interscript-maps 2.4.2 → 2.5.0

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

@@ -0,0 +1,191 @@
+system "ODNI:aze-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:aze
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Azeri Personal Names (2015)
+  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 {
+    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 {
+   "Рашад Садыхов" ->  "Rashad Sadykhov"
+}
+
+stage main {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁЖХЧШЩЮЯ".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("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 "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u049C" "G"
+    sub "\u0492" "Gh"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u04D8" "A"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u0408" "Y"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    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 "\u0427" "Ch"
+    sub "\u04B8" "J"
+    sub "\u0428" "Sh"
+    sub "\u0429" "Shch"
+    sub "\u042B" "Y"
+    sub "\u042D" "E"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u049D" "g"
+    sub "\u0493" "gh"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u04D9" "a"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u0458" "y"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    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 "\u0447" "ch"
+    sub "\u04B9" "j"
+    sub "\u0448" "sh"
+    sub "\u0449" "shch"
+    sub "\u044B" "y"
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+}

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

@@ -0,0 +1,140 @@
+system "ODNI:bel-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:bel
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Belarusian Personal Names (2015)
+  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 {
+   "Міхаіл" ->  "Mikhail"
+   "Беларусь" ->  "Byelarus"
+   "Кастусь Каліноўскі" ->  "Kastus Kalinowski"
+   "Васіль Быкау" ->  "Vasil Bykau"
+   "Янка Купала" ->  "Yanka Kupala"
+   "Маланка" ->  "Malanka"
+   "Пакаранне" ->  "Pakarannye"
+   "Бэз" ->  "Bez"
+   "Чабор" ->  "Chabor"
+   "Дзяўчына, дзяўчыначка пасярод гісторыі\nЗ прастадушнай шчырасьцю глядзіць на тэрыторыю.\nУ вакне заўсёды звыклая выява:\nШэры двор, шэры слуп, на слупе аб'явы." ->  "Dzyawchyna, dzyawchynachka pasyarod historyi\nZ prastadushnay shchyrastsyu hlyadzits na terytoryyu.\nU vaknye zawsyody zvyklaya vyyava:\nShery dvor, shery slup, na slupye abyavy."
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "\u0027" ""
+
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "H"
+    sub "\u0490" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "Ye"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0406" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    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 "\U040E" "W"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u042B" "Y"
+    sub "\u042C" ""
+    sub "\u042D" "E"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "h"
+    sub "\u0491" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "ye"
+    sub "\u0451" "yo"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0456" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    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 "\u045E" "w"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u044B" "y"
+    sub "\u044c" ""
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+}

data/maps/odni-bul-Cyrl-Latn-2005.isc

@@ -0,0 +1,93 @@
+system "ODNI:bul-Cyrl:Latn:2005" {
+
+metadata {
+  authority_id odni
+  id 2005
+  language iso-639-2:bul
+  source_script Cyrl
+  destination_script Latn
+  name Intelligence Community (IC) Standard for the Transliteration of Bulgarian Personal Names (2005)
+  creation_date 2005
+  description 
+}
+
+tests {
+   "Добри Христов" ->  "Dobri Khristov"
+   "болгарица" ->  "bolgaritsa"
+   "български език" ->  "bulgarski ezik"
+   "българска азбука" ->  "bulgarska azbuka"
+   "град" ->  "grad"
+   "аз държа" ->  "az durzha"
+   "Ядеш хляба с чубрица" ->  "Yadesh khlyaba s chubritsa"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041a" "K"
+    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 "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u0429" "Sht"
+    sub "\u042a" "U"
+    sub "\u042c" "Y"
+    sub "\u042e" "Yu"
+    sub "\u042f" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043a" "k"
+    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 "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u0449" "sht"
+    sub "\u044a" "u"
+    sub "\u044c" "y"
+    sub "\u044e" "yu"
+    sub "\u044f" "ya"
+  }
+
+}
+
+}

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

@@ -1,15 +1,16 @@
+system "ODNI:bul-Cyrl:Latn:2015" {
+
 metadata {
-  authority_id: odni
-  id: 2015
-  language: iso-639-2:bul
-  source_script: Cyrl
-  destination_script: Latn
-  name: ICS-630-01 Romanization of Bulgarian Personal Names (2015)
-  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
+  authority_id odni
+  id 2015
+  language iso-639-2:bul
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Bulgarian Personal Names (2015)
+  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
@@ -45,28 +46,30 @@ 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:
-    - 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').
+  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 (e.g. 's' followed by 'h')."
+  }
 }
 
 tests {
-  test "Добри Христов", "Dobri Khristov"
-  test "болгарица", "bolgaritsa"
-  test "български език", "balgarski ezik"
-  test "българска азбука", "balgarska azbuka"
-  test "град", "grad"
-  test "аз държа", "az darzha"
-  test "Ядеш хляба с чубрица", "Yadesh khlyaba s chubritsa"
+   "Добри Христов" ->  "Dobri Khristov"
+   "болгарица" ->  "bolgaritsa"
+   "български език" ->  "balgarski ezik"
+   "българска азбука" ->  "balgarska azbuka"
+   "град" ->  "grad"
+   "аз държа" ->  "az darzha"
+   "Ядеш хляба с чубрица" ->  "Yadesh khlyaba s chubritsa"
   # note[1]
-  test "шш", "sh"
-  test "ччччч", "ch"
+   "шш" ->  "sh"
+   "ччччч" ->  "ch"
 }
 
-dependency "bgnpcgn-bul-Cyrl-Latn-2013", as: cyrllatn
+dependency "bgnpcgn-bul-Cyrl-Latn-2013" as cyrllatn
 
-stage {
+stage main {
 
 
   # RULES
@@ -74,28 +77,29 @@ stage {
   #   #   sub capture(any_character) :interval_start ref( 1 ) :interval_stop , ref( 1 ) # warning: :interval unimplemented # warning: :
   #sub capture(any_character), ref( 1 )
 
-  sub "\u042C", "Y" # # Ь
+  sub "\u042C" "Y"
 
-  sub "\u042A", "A" # Ъ
+  sub "\u042A" "A"
 
-  sub "\u044C", "y" # ь
+  sub "\u044C" "y"
 
-  sub "\u044A", "a" # ъ
+  sub "\u044A" "a"
 
 parallel{
-  sub "\u0448", "sh" # ш
-  sub "\u0448\u0448", "sh" # шш
-  sub "\u0448\u0448\u0448", "sh" # шшш
-  sub "\u0448\u0448\u0448\u0448", "sh" # шшшш
-  sub "\u0448\u0448\u0448\u0448\u0448", "sh" # шшшшш
-  sub "\u0448\u0448\u0448\u0448\u0448\u0448", "sh" # шшшшшш
-  sub "\u0447", "ch" # ч
-  sub "\u0447\u0447", "ch" # чч
-  sub "\u0447\u0447\u0447", "ch" # ччч
-  sub "\u0447\u0447\u0447\u0447", "ch" # чччч
-  sub "\u0447\u0447\u0447\u0447\u0447", "ch" # ччччч
-  sub "\u0447\u0447\u0447\u0447\u0447\u0447", "ch" # чччччч
+  sub "\u0448" "sh"
+  sub "\u0448\u0448" "sh"
+  sub "\u0448\u0448\u0448" "sh"
+  sub "\u0448\u0448\u0448\u0448" "sh"
+  sub "\u0448\u0448\u0448\u0448\u0448" "sh"
+  sub "\u0448\u0448\u0448\u0448\u0448\u0448" "sh"
+  sub "\u0447" "ch"
+  sub "\u0447\u0447" "ch"
+  sub "\u0447\u0447\u0447" "ch"
+  sub "\u0447\u0447\u0447\u0447" "ch"
+  sub "\u0447\u0447\u0447\u0447\u0447" "ch"
+  sub "\u0447\u0447\u0447\u0447\u0447\u0447" "ch"
 }
-  run map.cyrllatn.stage.main
+  run  map.cyrllatn.stage.main
 }
 
+}