interscript 0.1.3 → 0.1.9

data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: stategeocadastre
 id: 1993
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: PROVISIONAL RULES OF REPRODUCING LETTERS OF THE UKRAINIAN ALPHABET WITH LATIN (ENGLISH) CHARACTERS

data/maps/ua-ukr-Cyrl-Latn-1996.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: ua
 id: 1996
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: Government of Ukraine Ukrainian System (1996)
+alias:
+  ogc11122:
+    code: ukr_Cyrl2Latn_GUP_1996
+    description: Ukrainian Government of Ukraine 1996 System
 url: http://transliteration.eki.ee/pdf/Ukrainian.pdf
 creation_date: 1996
 description: Romanization table for Ukrainian. The current national system of romanization.
@@ -190,4 +194,4 @@ map:
     "\u0449": "sch"     # щ
     "\u044e": "iu"      # ю
     "\u044f": "ia"      # я
-    "\u044c": "\u2019"  # Ь -> ’
+    "\u044c": "\u2019"  # ь -> ’

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

@@ -0,0 +1,75 @@
+---
+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
+  - source: ОЛЕКСАНДР ЯН
+    expected: OLEKSANDR YAN
+  - source: ТРАНСЛІТЕРАЦІЇ
+    expected: TRANSLITERATSII
+  - source: ПЕРЕВІРКА
+    expected: PEREVIRKA
+  - source: ВСІ МАТЕРІАЛИ РОЗМІЩЕНІ НА УМОВАХ ЛІЦЕНЗІЇ
+    expected: VSI MATERIALY ROZMISHCHENI NA UMOVAKH LITSENZII
+  - source: ВВЕДІТЬ ПРІЗВИЩЕ ТА ІМ'Я УКРАЇНСЬКИМИ ЛІТЕРАМИ
+    expected: VVEDIT PRIZVYSHCHE TA IMIA UKRAINSKYMY LITERAMY
+  - source: ДОДАТКОВА ІНФОРМАЦІЯ
+    expected: DODATKOVA INFORMATSIIA
+  - source: ДІЯЛЬНІСТЬ
+    expected: DIIALNIST
+  - source: ЮЛІЯ
+    expected: YULIIA
+  - source: ЗГОРАНИ
+    expected: ZGHORANY
+  - source: ЙОРКШИР-ТЕР'ЄР
+    expected: YORKSHYR-TERIER
+  - source: ПАПА ПАЧУКА
+    expected: PAPA PACHUKA
+  - source: ЄНАКІЄВЕ
+    expected: YENAKIIEVE
+
+map:
+  inherit: ua-ukr-Cyrl-Latn-1996
+
+  rules:
+    # override parent rules
+    - pattern: \u0027
+      result: ""
+    - pattern: \u2019
+      result: ""
+    - pattern: (?<=[З])\u0413 # Г after З or з
+      result: GH
+    - pattern: \b\u0404 # Є in initial position -> YE
+      result: YE
+    - pattern: \b\u0407 # Ї in initial position -> I
+      result: I
+    - pattern: \b\u042e # Ю in initial position -> YU
+      result: YU
+    - pattern: \b\u042f # Я in initial position -> YA
+      result: YA
+
+  characters:
+    "\u0413": 'G'    # Г
+    "\u0404": 'IE'   # Є
+    "\u0416": 'ZH'   # Ж
+    "\u0425": 'KH'   # Х
+    "\u0426": 'TS'   # Ц
+    "\u0427": 'CH'   # Ч
+    "\u0428": 'SH'   # Ш
+    "\u0429": 'SHCH' # Щ
+    "\u042e": 'IU'   # Ю
+    "\u042f": 'IA'   # Я
+    "\u042c": ''     # Ь ->
+    "\u0433": 'g'    # г
+    "\u0449": 'shch' # щ
+    "\u044e": 'iu'   # ю
+    "\u044f": 'ia'   # я
+    "\u044c": ''     # ь ->
+    "\u0027": ''     # ' ->
+    "\u2019": ''     # ’ ->

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

@@ -0,0 +1,192 @@
+---
+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://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:
+  - source: Алушта
+    expected: Alushta
+  - source: Андрій
+    expected: Andrii
+  - source: Борщагівка
+    expected: Borshchahivka
+  - source: Борисенко
+    expected: Borysenko
+  - source: Вінниця
+    expected: Vinnytsia
+  - source: Володимир
+    expected: Volodymyr
+  - source: Гадяч
+    expected: Hadiach
+  - source: Богдан
+    expected: Bohdan
+  - source: Згурський
+    expected: Zghurskyi
+  - source: Ґалаґан
+    expected: Galagan
+  - source: Ґорґани
+    expected: Gorgany
+  - source: Донецьк
+    expected: Donetsk
+  - source: Дмитро
+    expected: Dmytro
+  - source: Рівне
+    expected: Rivne
+  - source: Олег
+    expected: Oleh
+  - source: Есмань
+    expected: Esman
+  - source: Єнакієве
+    expected: Yenakiieve
+  - source: Гаєвич
+    expected: Haievych
+  - source: Короп'є
+    expected: Koropie
+  - source: Житомир
+    expected: Zhytomyr
+  - source: Жанна
+    expected: Zhanna
+  - source: Жежелів
+    expected: Zhezheliv
+  - source: Закарпаття
+    expected: Zakarpattia
+  - source: Казимирчук
+    expected: Kazymyrchuk
+  - source: Медвин
+    expected: Medvyn
+  - source: Михайленко
+    expected: Mykhailenko
+  - source: Іванків
+    expected: Ivankiv
+  - source: Іващенко
+    expected: Ivashchenko
+  - source: Їжакевич
+    expected: Yizhakevych
+  - source: Кадиївка
+    expected: Kadyivka
+  - source: Мар'їне
+    expected: Marine
+  - source: Йосипівка
+    expected: Yosypivka
+  - source: Стрий
+    expected: Stryi
+  - source: Олексій
+    expected: Oleksii
+  - source: Київ
+    expected: Kyiv
+  - source: Коваленко
+    expected: Kovalenko 
+  - source: Лебедин
+    expected: Lebedyn
+  - source: Леонід
+    expected: Leonid
+  - source: Миколаїв
+    expected: Mykolaiv
+  - source: Маринич
+    expected: Marynych
+  - source: Ніжин
+    expected: Nizhyn
+  - source: Наталія
+    expected: Nataliia
+  - source: Одеса
+    expected: Odesa
+  - source: Онищенко
+    expected: Onyshchenko
+  - source: Полтава
+    expected: Poltava
+  - source: Петро
+    expected: Petro
+  - source: Решетилівка
+    expected: Reshetylivka
+  - source: Рибчинський
+    expected: Rybchynskyi
+  - source: Суми
+    expected: Sumy
+  - source: Соломія
+    expected: Solomiia
+  - source: Тернопіль
+    expected: Ternopil
+  - source: Троць
+    expected: Trots
+  - source: Ужгород
+    expected: Uzhhorod
+  - source: Уляна
+    expected: Uliana
+  - source: Фастів
+    expected: Fastiv
+  - source: Філіпчук
+    expected: Filipchuk
+  - source: Харків
+    expected: Kharkiv
+  - source: Христина
+    expected: Khrystyna
+  - source: Біла Церква
+    expected: Bila Tserkva
+  - source: Стеценко
+    expected: Stetsenko
+  - source: Чернівці
+    expected: Chernivtsi
+  - source: Шевченко
+    expected: Shevchenko
+  - source: Шостка
+    expected: Shostka
+  - source: Кишеньки
+    expected: Kyshenky
+  - source: Щербухи
+    expected: Shcherbukhy
+  - source: Гоща
+    expected: Hoshcha
+  - source: Гаращенко
+    expected: Harashchenko
+  - source: Яготин
+    expected: Yahotyn
+  - source: Ярошенко
+    expected: Yaroshenko
+  - source: Костянтин
+    expected: Kostiantyn
+  - source: Знам'янка
+    expected: Znamianka
+  - source: Феодосія
+    expected: Feodosiia
+  - source: Згорани
+    expected: Zghorany
+  - source: Розгон
+    expected: Rozghon
+
+map:
+  inherit: ua-ukr-Cyrl-Latn-1996
+
+  rules:
+    - pattern: \u0027
+      result: ""
+    - pattern: \u2019
+      result: ""
+
+  characters:
+    "\u0429": 'Shch' # Щ
+    "\u0449": 'shch' # щ
+    "\u044c": ''     # Ь ->
+    "\u042c": ''     # ь ->
+    "\u0027": ''     # ' ->
+    "\u2019": ''     # ’ ->

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

@@ -0,0 +1,602 @@
+---
+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:
+  - source: የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ
+    expected: Ye̠zegi̠ne̠ti̠ Ki̠bi̠ri̠ Be̠ Iti̠yop’i̠yachi̠ni̠ Ts’e̠ni̠to
+  - source: ታየ ሕዝባዊነት ዳር እስከዳር በርቶ
+    expected: Taye̠ Hi̠zi̠bawine̠ti̠ Dari̠ I̠si̠ke̠dari̠ Be̠ri̠to
+  - source: ለሰላም ለፍትህ ለሕዝቦች ነጻነት
+    expected: Le̠se̠lami̠ Le̠fi̠ti̠hi̠ Le̠hi̠zi̠bochi̠ Ne̠ts’ane̠ti̠
+  - source: በእኩልነት በፍቅር ቆመናል ባንድነት
+    expected: Be̠i̠kuli̠ne̠ti̠ Be̠fi̠k’i̠ri̠ K’ome̠nali̠ Bani̠di̠ne̠ti̠
+  - source: መሠረተ ፅኑ ሰብዕናን ያልሻርን
+    expected: Me̠se̠re̠te̠ Ts’i̠nu Se̠bi̠i̠nani̠ Yali̠shari̠ni̠
+  - source: ሕዝቦች ነን ለሥራ በሥራ የኖርን
+    expected: Hi̠zi̠bochi̠ Ne̠ni̠ Le̠si̠ra Be̠si̠ra Ye̠nori̠ni̠
+  - source: ድንቅ የባህል መድረክ ያኩሪ ቅርስ ባለቤት
+    expected: Di̠ni̠k’i̠ Ye̠bahi̠li̠ Me̠di̠re̠ki̠ Yakuri K’i̠ri̠si̠ Bale̠beti̠
+  - source: የተፈጥሮ ጸጋ የጀግና ሕዝብ እናት
+    expected: Ye̠te̠fe̠t’i̠ro Ts’e̠ga Ye̠je̠gi̠na Hi̠zi̠bi̠ I̠nati̠
+  - source: እንጠብቅሻለን አለብን አደራ
+    expected: I̠ni̠t’e̠bi̠k’i̠shale̠ni̠ Ale̠bi̠ni̠ Ade̠ra
+  - source: ኢትዮጵያችን ኑሪ እኛም ባንቺ እንኩራ
+    expected: Iti̠yop’i̠yachi̠ni̠ Nuri I̠nyami̠ Bani̠chi I̠ni̠kura
+  - source: ቋንቋ የድምጽ፣ የምልክት ወይም የምስል ቅንብር ሆኖ
+    expected: K’wani̠k’wa Ye̠di̠mi̠ts’i̠፣ Ye̠mi̠li̠ki̠ti̠ We̠yi̠mi̠ Ye̠mi̠si̠li̠ K’i̠ni̠bi̠ri̠ Hono
+  - source: ለማሰብ ወይም የታሰበን ሃሳብ ለሌላ ለማስተላለፍ የሚረዳ መሳሪያ ነው
+    expected: Le̠mase̠bi̠ We̠yi̠mi̠ Ye̠tase̠be̠ni̠ Hasabi̠ Le̠lela Le̠masi̠te̠lale̠fi̠ Ye̠mire̠da Me̠sariya Ne̠wi̠
+  - source: በአጭሩ ቋንቋ የምልክቶች ስርዓትና እኒህን ምልክቶች ለማቀናበር
+    expected: Be̠ach’i̠ru K’wani̠k’wa Ye̠mi̠li̠ki̠tochi̠ Si̠ri̠ati̠na I̠nihi̠ni̠ Mi̠li̠ki̠tochi̠ Le̠mak’e̠nabe̠ri̠
+  - source: የሚያስፈልጉ ህጎች ጥንቅር ነው። ቋንቋወችን ለመፈረጅ እንዲሁም
+    expected: Ye̠miyasi̠fe̠li̠gu Hi̠gochi̠ T’i̠ni̠k’i̠ri̠ Ne̠wi̠። K’wani̠k’wawe̠chi̠ni̠ Le̠me̠fe̠re̠ji̠ I̠ni̠dihumi̠
+  - source: ለምክፈል የሚያስችሉ መስፈርቶችን ለማስቀመጥ ባለው ችግር
+    expected: Le̠mi̠ki̠fe̠li̠ Ye̠miyasi̠chi̠lu Me̠si̠fe̠ri̠tochi̠ni̠ Le̠masi̠k’e̠me̠t’i̠ Bale̠wi̠ Chi̠gi̠ri̠
+  - source: ምክንያት በአሁኑ ሰዓት በርግጠኝነት ስንት ቋንቋ በዓለም ላይ
+    expected: Mi̠ki̠ni̠yati̠ Be̠ahunu Se̠ati̠ Be̠ri̠gi̠t’e̠nyi̠ne̠ti̠ Si̠ni̠ti̠ K’wani̠k’wa Be̠ale̠mi̠ Layi̠
+  - source: እንዳለ ማወቅ አስቸጋሪ ነው
+    expected: I̠ni̠dale̠ Mawe̠k’i̠ Asi̠che̠gari Ne̠wi̠
+  - source: አሰላ
+    expected: Ase̠la
+  - source: አሶሳ
+    expected: Asosa
+  - source: አንኮበር
+    expected: Ani̠kobe̠ri̠
+  - source: አክሱም
+    expected: Aki̠sumi̠
+  - source: አዋሳ
+    expected: Awasa
+  - source: አዲስ ዘመን (ከተማ)
+    expected: Adisi̠ Ze̠me̠ni̠ (ke̠te̠ma)
+  - source: አዲግራት
+    expected: Adigi̠rati̠
+  - source: አዳማ
+    expected: Adama
+  - source: ደምበጫ
+    expected: De̠mi̠be̠ch’a
+  - source: ደርባ
+    expected: De̠ri̠ba
+  - source: ደብረ ማርቆስ
+    expected: De̠bi̠re̠ Mari̠k’osi̠
+  - source: ደብረ ብርሃን
+    expected: De̠bi̠re̠ Bi̠ri̠hani̠
+  - source: ደብረ ታቦር (ከተማ)
+    expected: De̠bi̠re̠ Tabori̠ (ke̠te̠ma)
+  - source: ደብረ ዘይት
+    expected: De̠bi̠re̠ Ze̠yi̠ti̠
+  - source: ደገሃቡር
+    expected: De̠ge̠haburi̠
+  - source: ወልቂጤ
+    expected: We̠li̠k’it’e
+  - source: ወልወል
+    expected: We̠li̠we̠li̠
+  - source: ወልደያ
+    expected: We̠li̠de̠ya
+  - source: ናይሎ ሳህራን
+    expected: Nayi̠lo Sahi̠rani̠
+  - source: አኙዋክኛ
+    expected: Anyuwaki̠nya
+  - source: ኡዱክኛ
+    expected: Uduki̠nya
+  - source: ኦፓኛ
+    expected: Opanya
+  - source: ጉምዝኛ
+    expected: Gumi̠zi̠nya
+  - source: አፋርኛ
+    expected: Afari̠nya
+  - source: አላባኛ
+    expected: Alabanya
+  - source: አርቦርኛ
+    expected: Ari̠bori̠nya
+  - source: ባይሶኛ
+    expected: Bayi̠sonya
+  - source: ቡሳኛ
+    expected: Busanya
+  - source: ሁለተኛ ጥፋት ከገበያ ማንቀላፋት
+    expected: Hule̠te̠nya T’i̠fati̠ Ke̠ge̠be̠ya Mani̠k’e̠lafati̠
+  - source: ሁሉም ከልኩ አያልፍም
+    expected: Hulumi̠ Ke̠li̠ku Ayali̠fi̠mi̠
+  - source: አልሞት ባይ ተጋዳይ
+    expected: Ali̠moti̠ Bayi̠ Te̠gadayi̠
+  - source: ውርድ ከራሴ
+    expected: Wi̠ri̠di̠ Ke̠rase
+  - source: ፀጉር መሰንጠቅ
+    expected: Ts’e̠guri̠ Me̠se̠ni̠t’e̠k’i̠
+  - source: ግንትር ፀሐይ
+    expected: Gi̠ni̠ti̠ri̠ Ts’e̠hayi̠
+  - source: በሬ ወለደ
+    expected: Be̠re We̠le̠de̠
+  - source: ራስ ሳይጠና ጉተና
+    expected: Rasi̠ Sayi̠t’e̠na Gute̠na
+  - source: ለሆዴ ጠግቤ በልብሴ አንግቤ
+    expected: Le̠hode T’e̠gi̠be Be̠li̠bi̠se Ani̠gi̠be
+  - source: ለልጅ ከሳቁለት ለውሻ ከሮጡለት
+    expected: Le̠li̠ji̠ Ke̠sak’ule̠ti̠ Le̠wi̠sha Ke̠rot’ule̠ti̠
+  - source: መልካም ባል መጥፎ ሴት ይገራል
+    expected: Me̠li̠kami̠ Bali̠ Me̠t’i̠fo Seti̠ Yi̠ge̠rali̠
+  - source: ሆድና ግንባር አይሸሸግም
+    expected: Hodi̠na Gi̠ni̠bari̠ Ayi̠she̠she̠gi̠mi̠
+  - source: ቀሊል አማት ሲሶ በትር አላት
+    expected: K’e̠lili̠ Amati̠ Siso Be̠ti̠ri̠ Alati̠
+  - source: ጨው ለራስህ ብለህ ጣፍጥ አለበለዚያ ድንጋይ ነው ብለው ይወረውሩሀል
+    expected: Ch’e̠wi̠ Le̠rasi̠hi̠ Bi̠le̠hi̠ T’afi̠t’i̠ Ale̠be̠le̠ziya Di̠ni̠gayi̠ Ne̠wi̠ Bi̠le̠wi̠ Yi̠we̠re̠wi̠ruhali̠
+  - source: ጀምሮ ይጨርሳል አልሞ ይተኩሳል
+    expected: Je̠mi̠ro Yi̠ch’e̠ri̠sali̠ Ali̠mo Yi̠te̠kusali̠
+
+map:
+  word_separator: " "
+  title_case: true
+  characters:
+    '\u1200' : 'ha'  # ሀ (see note B)
+    '\u1201' : 'hu'  # ሁ
+    '\u1202' : 'hi'  # ሂ
+    '\u1203' : 'ha'  # ሃ
+    '\u1204' : 'he'  # ሄ
+    '\u1205' :       # ህ
+      - 'hi̠'
+      - 'h'
+    '\u1206' : 'ho'  # ሆ
+    # Combinations with W and Y (see note C):
+    '\u1207' : 'hwa'  # ሇ
+
+    '\u1208' : 'le̠'  # ለ
+    '\u1209' : 'lu'  # ሉ
+    '\u120A' : 'li'  # ሊ
+    '\u120B' : 'la'  # ላ
+    '\u120C' : 'le'  # ሌ
+    '\u120D' :       # ል
+      - 'li̠'
+      - 'l'
+    '\u120E' : 'lo'  # ሎ
+    # Combinations with W and Y (see note C):
+    '\u120F' : 'lwa'  # ሏ
+
+    '\u1210' : 'ha'  # ሐ (see note B)
+    '\u1211' : 'hu'  # ሑ
+    '\u1212' : 'hi'  # ሒ
+    '\u1213' : 'ha'  # ሓ
+    '\u1214' : 'he'  # ሔ
+    '\u1215' :       # ሕ
+      - 'hi̠'
+      - 'h'
+    '\u1216' : 'ho'  # ሖ
+
+    '\u1218' : 'me̠'  # መ
+    '\u1219' : 'mu'  # ሙ
+    '\u121A' : 'mi'  # ሚ
+    '\u121B' : 'ma'  # ማ
+    '\u121C' : 'me'  # ሜ
+    '\u121D' :       # ም
+      - 'mi̠'
+      - 'm'
+    '\u121E' : 'mo'  # ሞ
+    # Combinations with W and Y (see note C):
+    '\u121F' : 'mwa'  # ሟ
+    '\u1359' : 'mya'  # ፙ
+
+    '\u1220' : 'se̠'  # ሠ
+    '\u1221' : 'su'  # ሡ
+    '\u1222' : 'si'  # ሢ
+    '\u1223' : 'sa'  # ሣ
+    '\u1224' : 'se'  # ሤ
+    '\u1225' :       # ሥ
+      - 'si̠'
+      - 's'
+    '\u1226' : 'so'  # ሦ
+
+    '\u1228' : 're̠'  # ረ
+    '\u1229' : 'ru'  # ሩ
+    '\u122A' : 'ri'  # ሪ
+    '\u122B' : 'ra'  # ራ
+    '\u122C' : 're'  # ሬ
+    '\u122D' :       # ር
+      - 'ri̠'
+      - 'r'
+    '\u122E' : 'ro'  # ሮ
+    # Combinations with W and Y (see note C):
+    '\u122F' : 'rwa'  # ሯ
+    '\u1358' : 'rya'  # ፘ
+
+    '\u1230' : 'se̠'  # ሰ
+    '\u1231' : 'su'  # ሱ
+    '\u1232' : 'si'  # ሲ
+    '\u1233' : 'sa'  # ሳ
+    '\u1234' : 'se'  # ሴ
+    '\u1235' :       # ስ
+      - 'si̠'
+      - 's'
+    '\u1236' : 'so'  # ሶ
+    # Combinations with W and Y (see note C):
+    '\u1237' : 'swa'  # ሷ
+
+    '\u1238' : 'she̠'  # ሸ
+    '\u1239' : 'shu'  # ሹ
+    '\u123A' : 'shi'  # ሺ
+    '\u123B' : 'sha'  # ሻ
+    '\u123C' : 'she'  # ሼ
+    '\u123D' :        # ሽ
+      - 'shi̠'
+      - 'sh'
+    '\u123E' : 'sho'  # ሾ
+    # Combinations with W and Y (see note C):
+    '\u123F' : 'shwa'  # ሿ
+
+    '\u1240' : 'k’e̠'  # ቀ
+    '\u1241' : 'k’u'  # ቁ
+    '\u1242' : 'k’i'  # ቂ
+    '\u1243' : 'k’a'  # ቃ
+    '\u1244' : 'k’e'  # ቄ
+    '\u1245' :        # ቅ
+      - 'k’i̠'
+      - 'k’'
+    '\u1246' : 'k’o'  # ቆ
+    # Combinations with W and Y (see note C):
+    '\u1248' : 'k’we̠'  # ቈ
+    '\u124A' : 'k’wi'  # ቊ
+    '\u124B' : 'k’wa'  # ቋ
+    '\u124C' : 'k’we'  # ቌ
+    '\u124D' : 'k’wi̠'  # ቍ
+
+    '\u1260' : 'be̠'  # በ
+    '\u1261' : 'bu'  # ቡ
+    '\u1262' : 'bi'  # ቢ
+    '\u1263' : 'ba'  # ባ
+    '\u1264' : 'be'  # ቤ
+    '\u1265' :       # ብ
+      - 'bi̠'
+      - 'b'
+    '\u1266' : 'bo'  # ቦ
+    # Combinations with W and Y (see note C):
+    '\u1267' : 'bwa'  # ቧ
+
+    '\u1270' : 'te̠'  # ተ
+    '\u1271' : 'tu'  # ቱ
+    '\u1272' : 'ti'  # ቲ
+    '\u1273' : 'ta'  # ታ
+    '\u1274' : 'te'  # ቴ
+    '\u1275' :       # ት
+      - 'ti̠'
+      - 't'
+    '\u1276' : 'to'  # ቶ
+    # Combinations with W and Y (see note C):
+    '\u1277' : 'twa'  # ቷ
+
+    '\u1278' : 'che̠'  # ቸ
+    '\u1279' : 'chu'  # ቹ
+    '\u127A' : 'chi'  # ቺ
+    '\u127B' : 'cha'  # ቻ
+    '\u127C' : 'che'  # ቼ
+    '\u127D' :        # ች
+      - 'chi̠'
+      - 'ch'
+    '\u127E' : 'cho'  # ቾ
+    # Combinations with W and Y (see note C):
+    '\u127F' : 'chwa'  # ቿ
+
+    '\u1280' : 'ha'  # ኀ (note B)
+    '\u1281' : 'hu'  # ኁ
+    '\u1282' : 'hi'  # ኂ
+    '\u1283' : 'ha'  # ኃ
+    '\u1284' : 'he'  # ኄ
+    '\u1285' :       # ኅ
+      - 'hi̠'
+      - 'h'
+    '\u1286' : 'ho'  # ኆ
+    # Combinations with W and Y (see note C):
+    '\u1288' : 'hwe̠'  # ኈ
+    '\u128A' : 'hwi'  # ኊ
+    '\u128B' : 'hwa'  # ኋ
+    '\u128C' : 'hwe'  # ኌ
+    '\u128D' : 'hwi̠'  # ኍ
+
+    '\u1290' : 'ne̠'  # ነ
+    '\u1291' : 'nu'  # ኑ
+    '\u1292' : 'ni'  # ኒ
+    '\u1293' : 'na'  # ና
+    '\u1294' : 'ne'  # ኔ
+    '\u1295' :       # ን
+      - 'ni̠'
+      - 'n'
+    '\u1296' : 'no'  # ኖ
+    # Combinations with W and Y (see note C):
+    '\u1297' : 'nwa'  # ኗ
+
+    '\u1298' : 'nye̠'  # ኘ
+    '\u1299' : 'nyu'  # ኙ
+    '\u129A' : 'nyi'  # ኚ
+    '\u129B' : 'nya'  # ኛ
+    '\u129C' : 'nye'  # ኜ
+    '\u129D' :        # ኝ
+      - 'nyi̠'
+      - 'ny'
+    '\u129E' : 'nyo'  # ኞ
+    # Combinations with W and Y (see note C):
+    '\u129F' : 'nywa'  # ኟ
+
+    '\u12A0' : 'a'  # አ (note B)
+    '\u12A1' : 'u'  # ኡ
+    '\u12A2' : 'i'  # ኢ
+    '\u12A3' : 'a'  # ኣ
+    '\u12A4' : 'e'  # ኤ
+    '\u12A5' : 'i̠'  # እ
+    '\u12A6' : 'o'  # ኦ
+
+    '\u12A8' : 'ke̠'  # ከ
+    '\u12A9' : 'ku'  # ኩ
+    '\u12AA' : 'ki'  # ኪ
+    '\u12AB' : 'ka'  # ካ
+    '\u12AC' : 'ke'  # ኬ
+    '\u12AD' :       # ክ
+      - 'ki̠'
+      - 'k'
+    '\u12AE' : 'ko'  # ኮ
+    # Combinations with W and Y (see note C):
+    '\u12B0' : 'kwe̠'  # ኰ
+    '\u12B2' : 'kwi'  # ኲ
+    '\u12B3' : 'kwa'  # ኳ
+    '\u12B4' : 'kwe'  # ኴ
+    '\u12B5' : 'kwi̠'  # ኵ
+
+    '\u12B8' : 'he̠'  # ኸ
+    '\u12B9' : 'hu'  # ኹ
+    '\u12BA' : 'hi'  # ኺ
+    '\u12BB' : 'ha'  # ኻ
+    '\u12BC' : 'he'  # ኼ
+    '\u12BD' :       # ኽ
+      - 'hi̠'
+      - 'h'
+    '\u12BE' : 'ho'  # ኾ
+
+    '\u12C8' : 'we̠'  # ወ
+    '\u12C9' : 'wu'  # ዉ
+    '\u12CA' : 'wi'  # ዊ
+    '\u12CB' : 'wa'  # ዋ
+    '\u12CC' : 'we'  # ዌ
+    '\u12CD' :       # ው
+      - 'wi̠'
+      - 'w'
+    '\u12CE' : 'wo'  # ዎ
+
+    '\u12D0' : 'a'  # ዐ (note B)
+    '\u12D1' : 'u'  # ዑ
+    '\u12D2' : 'i'  # ዒ
+    '\u12D3' : 'a'  # ዓ
+    '\u12D4' : 'e'  # ዔ
+    '\u12D5' : 'i̠'  # ዕ
+    '\u12D6' : 'o'  # ዖ
+
+    '\u12D8' : 'ze̠'  # ዘ
+    '\u12D9' : 'zu'  # ዙ
+    '\u12DA' : 'zi'  # ዚ
+    '\u12DB' : 'za'  # ዛ
+    '\u12DC' : 'ze'  # ዜ
+    '\u12DD' :       # ዝ
+      - 'zi̠'
+      - 'z'
+    '\u12DE' : 'zo'  # ዞ
+    # Combinations with W and Y (see note C):
+    '\u12DF' : 'zwa'  # ዟ
+
+    '\u12E0' : 'zhe̠'  # ዠ
+    '\u12E1' : 'zhu'  # ዡ
+    '\u12E2' : 'zhi'  # ዢ
+    '\u12E3' : 'zha'  # ዣ
+    '\u12E4' : 'zhe'  # ዤ
+    '\u12E5' :        # ዥ
+      - 'zhi̠'
+      - 'zh'
+    '\u12E6' : 'zho'  # ዦ
+    # Combinations with W and Y (see note C):
+    '\u12E7' : 'zhwa'  # ዧ
+
+    '\u12E8' : 'ye̠'  # የ
+    '\u12E9' : 'yu'  # ዩ
+    '\u12EA' : 'yi'  # ዪ
+    '\u12EB' : 'ya'  # ያ
+    '\u12EC' : 'ye'  # ዬ
+    '\u12ED' :       # ይ
+      - 'yi̠'
+      - 'y'
+    '\u12EE' : 'yo'  # ዮ
+    '\u12EF' : 'ywa'  # ዯ
+
+    '\u12F0' : 'de̠'  # ደ
+    '\u12F1' : 'du'  # ዱ
+    '\u12F2' : 'di'  # ዲ
+    '\u12F3' : 'da'  # ዳ
+    '\u12F4' : 'de'  # ዴ
+    '\u12F5' :       # ድ
+      - 'di̠'
+      - 'd'
+    '\u12F6' : 'do'  # ዶ
+    # Combinations with W and Y (see note C):
+    '\u12F7' : 'dwa'  # ዷ
+
+    '\u1300' : 'je̠'  # ጀ
+    '\u1301' : 'ju'  # ጁ
+    '\u1302' : 'ji'  # ጂ
+    '\u1303' : 'ja'  # ጃ
+    '\u1304' : 'je'  # ጄ
+    '\u1305' :       # ጅ
+      - 'ji̠'
+      - 'j'
+    '\u1306' : 'jo'  # ጆ
+    # Combinations with W and Y (see note C):
+    '\u1307' : 'jwa'  # ጇ
+
+    '\u1308' : 'ge̠'  # ገ
+    '\u1309' : 'gu'  # ጉ
+    '\u130A' : 'gi'  # ጊ
+    '\u130B' : 'ga'  # ጋ
+    '\u130C' : 'ge'  # ጌ
+    '\u130D' :       # ግ
+      - 'gi̠'
+      - 'g'
+    '\u130E' : 'go'  # ጎ
+    # Combinations with W and Y (see note C):
+    '\u1310' : 'gwe̠'  # ጐ
+    '\u1312' : 'gwi'  # ጒ
+    '\u1313' : 'gwa'  # ጓ
+    '\u1314' : 'gwe'  # ጔ
+    '\u1315' : 'gwi̠'  # ጕ
+
+    '\u1320' : 't’e̠'  # ጠ
+    '\u1321' : 't’u'  # ጡ
+    '\u1322' : 't’i'  # ጢ
+    '\u1323' : 't’a'  # ጣ
+    '\u1324' : 't’e'  # ጤ
+    '\u1325' :        # ጥ
+      - 't’i̠'
+      - 't’'
+    '\u1326' : 't’o'  # ጦ
+    # Combinations with W and Y (see note C):
+    '\u1327' : 't’wa'  # ጧ
+
+    '\u1328' : 'ch’e̠'  # ጨ
+    '\u1329' : 'ch’u'  # ጩ
+    '\u132A' : 'ch’i'  # ጪ
+    '\u132B' : 'ch’a'  # ጫ
+    '\u132C' : 'ch’e'  # ጬ
+    '\u132D' :         # ጭ
+      - 'ch’i̠'
+      - 'ch’'
+    '\u132E' : 'ch’o'  # ጮ
+    # Combinations with W and Y (see note C):
+    '\u132F' : 'ch’wa'  # ጯ
+
+    '\u1330' : 'p’e̠'  # ጰ
+    '\u1331' : 'p’u'  # ጱ
+    '\u1332' : 'p’i'  # ጲ
+    '\u1333' : 'p’a'  # ጳ
+    '\u1334' : 'p’e'  # ጴ
+    '\u1335' :        # ጵ
+      - 'p’i̠'
+      - 'p’'
+    '\u1336' : 'p’o'  # ጶ
+
+    '\u1338' : 'ts’e̠'  # ጸ
+    '\u1339' : 'ts’u'  # ጹ
+    '\u133A' : 'ts’i'  # ጺ
+    '\u133B' : 'ts’a'  # ጻ
+    '\u133C' : 'ts’e'  # ጼ
+    '\u133D' :         # ጽ
+      - 'ts’i̠'
+      - 'ts’'
+    '\u133E' : 'ts’o'  # ጾ
+    # Combinations with W and Y (see note C):
+    '\u133F' : 'ts’wa'  # ጿ
+
+    '\u1340' : 'ts’e̠'  # ፀ
+    '\u1341' : 'ts’u'  # ፁ
+    '\u1342' : 'ts’i'  # ፂ
+    '\u1343' : 'ts’a'  # ፃ
+    '\u1344' : 'ts’e'  # ፄ
+    '\u1345' :         # ፅ
+      - 'ts’i̠'
+      - 'ts’'
+    '\u1346' : 'ts’o'  # ፆ
+
+    '\u1348' : 'fe̠'  # ፈ
+    '\u1349' : 'fu'  # ፉ
+    '\u134A' : 'fi'  # ፊ
+    '\u134B' : 'fa'  # ፋ
+    '\u134C' : 'fe'  # ፌ
+    '\u134D' :       # ፍ
+      - 'fi̠'
+      - 'f'
+    '\u134E' : 'fo'  # ፎ
+    # Combinations with W and Y (see note C):
+    '\u134F' : 'fwa'  # ፏ
+    '\u135A' : 'fya'  # ፚ
+
+    '\u1350' : 'pe̠'  # ፐ
+    '\u1351' : 'pu'  # ፑ
+    '\u1352' : 'pi'  # ፒ
+    '\u1353' : 'pa'  # ፓ
+    '\u1354' : 'pe'  # ፔ
+    '\u1355' :       # ፕ
+      - 'pi̠'
+      - 'p'
+    '\u1356' : 'po'  # ፖ
+
+    '\u1268' : 've̠'  # ቨ
+    '\u1269' : 'vu'  # ቩ
+    '\u126A' : 'vi'  # ቪ
+    '\u126B' : 'va'  # ቫ
+    '\u126C' : 've'  # ቬ
+    '\u126D' :       # ቭ
+      - 'vi̠'
+      - 'v'
+    '\u126E' : 'vo'  # ቮ
+