interscript-maps 2.0.5

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

@@ -0,0 +1,151 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:uig
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of uyghur personal names in written reports and products
+  source: ICS-630-01 Annex U
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Uyghur 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 Uyghur 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 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: Zordun Sabir (also seen as Zordun Sabeer, Зордун Сабир ,زوردون سابیر). 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 Uyghur-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 "Зордун Сабир", "Zordun Sabir"
+}
+
+stage {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁҖҢЧШЮЯ".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("Җҗ"))+any("Җҗ"), ref(1)
+  sub capture(any("Ңң"))+any("Ңң"), 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)
+  # note[3]
+  sub any("\u044A\u044C"), none
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u04D8", "E" # Ә
+    sub "\u0411", "B" # Б
+    sub "\u0412", "W" # В
+    sub "\u0413", "G" # Г
+    sub "\u0492", "Gh" # Ғ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "J" # Ж
+    sub "\u0496", "Zh" # Җ
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    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 "\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", "X" # Х
+    sub "\u04BA", "H" # Һ
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+
+    sub "\u0430", "a" # а
+    sub "\u04D9", "e" # ә
+    sub "\u0431", "b" # б
+    sub "\u0432", "w" # в
+    sub "\u0433", "g" # г
+    sub "\u0493", "gh" # ғ
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "j" # ж
+    sub "\u0497", "zh" # җ
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    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 "\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", "x" # х
+    sub "\u04BB", "h" # һ
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}

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

@@ -0,0 +1,136 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:ukr
+  source_script: Cyrl
+  destination_script: Latn
+  name: Office of the Director Of National Intelligence Ukrainian Personal Names 2004 System, ICS 630-01 Annex M
+
+  # url:
+  source: ICS 630-01, Annex M
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community (IC) standard for the
+    transliteration of Ukrainian 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 Ukrainian that can then be linked to
+    forensic information in ways that will help identify the referent of
+    the name.
+}
+
+tests {
+  test "Андрій", "Andriy"
+  test "Борисенко", "Borysenko"
+  test "Володимир", "Volodymyr"
+  test "Богдан", "Bohdan"
+  test "Згурський", "Zhurskyy"
+  test "Дмитро", "Dmytro"
+  test "Олег", "Oleh"
+  test "Гаєвич", "Hayevych"
+  test "Жанна", "Zhanna"
+  test "Казимирчук", "Kazymyrchuk"
+  test "Михайленко", "Mykhaylenko"
+  test "Іващенко", "Ivashchenko"
+  test "Олексій", "Oleksiy"
+  test "Коваленко", "Kovalenko"
+  test "Леонід", "Leonid"
+  test "Маринич", "Marynych"
+  test "Наталія", "Nataliya"
+  test "Онищенко", "Onyshchenko"
+  test "Петро", "Petro"
+  test "Рибчинський", "Rybchynskyy"
+  test "Соломія", "Solomiya"
+  test "Троць", "Trots"
+  test "Уляна", "Ulyana"
+  test "Філіпчук", "Filipchuk"
+  test "Христина", "Khrystyna"
+  test "Стеценко", "Stetsenko"
+  test "Шевченко", "Shevchenko"
+  test "Гаращенко", "Harashchenko"
+  test "Юрій", "Yuriy"
+  test "Ярошенко", "Yaroshenko"
+  test "Костянтин", "Kostyantyn"
+  test "Новофедорівка", "Novofedorivka"
+  test "Гуляйгородок", "Hulyayhorodok"
+}
+
+stage {
+
+  # RULES
+  sub boundary+"\u2019"+boundary, none # remove ’
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "В", "V" # В
+    sub "Г", "H" # Г
+    sub "Ґ", "G" # Ґ
+    sub "Д", "D" # Д
+    sub "Е", "E" # Е
+    sub "Є", "Ye" # Є
+    sub "Ж", "Zh" # Ж
+    sub "З", "Z" # З
+    sub "И", "Y" # И
+    sub "І", "I" # І
+    sub "Ї", "Yi" # Ї
+    sub "Й", "Y" # Й
+    sub "К", "K" # К
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "Ф", "F" # Ф
+    sub "Х", "Kh" # Х
+    sub "Ц", "Ts" # Ц
+    sub "Ч", "Ch" # Ч
+    sub "Ш", "Sh" # Ш
+    sub "Щ", "Shch" # Щ
+    sub "Ю", "Yu" # Ю
+    sub "Я", "Ya" # Я
+    sub "Ь", "" # Ь
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "в", "v" # в
+    sub "г", "h" # г
+    sub "ґ", "g" # ґ
+    sub "д", "d" # д
+    sub "е", "e" # е
+    sub "є", "ye" # є
+    sub "ж", "zh" # ж
+    sub "з", "z" # з
+    sub "и", "y" # и
+    sub "і", "i" # і
+    sub "ї", "yi" # ї
+    sub "й", "y" # й
+    sub "к", "k" # к
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "u" # у
+    sub "ф", "f" # ф
+    sub "х", "kh" # х
+    sub "ц", "ts" # ц
+    sub "ч", "ch" # ч
+    sub "ш", "sh" # ш
+    sub "щ", "shch" # щ
+    sub "ю", "yu" # ю
+    sub "я", "ya" # я
+    sub "ь", "" # Ь
+  }
+
+}

data/maps/odni-urd-Arab-Latn-2015.imp

@@ -0,0 +1,220 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:urd
+  source_script: Arab
+  destination_script: Latn
+  name: Office of the Director Of National Intelligence Hindi Urdu Personal Names 2015 System, ICS-630-01 Annex F
+  
+  #url:
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community (IC) standard for the transliteration of names
+    from Hindi and Urdu 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 standard Hindi and Urdu that can then be linked to forensic
+    information in ways that will help identify the referent of the name.
+  
+    There are typically a number of ways that names can be Romanized from either
+    Devanagari (Hindi) or modified Arabic (Urdu) scripts. Ambiguities can result from the
+    Romanization of Hindi and Urdu names for several reasons, including the fact that some
+    sounds in South Asian languages (e.g., retroflex consonants, voiced aspirates) have no
+    equivalent in English or other European languages. In the case of Urdu, as in the original
+    Arabic source of many Islamic names, short vowel markings, double consonant marks
+    and other diacritics that would clearly distinguish the name are almost always omitted
+    from standard written texts. And many Islamic names of Arabic or Persian origin reflect
+    spelling distinctions from those languages that are lost in modern Urdu pronunciation
+    (e.g., three distinct Arabic letters all represent the identical sound [s] for Urdu speakers);
+    transliterations might either maintain those spelling distinctions or ignore them entirely.
+    And, as in the Arabic source, names containing the Arabic definite article ‘al’ (‘ul’) show
+    anticipatory assimilation in pronunciation (e.g., Shams al Din > Shamsuddin);
+    transliterations may either reflect spelling or pronunciation in such cases.
+  
+    Because Hindi and Urdu overlap so extensively, it is desirable to correlate Hindi and
+    Urdu transliterations as much as possible. In the area of names, this can become
+    problematic when the Urdu spelling accurately reflects original Arabic spelling while the
+    Hindi spelling was phonetically-based, in essence, already a transliteration. This would
+    argue for ignoring Arabic/Urdu spelling distinctions not reflected in pronunciation in
+    either Urdu or Hindi (e.g., letter sin versus letter sad) while maintaining Arabic/Urdu
+    spelling distinctions like Hindi also maintains (e.g., qaf as in Qutubbin versus kaf)).
+    However, this is not always possible (see Hindi va versus Urdu wau).
+  
+    In cases where an individual’s name has already been transliterated, that is to be indicated
+    – as found – in parentheses immediately following its rendition in the transliteration
+    standard (e.g., Muhammad Khulud (Mohamed Khulood)). In addition, if the original
+    Devanagari 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. 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 Hindi- or Urdu-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 of this system is to produce a consistent Romanized transcription of the
+    name that is readable to the 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.
+    Additionally, 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:
+  
+    - |
+      Long/Short Vowels: Long and short vowels are not distinguished in the system:
+      The borrowed Arabic name Samir could represent two distinct names, one with a
+      long /a/ (Saamir) and one with a long /i/ (Samiir). One solution would be to use
+      /ee/ to stand for the long /i/, as is often done (Sameer). The IC Standard will not
+      distinguish between these.
+  
+    - |
+      No distinction is made between: retroflex and non-retroflex consonants; and
+      nasalized vowels and vowels followed by /n/.
+    - |
+      No distinction is made between the several Arabic letters with the same phonetic
+      value in Urdu: e.g., letters sin/svad, zal/ze/zoe.
+    - |
+      A distinction is drawn between Urdu letters qaf and kaf (and correspondingly,
+      Hindi qa and ka).
+    - |
+      A distinction is drawn between aspirated (e.g., /d/) and nonaspirated consonants
+      (e.g., /dh/), with the exception of ch/chh, both represented by /ch/.
+    - |
+      Double consonants: Double consonants represented by the tashdid (shaddah) are
+      shown in most cases (e.g., Hassan, Muhammad). Exceptions: consonants
+      represented by digraphs are not doubled (e.g., Mubashir [not Mubashshir]).
+    - |
+      Hamzah (glottal stop) and ayn: Unlike in the Arabic IC Standard, these are not
+      represented in the IC standard.
+    - |
+      Digraphs: No distinction is made between digraphs such as /sh/ and single
+      contiguous letters such as /s/ followed by /h/.
+    - |
+      Arabic definite article “al” (‘the’): Shows sun letter assimilation in the
+      Romanized form (e.g., Abdur Rahman rather than Abdal Rahman, rather than
+      Arabic IC standard 'Abd al-Rahman).
+    - |
+      Special Rules
+      - |
+        Hyphens: Hyphens (-) are NOT used to connect name elements within a name:
+        Abdur Rahman. The single exception to this is the izafat (i.e., linking vowel in
+        noun-link-modifier construction of Persian origin), which does show a hyphen
+        before the /e/ and a following space: Koh-e Nur (‘mountain of light’), “Jaish-e
+        xx” (‘Army of xx’ construction).
+      - |
+        Names incorporating “din” are written as one unit: Azermuddin, Badruddin,
+      Faizuddin, Salahuddin.
+      - |
+        Names that incorporate Allah as part of the name show the Arabic grammatical
+        marker /u/ rather than the /a/ of Allah: Abdullah (not Abdallah).
+      - |
+        Inherent short vowel /a/ in Devanagari is represented with an /a/ in Roman. Final
+        consonants are assumed not to have a short /a/ (e.g., masc. name Ram Lal, not
+        Rama Lala).
+      - |
+        As a general rule, Devanagari va is transcribed as a /v/: Vijay, Vishal, etc.
+        Exception: /sw/ combination: Saraswati, Krishnaswami. Urdu wau, however, is
+        transcribed as /w/: Wasim, Walid.
+}
+
+tests {
+  test "وشال ٹھاکر", "ishal tsakr"
+  test "حسن محمود", "hasn mhamid"
+  test "یوسف خان", "iisf khan"
+  test "معین خان", "mein khan"
+  test "سعید اجمل", "seid ajml"
+  test "انضمام الحق", "anzmam alhaq"
+  test "فرہاد رضا", "frahad rza"
+  test "وسیم اکرام", "isim akram"
+  test "شکیب الحسن", "shkib alhasn"
+  test "حسن عبد اللہ", "hasn ebd allah"
+}
+
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    
+    
+    sub "\u0622", "a" # ARABIC ALEF W/MADDA ABOVE
+    sub "\u0627", "a" # or u ARABIC ALEF
+    sub "\u06cc", "i" # or ai or u ARABIC LETTER WAW
+    sub "\u0648", "i" # or o,au ARABIC LETTER FARSI YEH
+    sub "\u06d2", "e" # ARABIC LETTER YEH BARREE
+    sub "\u0650", "e" # ARABIC ARABIC KASRA
+    sub "\u0639", "e" # ARABIC LETTER AIN
+    sub "\u06c1", "ah" # ARABIC LETTER HEH GOAL
+    sub "\u062d", "ha" # ARABIC LETTER HAH
+    sub "\u0648\u0670", "a" # ARABIC LETTER FARSI YEH + ARABIC LETTER SUPERSCRIPT ALEF
+    sub "\u0670", "a" # ARABIC LETTER SUPERSCRIPT ALEF
+    sub "\u0627\u0650", "i" # ARABIC ALEF + ARABIC KASRA
+    sub "\u0639\u0650", "i" # ARABIC LETTER AIN + ARABIC KASRA
+    sub "\u064f", "i" # ARABIC DAMMA
+    sub "\u06d3", "i" #  ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
+    sub "\u06c2", "-e" #  ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
+    sub "\u06c1\u0650", "o" #  ARABIC LETTER YEH  WITH HAMZA ABOVE
+    sub "\u0624", "au" #  ARABIC LETTER WAW WITH HAMZA ABOVE
+    
+    
+    
+    sub "\u06a9", "k" #   ARABIC LETTER KEHEH
+    sub "\u0642", "q" #   ARABIC LETTER QAF
+    sub "\u062e", "kh" #   ARABIC LETTER KHAH
+    sub "\u06af", "g" #   ARABIC LETTER GAF
+    sub "\u063a", "gh" #   ARABIC LETTER GHAIN
+    sub "\u0686", "ch" #   ARABIC LETTER TCHEH
+    sub "\u062c", "j" #   Arabic Letter Jeem
+    
+    sub "\u0632", "z" #   Arabic Letter ZAIN
+    sub "\u0630", "z" #   Arabic Letter THAL
+    sub "\u0636", "z" #   Arabic Letter DAD
+    sub "\u0638", "z" #   Arabic Letter ZAH
+    sub "\u0698", "zh" #   Arabic Letter JEH
+    
+    
+    sub "\u0679", "t" #   ARABIC LETTER TTEH
+    sub "\u0688", "d" #   Arabic Letter DDAL
+    sub "\u062f", "d" #   Arabic Letter DAL
+    sub "\u0691", "r" #   Arabic Letter RREH
+    sub "\u062a", "t" #   Arabic Letter TEH
+    sub "\u0637", "t" #   Arabic Letter TAH
+    sub "\u0646", "n" #   Arabic Letter NOON
+    sub "\u06ba", "n" #   Arabic Letter NOON GHUNNA
+    
+    
+    sub "\u067e", "p" #   Arabic Letter PE
+    sub "\u0641", "f" #   Arabic Letter FEH
+    sub "\u0628", "b" #   Arabic Letter BEH
+    sub "\u0645", "m" #   Arabic Letter MEEM
+    sub "\u0631", "r" #   Arabic Letter REH
+    sub "\u0644", "l" #   Arabic Letter LAM
+    sub "\u0634", "sh" #   Arabic Letter SHEEN
+    sub "\u0633", "s" #   Arabic Letter SHEEN
+    sub "\u062b", "s" #   Arabic Letter THEH
+    sub "\u0635", "s" #   Arabic Letter SAD
+    sub "\u0621", "" #   Arabic Letter HAMZA
+    sub "\u06be", "s" #   Arabic Letter HEH DOACHASHMEE
+    sub "\u064b", "n" #   Arabic Letter FATHATAN
+    sub "\u064e", "n" #   Arabic sign FATHATAN
+    sub "\u0652", "" #   Arabic Letter SUKUN
+    sub "\u0651", "" #   Arabic Letter SHADDA
+  }
+
+}
+