interscript-maps 2.4.3 → 2.5.0

data/maps/{odni-srp-Cyrl-Latn-2015.imp → odni-srp-Cyrl-Latn-2015.isc}

@@ -1,15 +1,16 @@
+system "ODNI:srp-Cyrl:Latn:2015" {
+
 metadata {
-  authority_id: odni
-  id: 2015
-  language: iso-639-2:srp
-  source_script: Cyrl
-  destination_script: Latn
-  name: ICS-630-01 Romanization of Serbian Personal Names (2015)
-  source: ICS-630-01 Annex L
-  creation_date: 2015
-  confirmation_date: 2015
-  description: |
-    This system is the Intelligence Community (IC) standard for the transliteration of Serbian names
+  authority_id odni
+  id 2015
+  language iso-639-2:srp
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Serbian Personal Names (2015)
+  source ICS-630-01 Annex L
+  creation_date 2015
+  confirmation_date 2015
+  description {    This system is the Intelligence Community (IC) standard for the transliteration of Serbian names
     written in Cyrillic 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 Serbian that can then be
@@ -42,87 +43,90 @@ metadata {
     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:
+  notes {
+  }
 }
 
 tests {
-  test "Гојко Митић", "Gojko Mitic"
-  test "Горња Ваганица", "Gornja Vaganica"
-  test "Довиђења", "Dovidjenja"
-  test "Ћао! Здраво!", "Cao! Zdravo!"
-  test "Кључ", "Kljuc"
-  test "Цигарете", "Cigarete"
-  test "Пролеће", "Prolece"
-  test "Понедељак", "Ponedeljak"
+   "Гојко Митић" ->  "Gojko Mitic"
+   "Горња Ваганица" ->  "Gornja Vaganica"
+   "Довиђења" ->  "Dovidjenja"
+   "Ћао! Здраво!" ->  "Cao! Zdravo!"
+   "Кључ" ->  "Kljuc"
+   "Цигарете" ->  "Cigarete"
+   "Пролеће" ->  "Prolece"
+   "Понедељак" ->  "Ponedeljak"
 }
 
-stage {
+stage main {
 
   # CHARACTERS
   parallel {
-    sub "\u0410", "A" # А
-    sub "\u0411", "B" # Б
-    sub "\u0412", "V" # В
-    sub "\u0413", "G" # Г
-    sub "\u0414", "D" # Д
-    sub "\u0402", "Dj" # Ђ
-    sub "\u0415", "E" # Е
-    sub "\u0416", "Z" # Ж
-    sub "\u0417", "Z" # З
-    sub "\u0418", "I" # И
-    sub "\u0408", "J" # Ј
-    sub "\u041A", "K" # К
-    sub "\u041B", "L" # Л
-    sub "\u0409", "Lj" # Љ
-    sub "\u041C", "M" # М
-    sub "\u041D", "N" # Н
-    sub "\u040A", "Nj" # Њ
-    sub "\u041E", "O" # О
-    sub "\u041F", "P" # П
-    sub "\u0420", "R" # Р
-    sub "\u0421", "S" # С
-    sub "\u0422", "T" # Т
-    sub "\u040B", "C" # Ћ
-    sub "\u0423", "U" # У
-    sub "\u0424", "F" # Ф
-    sub "\u0425", "H" # Х
-    sub "\u0426", "C" # Ц
-    sub "\u0427", "C" # Ч
-    sub "\u040F", "Dz" # Џ
-    sub "\u0428", "S" # Ш
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0402" "Dj"
+    sub "\u0415" "E"
+    sub "\u0416" "Z"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0408" "J"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u0409" "Lj"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u040A" "Nj"
+    sub "\u041E" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u040B" "C"
+    sub "\u0423" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "H"
+    sub "\u0426" "C"
+    sub "\u0427" "C"
+    sub "\u040F" "Dz"
+    sub "\u0428" "S"
 
-    sub "\u0430", "a" # а
-    sub "\u0431", "b" # б
-    sub "\u0432", "v" # в
-    sub "\u0433", "g" # г
-    sub "\u0434", "d" # д
-    sub "\u0452", "dj" # ђ
-    sub "\u0435", "e" # e
-    sub "\u0436", "z" # ж
-    sub "\u0437", "z" # з
-    sub "\u0438", "i" # и
-    sub "\u0458", "j" # ј
-    sub "\u043A", "k" # к
-    sub "\u043B", "l" # л
-    sub "\u0459", "lj" # љ
-    sub "\u043C", "m" # м
-    sub "\u043D", "n" # н
-    sub "\u045A", "nj" # њ
-    sub "\u043E", "o" # о
-    sub "\u043F", "p" # п
-    sub "\u0440", "r" # р
-    sub "\u0441", "s" # с
-    sub "\u0442", "t" # т
-    sub "\u045B", "c" # ћ
-    sub "\u0443", "u" # у
-    sub "\u0444", "f" # ф
-    sub "\u0445", "h" # х
-    sub "\u0446", "c" # ц
-    sub "\u0447", "c" # ч
-    sub "\u045F", "dz" # џ
-    sub "\u0448", "s" # ш
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0452" "dj"
+    sub "\u0435" "e"
+    sub "\u0436" "z"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0458" "j"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u0459" "lj"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u045A" "nj"
+    sub "\u043E" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u045B" "c"
+    sub "\u0443" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "h"
+    sub "\u0446" "c"
+    sub "\u0447" "c"
+    sub "\u045F" "dz"
+    sub "\u0448" "s"
   }
 
 }
 
+}

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

@@ -0,0 +1,193 @@
+system "ODNI:tat-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:tat
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Tatar Personal Names (2015)
+  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 {
+    note "Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh"
+    note "In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters,\n (e.g. 's' followed by 'h')."
+    note "The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration."
+  }
+}
+
+tests {
+   "Рустам Абдрашитов" ->  "Rustam Abdrashitov"
+}
+
+stage main {
+
+  # RULES
+  # note[1]
+  # generated with: "ЁЖҢХЦЧШЩЮЯ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub {
+    from capture(any("Ёё")) + any("Ёё")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Жж")) + any("Жж")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Ңң")) + any("Ңң")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Хх")) + any("Хх")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Цц")) + any("Цц")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Чч")) + any("Чч")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Шш")) + any("Шш")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Щщ")) + any("Щщ")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Юю")) + any("Юю")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Яя")) + any("Яя")
+    to ref(1)
+  }
+  # note[3]
+  sub {
+    from any("\u044A\u044C")
+    to none
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u04D8" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Zh"
+    sub "\u0496" "J"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u04A2" "Ng"
+    sub "\u041E" "O"
+    sub "\u04E8" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04AE" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u04BA" "H"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u0429" "Shch"
+    sub "\u042B" "Y"
+    sub "\u042D" "E"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u04D9" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "zh"
+    sub "\u0497" "j"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u04A3" "ng"
+    sub "\u043E" "o"
+    sub "\u04E9" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04AF" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u04BB" "h"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u0449" "shch"
+    sub "\u044B" "y"
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+}

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

@@ -0,0 +1,203 @@
+system "ODNI:tgk-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:tgk
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Tajik Personal Names (2015)
+  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 {
+    note "Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh"
+    note "In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters,\n (e.g. 's' followed by 'h')."
+    note "The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration."
+    note "Transliterate ‘е‘ as ‘ye’ at beginning of words, ‘e’ elsewhere"
+  }
+}
+
+tests {
+   "Парвона Ҷамшедов" ->  "Parvona Jamshedov"
+}
+
+stage main {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁЖХЧШЮЯЦЩ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub {
+    from capture(any("Ғғ")) + any("Ғғ")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Ёё")) + any("Ёё")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Жж")) + any("Жж")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Хх")) + any("Хх")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Чч")) + any("Чч")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Шш")) + any("Шш")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Юю")) + any("Юю")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Яя")) + any("Яя")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Цц")) + any("Цц")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Щщ")) + any("Щщ")
+    to ref(1)
+  }
+  # note[3]
+  sub {
+    from any("\u044A\u044C")
+    to none
+  }
+  # note[4]
+  sub {
+    from boundary + "\u0415"
+    to "Ye"
+  }
+  sub {
+    from boundary + "\u0435"
+    to "ye"
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0492" "Gh"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u04E2" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u049A" "Q"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u041E" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04EE" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u04B2" "H"
+    sub "\u0427" "Ch"
+    sub "\u04B6" "J"
+    sub "\u0428" "Sh"
+    sub "\u042D" "E"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+    sub "\u0426" "Ts"
+    sub "\u0429" "Shch"
+    sub "\u042B" "Y"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0493" "gh"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u04E3" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u049B" "q"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u043E" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04EF" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u04B3" "h"
+    sub "\u0447" "ch"
+    sub "\u04B7" "j"
+    sub "\u0448" "sh"
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+    sub "\u0446" "ts"
+    sub "\u0449" "shch"
+    sub "\u044B" "y"
+  }
+
+}
+}