interscript-maps 2.0.5

data/maps/ua-ukr-Cyrl-Latn-2007.imp

@@ -0,0 +1,69 @@
+metadata {
+  authority_id: ua
+  id: 2007
+  language: iso-639-2:ukr
+  source_script: Cyrl
+  destination_script: Latn
+  name: The Cabinet of Ministers of Ukraine adopted Resolution No 858 "About the statement of the technical description and a sample passport form of a citizen of Ukraine to go abroad and make changes to some acts of the Cabinet of Ministers of Ukraine"
+  url: https://zakon.rada.gov.ua/laws/show/858-2007-%D0%BF/ed20070626
+  creation_date: 2007
+}
+
+tests {
+  # tests generated with https://dmsu.gov.ua/services/transliteration.html
+  test "ОЛЕКСАНДР ЯН", "OLEKSANDR YAN"
+  test "ТРАНСЛІТЕРАЦІЇ", "TRANSLITERATSII"
+  test "ПЕРЕВІРКА", "PEREVIRKA"
+  test "ВСІ МАТЕРІАЛИ РОЗМІЩЕНІ НА УМОВАХ ЛІЦЕНЗІЇ", "VSI MATERIALY ROZMISHCHENI NA UMOVAKH LITSENZII"
+  test "ВВЕДІТЬ ПРІЗВИЩЕ ТА ІМ'Я УКРАЇНСЬКИМИ ЛІТЕРАМИ", "VVEDIT PRIZVYSHCHE TA IMIA UKRAINSKYMY LITERAMY"
+  test "ДОДАТКОВА ІНФОРМАЦІЯ", "DODATKOVA INFORMATSIIA"
+  test "ДІЯЛЬНІСТЬ", "DIIALNIST"
+  test "ЮЛІЯ", "YULIIA"
+  test "ЗГОРАНИ", "ZGHORANY"
+  test "ЙОРКШИР-ТЕР'ЄР", "YORKSHYR-TERIER"
+  test "ПАПА ПАЧУКА", "PAPA PACHUKA"
+  test "ЄНАКІЄВЕ", "YENAKIIEVE"
+  test "УКРАЇНА", "UKRAINA"
+  test "КИЇВ", "KYIV"
+}
+
+dependency "ua-ukr-Cyrl-Latn-1996", as: cyrllatn
+
+
+stage {
+  # RULES
+  # override parent rules
+  sub "\u0027", ""
+  sub "\u2019", ""
+  sub "\u0413", "GH", before: any("З") # Г after З or з
+  sub boundary + "\u0404", "YE" # Є in initial position -> YE
+  sub boundary + "\u0407", "I" # Ї in initial position -> I
+  sub boundary + "\u042e", "YU" # Ю in initial position -> YU
+  sub boundary + "\u042f", "YA" # Я in initial position -> YA
+
+  # CHARACTERS
+  parallel {
+    sub "Г", "G" # Г
+    sub "Ґ", "G" # Ґ
+    sub "Є", "IE" # Є
+    sub "Ж", "ZH" # Ж
+    sub "Х", "KH" # Х
+    sub "Ц", "TS" # Ц
+    sub "Ч", "CH" # Ч
+    sub "Ш", "SH" # Ш
+    sub "Щ", "SHCH" # Щ
+    sub "Ю", "IU" # Ю
+    sub "Я", "IA" # Я
+    sub "Ь", "" # Ь ->
+    sub "г", "g" # г
+    sub "ґ", "g" # ґ
+    sub "щ", "shch" # щ
+    sub "ю", "iu" # ю
+    sub "я", "ia" # я
+    sub "ь", "" # ь ->
+    sub "'", "" # ' ->
+    sub "’", "" # ’ ->
+  }
+
+  run map.cyrllatn.stage.main
+}

data/maps/ua-ukr-Cyrl-Latn-2010.imp

@@ -0,0 +1,128 @@
+metadata {
+  authority_id: ua
+  id: 2010
+  language: iso-639-2:ukr
+  source_script: Cyrl
+  destination_script: Latn
+  name: The Cabinet of Ministers of Ukraine adopted Resolution No 55 "On Normalization of Transliteration of the Ukrainian Alphabet by Means of the Latin Alphabet"
+  url:
+   - https://zakon.rada.gov.ua/laws/show/55-2010-%D0%BF/ed20100127
+   - https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/26th-gegn-docs/WP/WP21_Roma_system_Ukraine%20_engl._.pdf
+  creation_date: 2010
+
+  description: |
+    The Cabinet of Ministers of Ukraine adopted Resolution No 55 "On
+    Normalization of Transliteration of the Ukrainian Alphabet by Means of the
+    Latin Alphabet" on January 27, 2010. The Resolution approved The Table of
+    transliteration of the Ukrainian Alphabet by Means of the Latin Alphabet.
+    As a result of the adoption of this Resolution Ukrainian proper names
+    (geographical names, names and surnames,) are rendered by means of the Latin
+    alphabet in accordance with unified rules of transliteration in official documents,
+    in cartographic editions, on signs of populated places, streets, metro stations,
+    stops, etc.
+
+  notes:
+    - Combination of letters "зг" is transliterated as "zgh" as opposed to "zh" – the equivalent of the Ukrainian letter "ж".
+    - Soft sign and the apostrophe are not reproduced in Latin.
+    - Transliteration of first and last names of individuals and geograpical names is carried out by way of letter-for-letter representation in Latin.
+}
+
+tests {
+  test "Алушта", "Alushta"
+  test "Андрій", "Andrii"
+  test "Борщагівка", "Borshchahivka"
+  test "Борисенко", "Borysenko"
+  test "Вінниця", "Vinnytsia"
+  test "Володимир", "Volodymyr"
+  test "Гадяч", "Hadiach"
+  test "Богдан", "Bohdan"
+  test "Згурський", "Zghurskyi"
+  test "Ґалаґан", "Galagan"
+  test "Ґорґани", "Gorgany"
+  test "Донецьк", "Donetsk"
+  test "Дмитро", "Dmytro"
+  test "Рівне", "Rivne"
+  test "Олег", "Oleh"
+  test "Есмань", "Esman"
+  test "Єнакієве", "Yenakiieve"
+  test "Гаєвич", "Haievych"
+  test "Короп'є", "Koropie"
+  test "Житомир", "Zhytomyr"
+  test "Жанна", "Zhanna"
+  test "Жежелів", "Zhezheliv"
+  test "Закарпаття", "Zakarpattia"
+  test "Казимирчук", "Kazymyrchuk"
+  test "Медвин", "Medvyn"
+  test "Михайленко", "Mykhailenko"
+  test "Іванків", "Ivankiv"
+  test "Іващенко", "Ivashchenko"
+  test "Їжакевич", "Yizhakevych"
+  test "Кадиївка", "Kadyivka"
+  test "Мар'їне", "Marine"
+  test "Йосипівка", "Yosypivka"
+  test "Стрий", "Stryi"
+  test "Олексій", "Oleksii"
+  test "Київ", "Kyiv"
+  test "Коваленко", "Kovalenko"
+  test "Лебедин", "Lebedyn"
+  test "Леонід", "Leonid"
+  test "Миколаїв", "Mykolaiv"
+  test "Маринич", "Marynych"
+  test "Ніжин", "Nizhyn"
+  test "Наталія", "Nataliia"
+  test "Одеса", "Odesa"
+  test "Онищенко", "Onyshchenko"
+  test "Полтава", "Poltava"
+  test "Петро", "Petro"
+  test "Решетилівка", "Reshetylivka"
+  test "Рибчинський", "Rybchynskyi"
+  test "Суми", "Sumy"
+  test "Соломія", "Solomiia"
+  test "Тернопіль", "Ternopil"
+  test "Троць", "Trots"
+  test "Ужгород", "Uzhhorod"
+  test "Уляна", "Uliana"
+  test "Фастів", "Fastiv"
+  test "Філіпчук", "Filipchuk"
+  test "Харків", "Kharkiv"
+  test "Христина", "Khrystyna"
+  test "Біла Церква", "Bila Tserkva"
+  test "Стеценко", "Stetsenko"
+  test "Чернівці", "Chernivtsi"
+  test "Шевченко", "Shevchenko"
+  test "Шостка", "Shostka"
+  test "Кишеньки", "Kyshenky"
+  test "Щербухи", "Shcherbukhy"
+  test "Гоща", "Hoshcha"
+  test "Гаращенко", "Harashchenko"
+  test "Яготин", "Yahotyn"
+  test "Ярошенко", "Yaroshenko"
+  test "Костянтин", "Kostiantyn"
+  test "Знам'янка", "Znamianka"
+  test "Феодосія", "Feodosiia"
+  test "Згорани", "Zghorany"
+  test "Розгон", "Rozghon"
+}
+
+dependency "ua-ukr-Cyrl-Latn-1996", as: cyrllatn
+
+
+stage {
+  # RULES
+  sub "\u0027", ""
+  sub "\u2019", ""
+
+  # CHARACTERS
+  parallel {
+    sub "Ґ", "G" # Ґ
+    sub "ґ", "g" # ґ
+    sub "Щ", "Shch" # Щ
+    sub "щ", "shch" # щ
+    sub "ь", "" # Ь ->
+    sub "Ь", "" # ь ->
+    sub "'", "" # ' ->
+    sub "’", "" # ’ ->
+  }
+
+  run map.cyrllatn.stage.main
+}

data/maps/un-amh-Ethi-Latn-2016.imp

@@ -0,0 +1,483 @@
+metadata {
+  authority_id: un
+  id: 2016
+  language: iso-639-2:amh
+  source_script: Ethi
+  destination_script: Latn
+  name: ROMANIZATION OF AMHARIC -- UNGEGN 2016 System
+  url: http://www.eki.ee/wgrs/rom1_am.pdf
+  creation_date: 1967
+  confirmation_date: 2016-03
+  description: |
+    The United Nations recommended romanization system was approved in 1967
+    (resolution I/17), based on the Amharic to English Transliteration System
+    (2nd revised edition, August 1962) by the Imperial Ethiopian Mapping and
+    Geography Institute. The table has been published in volume II of the
+    conference report (see Ref. in Notes section).
+
+    The UN-approved system is not being used in Ethiopia, instead a simple
+    version without diacritical marks is used. In international cartographic
+    products mostly the BGN/PCGN 1967 system is used which differs from the
+    former mainly by using diacritical marks differently. Often the same
+    spellings are used without any diacritical marks.
+
+    Amharic uses the Ethiopic syllabic script whereby each syllable denotes a
+    combination of a consonant and a vowel. It has 34 basic characters, each
+    character having several different forms, usually called orders, according to
+    the vowel with which the basic character is combined. The system is mainly
+    reversible with the exception of some syllables of the 1st order which are
+    pronounced in the same manner as the syllables of the 4th order, and some
+    consonants.
+
+  notes:
+    - (A) The vowel of the sixth order (i̠) is eliminated in spelling except when
+      the actual pronunciation requires it (e.g. not Me̠ni̠gi̠si̠ti̠ but Me̠ngi̠st).
+
+    - (B) Sounds identical to fourth-order form.
+
+    - (C) Row 34 and most combinations with W and Y are not present in the
+      original table. These Amharic syllable characters have been taken from the
+      BGN/PCGN 1967 table, preserving however the indication of vowels as it is
+      done elsewhere in the table.
+
+    - |
+      Other systems of romanization.
+      The BGN/PCGN 1967 System is practically very close to the system above,
+      except for the diacritical marks used with vowels:
+
+      UN  BGN/PCGN
+      1st order	e̠	 e
+      1st order	a	ā (ሀ hā, ሐ hā, ኀ hā, አ ā, ’ā, ዐ ‘ā)
+      3rd order	i	ī
+      5th order	e   ē
+      6th order	i̠	 i
+
+      Other differences:
+
+      1. The vowel characters in row 16 should be romanized in the BGN/PCGN
+      System ā, u, ī, a, ē, i, and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o
+      in all other positions.
+
+      2. The characters in row 20 should be romanized in the BGN/PCGN System ‘ā,
+      ‘u, ‘ī, ‘a, ‘ē, ‘ or ‘i, and ‘o.
+
+      3. The syllables gwe̠, hwe̠, kwe̠, k’we̠ of the UN system are treated as
+      variations of the syllables go, ho, ko, k’o in the BGN/PCGN system.
+
+      4. For documentation purposes the following consonants may be romanized
+      with diacritical marks in the BGN/PCGN system: ḥ (row 3), š (row 5), ḫ (row
+      13), ẖ (row 18), t͟s’ (row 31).
+
+    - (Ref.) Second United Nations Conference on the Standardization of
+      Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers, pp.
+      165–168 (Table 2).
+}
+
+tests {
+  test "የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ", "Ye̠zegi̠ne̠ti̠ Ki̠bi̠ri̠ Be̠ Iti̠yop’i̠yachi̠ni̠ Ts’e̠ni̠to"
+  test "ታየ ሕዝባዊነት ዳር እስከዳር በርቶ", "Taye̠ Hi̠zi̠bawine̠ti̠ Dari̠ I̠si̠ke̠dari̠ Be̠ri̠to"
+  test "ለሰላም ለፍትህ ለሕዝቦች ነጻነት", "Le̠se̠lami̠ Le̠fi̠ti̠hi̠ Le̠hi̠zi̠bochi̠ Ne̠ts’ane̠ti̠"
+  test "በእኩልነት በፍቅር ቆመናል ባንድነት", "Be̠i̠kuli̠ne̠ti̠ Be̠fi̠k’i̠ri̠ K’ome̠nali̠ Bani̠di̠ne̠ti̠"
+  test "መሠረተ ፅኑ ሰብዕናን ያልሻርን", "Me̠se̠re̠te̠ Ts’i̠nu Se̠bi̠i̠nani̠ Yali̠shari̠ni̠"
+  test "ሕዝቦች ነን ለሥራ በሥራ የኖርን", "Hi̠zi̠bochi̠ Ne̠ni̠ Le̠si̠ra Be̠si̠ra Ye̠nori̠ni̠"
+  test "ድንቅ የባህል መድረክ ያኩሪ ቅርስ ባለቤት", "Di̠ni̠k’i̠ Ye̠bahi̠li̠ Me̠di̠re̠ki̠ Yakuri K’i̠ri̠si̠ Bale̠beti̠"
+  test "የተፈጥሮ ጸጋ የጀግና ሕዝብ እናት", "Ye̠te̠fe̠t’i̠ro Ts’e̠ga Ye̠je̠gi̠na Hi̠zi̠bi̠ I̠nati̠"
+  test "እንጠብቅሻለን አለብን አደራ", "I̠ni̠t’e̠bi̠k’i̠shale̠ni̠ Ale̠bi̠ni̠ Ade̠ra"
+  test "ኢትዮጵያችን ኑሪ እኛም ባንቺ እንኩራ", "Iti̠yop’i̠yachi̠ni̠ Nuri I̠nyami̠ Bani̠chi I̠ni̠kura"
+  test "ቋንቋ የድምጽ፣ የምልክት ወይም የምስል ቅንብር ሆኖ", "K’wani̠k’wa Ye̠di̠mi̠ts’i̠፣ Ye̠mi̠li̠ki̠ti̠ We̠yi̠mi̠ Ye̠mi̠si̠li̠ K’i̠ni̠bi̠ri̠ Hono"
+  test "ለማሰብ ወይም የታሰበን ሃሳብ ለሌላ ለማስተላለፍ የሚረዳ መሳሪያ ነው", "Le̠mase̠bi̠ We̠yi̠mi̠ Ye̠tase̠be̠ni̠ Hasabi̠ Le̠lela Le̠masi̠te̠lale̠fi̠ Ye̠mire̠da Me̠sariya Ne̠wi̠"
+  test "በአጭሩ ቋንቋ የምልክቶች ስርዓትና እኒህን ምልክቶች ለማቀናበር", "Be̠ach’i̠ru K’wani̠k’wa Ye̠mi̠li̠ki̠tochi̠ Si̠ri̠ati̠na I̠nihi̠ni̠ Mi̠li̠ki̠tochi̠ Le̠mak’e̠nabe̠ri̠"
+  test "የሚያስፈልጉ ህጎች ጥንቅር ነው። ቋንቋወችን ለመፈረጅ እንዲሁም", "Ye̠miyasi̠fe̠li̠gu Hi̠gochi̠ T’i̠ni̠k’i̠ri̠ Ne̠wi̠። K’wani̠k’wawe̠chi̠ni̠ Le̠me̠fe̠re̠ji̠ I̠ni̠dihumi̠"
+  test "ለምክፈል የሚያስችሉ መስፈርቶችን ለማስቀመጥ ባለው ችግር", "Le̠mi̠ki̠fe̠li̠ Ye̠miyasi̠chi̠lu Me̠si̠fe̠ri̠tochi̠ni̠ Le̠masi̠k’e̠me̠t’i̠ Bale̠wi̠ Chi̠gi̠ri̠"
+  test "ምክንያት በአሁኑ ሰዓት በርግጠኝነት ስንት ቋንቋ በዓለም ላይ", "Mi̠ki̠ni̠yati̠ Be̠ahunu Se̠ati̠ Be̠ri̠gi̠t’e̠nyi̠ne̠ti̠ Si̠ni̠ti̠ K’wani̠k’wa Be̠ale̠mi̠ Layi̠"
+  test "እንዳለ ማወቅ አስቸጋሪ ነው", "I̠ni̠dale̠ Mawe̠k’i̠ Asi̠che̠gari Ne̠wi̠"
+  test "አሰላ", "Ase̠la"
+  test "አሶሳ", "Asosa"
+  test "አንኮበር", "Ani̠kobe̠ri̠"
+  test "አክሱም", "Aki̠sumi̠"
+  test "አዋሳ", "Awasa"
+  test "አዲስ ዘመን (ከተማ)", "Adisi̠ Ze̠me̠ni̠ (ke̠te̠ma)"
+  test "አዲግራት", "Adigi̠rati̠"
+  test "አዳማ", "Adama"
+  test "ደምበጫ", "De̠mi̠be̠ch’a"
+  test "ደርባ", "De̠ri̠ba"
+  test "ደብረ ማርቆስ", "De̠bi̠re̠ Mari̠k’osi̠"
+  test "ደብረ ብርሃን", "De̠bi̠re̠ Bi̠ri̠hani̠"
+  test "ደብረ ታቦር (ከተማ)", "De̠bi̠re̠ Tabori̠ (ke̠te̠ma)"
+  test "ደብረ ዘይት", "De̠bi̠re̠ Ze̠yi̠ti̠"
+  test "ደገሃቡር", "De̠ge̠haburi̠"
+  test "ወልቂጤ", "We̠li̠k’it’e"
+  test "ወልወል", "We̠li̠we̠li̠"
+  test "ወልደያ", "We̠li̠de̠ya"
+  test "ናይሎ ሳህራን", "Nayi̠lo Sahi̠rani̠"
+  test "አኙዋክኛ", "Anyuwaki̠nya"
+  test "ኡዱክኛ", "Uduki̠nya"
+  test "ኦፓኛ", "Opanya"
+  test "ጉምዝኛ", "Gumi̠zi̠nya"
+  test "አፋርኛ", "Afari̠nya"
+  test "አላባኛ", "Alabanya"
+  test "አርቦርኛ", "Ari̠bori̠nya"
+  test "ባይሶኛ", "Bayi̠sonya"
+  test "ቡሳኛ", "Busanya"
+  test "ሁለተኛ ጥፋት ከገበያ ማንቀላፋት", "Hule̠te̠nya T’i̠fati̠ Ke̠ge̠be̠ya Mani̠k’e̠lafati̠"
+  test "ሁሉም ከልኩ አያልፍም", "Hulumi̠ Ke̠li̠ku Ayali̠fi̠mi̠"
+  test "አልሞት ባይ ተጋዳይ", "Ali̠moti̠ Bayi̠ Te̠gadayi̠"
+  test "ውርድ ከራሴ", "Wi̠ri̠di̠ Ke̠rase"
+  test "ፀጉር መሰንጠቅ", "Ts’e̠guri̠ Me̠se̠ni̠t’e̠k’i̠"
+  test "ግንትር ፀሐይ", "Gi̠ni̠ti̠ri̠ Ts’e̠hayi̠"
+  test "በሬ ወለደ", "Be̠re We̠le̠de̠"
+  test "ራስ ሳይጠና ጉተና", "Rasi̠ Sayi̠t’e̠na Gute̠na"
+  test "ለሆዴ ጠግቤ በልብሴ አንግቤ", "Le̠hode T’e̠gi̠be Be̠li̠bi̠se Ani̠gi̠be"
+  test "ለልጅ ከሳቁለት ለውሻ ከሮጡለት", "Le̠li̠ji̠ Ke̠sak’ule̠ti̠ Le̠wi̠sha Ke̠rot’ule̠ti̠"
+  test "መልካም ባል መጥፎ ሴት ይገራል", "Me̠li̠kami̠ Bali̠ Me̠t’i̠fo Seti̠ Yi̠ge̠rali̠"
+  test "ሆድና ግንባር አይሸሸግም", "Hodi̠na Gi̠ni̠bari̠ Ayi̠she̠she̠gi̠mi̠"
+  test "ቀሊል አማት ሲሶ በትር አላት", "K’e̠lili̠ Amati̠ Siso Be̠ti̠ri̠ Alati̠"
+  test "ጨው ለራስህ ብለህ ጣፍጥ አለበለዚያ ድንጋይ ነው ብለው ይወረውሩሀል", "Ch’e̠wi̠ Le̠rasi̠hi̠ Bi̠le̠hi̠ T’afi̠t’i̠ Ale̠be̠le̠ziya Di̠ni̠gayi̠ Ne̠wi̠ Bi̠le̠wi̠ Yi̠we̠re̠wi̠ruhali̠"
+  test "ጀምሮ ይጨርሳል አልሞ ይተኩሳል", "Je̠mi̠ro Yi̠ch’e̠ri̠sali̠ Ali̠mo Yi̠te̠kusali̠"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u1200", "ha" # ሀ (see note B)
+    sub "\u1201", "hu" # ሁ
+    sub "\u1202", "hi" # ሂ
+    sub "\u1203", "ha" # ሃ
+    sub "\u1204", "he" # ሄ
+    sub "\u1205", any(["hi̠", "h"]) # ህ
+    sub "\u1206", "ho" # ሆ
+    # Combinations with W and Y (see note C):
+    sub "\u1207", "hwa" # ሇ
+
+    sub "\u1208", "le̠" # ለ
+    sub "\u1209", "lu" # ሉ
+    sub "\u120A", "li" # ሊ
+    sub "\u120B", "la" # ላ
+    sub "\u120C", "le" # ሌ
+    sub "\u120D", any(["li̠", "l"]) # ል
+    sub "\u120E", "lo" # ሎ
+    # Combinations with W and Y (see note C):
+    sub "\u120F", "lwa" # ሏ
+
+    sub "\u1210", "ha" # ሐ (see note B)
+    sub "\u1211", "hu" # ሑ
+    sub "\u1212", "hi" # ሒ
+    sub "\u1213", "ha" # ሓ
+    sub "\u1214", "he" # ሔ
+    sub "\u1215", any(["hi̠", "h"]) # ሕ
+    sub "\u1216", "ho" # ሖ
+
+    sub "\u1218", "me̠" # መ
+    sub "\u1219", "mu" # ሙ
+    sub "\u121A", "mi" # ሚ
+    sub "\u121B", "ma" # ማ
+    sub "\u121C", "me" # ሜ
+    sub "\u121D", any(["mi̠", "m"]) # ም
+    sub "\u121E", "mo" # ሞ
+    # Combinations with W and Y (see note C):
+    sub "\u121F", "mwa" # ሟ
+    sub "\u1359", "mya" # ፙ
+
+    sub "\u1220", "se̠" # ሠ
+    sub "\u1221", "su" # ሡ
+    sub "\u1222", "si" # ሢ
+    sub "\u1223", "sa" # ሣ
+    sub "\u1224", "se" # ሤ
+    sub "\u1225", any(["si̠", "s"]) # ሥ
+    sub "\u1226", "so" # ሦ
+
+    sub "\u1228", "re̠" # ረ
+    sub "\u1229", "ru" # ሩ
+    sub "\u122A", "ri" # ሪ
+    sub "\u122B", "ra" # ራ
+    sub "\u122C", "re" # ሬ
+    sub "\u122D", any(["ri̠", "r"]) # ር
+    sub "\u122E", "ro" # ሮ
+    # Combinations with W and Y (see note C):
+    sub "\u122F", "rwa" # ሯ
+    sub "\u1358", "rya" # ፘ
+
+    sub "\u1230", "se̠" # ሰ
+    sub "\u1231", "su" # ሱ
+    sub "\u1232", "si" # ሲ
+    sub "\u1233", "sa" # ሳ
+    sub "\u1234", "se" # ሴ
+    sub "\u1235", any(["si̠", "s"]) # ስ
+    sub "\u1236", "so" # ሶ
+    # Combinations with W and Y (see note C):
+    sub "\u1237", "swa" # ሷ
+
+    sub "\u1238", "she̠" # ሸ
+    sub "\u1239", "shu" # ሹ
+    sub "\u123A", "shi" # ሺ
+    sub "\u123B", "sha" # ሻ
+    sub "\u123C", "she" # ሼ
+    sub "\u123D", any(["shi̠", "sh"]) # ሽ
+    sub "\u123E", "sho" # ሾ
+    # Combinations with W and Y (see note C):
+    sub "\u123F", "shwa" # ሿ
+
+    sub "\u1240", "k’e̠" # ቀ
+    sub "\u1241", "k’u" # ቁ
+    sub "\u1242", "k’i" # ቂ
+    sub "\u1243", "k’a" # ቃ
+    sub "\u1244", "k’e" # ቄ
+    sub "\u1245", any(["k’i̠", "k’"]) # ቅ
+    sub "\u1246", "k’o" # ቆ
+    # Combinations with W and Y (see note C):
+    sub "\u1248", "k’we̠" # ቈ
+    sub "\u124A", "k’wi" # ቊ
+    sub "\u124B", "k’wa" # ቋ
+    sub "\u124C", "k’we" # ቌ
+    sub "\u124D", "k’wi̠" # ቍ
+
+    sub "\u1260", "be̠" # በ
+    sub "\u1261", "bu" # ቡ
+    sub "\u1262", "bi" # ቢ
+    sub "\u1263", "ba" # ባ
+    sub "\u1264", "be" # ቤ
+    sub "\u1265", any(["bi̠", "b"]) # ብ
+    sub "\u1266", "bo" # ቦ
+    # Combinations with W and Y (see note C):
+    sub "\u1267", "bwa" # ቧ
+
+    sub "\u1270", "te̠" # ተ
+    sub "\u1271", "tu" # ቱ
+    sub "\u1272", "ti" # ቲ
+    sub "\u1273", "ta" # ታ
+    sub "\u1274", "te" # ቴ
+    sub "\u1275", any(["ti̠", "t"]) # ት
+    sub "\u1276", "to" # ቶ
+    # Combinations with W and Y (see note C):
+    sub "\u1277", "twa" # ቷ
+
+    sub "\u1278", "che̠" # ቸ
+    sub "\u1279", "chu" # ቹ
+    sub "\u127A", "chi" # ቺ
+    sub "\u127B", "cha" # ቻ
+    sub "\u127C", "che" # ቼ
+    sub "\u127D", any(["chi̠", "ch"]) # ች
+    sub "\u127E", "cho" # ቾ
+    # Combinations with W and Y (see note C):
+    sub "\u127F", "chwa" # ቿ
+
+    sub "\u1280", "ha" # ኀ (note B)
+    sub "\u1281", "hu" # ኁ
+    sub "\u1282", "hi" # ኂ
+    sub "\u1283", "ha" # ኃ
+    sub "\u1284", "he" # ኄ
+    sub "\u1285", any(["hi̠", "h"]) # ኅ
+    sub "\u1286", "ho" # ኆ
+    # Combinations with W and Y (see note C):
+    sub "\u1288", "hwe̠" # ኈ
+    sub "\u128A", "hwi" # ኊ
+    sub "\u128B", "hwa" # ኋ
+    sub "\u128C", "hwe" # ኌ
+    sub "\u128D", "hwi̠" # ኍ
+
+    sub "\u1290", "ne̠" # ነ
+    sub "\u1291", "nu" # ኑ
+    sub "\u1292", "ni" # ኒ
+    sub "\u1293", "na" # ና
+    sub "\u1294", "ne" # ኔ
+    sub "\u1295", any(["ni̠", "n"]) # ን
+    sub "\u1296", "no" # ኖ
+    # Combinations with W and Y (see note C):
+    sub "\u1297", "nwa" # ኗ
+
+    sub "\u1298", "nye̠" # ኘ
+    sub "\u1299", "nyu" # ኙ
+    sub "\u129A", "nyi" # ኚ
+    sub "\u129B", "nya" # ኛ
+    sub "\u129C", "nye" # ኜ
+    sub "\u129D", any(["nyi̠", "ny"]) # ኝ
+    sub "\u129E", "nyo" # ኞ
+    # Combinations with W and Y (see note C):
+    sub "\u129F", "nywa" # ኟ
+
+    sub "\u12A0", "a" # አ (note B)
+    sub "\u12A1", "u" # ኡ
+    sub "\u12A2", "i" # ኢ
+    sub "\u12A3", "a" # ኣ
+    sub "\u12A4", "e" # ኤ
+    sub "\u12A5", "i̠" # እ
+    sub "\u12A6", "o" # ኦ
+
+    sub "\u12A8", "ke̠" # ከ
+    sub "\u12A9", "ku" # ኩ
+    sub "\u12AA", "ki" # ኪ
+    sub "\u12AB", "ka" # ካ
+    sub "\u12AC", "ke" # ኬ
+    sub "\u12AD", any(["ki̠", "k"]) # ክ
+    sub "\u12AE", "ko" # ኮ
+    # Combinations with W and Y (see note C):
+    sub "\u12B0", "kwe̠" # ኰ
+    sub "\u12B2", "kwi" # ኲ
+    sub "\u12B3", "kwa" # ኳ
+    sub "\u12B4", "kwe" # ኴ
+    sub "\u12B5", "kwi̠" # ኵ
+
+    sub "\u12B8", "he̠" # ኸ
+    sub "\u12B9", "hu" # ኹ
+    sub "\u12BA", "hi" # ኺ
+    sub "\u12BB", "ha" # ኻ
+    sub "\u12BC", "he" # ኼ
+    sub "\u12BD", any(["hi̠", "h"]) # ኽ
+    sub "\u12BE", "ho" # ኾ
+
+    sub "\u12C8", "we̠" # ወ
+    sub "\u12C9", "wu" # ዉ
+    sub "\u12CA", "wi" # ዊ
+    sub "\u12CB", "wa" # ዋ
+    sub "\u12CC", "we" # ዌ
+    sub "\u12CD", any(["wi̠", "w"]) # ው
+    sub "\u12CE", "wo" # ዎ
+
+    sub "\u12D0", "a" # ዐ (note B)
+    sub "\u12D1", "u" # ዑ
+    sub "\u12D2", "i" # ዒ
+    sub "\u12D3", "a" # ዓ
+    sub "\u12D4", "e" # ዔ
+    sub "\u12D5", "i̠" # ዕ
+    sub "\u12D6", "o" # ዖ
+
+    sub "\u12D8", "ze̠" # ዘ
+    sub "\u12D9", "zu" # ዙ
+    sub "\u12DA", "zi" # ዚ
+    sub "\u12DB", "za" # ዛ
+    sub "\u12DC", "ze" # ዜ
+    sub "\u12DD", any(["zi̠", "z"]) # ዝ
+    sub "\u12DE", "zo" # ዞ
+    # Combinations with W and Y (see note C):
+    sub "\u12DF", "zwa" # ዟ
+
+    sub "\u12E0", "zhe̠" # ዠ
+    sub "\u12E1", "zhu" # ዡ
+    sub "\u12E2", "zhi" # ዢ
+    sub "\u12E3", "zha" # ዣ
+    sub "\u12E4", "zhe" # ዤ
+    sub "\u12E5", any(["zhi̠", "zh"]) # ዥ
+    sub "\u12E6", "zho" # ዦ
+    # Combinations with W and Y (see note C):
+    sub "\u12E7", "zhwa" # ዧ
+
+    sub "\u12E8", "ye̠" # የ
+    sub "\u12E9", "yu" # ዩ
+    sub "\u12EA", "yi" # ዪ
+    sub "\u12EB", "ya" # ያ
+    sub "\u12EC", "ye" # ዬ
+    sub "\u12ED", any(["yi̠", "y"]) # ይ
+    sub "\u12EE", "yo" # ዮ
+    sub "\u12EF", "ywa" # ዯ
+
+    sub "\u12F0", "de̠" # ደ
+    sub "\u12F1", "du" # ዱ
+    sub "\u12F2", "di" # ዲ
+    sub "\u12F3", "da" # ዳ
+    sub "\u12F4", "de" # ዴ
+    sub "\u12F5", any(["di̠", "d"]) # ድ
+    sub "\u12F6", "do" # ዶ
+    # Combinations with W and Y (see note C):
+    sub "\u12F7", "dwa" # ዷ
+
+    sub "\u1300", "je̠" # ጀ
+    sub "\u1301", "ju" # ጁ
+    sub "\u1302", "ji" # ጂ
+    sub "\u1303", "ja" # ጃ
+    sub "\u1304", "je" # ጄ
+    sub "\u1305", any(["ji̠", "j"]) # ጅ
+    sub "\u1306", "jo" # ጆ
+    # Combinations with W and Y (see note C):
+    sub "\u1307", "jwa" # ጇ
+
+    sub "\u1308", "ge̠" # ገ
+    sub "\u1309", "gu" # ጉ
+    sub "\u130A", "gi" # ጊ
+    sub "\u130B", "ga" # ጋ
+    sub "\u130C", "ge" # ጌ
+    sub "\u130D", any(["gi̠", "g"]) # ግ
+    sub "\u130E", "go" # ጎ
+    # Combinations with W and Y (see note C):
+    sub "\u1310", "gwe̠" # ጐ
+    sub "\u1312", "gwi" # ጒ
+    sub "\u1313", "gwa" # ጓ
+    sub "\u1314", "gwe" # ጔ
+    sub "\u1315", "gwi̠" # ጕ
+
+    sub "\u1320", "t’e̠" # ጠ
+    sub "\u1321", "t’u" # ጡ
+    sub "\u1322", "t’i" # ጢ
+    sub "\u1323", "t’a" # ጣ
+    sub "\u1324", "t’e" # ጤ
+    sub "\u1325", any(["t’i̠", "t’"]) # ጥ
+    sub "\u1326", "t’o" # ጦ
+    # Combinations with W and Y (see note C):
+    sub "\u1327", "t’wa" # ጧ
+
+    sub "\u1328", "ch’e̠" # ጨ
+    sub "\u1329", "ch’u" # ጩ
+    sub "\u132A", "ch’i" # ጪ
+    sub "\u132B", "ch’a" # ጫ
+    sub "\u132C", "ch’e" # ጬ
+    sub "\u132D", any(["ch’i̠", "ch’"]) # ጭ
+    sub "\u132E", "ch’o" # ጮ
+    # Combinations with W and Y (see note C):
+    sub "\u132F", "ch’wa" # ጯ
+
+    sub "\u1330", "p’e̠" # ጰ
+    sub "\u1331", "p’u" # ጱ
+    sub "\u1332", "p’i" # ጲ
+    sub "\u1333", "p’a" # ጳ
+    sub "\u1334", "p’e" # ጴ
+    sub "\u1335", any(["p’i̠", "p’"]) # ጵ
+    sub "\u1336", "p’o" # ጶ
+
+    sub "\u1338", "ts’e̠" # ጸ
+    sub "\u1339", "ts’u" # ጹ
+    sub "\u133A", "ts’i" # ጺ
+    sub "\u133B", "ts’a" # ጻ
+    sub "\u133C", "ts’e" # ጼ
+    sub "\u133D", any(["ts’i̠", "ts’"]) # ጽ
+    sub "\u133E", "ts’o" # ጾ
+    # Combinations with W and Y (see note C):
+    sub "\u133F", "ts’wa" # ጿ
+
+    sub "\u1340", "ts’e̠" # ፀ
+    sub "\u1341", "ts’u" # ፁ
+    sub "\u1342", "ts’i" # ፂ
+    sub "\u1343", "ts’a" # ፃ
+    sub "\u1344", "ts’e" # ፄ
+    sub "\u1345", any(["ts’i̠", "ts’"]) # ፅ
+    sub "\u1346", "ts’o" # ፆ
+
+    sub "\u1348", "fe̠" # ፈ
+    sub "\u1349", "fu" # ፉ
+    sub "\u134A", "fi" # ፊ
+    sub "\u134B", "fa" # ፋ
+    sub "\u134C", "fe" # ፌ
+    sub "\u134D", any(["fi̠", "f"]) # ፍ
+    sub "\u134E", "fo" # ፎ
+    # Combinations with W and Y (see note C):
+    sub "\u134F", "fwa" # ፏ
+    sub "\u135A", "fya" # ፚ
+
+    sub "\u1350", "pe̠" # ፐ
+    sub "\u1351", "pu" # ፑ
+    sub "\u1352", "pi" # ፒ
+    sub "\u1353", "pa" # ፓ
+    sub "\u1354", "pe" # ፔ
+    sub "\u1355", any(["pi̠", "p"]) # ፕ
+    sub "\u1356", "po" # ፖ
+
+    sub "\u1268", "ve̠" # ቨ
+    sub "\u1269", "vu" # ቩ
+    sub "\u126A", "vi" # ቪ
+    sub "\u126B", "va" # ቫ
+    sub "\u126C", "ve" # ቬ
+    sub "\u126D", any(["vi̠", "v"]) # ቭ
+    sub "\u126E", "vo" # ቮ
+  }
+
+  title_case
+}