interscript-maps 2.1.0 → 2.3.1

data/maps/bgnpcgn-prs-Arab-Latn-yaghoubi.imp

@@ -5,7 +5,7 @@ metadata {
   # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
   source_script: Arab
   destination_script: Latn
-  name: BGN/PCGN NATIONAL ROMANIZATION SYSTEM FOR AFGHANISTAN -- BGN/PCGN 2007 System (Yaghoubi)
+  name: National Romanization System for Afghanistan -- Yaghoubi (2007)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693661/ROMANIZATION_FOR_AFGHANISTAN.pdf
   creation_date: 2007
   confirmation_date: 2017-11
@@ -379,20 +379,20 @@ stage {
 
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "at̄ t̄" # الت
-    sub boundary + "\u0627\u0644\u062b", "as̄ s̄" # الث
-    sub boundary + "\u0627\u0644\u062f", "aḏ ḏ" # الد
-    sub boundary + "\u0627\u0644\u0630", "az̄ z̄" # الذ
-    sub boundary + "\u0627\u0644\u0631", "aṟ ṟ" # الر
-    sub boundary + "\u0627\u0644\u0632", "az z" # الز
-    sub boundary + "\u0627\u0644\u0633", "as s" # الس
-    sub boundary + "\u0627\u0644\u0634", "aš š" # الش
-    sub boundary + "\u0627\u0644\u0635", "as̱ s̱" # الص
-    sub boundary + "\u0627\u0644\u0636", "ad͟z d͟z" # الض
-    sub boundary + "\u0627\u0644\u0637", "aṯ ṯ" # الط
-    sub boundary + "\u0627\u0644\u0638", "aẕ ẕ" # الظ
-    sub boundary + "\u0627\u0644\u0644", "al l" # الل
-    sub boundary + "\u0627\u0644\u0646", "an n" # الن
+    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at̄ t̄" # الت
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "as̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "aḏ ḏ" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "aṟ ṟ" # الر
+    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
+    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "aš š" # الش
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "as̱ s̱" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "ad͟z d͟z" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aṯ ṯ" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "aẕ ẕ" # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
 
     # consonant characters
 

data/maps/bgnpcgn-pus-Arab-Latn-1968.imp

@@ -1,10 +1,10 @@
 metadata {
   authority_id: bgnpcgn
-  id: 2007
+  id: 1968
   language: iso-639-3:prs
   source_script: Arab
   destination_script: Latn
-  name: BGN/PCGN Romanization System -- Pashto (1968)
+  name: Romanization of Pashto (1968)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693760/ROMANIZATION_OF_PASHTO.pdf
   creation_date: 1968
   confirmation_date: 2017-11
@@ -248,20 +248,20 @@ stage {
     sub "\u0659", "ê"
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "ut t" # الت
-    sub boundary + "\u0627\u0644\u062b", "us̄ s̄" # الث
-    sub boundary + "\u0627\u0644\u062f", "ud d" # الد
-    sub boundary + "\u0627\u0644\u0630", "uz̄ z̄" # الذ
-    sub boundary + "\u0627\u0644\u0631", "ur r" # الر
-    sub boundary + "\u0627\u0644\u0632", "uz z" # الز
-    sub boundary + "\u0627\u0644\u0633", "us s" # الس
-    sub boundary + "\u0627\u0644\u0634", "ush sh" # الش
-    sub boundary + "\u0627\u0644\u0635", "uş ş" # الص
-    sub boundary + "\u0627\u0644\u0636", "uẕ ẕ" # الض
-    sub boundary + "\u0627\u0644\u0637", "uţ ţ" # الط
-    sub boundary + "\u0627\u0644\u0638", "uz̧ z̧" # الظ
-    sub boundary + "\u0627\u0644\u0644", "ul l" # الل
-    sub boundary + "\u0627\u0644\u0646", "un n" # الن
+    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "ut t" # الت
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "us̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ud d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "uz̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ur r" # الر
+    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "uz z" # الز
+    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "us s" # الس
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ush sh" # الش
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "uş ş" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "uẕ ẕ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "uţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "uz̧ z̧" # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "ul l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "un n" # الن
 
     sub "\u0626", "êy" # ئ
   }

data/maps/bgnpcgn-ron-cyrl-latn-2002.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ron
   source_script: Cyrl
   destination_script: Latn
-  name: CYRILLIC - ROMAN BGN/PCGN 2002 Agreement
+  name: Table of Correspondences for Moldovan (Cyrillic-Roman) (2002 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816780/TABLE_OF_CORRESPONDENCES_FOR_MOLDOVAN.pdf
   creation_date: 2002
   confirmation_date: 2019
@@ -14,7 +14,7 @@ metadata {
     and the current Roman alphabet. When Moldovan Roman-alphabet spellings are not available, this table
     can be used to convert Moldovan Cyrillic spellings. It should be noted that Moldovan is little used as a
     language label now, and is usually considered as Romanian.
-  
+
   notes:
     - | # 1
       This Roman-script form is used before e, i and iu.

data/maps/bgnpcgn-rue-Cyrl-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rue
   source_script: Cyrl
   destination_script: Latn
-  name: ROMANIZATION OF RUSYN, BGN/PCGN 2016 System
+  name: Romanization of Rusyn (2016)
   url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20RUSYN.pdf
   creation_date: 2016
   confirmation_date: 2017
@@ -14,17 +14,17 @@ metadata {
     The Rusyn alphabet is almost identical to the Ukrainian alphabet, but contains three characters not
     present in the Ukrainian alphabet: ё, ы, and ъ. These letters are also absent from the alphabet used by
     Pannonian Rusyn. This table applies to both dialects of Rusyn.
-  
+
   notes:
     - |
       The letters ё, ы, and ъ are present in the orthography of the Carpatho‐Rusyn variant of the Rusyn
       language. This variant is predominant among Rusyn speakers in Ukraine, Poland, Slovakia, Hungary, and
       Romania. The letters are absent from the orthography of Pannonian Rusyn, which is predominant in
       Serbia and Croatia.
-  
+
     - |
       Unicode for Latin‐script characters: Ž/ž (017D, 017E); Č/č (010C, 010D); Š/š (0160, 0161); ’ (0027).
-  
+
     - |
       The Romanization columns show only lowercase forms but, when romanizing, uppercase and
       lowercase Roman letters as appropriate should be used.
@@ -91,7 +91,7 @@ stage {
     sub "Я", "Ya" # Я
     sub "Ь", "'" # Ь => '
     sub "Ъ", "'" # Ъ => '
-    
+
     sub "а", "a" # а
     sub "б", "b" # б
     sub "в", "v" # в

data/maps/bgnpcgn-rus-Cyrl-Latn-1947.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: ROMANIZATION OF RUSSIAN, BGN/PCGN 1947 System
+  name: Romanization of Russian (1947)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/807920/ROMANIZATION_OF_RUSSIAN.pdf
   creation_date: 1947
   confirmation_date: 2019-06

data/maps/bgnpcgn-sme-Latn-Latn-1984.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:sme
   source_script: Latn
   destination_script: Latn
-  name: BGN/PCGN Northern Sami (North Lappish) 1984 Roman-Script Spelling Convention Agreement
+  name: Roman-Script Spelling Convention of Northern Sami (North Lappish) (1984 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
   creation_date: 1984
 

data/maps/bgnpcgn-srp-Cyrl-Latn-1962.imp

@@ -4,15 +4,17 @@ metadata {
   language: iso-639-2:srp
   source_script: Cyrl
   destination_script: Latn
-  name: TRANSLITERATION OF SERBIAN CYRILLIC
+  name: Transliteration of Serbian Cyrillic
   creation_date: 1962
   confirmation_date: 1962
   description: |
     Serbo-Croatian, the official national language of Yugoslavia, is a single literary language.
+
     In Serbian areas it is written in the cyrillic (Serbian) alphabet, while in Croatian areas it is
     written in the roman (Croatian) alphabet.
-    Both the BGN and PCGN use the standard Croation equivalents for fomanizing the Serbian cyrillic
-    alphabet whenether romanized names are not available.
+
+    Both the BGN and PCGN use the standard Croatian equivalents for formalizing the Serbian cyrillic
+    alphabet whenever romanized names are not available.
 
   notes:
     - The digraph dj(Dj) will occasionally be found as the Croatian equivalent of ђ(Ђ),

data/maps/bgnpcgn-srp-Cyrl-Latn-2005.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:srp
   source_script: Cyrl
   destination_script: Latn
-  name: ROMANIZATION OF SERBIAN, BGN/PCGN 2005 System
+  name: Table of Correspondences for Serbian (Cyrillic-Roman) (2005 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816783/TABLE_OF_CORRESPONDENCES_FOR_SERBIAN.pdf
   creation_date: 2005
   confirmation_date: 2019-06

data/maps/bgnpcgn-tat-Cyrl-Latn-2007.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tat
   source_script: Cyrl
   destination_script: Latn
-  name: TATAR TABLE OF CORRESPONDENCES CYRILLIC - ROMAN BGN/PCGN 2007 Agreement
+  name: Table of Correspondences for Tatar (Cyrillic-Roman) (2007 Agreement)
   url: https://geonames.nga.mil/gns/html/Romanization/TABLE%20OF%20CORRESPONDENCES%20FOR%20TATAR.pdf
   creation_date: 2007
   confirmation_date: 2017-11

data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tgk
   source_script: Cyrl
   destination_script: Latn
-  name: BGN/PCGN Romanization System -- Tajik (1994)
+  name: Romanization of Tajik (1994)
   url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20TAJIK.pdf
   creation_date: 1994
   confirmation_date: 2017-11

data/maps/bgnpcgn-tir-Ethi-Latn-2007.imp

@@ -0,0 +1,511 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2007
+  language: iso-639-2:tir
+  source_script: Ethi
+  destination_script: Latn
+  name: Romanization of Tigrinya (2007)
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693783/ROMANIZATION_OF_TIGRINYA.pdf
+  creation_date: 2007
+  description: |
+    The BGN/PCGN system for Tigrinya is designed for use in romanizing
+    geographical names written in Tigrinya (Ge’ez) characters. The Roman letters
+    and letter combinations shown as ek’uivalents to the Tigrinya characters
+    reflect modern Tigrinya pronunciation, while taking into account some
+    conscious archaisms based on Ge’ez and liturgical practices.
+
+  notes:
+    - |
+      Where consonant character sequences give rise to the romanizations
+      k-h, n-y, z-h and s-h, a hyphen may be added between them to differentiate
+      those romanizations from the digraphs kh, ny, zh and sh.
+
+    - |
+      Where possible, consonant gemination should be reflected. Though not
+      evident from the Ge’ez script, this may be ascertained from a reference
+      source, such as the Tigrinya-English dictionary, Thomas Leiper Kane,
+      Dunwoody Press, Springfield, VA, 2000.
+
+    - |
+      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 21, which are U+2018.
+        Ĭ (U+012C) ĭ (U+012D)
+        Ḥ (U+0048+0323) ḥ (U+0068+0323)
+
+    - |
+      The Romanization column shows only lowercase forms but, when
+      romanizing, uppercase and lowercase Roman letters as appropriate should be
+      used.
+
+    - |
+      Table footnote 1. The 6th-order characters should be romanized either with
+      or without the letter ĭ, depending on pronunciation.
+
+    - |
+      Table footnote 2. Forms of the consonant character ሠ are understood to be
+      becoming obsolete in Tigrinya.
+
+    - |
+      Table footnote 3. The vowel characters in row 17 should be romanized with
+      the apostrophe unless appearing as a word-initial.
+
+    - |
+      Table footnote 4. Forms of the character አ are understood to be falling into
+      disuse in Tigrinya.
+}
+
+tests {
+  test "የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ", "yeziegĭnetĭ kĭbĭrĭ be ’itĭyop’ĭyachĭnĭ ts’enĭto"
+  test "ታየ ሕዝባዊነት ዳር እስከዳር በርቶ", "taye ḥĭzĭbawinetĭ darĭ ’ĭsĭkedarĭ berĭto"
+  test "ለሰላም ለፍትህ ለሕዝቦች ነጻነት", "leselamĭ lefĭtĭhĭ leḥĭzĭbochĭ nets’anetĭ"
+  test "በእኩልነት በፍቅር ቆመናል ባንድነት", "be’ĭkulĭnetĭ befĭk’ĭrĭ k’omenalĭ banĭdĭnetĭ"
+  test "መሠረተ ፅኑ ሰብዕናን ያልሻርን", "meserete ts’ĭnu sebĭ‘ĭnanĭ yalĭsharĭnĭ"
+  test "ሕዝቦች ነን ለሥራ በሥራ የኖርን", "ḥĭzĭbochĭ nenĭ lesĭra besĭra yenorĭnĭ"
+  test "ድንቅ የባህል መድረክ ያኩሪ ቅርስ ባለቤት", "dĭnĭk’ĭ yebahĭlĭ medĭrekĭ yakuri k’ĭrĭsĭ balebietĭ"
+  test "የተፈጥሮ ጸጋ የጀግና ሕዝብ እናት", "yetefet’ĭro ts’ega yejegĭna ḥĭzĭbĭ ’ĭnatĭ"
+  test "እንጠብቅሻለን አለብን አደራ", "’ĭnĭt’ebĭk’ĭshalenĭ ’elebĭnĭ ’edera"
+  test "ኢትዮጵያችን ኑሪ እኛም ባንቺ እንኩራ", "’itĭyop’ĭyachĭnĭ nuri ’ĭnyamĭ banĭchi ’ĭnĭkura"
+  test "ቋንቋ የድምጽ, የምልክት ወይም የምስል ቅንብር ሆኖ", "k’wanĭk’wa yedĭmĭts’ĭ, yemĭlĭkĭtĭ weyĭmĭ yemĭsĭlĭ k’ĭnĭbĭrĭ hono"
+  test "ለማሰብ ወይም የታሰበን ሃሳብ ለሌላ ለማስተላለፍ የሚረዳ መሳሪያ ነው", "lemasebĭ weyĭmĭ yetasebenĭ hasabĭ leliela lemasĭtelalefĭ yemireda mesariya newĭ"
+  test "በአጭሩ ቋንቋ የምልክቶች ስርዓትና እኒህን ምልክቶች ለማቀናበር", "be’ech’ĭru k’wanĭk’wa yemĭlĭkĭtochĭ sĭrĭ‘atĭna ’ĭnihĭnĭ mĭlĭkĭtochĭ lemak’enaberĭ"
+  test "የሚያስፈልጉ ህጎች ጥንቅር ነው. ቋንቋወችን ለመፈረጅ እንዲሁም", "yemiyasĭfelĭgu hĭgochĭ t’ĭnĭk’ĭrĭ newĭ. k’wanĭk’wawechĭnĭ lemeferejĭ ’ĭnĭdihumĭ"
+  test "ለምክፈል የሚያስችሉ መስፈርቶችን ለማስቀመጥ ባለው ችግር", "lemĭkĭfelĭ yemiyasĭchĭlu mesĭferĭtochĭnĭ lemasĭk’emet’ĭ balewĭ chĭgĭrĭ"
+  test "ምክንያት በአሁኑ ሰዓት በርግጠኝነት ስንት ቋንቋ በዓለም ላይ", "mĭkĭnĭyatĭ be’ehunu se‘atĭ berĭgĭt’enyĭnetĭ sĭnĭtĭ k’wanĭk’wa be‘alemĭ layĭ"
+  test "እንዳለ ማወቅ አስቸጋሪ ነው", "’ĭnĭdale mawek’ĭ ’esĭchegari newĭ"
+  test "አሰላ", "’esela"
+  test "አሶሳ", "’esosa"
+  test "አንኮበር", "’enĭkoberĭ"
+  test "አክሱም", "’ekĭsumĭ"
+  test "አዋሳ", "’ewasa"
+  test "አዲስ ዘመን (ከተማ)", "’edisĭ zemenĭ (ketema)"
+  test "አዲግራት", "’edigĭratĭ"
+  test "አዳማ", "’edama"
+  test "ደምበጫ", "demĭbech’a"
+  test "ደርባ", "derĭba"
+  test "ደብረ ማርቆስ", "debĭre marĭk’osĭ"
+  test "ደብረ ብርሃን", "debĭre bĭrĭhanĭ"
+  test "ደብረ ታቦር (ከተማ)", "debĭre taborĭ (ketema)"
+  test "ደብረ ዘይት", "debĭre zeyĭtĭ"
+  test "ደገሃቡር", "degehaburĭ"
+  test "ወልቂጤ", "welĭk’it’ie"
+  test "ወልወል", "welĭwelĭ"
+  test "ወልደያ", "welĭdeya"
+  test "ናይሎ ሳህራን", "nayĭlo sahĭranĭ"
+  test "አኙዋክኛ", "’enyuwakĭnya"
+  test "ኡዱክኛ", "’udukĭnya"
+  test "ኦፓኛ", "’opanya"
+  test "ጉምዝኛ", "gumĭzĭnya"
+  test "አፋርኛ", "’efarĭnya"
+  test "አላባኛ", "’elabanya"
+  test "አርቦርኛ", "’erĭborĭnya"
+  test "ባይሶኛ", "bayĭsonya"
+  test "ቡሳኛ", "busanya"
+  test "ሁለተኛ ጥፋት ከገበያ ማንቀላፋት", "huletenya t’ĭfatĭ kegebeya manĭk’elafatĭ"
+  test "ሁሉም ከልኩ አያልፍም", "hulumĭ kelĭku ’eyalĭfĭmĭ"
+  test "አልሞት ባይ ተጋዳይ", "’elĭmotĭ bayĭ tegadayĭ"
+  test "ውርድ ከራሴ", "wĭrĭdĭ kerasie"
+  test "ፀጉር መሰንጠቅ", "ts’egurĭ mesenĭt’ek’ĭ"
+  test "ግንትር ፀሐይ", "gĭnĭtĭrĭ ts’eḥeyĭ"
+  test "በሬ ወለደ", "berie welede"
+  test "ራስ ሳይጠና ጉተና", "rasĭ sayĭt’ena gutena"
+  test "ለሆዴ ጠግቤ በልብሴ አንግቤ", "lehodie t’egĭbie belĭbĭsie ’enĭgĭbie"
+  test "ለልጅ ከሳቁለት ለውሻ ከሮጡለት", "lelĭjĭ kesak’uletĭ lewĭsha kerot’uletĭ"
+  test "መልካም ባል መጥፎ ሴት ይገራል", "melĭkamĭ balĭ met’ĭfo sietĭ yĭgeralĭ"
+  test "ሆድና ግንባር አይሸሸግም", "hodĭna gĭnĭbarĭ ’eyĭsheshegĭmĭ"
+  test "ቀሊል አማት ሲሶ በትር አላት", "k’elilĭ ’ematĭ siso betĭrĭ ’elatĭ"
+  test "ጨው ለራስህ ብለህ ጣፍጥ አለበለዚያ ድንጋይ ነው ብለው ይወረውሩሀል", "ch’ewĭ lerasĭhĭ bĭlehĭ t’afĭt’ĭ ’elebeleziya dĭnĭgayĭ newĭ bĭlewĭ yĭwerewĭruhelĭ"
+  test "ጀምሮ ይጨርሳል አልሞ ይተኩሳል", "jemĭro yĭch’erĭsalĭ ’elĭmo yĭtekusalĭ"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u1200", "he" # ሀ
+    sub "\u1201", "hu" # ሁ
+    sub "\u1202", "hi" # ሂ
+    sub "\u1203", "ha" # ሃ
+    sub "\u1204", "hie" # ሄ
+    sub "\u1205", any(["hĭ", "h"]) # ህ
+    sub "\u1206", "ho" # ሆ
+
+    sub "\u1208", "le" # ለ
+    sub "\u1209", "lu" # ሉ
+    sub "\u120A", "li" # ሊ
+    sub "\u120B", "la" # ላ
+    sub "\u120C", "lie" # ሌ
+    sub "\u120D", any(["lĭ", "l"]) # ል
+    sub "\u120E", "lo" # ሎ
+
+    sub "\u1210", "ḥe" # ሐ
+    sub "\u1211", "ḥu" # ሑ
+    sub "\u1212", "ḥi" # ሒ
+    sub "\u1213", "ḥa" # ሓ
+    sub "\u1214", "ḥie" # ሔ
+    sub "\u1215", any(["ḥĭ", "ḥ"]) # ሕ
+    sub "\u1216", "ḥo" # ሖ
+
+    sub "\u1218", "me" # መ
+    sub "\u1219", "mu" # ሙ
+    sub "\u121A", "mi" # ሚ
+    sub "\u121B", "ma" # ማ
+    sub "\u121C", "mie" # ሜ
+    sub "\u121D", any(["mĭ", "m"]) # ም
+    sub "\u121E", "mo" # ሞ
+
+    # TODO: NOTE 2:
+    # Where possible, consonant gemination should be reflected. Though not
+    # evident from the Ge’ez script, this may be ascertained from a reference
+    # source, such as the Tigrinya-English dictionary, Thomas Leiper Kane,
+    # Dunwoody Press, Springfield, VA, 2000.
+    sub "\u1220", "se" # ሠ
+    sub "\u1221", "su" # ሡ
+    sub "\u1222", "si" # ሢ
+    sub "\u1223", "sa" # ሣ
+    sub "\u1224", "sie" # ሤ
+    sub "\u1225", any(["sĭ", "s"]) # ሥ
+    sub "\u1226", "so" # ሦ
+
+    sub "\u1228", "re" # ረ
+    sub "\u1229", "ru" # ሩ
+    sub "\u122A", "ri" # ሪ
+    sub "\u122B", "ra" # ራ
+    sub "\u122C", "rie" # ሬ
+    sub "\u122D", any(["rĭ", "r"]) # ር
+    sub "\u122E", "ro" # ሮ
+
+    sub "\u1230", "se" # ሰ
+    sub "\u1231", "su" # ሱ
+    sub "\u1232", "si" # ሲ
+    sub "\u1233", "sa" # ሳ
+    sub "\u1234", "sie" # ሴ
+    sub "\u1235", any(["sĭ", "s"]) # ስ
+    sub "\u1236", "so" # ሶ
+
+    sub "\u1238", "she" # ሸ
+    sub "\u1239", "shu" # ሹ
+    sub "\u123A", "shi" # ሺ
+    sub "\u123B", "sha" # ሻ
+    sub "\u123C", "shie" # ሼ
+    sub "\u123D", any(["shĭ", "sh"]) # ሽ
+    sub "\u123E", "sho" # ሾ
+
+    sub "\u1240", "k’e" # ቀ
+    sub "\u1241", "k’u" # ቁ
+    sub "\u1242", "k’i" # ቂ
+    sub "\u1243", "k’a" # ቃ
+    sub "\u1244", "k’ie" # ቄ
+    sub "\u1245", any(["k’ĭ", "k’"]) # ቅ
+    sub "\u1246", "k’o" # ቆ
+
+    sub "\u1250", "kh’e" # ቐ
+    sub "\u1251", "kh’u" # ቑ
+    sub "\u1252", "kh’i" # ቒ
+    sub "\u1253", "kh’a" # ቓ
+    sub "\u1254", "kh’ie" # ቔ
+    sub "\u1255", any(["kh’ĭ", "kh’"]) # ቕ
+    sub "\u1256", "kh’o" # ቖ
+
+    sub "\u1260", "be" # በ
+    sub "\u1261", "bu" # ቡ
+    sub "\u1262", "bi" # ቢ
+    sub "\u1263", "ba" # ባ
+    sub "\u1264", "bie" # ቤ
+    sub "\u1265", any(["bĭ", "b"]) # ብ
+    sub "\u1266", "bo" # ቦ
+
+    sub "\u1270", "te" # ተ
+    sub "\u1271", "tu" # ቱ
+    sub "\u1272", "ti" # ቲ
+    sub "\u1273", "ta" # ታ
+    sub "\u1274", "tie" # ቴ
+    sub "\u1275", any(["tĭ", "t"]) # ት
+    sub "\u1276", "to" # ቶ
+
+    sub "\u1278", "che" # ቸ
+    sub "\u1279", "chu" # ቹ
+    sub "\u127A", "chi" # ቺ
+    sub "\u127B", "cha" # ቻ
+    sub "\u127C", "chie" # ቼ
+    sub "\u127D", any(["chĭ", "ch"]) # ች
+    sub "\u127E", "cho" # ቾ
+
+    sub "\u1280", "ḥe" # ኀ
+    sub "\u1281", "ḥu" # ኁ
+    sub "\u1282", "ḥi" # ኂ
+    sub "\u1283", "ḥa" # ኃ
+    sub "\u1284", "ḥie" # ኄ
+    sub "\u1285", any(["ḥĭ", "ḥ"]) # ኅ
+    sub "\u1286", "ḥo" # ኆ
+
+    sub "\u1290", "ne" # ነ
+    sub "\u1291", "nu" # ኑ
+    sub "\u1292", "ni" # ኒ
+    sub "\u1293", "na" # ና
+    sub "\u1294", "nie" # ኔ
+    sub "\u1295", any(["nĭ", "n"]) # ን
+    sub "\u1296", "no" # ኖ
+
+    sub "\u1298", "nye" # ኘ
+    sub "\u1299", "nyu" # ኙ
+    sub "\u129A", "nyi" # ኚ
+    sub "\u129B", "nya" # ኛ
+    sub "\u129C", "nyie" # ኜ
+    sub "\u129D", any(["nyĭ", "ny"]) # ኝ
+    sub "\u129E", "nyo" # ኞ
+
+    # NOTE 3 The vowel characters in row 17 should be romanized with the
+    # apostrophe unless appearing as a word-initial.
+    # NOTE 4 Forms of the character አ are understood to be falling into disuse
+    # in Tigrinya.
+    sub "\u12A0", "’e" # አ
+    sub "\u12A1", "’u" # ኡ
+    sub "\u12A2", "’i" # ኢ
+    sub "\u12A3", "’a" # ኣ
+    sub "\u12A4", "’ie" # ኤ
+    sub "\u12A5", any(["’ĭ", "ĭ"]) # እ
+    sub "\u12A6", "’o" # ኦ
+
+    sub "\u12A8", "ke" # ከ
+    sub "\u12A9", "ku" # ኩ
+    sub "\u12AA", "ki" # ኪ
+    sub "\u12AB", "ka" # ካ
+    sub "\u12AC", "kie" # ኬ
+    sub "\u12AD", any(["kĭ", "k"]) # ክ
+    sub "\u12AE", "ko" # ኮ
+
+    sub "\u12B8", "khe" # ኸ
+    sub "\u12B9", "khu" # ኹ
+    sub "\u12BA", "khi" # ኺ
+    sub "\u12BB", "kha" # ኻ
+    sub "\u12BC", "khie" # ኼ
+    sub "\u12BD", any(["khĭ", "kh"]) # ኽ
+    sub "\u12BE", "kho" # ኾ
+
+    sub "\u12C8", "we" # ወ
+    sub "\u12C9", "wu" # ዉ
+    sub "\u12CA", "wi" # ዊ
+    sub "\u12CB", "wa" # ዋ
+    sub "\u12CC", "wie" # ዌ
+    sub "\u12CD", any(["wĭ", "w"]) # ው
+    sub "\u12CE", "wo" # ዎ
+
+    sub "\u12D0", "‘e" # ዐ
+    sub "\u12D1", "‘u" # ዑ
+    sub "\u12D2", "‘i" # ዒ
+    sub "\u12D3", "‘a" # ዓ
+    sub "\u12D4", "‘ie" # ዔ
+    sub "\u12D5", any(["‘ĭ", "‘"]) # ዕ
+    sub "\u12D6", "‘o" # ዖ
+
+    sub "\u12D8", "ze" # ዘ
+    sub "\u12D9", "zu" # ዙ
+    sub "\u12DA", "zi" # ዚ
+    sub "\u12DB", "za" # ዛ
+    sub "\u12DC", "zie" # ዜ
+    sub "\u12DD", any(["zĭ", "z"]) # ዝ
+    sub "\u12DE", "zo" # ዞ
+
+    sub "\u12E0", "zhe" # ዠ
+    sub "\u12E1", "zhu" # ዡ
+    sub "\u12E2", "zhi" # ዢ
+    sub "\u12E3", "zha" # ዣ
+    sub "\u12E4", "zhie" # ዤ
+    sub "\u12E5", any(["zhĭ", "zh"]) # ዥ
+    sub "\u12E6", "zho" # ዦ
+
+    sub "\u12E8", "ye" # የ
+    sub "\u12E9", "yu" # ዩ
+    sub "\u12EA", "yi" # ዪ
+    sub "\u12EB", "ya" # ያ
+    sub "\u12EC", "yie" # ዬ
+    sub "\u12ED", any(["yĭ", "y"]) # ይ
+    sub "\u12EE", "yo" # ዮ
+
+    sub "\u12F0", "de" # ደ
+    sub "\u12F1", "du" # ዱ
+    sub "\u12F2", "di" # ዲ
+    sub "\u12F3", "da" # ዳ
+    sub "\u12F4", "die" # ዴ
+    sub "\u12F5", any(["dĭ", "d"]) # ድ
+    sub "\u12F6", "do" # ዶ
+
+    sub "\u1300", "je" # ጀ
+    sub "\u1301", "ju" # ጁ
+    sub "\u1302", "ji" # ጂ
+    sub "\u1303", "ja" # ጃ
+    sub "\u1304", "jie" # ጄ
+    sub "\u1305", any(["jĭ", "j"]) # ጅ
+    sub "\u1306", "jo" # ጆ
+
+    sub "\u1308", "ge" # ገ
+    sub "\u1309", "gu" # ጉ
+    sub "\u130A", "gi" # ጊ
+    sub "\u130B", "ga" # ጋ
+    sub "\u130C", "gie" # ጌ
+    sub "\u130D", any(["gĭ", "g"]) # ግ
+    sub "\u130E", "go" # ጎ
+
+    sub "\u1320", "t’e" # ጠ
+    sub "\u1321", "t’u" # ጡ
+    sub "\u1322", "t’i" # ጢ
+    sub "\u1323", "t’a" # ጣ
+    sub "\u1324", "t’ie" # ጤ
+    sub "\u1325", any(["t’ĭ", "t’"]) # ጥ
+    sub "\u1326", "t’o" # ጦ
+
+    sub "\u1328", "ch’e" # ጨ
+    sub "\u1329", "ch’u" # ጩ
+    sub "\u132A", "ch’i" # ጪ
+    sub "\u132B", "ch’a" # ጫ
+    sub "\u132C", "ch’ie" # ጬ
+    sub "\u132D", any(["ch’ĭ", "ch’"]) # ጭ
+    sub "\u132E", "ch’o" # ጮ
+
+    sub "\u1330", "p’e" # ጰ
+    sub "\u1331", "p’u" # ጱ
+    sub "\u1332", "p’i" # ጲ
+    sub "\u1333", "p’a" # ጳ
+    sub "\u1334", "p’ie" # ጴ
+    sub "\u1335", any(["p’ĭ", "p’"]) # ጵ
+    sub "\u1336", "p’o" # ጶ
+
+    sub "\u1338", "ts’e" # ጸ
+    sub "\u1339", "ts’u" # ጹ
+    sub "\u133A", "ts’i" # ጺ
+    sub "\u133B", "ts’a" # ጻ
+    sub "\u133C", "ts’ie" # ጼ
+    sub "\u133D", any(["ts’ĭ", "ts’"]) # ጽ
+    sub "\u133E", "ts’o" # ጾ
+
+    sub "\u1340", "ts’e" # ፀ
+    sub "\u1341", "ts’u" # ፁ
+    sub "\u1342", "ts’i" # ፂ
+    sub "\u1343", "ts’a" # ፃ
+    sub "\u1344", "ts’ie" # ፄ
+    sub "\u1345", any(["ts’ĭ", "ts’"]) # ፅ
+    sub "\u1346", "ts’o" # ፆ
+
+    sub "\u1348", "fe" # ፈ
+    sub "\u1349", "fu" # ፉ
+    sub "\u134A", "fi" # ፊ
+    sub "\u134B", "fa" # ፋ
+    sub "\u134C", "fie" # ፌ
+    sub "\u134D", any(["fĭ", "f"]) # ፍ
+    sub "\u134E", "fo" # ፎ
+
+    sub "\u1350", "pe" # ፐ
+    sub "\u1351", "pu" # ፑ
+    sub "\u1352", "pi" # ፒ
+    sub "\u1353", "pa" # ፓ
+    sub "\u1354", "pie" # ፔ
+    sub "\u1355", any(["pĭ", "p"]) # ፕ
+    sub "\u1356", "po" # ፖ
+
+    sub "\u1268", "ve" # ቨ
+    sub "\u1269", "vu" # ቩ
+    sub "\u126A", "vi" # ቪ
+    sub "\u126B", "va" # ቫ
+    sub "\u126C", "vie" # ቬ
+    sub "\u126D", any(["vĭ", "v"]) # ቭ
+    sub "\u126E", "vo" # ቮ
+
+    # Combinations with W (Labialized Consonants)
+
+    sub "\u1248", "k’we" # ቈ
+    sub "\u124a", "k’wi" # ቊ
+    sub "\u124b", "k’wa" # ቋ
+    sub "\u124c", "k’wie" # ቌ
+    sub "\u124d", any(["k’wĭ", "k’w"]) # ቍ
+
+    sub "\u1288", "ḥwe" # ኈ
+    sub "\u128a", "ḥwi" # ኊ
+    sub "\u128b", "ḥwa" # ኋ
+    sub "\u128c", "ḥwie" # ኌ
+    sub "\u128d", any(["ḥwĭ", "ḥw"]) # ኍ
+
+    sub "\u12b0", "kwe" # ኰ
+    sub "\u12b2", "kwi" # ኲ
+    sub "\u12b3", "kwa" # ኳ
+    sub "\u12b4", "kwie" # ኴ
+    sub "\u12b5", any(["kwĭ", "kw"]) # ኵ
+
+    sub "\u1310", "gwe" # ጐ
+    sub "\u1312", "gwi" # ጒ
+    sub "\u1313", "gwa" # ጓ
+    sub "\u1314", "gwie" # ጔ
+    sub "\u1315", any(["gwĭ", "gw"]) # ጕ
+
+    sub "\u12c0", "khwe" # ዀ
+    sub "\u12c2", "khwi" # ዂ
+    sub "\u12c3", "khwa" # ዃ
+    sub "\u12c4", "khwie" # ዄ
+    sub "\u12c5", any(["khwĭ", "khw"]) # ዅ
+
+    sub "\u1258", "kh’e" # ቘ
+    sub "\u125a", "kh’i" # ቚ
+    sub "\u125b", "kh’a" # ቛ
+    sub "\u125c", "kh’ie" # ቜ
+    sub "\u125d", any(["kh’ĭ", "kh’"]) # ቝ
+
+    sub "\u120f", "lwa" # ሏ
+    sub "\u121f", "mwa" # ሟ
+    sub "\u122f", "rwa" # ሯ
+    sub "\u1237", "swa" # ሷ
+    sub "\u123f", "shwa" # ሿ
+    sub "\u1267", "bwa" # ቧ
+    sub "\u1277", "twa" # ቷ
+    sub "\u127f", "chwa" # ቿ
+
+    sub "\u1297", "nwa" # ኗ
+    sub "\u129f", "nywa" # ኟ
+    sub "\u12df", "zwa" # ዟ
+    sub "\u12e7", "zhwa" # ዧ
+    sub "\u12f7", "dwa" # ዷ
+    sub "\u1307", "jwa" # ጇ
+    sub "\u1327", "t’wa" # ጧ
+    sub "\u132f", "ch’wa" # ጯ
+    sub "\u133f", "ts’wa" # ጿ
+    sub "\u134f", "fwa" # ፏ
+
+    # Numerals
+
+    sub "\u1369", "1" # ፩
+    sub "\u136A", "2" # ፪
+    sub "\u136B", "3" # ፫
+    sub "\u136C", "4" # ፬
+    sub "\u136D", "5" # ፭
+    sub "\u136E", "6" # ፮
+    sub "\u136F", "7" # ፯
+    sub "\u1370", "8" # ፰
+    sub "\u1371", "9" # ፱
+    sub "\u1372", "10" # ፲
+    sub "\u1372\u1369", "11" # ፲፩
+    sub "\u1373", "20" # ፳
+    sub "\u1373\u1369", "21" # ፳፩
+    sub "\u1374", "30" # ፴
+    sub "\u1375", "40" # ፵
+    sub "\u1376", "50" # ፶
+    sub "\u1377", "60" # ፷
+    sub "\u1379", "80" # ፹
+    sub "\u137A", "90" # ፺
+    sub "\u137B", "100" # ፻
+
+    # These two rules are not defined in the sytsem.
+    # sub "\u1372\u137B", "1000" # ፲፻
+    # sub "\u137B\u137B", "10000" # ፻፻
+
+    # Punctuation
+
+    sub "፡", " " # Word Break (space)
+    sub "፣", "," # Comma
+    sub "፤", ";" # Semicolon
+    sub "።", "." # Period
+
+  }
+
+}
+