interscript-maps 2.0.5

data/maps/odni-tat-Cyrl-Latn-2015.imp

@@ -0,0 +1,157 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:tat
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of tatar personal names in written reports and products
+  source: ICS-630-01 Annex S
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Tatar 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 Tatar 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:
+    Rustam Abdrashitov (also seen as Rustem Abdrashitov, Рустам Абдрашитов). 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 Tatar-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 {
+  test "Рустам Абдрашитов", "Rustam Abdrashitov"
+}
+
+stage {
+
+  # RULES
+  # note[1]
+  # generated with: "ЁЖҢХЦЧШЩЮЯ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub capture(any("Ёё"))+any("Ёё"), ref(1)
+  sub capture(any("Жж"))+any("Жж"), ref(1)
+  sub capture(any("Ңң"))+any("Ңң"), ref(1)
+  sub capture(any("Хх"))+any("Хх"), ref(1)
+  sub capture(any("Цц"))+any("Цц"), ref(1)
+  sub capture(any("Чч"))+any("Чч"), ref(1)
+  sub capture(any("Шш"))+any("Шш"), ref(1)
+  sub capture(any("Щщ"))+any("Щщ"), ref(1)
+  sub capture(any("Юю"))+any("Юю"), ref(1)
+  sub capture(any("Яя"))+any("Яя"), ref(1)
+  # note[3]
+  sub any("\u044A\u044C"), none
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u04D8", "A" # Ә
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0496", "J" # Җ
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u04A2", "Ng" # Ң
+    sub "\u041E", "O" # О
+    sub "\u04E8", "O" # Ө
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "U" # У
+    sub "\u04AE", "U" # Ү
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u04BA", "H" # Һ
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u0429", "Shch" # Щ
+    sub "\u042B", "Y" # Ы
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+
+    sub "\u0430", "a" # а
+    sub "\u04D9", "a" # ә
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0497", "j" # җ
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u04A3", "ng" # ң
+    sub "\u043E", "o" # о
+    sub "\u04E9", "o" # ө
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у
+    sub "\u04AF", "u" # ү
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u04BB", "h" # һ
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u0449", "shch" # щ
+    sub "\u044B", "y" # ы
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}

data/maps/odni-tgk-Cyrl-Latn-2015.imp

@@ -0,0 +1,161 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:tgk
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of tajik personal names in written reports and products
+  source: ICS-630-01 Annex N
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Tajik 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 Tajik 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:
+    Parvona Jamshedov (also seen as Parvona Dzhamshedov, Парвона Ҷамшедов). 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 Tajik-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 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.
+    - Transliterate ‘е‘ as ‘ye’ at beginning of words, ‘e’ elsewhere
+}
+
+tests {
+  test "Парвона Ҷамшедов", "Parvona Jamshedov"
+}
+
+stage {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁЖХЧШЮЯЦЩ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub capture(any("Ғғ"))+any("Ғғ"), ref(1)
+  sub capture(any("Ёё"))+any("Ёё"), ref(1)
+  sub capture(any("Жж"))+any("Жж"), ref(1)
+  sub capture(any("Хх"))+any("Хх"), ref(1)
+  sub capture(any("Чч"))+any("Чч"), ref(1)
+  sub capture(any("Шш"))+any("Шш"), ref(1)
+  sub capture(any("Юю"))+any("Юю"), ref(1)
+  sub capture(any("Яя"))+any("Яя"), ref(1)
+  sub capture(any("Цц"))+any("Цц"), ref(1)
+  sub capture(any("Щщ"))+any("Щщ"), ref(1)
+  # note[3]
+  sub any("\u044A\u044C"), none
+  # note[4]
+  sub boundary+"\u0415", "Ye"
+  sub boundary+"\u0435", "ye"
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0492", "Gh" # Ғ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u04E2", "I" # Ӣ
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u049A", "Q" # Қ
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u041E", "O" # О
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "U" # У
+    sub "\u04EE", "U" # Ӯ
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u04B2", "H" # Ҳ
+    sub "\u0427", "Ch" # Ч
+    sub "\u04B6", "J" # Ҷ
+    sub "\u0428", "Sh" # Ш
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+    sub "\u0426", "Ts" # Ц
+    sub "\u0429", "Shch" # Щ
+    sub "\u042B", "Y" # Ы
+
+    sub "\u0430", "a" # а
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0493", "gh" # ғ
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u04E3", "i" # ӣ
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u049B", "q" # қ
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u043E", "o" # о
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у
+    sub "\u04EF", "u" # ӯ
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u04B3", "h" # ҳ
+    sub "\u0447", "ch" # ч
+    sub "\u04B7", "j" # ҷ
+    sub "\u0448", "sh" # ш
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+    sub "\u0446", "ts" # ц
+    sub "\u0449", "shch" # щ
+    sub "\u044B", "y" # ы
+  }
+
+}

data/maps/odni-tuk-Cyrl-Latn-2015.imp

@@ -0,0 +1,159 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:tuk
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of Turkmen personal names in written reports and products
+  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20T%20-%20Turkmen_Personal_Names_FLTS%20(U).pdf
+  source: ICS-630-01 Annex T
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Turkmen 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 Turkmen 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:
+    Azat Muhadov (also seen as Azat Muhadow, Азат Мухадов). 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 Turkmen-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 {
+  test "Акгюль", "Akgyul"
+  test "Акгыз", "Akgyz"
+  test "Арсланбек", "Arslanbek"
+  test "Берди", "Berdi"
+  test "Дидар", "Didar"
+  test "Гөзел", "Gozel"
+  test "Гуля", "Gulya"
+  test "Гюля", "Gyulya"
+  test "Мәхри", "Mahri"
+  test "Майса", "Maysa"
+  test "Мырат", "Myrat"
+  test "Өвез", "Ovez"
+  test "Рашит", "Rashit"
+  test "Сапармырат", "Saparmyrat"
+}
+
+stage {
+
+  # RULES
+  sub "шш", "sh" # шш -> sh
+  sub "Шш", "Sh" # Шш -> Sh
+  sub "ШШ", "SH" # ШШ -> SH
+  sub "шШ", "sH" # шШ -> sH
+  sub any("Ьь"), none # remove Ь and ь
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0496", "J" # җ
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u04A2", "Ng" # Ң
+    sub "\u041E", "O" # О
+    sub "\u04E8", "O" # Ө
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "U" # У
+    sub "\u04AE", "U" # Ү
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "H" # Х
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u0429", "Shch" # Щ
+    sub "\u042B", "Y" # Ы
+    sub "\u042D", "E" # Э
+    sub "\u04D8", "A" # Ә
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+
+    sub "\u0430", "a" # а
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # е
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0497", "j" # җ
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u04A3", "ng" # ң
+    sub "\u043E", "o" # о
+    sub "\u04E9", "o" # ө
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у
+    sub "\u04AF", "u" # ү
+    sub "\u0444", "f" # ф
+    sub "\u0445", "h" # х
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u0449", "shch" # щ
+    sub "\u044B", "y" # ы
+    sub "\u044D", "e" # э
+    sub "\u04D9", "a" # ә
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}