interscript 0.1.1 → 0.1.6

data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml

@@ -0,0 +1,48 @@
+---
+authority_id: bgnpcgn
+id: 2011
+language: kor
+source_script: Hang
+destination_script: Latn
+name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
+url:
+creation_date:
+adoption_date:
+description:
+
+notes:
+  BGN/PCGN 2011 Agreement
+
+tests:
+  - source: 불국사
+    expected: "Bulguksa"
+  - source: 묵호
+    expected: "Mukho"
+  - source: 울산
+    expected: "Ulsan"
+  - source: 독립문
+    expected: "Dongnimmun"
+  - source: 강남역
+    expected: "Gangnamyeok"
+  - source: 남산리
+    expected: "Namsan-ri" #Note: no assimilation for -ri even after nasals
+  - source: 내월리
+    expected: "Naewol-ri"
+  - source: 울릉군
+    expected: "Ulleung-gun"
+  - source: 설악산
+    expected: "Seoraksan"
+  - source: 삼죽면
+    expected: "Samjuk-myeon"
+  - source: 평리1동
+    expected: "Pyeongni Il-dong"
+  - source: 평리2동
+    expected: "Pyeongni I-dong"
+  - source: 탑안이
+    expected: "Tabani"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: moct-kor-Hang-Latn-2000

data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml

@@ -0,0 +1,48 @@
+---
+authority_id: bgnpcgn
+id: 2011
+language: kor
+source_script: Kore
+destination_script: Latn
+name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
+url:
+creation_date:
+adoption_date:
+description:
+
+notes:
+  BGN/PCGN 2011 Agreement
+
+tests:
+  - source: 佛國寺
+    expected: "Bulguksa"
+  - source: 묵호
+    expected: "Mukho"
+  - source: 蔚山
+    expected: "Ulsan"
+  - source: 獨立門
+    expected: "Dongnimmun"
+  - source: 江南驛
+    expected: "Gangnamyeok"
+  - source: 南山里
+    expected: "Namsan-ri" #Note: no assimilation for -ri even after nasals
+  - source: 내월里
+    expected: "Naewol-ri"
+  - source: 鬱陵郡
+    expected: "Ulleung-gun"
+  - source: 雪嶽山
+    expected: "Seoraksan"
+  - source: 三竹面
+    expected: "Samjuk-myeon"
+  - source: 坪里1洞
+    expected: "Pyeongni Il-dong"
+  - source: 坪里2洞
+    expected: "Pyeongni I-dong"
+  - source: 탑안이
+    expected: "Tabani"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: [var-kor-Kore-Hang-2013, moct-kor-Hang-Latn-2000]

data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml

@@ -0,0 +1,159 @@
+---
+authority_id: bgnpcgn
+id: 1981
+language: mkd
+source_script: Cyrl
+destination_script: Latn
+name: Makedonian Romanization, BGN/PCGN 1981 System
+url: https://github.com/riboseinc/interscript/files/4247920/USBGN_romanization_Macedonian_1981.pdf
+creation_date: 1981
+description: BGN/PCGN Romanization table for Makedonian.
+
+tests:
+  - source: Ѓол
+    expected: Đol
+  - source: Јусек Тепеси
+    expected: Jusek Tepesi
+  - source: Љуги Ќарит
+    expected: Ljugi Ćarit
+  - source: Ќафа Сан
+    expected: Ćafa San
+  - source: Агроплод Ресен
+    expected: Agroplod Resen
+  - source: Алта Чука
+    expected: Alta Čuka
+  - source: Баш Тепе
+    expected: Baš Tepe
+  - source: Браќам
+    expected: Braćam
+  - source: Винарска Визба Агропин
+    expected: Vinarska Vizba Agropin
+  - source: Галичица
+    expected: Galičica
+  - source: Дрењево
+    expected: Drenjevo
+  - source: Енешево
+    expected: Eneševo
+  - source: Иберлија
+    expected: Iberlija
+  - source: Крмзи Су
+    expected: Krmzi Su
+  - source: Лесноски Рид
+    expected: Lesnoski Rid
+  - source: Мала Корабска Врата
+    expected: Mala Korabska Vrata
+  - source: Низок Врв
+    expected: Nizok Vrv
+  - source: Охридско Езеро
+    expected: Ohridsko Ezero
+  - source: Прлиќ
+    expected: Prlić
+  - source: Равна Гора
+    expected: Ravna Gora
+  - source: Сеѓавечкиот Рид
+    expected: Seđavečkiot Rid
+  - source: Трновите Њиве
+    expected: Trnovite Njive
+  - source: Фасов Рид
+    expected: Fasov Rid
+  - source: Црни Камен
+    expected: Crni Kamen
+  - source: Чатал Чешми
+    expected: Čatal Češmi
+  - source: Шехово
+    expected: Šehovo
+
+notes:
+  - The character ѓ should be romanized g when it occurs before е and и. In other
+    instances, it should be romanized ǵ (Ǵ).
+  - The character ќ should be romanized k when it occurs before е and и. In other
+    instances, it should be romanized ć.
+
+map:
+  rules:
+    - pattern: "Ѓ(?=[еЕиИ])"
+      result: "G"
+    - pattern: "ѓ(?=[еЕиИ])"
+      result: "g"
+    - pattern: "Ќ(?=[еЕиИ])"
+      result: "K"
+    - pattern: "ќ(?=[еЕиИ])"
+      result: "k"
+
+  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": "\u0110" # Đ
+    "\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": "\u0106" # Ć
+    "\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": "\u0111" # đ
+    "\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": "\u0107" # ć
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š

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

@@ -0,0 +1,190 @@
+---
+authority_id: bgnpcgn
+id: 2013
+language: 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-nep-Deva-Latn-2011.yaml

@@ -0,0 +1,200 @@
+---
+authority_id: bgnpcgn
+id: 2020
+language: 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"
+
+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)