interscript 0.1.6 → 0.1.7

data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1952
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: ROMANIZATION SYSTEM FOR BULGARIAN BGN/PCGN of 1952
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_BGN_1952
+    description: Bulgarian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) Bulgarian 1952 System
 url: https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
 creation_date: 1945
 confirmation_date: 1952

data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 2013
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: BGN/PCGN 2013 Agreement
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_BGN_2013
+    description: Bulgarian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names(PCGN) Bulgarian 2013 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811509/ROMANIZATION_OF_BULGARIAN.pdf
 creation_date: 2013
 confirmation date: 2019-06

data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml

@@ -0,0 +1,184 @@
+---
+authority_id: bgnpcgn
+id: 2008
+language: iso-639-2:che
+source_script: Cyrl
+destination_script: Latn
+name: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+creation_date: 2008
+confirmation_date: 2019-07
+description: |
+  Chechen is an official language within Chechnya, 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 letter ə is used to represent short a; a is used for long a.
+  - Ye is used word- and syllable-initially. This Cyrillic letter may be encountered as the ligature ie in Chechen-Roman sources.
+  - This character occurs only in loan words.
+  - q in the combination ккх (qq) and q̇in the combination ккъ (q̇q̇)
+  - ŋ when preceding vowel is nasalized.
+  - This Cyrillic letter may be encountered as the ligature ꭣ [U+AB63] or the diphthong oa in Chechen Roman sources.
+  - Unless in the combinations гӀ, кӀ, пӀ, тӀ, хӀ, цӀ and чӀ.
+  - |
+    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
+
+        Ə (U+018F)       ə (U+0259)
+        Ä (U+00C4)       ä (U+00E4)
+        Ġ (U+0047+0307)  ġ (U+0067+0307)
+        Z̵ (U+005A+0335)  z̵ (U+007A+0335)
+        Q̇ (U+0051+0307)  q̇ (U+0071+0307)
+        Ŋ (U+014A)       ŋ (U+014B)
+        Ö (U+00D6)       ö (U+00F6)
+        Ü (U+00DC)       ü (U+00FC)
+        Ẋ (U+0058+0307)  ẋ (U+0078+0307)
+        Ċ (U+0043+0307)  ċ (U0063+0307)
+        Ç (U+00C7)       ç (U+00E7)
+        Ç̇ (U+00C7+0307)  ç̇ (U+00E7+0307)
+        Ş (U+015E)       ş (U+015F)
+
+  - The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used
+
+tests:
+  - source: кӏант
+    expected: khant
+  - source: зуда
+    expected: zuda
+  - source: пхьагал
+    expected: pẋagal
+  - source: наж
+    expected: naz̵
+  - source: мангал
+    expected: mangal
+  - source: Ӏаж
+    expected: Jaz̵
+  - source: Нохчийн Википеди
+    expected: Noxçiyn Vikipedi
+  - source: сагӏадаккхар
+    expected: saġadaqqar
+  - source: йеза
+    expected: yeza
+  - source: еара
+    expected: yeara
+  - source: елха
+    expected: yelxa
+
+map:
+  rules:
+    # note[2]
+    - pattern: (?<!\b\u2019)\b\u0415 # Е in initial position -> Ye
+      result: Ye
+    - pattern: (?<!\b\u2019)\b\u0435 # е in initial position -> ye
+      result: ye
+    # note[4]
+    - pattern: \u043A\u043A\u0445
+      result: qq
+    - pattern: \u043A\u043A\u042A
+      result: q̇q̇
+    - pattern: \u041A\u041A\u0445
+      result: QQ
+    - pattern: \u041A\u041A\u042A
+      result: Q̇Q̇
+
+  characters:
+    '\u0410'        : ['A', 'Ə']        # А note[1]
+    '\u0410\u044C'  : "A\u0308"         # Аь -> Ä
+    '\u0411'        : 'B'               # Б
+    '\u0412'        : 'V'               # В
+    '\u0413'        : 'G'               # Г
+    '\u0413\u04C0'  : "G\u0307"         # ГӀ -> Ġ
+    '\u0414'        : 'D'               # Д
+    '\u0415'        : 'E'               # Е note[2]
+    '\u0401'        : 'Yo'              # Ё note[3]
+    '\u0416'        : "Z\u0335"         # Ж -> Ƶ
+    '\u0417'        : 'Z'               # З
+    '\u0418'        : 'I'               # И
+    '\u042B'        : 'Y'               # Й
+    '\u041A'        : 'K'               # К note[4]
+    '\u041A\u0445'  : 'Q'               # Кх note[4]
+    '\u041A\u044A'  : "Q\u0307"         # Къ -> Q̇ note[4]
+    '\u041A\u04C0'  : 'Kh'              # КӀ note[4]
+    '\u041B'        : 'L'               # Л
+    '\u041C'        : 'M'               # М
+    '\u041D'        : ['N', 'Ŋ']        # Н note[5]
+    '\u041E'        : 'O'               # О note[6]
+    '\u041E\u044C'  : "O\u0308"         # Оь -> Ö
+    '\u041F'        : 'P'               # П
+    '\u041F\u04C0'  : 'Ph'              # ПӀ
+    '\u0420'        : 'R'               # Р
+    '\u0421'        : 'S'               # С
+    '\u0422'        : 'T'               # Т
+    '\u0422\u04C0'  : 'Th'              # TӀ
+    '\u0423'        : 'U'               # У
+    '\u0423\u044C'  : "U\u0308"         # Уь -> Ü
+    '\u0424'        : 'F'               # Ф
+    '\u0425'        : 'X'               # Х
+    '\u0425\u044C'  : "X\u0307"         # Хь -> Ẋ
+    '\u0425\u04C0'  : "H"               # ХӀ
+    '\u04B8'        : 'C'               # Ц
+    '\u04B8\u04C0'  : "C\u0307"         # ЦӀ -> Ċ
+    '\u0427'        : "C\u0327"         # Ч -> Ç
+    '\u0427\u04C0'  : "\u00C7\u0307"    # ЧӀ -> Ç̇
+    '\u0428'        : "S\u0327"         # Ш -> Ş
+    '\u0429'        : "S\u0327C\u0327"  # Щ -> ŞÇ note[3]
+    '\u042A'        : "’"               # Ъ note[3]
+    '\u042B'        : "Y"               # Ы
+    '\u042C'        : ""                # Ь note[3]
+    '\u042D'        : "E"               # Э
+    '\u042E'        : "Yu"              # Ю
+    '\u042E\u044C'  : "Yu\u0308"        # Юь -> Yü
+    '\u042F'        : "Ya"              # Я
+    '\u042F\u044C'  : "Ya\u0308"        # Яь -> Yä
+    '\u04C0'        : "J"               # Ӏ note[7]
+
+    '\u0430'        : ['a', 'ə']        # а note[1]
+    '\u0430\u044C'  : "a\u0308"         # аь -> ä
+    '\u0431'        : 'b'               # б
+    '\u0432'        : 'v'               # в
+    '\u0433'        : 'g'               # г
+    '\u0433\u04CF'  : "g\u0307"         # гӏ -> ġ
+    '\u0434'        : 'd'               # д
+    '\u0435'        : 'e'               # е note[2]
+    '\u0451'        : 'yo'              # ё note[3]
+    '\u0436'        : "z\u0335"         # ж -> ƶ
+    '\u0437'        : 'z'               # з
+    '\u0438'        : 'i'               # и
+    '\u0439'        : 'y'               # й
+    '\u043A'        : 'k'               # к note[4]
+    '\u043A\u0445'  : 'q'               # кх note[4]
+    '\u043A\u044A'  : "q\u0307"         # къ -> q̇ note[4]
+    '\u043A\u04CF'  : 'kh'              # кӏ note[4]
+    '\u043B'        : 'l'               # л
+    '\u043C'        : 'm'               # м
+    '\u043D'        : ['n', 'ŋ']        # н note[5]
+    '\u043E'        : 'o'               # о note[6]
+    '\u043E\u044C'  : "o\u0308"         # оь -> ö
+    '\u043F'        : 'p'               # п
+    '\u0440'        : 'r'               # р
+    '\u0441'        : 's'               # с
+    '\u0442'        : 't'               # т
+    '\u0442\u04CF'  : 'th'              # тӏ
+    '\u0443'        : 'u'               # у
+    '\u0443\u044C'  : "u\u0308"         # Уь -> ü
+    '\u0444'        : 'f'               # ф
+    '\u0445'        : 'x'               # х
+    '\u0445\u044C'  : "x\u0307"         # хь -> ẋ
+    '\u0445\u04CF'  : "h"               # хӏ
+    '\u04B9'        : 'c'               # ц
+    '\u04B9\u04CF'  : "с\u0307"         # цӏ -> ċ
+    '\u0447'        : "c\u0327"         # ч -> ç
+    '\u0447\u04CF'  : "c\u00E7\u0307"   # чӏ -> ç̇
+    '\u0448'        : "s\u0327"         # ш -> ş
+    '\u0449'        : "s\u0327c\u0327"  # щ -> şç note[3]
+    '\u044A'        : "’"               # ъ note[3]
+    '\u044B'        : "y"               # ы
+    '\u044C'        : ''                # ь note[3]
+    '\u044D'        : "e"               # э
+    '\u044E'        : "yu"              # ю
+    '\u044E'        : "yu\u0308"        # юь -> yü
+    '\u044F'        : "ya"              # я
+    '\u044F'        : "ya\u0308"        # яь -> yä
+    '\u04CF'        : "j"               # ӏ note[7]

data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1962
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: BGN/PCGN 1962 System
+alias:
+  ogc11122:
+    code: ell_Grek2Latn_BGN_1962
+    description: US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) Greek 1962 System (out of date)
 url: https://github.com/riboseinc/interscript/files/4225556/BGN_Romanization_Guide_1962_greek.pdf
 creation_date: 1962
 description: |

data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1996
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: BGN/PCGN 1996 System
+alias:
+  ogc11122:
+    code: ell_Grek2Latn_ELOT743_1996
+    description: Greek ELOT 743 System, US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1996 agreement
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693694/ROMANIZATION_OF_GREEK.pdf
 creation_date: 1996
 description: |

data/maps/{bgnpcgn-per-Arab-Latn-1956.yaml → bgnpcgn-fas-Arab-Latn-1956.yaml}

@@ -3,10 +3,14 @@
 # TODO: Add tests from PDF
 authority_id: bgnpcgn
 id: 1956
-language: per
+language: iso-639-2:fas
 source_script: Arab
 destination_script: Latn
 name: BGN/PCGN 1956 System
+alias:
+  ogc11122:
+    code: fas_Arab2Latn_BGN_1958
+    description: Persian (Afghan and Iranian) BGN/Permanent Committee on Geographical Names for British Official Use(PCGN) 1958 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/320079/Arabic_Romanization.pdf
 creation_date: 1947
 confirmation_date: 2019-06

data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 1930
-language: jpn
+language: iso-639-2:jpn
 source_script: Hrkt
 destination_script: Latn
 name: Japanese Kana Modified Hepburn 1930 System

data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1981
-language: kat
+language: iso-639-2:kat
 source_script: Geor
 destination_script: Latn
 name: ROMANIZATION OF GEORGIAN; BGN/PCGN 1981 System
+alias:
+  ogc11122:
+    code: kat_Geor2Latn_BGN_1981
+    description: Georgian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1981 System
 url: https://transliteration.eki.ee/pdf/Georgian.pdf
 creation_date: 1981
 confirmation_date: 1981

data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 2009
-language: kat
+language: iso-639-2:kat
 source_script: Geor
 destination_script: Latn
 name: ROMANIZATION OF GEORGIAN; Georgia 2011 national system; BGN/PCGN 2009 Agreement

data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: kn-1945
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: BGN/PCGN 1945 Agreement

data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 2011
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement

data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 2011
-language: kor
+language: iso-639-2:kor
 source_script: Kore
 destination_script: Latn
 name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement

data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1981
-language: mkd
+language: iso-639-2:mkd
 source_script: Cyrl
 destination_script: Latn
 name: Makedonian Romanization, BGN/PCGN 1981 System
+alias:
+  ogc11122:
+    code: mkd_Cyrl2Latn_BGN_1981
+    description: Macedonian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1981 System
 url: https://github.com/riboseinc/interscript/files/4247920/USBGN_romanization_Macedonian_1981.pdf
 creation_date: 1981
 description: BGN/PCGN Romanization table for Makedonian.

data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 2013
-language: mkd
+language: iso-639-2:mkd
 source_script: Cyrl
 destination_script: Latn
 name: Makedonian Romanization, BGN/PCGN 2013 System

data/maps/bgnpcgn-mon-Cyrl-Latn-1964.yaml

@@ -0,0 +1,223 @@
+---
+authority_id: bgnpcgn
+id: 1964
+language: iso-639-2:mon
+source_script: Cyrl
+destination_script: Latn
+name: BGN/PCGN 1964 System
+alias:
+  ogc11122:
+    code: mon_Cyrl2Latn_BGN_1964
+    description: Mongolian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1964 System
+url: https://github.com/interscript/interscript/files/5180767/BGN_Romanization_Guide_1964_mongolian_1964.pdf
+creation_date:
+confirmation_date:
+description: |
+  This system was originated by the PCGN in 1957 and adopted as a
+  BGN/PCGN System in 1964. It is intended for use in the romanization of
+  geographic names in the "Mongolian People's Republic" but not to romanize
+  Mongolian names in adjacent parts of China and the U.S.S.R.
+
+notes: |
+  - b occurs initially and after л, м, and б.
+  - v occurs medially in Mongolian words and initially in foreign words.
+  - y occurs only as the second element of diphthongs.
+  - k, p, f, and shch occurs foreign words only.
+  - "\u2019" occurs only in Russion words.
+  - ï occurs only in suffixes to words containing back vowels (a, o, and u).
+  - In monosyllables yu or yü depending on pronunciation; in polysyllables yu when followed by a, o, or u, but yü when followed by i, e, ö, or ü.
+
+tests:
+  - source: Эрдэнэт Сум
+    expected: Erdenet Sum
+  - source: Эрдэнэт
+    expected: Erdenet
+  - source: Эрдэнэ
+    expected: Erdene
+  - source: Шивээговь Сум
+    expected: Shiveegovĭ Sum
+  - source: Шивээговь
+    expected: Shiveegovĭ
+  - source: Шарынгол Сум
+    expected: Sharïngol Sum
+  - source: Шарынгол
+    expected: Sharïngol
+  - source: Цагааннуур
+    expected: Tsagaannuur
+  - source: Хонгор Сум
+    expected: Hongor Sum
+  - source: Хонгор
+    expected: Hongor
+  - source: Хайлаастай
+    expected: Haylaastay
+  - source: Түнэл Сум
+    expected: Tünel Sum
+  - source: Түнэл
+    expected: Tünel
+  - source: Сүхбаатар
+    expected: Sühbaatar
+  - source: Сүмбэр Сум
+    expected: Sümber Sum
+  - source: Сүмбэр
+    expected: Sümber
+  - source: Сайншанд Сум
+    expected: Saynshand Sum
+  - source: Сайншанд
+    expected: Saynshand
+  - source: Орхон Сум
+    expected: Orhon Sum
+  - source: Орхон
+    expected: Orhon
+  - source: Нарст
+    expected: Narst
+  - source: Мөрөн Сум
+    expected: Mörön Sum
+  - source: Мөрөн
+    expected: Mörön
+  - source: Зүүнхөвөө
+    expected: Dzüünhövöö
+  - source: Жаргалант Сум
+    expected: Jargalant Sum
+  - source: Жаргалант
+    expected: Jargalant
+  - source: Дархан Сум
+    expected: Darhan Sum
+  - source: Даланзадгад Сум
+    expected: Dalandzadgad Sum
+  - source: Даланзадгад
+    expected: Dalandzadgad
+  - source: Давст Сум
+    expected: Davst Sum
+  - source: Давст
+    expected: Davst
+  - source: Говьсүмбэр Сум
+    expected: Govĭsümber Sum
+  - source: Говь
+    expected: Govĭ
+  - source: Буга
+    expected: Buga
+  - source: Бор-Өндөр Сум
+    expected: Bor-Öndör Sum
+  - source: Бор-Өндөр
+    expected: Bor-Öndör
+  - source: Баянхонгор
+    expected: Bayanhongor
+  - source: Баянтал
+    expected: Bayantal
+  - source: Баяндэлгэр Сум
+    expected: Bayandelger Sum
+  - source: Баяндэлгэр
+    expected: Bayandelger
+  - source: Баян-Өндөр Сум
+    expected: Bayan-Öndör Sum
+  - source: Баруун-Урт Сум
+    expected: Baruun-Urt Sum
+  - source: Баруун-Урт
+    expected: Baruun-Urt
+  - source: Архуст
+    expected: Arhust
+  - source: Арвайхээр Сум
+    expected: Arvayheer Sum
+  - source: Арвайхээр
+    expected: Arvayheer
+  - source: Есөнбулаг Сум
+    expected: Yösönbulag Sum
+  - source: Ерөө Сум
+    expected: Yöröö Sum
+  - source: Есөнзүйл Сум
+    expected: Yösöndzüyl Sum
+  - source: Ноён Сум
+    expected: Noyon Sum
+  - source: Родник Балянгийн-Булак
+    expected: Rodnik Balyangiyn-Bulak
+  - source: Замын-Үүд Сум
+    expected: Dzamïn-Üüd Sum
+  - source: Адаацаг Сум
+    expected: Adaatsag Sum
+  - source: Чандмань Сум
+    expected: Chandmanĭ Sum
+  - source: Хяргас Сум
+    expected: Hyargas Sum
+
+map:
+  rules:
+    - pattern: \u042e(?=[АаОоУу]) # Ю before а, о, or у
+      result: "Yu"
+    - pattern: \u044e(?=[АаОоУу]) # ю before а, о, or у
+      result: "yu"
+    - pattern: \u042e(?=[ИиЭэӨөҮү]) # Ю before и, э, ө, or ү
+      result: "Yü"
+    - pattern: \u044e(?=[ИиЭэӨөҮү]) # ю before и, э, ө, or ү
+      result: "yü"
+
+  characters:
+    "А": "A"      # \u0410
+    "Б": "B"      # \u0411
+    "В": "V"      # \u0412
+    "Г": "G"      # \u0413
+    "Д": "D"      # \u0414
+    "Е": "Yö"     # \u0415
+    "Ё": "Yo"     # \u0401
+    "Ж": "J"      # \u0416
+    "З": "Dz"     # \u0417
+    "И": "I"      # \u0418
+    "Й": "Y"      # \u0419
+    "К": "K"      # \u041a
+    "Л": "L"      # \u041b
+    "М": "M"      # \u041c
+    "Н": "N"      # \u041d
+    "О": "O"      # \u041e
+    "Ө": "Ö"      # \u04e8
+    "П": "P"      # \u041f
+    "Р": "R"      # \u0420
+    "С": "S"      # \u0421
+    "Т": "T"      # \u0422
+    "У": "U"      # \u0423
+    "Ү": "Ü"      # \u04ae
+    "Ф": "F"      # \u0424
+    "Х": "H"      # \u0425
+    "Ц": "Ts"     # \u0426
+    "Ч": "Ch"     # \u0427
+    "Ш": "Sh"     # \u0428
+    "Щ": "Shch"   # \u0429
+    "Ъ": "\u2019" # \u042a
+    "Ы": "Ï"      # \u042b
+    "Ь": "Ĭ"      # \u042c
+    "Э": "E"      # \u042d
+    "Ю": "Yu"     # \u042e
+    "Я": "Ya"     # \u042f
+    "а": "a"      # \u0430
+    "б": "b"      # \u0431
+    "в": "v"      # \u0432
+    "г": "g"      # \u0433
+    "д": "d"      # \u0434
+    "е": "yö"     # \u0435
+    "ё": "yo"     # \u0451
+    "ж": "j"      # \u0436
+    "з": "dz"     # \u0437
+    "и": "i"      # \u0438
+    "й": "y"      # \u0439
+    "к": "k"      # \u043a
+    "л": "l"      # \u043b
+    "м": "m"      # \u043c
+    "н": "n"      # \u043d
+    "о": "o"      # \u043e
+    "ө": "ö"      # \u04e9
+    "п": "p"      # \u043f
+    "р": "r"      # \u0440
+    "с": "s"      # \u0441
+    "т": "t"      # \u0442
+    "у": "u"      # \u0443
+    "ү": "ü"      # \u04af
+    "ф": "f"      # \u0444
+    "х": "h"      # \u0445
+    "ц": "ts"     # \u0446
+    "ч": "ch"     # \u0447
+    "ш": "sh"     # \u0448
+    "щ": "shch"   # \u0449
+    "ъ": "\u2019" # \u044a
+    "ы": "ï"      # \u044b
+    "ь": "ĭ"      # \u044c
+    "э": "e"      # \u044d
+    "ю": "yu"     # \u044e
+    "я": "ya"     # \u044f