interscript-maps 2.0.5

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

@@ -0,0 +1,48 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1984
+  language: iso-639-2:sme
+  source_script: Latn
+  destination_script: Latn
+  name: BGN/PCGN Northern Sami (North Lappish) 1984 Roman-Script Spelling Convention Agreement
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
+  creation_date: 1984
+
+  notes:
+    - |
+      The special letter Ŋ ŋ, known as eng, [Unicode: 014A, 014B] should be reproduced in that form whenever
+      encountered. In those instances when it cannot be reproduced, however, the letter Ń ń [Unicode: 0143, 0144]
+      may be substituted for it.
+    - |
+      In a further note additional to the 1984 agreement, other special letters should be retained as found:
+        Á á [Unicode: 00C1, 00E1],
+        Č č [Unicode: 010C, 010D],
+        Đ đ [Unicode: 0110, 0111],
+        Š š [Unicode: 0160, 0161],
+        Ŧ ŧ [Unicode: 0166, 0167],
+        Ž ž [Unicode: 017D, 017E].
+}
+
+tests {
+  # https://web.archive.org/web/20120918094122/http://www.uta.fi/~km56049/same/svocab.html
+  test "adjágas", "adjágas"
+  test "agálaš", "agálaš"
+  test "ÁEL", "ÁEL"
+  test "hčagastinárpu", "hčagastinárpu"
+  test "algŋa", "algńa"
+  test "Šveica", "Šveica"
+  test "MAŊŊIL", "MAŃŃIL"
+  test "giđa", "giđa"
+  test "ruoŧŧelaš", "ruoŧŧelaš"
+  test "skálžu", "skálžu"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "Ŋ", "Ń" # Ŋ => Ń
+    sub "ŋ", "ń" # ŋ => ń
+  }
+
+}

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

@@ -0,0 +1,55 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1962
+  language: iso-639-2:srp
+  source_script: Cyrl
+  destination_script: Latn
+  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.
+
+  notes:
+    - The digraph dj(Dj) will occasionally be found as the Croatian equivalent of ђ(Ђ),
+      but the use of dj should be limited to those instances where it is found in roman sources.
+}
+
+tests {
+  test "Шупља Стена", "Šuplja Stena"
+  test "Чукарица", "Čukarica"
+  test "Црна Трава", "Crna Trava"
+  test "Херцег Нови", "Herceg Novi"
+  test "Улцињ", "Ulcinj"
+  test "Ужице", "Užice"
+  test "Тресаначка Река", "Tresanačka Reka"
+  test "Сјеница", "Sjenica"
+  test "Рожаје", "Rožaje"
+  test "Пљевља", "Pljevlja"
+  test "Оџаци", "Odžaci"
+  test "Никшић", "Nikšić"
+  test "Медвеђа", "Medveđa"
+  test "Лозница", "Loznica"
+  test "Књажевац", "Knjaževac"
+  test "Зрењанин", "Zrenjanin"
+  test "Житорађа", "Žitorađa"
+  test "Ервеник", "Ervenik"
+  test "Доње Љупче", "Donje Ljupče"
+  test "Гусиње", "Gusinje"
+  test "ГУСИЊЕ", "GUSINJE"
+  test "Врњачка Бања", "Vrnjačka Banja"
+  test "Бијело Поље", "Bijelo Polje"
+  test "Алибунар", "Alibunar"
+}
+
+dependency "bgnpcgn-srp-Cyrl-Latn-2005", as: cyrllatn
+
+stage {
+
+  run map.cyrllatn.stage.main
+
+}

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

@@ -0,0 +1,146 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2005
+  language: iso-639-2:srp
+  source_script: Cyrl
+  destination_script: Latn
+  name: ROMANIZATION OF SERBIAN, BGN/PCGN 2005 System
+  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
+  description: |
+    The tabulation below reflects the Serbian Cyrillic alphabet and the standard Roman script equivalents
+    used in both Serbia and Montenegro.
+
+  notes:
+    - The Serbian Cyrillic lowercase italic Д may sometimes be seen as g.
+      There is no specific Unicode encoding for this variant form so a comparable character
+      has been used here for illustrative purposes.
+
+    - The digraph dj(Dj) will occasionally be found as an alternative form of đ(Đ).
+
+    - The Serbian Cyrillic lowercase italic П may sometimes be seen as ӣ.
+      There is no specific Unicode encoding for this variant form so a comparable character
+      has been used here for illustrative purposes.
+
+    - The Serbian Cyrillic lowercase italic Т may sometimes be seen as w.
+      There is no specific Unicode encoding for this variant form so a comparable character
+      has been used here for illustrative purposes.
+
+    - |
+      An inventory of letter-diacritic combinations, with their Unicode encoding,
+      in addition to the unmodified letters of the basic Roman script is:
+      | Đ (U+0110)   | đ (U+0111)   |
+      | Ž (U+017D)   | ž (U+017E)   |
+      | Lj (U+01C8)* | lj (U+01C9)* |
+      | Ć (U+0106)   | ć (U+0107)   |
+      | Dž (U+01C5)* | dž (U+01C6)* |
+      | Š (U+0160)   | š (U+0161)   |
+      * Note that these characters can also be reproduced with individual letters (e.g. l+j).
+
+    - The Roman-script columns show only lowercase forms but, when applying the table,
+      uppercase and lowercase Roman letters as appropriate should be used.
+}
+
+tests {
+  test "Шупља Стена", "Šuplja Stena"
+  test "Чукарица", "Čukarica"
+  test "Црна Трава", "Crna Trava"
+  test "Херцег Нови", "Herceg Novi"
+  test "Улцињ", "Ulcinj"
+  test "Ужице", "Užice"
+  test "Тресаначка Река", "Tresanačka Reka"
+  test "Сјеница", "Sjenica"
+  test "Рожаје", "Rožaje"
+  test "Пљевља", "Pljevlja"
+  test "Оџаци", "Odžaci"
+  test "Никшић", "Nikšić"
+  test "Медвеђа", "Medveđa"
+  test "Лозница", "Loznica"
+  test "Књажевац", "Knjaževac"
+  test "Зрењанин", "Zrenjanin"
+  test "Житорађа", "Žitorađa"
+  test "Ервеник", "Ervenik"
+  test "Доње Љупче", "Donje Ljupče"
+  test "Гусиње", "Gusinje"
+  test "ГУСИЊЕ", "GUSINJE"
+  test "Врњачка Бања", "Vrnjačka Banja"
+  test "Бијело Поље", "Bijelo Polje"
+  test "Алибунар", "Alibunar"
+}
+
+aliases {
+  def_alias srp_multichar, any(["Lj", "Nj", "Dž"])
+  def_alias srp_latupper, any("A".."Z")
+}
+
+stage {
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Д", "D"
+    sub "Ђ", "Đ" # Đ
+    sub "Е", "E"
+    sub "Ж", "Ž" # Ž
+    sub "З", "Z"
+    sub "И", "I"
+    sub "Ј", "J"
+    sub "К", "K"
+    sub "Л", "L"
+    sub "Љ", "Lj"
+    sub "М", "M"
+    sub "Н", "N"
+    sub "Њ", "Nj"
+    sub "О", "O"
+    sub "П", "P"
+    sub "Р", "R"
+    sub "С", "S"
+    sub "Т", "T"
+    sub "Ћ", "Ć" # Ć
+    sub "У", "U"
+    sub "Ф", "F"
+    sub "Х", "H"
+    sub "Ц", "C"
+    sub "Ч", "Č" # Č
+    sub "Џ", "Dž" # Dž
+    sub "Ш", "Š" # Š
+    sub "а", "a"
+    sub "б", "b"
+    sub "в", "v"
+    sub "г", "g"
+    sub "д", "d"
+    sub "ђ", "đ" # đ
+    sub "е", "e"
+    sub "ж", "ž" # ž
+    sub "з", "z"
+    sub "и", "i"
+    sub "ј", "j"
+    sub "к", "k"
+    sub "л", "l"
+    sub "љ", "lj"
+    sub "м", "m"
+    sub "н", "n"
+    sub "њ", "nj"
+    sub "о", "o"
+    sub "п", "p"
+    sub "р", "r"
+    sub "с", "s"
+    sub "т", "t"
+    sub "ћ", "ć" # ć́
+    sub "у", "u"
+    sub "ф", "f"
+    sub "х", "h"
+    sub "ц", "c"
+    sub "ч", "č" # č
+    sub "џ", "dž" # dž
+    sub "ш", "š" # š
+  }
+
+  # POSTRULES
+  sub srp_multichar, upcase, before: srp_latupper
+  sub srp_multichar, upcase, after: srp_latupper
+  compose
+}

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

@@ -0,0 +1,185 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2007
+  language: iso-639-2:tat
+  source_script: Cyrl
+  destination_script: Latn
+  name: TATAR TABLE OF CORRESPONDENCES CYRILLIC - ROMAN BGN/PCGN 2007 Agreement
+  url: https://geonames.nga.mil/gns/html/Romanization/TABLE%20OF%20CORRESPONDENCES%20FOR%20TATAR.pdf
+  creation_date: 2007
+  confirmation_date: 2017-11
+  description: |
+    Tatar is an official language within Respublika Tatarstan, one of the republics of the Russian
+    Federation. It will normally be encountered in Cyrillic script, in which case it should be romanized by means
+    of the Cyrillic-Roman table of correspondences given below.
+
+  notes:
+    - |
+      The alphabet portrayed in the above table is referred to as yaꞑalif-2.
+      A set of simpler characters is also encountered; this is known as zamanalif.
+      In this latter set, the alternative characters ä, ñ and ö are used for letters
+      2, 17 and 19 respectively where the user has difficulty reproducing ə, ꞑ, and ө.
+      Please note that all three alternatives must be used as a set, and the letters should not be intermingled.
+    - Used only in borrowed words.
+    - The first option is used in words with back vowels, the second in words with front vowels (though this does not apply to borrowed words).
+    - yı/ye is used after a vowel (except и, ю), ъ and ь, also word-initially.
+    - w is used after a vowel.
+    - After ğ or q, ый is represented i
+    - Э is represented ’ after a vowel in words of Arabic origin.
+    - Ю and Я are represented ü and a/ä respectively after и.
+    - |
+      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters
+      of the basic Roman script is:
+          Ə (U+018F) ə (U+0259)
+          Ğ (U+011E) ğ (U+011F)
+          İ (U+0130) ı (U+0131)
+          Ü (U+00DC) ü (U+00FC)
+          Ꞑ (U+A790) ꞑ (U+A791)
+          Ɵ (U+019F) ɵ (U+0275)
+          Ç (U+00C7) ç (U+00E7)
+          Ş (U+015E) ş (U+015F)
+          Ä (U+00C4) ä (U+00E4)
+          ’ (U+2019)
+    - |
+      The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase
+      Roman letters as appropriate should be used.
+}
+
+tests {
+  test "Гыйльмиев", "Ğil’miew" #  # note[6] in the note it's Ğilmiev which incorrect according to the rules
+  # https://en.wikipedia.org/wiki/Tatar_alphabet
+  test "баеды", "bayıdı" # note[4]
+  test "кардәш", "qardəş"
+  test "калынлык һәм аеру билгесе", "qalınlıq həm ayıru bilgese" # note[4]
+  test "Барлык кешеләр дә азат һәм үз абруйлары һәм хокуклары ягыннан тиң булып туалар.\nАларга акыл һәм вөҗдан бирелгән һәм бер-берсенә карата туганнарча мөнасәбәттә булырга тиешләр.", "Barlıq keşelər də azat həm üz abruyları həm xoquqları yağınnan tiꞑ bulıp tualar.\nAlarğa aqıl həm wocdan birelgən həm ber-bersenə qarata tuğannarça monasəbəttə bulırğa tieşlər."
+  # https://www.azatliq.org/a/30820571.html
+  test "Әлдермештән Әлмәндәр", "Əldermeştən Əlməndər"
+  test "Әссәламү галәйкүм", "Əssəlamü ğaləyküm"
+  test "Танымаган кешегә", "Tanımağan keşegə" # note[3]
+  test "Иң әүвәл кул бирешеп күрешик", "İꞑ əwwəl qul bireşep küreşiq" # note[5]
+  test "Ялгышмыйсың", "Yalğışmıysıꞑ"
+  test "Нәкъ үзе", "Nəq üze"
+  test "Кирәгеннән артыгын", "Kirəgennən artığın" # note[3]
+  test "мәңгелеккә килмәгән", "məꞑgeleqkə kilməgən"
+  test "кулыңны куй", "qulıꞑnı quy"
+  test "Өммия", "Ommiä" # note[8]
+  test "Җиһангир", "Cihangir" # note[3]
+}
+
+stage {
+
+  # RULES
+  # note[3] http://www.hintfox.com/article/sistema-glasnih-zvykov-na-tatarskom-i-anglijskom-jazikah.html
+  # back vowels: у, а, ы, о,
+  # front vowels: е, ә, и, ө, ү, э
+  sub "Г", "G", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "г", "g", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "К", "K", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "к", "k", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "Ю", "Yü", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "ю", "yü", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "Я", "Yä", after: any("ЕеƏәИиӨөҮүЭэ")
+  sub "я", "yä", after: any("ЕеƏәИиӨөҮүЭэ")
+
+  # note[4]
+  sub "\u0415", "Yı", before: any("АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь")
+  sub "\u0435", "yı", before: any("АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь")
+
+  # note[5]
+  sub "\u0423", "W", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  sub "\u0443", "w", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  sub "\u04AE", "W", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  sub "\u04AF", "w", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+
+  # note[6]
+  sub "ый", "i", before: any("Гг")
+
+  # note[8]
+  sub "\u042E", "Ü", before: any("Ии")
+  sub "\u044E", "ü", before: any("Ии")
+  sub "\u042F", "Ä", before: any("Ии")
+  sub "\u044F", "ä", before: any("Ии")
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # А
+    sub "Ә", any("ƏÄ") # Ә => [Ə, Ä] note[1]
+    sub "Б", "B" # Б
+    sub "В", any("WV") # В note[2]
+    sub "Г", "Ğ" # Г => Ğ note[3]
+    sub "Д", "D" # Д
+    sub "Е", "E" # Е note[3] note[4]
+    sub "Ж", "J" # Ж
+    sub "Җ", "C" # Җ
+    sub "З", "Z" # З
+    sub "И", "İ" # И => İ
+    sub "Й", "Y" # Й
+    sub "К", "Q" # К note[3]
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "Ң", any("ꞐÑ") # Ң => [Ꞑ, Ñ] note[1]
+    sub "О", "O" # О
+    sub "Ө", any("OÖ") # Ө => [O, Ö] note[1]
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У note[5]
+    sub "Ү", "Ü" # Ү => Ü note[5]
+    sub "Ф", "F" # Ф
+    sub "Х", "Х" # Х
+    sub "Һ", "H" # Һ
+    sub "Ц", "Ts" # Ц
+    sub "Ч", "Ç" # Ч => Ç
+    sub "Ш", "Ş" # Ш => Ş
+    sub "Щ", "ŞÇ" # Щ
+    sub "Ъ", "" # Ъ
+    sub "Ы", "I" # Ы => I note[2] note[6]
+    sub "Ь", "’" # Ь => ’
+    sub "Э", "E" # Э note[7]
+    sub "Ю", "Yu" # Ю note[3] note[8]
+    sub "Я", "Ya" # Я note[3] note[8]
+
+    sub "\u0430", "a" # а
+    sub "\u04D9", any("əä") # ә => [ə, ä] note[1]
+    sub "\u0431", "b" # б
+    sub "\u0432", any("wv") # в note[2]
+    sub "\u0433", "ğ" # г => ğ note[3]
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e note[3] note[4]
+    sub "\u0436", "j" # ж
+    sub "\u0497", "c" # җ
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0439", "y" # й
+    sub "\u043A", "q" # к note[3]
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u04A3", any("ꞑñ") # ң => [ꞑ, ñ] note[1]
+    sub "\u043E", "o" # о
+    sub "\u04E9", any("oö") # ө => [o, ö] note[1]
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у note[5]
+    sub "\u04AF", "ü" # ү => ü note[5]
+    sub "\u0444", "f" # ф
+    sub "\u0445", "x" # х
+    sub "\u04BB", "h" # һ
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ç" # ч => ç
+    sub "\u0448", "ş" # ш => ş
+    sub "\u0449", "şç" # щ => şç
+    sub "ъ", "" # ъ
+    sub "\u044B", "ı" # ы => ı note[2] note[6]
+    sub "ь", "’" # ь => ’
+    sub "\u044D", "e" # э note[7]
+    sub "\u044E", "yu" # ю note[3] note[8]
+    sub "\u044F", "ya" # я note[3] note[8]
+  }
+
+}

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

@@ -0,0 +1,188 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1994
+  language: iso-639-2:tgk
+  source_script: Cyrl
+  destination_script: Latn
+  name: BGN/PCGN Romanization System -- Tajik (1994)
+  url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20TAJIK.pdf
+  creation_date: 1994
+  confirmation_date: 2017-11
+  description: |
+    The BGN/PCGN system for Tajik was designed for use in romanizing names written in the Tajik Cyrillic alphabet.
+    The Tajik Cyrillic alphabet contains six characters not present in the Russian alphabet: ғ, ӣ, қ, ӯ, ҳ and ҷ. An
+    orthographic reform of the Tajik Cyrillic alphabet was implemented under the auspices of the Academy of Sciences of
+    Tajikistan. This reform was promulgated in a decree of 3 September 1998 by the government of the Republic of
+    Tajikistan. The reform abolished the characters ц, щ, ь and ы (see notes 2 through 5).
+
+  notes:
+    - |
+      The character sequences гҳ , зҳ , кҳ , and сҳ may be romanized g·h, z·h, k·h, and s·h in order
+      to differentiate those romanizations from the digraphs gh, zh, kh, and sh which are used to
+      render the characters ғ, ж, x, and ш.
+    - |
+      The obsolete character ц, abolished in 1998, should be romanized s (before a vowel and/or
+      after a consonant within a word) or ts intervocalically.
+    - The obsolete character щ, replaced by ш in 1998, should be romanized sh.
+    - The obsolete character ь, abolished in 1998, should not be romanized.
+    - The obsolete character ы, replaced by и in 1998, should be romanized i.
+    - Unicode values are shown with the uppercase Cyrillic character first, followed by the lowercase character.
+    - |
+      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
+          Í (U+00CD) í (U+00ED)
+          Ŭ (U+016C) ŭ (U+016D)
+          Ė (U+0116) ė (U+0117)
+    - |
+      The Romanization column shows only lowercase forms but, when romanizing, uppercase and
+      lowercase Roman letters as appropriate should be used.
+}
+
+tests {
+  # https://ru.wikipedia.org/wiki/Таджикская_письменность#Образцы_записи
+  test "Тамоми одамон озод ба дунё меоянд ва аз лиҳози манзилату ҳуқуқ бо ҳам баробаранд.\nҲама соҳиби ақлу виҷдонанд, бояд нисбат ба якдигар бародарвор муносабат намоянд.", "Tamomi odamon ozod ba dunyo meoyand va az lihozi manzilatu huquq bo ham barobarand.\nHama sohibi aqlu vijdonand, boyad nisbat ba yakdigar barodarvor munosabat namoyand."
+  test "Баниодам аъзои як пайкаранд, ки дар офариниш зи як гавҳаранд. Чу узве ба дард оварад рӯзгор, дигар узвҳоро намонад қарор.", "Baniodam a’zoi yak paykarand, ki dar ofarinish zi yak gavharand. Chu uzve ba dard ovarad rŭzgor, digar uzvhoro namonad qaror."
+  test "Саъдӣ", "Sa’dí"
+  test "Мурда будам, зинда шудам; гиря будам, xанда шудам. Давлати ишқ омаду ман давлати поянда шудам.", "Murda budam, zinda shudam; girya budam, xanda shudam. Davlati ishq omadu man davlati poyanda shudam."
+  test "Мавлавӣ", "Mavlaví"
+  test "санг", "sang"
+  test "барг", "barg"
+  test "номвар", "nomvar"
+  test "Бағдод", "Baghdod"
+  test "ғор", "ghor"
+  test "модар", "modar"
+  test "меравам", "meravam"
+  test "дарё", "daryo"
+  test "осиёб", "osiyob"
+  test "жола", "zhola"
+  test "каждум", "kazhdum"
+  test "баъз", "ba’z"
+  test "назар", "nazar"
+  test "заҳоб", "zahob"
+  test "ихтиёр", "ikhtiyor"
+  test "зебоӣ", "zeboí"
+  test "май", "may"
+  test "кадом", "kadom"
+  test "қадам", "qadam"
+  test "лола", "lola"
+  test "мурдагӣ", "murdagí"
+  test "нон", "non"
+  test "орзу", "orzu"
+  test "панҷ", "panj"
+  test "ранг", "rang"
+  test "сар", "sar"
+  test "субҳ", "subh"
+  test "сурайё", "surayyo"
+  test "тоҷик", "tojik"
+  test "талаб", "talab"
+  test "дуд", "dud"
+  test "хӯрдан", "khŭrdan"
+  test "фурӯғ", "furŭgh"
+  test "хондан", "khondan"
+  test "ҳофиз", "hofiz"
+  test "чӣ", "chí"
+  test "ҷанг", "jang"
+  test "шаб", "shab"
+  test "таъриф", "ta’rif"
+  test "эй", "ėy"
+  test "июн", "iyun"
+  test "ягонагӣ", "yagonagí"
+  test "РАМЗҲО", "RAMZ·HO"
+}
+
+stage {
+
+  # RULES
+  # note[1]
+  sub "\u04B3", "·h", before: any("ГгЗзКкСс")
+  sub "\u04B2", "·H", before: any("ГгЗзКкСс")
+  # note[2]
+  sub "\u0426", "S", after: any("АаЕеЁёИиОоУуЫыЭэЮюЯя")
+  sub "\u0446", "s", after: any("АаЕеЁёИиОоУуЫыЭэЮюЯя")
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "В", "V" # В
+    sub "Г", "G" # Г
+    sub "Ғ", "Gh" # Ғ
+    sub "Д", "D" # Д
+    sub "Е", "E" # Е
+    sub "Ё", "Yo" # Ё
+    sub "Ж", "Zh" # Ж
+    sub "З", "Z" # З
+    sub "И", "I" # И
+    sub "Ӣ", "Í" # Ӣ => Í
+    sub "Й", "Y" # Й
+    sub "К", "K" # К
+    sub "Қ", "Q" # Қ
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "Ӯ", "Ŭ" # Ӯ => Ŭ
+    sub "Ф", "F" # Ф
+    sub "Х", "Kh" # Х
+    sub "Ҳ", "H" # Ҳ
+    sub "Ч", "Ch" # Ч
+    sub "Ҷ", "J" # Ҷ
+    sub "Ц", "Ts" # Ц note[2]
+    sub "Ш", "Sh" # Ш
+    sub "Щ", "Sh" # Щ note[3]
+    sub "Ъ", "’" # Ъ
+    sub "Ы", "I" # Ы note[5]
+    sub "Ь", "" # Ь note[4]
+    sub "Э", "Ė" # Э => Ė
+    sub "Ю", "Yu" # Ю
+    sub "Я", "Ya" # Я
+
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "в", "v" # в
+    sub "г", "g" # г
+    sub "ғ", "gh" # ғ
+    sub "д", "d" # д
+    sub "е", "e" # e
+    sub "ё", "yo" # ё
+    sub "ж", "zh" # ж
+    sub "з", "z" # з
+    sub "и", "i" # и
+    sub "ӣ", "í" # ӣ => í
+    sub "й", "y" # й
+    sub "к", "k" # к
+    sub "қ", "q" # қ
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "u" # у
+    sub "ӯ", "ŭ" # ӯ => ŭ
+    sub "ф", "f" # ф
+    sub "х", "kh" # х
+    sub "ҳ", "h" # ҳ
+    sub "ч", "ch" # ч
+    sub "ҷ", "j" # ҷ
+    sub "ц", "ts" # ц note[2]
+    sub "ш", "sh" # ш
+    sub "щ", "sh" # щ note[3]
+    sub "ъ", "’" # ъ
+    sub "ы", "i" # ы note[5]
+    sub "ь", "" # ь note[4]
+    sub "э", "ė" # э => ė
+    sub "ю", "yu" # ю
+    sub "я", "ya" # я
+  }
+
+}