interscript-maps 2.4.3 → 2.5.0

data/maps/alalc-mar-Deva-Latn-1997.isc

@@ -0,0 +1,182 @@
+system "ALA-LC:mar-Deva:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:mar
+  source_script Deva
+  destination_script Latn
+  name Romanization Table -- Marathi (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/marathi.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization table for Marathi
+  }
+
+  notes {
+
+    note "Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for\n vowels following a consonant can be found in grammars; no distinction between the two is\n made in transliteration."
+
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the subscript sign ( ् ) called halanta or\n         virāma."
+
+    note "      Exception: Anusvāra is transliterated by:\n\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials.\n      In other circumstances it is transliterated by a tilde (~) over the vowel."
+
+    note "When doubled, avagraha is transliterated by two apostrophes ( ’’ )."
+  }
+}
+
+tests {
+   "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद" ->  "ṭhaāṇae - jailahayaāta baudhavaāraī eka hajaāra raugaṇaāñcaī vaāḍha, tara jaṇaāñcayaā maṛitayaūcaī naonda"
+   "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक" ->  "ekataā kapaūra paunahaā aḍakalaī vaādaāta, vaebasaīraijamadhalayaā 'tayaā' saīnamaulae jamaāvaācaī gharaāvara dagaḍaphaeka"
+   "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं" ->  "jaāṇaūna ghayaā, baīemasaīcayaā adhaikaāऱyaānnaī kaṅganaā raāṇaautacayaā ôphaisamadhalae nakakaī kaāya- kaāya taoḍalam"
+   "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश" ->  "kaṅganaā maumbaīta daākhala haoṇayaāpaūravaī 'maātaośaraī'varaūna pharamaāna sauṭalae; paravakatayaānnaā sakata ādaeśa"
+   "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय" ->  "maraāṭhaā ārakashaṇaāsa taātapaurataī sathagaitaī; saravaocaca nayaāyaālayaācaā nairaṇaya"
+   "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात" ->  "bhaārataācayaā tainahaī laśaīñcaā pahailaā ṭapapaā yaśasavaī, vaācaā kadhaī yaeṇaāra baājaāraāta"
+   "रुग्णवाढीमुळे खाटांची चणचण" ->  "raugaṇavaāḍhaīmaulae khaāṭaāñcaī caṇacaṇa"
+   "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद" ->  "paīema savanaidhaī karaja yaojanaelaā maumbaītaūna alapa parataisaāda"
+   "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती" ->  "saāntaākaraūjha-caembaūra laiṅka raoḍavaraīla unanata maāragaālaā sathagaitaī"
+   "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार" ->  "sampaādaka araṇaba gaosavaāmaī yaāñcayaāvairaūdadha khaḍaka paolaisa ṭhaāṇayaāta takaraāra"
+   "२५६८७५४४६४४६१६११" ->  "2568754464461611"
+}
+
+stage main {
+
+  # RULES
+  # note[3]
+  sub {
+    from "\u0902"
+    to "ṅ"
+    after any("कखगघङ")
+  }
+  sub {
+    from "\u0902"
+    to "ñ"
+    after any("चछजझञ")
+  }
+  sub {
+    from "\u0902"
+    to "ṇ"
+    after any("टठडढण")
+  }
+  sub {
+    from "\u0902"
+    to "n"
+    after any("तथदधन")
+  }
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    sub "अ" "a"
+    sub "आ" "ā"
+    sub "इ" "i"
+    sub "ई" "ī"
+    sub "उ" "u"
+    sub "ऊ" "ū"
+    sub "ऋ" "ṛ"
+    sub "ॠ" "ṝ"
+    sub "ऌ" "ḹ"
+    #'ॳ': 'ĕ'
+    sub "ए" "e"
+    sub "ॲ" "ê"
+    #'अै': 'ai'
+    sub "ऐ" "ai"
+    #'ऒ': 'ŏ'
+    sub "ओ" "o"
+    sub "ऑ" "ô"
+    sub "औ" "ău"
+
+    # II. Consonants
+    # Gutturals
+    sub "क" "ka"
+    sub "ख" "kha"
+    sub "ग" "ga"
+    sub "घ" "gha"
+    sub "ङ" "ṅa"
+
+    # Palatals
+    sub "च" "ca"
+    sub "छ" "cha"
+    sub "ज" "ja"
+    sub "झ" "jha"
+    sub "ञ" "ña"
+
+    # Cerebrals
+    sub "ट" "ṭa"
+    sub "ठ" "ṭha"
+    sub "ड" "ḍa"
+    #'ड़': 'ṛa'
+    sub "ढ" "ḍha"
+    #'ढ़': 'ṛha'
+    sub "ण" "ṇa"
+
+    # Dentals
+    sub "त" "ta"
+    sub "थ" "tha"
+    sub "द" "da"
+    sub "ध" "dha"
+    sub "न" "na"
+
+    # Labials
+    sub "प" "pa"
+    sub "फ" "pha"
+    sub "ब" "ba"
+    sub "भ" "bha"
+    sub "म" "ma"
+
+    # Semivowels
+    sub "य" "ya"
+    sub "र" "ra"
+    sub "ल" "la"
+    sub "ळ" "la"
+    sub "व" "va"
+
+    # Sibilants
+    sub "श" "śa"
+    sub "ष" "sha"
+    sub "स" "sa"
+
+    # Aspirate
+    sub "ह" "ha"
+
+    # Anusvāra
+    sub "ं" "m"
+
+    # Bisarga
+    sub "ः " "ḥ"
+
+    # Abagraha
+    sub "ऽ" "’"
+
+    # Medials # Needed for connecting constants
+    sub "ा" "ā"
+    sub "ि" "i"
+    sub "ी" "ī"
+    sub "ु" "u"
+    sub "ू" "ū"
+    sub "ृ" "ṛi"
+    sub "ॄ" "rī"
+    sub "े" "e"
+    sub "ो" "o"
+    sub "ौ" "au"
+    sub "्" ""
+
+    # digits
+
+    sub "०" "0"
+    sub "१" "1"
+    sub "२" "2"
+    sub "३" "3"
+    sub "४" "4"
+    sub "५" "5"
+    sub "६" "6"
+    sub "७" "7"
+    sub "८" "8"
+    sub "९" "9"
+  }
+
+  compose
+}
+}

data/maps/alalc-mar-Deva-Latn-2011.isc

@@ -0,0 +1,39 @@
+system "ALA-LC:mar-Deva:Latn:2011" {
+
+metadata {
+  authority_id alalc
+  id 2011
+  language iso-639-2:mar
+  source_script Deva
+  destination_script Latn
+  name Romanization Table -- Marathi (2011)
+  url https://loc.gov/catdir/cpso/romanization/marathi.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization table for Marathi
+  }
+
+  notes {
+
+    note "Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for\n vowels following a consonant can be found in grammars; no distinction between the two is\n made in transliteration."
+
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the subscript sign ( ् ) called halanta or\n         virāma."
+
+    note "      Exception: Anusvāra is transliterated by:\n\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials.\n      In other circumstances it is transliterated by a tilde (~) over the vowel."
+
+    note "When doubled, avagraha is transliterated by two apostrophes ( ’’ )."
+  }
+}
+
+tests {
+   "कोरोनाच्या लढाईत पोलीस थकलेत, पण हिंमत हरलेले नाहीत; गृहमंत्र्यांकडून कौतुक" ->  "kaoraonaācayaā laḍhaāīta paolaīsa thakalaeta, paṇa haimmata haralaelae naāhaīta; gaṛihamantarayaāṅkaḍaūna kaautauka"
+}
+
+dependency "alalc-mar-Deva-Latn-1997" as devalatn
+
+stage main {
+
+  run  map.devalatn.stage.main
+
+}
+
+}

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

@@ -0,0 +1,149 @@
+system "ALA-LC:mkd-Cyrl:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:mkd
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Serbian and Macedonian (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/serbian.pdf
+  creation_date 1997
+  description ALA-LC Romanization table for Serbian and Macedonian.
+
+  notes {
+    note "Special characters in romanization\n Đ - D with crossbar (upper case). USMARC hexadecimal code A3.\n đ - d with crossbar (upper case). USMARC hexadecimal code B3."
+
+    note "Character modifiers in romanization\n ´ - acute. USMARC hexadecimal code E2.\n ˇ - hachek. USMARC hexadecimal code E9."
+  }
+}
+
+tests {
+   "Општина Ердут" ->  "Opština Erdut"
+   "Општина Двор" ->  "Opština Dvor"
+   "ЛУЃЕ луѓе" ->  "LUǴE luǵe"
+   "ЅВЕЗДА ѕвезда Ѕвезда" ->  "DZVEZDA dzvezda Dzvezda"
+   "ЌАРУВАЊЕ ќарување" ->  "ḰARUVANJE ḱaruvanje"
+}
+
+dependency "posix"
+
+stage main {
+
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Ѓ" "Ǵ"
+    sub "Д" "D"
+    sub "Ђ" "Đ"
+    sub "Е" "E"
+    sub "Ж" "Ž"
+    sub "З" "Z"
+    sub "Ѕ" "Dz"
+    sub "И" "I"
+    sub "Ј" "J"
+    sub "К" "K"
+    sub "Ќ" "Ḱ"
+    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"
+    sub "У" "U"
+    sub "Ф" "F"
+    sub "Х" "H"
+    sub "Ц" "C"
+    sub "Ч" "Č"
+    sub "Џ" "Dž"
+    sub "Ш" "Š"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "ѓ" "ǵ"
+    sub "д" "d"
+    sub "ђ" "đ"
+    sub "е" "e"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "ѕ" "dz"
+    sub "и" "i"
+    sub "ј" "j"
+    sub "к" "k"
+    sub "ќ" "ḱ"
+    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"
+    sub "у" "u"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "џ" "dž"
+    sub "ш" "š"
+  }
+
+  # POSTRULES
+  # rewritten by hand to work properly
+  # DZ
+  sub {
+    from capture(maybe(upper)) + "Dz" + capture(upper)
+    to ref(1) + "DZ" + ref(2)
+  }
+  sub {
+    from capture(upper) + "Dz" + capture(maybe(upper))
+    to ref(1) + "DZ" + ref(2)
+  }
+
+  #LJ
+  sub {
+    from capture(upper) + "Lj" + capture(maybe(upper))
+    to ref(1) + "LJ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Lj" + capture(upper)
+    to ref(1) + "LJ" + ref(2)
+  }
+
+  #NJ
+  sub {
+    from capture(upper) + "Nj" + capture(maybe(upper))
+    to ref(1) + "NJ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Nj" + capture(upper)
+    to ref(1) + "NJ" + ref(2)
+  }
+
+  #DŽ
+  sub {
+    from capture(upper) + "Dž" + capture(maybe(upper))
+    to ref(1) + "DŽ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Dž" + capture(upper)
+    to ref(1) + "DŽ" + ref(2)
+  }
+
+  compose
+}
+
+}

data/maps/alalc-mkd-Cyrl-Latn-2013.isc

@@ -0,0 +1,140 @@
+system "ALA-LC:mkd-Cyrl:Latn:2013" {
+
+metadata {
+  authority_id alalc
+  id 2013
+  language iso-639-2:mkd
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Macedonian (2013)
+  url https://www.loc.gov/catdir/cpso/romanization/macedonian.pdf
+  creation_date 2013
+  description ALA-LC Romanization table for Macedonian.
+}
+
+tests {
+   "Општина Ердут" ->  "Opština Erdut"
+   "Општина Двор" ->  "Opština Dvor"
+   "ЛУЃЕ луѓе" ->  "LUǴE luǵe"
+   "ЅВЕЗДА ѕвезда Ѕвезда" ->  "DZVEZDA dzvezda Dzvezda"
+   "ЌАРУВАЊЕ ќарување" ->  "ḰARUVANJE ḱaruvanje"
+}
+
+dependency "posix"
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Ѓ" "Ǵ"
+    sub "Д" "D"
+    sub "Ђ" "Đ"
+    sub "Е" "E"
+    sub "Ж" "Ž"
+    sub "З" "Z"
+    sub "Ѕ" "Dz"
+    sub "И" "I"
+    sub "Ј" "J"
+    sub "К" "K"
+    sub "Ќ" "Ḱ"
+    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 "У" "U"
+    sub "Ф" "F"
+    sub "Х" "H"
+    sub "Ц" "C"
+    sub "Ч" "Č"
+    sub "Џ" "Dž"
+    sub "Ш" "Š"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "ѓ" "ǵ"
+    sub "д" "d"
+    sub "ђ" "đ"
+    sub "е" "e"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "ѕ" "dz"
+    sub "и" "i"
+    sub "ј" "j"
+    sub "к" "k"
+    sub "ќ" "ḱ"
+    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 "у" "u"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "џ" "dž"
+    sub "ш" "š"
+  }
+
+  # POSTRULES
+  # rewritten by hand to work properly
+  # DZ
+  sub {
+    from capture(maybe(upper)) + "Dz" + capture(upper)
+    to ref(1) + "DZ" + ref(2)
+  }
+  sub {
+    from capture(upper) + "Dz" + capture(maybe(upper))
+    to ref(1) + "DZ" + ref(2)
+  }
+
+  #LJ
+  sub {
+    from capture(upper) + "Lj" + capture(maybe(upper))
+    to ref(1) + "LJ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Lj" + capture(upper)
+    to ref(1) + "LJ" + ref(2)
+  }
+
+  #NJ
+  sub {
+    from capture(upper) + "Nj" + capture(maybe(upper))
+    to ref(1) + "NJ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Nj" + capture(upper)
+    to ref(1) + "NJ" + ref(2)
+  }
+
+  #DŽ
+  sub {
+    from capture(upper) + "Dž" + capture(maybe(upper))
+    to ref(1) + "DŽ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Dž" + capture(upper)
+    to ref(1) + "DŽ" + ref(2)
+  }
+
+  compose
+}
+
+}

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

@@ -0,0 +1,164 @@
+system "ALA-LC:mon-Cyrl:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:mon
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Mongolian Cyrillic Khalkha (1997)
+  url https://collab.its.virginia.edu/wiki/tibetan-script/Transliteration%20Schemes%20Mongolian%20Cyrillic%20Script.html
+  creation_date 1997
+  confirmation_date 
+  description {    In Mongolia, the Khalkha dialect, currently written in both Cyrillic and traditional Mongolian script
+    (and at times in Latin for social networking), is predominant, while in Inner Mongolia, the language
+    is dialectically more diverse and is written in the traditional Mongolian script.
+  }
+}
+
+tests {
+   "Эрдэнэт Сум" ->  "Êrdênêt Sum"
+   "Эрдэнэт" ->  "Êrdênêt"
+   "Эрдэнэ" ->  "Êrdênê"
+   "Шивээговь Сум" ->  "Shivêêgovi Sum"
+   "Шивээговь" ->  "Shivêêgovi"
+   "Шарынгол Сум" ->  "Sharyngol Sum"
+   "Шарынгол" ->  "Sharyngol"
+   "Цагааннуур" ->  "Tsagaannuur"
+   "Хонгор Сум" ->  "Khongor Sum"
+   "Хонгор" ->  "Khongor"
+   "Хайлаастай" ->  "Khaĭlaastaĭ"
+   "Түнэл Сум" ->  "Tünêl Sum"
+   "Түнэл" ->  "Tünêl"
+   "Сүхбаатар" ->  "Sükhbaatar"
+   "Сүмбэр Сум" ->  "Sümbêr Sum"
+   "Сүмбэр" ->  "Sümbêr"
+   "Сайншанд Сум" ->  "Saĭnshand Sum"
+   "Сайншанд" ->  "Saĭnshand"
+   "Орхон Сум" ->  "Orkhon Sum"
+   "Орхон" ->  "Orkhon"
+   "Нарст" ->  "Narst"
+   "Мөрөн Сум" ->  "Mörön Sum"
+   "Мөрөн" ->  "Mörön"
+   "Зүүнхөвөө" ->  "Züünkhövöö"
+   "Жаргалант Сум" ->  "Zhargalant Sum"
+   "Жаргалант" ->  "Zhargalant"
+   "Дархан Сум" ->  "Darkhan Sum"
+   "Даланзадгад Сум" ->  "Dalanzadgad Sum"
+   "Даланзадгад" ->  "Dalanzadgad"
+   "Давст Сум" ->  "Davst Sum"
+   "Давст" ->  "Davst"
+   "Говьсүмбэр Сум" ->  "Govisümbêr Sum"
+   "Говь" ->  "Govi"
+   "Буга" ->  "Buga"
+   "Бор-Өндөр Сум" ->  "Bor-Öndör Sum"
+   "Бор-Өндөр" ->  "Bor-Öndör"
+   "Баянхонгор" ->  "Baiankhongor"
+   "Баянтал" ->  "Baiantal"
+   "Баяндэлгэр Сум" ->  "Baiandêlgêr Sum"
+   "Баяндэлгэр" ->  "Baiandêlgêr"
+   "Баян-Өндөр Сум" ->  "Baian-Öndör Sum"
+   "Баруун-Урт Сум" ->  "Baruun-Urt Sum"
+   "Баруун-Урт" ->  "Baruun-Urt"
+   "Архуст" ->  "Arkhust"
+   "Арвайхээр Сум" ->  "Arvaĭkhêêr Sum"
+   "Арвайхээр" ->  "Arvaĭkhêêr"
+   "Есөнбулаг Сум" ->  "Esönbulag Sum"
+   "Ерөө Сум" ->  "Eröö Sum"
+   "Есөнзүйл Сум" ->  "Esönzüĭl Sum"
+   "Ноён Сум" ->  "Noën Sum"
+   "Родник Балянгийн-Булак" ->  "Rodnik Baliangiĭn-Bulak"
+   "Замын-Үүд Сум" ->  "Zamyn-Üüd Sum"
+   "Адаацаг Сум" ->  "Adaatsag Sum"
+   "Чандмань Сум" ->  "Chandmani Sum"
+   "Хяргас Сум" ->  "Khiargas Sum"
+   "Еэвэн, ерөөл" ->  "Eêvên, erööl"
+   "Ёроол, оёдол" ->  "Ërool, oëdol"
+   "Пуужин, апарат" ->  "Puuzhin, aparat"
+   "Фото, фонд" ->  "Foto, fond"
+   "Щедрин, щорс" ->  "Shchedrin, shchors"
+   "Оръё, суръя, гаръя" ->  "Or“ë, sur“ia, gar“ia"
+   "Юм, юүдэн" ->  "Ium, iuüdên"
+   "Ямар, ядуу, ая" ->  "Iamar, iaduu, aia"
+}
+
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ё" "Ë"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "Й" "Ĭ"
+    sub "К" "K"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "О" "O"
+    sub "Ө" "Ö"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ү" "Ü"
+    sub "Ф" "F"
+    sub "Х" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Щ" "Shch"
+    sub "Ъ" "“"
+    sub "Ы" "Y"
+    sub "Ь" "I"
+    sub "Э" "Ê"
+    sub "Ю" "Iu"
+    sub "Я" "Ia"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ë"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "ĭ"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "ө" "ö"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ү" "ü"
+    sub "ф" "f"
+    sub "х" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "щ" "shch"
+    sub "ъ" "“"
+    sub "ы" "y"
+    sub "ь" "i"
+    sub "э" "ê"
+    sub "ю" "iu"
+    sub "я" "ia"
+  }
+
+}
+
+}