interscript-maps 2.0.5

data/maps/un-prs-Arab-Latn-1967.imp

@@ -0,0 +1,214 @@
+metadata {
+  authority_id: ungen
+  id: 2017
+  language: iso-639-3:prs
+  # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
+  source_script: Arab
+  destination_script: Latn
+  name: Persian UN 1967
+  url: http://www.eki.ee/wgrs/v2_2/rom1_fa.htm
+  creation_date: 1967
+  confirmation_date: 01-2003
+  description: |
+    The United Nations recommended system was approved in 1967 (
+    I/13), based on the official system adopted by Iran and
+    published in its English version as Transliteration of
+    Farsi Geographic Names to Latin Alphabet (September 1966).
+    The romanization table was also published as an annex to
+    the Toponymic Guidelines for the Islamic Republic of Iran
+    in 2000 (Toponymic Guidelines for map and other editors –
+    Revised edition 1998. Submitted by the Islamic Republic of
+    Iran. UNGEGN, 20th session. New York, 17-28 January 2000,
+    Working Paper No. 41.).
+
+    The system is used in the Islamic Republic of Iran and in
+    international cartographic products.
+
+    Persian (Farsi) uses the Perso-Arabic script that is
+    written from right to left. The Persian script usually
+    omits vowel points and diacritical marks from writing which
+    makes it difficult to obtain uniform results in the
+    romanization of Persian. The romanization is generally
+    reversible though there are some ambiguous letter
+    sequences (kh, sh, th, zh) which also may represent the
+    romanized values of two Persian characters in addition to
+    the respective single ones.
+
+
+  notes:
+    - A Word-initially.
+    - B Not romanized; marks absence of the vowel.
+    - C Doubling of the consonant letter.
+    - D After a consonant (excl. -ah).
+    - E After a vowel (see also note 2).
+    - 1-The adjectival ending of Arabic origin -يه in Persian is
+      romanized -īyeh. In romanizing the definite article the
+      same rules of assimilation of consonants are applied as in
+      Arabic, e.g. زين الدين Zeyn od Dīn.
+
+    - 2-The relational suffix (eẕāfeh) -e is usually not
+      expressed in Persian writing after a consonant. After final
+      ا or و it is written with ى, e.g. پاى آب Pā-ye Āb. After
+      final ى and ه it is expressed by writing hamzeh over the
+      character دهانۀ ممبر Dahāneh-ye Mambar.
+
+    - 3-To point Persian vowels two systems are in use that are
+      separated by a column in the table. The first system is a
+      Persian one while the other adheres to the Arabic
+      tradition. In normal spelling vowel points are not used.
+}
+
+tests {
+  test "اَنجِيرة", "Anjīrah"
+  test "اِيْوَانِي", "Eyvānī"
+  test "آبَادَان", "Ābādān"
+  test "قُرآن", "Qor’ān"
+  test "مَآب", "Ma’āb"
+  test "مُحَمَّد", "Moḩammad"
+  test "كُوهِ مَرغُوب", "Kūh-e Marghūb"
+  test "پَايِ آب", "Pā-ye Āb"
+  test "جُويِ آس", "Jū-ye Ās"
+  test "دَهَانِهٴ مَمبَر", "Dahāneh-ye Mambar"
+  test "سَلَسِيٴ بُذُرگ", "Salasī-ye Boz̄org"
+  test "ذُو الفَقَار", "Z̄ū ol Faqār"
+}
+
+stage {
+  # CHARACTERS
+  parallel {
+
+    sub "\u064e", "a" # َ fatha
+    sub "\u064e", "", after: "\u0629" # َ fatha followed by ta' marboota
+    sub "\u064e", "", after: "a" + any("ht") # َ fatha followed by ta' marboota, handling different order of conversion
+    sub "\u0650", "e" # ِ kasra
+    sub "\u064f", "o" # ُ damma
+    sub "\u0652", "" # ْ sokoon, see Note B
+
+    sub "\u064e\u0627", "ā" # ـَا fatha followed by ا
+    sub "\u064e\u0649", "á" # ـَى fatha followed by ى which is ا not ي
+    sub boundary + "\u0622", "ā" # آ  NOTE A
+    sub "\u0622", "’ā" # آ
+    sub "\u0650\u064a", "ī" # ـِي kasra followed by ي
+    sub "\u064f\u0648", "ū" # ـُو damma followed by و
+    sub any("\u064e\u0650") + "\u064a\u0652", "ey" # ـَيْ
+    sub any("\u064e\u064f") + "\u0648\u0652", "ow" # ـَوْ
+    sub "\u0621", "’" # ء
+    sub "\u2013", "–"
+    sub "\u2013" + any("\u0649\u064a") + "\u0647", "-īyeh"
+    sub any("\u0654\u0674"), "-e" # ٴ ezafeh
+    sub any("\u0654\u0674"), "-ye", before: any("\u064a\u0647") # ٴ ezafeh
+    sub "\u0650" + boundary, "-e" # ِ kasra
+    sub any("\u064a\u06cc") + "\u0650" + boundary, "-ye" # ِ kasra
+
+    # NOTE C
+    sub "\u0628\u0651", "bb" # ب
+    sub "\u062a\u0651", "tt" # ت
+    sub "\u062b\u0651", "s̄s̄" # ث
+    sub "\u062c\u0651", "jj" # ج
+    sub "\u062d\u0651", "ḩḩ" # ح
+    sub "\u062e\u0651", "kh" # خ
+    sub "\u062f\u0651", "dd" # د
+    sub "\u0630\u0651", "z̄z̄" # ذ
+    sub "\u0631\u0651", "rr" # ر
+    sub "\u0632\u0651", "zz" # ز
+    sub "\u0633\u0651", "ss" # س
+    sub "\u0634\u0651", "sh" # ش
+    sub "\u0635\u0651", "şş" # ص
+    sub "\u0636\u0651", "ẕẕ" # ض
+    sub "\u0637\u0651", "ţţ" # ط
+    sub "\u0638\u0651", "z̧z̧" # ظ
+    sub "\u063a\u0651", "gh" # غ
+    sub "\u0641\u0651", "ff" # ف
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0643\u0651", "kk" # ك
+    sub "\u0644\u0651", "ll" # ل
+    sub "\u0645\u0651", "mm" # م
+    sub "\u0646\u0651", "nn" # ن
+    sub "\u0647\u0651", "hh" # ه
+    sub "\u0648\u0651", "vv" # و
+    sub "\u064a\u0651", "yy" # ي
+
+    # NOTE 1
+    # Sun letters
+    sub boundary + "\u0627\u0644\u062a", "ot t" # الت
+    sub boundary + "\u0627\u0644\u062b", "os̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f", "od d" # الد
+    sub boundary + "\u0627\u0644\u0630", "oz̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631", "or r" # الر
+    sub boundary + "\u0627\u0644\u0632", "oz z" # الز
+    sub boundary + "\u0627\u0644\u0633", "os s" # الس
+    sub boundary + "\u0627\u0644\u0634", "osh sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "oş ş" # الص
+    sub boundary + "\u0627\u0644\u0636", "oẕ ẕ" # الض
+    sub boundary + "\u0627\u0644\u0637", "oţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0638", "oz̧ z̧" # الظ
+    sub boundary + "\u0627\u0644\u0644", "ol l" # الل
+    sub boundary + "\u0627\u0644\u0646", "on n" # الن
+
+    sub "\u0650\u064a\u0651", "īy" # ـِيَّ
+    sub "\u0650\u064a", "iy", after: any("\u064e\u064f") # ـِي kasra followed by ي
+
+    # ta' marboota
+    sub "\u0629", "at" # ة in the middle of the sentence
+    sub "\u0629" + line_end, "ah"
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+
+    sub boundary + "\u0627\u0644", "al " # ال
+    sub space + boundary + "\u0627\u0644", " ol " # ال #special Rule 1
+
+    sub boundary + "\u0627", "" # ا initial
+    sub "\u0627", "ā" # ا middial
+    sub "\u0627" + boundary, "ā" # ا final
+
+    sub "\u0628", "b" # ب
+    sub "\u067E", "p" # پ
+    sub "\u062A", "t" # ت
+    sub "\u062B", "s̄" # ث
+    sub "\u062C", "j" # ج
+    sub "\u0686", "ch" # ‫چ‬
+    sub "\u062D", "ḩ" # ح
+    sub "\u062E", "kh" # خ
+    sub "\u062F", "d" # د
+    sub "\u0630", "z̄" # ذ
+    sub "\u0631", "r" # ر
+    sub "\u0632", "z" # ز
+    sub "\u0698", "zh" # ‫ژ‬
+    sub "\u0633", "s" # س
+    sub "\u0634", "sh" # ش
+    sub "\u0635", "ş" # ص
+    sub "\u0636", "ẕ" # ض
+    sub "\u0637", "ţ" # ط
+    sub "\u0638", "z̧" # ظ
+    sub "\u0639", "’" # ع
+    sub "\u063A", "gh" # غ
+    sub "\u0641", "f" # ف
+    sub "\u0642", "q" # ق
+    sub "\u0643", "k" # ك
+    sub "\u06A9", "k" # ک
+    sub "\u06AF", "g" # گ
+    sub "\u0644", "l" # ل‫‬
+    sub "\u0645", "m" # م
+    sub "\u0646", "n" # ن
+    sub "\u0648", "v" # و
+    sub "\u0647", "h" # ه
+    sub "\u0649", "y" # ي
+    sub "\u064a", "y" # ي
+  }
+
+  # POSTRULES
+  sub any("\u0061".."\uFFFF"), upcase, before: boundary, not_before: boundary + any("‘’'-")
+
+  sub " Al", " al"
+  sub " Ol", " ol"
+}

data/maps/un-rus-Cyrl-Latn-1987.imp

@@ -0,0 +1,96 @@
+metadata {
+  authority_id: ungegn
+  id: 1987
+  language: iso-639-2:rus
+  source_script: Cyrl
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Russian Romanization system
+  url: http://www.eki.ee/wgrs/rom1_ru.htm
+  creation_date: 1987
+  confirmation_date: 2016
+  description: |
+    The United Nations recommended system was approved in 1987 (V/18),
+    based on the official system of the Main Administration of Geodesy and
+    Cartography of the former Soviet Union, also known as the GOST 1983
+    system (GOST 16876-71). The table was published as an annex to the
+    resolution.
+
+    The system is used in the Russian Federation and increasingly in
+    international cartographic products.
+
+    Russian uses the Cyrillic script which is alphabetic. The
+    romanization table is unambiguous and can be applied automatically. The
+    system is reversible, although rarely there can be ambiguities.
+
+  notes:
+    - "Cursive forms of some characters might be formed differently: Аа Бб
+      Вв Гг Дд Ее Ёё Жж Зз Ии Йй Кк Лл Мм Нн Оо Пп Рр Сс Тт Уу Фф Хх Цц Чч Шш
+      Щщ Ъъ Ыы Ьь Ээ Юю Яя."
+
+    - Fifth United Nations Conference on the Standardization of
+      Geographical Names. Montreal, 18–31 August 1987. Vol. I. Report of the
+      Conference, pp. 40–41.
+}
+
+tests {
+  test "Aнaпa", "Anapa"
+  test "Бaбушкин", "Babuškin"
+  test "Вaвилово", "Vavilovo"
+  test "Гaгaрин", "Gagarin"
+  test "Дудинкa", "Dudinka"
+  test "Елисeeвкa", "Eliseevka"
+  test "Ёлкино", "Ëlkino"
+  test "Псëл", "Psël"
+  test "Жужa", "Žuža"
+  test "Звëздный", "Zvëzdnyj"
+  test "Идрицa", "Idrica"
+  test "Зaрaйск", "Zarajsk"
+  test "Кокaнд", "Kokand"
+  test "Лaлвaр", "Lalvar"
+  test "Мaймaк", "Majmak"
+  test "Нeжин", "Nežin"
+  test "Обoдoвкa", "Obodovka"
+  test "Пaп", "Pap"
+  test "Рeбрихa", "Rebriha"
+  test "Сaсoвo", "Sasovo"
+  test "Тaттa", "Tatta"
+  test "Уржум", "Uržum"
+  test "Фoфaнoвo", "Fofanovo"
+  test "Хoхломa", "Hohloma"
+  test "Цвeткoвo", "Cvetkovo"
+  test "Чeчeльник", "Čečel’nik"
+  test "Шишкинo", "Šiškino"
+  test "Щукинo", "Ščukino"
+  test "Пoдъячeвo", "Pod”jačevo"
+  test "Ыныкчaнский", "Ynykčanskij"
+  test "Пaрaньгa", "Paran’ga"
+  test "Кaзaнь", "Kazan’"
+  test "Щучьe", "Ščuč’e"
+  test "Элистa", "Èlista"
+  test "Юринo", "Jurino"
+  test "Юхнoв", "Juhnov"
+  test "Юрюзaнь", "Jurjuzan’"
+  test "Ямaл", "Jamal"
+  test "Язъявaн", "Jaz”javan"
+  test "Яя", "Jaja"
+  test "Вязьмa", "Vjaz’ma"
+}
+
+dependency "gost-rus-Cyrl-Latn-16876-71-1983", as: cyrllatn
+
+
+stage {
+  # CHARACTERS
+  parallel {
+    sub "\u042A", "”" # Ъ
+    sub "\u042C", "’" # Ь
+    sub "\u044A", "”" # ъ
+    sub "\u044C", "’" # ь
+    sub "\u042E", "Ju" # Ю
+    sub "\u044E", "ju" # ю
+    sub "\u042F", "Ja" # Я
+    sub "\u044F", "ja" # я
+  }
+
+  run map.cyrllatn.stage.main
+}

data/maps/un-sin-Sinh-Latn-1972.imp

@@ -0,0 +1,193 @@
+metadata {
+  authority_id: un
+  id: 1972
+  language: iso-639-2:sin
+  source_script: Sinh
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Sinhalese Romanization Version 4.0
+  url: https://www.eki.ee/wgrs/rom1_ml.htm
+  creation_date: 1972
+  confirmation_date: 2016
+  description: |
+    There does not seem to exist any national systems of romanization for Sinhalese (Sinhala) in Sri Lanka.
+
+    In 1972, D. N. Sharma prepared a romanization table for Sinhalese (Sinhala) which was published in vol. II
+    of the conference report together with the other languages of the Indian group1.
+
+    Sinhalese 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.
+
+
+  notes:
+    - |
+      The character ඇ was romanized as a͝i and the character ඈ as ai in Sharma's table, but there was no romanization for the character ඓ which,
+      though rarely used, represents the ai proper of the Indian languages; here the romanization of these characters is given in accordance with the pronunciation.
+    - |
+      ැ ෑ Exceptions: රැ ræ̆, රෑ ræ.
+    - |
+      ු Exceptions: කූ kū, ගූ gū, තූ tū, භූ bhū, රූ rū, ශූ shū.
+    - |
+      ූ Exceptions: කූ kū, ගූ gū, තූ tū, භූ bhū, රූ rū, ශූ shū
+    - |
+      ් Marks absence of the inherent vowel. Special forms: ඛ් kh, ඞ් ṅ, ච් ch, ට් ṭ, ඩ් ḍ, ධ් dh, බ් b, ම් m, ව් v.
+    - |
+      ඛ ඝ ඞ ච ඡ ඣ ඤ ඨ ඪ ථ ධ ඵ භ ශ ෂ These consonants are used only in Sanskrit and Pali loanwords.
+}
+
+tests {
+  test "ශී‍්‍ර ලංකාවේ කී‍්‍රඩාව ඉතිහාසයේ ඉහළම තැනකට ගේන්න කටයුතු කරනවා", "shīra laṁkāve kīraḍāva itihāsaye ihaḷama tæ̆nakaṭa genna kaṭayutu karanavā"
+  test "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්", "kŏchchikaඬe moyakaṭa asala næmaṭa giya taruṇayo 3k maruṭa - miturāge upan dinaya sæ̆marīmaṭa æ̆vit"
+  test "ලෝක ළමා දිනයදා සිසුන් පිරිසක් කසිප්පු බීලා", "loka ḷamā dinayadā sisun pirisak kasippu bīlā"
+  test "කෝටි 16ක හෙරොයින් සමග දන්කොටුවේදී 7ක් දැලේ", "koṭi 16ka hĕrŏyin samaga dankŏṭuvedī 7k dæ̆le"
+  test "මිනුවන්ගොඩ පීසීආර් දෙදහසක් සිදුකරයි", "minuvangŏḍa pīsīār dĕdahasak sidukarayi"
+  test "පාස්කු ප‍්‍රහාරය වගේම පාස්කු ප්‍රෝඩාව ගැනත් සොයන්න කොමිසමක් පත්කළ යුතුයි - විපක්‍ෂ නායක සජිත් පේ‍්‍රමදාස", "pāsku parahāraya vagema pāsku proḍāva gæ̆nat sŏyanna kŏmisamak patkaḷa yutuyi - vipakṣha nāyaka sajit peramadāsa"
+  test "ට‍්‍රම්ප්ගේ සෞඛ්‍යය තීරණාත්මකයි - ට්විටර් හරහා ජනතාව අමතයි", "ṭarampge saukhyaya tīraṇātmakayi - ṭviṭar harahā janatāva amatayi"
+  test "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති", "pāsku dā parahāraya piḷibaඳ parīkṣhaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa dĕnne næ - agamæ̆ti"
+  test "දිල්ලි කැපිටල්ස් සහ කෝලිගේ බැංගලෝර් තෙවැනි ජය ලබයි", "dilli kæ̆piṭals saha kolige bæ̆ṁgalor tĕvæ̆ni jaya labayi"
+  test "ශ‍්‍රී ලාංකික සම්භවයක් සහිත ප‍්‍රංශයේ පවුලක 5 ක් ඝාතනය කරලා", "sharī lāṁkika sambhavayak sahita paraṁshaye pavulaka 5 k ghātanaya karalā"
+  test "පැතිකුදය ඉක්මනින් සුව කරන ප‍්‍රතිකාර", "pæ̆tikudaya ikmanin suva karana paratikāra"
+}
+
+aliases {
+  def_alias sinh_chars_1, any("\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca")
+}
+
+stage {
+
+  # RULES
+    sub "ක", "k", after: sinh_chars_1
+    sub "ඛ", "kh", after: sinh_chars_1
+    sub "ග", "g", after: sinh_chars_1
+    sub "ඝ", "gh", after: sinh_chars_1
+    sub "ඞ", "ṅ", after: sinh_chars_1
+    sub "ච", "ch", after: sinh_chars_1
+    sub "ඡ", "chh", after: sinh_chars_1
+    sub "ජ", "j", after: sinh_chars_1
+    sub "ඣ", "jh", after: sinh_chars_1
+    sub "ඤ", "ñ", after: sinh_chars_1
+    sub "ට", "ṭ", after: sinh_chars_1
+    sub "ඨ", "ṭh", after: sinh_chars_1
+    sub "ඩ", "ḍ", after: sinh_chars_1
+    sub "ඪ", "ḍh", after: sinh_chars_1
+    sub "ණ", "ṇ", after: sinh_chars_1
+    sub "ත", "t", after: sinh_chars_1
+    sub "ථ", "th", after: sinh_chars_1
+    sub "ද", "d", after: sinh_chars_1
+    sub "ධ", "dh", after: sinh_chars_1
+    sub "න", "n", after: sinh_chars_1
+    sub "ප", "p", after: sinh_chars_1
+    sub "ඵ", "ph", after: sinh_chars_1
+    sub "බ", "b", after: sinh_chars_1
+    sub "භ", "bh", after: sinh_chars_1
+    sub "ම", "m", after: sinh_chars_1
+    sub "ය", "y", after: sinh_chars_1
+    sub "ර", "r", after: sinh_chars_1
+    sub "ල", "l", after: sinh_chars_1
+    sub "ව", "v", after: sinh_chars_1
+    sub "ශ", "sh", after: sinh_chars_1
+    sub "ෂ", "ṣh", after: sinh_chars_1
+    sub "ස", "s", after: sinh_chars_1
+    sub "හ", "h", after: sinh_chars_1
+    sub "ෆ", "f", after: sinh_chars_1
+    sub "ළ", "ḷ", after: sinh_chars_1
+
+
+  # CHARACTERS
+  parallel {
+    # I. Independent vowel characters
+    sub "අ", "a"
+    sub "ආ", "ā"
+    sub "ඇ", "æ̆"
+    sub "ඈ", "æ"
+    sub "ඉ", "i"
+    sub "ඊ", "ī"
+    sub "උ", "u"
+    sub "ඌ", "ū"
+    sub "ඍ", "ṛ"
+    sub "ඎ", "ṝ"
+    sub "එ", "ĕ"
+    sub "ඒ", "e"
+    sub "ඓ", "ai"
+    sub "ඔ", "ŏ"
+    sub "ඕ", "o"
+    sub "ඖ", "au"
+
+    # II. Abbreviated vowel characters and other symbols
+    sub "ා", "ā"
+    sub "ැ", "æ̆"
+    sub "ෑ", "æ"
+    sub "ි", "i"
+    sub "ී", "ī"
+    sub "ු", "u"
+    sub "ූ", "ū"
+    sub "ෘ", "ṛ"
+    sub "ෲ", "ṝ"
+    sub "ෙ", "ĕ"
+    sub "ේ", "e"
+    sub "ෛ", "ai"
+    sub "ො", "ŏ"
+    sub "ෝ", "o"
+    sub "ෞ", "au"
+    sub "ඃ", "ḥ"
+    sub "ං", "ṁ"
+    sub "්", ""
+
+
+    # III. Consonant characters
+    sub "ක", "ka"
+    sub "ඛ", "kha"
+    sub "ග", "ga"
+    sub "ඝ", "gha"
+    sub "ඞ", "ṅa"
+    sub "ච", "cha"
+    sub "ඡ", "chha"
+    sub "ජ", "ja"
+    sub "ඣ", "jha"
+    sub "ඤ", "ña"
+    sub "ට", "ṭa"
+    sub "ඨ", "ṭha"
+    sub "ඩ", "ḍa"
+    sub "ඪ", "ḍha"
+    sub "ණ", "ṇa"
+    sub "ත", "ta"
+    sub "ථ", "tha"
+    sub "ද", "da"
+    sub "ධ", "dha"
+    sub "න", "na"
+    sub "ප", "pa"
+    sub "ඵ", "pha"
+    sub "බ", "ba"
+    sub "භ", "bha"
+    sub "ම", "ma"
+    sub "ය", "ya"
+    sub "ර", "ra"
+    sub "ල", "la"
+    sub "ව", "va"
+    sub "ශ", "sha"
+    sub "ෂ", "ṣha"
+    sub "ස", "sa"
+    sub "හ", "ha"
+    sub "ෆ", "fa"
+    sub "ළ", "ḷa"
+
+    # numbers
+    sub "\u0DE6", "0"
+    sub "\u0DE7", "1"
+    sub "\u0DE8", "2"
+    sub "\u0DE9", "3"
+    sub "\u0DEA", "4"
+    sub "\u0DEB", "5"
+    sub "\u0DEC", "6"
+    sub "\u0DED", "7"
+    sub "\u0DEE", "8"
+    sub "\u0DEF", "9"
+
+
+    sub "‍", "" # Used for joining
+    sub "‌", "" # Used for non joining
+  }
+
+  compose
+}
+