interscript 0.1.3 → 0.1.9

data/maps/mext-jpn-Hrkt-Latn-1954.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: mext
 id: 1954
-language: jpn
+language: iso-639-2:jpn
 source_script: Hrkt
 destination_script: Latn
 name: 内閣告示第一号 -- ローマ字のつづり方

data/maps/moct-kor-Hang-Latn-2000.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: moct
 id: 2000-viajamo
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: Korean Ministry of Culture and Tourism 2000 System
+alias:
+  ogc11122:
+    code: kor_Hang2Latn_MOCT_2000
+    description: Korean Ministry of Culture and Tourism 2000 System
 url: https://www.korean.go.kr/front_eng/roman/roman_01.do
 creation_date: 2000
 adoption_date: 2002
@@ -91,7 +95,7 @@ map:
   character_separator: ""
   word_separator: " "
   title_case: True
-  inherit: "nil-kor-Hang-Hang-jamo"
+  inherit: "var-kor-Hang-Hang-jamo"
 
   rules:
     # convert numbers to space + Hangul

data/maps/mofa-jpn-Hrkt-Latn-1989.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: mofa
 id: 1989
-language: jpn
+language: iso-639-2:jpn
 source_script: Hrkt
 destination_script: Latn
 name: Hepburn Romanization, Ministry of Foreign Affairs of Japan

data/maps/mv-div-Thaa-Latn-1987.yaml

@@ -0,0 +1,200 @@
+---
+authority_id: mv
+id: 1987
+language: iso-639-2:div
+source_script: Thaa
+destination_script: Latn
+name: Maldivian (Divehi) Maldivian Government 1987 system
+url: https://www.eki.ee/wgrs/rom2_dv.htm
+creation_date: 1887
+description: |
+  In 1987 the Maldivian government adopted a system for the romanization of Maldivian. It was also approved by the BGN and the PCGN in 1988.
+  Maldivian is written from right to left. Vowels are marked as diacritical marks accompanying a consonant character.
+
+notes:
+  - The character އ is not romanized. If it bears a vowel character, that vowel character alone is romanized, e.g. އިރުގައި irugai.
+  - Characters އް and ށް word-finally and before a digraph are romanized h, e.g. ވޭވަށް Veyvah, ކެރެއްދޫ Kerehdhoo. In other cases,
+    when އް and ށް are used, the romanized value of the following consonant character is doubled, e.g. ބައްޓެށް batteh, ކަޅެހުއްޓާ Kalhehuttaa.
+  - The character ނ is romanized n’ if used without any vowel or auxiliary sign. For example kan’du (ކަނޑު).
+  - The character އ is Not romanized but see note 1
+  - Character ތް is romanized iy, e.g. ޒިޔާރަތްފުށި Ziyaaraiyfushi.
+
+tests:
+  - source: "އެނބޫދޫ"
+    expected: "en’boodhoo"
+  - source: "ކަޅެހުއްޓާ"
+    expected: "kalhehuttaa"
+  - source: "ކެރެށްދޫ"
+    expected: "kerehdhoo"
+  - source: "ވޭވައް"
+    expected: "veyvah"
+  - source: "ކަނޑުފުށި"
+    expected: "kan’dufushi"
+  - source: "ޒިޔާރަތްފުށި"
+    expected: "ziyaaraiyfushi"
+  - source: "ރައްކާތެރިކުރުމާއި"
+    expected: "rakkaatherikurumaai"
+  - source: "ދަރިވަރެއްގެވެސް"
+    expected: "dharivareggeves"
+  - source: "ދަރިވަރުންނާއި"
+    expected: "dharivarun’n’aai"
+  - source: "ރަށްރަށުގައި"
+    expected: "rarrashugai"
+  - source: "ޑިޕާޓްމަންޓުން"
+    expected: "dipaatman’tun’"
+  - source: "ހޯދިފައިނުވާ"
+    expected: "hoadhifain’uvaa"
+
+
+map:
+
+  rules:
+    # Note 4
+    - pattern: \u0787\u07b0(?=[ހ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ށ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ނ])
+      result:  "n"
+    - pattern: \u0787\u07b0(?=[ރ])
+      result:  "r"
+    - pattern: \u0787\u07b0(?=[ބ])
+      result:  "b"
+    - pattern: \u0787\u07b0(?=[ޅ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ކ])
+      result:  "k"
+    - pattern: \u0787\u07b0(?=[ވ])
+      result:  "v"
+    - pattern: \u0787\u07b0(?=[މ])
+      result:  "m"
+    - pattern: \u0787\u07b0(?=[ފ])
+      result:  "f"
+    - pattern: \u0787\u07b0(?=[ދ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ތ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ލ])
+      result:  "l"
+    - pattern: \u0787\u07b0(?=[ގ])
+      result:  "g"
+    - pattern: \u0787\u07b0(?=[ޏ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ސ])
+      result:  "s"
+    - pattern: \u0787\u07b0(?=[ޑ])
+      result:  "d"
+    - pattern: \u0787\u07b0(?=[ޖ])
+      result:  "j"
+    - pattern: \u0787\u07b0(?=[ޗ])
+      result:  "h"
+    - pattern: \u0787\u07b0(?=[ޒ])
+      result:  "z"
+    - pattern: \u0787\u07b0(?=[ޓ])
+      result:  "t"
+    - pattern: \u0787\u07b0(?=[ޕ])
+      result:  "p"
+    - pattern: \u0787\u07b0(?=[ޔ])
+      result:  "y"
+
+    - pattern: \u0781\u07b0(?=[ހ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ށ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ނ])
+      result:  "n"
+    - pattern: \u0781\u07b0(?=[ރ])
+      result:  "r"
+    - pattern: \u0781\u07b0(?=[ބ])
+      result:  "b"
+    - pattern: \u0781\u07b0(?=[ޅ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ކ])
+      result:  "k"
+    - pattern: \u0781\u07b0(?=[ވ])
+      result:  "v"
+    - pattern: \u0781\u07b0(?=[މ])
+      result:  "m"
+    - pattern: \u0781\u07b0(?=[ފ])
+      result:  "f"
+    - pattern: \u0781\u07b0(?=[ދ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ތ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ލ])
+      result:  "l"
+    - pattern: \u0781\u07b0(?=[ގ])
+      result:  "g"
+    - pattern: \u0781\u07b0(?=[ޏ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ސ])
+      result:  "s"
+    - pattern: \u0781\u07b0(?=[ޑ])
+      result:  "d"
+    - pattern: \u0781\u07b0(?=[ޖ])
+      result:  "j"
+    - pattern: \u0781\u07b0(?=[ޗ])
+      result:  "h"
+    - pattern: \u0781\u07b0(?=[ޒ])
+      result:  "z"
+    - pattern: \u0781\u07b0(?=[ޓ])
+      result:  "t"
+    - pattern: \u0781\u07b0(?=[ޕ])
+      result:  "p"
+    - pattern: \u0781\u07b0(?=[ޔ])
+      result:  "y"
+
+    - pattern: \u0787\u07b0(?=\b)
+      result:  'h'
+    - pattern: \u0781\u07b0(?=\b)
+      result:  'h'
+
+      # Note 5
+    - pattern: \u0782(?!=[\u07a6\u07a7\u07a8\u07a9\u07aa\u07ab\u07ac\u07ad\u07ae\u07af\u07B0])
+      result: "n’"
+
+    # Note 6
+    - pattern: \u078C(?=\u07B0)
+      result: "iy"
+
+  characters:
+    # Vowels
+    "\u07a6" : "a"
+    "\u07a7" : "aa"
+    "\u07a8" : "i"
+    "\u07a9" : "ee"
+    "\u07aa" : "u"
+    "\u07ab" : "oo"
+    "\u07ac" : "e"
+    "\u07ad" : "ey"
+    "\u07ae" : "o"
+    "\u07af" : "oa"
+    "\u07B0" : "" # not romanized but see notes 4 & 6
+
+
+    # Consonants
+    "ހ": "h"
+    "ށ": "sh" # Note 4
+    "ނ": "n" # Note 5
+    "ރ": "r"
+    "ބ": "b"
+    "ޅ": "lh"
+    "ކ": "k"
+    "އ": "" # Notes 3 & 4
+    "ވ": "v"
+    "މ": "m"
+    "ފ": "f"
+    "ދ": "dh"
+    "ތ": "th" # Note 6
+    "ލ": "l"
+    "ގ": "g"
+    "ޏ": "gn"
+    "ސ": "s"
+    "ޑ": "d"
+    "ޖ": "j"
+    "ޗ": "ch"
+    "ޒ": "z"
+    "ޓ": "t"
+    "ޕ": "p"
+    "ޔ": "y"
+

data/maps/mvd-bel-Cyrl-Latn-2008.yaml

@@ -0,0 +1,225 @@
+---
+authority_id: mvd
+id: 2008
+language: iso-639-2:bel
+source_script: Cyrl
+destination_script: Latn
+name: About approval of the Instructions for transliteration of surnames and proper names of citizens of the Republic of Belarus when their personal data is included in the population register
+url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+creation_date: 2008
+
+description: |
+  RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
+  October 9, 2008, No. 288
+  8/19678 (10.23.2008)
+  About 8/19678 approval of the Instructions for transliteration of surnames and proper names of citizens of
+  the Republic of Belarus when their personal data is included in the population register
+
+notes:
+  # Original notes
+  # - |
+  #   Инструкция по транслитерации фамилий и собственных имен граждан Республики Беларусь при включении
+  #   их персональных данных в регистр населения устанавливает правила передачи с белорусской либо русской формы
+  #   написания на латиницу при включении фамилий и собственных имен граждан Республики Беларусь в регистр населения.
+  # - |
+  #   Передача фамилий и собственных имен граждан Республики Беларусь на латиницу осуществляется с их правильного
+  #   написания на белорусском либо русском языке, за свидетельствованного документами, удостоверяющими личность.
+  # - Передача фамилий и собственных имен граждан Республики Беларусь осуществляется путем транслитерации
+  #   литер (букв, знаков) белорусского либорусского написания соответствующими литерами латиницы.
+  # - Транслитерацией достигается общность и унифицированность системы латинизированного написания,
+  #   позволяющей пользоваться ею во всех латинопишущих государствах.
+  # - Смягчение согласной буквы, обозначенное мягким знаком, в белорусской латинице следует показывать
+  #   диакритическим знаком (́), который располагается над соответствующей буквой: дзь – dź, зь – ź, ль – ĺ,
+  #   нь – ń, сь – ś, ць – ć.
+  # - Правила транслитерации букв белорусского и русского алфавитов соответствующими буквами латиницы
+  #   приведены в таблице транслитерации букв белорусского и русского алфавитов буквами латиницы соглас
+  #   но приложению к настоящей Инструкции.
+  # - Сложные и составные фамилии и собственные имена, пишущиеся слитно, раздельно или через дефис,
+  #   сохраняют слитное, раздельное или дефисное написание и в латинице.
+  - | # 1
+    Instructions for transliterating the names and first names of citizens of the Republic of Belarus
+    when including their personal data in the population register sets the rules for transferring
+    from the Belarusian or Russian form of writing in Latin when including the names and first names
+    of citizens of the Republic of Belarus in the population register.
+  - | # 2
+    Transfer of surnames and proper names of citizens of the Republic of Belarus to the Latin alphabet
+    is carried out with their correct spelling in Belarusian or Russian, for evidence of identity documents.
+  - | # 3
+    The transfer of surnames and proper names of citizens of the Republic of Belarus is carried out by
+    transliteration of the letters (letters, signs) of the Belarusian or Russian spelling in the corresponding
+    Latin letters.
+  - | # 4
+    Transliteration achieves the generality and unification of the system of Latinized writing,
+    which allows it to be used in all Latin-writing countries.
+  - | # 5
+    The softening of the consonant, indicated by a soft sign, in the Belarusian Latin should be shown
+    with a diacritic mark (́), which is located above the corresponding letter:
+      дзь - dź,
+      зь - ź,
+      ль - ĺ,
+      нь - ń,
+      сь - ś,
+      ць - ć.
+  # 6
+  - The rules for transliterating letters of the Belarusian and Russian alphabets with the corresponding
+    letters of the Latin alphabet are given in the table of transliteration of letters of the Belarusian
+    and Russian alphabets with the Latin letters according to the appendix to this Instruction.
+  # 7
+  - Compound and compound surnames and proper names, spelled together, separately or through a hyphen,
+    keep a single, separate or hyphen spelling in Latin.
+
+tests:
+  - source: Ева
+    expected: Jeva
+  - source: Васiльева
+    expected: Vasiĺjeva
+  - source: Васiлёнак
+    expected: Vasilionak
+  - source: Ёрш
+    expected: Jorsh
+  - source: Вераб’ёў
+    expected: Vierabjow
+  - source: Салаўёва
+    expected: Salawjova
+  - source: Любоў
+    expected: Liubow
+  - source: В’юноў
+    expected: Vjunow
+  - source: Чарняк
+    expected: Charniak
+  - source: Лябецкая
+    expected: Liabietskaja # in reference doc it's Liabetskaja CAMOBAP waiting confirmation from officials
+  - source: Дар’я
+    expected: Darja
+
+map:
+  rules:
+    - pattern: (\u2019\u0415) # Е
+      result: Je
+    - pattern: (\u2019\u0435) # е
+      result: je
+    - pattern: (\u2019\u0401) # Ë
+      result: Jo
+    - pattern: (\u2019\u0451) # ё
+      result: jo
+    - pattern: (\u2019\u042E) # Ю
+      result: Ju
+    - pattern: (\u2019\u044E) # ю
+      result: ju
+    - pattern: (\u2019\u042F) # Я
+      result: Ja
+    - pattern: (\u2019\u044F) # я
+      result: ja
+
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u0415 # Е after vowels
+      result: Je
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u0435 # е after vowels
+      result: je
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u0401 # Ё after vowels
+      result: Jo
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u0451 # ё after vowels
+      result: jo
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u042E # Ю after vowels
+      result: Ju
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u044E # ю after vowels
+      result: ju
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u042F # Я after vowels
+      result: Ja
+    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЬьЎў])\u044F # я after vowels
+      result: ja
+
+    # note[5]
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u044C # ь after consonants
+      result: "\\1\u0301"
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u02B9 # Ь after consonants
+      result: "\\1\u0301"
+
+    # vowels initially
+    - pattern: \b\u0415 # Е
+      result: Je
+    - pattern: \b\u0435 # е
+      result: je
+    - pattern: \b\u0401 # Ё
+      result: Jo
+    - pattern: \b\u0451 # ё
+      result: jo
+    - pattern: \b\u042E # Ю
+      result: Ju
+    - pattern: \b\u044E # ю
+      result: ju
+    - pattern: \b\u042F # Я
+      result: Ja
+    - pattern: \b\u044F # я
+      result: ja
+
+  postrules:
+    - pattern: \u2019
+      result: j
+
+  characters:
+
+    '\u0410' : 'A'  # А
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'G'  # Г
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'Ie' # Е or JE TODO add rule
+    '\u0401' : 'Io' # Ё or JO TODO add rule
+    '\u0416' : 'Zh' # Ж
+    '\u0417' : 'Z'  # З
+    '\u0406' : 'I'  # І
+    '\u0419' : "J"  # Й
+    '\u041A' : 'K'  # К
+    '\u041B' : 'L'  # Л
+    '\u041C' : 'M'  # М
+    '\u041D' : 'N'  # Н
+    '\u041E' : 'O'  # О
+    '\u041F' : 'P'  # П
+    '\u0420' : 'R'  # Р
+    '\u0421' : 'S'  # С
+    '\u0422' : 'T'  # Т
+    '\u0423' : 'U'  # У
+    '\U040E' : 'W'  # Ў
+    '\u0424' : 'F'  # Ф
+    '\u0425' : 'Kh' # Х
+    '\u0426' : 'Ts' # Ц
+    '\u0427' : 'Ch' # Ч
+    '\u0428' : 'Sh' # Ш
+    '\u0429' : 'Shch' # Щ
+    '\u042B' : 'Y'  # Ы
+    '\u042D' : 'E'  # Э
+    '\u042E' : "Iu" # Ю
+    '\u042F' : "Ia" # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'g'  # г
+    '\u0434' : 'd'  # д
+    '\u0435' : 'ie' # е
+    '\u0451' : 'io' # ё
+    '\u0436' : 'zh' # ж
+    '\u0437' : 'z'  # з
+    '\u0456' : 'i'  # і
+    '\u0439' : 'j'  # й
+    '\u043A' : 'k'  # к
+    '\u043B' : 'l'  # л
+    '\u043C' : 'm'  # м
+    '\u043D' : 'n'  # н
+    '\u043E' : 'o'  # о
+    '\u043F' : 'p'  # п
+    '\u0440' : 'r'  # р
+    '\u0441' : 's'  # с
+    '\u0442' : 't'  # т
+    '\u0443' : 'u'  # у
+    '\u045E' : 'w'  # ў
+    '\u0444' : 'f'  # ф
+    '\u0445' : 'kh' # х
+    '\u0446' : 'ts' # Ц
+    '\u0447' : 'ch' # ч
+    '\u0448' : 'sh' # ш
+    '\u0449' : 'shch' # щ
+    '\u044B' : 'y'  # ы
+    '\u044D' : 'e'  # э
+    '\u044E' : "iu" # ю
+    '\u044F' : "ia" # я