interscript-maps 2.4.3 → 2.5.0

data/maps/alalc-aze-Arab-Latn-1997.isc

@@ -0,0 +1,341 @@
+system "ALA-LC:aze-Arab:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:aze
+  source_script Arab
+  destination_script Latn
+  name Romanization Table -- azerbaij (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/azerbaij.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization table for Arabic
+  }
+
+  notes {
+    note "1. As seen in the examples above, vowel harmony, which is\n found in Modern Turkish, applies to Azerbaijani as well."
+
+    note "2. The letter ى in final position may represent the long\n vowel romanized á, in addition to the\n vowels romanized i and 1. This occurs in Arabic names, such\n as Mustafá\n al-Musanná"
+
+    note "3. Vowel points are used sparingly in Azerbaijani\n publications. For romanization, they must be\n supplied from a dictionary."
+
+    note "Rule 1 ء hamza\n (a) When initial, ء is not represented in romanization\n üzdah  أوزدة\n (b) When medial or final in words of Perso-Arabic origin, 9 is\n romanized as ’ (alit), except when it accompanies the\n phonetic sound e (as in men), in which case it is romanized\n by e.\n mas’alah مَسئَلة\n gecah كئجة\n necah نئجة"
+
+    note "Rule 2 ˜ (maddah)\n (a) Initial آ is romanized ā.\n ādām				        آدام\n (b) Medial آ, when it represents the phonetic combination ’ā, is so romanized.\n Heydar'ãbãd     حيدَرآبَاد"
+
+    note "Rule 3  ّ\n (shaddah or tashdid) is represented by doubling the letter or digraph concerned.\n sãqqãl   سَاقَّال\n Note the exceptional case where  ّ is written over و and ي to represent\n the combination of long vowel plus consonants.\n madaníyat  مَدَنِيَّت"
+
+    note "      Rule 4 Tanvīn (written form ٌ, ً (ًا), or ٍ ) which occurs chiefly in Arabic words,\n      is romanized un, in, an, and an, respectively.\n\n      (a)	When it occurs in indefinite nouns derived from defective roots.\n\n        qāḍin				قاضٍ\n        ma‘nan				معنىً\n\n      (b)	When it indicates the adverbial use of a noun or adjective.\n\n        ṭab‘an				  طبعًا\n        faj’atan				فجأةً\n        al-Mushtarik waḍ‘an		المشترك وضعاً\n              wa-al-muftariq ṣuq‘an	والمفترق صقعاً"
+
+    note "ة in a word in the construct state is romanized t.  See rule 7(b)."
+
+    note "The consonant letter ö at the end of Arabic words in the\n genetive construction (izãfah) is romanized by t.\n takmilat al-axbãr    تَكمِلَة الأخبَار"
+    # Grammatical Structure as It Affects Romanization
+    note "Rule 6 izãfah. When two Persian words are used in an Azerbaijani\n context in a relationship known as izãfah, the first word (\n the muzãf) is followed by an additional letter or syllable\n in romanization. This is added according to the following\n rules\n (a) When the muzaf bears no special mark of izãfah, it is\n followed by -i.\n Sazman-i tabligãti-Islãm   سازمان تبليغات اسلامي\n (b) When the muzãf is marked by the addition of 9, it is followed by -'i.\n Nãbigah-'i dahr   نابغة دَهر\n (c) When the muzãf is marked by the addition of û, it is followed by -yi.\n darya-yi nur    دَريَاي نُور\n (d) izãfah is represented in romanization of personal names only when\n implied in the Persian script.\n Mucír-i BeylaqãnT   مَجير بيلقاني\n Maktabí-i Sírãzí    مكتبي شيرازي"
+    # Affixes and Compounds
+    note "Rule 7 Affixes.\n (a) When the affix and the word with it is connected grammatically are\n written separately in Azerbaijani, the two are separated in romanization\n by a single prime(').\n (b) The Arabic article al is separated by a hyphen, in romanization,\n from the word to which it is prefixed."
+
+    note "Rule 8 Compounds.\n When the elements of a compound (except a compound personal name)\n are written separately in Azerbaijani, they are separated in\n romanization by a single prime(')."
+    # Orthography of Azerbaijani in Romanization
+
+    note "Rule 9 Capitalization\n (a) Rules for the capitalization of English are followed, except that\n the Arabic article al, is lower cased in all positions.\n (b)	Diacritics are used with both upper and lower case letters in romanization."
+
+    note "Rule 10 Foreign words.\n Foreign words in an Azerbaijani context, including Persian and Arabic words,\n are romanized according to the rules for Azerbaijani. For short vowels not\n indicated in the script, the Azerbaijani vowels nearest the original\n pronunciation of the word are supplied in romanization."
+  }
+}
+
+tests {
+   "بَرَكَت" ->  "Barakat"
+   "سَاحِل" ->  "Sāḥil"
+   "بَادِمجَان" ->  "Bādimcān"
+   "قُدرَت" ->  "Qudrat"
+   "بُوغَا" ->  "Būğā"
+   "آرَام" ->  "Ārām"
+   "اِئنلِي" ->  "Enlī"
+   "دَلِيل" ->  "Dalīl"
+   "قَارَانلِيق" ->  "Qārānlīq"
+   "اِيش" ->  "Īş"
+   "اِيشِيق" ->  "Īşīq"
+   "اُون" ->  "On"
+   "ُاون" ->  "Ūn"
+   "ُاؤن" ->  "Ön"
+  # - source: ُأوزُوم
+  #   expected: üzūm
+   "اَيْوَان" ->  "Eyvān"
+   "اَوحَدِي" ->  "Awḥadī"
+   "َاوَّل" ->  "Avval"
+   "طَهي" ->  "Ṭahy"
+  # From Rule 1 - part a
+   "ُأوزدَة" ->  "Üzdah"
+  # From Rule 1 - part b
+   "مَسئَلَة" ->  "Mas’alah"
+   "گِئجَة" ->  "Gecah"
+   "نِئچَة" ->  "Neçah"
+  # From Rule 2 - part a
+   "آدَام" ->  "Ādām"
+  # From Rule 2 - part b
+   "حَيْدَرآبَاد" ->  "Ḥeydar’ābād"
+  # From Rule 3
+   "سَاقَّال" ->  "Sāqqāl"
+   "مَدَنِيَّت" ->  "Madanīyat"
+  # From Rule 5
+   "تَكمِلَة الأَخبَار" ->  "Takmilat al-Axbār"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+
+    sub "\u0628\u0651" "bb"
+    sub "\u067E\u0651" "pp"
+    sub "\u062A\u0651" "tt"
+    sub "\u062b\u0651" "s̱s̱"
+    sub "\u062C\u0651" "cc"
+    sub "\u0686\u0651" "çç"
+    sub "\u062d\u0651" "ḥḥ"
+    sub "\u062E\u0651" "xx"
+    sub "\u062F\u0651" "dd"
+    sub "\u0630\u0651" "ẕẕ"
+    sub "\u0631\u0651" "rr"
+    sub "\u0632\u0651" "zz"
+    sub "\u0698\u0651" "jj"
+    sub "\u0633\u0651" "ss"
+    sub "\u0634\u0651" "şş"
+    sub "\u0635\u0651" "ṣṣ"
+    sub "\u0636\u0651" "z̤z̤"
+    sub "\u0637\u0651" "ṭṭ"
+    sub "\u0638\u0651" "ẓẓ"
+    sub "\u0639\u0651" "‘‘"
+    sub "\u063A\u0651" "ğğ"
+    sub "\u0341\u0651" "ff"
+    sub "\u0642\u0651" "qq"
+    sub "\u06A9\u0651" "kk"
+    sub "\u0643\u0651" "kk"
+    sub "\u06AF\u0651" "gg"
+    sub "\u0644\u0651" "ll"
+    sub "\u0645\u0651" "mm"
+    sub "\u0646\u0651" "nn"
+    sub "\u0648\u0651" "vv"
+    sub "\u0647\u0651" "hh"
+    sub "\u064A\u0651" "yy"
+
+    sub "\u060c" ","
+
+    sub "\u0627\u0644\u0644\u0651\u064e\u0647" "Allāh"
+
+    sub {
+    from boundary + "\u0627\u0644"
+    to "al-"
+  }
+
+    sub "\u0628" "b"
+    sub "\u067E" "p"
+    sub "\u062A" "t"
+    sub "\u062b" "s̱"
+    sub "\u062C" "c"
+    sub "\u0686" "ç"
+    sub "\u062d" "ḥ"
+    sub "\u062E" "x"
+    sub "\u062F" "d"
+    sub "\u0630" "ẕ"
+    sub "\u0631" "r"
+    sub "\u0632" "z"
+    sub "\u0698" "j"
+    sub "\u0633" "s"
+    sub "\u0634" "ş"
+    sub "\u0635" "ṣ"
+    sub "\u0636" "z̤"
+    sub "\u0637" "ṭ"
+    sub "\u0638" "ẓ"
+    sub "\u0639" "‘"
+    sub "\u063A" "ğ"
+    sub "\u0341" "f"
+    sub "\u0642" "q"
+    sub "\u06A9" "k"
+    sub "\u0643" "k"
+    sub "\u06AF" "g"
+    sub "\u0644" "l"
+    sub "\u0645" "m"
+    sub "\u0646" "n"
+    sub "\u0648" "v"
+    sub "\u0647" "h"
+    sub "\u064A" "y"
+
+    # Vowels and Diphthongs
+    sub "\u064e" "a"
+    sub "\u0650" "i"
+    sub "\u064f" "u"
+    sub "\u064f\u0648" "ū"
+    sub "\u064e\u0627" "ā"
+    sub "\u0622" "ā"
+    sub {
+    from "\u0650" + any("\u0621\u0623\u0624\u0626")
+    to "e"
+  }
+    sub "\u0650\u064a" "ī"
+    sub "\u0650\u0627\u064a" "ī"
+    sub {
+    from maybe(any("\u064f")) + "\u0627\u064f\u0648"
+    to "o"
+  }
+    sub "\u064f\u0627\u0648" "ū"
+    sub "\u064f\u0627\u0624" "ö"
+    sub "\u064f\u0623\u0648" "ü"
+    sub "\u064e\u064a\u0652" "ey"
+    sub {
+    from "\u064e\u0648" + maybe("\u0652")
+    to "aw"
+  }
+    sub {
+    from boundary + "\u0627"
+    to ""
+  }
+    sub {
+    from boundary + "\u064e\u0627"
+    to "a"
+  }
+    sub {
+    from boundary + "\u0650\u0627"
+    to "i"
+  }
+
+    # hamzah
+    sub {
+    from boundary + "\u0623"
+    to ""
+  }
+    sub {
+    from "\u0623"
+    to "’"
+    not_before "\u0644"
+  }
+    sub "\u0623" ""
+    sub "\u0624" "’"
+    sub "\u0626" "’"
+    sub {
+    from boundary + "\u0622"
+    to "ā"
+  }
+    sub {
+    from "\u0622"
+    to "’ā"
+    not_before any([boundary + "\u0627\u0644", boundary])
+    not_after any([boundary, "\u0621"])
+  }
+    sub "\u064e\u0622" "ā"
+    sub "\u0622" ""
+
+    # Rule 3 - shadda
+    sub "\u0650\u064a\u0651" "īy"
+    sub "\u064f\u0648\u0651" "ūw"
+    sub {
+    from "\u0650\u064a\u0651" + boundary
+    to "ī"
+  }
+    sub "\u064e\u0648\u0651" "aww"
+    sub "\u064e\u064a\u0651" "ayy"
+
+    # Rule 4 - tanvin
+    sub "\u064c" "un"
+    sub "\u064b" "an"
+    sub "\u064d" "in"
+    # tanween should be onb the letter preceeding the end in case of ا, ى
+    # however, it's common that people mistake that, so we're handling both orders
+    sub "\u064b\u0649" "an"
+    sub "\u064b\u0627" "an"
+    sub "\u0649\u064b" "an"
+    sub "\u0627\u064b" "an"
+
+    # Rule 5 ta' marboota
+    sub "\u0629" "t"
+    sub {
+    from "\u0629" + line_end
+    to "h"
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0629"
+    to "h"
+    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 {
+    from "\u0650\u064a"
+    to "iy"
+    after any("\u064e\u064f")
+  }
+    sub "\u064e\u0649" "á"
+  }
+
+  # POSTRULES
+  sub {
+    from any("\u0061".."\uFFFF")
+    to upcase
+    before boundary
+    not_before boundary + any("‘’'")
+  }
+
+  sub {
+    from boundary + "Al"
+    to "al"
+  }
+
+  compose
+}
+}

data/maps/alalc-aze-Cyrl-Latn-1997.isc

@@ -0,0 +1,105 @@
+system "ALA-LC:aze-Cyrl:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:aze
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Azerbaijani (1997)
+  url https://transliteration.eki.ee/pdf/Azerbaijani.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization Tables: Transliteration Schemes for Non-Roman Scripts. Randal K. Berry (ed.). Library of Congress, 1997.
+  }
+
+  notes {
+    note "Ј ј replaced Й й in 1959 (Roman: y; ISO 9: j; ALA-LC: ĭ)."
+  }
+}
+
+tests {
+  # from internet
+   "Азәрбајҹан дили" ->  "Azărbaı̐jan dili"
+   "Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад вә бәрабәр доғулурлар.\nОнларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар." ->  "Bu̇tu̇n insanlar lăı̐agăt vă ḣu̇guglaryna ġȯră azad vă bărabăr doghulurlar.\nOnlaryn shu̇urlary vă vijdanlary var vă bir-birlărină mu̇nasibătdă gardashlyg ruḣunda davranmalydyrlar."
+   "Азәрбајҹан! Азәрбајҹан!\nЕј гәһрәман өвладын шанлы Вәтәни!\nСәндән өтрү ҹан вермәјә ҹүмлә һазырыз!\nСәндән өтрү ган төкмәјә ҹүмлә гадириз!\nҮчрәнҝли бајрағынла мәсуд јаша!\nҮчрәнҝли бајрағынла мәсуд јаша!\nМинләрлә ҹан гурбан олду,\nСинән һәрбә мејдан олду!\nҺүгугундан кечән әсҝәр,\nҺәрә бир гәһрәман олду!\nСән оласан ҝүлүстан,\nСәнә һәр ан ҹан гурбан!\nСәнә мин бир мәһәббәт\nСинәмдә тутмуш мәкан!\nНамусуну һифз етмәјә,\nБајрағыны јүксәлтмәјә\nНамусуну һифз етмәјә,\nҸүмлә ҝәнҹләр мүштагдыр!\nШанлы Вәтән! Шанлы Вәтән!\nАзәрбајҹан! Азәрбајҹан!\nАзәрбајҹан! Азәрбајҹан!" ->  "Azărbaı̐jan! Azărbaı̐jan!\nEı̐ găḣrăman ȯvladyn shanly Vătăni!\nSăndăn ȯtru̇ jan vermăı̐ă ju̇mlă ḣazyryz!\nSăndăn ȯtru̇ gan tȯkmăı̐ă ju̇mlă gadiriz!\nU̇chrănġli baı̐raghynla măsud ı̐asha!\nU̇chrănġli baı̐raghynla măsud ı̐asha!\nMinlărlă jan gurban oldu,\nSinăn ḣărbă meı̐dan oldu!\nḢu̇gugundan kechăn ăsġăr,\nḢără bir găḣrăman oldu!\nSăn olasan ġu̇lu̇stan,\nSănă ḣăr an jan gurban!\nSănă min bir măḣăbbăt\nSinămdă tutmush măkan!\nNamusunu ḣifz etmăı̐ă,\nBaı̐raghyny ı̐u̇ksăltmăı̐ă\nNamusunu ḣifz etmăı̐ă,\nJu̇mlă ġănjlăr mu̇shtagdyr!\nShanly Vătăn! Shanly Vătăn!\nAzărbaı̐jan! Azărbaı̐jan!\nAzărbaı̐jan! Azărbaı̐jan!"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0492" "Gh"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u04D8" "Ă"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u042B" "Y"
+    sub "\u0408" "I̐"
+    sub "\u0419" "Y"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u049C" "Ġ"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u041E" "O"
+    sub "\u04E8" "Ȯ"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04AE" "U̇"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u04BA" "Ḣ"
+    sub "\u0427" "Ch"
+    sub "\u04B8" "J"
+    sub "\u0428" "Sh"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0493" "gh"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u04D9" "ă"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u044B" "y"
+    sub "\u0458" "ı̐"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u049D" "ġ"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u043E" "o"
+    sub "\u04E9" "ȯ"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04AF" "u̇"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u04BB" "ḣ"
+    sub "\u0447" "ch"
+    sub "\u04B9" "j"
+    sub "\u0448" "sh"
+
+    sub "\u2019" "\u2019"
+  }
+
+  compose
+}
+}

data/maps/alalc-bel-Cyrl-Latn-1997.isc

@@ -0,0 +1,122 @@
+system "ALA-LC:bel-Cyrl:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:bel
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Byelorussian (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/beloruss.pdf
+  creation_date 1997
+
+  notes {
+    note "Ґ letter found in Old Belarusian and in modern publications in Tarashkevitsa orthography."
+    note "Do not confuse with the digraph кг (also romanized as “kh”). Manual review may be needed when transcribing data in vernacular characters in order to distinguish х from кг."
+    note "The apostrophe (´) is not transliterated."
+    note "Soft sign (prime) is USMARC hexadecimal code A7 ~ U+02B9 Unicode character"
+  }
+}
+
+tests {
+  # https://en.wikipedia.org/wiki/Romanization_of_Belarusian#Examples
+  # https://img.tyt.by/n/02/d/belorusskiy_translit.jpg - with issues
+   "Беларусь" ->  "Belarusʹ"
+   "Магілёў" ->  "Mahili͡oŭ"
+   "Лукашэнка" ->  "Lukashėnka"
+   "сям´я" ->  "si͡ami͡a"
+   "Уручча" ->  "Uruchcha"
+   "Барысаўскі тракт" ->  "Barysaŭski trakt"
+   "Усход" ->  "Uskhod"
+   "Маскоўская" ->  "Maskoŭskai͡a"
+   "Парк Чалюскінцаў" ->  "Park Chali͡uskintsaŭ"
+   "Акадэмія навук" ->  "Akadėmii͡a navuk"
+   "Плошча Якуба Коласа" ->  "Ploshcha I͡Akuba Kolasa"
+   "Плошча Перамогі" ->  "Ploshcha Peramohi"
+   "Кастрычніцкая" ->  "Kastrychnitskai͡a"
+   "Плошча Леніна" ->  "Ploshcha Lenina"
+   "Інстытут Культуры" ->  "Instytut Kulʹtury"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    # Apostrophes
+    sub "\u00B4" ""
+    sub "\u02BC" ""
+    sub "\u0027" ""
+
+    # Characters
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "H"
+    sub "\u0490" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "I͡O"
+    sub "\u0416" "Z͡H"
+    sub "\u0417" "Z"
+    sub "\u0406" "I"
+    sub "\u0419" "Ĭ"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u041E" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\\U040E" "Ŭ"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u042B" "Y"
+    sub "\u042C" "ʹ"
+    sub "\u042D" "Ė"
+    sub "\u042E" "I͡U"
+    sub "\u042F" "I͡A"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "h"
+    sub "\u0491" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "i͡o"
+    sub "\u0436" "z͡h"
+    sub "\u0437" "z"
+    sub "\u0456" "i"
+    sub "\u0439" "ĭ"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u043E" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u045E" "ŭ"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u044B" "y"
+    sub "\u044C" "ʹ"
+    sub "\u044D" "ė"
+    sub "\u044E" "i͡u"
+    sub "\u044F" "i͡a"
+  }
+
+}
+
+}