interscript 0.1.3 → 0.1.4

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

@@ -0,0 +1,110 @@
+---
+authority_id: mvd
+id: 19678
+language: rus
+source_script: Cyrl
+destination_script: Latn
+name: 8/19678 On 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
+
+notes:
+  - check notes from mvd-bel-Cyrl-Latn-2008
+
+tests:
+  - source: Ева
+    expected: Eva
+  - source: Васiльева
+    expected: Vasiĺeva
+  - source: Адъютантов
+    expected: Adjutantov
+
+map:
+  rules:
+    # note[5]
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u044C # ь after consonants
+      result: "\\1\u0301"
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u02B9 # Ь after consonants
+      result: "\\1\u0301"
+    - pattern: ([’Ъъ]\u042E)
+      result: Ju
+    - pattern: ([’Ъъ]\u044E)
+      result: ju
+    - pattern: ([’Ъъ]\u042F)
+      result: Ja
+    - pattern: ([’Ъъ]\u044F)
+      result: ja
+
+  characters:
+    '’' : 'j'
+
+    '\u0410' : 'A'  # А
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'G'  # Г
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'E'  # Е
+    '\u0401' : 'E'  # Ё
+    '\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
+    '\u042A' : 'J'  # Ъ
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : ''   # Ь
+    '\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' : 'e'  # е
+    '\u0451' : 'e'  # 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
+    '\u044A' : 'j'  # ъ
+    '\u044B' : 'y'  # ы
+    '\u044C' : ''   # ь
+    '\u044D' : 'e'  # э
+    '\u044E' : 'iu' # ю
+    '\u044F' : 'ia' # я
+

data/maps/mvd-rus-Cyrl-Latn-2010.yaml

@@ -0,0 +1,37 @@
+---
+authority_id: mvd
+id: 22721
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: |
+  8/22721 On approval of the Instructions on the organization of work of units of citizenship 
+  and migration of internal affairs bodies on the issuance, registration, exchange, 
+  invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+url: https://pravo.by/document/?guid=3871&p0=W21022721
+creation_date: 2010
+
+description: |
+  RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
+  June 28, 2010 No. 200
+  On approval of the Instructions on the organization of work of units of citizenship 
+  and migration of internal affairs bodies on the issuance, registration, exchange, 
+  invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+
+notes:
+  - check notes from mvd-rus-Cyrl-Latn-2008
+
+tests:
+  - source: Ева
+    expected: Eva
+  - source: Васiльева
+    expected: Vasileva
+  - source: Адъютантов
+    expected: Adjutantov
+
+map:
+  inherit: "mvd-rus-Cyrl-Latn-2008"
+
+  postrules:
+    - pattern: \u0301 # remove diacritics
+      result: ""

data/maps/odni-bel-Cyrl-Latn-2015.yaml

@@ -0,0 +1,148 @@
+---
+authority_id: odni
+id: 2015
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Belarusian Personal Names 2015, ICS 630-01 Annex B
+# url:
+source: ICS 630-01, Annex B
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the transliteration of Belarusian
+  names that will be applied to all final written reports and products for IC consumers. It is not
+  intended to eliminate variations of a name that can contribute forensic information. Rather, it is to
+  provide an IC standard Romanized (English) transliteration from Belarusian that can then be
+  linked to forensic information in ways that will help identify the referent of the name.
+  
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the first
+  usage. In addition, if the original Cyrillic spelling is known, that spelling should also appear in
+  parentheses following the name, if possible, following best practices of the issuing organization
+  and taking into consideration information system capabilities. This convention is designed to
+  ensure that vital forensic information is not lost.
+
+  For names of persons who are known to not be part of the Belarusian-speaking community, use
+  the relevant IC transliteration standard for names from that language (e.g., Mikhail, Yitzhak). A
+  translator’s note may be used to clarify the known origin of the person. Spell names of
+  individuals from languages that are written in Roman letters as they are spelled in those
+  languages (e.g., George Clooney, Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the online directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings
+  given in these on-line reference works should be used in place of the IC Standard. For any
+  individual who has at one time been listed in the Factbook or Chiefs of State directory but who no
+  longer appears in those resources (i.e. is no longer a government official), the IC Standard
+  spelling should appear first, with the spelling, if known, as it previously appeared in those
+  resources listed within parentheses at the first usage.
+
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+  (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
+  of diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name
+
+notes:
+
+tests:
+  - source: Міхаіл
+    expected: Mikhail
+  - source: Беларусь
+    expected: Byelarus
+  - source: Кастусь Каліноўскі
+    expected: Kastus Kalinowski
+  - source: Васіль Быкау
+    expected: Vasil Bykau
+  - source: Янка Купала
+    expected: Yanka Kupala
+  - source: Маланка
+    expected: Malanka
+  - source: Пакаранне
+    expected: Pakarannye
+  - source: Бэз
+    expected: Bez
+  - source: Чабор
+    expected: Chabor
+  - source: |
+      Дзяўчына, дзяўчыначка пасярод гісторыі
+      З прастадушнай шчырасьцю глядзіць на тэрыторыю.
+      У вакне заўсёды звыклая выява:
+      Шэры двор, шэры слуп, на слупе аб'явы.
+    expected: |
+      Dzyawchyna, dzyawchynachka pasyarod historyi
+      Z prastadushnay shchyrastsyu hlyadzits na terytoryyu.
+      U vaknye zawsyody zvyklaya vyyava:
+      Shery dvor, shery slup, na slupye abyavy.
+
+map:
+  characters:
+    '\u0027' : ''   # '
+
+    '\u0410' : 'A'  # A
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'H'  # Г
+    '\u0490' : 'G'  # Ґ
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'Ye' # Е
+    '\u0401' : 'Yo' # Ё
+    '\u0416' : 'Zh' # Ж
+    '\u0417' : 'Z'  # З
+    '\u0406' : 'I'  # І
+    '\u0419' : 'Y'  # 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
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : ''   # Ь
+    '\u042D' : 'E'  # Э
+    '\u042E' : 'Yu' # Ю
+    '\u042F' : 'Ya' # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'h'  # г
+    '\u0491' : 'g'  # ґ
+    '\u0434' : 'd'  # д
+    '\u0435' : 'ye' # е
+    '\u0451' : 'yo' # ё
+    '\u0436' : 'zh' # ж
+    '\u0437' : 'z'  # з
+    '\u0456' : 'i'  # і
+    '\u0439' : 'y'  # 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
+    '\u044B' : 'y'  # ы
+    '\u044c' : ''   # Ь
+    '\u044D' : 'e'  # э
+    '\u044E' : 'yu' # ю
+    '\u044F' : 'ya' # я

data/maps/odni-bul-Cyrl-Latn-2015.yaml

@@ -0,0 +1,96 @@
+---
+authority_id: odni
+id: 2015
+language: bul
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Bulgarian Personal Names 2015, ICS-630-01 Annex O
+# url:
+source: ICS-630-01 Annex O
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Bulgarian person
+  names that will be applied to all final written reports and products for IC consumers. This
+  standard matches both the Bulgarian national standard adopted in 2009 and the Board of
+  Geographic Names / Permanent Committee on Geographic Names standard adopted in 2013. It is
+  not intended to eliminate variations of a name that can contribute forensic information. Rather, it
+  is to provide an IC standard Romanized (English) transliteration from Bulgarian that can then be
+  linked to forensic information in ways that will help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the first
+  usage. In addition, if the original Cyrillic-script spelling is known, that spelling should also
+  appear in parentheses following the name, if possible, following best practices of the issuing
+  organization and taking into consideration information system capabilities. For example: Dobri
+  Hristov (also seen as Dobri Khristov, Добри Христов). This convention is designed to ensure
+  that vital forensic information is not lost.
+
+  For names of persons who are known to not be part of the Bulgarian-speaking community, use
+  the relevant IC transliteration standard for names from that language (e.g., Yitzhak). A
+  translator’s note may be used to clarify the known origin of the person. Spell names of
+  individuals from languages that are written in Roman letters as they are spelled in those
+  languages (e.g., George Clooney, Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the online directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings
+  given in these on-line reference works should be used in place of the IC Standard. For any
+  individual who has at one time been listed in the Factbook or Chiefs of State directory but who no
+  longer appears in those resources (i.e. is no longer a government official), the IC Standard
+  spelling should appear first, with the spelling, if known, as it previously appeared in those
+  resources listed within parentheses at the first usage.
+
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+  (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
+  of diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
+  names of well-known individuals.
+
+notes:
+  - Transliterate double digraphs as a single digraph i.e. шш -> sh, not shsh
+  - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters (e.g. 's' followed by 'h').
+
+tests:
+
+  - source: Добри Христов
+    expected: Dobri Khristov
+  - source: болгарица
+    expected: bolgaritsa
+  - source: български език
+    expected: balgarski ezik
+  - source: българска азбука
+    expected: balgarska azbuka
+  - source: градъ
+    expected: grad
+  - source: аз държа
+    expected: az darzha
+  - source: Ядеш хляба с чубрица
+    expected: Yadesh khlyaba s chubritsa
+
+    
+  # note[1]
+  - source: шш
+    expected: sh
+  - source: ччччч
+    expected: ch
+
+map:
+  inherit: bgnpcgn-bul-Cyrl-Latn-2013
+
+  rules:
+    # note[1]
+    - pattern: "(.)\\1{1,}"
+      result: "\\1"
+
+    - pattern: \u042C# # Ь
+      result: "Y"
+      
+    - pattern: \u042A # Ъ
+      result: "A"
+      
+    - pattern: \u044C # ь
+      result: "y"
+
+    - pattern: \u044A # ъ
+      result: "a"

data/maps/odni-kat-Geor-Latn-2015.yaml

@@ -4,7 +4,7 @@ id: 2015
 language: kat
 source_script: Geor
 destination_script: Latn
-name: Office of the Director Of National Intelligence Georgian Personal Names 2015
+name: Office of the Director Of National Intelligence Georgian Personal Names 2015, ICS 630-01 Annex E
 # url:
 source: ICS 630-01, Annex E
 creation_date: 2015

data/maps/odni-rus-Cyrl-Latn-2015.yaml

@@ -0,0 +1,77 @@
+---
+authority_id: odni
+id: 2015
+language: rus
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Russian Personal Names 2015, ICS-630-01 Annex K
+# url:
+source: ICS-630-01 Annex K
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system, adapted from the Board of Geographic Names (BGN) Romanization system for Russian
+  (1947), is the Intelligence Community (IC) standard for the transliteration of Russian names that will be
+  applied to all final written reports and products for IC consumers. It is not intended to eliminate variations
+  of a name that can contribute forensic information. Rather, it is to provide an IC standard Romanized
+  (English) transliteration from Russian that can then be linked to forensic information in ways that will
+  help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC Standard
+  spelling should appear first, followed by the variant spelling(s) in parentheses at the first usage. E.g.,
+  Sergey Nikolayevich Tyurin (Serguei Nicolaivitch Tiourine). In addition, if the original Cyrillic spelling
+  is known, that spelling should also appear in parentheses following the name, if possible, following best
+  practices of the issuing organization and taking into consideration information system capabilities. This
+  convention is designed to ensure that vital forensic information is not lost.
+
+  For non-Russian names, use the relevant IC transliteration standard for names from that language. A
+  translator’s note may be used to clarify the known origin of the person. Spell names of individuals from
+  languages that are written in Roman letters as they are spelled in those languages (e.g., George Clooney,
+  Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the on-line
+  directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings given in these
+  on-line reference works should be used in place of the IC Standard. For any individual who has at one
+  time been listed in the Factbook or Chiefs of State directory but who no longer appears in those resources
+  (i.e. is no longer a government official), the IC Standard spelling should appear first, with the spelling, if
+  known, as it previously appeared in those resources listed within parentheses at the first usage.
+  
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically readable
+  to the English-speaking non-specialist. The system uses the 26 letters of the standard (English) Roman
+  alphabet. Some ambiguities in the Romanized form will occur without the use of diacritics. However,
+  within the context of a report, where additional information about the individual is provided, the referent
+  will be clearly identified. This system will be used in conjunction with on-line tools, name dictionaries,
+  and lists containing conventional spellings of names of well-known individuals.
+
+notes:
+
+tests:
+  - source: Ирина Ивановна Никитина
+    expected: Irina Ivanovna Nikitina
+  - source: Николай Римский-Корсаков
+    expected: Nikolay Rimskiy-Korsakov
+  - source: Михаил Тимофеевич Калашников
+    expected: Mikhail Timofeyevich Kalashnikov
+  - source: Корж Василий Захарович
+    expected: Korzh Vasiliy Zakharovich
+  - source: Циолковский Константин Эдуардович
+    expected: Tsiolkovskiy Konstantin Eduardovich
+  - source: Лобачевский Николай Иванович
+    expected: Lobachevskiy Nikolay Ivanovich
+  - source: Пушкин Александр Сергеевич
+    expected: Pushkin Aleksandr Sergeyevich
+  - source: Гоголь Николай Васильевич
+    expected: Gogol Nikolay Vasilyevich
+  - source: Ломоносов Михаил Васильевич
+    expected: Lomonosov Mikhail Vasilyevich
+
+map:
+  inherit: bgnpcgn-rus-Cyrl-Latn-1947
+
+  characters:
+    '\u042a': '' # Ъ
+    '\u042c': '' # Ь
+
+
+    '\u044a': '' # ъ
+    '\u044c': '' # ь