interscript 0.1.3 → 0.1.9

data/maps/alalc-tel-Telu-Latn-2011.yaml

@@ -0,0 +1,64 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:tel
+source_script: Telu
+destination_script: Latn
+name: Telugu Romanization, 2011
+url: http://catdir.loc.gov/catdir/cpso/romanization/telugu.pdf
+creation_date: 2011
+description: |
+  ALA-LC Romanization table for Telugu
+
+notes:
+
+  - |
+    Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the superscript sign ( ౬ ) called valapalagilaka.
+  - |
+    Exception: Sunna is transliterated by:
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+  - |
+    Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.
+    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+    transliterated m
+
+tests:
+  - source: "తమిళనాడు"
+    expected: "tamiḷanāḍu"
+  - source: "దేవాస్‌కు ౮౯౩౯ కోట్లివ్వండి"
+    expected: "dēvāsaku 8939 kŏṭalivavaṃḍi"
+  - source: "యూరప్, అమెరికాకు కోవిడ్‌ దడ"
+    expected: "yūrapa, amerikāku kŏviḍa daḍa"
+  - source: "జనవరి నాటికి అమెరికాలో టీకా"
+    expected: "janavari nāṭiki amerikālŏ ṭīkā"
+  - source: "ఫ్రాన్స్‌ను ముస్లింలు శిక్షించవచ్చు"
+    expected: "pharānasanu musaliṃlu śikaṣiñcavacacu"
+  - source: "క్లాస్‌ రూంలో ఉపాధ్యాయుడి వికృత చేష్టలు"
+    expected: "kalāsa rūṃlŏ upādhayāyuḍi vikṛta cēṣaṭalu"
+  - source: "భారీ భూకంపం; భయంకరమైన అనుభవాలు"
+    expected: "bhārī bhūkampaṃ; bhayaṅkaramaina anubhavālu"
+  - source: "నిట్ట నిలువునా కూలిన అపార్ట్‌మెంట్‌"
+    expected: "niṭaṭa niluvunā kūlina apāraṭameṇṭa"
+  - source: "పిచ్చి ప్రయోగాలకు పోతే జరిగేది ఇదే"
+    expected: "picaci parayŏgālaku pŏtē jarigēdi idē"
+  - source: "కరోనాపై సీడీసీ వైఫల్యం ఎందుకు?"
+    expected: "karŏnāpai sīḍīsī vaiphalayaṃ eṃduku?"
+  - source: "అత్యంత అరుదైన పులి పిల్లలు ఇవే!"
+    expected: "atayanta arudaina puli pilalalu ivē!"
+
+map:
+
+  inherit: alalc-tel-Telu-Latn-1997
+
+

data/maps/alalc-ukr-Cyrl-Latn-1997.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: alalc
 id: 1997
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: ALA-LC Romanization System 1997
+alias:
+  ogc11122:
+    code: ukr_Cyrl2Latn_ALA_1997
+    description: Ukrainian ALA-Library of Congress 1997 System
 url: http://catdir.loc.gov/catdir/cpso/romanization/ukrainia.pdf
 creation_date: 1997
 description: |

data/maps/alalc-ukr-Cyrl-Latn-2011.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 2011
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: ALA-LC Romanization System 1997

data/maps/apcbg-bul-Cyrl-Latn-1995.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: apcbg
 id: 1995
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: Toponymic Guidelines for Antarctica, Lyubomir Ivanov. Antarctic Place-names Commission of Bulgaria, Sofia, 1995.

data/maps/az-aze-Cyrl-Latn-1939.yaml

@@ -0,0 +1,105 @@
+---
+authority_id: az
+id: 1939
+language: iso-639-2:aze
+source_script: Cyrl
+destination_script: Latn
+url: https://omniglot.com/writing/azeri.htm
+creation_date: 1939
+description: |
+  In 1939 Joseph Stalin ordered the Cyrillic alphabet to be used by Azeri speakers in the Soviet Union.
+
+notes:
+  # from Wikipedia
+  - The letter Ц, intended for the sound [ц] in borrowed words, was used in the Azerbaijani Cyrillic alphabet until 1951. In the Azeri language, the sound [c] usually becomes [s].
+
+tests:
+  - source: Юя
+    expected: Yuya
+  # from internet
+  - source: Азәрбайҹан әлифбасы
+    expected: Azərbaycan əlifbası
+  - source: |
+      Бүтүн инсанлар ләйагәт вә һүгугларына ҝөрә азад бәрабәр доғулурлар.
+      Онларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар.
+    expected: |
+      Bütün insanlar ləyaqət və hüquqlarına görə azad bərabər doğulurlar.
+      Onların şüurları və vicdanları var və bir-birlərinə münasibətdə qardaşlıq ruhunda davranmalıdırlar.
+
+map:
+  characters:
+    "\u0410": "A"       # А
+    "\u0411": "B"       # Б
+    "\u0412": "V"       # В
+    "\u0413": "Q"       # Г
+    "\u0492": "\u011E"  # Ғ
+    "\u0414": "D"       # Д
+    "\u0415": "E"       # Е
+    "\u04D8": "\u018F"  # Ә
+    "\u0416": "J"       # Ж
+    "\u0417": "Z"       # З
+    "\u0418": "\u0130"  # И
+    "\u0419": "Y"       # Й
+    "\u041A": "K"       # К
+    "\u049C": "G"       # Ҝ
+    "\u041B": "L"       # Л
+    "\u041C": "M"       # М
+    "\u041D": "N"       # Н
+    "\u041E": "O"       # О
+    "\u04E8": "\u00D6"  # Ө
+    "\u041F": "P"       # П
+    "\u0420": "R"       # Р
+    "\u0421": "S"       # С
+    "\u0422": "T"       # Т
+    "\u0423": "U"       # У
+    "\u04AE": "\u00DC"  # Ү
+    "\u0424": "F"       # Ф
+    "\u0425": "X"       # Х
+    "\u0426": "s"       # Ц note[1]
+    "\u04BA": "H"       # Һ
+    "\u0427": "\u00C7"  # Ч
+    "\u04B8": "C"       # Ҹ
+    "\u0428": "\u015E"  # Ш
+    "\u042B": "I"       # Ы
+    "\u042D": "E"       # Э
+    "\u042E": "Yu"      # Ю
+    "\u042F": "Ya"      # Я
+
+    "\u0430": "a"       # а
+    "\u0431": "b"       # б
+    "\u0432": "v"       # в
+    "\u0433": "q"       # г
+    "\u0493": "\u011F"  # ғ
+    "\u0434": "d"       # д
+    "\u0435": "e"       # е
+    "\u04D9": "\u0259"  # ә
+    "\u0436": "j"       # ж
+    "\u0437": "z"       # з
+    "\u0438": "i"       # и
+    "\u0439": "y"       # й
+    "\u043A": "k"       # к
+    "\u049D": "g"       # ҝ
+    "\u043B": "l"       # л
+    "\u043C": "m"       # м
+    "\u043D": "n"       # н
+    "\u043E": "o"       # о
+    "\u04E9": "\u00F6"  # ө
+    "\u043F": "p"       # п
+    "\u0440": "r"       # р
+    "\u0441": "s"       # с
+    "\u0442": "t"       # т
+    "\u0443": "u"       # у
+    "\u04AF": "\u00FC"  # ү
+    "\u0444": "f"       # ф
+    "\u0445": "x"       # х
+    "\u0446": "s"       # ц note[1]
+    "\u04BB": "h"       # һ
+    "\u0447": "\u00E7"  # ч
+    "\u04B9": "c"       # ҹ
+    "\u0448": "\u015F"  # ш
+    "\u044B": "\u0131"  # ы
+    "\u044D": "e"       # э
+    "\u044E": "yu"      # ю
+    "\u044F": "ya"      # я
+
+    "\u0027": ""        # '

data/maps/az-aze-Cyrl-Latn-1958.yaml

@@ -0,0 +1,45 @@
+---
+authority_id: az
+id: 1958
+language: iso-639-2:aze
+source_script: Cyrl
+destination_script: Latn
+url: https://omniglot.com/writing/azeri.htm
+creation_date: 1958
+description: |
+  In 1939 Joseph Stalin ordered the Cyrillic alphabet to be used by Azeri speakers in the Soviet Union.
+
+notes:
+  - In 1947, the letter Цц was excluded from the alphabet. Previously, it was used for Russian borrowings
+  - In 1958, the letters Ээ, Юю, Яя were eliminated, and the letter Йй was replaced by Јј
+
+tests:
+  - source: Юя
+    expected: Юя
+  # from internet
+  - source: Азәрбајҹан әлифбасы
+    expected: Azərbaycan əlifbası
+  - source: |
+      Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад бәрабәр доғулурлар.
+      Онларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар.
+    expected: |
+      Bütün insanlar ləyaqət və hüquqlarına görə azad bərabər doğulurlar.
+      Onların şüurları və vicdanları var və bir-birlərinə münasibətdə qardaşlıq ruhunda davranmalıdırlar.
+
+map:
+  inherit: az-aze-Cyrl-Latn-1939
+
+  characters:
+    "\u0408": "Y"  # Ј note[2]
+    "\u0419": ~    # Й note[2]
+    "\u0426": ~    # Ц note[1]
+    "\u042D": ~    # Э note[2]
+    "\u042E": ~    # Ю note[2]
+    "\u042F": ~    # Я note[2]
+
+    "\u0458": "y"  # ј note[2]
+    "\u0439": ~    # й note[2]
+    "\u0446": ~    # ц note[1]
+    "\u044D": ~    # э note[2]
+    "\u044E": ~    # ю note[2]
+    "\u044F": ~    # я note[2]

data/maps/bas-rus-Cyrl-Latn-2017-bss.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bas
 id: 2017-bss
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: Streamlined Romanization of Russian Cyrillic -- Basic Streamlined System
@@ -172,4 +172,3 @@ map:
 
     # ъ -> (none)
     "\u044a": ""
-

data/maps/bas-rus-Cyrl-Latn-2017-oss.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bas
 id: 2017-oss
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: Streamlined Romanization of Russian Cyrillic -- Optimized Streamlined System

data/maps/bgn-jpn-Hrkt-Latn-1962.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgn
 id: 1962
-language: jpn
+language: iso-639-2:jpn
 source_script: Hrkt
 destination_script: Latn
 name: BGN (Modified Hepburn) System
@@ -290,5 +290,3 @@ map:
     # "ゑふ": "yō"
     # "をう": "ō"
     # "をふ": "ō"
-
-

data/maps/bgn-kor-Hang-Latn-1943.yaml

@@ -1,11 +1,15 @@
 ---
 authority_id: bgn
 id: 1943
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: BGN Agreement -- Korean McCune-Reischauer System (1943)
-url: 
+alias:
+  ogc11122:
+    code: kor_Hang2Latn_MR_1939
+    description: Korean McCune-Reischauer System, 1943 US Board on Geographic Names (BGN) Agreement
+url:
 creation_date: 1943
 adoption_date:
 description:
@@ -13,8 +17,8 @@ description:
 notes:
 
 tests:
-  - source: 서을
-    expected: "Sŏŭl"
+  - source: 서울
+    expected: "Sŏul"
   - source: 평양
     expected: "P’yŏngyang"
   - source: 부산

data/maps/bgn-kor-Kore-Latn-1943.yaml

@@ -1,11 +1,11 @@
 ---
 authority_id: bgn
 id: 1943
-language: kor
+language: iso-639-2:kor
 source_script: Kore
 destination_script: Latn
 name: BGN Agreement -- Korean McCune-Reischauer System (1943)
-url: 
+url:
 creation_date: 1943
 adoption_date:
 description:
@@ -13,8 +13,8 @@ description:
 notes:
 
 tests:
-  - source: 서을
-    expected: "Sŏŭl"
+  - source: 서울
+    expected: "Sŏul"
   - source: 平壤
     expected: "P’yŏngyang"
   - source: 釜山

data/maps/bgna-bul-Cyrl-Latn-2006.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgna
 id: 2006
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: Republic of Bulgaria system for transliteration of Bulgarian geographical names with Roman letters

data/maps/bgna-bul-Cyrl-Latn-2009.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgna
 id: 2009
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: Streamlined System for Romanization of Bulgarian

data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml

@@ -0,0 +1,532 @@
+---
+authority_id: bgnpcgn
+id: 1967
+language: iso-639-2:amh
+source_script: Ethi
+destination_script: Latn
+name: BGN/PCGN Romanization System -- Amharic (1967)
+alias:
+  ogc11122:
+    code: amh_Ethi2Latn_BGN_1967
+    description: Amharic Board on Geographic Names/Permanent Committee on Geographical Names for British Official Use(PCGN) 1967 System
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693663/ROMANIZATION_OF_AMHARIC.pdf
+creation_date: 1967
+description: |
+  Amharic is the principal and official language of Ethiopia. The BGN/PCGN system for Amharic was designed for use in romanizing names written in the Amharic alphabet. The Roman letters and letter combinations shown as equivalents to the Amharic characters reflect modern Amharic pronunciation.
+
+notes:
+  - 1. The 6th-order characters should be romanized either with or without the letter i, depending on pronunciation.
+
+  - 2. For documentation purposes, the characters romanized with h in rows 1, 3, 13, and 18 may, instead, be romanized with h, ḥ, ḫ, and ẖ, respectively; the characters both romanized with s in rows 5 and 7 may, instead, be romanized with š and s, respectively; and the characters both romanized with ts’ in rows 30 and 31 may, instead, be romanized with ts’ and ts’, respectively.
+
+  - 3. When the character ና in row 14 is known to represent the Amharic word meaning ‘and’, its romanization (na) should always be separated from the preceding and following words by spaces and should never be capitalized, e.g., Raya na K’obo.
+
+  - 4. The vowel characters in row 16 should be romanized ā, u, ī, a, ē, i, and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o in all other positions.
+
+  - 5. When the character የ in row 23 is known to represent the Amharic preposition, its romanization (Ye) should begin with an upper-case letter and written together with the following word, which should also begin with an upper-case letter, e.g., YeWiha Shet’.
+
+  - |
+    6. An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:
+
+    All apostrophes appearing in romanization are U+2019, except as they appear in row 20, which are U+2018.
+
+    Ā (U+0100) ā (U+0101)
+    Ī (U+012A) ī (U+012B)
+    Ē (U+0112) ē (U+0113)
+
+  - 7.The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used.
+
+
+tests:
+  - source: የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ
+    expected: yezēgnet kbr be ītyop’yachn ts’ento
+  - source: ታየ ሕዝባዊነት ዳር እስከዳር በርቶ
+    expected: taye hzbawīnet dar iskedar berto
+  - source: ለሰላም ለፍትህ ለሕዝቦች ነጻነት
+    expected: leselam lefth lehzboch nets’anet
+  - source: በእኩልነት በፍቅር ቆመናል ባንድነት
+    expected: beikulnet befk’r k’omenal bandnet
+  - source: መሠረተ ፅኑ ሰብዕናን ያልሻርን
+    expected: meserete ts’nu seb‘nan yalsharn
+  - source: ሕዝቦች ነን ለሥራ በሥራ የኖርን
+    expected: hzboch nen lesra besra yenorn
+  - source: ድንቅ የባህል መድረክ ያኩሪ ቅርስ ባለቤት
+    expected: dnk’ yebahl medrek yakurī k’rs balebēt
+  - source: የተፈጥሮ ጸጋ የጀግና ሕዝብ እናት
+    expected: yetefet’ro ts’ega yejegna hzb inat
+  - source: እንጠብቅሻለን አለብን አደራ
+    expected: int’ebk’shalen ālebn ādera
+  - source: ኢትዮጵያችን ኑሪ እኛም ባንቺ እንኩራ
+    expected: ītyop’yachn nurī inyam banchī inkura
+  - source: ቋንቋ የድምጽ፣ የምልክት ወይም የምስል ቅንብር ሆኖ
+    expected: k’wank’wa yedmts’፣ yemlkt weym yemsl k’nbr hono
+  - source: ለማሰብ ወይም የታሰበን ሃሳብ ለሌላ ለማስተላለፍ የሚረዳ መሳሪያ ነው
+    expected: lemaseb weym yetaseben hasab lelēla lemastelalef yemīreda mesarīya new
+  - source: በአጭሩ ቋንቋ የምልክቶች ስርዓትና እኒህን ምልክቶች ለማቀናበር
+    expected: beāch’ru k’wank’wa yemlktoch sr‘atna inīhn mlktoch lemak’enaber
+  - source: የሚያስፈልጉ ህጎች ጥንቅር ነው። ቋንቋወችን ለመፈረጅ እንዲሁም
+    expected: yemīyasfelgu hgoch t’nk’r new። k’wank’wawechn lemeferej indīhum
+  - source: ለምክፈል የሚያስችሉ መስፈርቶችን ለማስቀመጥ ባለው ችግር
+    expected: lemkfel yemīyaschlu mesfertochn lemask’emet’ balew chgr
+  - source: ምክንያት በአሁኑ ሰዓት በርግጠኝነት ስንት ቋንቋ በዓለም ላይ
+    expected: mknyat beāhunu se‘at bergt’enynet snt k’wank’wa be‘alem lay
+  - source: እንዳለ ማወቅ አስቸጋሪ ነው
+    expected: indale mawek’ āschegarī new
+  - source: አሰላ
+    expected: āsela
+  - source: አሶሳ
+    expected: āsosa
+  - source: አንኮበር
+    expected: ānkober
+  - source: አክሱም
+    expected: āksum
+  - source: አዋሳ
+    expected: āwasa
+  - source: አዲስ ዘመን (ከተማ)
+    expected: ādīs zemen (ketema)
+  - source: አዲግራት
+    expected: ādīgrat
+  - source: አዳማ
+    expected: ādama
+  - source: ደምበጫ
+    expected: dembech’a
+  - source: ደርባ
+    expected: derba
+  - source: ደብረ ማርቆስ
+    expected: debre mark’os
+  - source: ደብረ ብርሃን
+    expected: debre brhan
+  - source: ደብረ ታቦር (ከተማ)
+    expected: debre tabor (ketema)
+  - source: ደብረ ዘይት
+    expected: debre zeyt
+  - source: ደገሃቡር
+    expected: degehabur
+  - source: ወልቂጤ
+    expected: welk’īt’ē
+  - source: ወልወል
+    expected: welwel
+  - source: ወልደያ
+    expected: weldeya
+  - source: ናይሎ ሳህራን
+    expected: naylo sahran
+  - source: አኙዋክኛ
+    expected: ānyuwaknya
+  - source: ኡዱክኛ
+    expected: uduknya
+  - source: ኦፓኛ
+    expected: opanya
+  - source: ጉምዝኛ
+    expected: gumznya
+  - source: አፋርኛ
+    expected: āfarnya
+  - source: አላባኛ
+    expected: ālabanya
+  - source: አርቦርኛ
+    expected: ārbornya
+  - source: ባይሶኛ
+    expected: baysonya
+  - source: ቡሳኛ
+    expected: busanya
+  - source: ራስ ዓሊ (ትልቁ) ፬
+    expected: ras ‘alī (tlk’u) 4
+  - source: ራስ ዓሊጋዝ ፭
+    expected: ras ‘alīgaz 5
+  - source: ራስ ዐሥራትና ፮
+    expected: ras ‘āsratna 6
+  - source: ራስ ጉግሣ ፳፩
+    expected: ras gugsa 21
+  - source: ራስ ይማም ፪
+    expected: ras ymam 2
+  - source: ራስ ማርዬ ፫
+    expected: ras maryē 3
+  - source: ራስ ዶሪ ፫ ወር
+    expected: ras dorī 3 wer
+  - source: ራስ ዓሊ (ትንሹ) ፳
+    expected: ras ‘alī (tnshu) 20
+  - source: ዓፄ ቴዎድሮስ ፲፩
+    expected: ‘ats’ē tēwodros 11
+  - source: ዳግማዊ ዓጼ ተክለ ጊዮርጊስ ፫
+    expected: dagmawī ‘ats’ē tekle gīyorgīs 3
+  - source: ዓፄ ዮሐንስ ፲፩
+    expected: ‘ats’ē yohāns 11
+  - source: ዳግማዊ ዓጼ ምኒልክ ፳፩
+    expected: dagmawī ‘ats’ē mnīlk 21
+  - source: ልጅ ኢያሱ ፫
+    expected: lj īyasu 3
+  - source: ንግሥት ዘውዲቱ ፲፩
+    expected: ngst zewdītu 11
+  - source: ቀዳማዊ ኃይለ ሥላሴ
+    expected: k’edamawī hayle slasē
+
+map:
+  word_separator: " "
+  title_case: false
+  characters:
+    "\u1200": "hā" # ሀ
+    "\u1201": "hu" # ሁ
+    "\u1202": "hī" # ሂ
+    "\u1203": "ha" # ሃ
+    "\u1204": "hē" # ሄ
+    "\u1205":      # ህ
+      - "h"
+      - "hi"
+    "\u1206": "ho" # ሆ
+    "\u1208": "le" # ለ
+    "\u1209": "lu" # ሉ
+    "\u120a": "lī" # ሊ
+    "\u120b": "la" # ላ
+    "\u120c": "lē" # ሌ
+    "\u120d":      # ል
+      - "l"
+      - "li"
+    "\u120e": "lo"  # ሎ
+    "\u120f": "lwa" # ሏ
+    "\u1210": "hā"  # ሐ
+    "\u1211": "hu"  # ሑ
+    "\u1212": "hī"  # ሒ
+    "\u1213": "ha"  # ሓ
+    "\u1214": "hē"  # ሔ
+    "\u1215":       # ሕ
+      - "h"
+      - "hi"
+    "\u1216": "ho" # ሖ
+    "\u1218": "me" # መ
+    "\u1219": "mu" # ሙ
+    "\u121a": "mī" # ሚ
+    "\u121b": "ma" # ማ
+    "\u121c": "mē" # ሜ
+    "\u121d":      # ም
+      - "m"
+      - "mi"
+    "\u121e": "mo"  # ሞ
+    "\u121f": "mwa" # ሟ
+    "\u1220": "se"  # ሠ
+    "\u1221": "su"  # ሡ
+    "\u1222": "sī"  # ሢ
+    "\u1223": "sa"  # ሣ
+    "\u1224": "sē"  # ሤ
+    "\u1225":       # ሥ
+      - "s"
+      - "si"
+    "\u1226": "so" # ሦ
+    "\u1228": "re" # ረ
+    "\u1229": "ru" # ሩ
+    "\u122a": "rī" # ሪ
+    "\u122b": "ra" # ራ
+    "\u122c": "rē" # ሬ
+    "\u122d":      # ር
+      - "r"
+      - "ri"
+    "\u122e": "ro"  # ሮ
+    "\u122f": "rwa" # ሯ
+    "\u1230": "se"  # ሰ
+    "\u1231": "su"  # ሱ
+    "\u1232": "sī"  # ሲ
+    "\u1233": "sa"  # ሳ
+    "\u1234": "sē"  # ሴ
+    "\u1235":       # ስ
+      - "s"
+      - "si"
+    "\u1236": "so"  # ሶ
+    "\u1237": "swa" # ሷ
+    "\u1238": "she" # ሸ
+    "\u1239": "shu" # ሹ
+    "\u123a": "shī" # ሺ
+    "\u123b": "sha" # ሻ
+    "\u123c": "shē" # ሼ
+    "\u123d":       # ሽ
+      - "sh"
+      - "shi"
+    "\u123e": "sho"  # ሾ
+    "\u123f": "shwa" # ሿ
+    "\u1240": "k’e"  # ቀ
+    "\u1241": "k’u"  # ቁ
+    "\u1242": "k’ī"  # ቂ
+    "\u1243": "k’a"  # ቃ
+    "\u1244": "k’ē"  # ቄ
+    "\u1245":        # ቅ
+      - "k’"
+      - "k’i"
+    "\u1246": "k’o"  # ቆ
+    "\u1248": "k’o"  # ቈ
+    "\u124b": "k’wa" # ቋ
+    "\u1260": "be"   # በ
+    "\u1261": "bu"   # ቡ
+    "\u1262": "bī"   # ቢ
+    "\u1263": "ba"   # ባ
+    "\u1264": "bē"   # ቤ
+    "\u1265":        # ብ
+      - "b"
+      - "bi"
+    "\u1266": "bo"  # ቦ
+    "\u1267": "bwa" # ቧ
+    "\u1270": "te"  # ተ
+    "\u1271": "tu"  # ቱ
+    "\u1272": "tī"  # ቲ
+    "\u1273": "ta"  # ታ
+    "\u1274": "tē"  # ቴ
+    "\u1275":       # ት
+      - "t"
+      - "ti"
+    "\u1276": "to"  # ቶ
+    "\u1277": "twa" # ቷ
+    "\u1278": "che" # ቸ
+    "\u1279": "chu" # ቹ
+    "\u127a": "chī" # ቺ
+    "\u127b": "cha" # ቻ
+    "\u127c": "chē" # ቼ
+    "\u127d":       # ች
+      - "ch"
+      - "chi"
+    "\u127e": "cho"  # ቾ
+    "\u127f": "chwa" # ቿ
+    "\u1280": "hā"   # ኀ
+    "\u1281": "hu"   # ኁ
+    "\u1282": "hī"   # ኂ
+    "\u1283": "ha"   # ኃ
+    "\u1284": "hē"   # ኄ
+    "\u1285":        # ኅ
+      - "h"
+      - "hi"
+    "\u1286": "ho"   # ኆ
+    "\u1288": "ho"   # ኈ
+    "\u128b": "hwa"  # ኋ
+    "\u1290": "ne"   # ነ
+    "\u1291": "nu"   # ኑ
+    "\u1292": "nī"   # ኒ
+    "\u1293": "na"   # ና
+    "\u1294": "nē"   # ኔ
+    "\u1295":        # ን
+      - "n"
+      - "ni"
+    "\u1296": "no"   # ኖ
+    "\u1297": "nwa"  # ኗ
+    "\u1298": "nye"  # ኘ
+    "\u1299": "nyu"  # ኙ
+    "\u129a": "nyī"  # ኚ
+    "\u129b": "nya"  # ኛ
+    "\u129c": "nyē"  # ኜ
+    "\u129d":        # ኝ
+      - "ny"
+      - "nyi"
+    "\u129e": "nyo"  # ኞ
+    "\u129f": "nywa" # ኟ
+    "\u12a0":        # አ
+      - "ā"
+      - "’ā"
+    "\u12a1":        # ኡ
+      - "u"
+      - "’u"
+    "\u12a2":        # ኢ
+      - "ī"
+      - "’ī"
+    "\u12a3":        # ኣ
+      - "a"
+      - "’a"
+    "\u12a4":        # ኤ
+      - "ē"
+      - "’ē"
+    "\u12a5":        # እ
+      - "i"
+      - "’i"
+    "\u12a6":        # ኦ
+      - "o"
+      - "’o"
+    "\u12a8": "ke" # ከ
+    "\u12a9": "ku" # ኩ
+    "\u12aa": "kī" # ኪ
+    "\u12ab": "ka" # ካ
+    "\u12ac": "kē" # ኬ
+    "\u12ad":      # ክ
+      - "k"
+      - "ki"
+    "\u12ae": "ko"  # ኮ
+    "\u12b0": "ko"  # ኰ
+    "\u12b3": "kwa" # ኳ
+    "\u12b8": "he"  # ኸ
+    "\u12b9": "hu"  # ኹ
+    "\u12ba": "hī"  # ኺ
+    "\u12bb": "ha"  # ኻ
+    "\u12bc": "hē"  # ኼ
+    "\u12bd":       # ኽ
+      - "h"
+      - "hi"
+    "\u12be": "ho" # ኾ
+    "\u12c0": "ho" # ዀ
+    "\u12c8": "we" # ወ
+    "\u12c9": "wu" # ዉ
+    "\u12ca": "wī" # ዊ
+    "\u12cb": "wa" # ዋ
+    "\u12cc": "wē" # ዌ
+    "\u12cd":      # ው
+      - "w"
+      - "wi"
+    "\u12ce": "wo" # ዎ
+    "\u12d0": "‘ā" # ዐ
+    "\u12d1": "‘u" # ዑ
+    "\u12d2": "‘ī" # ዒ
+    "\u12d3": "‘a" # ዓ
+    "\u12d4": "‘ē" # ዔ
+    "\u12d5":      # ዕ
+      - "‘"
+      - "‘i"
+    "\u12d6": "‘o" # ዖ
+    "\u12d8": "ze" # ዘ
+    "\u12d9": "zu" # ዙ
+    "\u12da": "zī" # ዚ
+    "\u12db": "za" # ዛ
+    "\u12dc": "zē" # ዜ
+    "\u12dd":      # ዝ
+      - "z"
+      - "zi"
+    "\u12de": "zo"  # ዞ
+    "\u12df": "zwa" # ዟ
+    "\u12e0": "zhe" # ዠ
+    "\u12e1": "zhu" # ዡ
+    "\u12e2": "zhī" # ዢ
+    "\u12e3": "zha" # ዣ
+    "\u12e4": "zhē" # ዤ
+    "\u12e5":       # ዥ
+      - "zh"
+      - "zhi"
+    "\u12e6": "zho"  # ዦ
+    "\u12e7": "zhwa" # ዧ
+    "\u12e8": "ye"   # የ
+    "\u12e9": "yu"   # ዩ
+    "\u12ea": "yī"   # ዪ
+    "\u12eb": "ya"   # ያ
+    "\u12ec": "yē"   # ዬ
+    "\u12ed":        # ይ
+      - "y"
+      - "yi"
+    "\u12ee": "yo" # ዮ
+    "\u12f0": "de" # ደ
+    "\u12f1": "du" # ዱ
+    "\u12f2": "dī" # ዲ
+    "\u12f3": "da" # ዳ
+    "\u12f4": "dē" # ዴ
+    "\u12f5":      # ድ
+      - "d"
+      - "di"
+    "\u12f6": "do"  # ዶ
+    "\u12f7": "dwa" # ዷ
+    "\u1300": "je"  # ጀ
+    "\u1301": "ju"  # ጁ
+    "\u1302": "jī"  # ጂ
+    "\u1303": "ja"  # ጃ
+    "\u1304": "jē"  # ጄ
+    "\u1305":       # ጅ
+      - "j"
+      - "ji"
+    "\u1306": "jo"  # ጆ
+    "\u1307": "jwa" # ጇ
+    "\u1308": "ge"  # ገ
+    "\u1309": "gu"  # ጉ
+    "\u130a": "gī"  # ጊ
+    "\u130b": "ga"  # ጋ
+    "\u130c": "gē"  # ጌ
+    "\u130d":       # ግ
+      - "g"
+      - "gi"
+    "\u130e": "go"  # ጎ
+    "\u1310": "go"  # ጐ
+    "\u1313": "gwa" # ጓ
+    "\u1320": "t’e" # ጠ
+    "\u1321": "t’u" # ጡ
+    "\u1322": "t’ī" # ጢ
+    "\u1323": "t’a" # ጣ
+    "\u1324": "t’ē" # ጤ
+    "\u1325":       # ጥ
+      - "t’"
+      - "t’i"
+    "\u1326": "t’o"  # ጦ
+    "\u1327": "t’wa" # ጧ
+    "\u1328": "ch’e" # ጨ
+    "\u1329": "ch’u" # ጩ
+    "\u132a": "ch’ī" # ጪ
+    "\u132b": "ch’a" # ጫ
+    "\u132c": "ch’ē" # ጬ
+    "\u132d":        # ጭ
+      - "ch’"
+      - "ch’i"
+    "\u132e": "ch’o"  # ጮ
+    "\u132f": "ch’wa" # ጯ
+    "\u1330": "p’e"   # ጰ
+    "\u1331": "p’u"   # ጱ
+    "\u1332": "p’ī"   # ጲ
+    "\u1333": "p’a"   # ጳ
+    "\u1334": "p’ē"   # ጴ
+    "\u1335":  # ጵ
+      - "p’"
+      - "p’i"
+    "\u1336": "p’o"  # ጶ
+    "\u1338": "ts’e" # ጸ
+    "\u1339": "ts’u" # ጹ
+    "\u133a": "ts’ī" # ጺ
+    "\u133b": "ts’a" # ጻ
+    "\u133c": "ts’ē" # ጼ
+    "\u133d":        # ጽ
+      - "ts’"
+      - "ts’i"
+    "\u133e": "ts’o" # ጾ
+    "\u1340": "ts’e" # ፀ
+    "\u1341": "ts’u" # ፁ
+    "\u1342": "ts’ī" # ፂ
+    "\u1343": "ts’a" # ፃ
+    "\u1344": "ts’ē" # ፄ
+    "\u1345":        # ፅ
+      - "ts’"
+      - "ts’i"
+    "\u1346": "ts’o"  # ፆ
+    "\u133f": "ts’wa" # ጿ
+    "\u1348": "fe"    # ፈ
+    "\u1349": "fu"    # ፉ
+    "\u134a": "fī"    # ፊ
+    "\u134b": "fa"    # ፋ
+    "\u134c": "fē"    # ፌ
+    "\u134d":         # ፍ
+      - "f"
+      - "fi"
+    "\u134e": "fo"  # ፎ
+    "\u134f": "fwa" # ፏ
+    "\u1350": "pe"  # ፐ
+    "\u1351": "pu"  # ፑ
+    "\u1352": "pī"  # ፒ
+    "\u1353": "pa"  # ፓ
+    "\u1354": "pē"  # ፔ
+    "\u1355":       # ፕ
+      - "p"
+      - "pi"
+    "\u1356": "po" # ፖ
+    "\u1268": "ve" # ቨ
+    "\u1269": "vu" # ቩ
+    "\u126a": "vī" # ቪ
+    "\u126b": "va" # ቫ
+    "\u126c": "vē" # ቬ
+    "\u126d":      # ቭ
+      - "v"
+      - "vi"
+    "\u126e": "vo" # ቮ
+
+    "\u1369": "1"    # ፩
+    "\u136a": "2"    # ፪
+    "\u136b": "3"    # ፫
+    "\u136c": "4"    # ፬
+    "\u136d": "5"    # ፭
+    "\u136e": "6"    # ፮
+    "\u136f": "7"    # ፯
+    "\u1370": "8"    # ፰
+    "\u1371": "9"    # ፱
+    "\u1372": "10"   # ፲
+    "\u1372\u1369": "11"   # ፲፩
+    "\u1373": "20"   # ፳
+    "\u1373\u1369": "21"   # ፳፩
+    "\u1374": "30"   # ፴
+    "\u1375": "40"   # ፵
+    "\u1376": "50"   # ፶
+    "\u1377": "60"   # ፷
+    "\u1378": "70"   # ፸
+    "\u1379": "80"   # ፹
+    "\u137a": "90"   # ፺
+    "\u137b": "100"  # ፻