interscript-maps 2.0.5

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

@@ -0,0 +1,28 @@
+metadata {
+  authority_id: odni
+  id: 2005
+  language: iso-639-2:mkd
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of macedonian personal names in written reports and products
+  creation_date: 2005
+  confirmation_date: 2005
+  description: |
+    Office of the Director Of National Intelligence Macedonian Personal Names 2004 System
+}
+
+tests {
+  test "Билјана", "Biljana"
+  test "Душко", "Dushko"
+}
+
+dependency "odni-mkd-Cyrl-Latn-2015", as: cyrllatn
+
+stage {
+
+  run map.cyrllatn.stage.main
+
+  # RULES
+
+}
+

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

@@ -0,0 +1,124 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:mkd
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of macedonian personal names in written reports and products
+  source: ICS-630-01 Annex H
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community (IC) standard for the transliteration of Macedonian
+    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 Macedonian 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 Macedonian-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.
+}
+
+tests {
+  test "Билјана", "Biljana"
+  test "Душко", "Dushko"
+}
+
+stage {
+  parallel {
+    # RULES
+    sub "\u0053", "Dz" # S => Dz
+    sub "\u0073", "dz" # s => dz
+
+    # CHARACTERS
+    sub "\u0410", "A" # А
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0414", "D" # Д
+    sub "\u0403", "Gj" # Ѓ
+    sub "\u0415", "E" # Е
+    sub "\u0416", "Zh" # 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 "\u040C", "Kj" # Ќ
+    sub "\u0423", "U" # У
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "H" # Х
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u040F", "Dzh" # Џ
+    sub "\u0428", "Sh" # Ш
+    sub "\u2019", "" # ’
+
+    sub "\u0430", "a" # а
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0434", "d" # д
+    sub "\u0453", "gj" # ѓ
+    sub "\u0435", "e" # e
+    sub "\u0436", "zh" # 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 "\u045C", "kj" # ќ
+    sub "\u0443", "u" # у
+    sub "\u0444", "f" # ф
+    sub "\u0445", "h" # х
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u045F", "dzh" # џ
+    sub "\u0448", "sh" # ш
+  }
+
+}

data/maps/odni-prs-Arab-Latn-2004.imp

@@ -0,0 +1,120 @@
+metadata {
+  authority_id: odni
+  id: 2004
+  language: iso-639-3:prs
+  source_script: Arab
+  destination_script: Latn
+  name: Intelligence Community (IC) Standard for the Transliteration of Dari Personal Names (2004)
+  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Farsi_(Persian)_%26_Dari_IC_Standards.doc
+  creation_date: 2004
+  confirmation_date: 2004-11
+  description: |
+
+  notes:
+    - This standard is intended only for those Afghan names
+      that have a common bond or similarity with Iranian or
+      Arabic names.  They should not, for example, be used for
+      Pashto names, for which a separate standard should be used.
+    - Long/short vowels:- There is no distinction made in Roman
+      between long and short a:-  E.g., Farhad (first a is short,
+      second is long).
+    - Double consonants:-  Double consonants represented by the
+      tashdid are shown by doubling the Roman letter:-  Mohammad.
+      Exceptions:-  Consonants represented by Roman digraphs (
+      e.g., sh, ch) are not doubled:-  Mobasher [not:-  Mobashsher]
+      .  Double letters are only used for tashdid (thus, Hosein [
+      not Hossein]) or to reflect the ‘sun letter’ assimilation (
+      see below).
+    - Hamzeh:-  The hamzeh is represented name-internally by an
+      apostrophe, as is the ain.  Name-initially, however,
+      neither hamzeh nor ain are indicated in transliteration (
+      e.g., Abdorrahman, not 'Abdorrahman).
+    - Digraphs:-  No distinction is drawn in Roman between
+      digraphs such as sh and single contiguous letters (e.g., s
+      followed by h).
+    - Arabic definite article "al" ('the'):-  Common in many
+      names borrowed from Arabic, the transliteration should show
+      the 'sun letter' assimilation rather than the “l” for the
+      lam.  That  is:-  Abdorrahman.  Note also that the "Abdol +
+      attribute of Allah" names are written as one unanalyzed
+      word, as are other names that contain the definite
+      article:-  Shamsoddin (not Shams al-Din), Nezamoddin, etc.
+    - Diphthongs:-  Diphthongs are written ei and ow
+      respectively:-  Hosein; Khosrow.
+    - Yeh maqsura (final yeh pronounced as “a”):-  should be
+      written as “a” as in “Musa”.
+
+    - Special Rules
+
+    - Hyphens:-  A hyphen is used to indicate the ezafeh
+      construction:-  Arshad-e Ameri
+    - Borrowed names that incorporate the name of God (Allah)
+      are transliterated as one word, with the letter "o":-  E.g.,
+      Abdollah, Ayatollah, Azizollah.
+    - Foreign names borrowed or appearing in Dari are spelled
+      according to the standard Western tradition (even if there
+      is an Arabic or Dari version of the same name):-  Joseph,
+      Michael.
+    - Common suffixes, such as gol, pur, mand, yar, zadeh,
+      etc., as well as nesbeh (‘relationship’ (to place of birth,
+      etc.)) names derived with these suffixes  (e.g., abadi) are
+      written as part of the name:-
+
+      gol		Parigol, Ziagol
+      pur		Shahpur, Mehrpur
+      mand		Gulahmand
+      yar		Aminyar
+      zadeh		Ismailzadeh, Karimzadeh
+
+      abadi		Kamalabadi
+}
+
+tests {
+  test "مُوسَى", "musa"
+  test "مُؤمِن", "momen"
+  test "رِضايي", "rezai"
+  test "مُبَشِّر", "mobasher"
+  test "حَسَّان", "hassan"
+  test "حَسَن", "hasan"
+  test "صَفَّار", "saffar"
+  test "صَفَر", "safar"
+}
+
+dependency "odni-fas-Arab-Latn-2004", as: arablatn
+
+stage {
+
+
+  # CHARACTERS
+  parallel {
+s
+    sub "\u0626", "" # ئ
+    sub "\u0624", "" # ؤ
+
+    # shadda
+
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0648\u0651", "ww" # و
+
+    sub "\u0621", "" # ء
+
+    # FROM NOTES
+
+    sub "\u064a\u064a", "i" # NOTE 4 (2)
+    sub "\u06cc\u06cc", "i"
+
+    sub "\u0627\u064a" + boundary, "i" # NOTE 4 (3)
+    sub "\u0627\u06cc" + boundary, "i"
+
+    sub "\u064f\u0648", "u" # ـُو damma followed by و     #gets broken by "w" lower
+
+    # Farsi consonant characters
+
+    sub "\u0639", "" # ع # new
+    sub "\u0642", "q" # ق
+    sub "\u0648", "w" # و
+  }
+
+  run map.arablatn.stage.main
+}
+

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

@@ -0,0 +1,225 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-3:prs
+  source_script: Arab
+  destination_script: Latn
+  name: ODNI Persian Farsi Dari Personal Names 2015 System, ICS-630-01 Annex J
+  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+  creation_date: 2015
+  confirmation_date: 2015-11
+  description: |
+    This system is the Intelligence Community (IC) standard for
+    the transliteration of Persian (Farsi)
+    and Dari names that is 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 Persian (Farsi) and Dari 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 Perso-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 while maintaining consistency.
+
+    For names of individuals who are not part of the Persian-(
+    Farsi) or Dari-speaking community,
+    but whose names are encountered in Farsi or Dari, use the
+    relevant IC transliteration standard for
+    names from that language (e.g., Mikhail, Yitzhak, Abu-
+    Murtada). 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
+    online CIA World Factbook and the
+    online directory of Chiefs of State and Cabinet Members of
+    Foreign Governments, the spellings
+    given in these online reference works should be used in
+    place of the IC Standard, with the IC
+    Standard included as a variant in parentheses at the first
+    usage. 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 (e.g., former president Mahmud
+    Ahmadinezhad (Ahmadi-Nejad).
+
+    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 and hyphen.
+    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 online tools,
+    name dictionaries, and lists containing
+    conventional spellings of names of well-known individuals.
+
+  notes:
+    - |
+      This standard is intended only for those Afghan names that
+      have a common bond or similarity with Iranian names. It
+      should not, for example, be used for names of Pashtuns, for
+      which the Pashto IC Standard should be used.
+
+    - |
+      Alef maqsura (final yeh pronounced as “a”): should be written “a” as in
+      “Musa”.
+
+    - |
+      Digraphs: No distinction is drawn between digraphs
+      such as sh and single contiguous letters (e.g., s followed
+      by h).
+
+    - |
+      Long/short vowels: There is no distinction made in
+      Roman between long and short a: E.g., Farhad (first a is
+      short, second is long).
+
+    - |
+      Diphthongs: Diphthongs are written ei and ow respectively:
+      Hosein; Khosrow.
+
+    - |
+      Double consonants: Double consonants represented by the
+      tashdid are shown by doubling the
+      Roman letter: Mo'azzami, Tavakkoli, Sajjad. Exceptions: Ein
+      and consonants represented by
+      Roman digraphs (e.g., sh, ch) are not doubled (Mobasher,
+      not Mobashsher). Double letters
+      are only used for tashdid (Hosein, not Hossein) or to
+      reflect “sun-letter” assimilation (see
+      below). Special care should be taken when possible to
+      discriminate between doubled and
+      non-doubled letters in names that are otherwise
+      indistinguishable in their transliterated forms:
+      Hasan (حسن (vs. Hassan (حسان(
+
+    - |
+      Compound first names will be written as distinct words:
+      Ali Reza (not Alireza or Ali-Reza);
+      Mohammad Hosein (not Mohammadhosein or Mohammad-Hosein),
+      with the exception of cases identified below.
+
+    - |
+      Arabic-origin names that incorporate the word “Allah” are
+      transliterated as one word, with the letter ‘o’ replacing the
+      alef in Allah (Azizollah, Rahimollah).
+
+    - |
+      Name-internal Arabic definite article "al" (‫)ال‬: Common
+      in many names borrowed
+      from Arabic, the transliteration should follow the Arabic
+      rules for “sun letter” assimilation in spoken form and
+      reflect the nominative case. That is: Abdorrahman, not Abd-
+      al-Rahman. (The Arabic sun letters are: ‫ت‬،‫ث‬،‫د‬،‫ذ‬،
+      ‫ر‬، ‫ز‬،‫س‬،‫ش‬،‫ص‬،‫ض‬،‫ط‬،‫ظ‬،‫ل‬،‫ن‬ . These correspond with
+      d, l, n, r, s, sh, t, and z.) Note that the moon letters (
+      i.e., all other Arabic letters) are not assimilated (e.g.,
+      Abdolhasan, Abolfazl). Note also that the “Abdollah” and
+      “Abdol + attribute of Allah” names are written as a single
+      word, as are other names that contain the definite article:
+      Shamsoddin (not Shams-al-Din), Nezamoddin, etc.
+
+    - |
+      Name-initial Arabic definite article "al" (‫)ال‬: For
+      Arabic-origin names starting with the definite article “al” (‫)
+      ال‬, follow the Arabic standard of al-Sisi (‫)الصیصی‬ (not
+      Alsisi or Assisi) and forego sun-letter assimilation.
+
+    - |
+      Arabic "family marker" of Al (‫)آل‬: For Arabic-origin
+      names starting with the "family marker" of Al (‫)آل‬,
+      follow the Arabic standard of Al Davud (‫داود‬ ‫)آل‬ (not
+      Aldavud or Aledavud).
+
+    - |
+      Kunyas: In the rather rare case where
+      a Persian uses a kunya (a name for an adult normally
+      derived from his or her eldest child, and sometimes
+      employed as a nom de guerre), this name will be rendered
+      with a space separating the two elements (Abu Hosein, Abu
+      Ghasem). Note that this does not apply when the person's
+      given or family name was derived from a predecessor's
+      kunya. In these cases, the leading element should be
+      treated as a prefix as indicated below (Abuhosein[i],
+      Abughasem[i]).
+}
+
+tests {
+  test "مُوسَى", "musa"
+  test "مُؤمِن", "momen"
+  test "رِضايي", "rezai"
+  test "مُبَشِّر", "mobasher"
+  test "حَسَّان", "hassan"
+  test "حَسَن", "hasan"
+  test "صَفَّار", "saffar"
+  test "صَفَر", "safar"
+}
+
+dependency "odni-fas-Arab-Latn-2015", as: arablatn
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    # ta' marboota
+    sub "\u0629", "ah"
+
+    sub "\u0626", "" # ئ
+    sub "\u0624", "" # ؤ
+
+    # Farsi Vowel (Pointing)
+
+    # '\u064e\u0648' : 'ow'  # ـَو
+    # '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+
+    # additional symbols
+
+    # shadda
+
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0648\u0651", "ww" # و
+
+    sub "\u0621", "" # ء
+
+    # FROM NOTES
+
+    sub "\u064a\u064a", "i" # NOTE 4 (2)
+    sub "\u06cc\u06cc", "i"
+
+    sub "\u0627\u064a" + boundary, "i" # NOTE 4 (3)
+    sub "\u0627\u06cc" + boundary, "i"
+    sub "\u064f\u0648", "u" # ـُو damma followed by و     #gets broken by "w" lower
+
+    # Farsi consonant characters
+
+    sub "\u0639", "" # ع # new
+    sub "\u0642", "q" # ق
+    sub "\u0648", "w" # و
+  }
+
+  run map.arablatn.stage.main
+
+}
+