interscript-maps 2.0.5

data/maps/un-ukr-Cyrl-Latn-2012.imp

@@ -0,0 +1,95 @@
+metadata {
+  authority_id: un
+  id: 2012
+  language: iso-639-2:ukr
+  source_script: Cyrl
+  destination_script: Latn
+  name: ROMANIZATION SYSTEM FOR BELARUSIAN, RUSSIAN AND UKRAINIAN CYRILLIC
+  url: http://www.eki.ee/wgrs/rom1_uk.htm
+  creation_date: 2010
+}
+
+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-2010", as: cyrllatn
+
+stage {
+
+  run map.cyrllatn.stage.main
+
+}

data/maps/un-urd-Arab-Latn-1972.imp

@@ -0,0 +1,290 @@
+metadata {
+  authority_id: ungegn
+  id: 2017
+  language: iso-639-2:ara
+  source_script: Arab
+  destination_script: Latn
+  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+  url: https://www.eki.ee/wgrs/rom1_ur.htm
+  creation_date: 2017
+  confirmation_date: 2018-06
+  description: |
+    The United Nations recommended system was approved in 1972 (
+    II/11) and amended in 1977 (III/12), based on a report
+    prepared by D. N. Sharma. The tables and their corrections
+    were published in volume II of the conference reports1,2.
+
+    There is no evidence of the use of the system either in
+    Pakistan, India or in international cartographic products.
+    Instead, in Pakistan the Hunterian system is officially
+    used3. The resolutions III/12 (1977) and IV/17 (1982)
+    recommended association, inter alia, with Pakistan, in
+    carrying out further studies on the system.
+
+    Urdu (Urdū) uses the Perso-Arabic script which is written
+    from right to left. In the script vowel points are usually
+    omitted which makes it difficult to obtain uniform
+    romanizations. Some of the Arabic consonants are
+    undifferentiated in romanization which means that the
+    system is not fully reversible.
+  notes:
+    - A If preceded by short a, it is romanized ‘ā, e.g. مَعمُل M‘āmul.
+    - B When و is imperceptible, e.g. in a few words of Persian origin when preceded by خ (ḳh).
+    - C Word-finally after a short vowel.
+    - D Marks aspiration of consonants.
+    - E The character ے is used only word-finally.
+}
+
+tests {
+  test "بوغدِی", "Bvghdī"
+  test "مَعمُل", "M‘āmul"
+  test "پَالِير", "Pālīr"
+  test "بیزوت كَلے", "Byzvt Kale"
+  test "عَمَل كوٹ", "‘Amal Kvṭ"
+  test "ثَابِر", "Sābir"
+  test "شَاه نَثَار ميلة", "Shāh Nasār Mylah"
+  test "چَپرِی", "Chaprī"
+  test "أَحمَد خَان كَلے", "Ahmad Ḳhān Kale"
+  test "دُرَانِي", "Durānī"
+  test "ڈَنگِیلا", "Ḍangīlā"
+  test "ذَرَانِی", "Zarānī"
+  test "بُركِي", "Burkī"
+  test "گِیدَڑَه", "Gīdaṙah"
+  test "عَلِي زَائِي", "‘Alī Zā-ī"
+  test "ژوب", "Ỵvb"
+  test "بِسَاتُو", "Bisātū"
+  test "أَحمَدِي شَامَا", "Ahmadī Shāmā"
+  test "اَصَالَت كَلے", "Asālat Kale"
+  test "خَضَر خَان", "Ḳhazar Ḳhān"
+  test "سُلْطَان", "Sultān"
+  test "عَزَم سَيِّد نُور كَلے", "‘Azam Sayyid Nūr Kale"
+  test "بغَاكِي", "Bghākī"
+  test "حَقدَرَه", "Haqdarah"
+  test "کَچکِینَہ", "Kachkīnaḥ"
+  test "بَاگَن", "Bāgan"
+  test "بُلبَلَک", "Bulbalak"
+  test "بِلیَامِین", "Bilyāmīn"
+  test "نَہر", "Nahr"
+  test "اَرَوْالِی", "Arawālī"
+  test "مَہردِی", "Mahrdī"
+  test "بَڑھ", "Baṙh"
+  test "یَاردَا کَلے", "Yārdā Kale"
+  test "بهَائِي خَان", "Bhā-ī Ḳhān"
+  test "پھاشک", "Phāshk"
+  test "تھَلّ", "Thall"
+  test "پَٹھان ريَا", "Paṭhān Ryā"
+  test "جھِیل", "Jhīl"
+  test "غَزْنِي سْپِين", "Ghaznī Spīn"
+  test "بَادشَاه چھُم", "Bādshāh Chhum"
+  test "سِندھ", "Sindh"
+  test "ڈھَنڈ", "Ḍhanḍ"
+  test "خَان گھَڑِی", "Ḳhān Ghaṙī"
+  test "غُلَامَک كَلے", "Ghulāmak Kale"
+  test "خَپیَنگا", "Ḳhapyangā"
+  test "گَندَه كَلے", "Gandah Kale"
+  test "مَورپِتھِی", "Maurpithī"
+  test "درے پلارِی", "Dre Plārī"
+  test "آگرَہ", "Āgraḥ"
+  test "ڈَنڈَر", "Ḍanḍar"
+  test "گُبازانَہ", "Gubāzānaḥ"
+  test "حَےدَر عَلِی كَلے", "Haidar ‘Alī Kale"
+  test "تَودَہ چِینَہ", "Taudaḥ Chīnaḥ"
+  test "مُوسى خَان كَلے", "Mūsá Ḳhān Kale"
+  test "مُلَّا بَاغ", "Mullā Bāgh"
+}
+
+stage {
+  # Somehow, this should execute first to pass the test.
+  sub any("\u064a\u06cc") + "\u0651", "yy" # ي
+
+  # CHARACTERS
+  parallel {
+    # special rules
+
+    sub space, "", after: "\u0622\u0628\u064E\u0627\u062F" # space followed by abad is removed
+    sub "\ufdf2", "Allāh" # See note 5
+
+    # Vowels, Diphthongs, and Diacritical Marks
+    sub "\u064e", "a" # َ fatha
+    sub "\u064e\u0627", "ā" # ـَا fatha followed by ا
+    sub "\u0627", "ā" # ا
+    sub "\u0649\u0670", "ā" # ىٰ
+    sub "\u06D2\u0670", "ā" # ےٰ
+    sub "\u0622", "ā" # آ
+    sub boundary + "\u0627", "" # ا
+    sub "\u064e", "", after: "\u0629" # َ fatha followed by ta' marboota
+    sub "\u064e", "", after: "a" + any("ht") # َ fatha followed by ta' marboota, handling different order of conversion
+
+    sub "\u0652", "" # ْ sokoon
+    sub "\u0659", "ê"
+
+    sub "\u0650", "i" # karsra
+    sub "\u0650" + any("\u064a\u06cc"), "ī" # ـِي kasra followed by ي
+    sub "\u0650\u06d2\u0652", "e" # ـے
+    sub "\u0650\u06d2", "e" # ـے
+    sub "\u06d2", "e" # ـے
+
+    sub "\u064f", "u" # ُ damma
+    sub "\u064f\u0648", "ū" # ـُو damma followed by و
+    sub "\u064f\u0648\u0652", "o" # ـَوْ
+
+
+    sub "\u064e\u06d2", "ai" # ـے
+    sub "\u064e\u0648", "au" # ـَو
+    sub "\u0670", "á" # ىٰ
+    sub "\u0649", "á" # ىٰ
+
+    # shadda
+    sub "\u0628\u0651", "bb" # ب
+    sub "\u062a\u0651", "tt" # ت
+    sub "\u062b\u0651", "ss" # ث
+    sub "\u062c\u0651", "jj" # ج
+    sub "\u062d\u0651", "hh" # ح
+    sub "\u062e\u0651", "ḳhḳh" # خ
+    sub "\u062f\u0651", "dd" # د
+    sub "\u0630\u0651", "zz" # ذ
+    sub "\u0631\u0651", "rr" # ر
+    sub "\u0632\u0651", "zz" # ز
+    sub "\u0633\u0651", "ss" # س
+    sub "\u0634\u0651", "sh" # ش
+    sub "\u0635\u0651", "ss" # ص
+    sub "\u0636\u0651", "ḏḏ" # ض
+    sub "\u0637\u0651", "tt" # ط
+    sub "\u0638\u0651", "zz" # ظ
+    sub "\u063a\u0651", "ghgh" # غ
+    sub "\u0641\u0651", "ff" # ف
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0643\u0651", "kk" # ك
+    sub "\u0644\u0651", "ll" # ل
+    sub "\u0645\u0651", "mm" # م
+    sub "\u0646\u0651", "nn" # ن
+    sub "\u0647\u0651", "hh" # ه
+    sub "\u0648\u0651", "vv" # و
+
+    # NOTE 1
+    sub "\u0650" + boundary, "-e" # ِ kasra
+    sub "\u0674", "-e" # ٴ
+    sub "\u0654", "-e" #  ٔ
+
+    sub "\u0650\u064a\u0651\u064e", "īy" # ـِيَّ
+    sub "\u0650\u064a", "iy", after: any(["\u064e", "u064f"]) # ـِي kasra followed by ي
+    sub "\u064e\u0649", "ay" # ـَى fatha followed by ى which is ا not ي
+    sub "\u064e\u0648\u0652", "aw" # ـَوْ
+    sub "\u064e\u064a\u0652", "ay" # ـَيْ
+    sub "\u0650\u06cc\u0651\u064e", "īy" # ـِيَّ
+    sub "\u064e\u064a", "aī" # ـَي
+    sub "\u064e\u06cc", "aī" # ـَي
+    # - '-ye'
+
+
+    # TODO: compress this
+    # ta' marboota
+    sub "\u0629", "at" # ة in the middle of the sentence
+    sub "\u0629" + line_end, "ah"
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+
+
+
+    sub "\u0621", "-" # ء
+    sub "\u0624", "-" # ؤ
+    sub "\u0626", "-" # ئ
+
+    sub "\u0623", "" # أ
+    sub "\u0625", "" # إ
+    # See note B
+    sub boundary + "\u0627\u0644", "al " # ال
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    sub boundary + "\u0627\u0644\u062a", "at t" # الت
+    sub boundary + "\u0627\u0644\u062b", "as s" # الث
+    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630", "az z" # الذ
+    sub boundary + "\u0627\u0644\u0631", "ar r" # الر
+    sub boundary + "\u0627\u0644\u0632", "az z" # الز
+    sub boundary + "\u0627\u0644\u0633", "as s" # الس
+    sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "as s" # الص
+    sub boundary + "\u0627\u0644\u0636", "az z" # الض
+    sub boundary + "\u0627\u0644\u0637", "at t" # الط
+    sub boundary + "\u0627\u0644\u0638", "az z" # الظ
+    sub boundary + "\u0627\u0644\u0644", "al l" # الل
+    sub boundary + "\u0627\u0644\u0646", "an n" # الن
+
+
+    # consonant characters
+
+    sub "\u0628", "b" # ب
+    sub "\u067E", "p" # پ
+    sub "\u062a", "t" # ت
+    sub "\u0679", "ṭ" # ٹ
+    sub "\u062B", "s" # ث
+    sub "\u062c", "j" # ج
+    sub "\u0686", "ch" # ‫چ‬
+    sub "\u062d", "h" # ح
+    sub "\u062e", "ḳh" # خ
+    sub "\u062f", "d" # د
+    sub "\u0688", "ḍ" # ‫ڈ
+    sub "\u0630", "z" # ذ
+    sub "\u0631", "r" # ر
+    sub "\u0691", "ṙ" # ڑ
+    sub "\u0632", "z" # ز
+    sub "\u0698", "ỵ" # ‫ژ‬
+    sub "\u0633", "s" # س
+    sub "\u0634", "sh" # ش
+    sub "\u0635", "s" # ص
+    sub "\u0636", "z" # ض
+    sub "\u0637", "t" # ط
+    sub "\u0638", "z" # ظ
+    sub "\u0639", "‘" # ع
+    sub "\u064e\u0639", "‘ā" # ع NOTE A
+    sub "\u063a", "gh" # غ
+    sub "\u0641", "f" # ف
+    sub "\u0642", "q" # ق
+    sub "\u0643", "k" # ك
+    sub "\u06A9", "k" # ک
+    sub "\u06AF", "g" # ‫گ‬
+    sub "\u0644", "l" # ل
+    sub "\u0645", "m" # م
+    sub any("\u06BA\u0646"), "n" # ن, ں
+    sub any("\ufba9\u06c1"), "h" # ہ , ﮩ
+    sub any("\ufba9\u06c1") + boundary, "ḥ", before: any("\u064e\u0650\u064f") # ہ , ﮩ NOTE C
+    sub any("\u0647\u06be"), "h" # ه, ھ
+    sub "\u0648", "v" # و
+    sub "\u0648", "ẉ", before: "\u062e" # و NOTE B
+    sub any("\u064a|\u06cc"), "y" # ي
+    # '\u0649' : 'y'  # ي
+    sub "\u06D0", "ē" # ې
+    sub "\u06CD", "êy" # ‫ۍ‬
+  }
+
+  # POSTRULES
+  sub any("\u0061".."\uFFFF"), upcase, before: boundary, not_before: boundary + any("‘’'-")
+  # don't capitalize defined article in the middle of a sentence
+  sub " At T", " at T" # الت
+  sub " As̄ S̄", " as̄ S̄" # الث
+  sub " Ad D", " ad D" # الد
+  sub " Az Z", " az Z" # الذ
+  sub " Ar R", " ar R" # الر
+  sub " Az Z", " az Z" # الز
+  sub " As S", " as S" # الس
+  sub " Ash Sh", " ash Sh" # الش
+  sub " As S", " as S" # الص
+  sub " Az Z", " az Z" # الض
+  sub " At T", " at T" # الط
+  sub " Az Z", " az Z" # الظ
+  sub " Al L", " al L" # الل
+  sub " An N", " an N" # الن
+  sub " Al ", " al " # ال
+}

data/maps/var-amh-Ethi-Latn-eae-2003.imp

@@ -0,0 +1,414 @@
+metadata {
+  authority_id: var
+  id: 2003
+  language: amh
+  source_script: Ethi
+  destination_script: Latn
+  name: Encyclopaedia Aethiopica Amharic transliteration system (2003)
+  url: https://brill.com/view/book/edcoll/9789004419582/front-11.xml?language=en
+  creation_date: 2003
+  description: |
+    The Encyclopaedia Aethiopica (EAe) is a basic encyclopedia for Ethiopian and Eritrean studies. It employs an in-house form of romanization of Geez, Amharic, and other languages, which varies greatly from standard formats, such as BGN/PCGN: the emperor Menelek II's name, for example, is written as "Mənilək II".
+}
+
+tests {
+  test "የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ", "yäzegənätə kəbərə bä ʾitəyoṗəyačənə ṣänəto"
+  test "ታየ ሕዝባዊነት ዳር እስከዳር በርቶ", "tayä ḥəzəbawinätə darə ʾəsəkädarə bärəto"
+  test "ለሰላም ለፍትህ ለሕዝቦች ነጻነት", "läsälamə läfətəhə läḥəzəbočə näṣanätə"
+  test "በእኩልነት በፍቅር ቆመናል ባንድነት", "bäʾəkulənätə bäfəqərə qomänalə banədənätə"
+  test "መሠረተ ፅኑ ሰብዕናን ያልሻርን", "mäśärätä ṣ̓ənu säbəʿənanə yaləšarənə"
+  test "ሕዝቦች ነን ለሥራ በሥራ የኖርን", "ḥəzəbočə nänə läśəra bäśəra yänorənə"
+  test "ድንቅ የባህል መድረክ ያኩሪ ቅርስ ባለቤት", "dənəqə yäbahələ mädəräkə yakuri qərəsə baläbetə"
+  test "የተፈጥሮ ጸጋ የጀግና ሕዝብ እናት", "yätäfäṭəro ṣäga yäǧägəna ḥəzəbə ʾənatə"
+  test "እንጠብቅሻለን አለብን አደራ", "ʾənəṭäbəqəšalänə ʾaläbənə ʾadära"
+  test "ኢትዮጵያችን ኑሪ እኛም ባንቺ እንኩራ", "ʾitəyoṗəyačənə nuri ʾəñamə banəči ʾənəkura"
+  test "ቋንቋ የድምጽ፣ የምልክት ወይም የምስል ቅንብር ሆኖ", "qʷanəqʷa yädəməṣə፣ yämələkətə wäyəmə yäməsələ qənəbərə hono"
+  test "ለማሰብ ወይም የታሰበን ሃሳብ ለሌላ ለማስተላለፍ የሚረዳ መሳሪያ ነው", "lämasäbə wäyəmə yätasäbänə hasabə lälela lämasətälaläfə yämiräda mäsariya näwə"
+  test "በአጭሩ ቋንቋ የምልክቶች ስርዓትና እኒህን ምልክቶች ለማቀናበር", "bäʾač̣əru qʷanəqʷa yämələkətočə sərəʿatəna ʾənihənə mələkətočə lämaqänabärə"
+  test "የሚያስፈልጉ ህጎች ጥንቅር ነው። ቋንቋወችን ለመፈረጅ እንዲሁም", "yämiyasəfäləgu həጎčə ṭənəqərə näwə። qʷanəqʷawäčənə lämäfäräǧə ʾənədihumə"
+  test "ለምክፈል የሚያስችሉ መስፈርቶችን ለማስቀመጥ ባለው ችግር", "läməkəfälə yämiyasəčəlu mäsəfärətočənə lämasəqämäṭə baläwə čəgərə"
+  test "ምክንያት በአሁኑ ሰዓት በርግጠኝነት ስንት ቋንቋ በዓለም ላይ", "məkənəyatə bäʾahunu säʿatə bärəgəṭäñənätə sənətə qʷanəqʷa bäʿalämə layə"
+  test "እንዳለ ማወቅ አስቸጋሪ ነው", "ʾənədalä mawäqə ʾasəčägari näwə"
+  test "አሰላ", "ʾasäla"
+  test "አሶሳ", "ʾasosa"
+  test "አንኮበር", "ʾanəkobärə"
+  test "አክሱም", "ʾakəsumə"
+  test "አዋሳ", "ʾawasa"
+  test "አዲስ ዘመን (ከተማ)", "ʾadisə zämänə (kätäma)"
+  test "አዲግራት", "ʾadigəratə"
+  test "አዳማ", "ʾadama"
+  test "ደምበጫ", "däməbäč̣a"
+  test "ደርባ", "därəba"
+  test "ደብረ ማርቆስ", "däbərä marəqosə"
+  test "ደብረ ብርሃን", "däbərä bərəhanə"
+  test "ደብረ ታቦር (ከተማ)", "däbərä taborə (kätäma)"
+  test "ደብረ ዘይት", "däbərä zäyətə"
+  test "ደገሃቡር", "dägähaburə"
+  test "ወልቂጤ", "wäləqiṭe"
+  test "ወልወል", "wäləwälə"
+  test "ወልደያ", "wälədäya"
+  test "ናይሎ ሳህራን", "nayəlo sahəranə"
+  test "አኙዋክኛ", "ʾañuwakəña"
+  test "ኡዱክኛ", "ʾudukəña"
+  test "ኦፓኛ", "ʾopaña"
+  test "ጉምዝኛ", "guməzəña"
+  test "አፋርኛ", "ʾafarəña"
+  test "አላባኛ", "ʾalabaña"
+  test "አርቦርኛ", "ʾarəborəña"
+  test "ባይሶኛ", "bayəsoña"
+  test "ቡሳኛ", "busaña"
+  test "ሁለተኛ ጥፋት ከገበያ ማንቀላፋት", "hulätäña ṭəfatə kägäbäya manəqälafatə"
+  test "ሁሉም ከልኩ አያልፍም", "hulumə käləku ʾayaləfəmə"
+  test "አልሞት ባይ ተጋዳይ", "ʾaləmotə bayə tägadayə"
+  test "ውርድ ከራሴ", "wərədə kärase"
+  test "ፀጉር መሰንጠቅ", "ṣ̓ägurə mäsänəṭäqə"
+  test "ግንትር ፀሐይ", "gənətərə ṣ̓äḥayə"
+  test "በሬ ወለደ", "bäre wälädä"
+  test "ራስ ሳይጠና ጉተና", "rasə sayəṭäna gutäna"
+  test "ለሆዴ ጠግቤ በልብሴ አንግቤ", "lähode ṭägəbe bäləbəse ʾanəgəbe"
+  test "ለልጅ ከሳቁለት ለውሻ ከሮጡለት", "läləǧə käsaqulätə läwəša käroṭulätə"
+  test "መልካም ባል መጥፎ ሴት ይገራል", "mäləkamə balə mäṭəfo setə yəgäralə"
+  test "ሆድና ግንባር አይሸሸግም", "hodəna gənəbarə ʾayəšäšägəmə"
+  test "ቀሊል አማት ሲሶ በትር አላት", "qälilə ʾamatə siso bätərə ʾalatə"
+  test "ጨው ለራስህ ብለህ ጣፍጥ አለበለዚያ ድንጋይ ነው ብለው ይወረውሩሀል", "č̣äwə lärasəhə bəlähə ṭafəṭə ʾaläbäläziya dənəgayə näwə bəläwə yəwäräwəruhalə"
+  test "ጀምሮ ይጨርሳል አልሞ ይተኩሳል", "ǧäməro yəč̣ärəsalə ʾaləmo yətäkusalə"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u1200", "ha" # ሀ
+    sub "\u1201", "hu" # ሁ
+    sub "\u1202", "hi" # ሂ
+    sub "\u1203", "ha" # ሃ
+    sub "\u1204", "he" # ሄ
+    sub "\u1205", "hə" # ህ
+    sub "\u1206", "ho" # ሆ
+    
+    sub "\u1208", "lä" # ለ
+    sub "\u1209", "lu" # ሉ
+    sub "\u120A", "li" # ሊ
+    sub "\u120B", "la" # ላ
+    sub "\u120C", "le" # ሌ
+    sub "\u120D", "lə" # ል
+    sub "\u120E", "lo" # ሎ
+    
+    sub "\u1210", "ḥa" # ሐ
+    sub "\u1211", "ḥu" # ሑ
+    sub "\u1212", "ḥi" # ሒ
+    sub "\u1213", "ḥa" # ሓ
+    sub "\u1214", "ḥe" # ሔ
+    sub "\u1215", "ḥə" # ሕ
+    sub "\u1216", "ḥo" # ሖ
+    
+    sub "\u1218", "mä" # መ
+    sub "\u1219", "mu" # ሙ
+    sub "\u121A", "mi" # ሚ
+    sub "\u121B", "ma" # ማ
+    sub "\u121C", "me" # ሜ
+    sub "\u121D", "mə" # ም
+    sub "\u121E", "mo" # ሞ
+    
+    sub "\u1220", "śä" # ሠ
+    sub "\u1221", "śu" # ሡ
+    sub "\u1222", "śi" # ሢ
+    sub "\u1223", "śa" # ሣ
+    sub "\u1224", "śe" # ሤ
+    sub "\u1225", "śə" # ሥ
+    sub "\u1226", "śo" # ሦ
+    
+    sub "\u1228", "rä" # ረ
+    sub "\u1229", "ru" # ሩ
+    sub "\u122A", "ri" # ሪ
+    sub "\u122B", "ra" # ራ
+    sub "\u122C", "re" # ሬ
+    sub "\u122D", "rə" # ር
+    sub "\u122E", "ro" # ሮ
+    
+    sub "\u1230", "sä" # ሰ
+    sub "\u1231", "su" # ሱ
+    sub "\u1232", "si" # ሲ
+    sub "\u1233", "sa" # ሳ
+    sub "\u1234", "se" # ሴ
+    sub "\u1235", "sə" # ስ
+    sub "\u1236", "so" # ሶ
+    
+    sub "\u1238", "šä" # ሸ
+    sub "\u1239", "šu" # ሹ
+    sub "\u123A", "ši" # ሺ
+    sub "\u123B", "ša" # ሻ
+    sub "\u123C", "še" # ሼ
+    sub "\u123D", "šə" # ሽ
+    sub "\u123E", "šo" # ሾ
+    
+    sub "\u1240", "qä" # ቀ
+    sub "\u1241", "qu" # ቁ
+    sub "\u1242", "qi" # ቂ
+    sub "\u1243", "qa" # ቃ
+    sub "\u1244", "qe" # ቄ
+    sub "\u1245", "qə" # ቅ
+    sub "\u1246", "qo" # ቆ
+    
+    sub "\u1260", "bä" # በ
+    sub "\u1261", "bu" # ቡ
+    sub "\u1262", "bi" # ቢ
+    sub "\u1263", "ba" # ባ
+    sub "\u1264", "be" # ቤ
+    sub "\u1265", "bə" # ብ
+    sub "\u1266", "bo" # ቦ
+    
+    sub "\u1270", "tä" # ተ
+    sub "\u1271", "tu" # ቱ
+    sub "\u1272", "ti" # ቲ
+    sub "\u1273", "ta" # ታ
+    sub "\u1274", "te" # ቴ
+    sub "\u1275", "tə" # ት
+    sub "\u1276", "to" # ቶ
+    
+    sub "\u1278", "čä" # ቸ
+    sub "\u1279", "ču" # ቹ
+    sub "\u127A", "či" # ቺ
+    sub "\u127B", "ča" # ቻ
+    sub "\u127C", "če" # ቼ
+    sub "\u127D", "čə" # ች
+    sub "\u127E", "čo" # ቾ
+    
+    sub "\u1280", "ḫa" # ኀ
+    sub "\u1281", "ḫu" # ኁ
+    sub "\u1282", "ḫi" # ኂ
+    sub "\u1283", "ḫa" # ኃ
+    sub "\u1284", "ḫe" # ኄ
+    sub "\u1285", "ḫə" # ኅ
+    sub "\u1286", "ḫo" # ኆ
+    
+    sub "\u1290", "nä" # ነ
+    sub "\u1291", "nu" # ኑ
+    sub "\u1292", "ni" # ኒ
+    sub "\u1293", "na" # ና
+    sub "\u1294", "ne" # ኔ
+    sub "\u1295", "nə" # ን
+    sub "\u1296", "no" # ኖ
+    
+    sub "\u1298", "ñä" # ኘ
+    sub "\u1299", "ñu" # ኙ
+    sub "\u129A", "ñi" # ኚ
+    sub "\u129B", "ña" # ኛ
+    sub "\u129C", "ñe" # ኜ
+    sub "\u129D", "ñə" # ኝ
+    sub "\u129E", "ño" # ኞ
+    
+    sub "\u12A0", "ʾa" # አ
+    sub "\u12A1", "ʾu" # ኡ
+    sub "\u12A2", "ʾi" # ኢ
+    sub "\u12A3", "ʾa" # ኣ
+    sub "\u12A4", "ʾe" # ኤ
+    sub "\u12A5", "ʾə" # እ
+    sub "\u12A6", "ʾo" # ኦ
+    
+    sub "\u12A8", "kä" # ከ
+    sub "\u12A9", "ku" # ኩ
+    sub "\u12AA", "ki" # ኪ
+    sub "\u12AB", "ka" # ካ
+    sub "\u12AC", "ke" # ኬ
+    sub "\u12AD", "kə" # ክ
+    sub "\u12AE", "ko" # ኮ
+    
+    sub "\u12B8", "ḵä" # ኸ
+    sub "\u12B9", "ḵu" # ኹ
+    sub "\u12BA", "ḵi" # ኺ
+    sub "\u12BB", "ḵa" # ኻ
+    sub "\u12BC", "ḵe" # ኼ
+    sub "\u12BD", "ḵə" # ኽ
+    sub "\u12BE", "ḵo" # ኾ
+    
+    sub "\u12C8", "wä" # ወ
+    sub "\u12C9", "wu" # ዉ
+    sub "\u12CA", "wi" # ዊ
+    sub "\u12CB", "wa" # ዋ
+    sub "\u12CC", "we" # ዌ
+    sub "\u12CD", "wə" # ው
+    sub "\u12CE", "wo" # ዎ
+    
+    sub "\u12D0", "ʿa" # ዐ
+    sub "\u12D1", "ʿu" # ዑ
+    sub "\u12D2", "ʿi" # ዒ
+    sub "\u12D3", "ʿa" # ዓ
+    sub "\u12D4", "ʿe" # ዔ
+    sub "\u12D5", "ʿə" # ዕ
+    sub "\u12D6", "ʿo" # ዖ
+    
+    sub "\u12D8", "zä" # ዘ
+    sub "\u12D9", "zu" # ዙ
+    sub "\u12DA", "zi" # ዚ
+    sub "\u12DB", "za" # ዛ
+    sub "\u12DC", "ze" # ዜ
+    sub "\u12DD", "zə" # ዝ
+    sub "\u12DE", "zo" # ዞ
+    
+    sub "\u12E0", "žä" # ዠ
+    sub "\u12E1", "žu" # ዡ
+    sub "\u12E2", "ži" # ዢ
+    sub "\u12E3", "ža" # ዣ
+    sub "\u12E4", "že" # ዤ
+    sub "\u12E5", "žə" # ዥ
+    sub "\u12E6", "žo" # ዦ
+    
+    sub "\u12E8", "yä" # የ
+    sub "\u12E9", "yu" # ዩ
+    sub "\u12EA", "yi" # ዪ
+    sub "\u12EB", "ya" # ያ
+    sub "\u12EC", "ye" # ዬ
+    sub "\u12ED", "yə" # ይ
+    sub "\u12EE", "yo" # ዮ
+    
+    sub "\u12F0", "dä" # ደ
+    sub "\u12F1", "du" # ዱ
+    sub "\u12F2", "di" # ዲ
+    sub "\u12F3", "da" # ዳ
+    sub "\u12F4", "de" # ዴ
+    sub "\u12F5", "də" # ድ
+    sub "\u12F6", "do" # ዶ
+    
+    sub "\u1300", "ǧä" # ጀ
+    sub "\u1301", "ǧu" # ጁ
+    sub "\u1302", "ǧi" # ጂ
+    sub "\u1303", "ǧa" # ጃ
+    sub "\u1304", "ǧe" # ጄ
+    sub "\u1305", "ǧə" # ጅ
+    sub "\u1306", "ǧo" # ጆ
+    
+    sub "\u1308", "gä" # ገ
+    sub "\u1309", "gu" # ጉ
+    sub "\u130A", "gi" # ጊ
+    sub "\u130B", "ga" # ጋ
+    sub "\u130C", "ge" # ጌ
+    sub "\u130D", "gə" # ግ
+    
+    sub "\u1320", "ṭä" # ጠ
+    sub "\u1321", "ṭu" # ጡ
+    sub "\u1322", "ṭi" # ጢ
+    sub "\u1323", "ṭa" # ጣ
+    sub "\u1324", "ṭe" # ጤ
+    sub "\u1325", "ṭə" # ጥ
+    sub "\u1326", "ṭo" # ጦ
+    
+    sub "\u1328", "č̣ä" # ጨ
+    sub "\u1329", "č̣u" # ጩ
+    sub "\u132A", "č̣i" # ጪ
+    sub "\u132B", "č̣a" # ጫ
+    sub "\u132C", "č̣e" # ጬ
+    sub "\u132D", "č̣ə" # ጭ
+    sub "\u132E", "č̣o" # ጮ
+    
+    sub "\u1330", "ṗä" # ጰ
+    sub "\u1331", "ṗu" # ጱ
+    sub "\u1332", "ṗi" # ጲ
+    sub "\u1333", "ṗa" # ጳ
+    sub "\u1334", "ṗe" # ጴ
+    sub "\u1335", "ṗə" # ጵ
+    sub "\u1336", "ṗo" # ጶ
+    
+    sub "\u1338", "ṣä" # ጸ
+    sub "\u1339", "ṣu" # ጹ
+    sub "\u133A", "ṣi" # ጺ
+    sub "\u133B", "ṣa" # ጻ
+    sub "\u133C", "ṣe" # ጼ
+    sub "\u133D", "ṣə" # ጽ
+    sub "\u133E", "ṣo" # ጾ
+    
+    sub "\u1340", "ṣ̓ä" # ፀ
+    sub "\u1341", "ṣ̓u" # ፁ
+    sub "\u1342", "ṣ̓i" # ፂ
+    sub "\u1343", "ṣ̓a" # ፃ
+    sub "\u1344", "ṣ̓e" # ፄ
+    sub "\u1345", "ṣ̓ə" # ፅ
+    sub "\u1346", "ṣ̓o" # ፆ
+    
+    sub "\u1348", "fä" # ፈ
+    sub "\u1349", "fu" # ፉ
+    sub "\u134A", "fi" # ፊ
+    sub "\u134B", "fa" # ፋ
+    sub "\u134C", "fe" # ፌ
+    sub "\u134D", "fə" # ፍ
+    sub "\u134E", "fo" # ፎ
+    
+    sub "\u1350", "pä" # ፐ
+    sub "\u1351", "pu" # ፑ
+    sub "\u1352", "pi" # ፒ
+    sub "\u1353", "pa" # ፓ
+    sub "\u1354", "pe" # ፔ
+    sub "\u1355", "pə" # ፕ
+    sub "\u1356", "po" # ፖ
+    
+    sub "\u1268", "vä" # ቨ
+    sub "\u1269", "vu" # ቩ
+    sub "\u126A", "vi" # ቪ
+    sub "\u126B", "va" # ቫ
+    sub "\u126C", "ve" # ቬ
+    sub "\u126D", "və" # ቭ
+    sub "\u126E", "vo" # ቮ
+    
+    # Labiovelars
+    sub "\u1248", "qʷä" # ቈ
+    sub "\u124a", "qʷi" # ቊ
+    sub "\u124b", "qʷa" # ቋ
+    sub "\u124c", "qʷe" # ቌ
+    sub "\u124d", "qʷə" # ቍ
+    
+    sub "\u1288", "ḫʷä" # ኈ
+    sub "\u128a", "ḫʷi" # ኊ
+    sub "\u128b", "ḫʷa" # ኋ
+    sub "\u128c", "ḫʷe" # ኌ
+    sub "\u128d", "ḫʷə" # ኍ
+    
+    sub "\u12b0", "kʷä" # ኰ
+    sub "\u12b2", "kʷi" # ኲ
+    sub "\u12b3", "kʷa" # ኳ
+    sub "\u12b4", "kʷe" # ኴ
+    sub "\u12b5", "kʷə" # ኵ
+    
+    sub "\u1310", "gʷä" # ጐ
+    sub "\u1312", "gʷi" # ጒ
+    sub "\u1313", "gʷa" # ጓ
+    sub "\u1314", "gʷe" # ጔ
+    sub "\u1315", "gʷə" # ጕ
+    
+    sub "\u12c0", "ḵʷä" # ዀ
+    sub "\u12c2", "ḵʷi" # ዂ
+    sub "\u12c3", "ḵʷa" # ዃ
+    sub "\u12c4", "ḵʷe" # ዄ
+    sub "\u12c5", "ḵʷə" # ዅ
+    
+    sub "\u1258", "q̱ʷä" # ቘ
+    sub "\u125a", "q̱ʷi" # ቚ
+    sub "\u125b", "q̱ʷa" # ቛ
+    sub "\u125c", "q̱ʷe" # ቜ
+    sub "\u125d", "q̱ʷə" # ቝ
+    
+    # Numbers
+    
+    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 "\u1373", "20" # ፳
+    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
+    sub "\u1372\u137B", "1000" # ፲፻
+    sub "\u137B\u137B", "10000" # ፻፻
+  }
+
+}
+