interscript 0.1.0 → 0.1.5

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

@@ -0,0 +1,144 @@
+---
+authority_id: odni
+id: 2015
+language: aze
+source_script: Cyrl
+destination_script: Latn
+name: Standards for the transliteration of azeri personal names in written reports and products
+source: ICS-630-01 Annex P
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Azeri person 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 Azeri 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:
+  Rashad Sadykhov (also seen as Rashad Sadigov, Рашад Садыхов). 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 Azeri-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 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:
+  - 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').
+  - The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration.
+
+tests:
+  - source: Рашад Садыхов
+    expected: Rashad Sadykhov
+
+map:
+  rules:
+    # note[1]
+    - pattern: "(?i)(\u0492|\u0401|\u0416|\u0425|\u0427|\u0428|\u0429|\u042E|\u042F)\\1(?-i)"
+      result: "\\1"
+    # note[3]
+    - pattern: \u044A|\u044C
+      result: ""
+
+  characters:
+    '\u0410': 'A'      # А
+    '\u0411': 'B'      # Б
+    '\u0412': 'V'      # В
+    '\u0413': 'G'      # Г
+    '\u049C': 'G'      # Ҝ
+    '\u0492': 'Gh'     # Ғ
+    '\u0414': 'D'      # Д
+    '\u0415': 'E'      # Е
+    '\u0401': 'Yo'     # Ё
+    '\u04D8': 'A'      # Ә
+    '\u0416': 'Zh'     # Ж
+    '\u0417': 'Z'      # З
+    '\u0418': 'I'      # И
+    '\u0419': 'Y'      # Й
+    '\u0408': 'Y'      # Ј
+    '\u041A': 'K'      # К
+    '\u041B': 'L'      # Л
+    '\u041C': 'M'      # М
+    '\u041D': 'N'      # Н
+    '\u041E': 'O'      # О
+    '\u04E8': 'O'      # Ө
+    '\u041F': 'P'      # П
+    '\u0420': 'R'      # Р
+    '\u0421': 'S'      # С
+    '\u0422': 'T'      # Т
+    '\u0423': 'U'      # У
+    '\u04AE': 'U'      # Ү
+    '\u0424': 'F'      # Ф
+    '\u0425': 'Kh'     # Х
+    '\u04BA': 'H'      # Һ
+    '\u0427': 'Ch'     # Ч
+    '\u04B8': 'J'      # Ҹ
+    '\u0428': 'Sh'     # Ш
+    '\u0429': 'Shch'   # Щ
+    '\u042B': 'Y'      # Ы
+    '\u042D': 'E'      # Э
+    '\u042E': 'Yu'     # Ю
+    '\u042F': 'Ya'     # Я
+
+    '\u0430': 'a'      # а
+    '\u0431': 'b'      # б
+    '\u0432': 'v'      # в
+    '\u0433': 'g'      # г
+    '\u049D': 'g'      # ҝ
+    '\u0493': 'gh'     # ғ
+    '\u0434': 'd'      # д
+    '\u0435': 'e'      # e
+    '\u0451': 'yo'     # ё
+    '\u04D9': 'a'      # ә
+    '\u0436': 'zh'     # ж
+    '\u0437': 'z'      # з
+    '\u0438': 'i'      # и
+    '\u0439': 'y'      # й
+    '\u0458': 'y'      # ј
+    '\u043A': 'k'      # к
+    '\u043B': 'l'      # л
+    '\u043C': 'm'      # м
+    '\u043D': 'n'      # н
+    '\u043E': 'o'      # о
+    '\u04E9': 'o'      # ө
+    '\u043F': 'p'      # п
+    '\u0440': 'r'      # р
+    '\u0441': 's'      # с
+    '\u0442': 't'      # т
+    '\u0443': 'u'      # у
+    '\u04AF': 'u'      # ү
+    '\u0444': 'f'      # ф
+    '\u0445': 'kh'     # х
+    '\u04BB': 'h'      # һ
+    '\u0447': 'ch'     # ч
+    '\u04B9': 'j'      # ҹ
+    '\u0448': 'sh'     # ш
+    '\u0449': 'shch'   # щ
+    '\u044B': 'y'      # ы
+    '\u044D': 'e'      # э
+    '\u044E': 'yu'     # ю
+    '\u044F': 'ya'     # я

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

@@ -0,0 +1,88 @@
+---
+authority_id: odni
+id: 2015
+language: kat
+source_script: Geor
+destination_script: Latn
+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
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Georgian 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 Georgian that can then be linked to forensic
+  information in ways that will help identify the referent of the name.
+
+notes:
+
+tests:
+
+  - source: ბაყაყი
+    expected: baqaqi
+
+  - source: ძროხა
+    expected: dzrokha
+
+  - source: ჰაერი
+    expected: haeri
+
+  - source: ჟოლო
+    expected: zholo
+
+  - source: ჯართი
+    expected: jarti
+
+  - source: ღრმაღელე
+    expected: ghrmaghele
+
+  - source: ზვიად გამსახურდია
+    expected: zviad gamsakhurdia
+
+  - source: ედუარდ შევარდნაძე
+    expected: eduard shevardnadze
+
+  - source: მიხეილ სააკაშვილი
+    expected: mikheil saakashvili
+
+  - source: გიორგი მარგველაშვილი
+    expected: giorgi margvelashvili
+
+map:
+  characters:
+    '\u10d0' : 'a' # ა
+    '\u10d1' : 'b' # ბ
+    '\u10d2' : 'g' # გ
+    '\u10d3' : 'd' # დ
+    '\u10d4' : 'e' # ე
+    '\u10d5' : 'v' # ვ
+    '\u10d6' : 'z' # ზ
+    '\u10d7' : 't' # თ
+    '\u10d8' : 'i' # ი
+    '\u10d9' : 'k' # კ
+    '\u10da' : 'l' # ლ
+    '\u10db' : 'm' # მ
+    '\u10dc' : 'n' # ნ
+    '\u10dd' : 'o' # ო
+    '\u10de' : 'p' # პ
+    '\u10df' : 'zh' # ჟ
+    '\u10e0' : 'r' # რ
+    '\u10e1' : 's' # ს
+    '\u10e2' : 't' # ტ
+    '\u10e3' : 'u' # უ
+    '\u10e4' : 'p' # ფ
+    '\u10e5' : 'k' # ქ
+    '\u10e6' : 'gh' # ღ
+    '\u10e7' : 'q' # ყ
+    '\u10e8' : 'sh' # შ
+    '\u10e9' : 'ch' # ჩ
+    '\u10ea' : 'ts' # ც
+    '\u10eb' : 'dz' # ძ
+    '\u10ec' : 'ts' # წ
+    '\u10ed' : 'ch' # ჭ
+    '\u10ee' : 'kh' # ხ
+    '\u10ef' : 'j' # ჯ
+    '\u10f0' : 'h' # ჰ
+