргалант
+    expected: Jargalant
+  - source: Дархан Сум
+    expected: Darhan Sum
+  - source: Даланзадгад Сум
+    expected: Dalandzadgad Sum
+  - source: Даланзадгад
+    expected: Dalandzadgad
+  - source: Давст Сум
+    expected: Davst Sum
+  - source: Давст
+    expected: Davst
+  - source: Говьсүмбэр Сум
+    expected: Govĭsümber Sum
+  - source: Говь
+    expected: Govĭ
+  - source: Буга
+    expected: Buga
+  - source: Бор-Өндөр Сум
+    expected: Bor-Öndör Sum
+  - source: Бор-Өндөр
+    expected: Bor-Öndör
+  - source: Баянхонгор
+    expected: Bayanhongor
+  - source: Баянтал
+    expected: Bayantal
+  - source: Баяндэлгэр Сум
+    expected: Bayandelger Sum
+  - source: Баяндэлгэр
+    expected: Bayandelger
+  - source: Баян-Өндөр Сум
+    expected: Bayan-Öndör Sum
+  - source: Баруун-Урт Сум
+    expected: Baruun-Urt Sum
+  - source: Баруун-Урт
+    expected: Baruun-Urt
+  - source: Архуст
+    expected: Arhust
+  - source: Арвайхээр Сум
+    expected: Arvayheer Sum
+  - source: Арвайхээр
+    expected: Arvayheer
+  - source: Есөнбулаг Сум
+    expected: Yösönbulag Sum
+  - source: Ерөө Сум
+    expected: Yöröö Sum
+  - source: Есөнзүйл Сум
+    expected: Yösöndzüyl Sum
+  - source: Ноён Сум
+    expected: Noyon Sum
+  - source: Родник Балянгийн-Булак
+    expected: Rodnik Balyangiyn-Bulak
+  - source: Замын-Үүд Сум
+    expected: Dzamïn-Üüd Sum
+  - source: Адаацаг Сум
+    expected: Adaatsag Sum
+  - source: Чандмань Сум
+    expected: Chandmanĭ Sum
+  - source: Хяргас Сум
+    expected: Hyargas Sum
+
+map:
+  rules:
+    - pattern: \u042e(?=[АаОоУу]) # Ю before а, о, or у
+      result: "Yu"
+    - pattern: \u044e(?=[АаОоУу]) # ю before а, о, or у
+      result: "yu"
+    - pattern: \u042e(?=[ИиЭэӨөҮү]) # Ю before и, э, ө, or ү
+      result: "Yü"
+    - pattern: \u044e(?=[ИиЭэӨөҮү]) # ю before и, э, ө, or ү
+      result: "yü"
+
+  characters:
+    "А": "A"      # \u0410
+    "Б": "B"      # \u0411
+    "В": "V"      # \u0412
+    "Г": "G"      # \u0413
+    "Д": "D"      # \u0414
+    "Е": "Yö"     # \u0415
+    "Ё": "Yo"     # \u0401
+    "Ж": "J"      # \u0416
+    "З": "Dz"     # \u0417
+    "И": "I"      # \u0418
+    "Й": "Y"      # \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": "H"      # \u0425
+    "Ц": "Ts"     # \u0426
+    "Ч": "Ch"     # \u0427
+    "Ш": "Sh"     # \u0428
+    "Щ": "Shch"   # \u0429
+    "Ъ": "\u2019" # \u042a
+    "Ы": "Ï"      # \u042b
+    "Ь": "Ĭ"      # \u042c
+    "Э": "E"      # \u042d
+    "Ю": "Yu"     # \u042e
+    "Я": "Ya"     # \u042f
+    "а": "a"      # \u0430
+    "б": "b"      # \u0431
+    "в": "v"      # \u0432
+    "г": "g"      # \u0433
+    "д": "d"      # \u0434
+    "е": "yö"     # \u0435
+    "ё": "yo"     # \u0451
+    "ж": "j"      # \u0436
+    "з": "dz"     # \u0437
+    "и": "i"      # \u0438
+    "й": "y"      # \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": "h"      # \u0445
+    "ц": "ts"     # \u0446
+    "ч": "ch"     # \u0447
+    "ш": "sh"     # \u0448
+    "щ": "shch"   # \u0449
+    "ъ": "\u2019" # \u044a
+    "ы": "ï"      # \u044b
+    "ь": "ĭ"      # \u044c
+    "э": "e"      # \u044d
+    "ю": "yu"     # \u044e
+    "я": "ya"     # \u044f

data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml

@@ -0,0 +1,230 @@
+---
+authority_id: bgnpcgn
+id: 2020
+language: iso-639-2:nep
+source_script: Deva
+destination_script: Latn
+name: Nepali Romanization, 2020
+url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20NEPALI.pdf
+creation_date: 1964
+description: |
+  BGN/PCGN 2011 Agreement Romanization of Nepali
+  The BGN and the PCGN have adopted the Nepal Survey Department (NSD) system for the
+  romanization of Nepali names.  This system, below, should be applied to Nepali names for which Roman‐
+  script spellings in materials produced by the government of Nepal are not available.
+
+notes:
+
+  - Only the isolated forms of the characters are given in the consonant table.  See any grammar of Nepali
+    (or other language using the Devanagari alphabet) for variant forms used in conjunct characters.
+  - These two consonant characters appear sometimes to represent ṛ (cerebral r), e.g., पहाड  →  pahāṛ
+    instead of pahāḍ.  At one time they were written with dots below, i.e., as ड़ and ढ़, though this is no
+    longer normal practice in Nepali.    The romanizations ṛ and ṛh, respectively, are optional for
+    documentary purposes if such dots appear in Nepali writing.
+  -  व , can be romanized as either v or w.    This character is primarily
+    romanized as v in consonant initial, medial, and final position; however, initial, medial, and final w
+    romanizations can occur. The w romanization is a special case which is believed to be dependent on
+    dialect, pronunciation, or stress.
+  - |
+    An inventory of letter‐diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:
+      Ṅ(U+1E44)  ṅ (U+1E45)
+      Ñ (U+00D1) ñ (U+00F1)
+      Ṭ (1E6C)   ṭ (1E6D)
+      Ḍ (1E0C)   ḍ (1E0D)
+      Ṇ (1E46)   ṇ (1E47)
+      Ṣ (1E62)   ṣ (1E63)
+      Ā (U+0100) ā (U+0101)
+      Ī (U+012A) ī (U+012B)
+      Ū (U+016A) ū (U+016B)
+      Ṛ (1E5A)   ṛ (1E5B)
+
+  - The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase
+    Roman letters as appropriate should be used.
+
+  - |
+    ं (anusvara) is rendered by
+    ṅ before क, ख, ग, and घ
+    ñ before च, छ, ज, and झ
+    ṇ before ट, ठ, ड, and ढ
+    n before त, थ, द, and ध
+    ṁ before य, र, ल, व, श, ष, स and ह
+
+tests:
+  - source: "लेखन"
+    expected: "lekhn"
+  - source: "मुद्रा"
+    expected: "mudarā"
+  - source: "प्रशंसा"
+    expected: "parshṃsā" # note 5 rule checking
+  - source: "अंक"
+    expected: "aṅk" # note 5 rule checking
+  - source: "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको"
+    expected: "nekpāle sathgit sathāyī kmiṭīko baiṭhk bhdau gte bolāune bheko"
+  - source: "न घर रह्यो, न परिवार"
+    expected: "n ghr rhayo, n privār"
+  - source: "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली"
+    expected: "ḍhorpāṭnmā bhujīkholā bāḍhīphirole abhibhāvk gumāekā bālbālikāko bichlalī"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "susamitākā kākā hembhādur r kākīlāī pni phirole bgāyo"
+  - source: "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो"
+    expected: "sṃvidhān jārī bhes~gai sāravjnik parshāsnmā nyā~ utasāh āune apekṣā thiyo"
+  - source: "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ"
+    expected: "deshmā koronā sṅkarmit r mṛitkko sṅkhayā hrek din bḍhado chh"
+  - source: "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए"
+    expected: "gāu~pālikākā adhaykṣ ṭikā guruṅkā anusār viṣaṇudāslāī rājule sutankā lāgi belukā sāthī lgekā thie"
+  - source: "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ"
+    expected: "yo āyojnā gāu~pālikāko kenadar telalokmā prachh"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "susamitākā kākā hembhādur r kākīlāī pni phirole bgāyo"
+  - source: "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए"
+    expected: "chait philo sātā ghr āekā unī lkḍāun bhepchhi ytai rokie"
+  - source: "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ"
+    expected: "kām gran jāneko hkmā rojgārdātā kmapnīko ptrs~gai vḍā r jilalā parshāsnko siphāris anivāray grieko chh"
+  - source: "दुःख"
+    expected: "duḥkh"
+  - source: "निकुञ्जको स्थानीय पोस्टका कर्मचारी पनि त्यहीँ थिए"
+    expected: "nikuñajko sathānīy posaṭkā kramchārī pni tayhī~ thie"
+  - source: "युद्धकालको मनोविज्ञान"
+    expected: "yudadhkālko mnovijñān"
+  - source: "जर्मन वायुसेवाको आक्रमणमा दुई लाख पचास हजार मानिसको ज्यान जानसक्ने र करिब ३० देखि ४० लाख मान्छे विस्थापित हुने अनुमान बेलायत सरकारको थियो"
+    expected: "jramn vāyusevāko ākarmṇmā duī lākh pchās hjār mānisko jayān jānskane r krib 30 dekhi 40 lākh mānachhe visathāpit hune anumān belāyt srkārko thiyo"
+  - source: "युद्ध"
+    expected: "yudadh"
+  - source: "कोरोनासँग जम्काभेट"
+    expected: "koronās~g jmakābheṭ"
+  - source: "संक्रमित"
+    expected: "sṅkarmit"
+  - source: "स्वयम्"
+    expected: "savyma"
+  - source: "संख्या"
+    expected: "sṅkhayā"
+  - source: "गौरीटारस्थित रंगशाला"
+    expected: "gaurīṭārsathit rṅgshālā"
+
+map:
+
+  rules:
+    # note[5]
+    - pattern: \u0902(?=[कखगघ])    # ं  before क, ख, ग, and घ
+      result: ṅ
+    - pattern: \u0902(?=[चछजझ])    # ं  before च, छ, ज, and झ
+      result: ñ
+    - pattern: \u0902(?=[टठडढ])    # ं  before ट, ठ, ड, and ढ
+      result: ṇ
+    - pattern: \u0902(?=[तथदध])    # ं  before त, थ, द, and ध
+      result: n
+
+  characters:
+
+    # Vowels and Diphthongs
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ṛi'
+    'ॠ': 'rī'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+
+    # Medials # Needed for connecting constants
+
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛi"
+    'ॄ': "rī"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+
+
+    # Consonants (see Note 1)
+
+    # Gutturals
+    'क': 'k'
+    'ख': 'kh'
+    'ग': 'g'
+    'घ': 'gh'
+    'ङ': 'ṅ'
+
+    # Palatals
+    'च': 'ch'
+    'छ': 'chh'
+    'ज': 'j'
+    'झ': 'jh'
+    'ञ': 'ñ'
+
+    # Cerebrals
+    'ट': 'ṭ'
+    'ठ': 'ṭh'
+    'ड': 'ḍ'
+    'ढ': 'ḍh'
+    'ण': 'ṇ'
+
+    # Dentals
+    'त': 't'
+    'थ': 'th'
+    'द': 'd'
+    'ध': 'dh'
+    'न': 'n'
+
+    # Labials
+    'प': 'p'
+    'फ': 'ph'
+    'ब': 'b'
+    'भ': 'bh'
+    'म': 'm'
+
+    # Semivowels
+    'य': 'y'
+    'र': 'r'
+    'ल': 'l'
+    'व': 'v' # or wa [Note#3]
+
+    # Sibilants
+    'श': 'sh'
+    'ष': 'ṣ'
+    'स': 's'
+    'क्ष': 'kṣ'
+    'त्र': 'tr'
+    'ज्ञ' : 'jñ'
+
+    # Aspirate
+    'ह': 'h'
+
+    # Anusvāra
+    'ं': 'ṃ'
+
+    # Bisarga
+    'ः': 'ḥ'
+
+    # Anunāsika
+    'ँ': '~'
+
+    'ॅ': 'r'
+
+    # halanta
+    '्': 'a'
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    # Numerals / सङ्ख्या
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'