interscript-maps 2.0.5

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

@@ -0,0 +1,138 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2: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 {
+  test "Міхаіл", "Mikhail"
+  test "Беларусь", "Byelarus"
+  test "Кастусь Каліноўскі", "Kastus Kalinowski"
+  test "Васіль Быкау", "Vasil Bykau"
+  test "Янка Купала", "Yanka Kupala"
+  test "Маланка", "Malanka"
+  test "Пакаранне", "Pakarannye"
+  test "Бэз", "Bez"
+  test "Чабор", "Chabor"
+  test "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 {
+
+  # CHARACTERS
+  parallel {
+    sub "\u0027", "" # '
+
+    sub "\u0410", "A" # A
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # B
+    sub "\u0413", "H" # Г
+    sub "\u0490", "G" # Ґ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "Ye" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0406", "I" # І
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    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 "\U040E", "W" # Ў
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u042B", "Y" # Ы
+    sub "\u042C", "" # Ь
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+
+    sub "\u0430", "a" # а
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "h" # г
+    sub "\u0491", "g" # ґ
+    sub "\u0434", "d" # д
+    sub "\u0435", "ye" # е
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0437", "z" # з
+    sub "\u0456", "i" # і
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    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 "\u045E", "w" # ў
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u044B", "y" # ы
+    sub "\u044c", "" # Ь
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}

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

@@ -0,0 +1,90 @@
+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
+  creation_date: 2005
+  description:
+}
+
+tests {
+  test "Добри Христов", "Dobri Khristov"
+  test "болгарица", "bolgaritsa"
+  test "български език", "bulgarski ezik"
+  test "българска азбука", "bulgarska azbuka"
+  test "град", "grad"
+  test "аз държа", "az durzha"
+  test "Ядеш хляба с чубрица", "Yadesh khlyaba s chubritsa"
+}
+
+stage {
+
+  # 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

@@ -0,0 +1,103 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2: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 {
+  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"
+  # note[1]
+  test "шш", "sh"
+  test "ччччч", "ch"
+}
+
+dependency "bgnpcgn-bul-Cyrl-Latn-2013", as: cyrllatn
+
+stage {
+
+
+  # RULES
+  # note[1]
+  #   #   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 "\u042A", "A" # Ъ
+
+  sub "\u044C", "y" # ь
+
+  sub "\u044A", "a" # ъ
+
+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
+}
+  run map.cyrllatn.stage.main
+}
+

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

@@ -0,0 +1,165 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:che
+  source_script: Cyrl
+  destination_script: Latn
+  name: Office of the Director Of National Intelligence -- ICS 630-01 -- Chechen Cyrillic 2015
+  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20C%20-%20Chechen_Personal_Names_FLTS%20(U).pdf
+  source: ICS-630-01 Annex C
+  creation_date: 2015
+  confirmation_date: 2015
+
+  description: |
+    This system is the Intelligence Community (IC) standard for the transliteration of Chechen 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 Chechen 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 or Arabic-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: Ilyas
+    Akhmadkant (also seen as Ilyas Axmadkhant, Ильяс Ахмадкӏант). 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 Chechen-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 plus the apostrophe. 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:
+    - Add a preceding 'y' if the vowel is preceded by the sound of a 'y' consonant.
+    - |
+      This is a single apostrophe as found on regular US keyboards (ASCII character 39),
+      though software may render the apostrophe with differing appearances (e.g. curved left or right).
+      Note that the same apostrophe is used for 'ъ', '|', 'ӏ', and '1'.
+    - A word-initial hard sign 'ъ' is not represented, but instead is left out of the transliteration.
+    - The romanization follows the dialect spoken in Chechnya rather than other local pronunciations.
+    - Long and short vowels are not distinguished in this system.
+    - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters (e.g. 's' followed by 'h').
+    - The Cyrillic soft sign ('ь') by itself (not part of a digraph) is not represented, but instead is left out of the transliteration.
+    - Interpretation of Cyrillic digraphs in Table 1 takes precedence over interpretation of the individual
+      characters. Thus, 'кх' -> 'q', and not to 'k' followed by 'kh'.
+    - Transliteration of Cyrillic digraphs for diphthongs will follow the combination of the transliteration of
+      the individual characters. Thus, 'aй' -> 'ay', 'oй' -> 'oy', and both 'эй' and 'eй' -> 'ey'.
+}
+
+tests {
+  test "Ильяс Ахмадкӏант", "Ilyas Akhmadkant"
+  test "Ильяс Ахмадк1ант", "Ilyas Akhmadkant"
+}
+
+stage {
+  # note[1]
+  sub boundary + "\u0415", "Ye", not_before: boundary + "\u2019"
+  sub boundary + "\u0435", "ye", not_before: boundary + "\u2019"
+  # note[2]
+  sub "1", "ӏ", before: not_word, after: not_word
+  sub "1", "ӏ", before: not_word
+  sub "1", "ӏ", after: not_word
+
+  parallel {
+    sub "\u0410"        , 'A'               # А
+    sub "\u0411"        , 'B'               # Б
+    sub "\u0412"        , 'V'               # В
+    sub "\u0413"        , 'G'               # Г
+    sub "\u0413\u04C0"  , 'Gh'              # ГӀ
+    sub "\u0414"        , 'D'               # Д
+    sub "\u0415"        , 'E'               # Е note[1]
+    sub "\u0416"        , 'J'               # Ж
+    sub "\u0417"        , 'Z'               # З
+    sub "\u0418"        , 'I'               # И
+    sub "\u0418\u042B"  , 'I'               # ИЙ
+    sub "\u042B"        , 'Y'               # Й
+    sub "\u041A"        , 'K'               # К
+    sub "\u041A\u04C0"  , 'K'               # КӀ
+    sub "\u041A\u0445"  , 'Q'               # Кх note[8]
+    sub "\u041A\u044A"  , 'Q'               # Къ
+    sub "\u041B"        , 'L'               # Л
+    sub "\u041C"        , 'M'               # М
+    sub "\u041D"        , 'N'               # Н
+    sub "\u041E"        , 'O'               # О
+    sub "\u041F"        , 'P'               # П
+    sub "\u041F\u04C0"  , 'Ph'              # ПӀ
+    sub "\u0420"        , 'R'               # Р
+    sub "\u0421"        , 'S'               # С
+    sub "\u0422"        , 'T'               # Т
+    sub "\u0422\u04C0"  , 'T'               # TӀ
+    sub "\u0423"        , 'U'               # У
+    sub "\u0424"        , 'F'               # Ф
+    sub "\u0425"        , 'Kh'              # Х
+    sub "\u0425\u044C"  , 'H'               # Хь
+    sub "\u0425\u04C0"  , 'H'               # ХӀ
+    sub "\u04B8"        , 'Ts'              # Ц
+    sub "\u04B8\u04C0"  , 'Ts'              # ЦӀ
+    sub "\u0427"        , 'Ch'              # Ч
+    sub "\u0427\u04C0"  , 'Ch'              # ЧӀ
+    sub "\u0428"        , 'Sh'              # Ш
+    sub "\u042A"        , "'"               # Ъ note[2] note[3]
+    sub "\u042B"        , 'Е'               # Ы
+    sub "\u042D"        , 'E'               # Э
+    sub "\u042E"        , 'Yu'              # Ю
+    sub "\u042F"        , 'Ya'              # Я
+    sub "\u04C0"        , "'"               # Ӏ note[2]
+    sub "\u042C"        , ''                # Ь note[7]
+
+    sub "\u0430"        , 'a'               # а
+    sub "\u0431"        , 'b'               # б
+    sub "\u0432"        , 'v'               # в
+    sub "\u0433"        , 'g'               # г
+    sub "\u0433\u04CF"  , 'gh'              # гӏ
+    sub "\u0434"        , 'd'               # д
+    sub "\u0435"        , 'e'               # е note[1]
+    sub "\u0436"        , 'j'               # ж
+    sub "\u0437"        , 'z'               # з
+    sub "\u0438"        , 'i'               # и
+    sub "\u0438\u0439"  , 'i'               # ий
+    sub "\u0439"        , 'y'               # й
+    sub "\u043A"        , 'k'               # к
+    sub "\u043A\u04CF"  , 'k'               # кӏ
+    sub "\u043A\u0445"  , 'q'               # кх note[8]
+    sub "\u043A\u044A"  , 'q'               # къ
+    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 "\u0442\u04CF"  , 't'               # тӏ
+    sub "\u0443"        , 'u'               # у
+    sub "\u0444"        , 'f'               # ф
+    sub "\u0445"        , 'kh'              # х
+    sub "\u0445\u044C"  , 'h'               # хь
+    sub "\u0445\u04CF"  , 'h'               # хӏ
+    sub "\u04B9"        , 'ts'              # ц
+    sub "\u04B9\u04CF"  , 'ts'              # цӏ
+    sub "\u0447"        , 'ch'              # ч
+    sub "\u0447\u04CF"  , 'ch'              # чӏ
+    sub "\u0448"        , 'sh'              # ш
+    sub "\u044A"        , "'"               # ъ note[2] note[3]
+    sub "\u044B"        , 'e'               # ы
+    sub "\u044D"        , 'e'               # э
+    sub "\u044E"        , 'yu'              # ю
+    sub "\u044F"        , 'ya'              # я
+    sub "\u04CF"        , "'"               # ӏ note[2]
+    sub "\u044C"        , ''                # ь note[7]
+  }
+}