interscript-maps 2.4.3 → 2.5.0

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

@@ -1,164 +0,0 @@
-metadata {
-  authority_id: odni
-  id: 2015
-  language: iso-639-2:che
-  source_script: Cyrl
-  destination_script: Latn
-  name: ICS-630-01 Romanization of Chechen Cyrillic Personal Names (2015)
-  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]
-  }
-}

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

@@ -1,267 +0,0 @@
-metadata {
-  authority_id: odni
-  id: 2004
-  language: iso-639-2:fas
-  source_script: Arab
-  destination_script: Latn
-  name: Intelligence Community (IC) Standard for the Transliteration of Farsi (Persian) Personal Names (2004)
-  creation_date: 2004
-  confirmation_date: 2004-11
-  description: |
-
-  notes:
-    - Long/short vowels:- There is no distinction made in Roman
-      between long and short a:-  E.g., Parvas (first a is short,
-      second is long).
-    - Double consonants:-  Double consonants represented by the
-      tashdid are shown by doubling the Roman letter:-
-      Mo'azzami.  Exceptions:-  Ain and 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 beelow).
-    - 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
-      follow the Arabic rules for “sun letter” assimilation in
-      spoken form and reflect the nominative case.  That  is:-
-      Abdorrahman, not Abd al-Rahman.  Note also that the
-      “Abdollah” and “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, as in,
-      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 Farsi are spelled
-      according to the standard Western tradition (even if there
-      is an Arabic or Farsi version of the same name):-  Joseph,
-      Michael.
-    - Common suffixes, such as nia, pur, fard, far, abad,
-      zadeh, khah, and nezhad as well as nesbeh (‘relationship’ (
-      to place of birth, etc.)) names derived with these
-      suffixes  (e.g., nezhadi, abadi) are written as part of the
-      name:-
-
-      asa		Mehrasa
-      baksh		Tajbaksh
-      dust		Rafighdust
-      far		Parvizfar
-      fard		Akhavanfard
-      gar		Fuladgar
-      gol		Zarringol
-      kar		Parhizkar
-      khah		Vatankhah
-      khu		Nikkhu
-      mand		Purmand
-      mehr		Zadmehr
-      nezhad		Niknezhad
-      nia		Montajebnia
-      parast		Khodaparast
-      parvar		Golparvar
-      pur		Mohteshemipur
-      tabar		Shayestehtbar
-      yar		Mohammadyar
-      zadeh		Vakilzadeh
-
-      abadi		Salehabadi
-      khani		Alikhani
-      nezhadi 	Niknezhadi
-
-    - Note also that yar can function as a prefix and, as such,
-      should be affixed directly to the name:-
-
-      yar		Yarmohammadi, Yarshater
-
-    - This is in contrast with hyphenated names such as Raja’i-
-      Khorasani, Tabataba’i-Shirazi, Soleimani-Maimandi, etc.
-}
-
-tests {
-  test "مُوسَى", "musa"
-  test "مُؤمِن", "mo’men"
-  test "رِضايي", "reza’i"
-  test "مُبَشِّر", "mobasher"
-  test "حَسَّان", "hassan"
-  test "حَسَن", "hasan"
-  test "صَفَّار", "saffar"
-  test "صَفَر", "safar"
-}
-
-stage {
-
-  # CHARACTERS
-  parallel {
-    # special rules
-
-    sub space, "", after: "\u0622\u0628\u064E\u0627\u062F" # space followed by abad is removed
-    sub "\ufdf2", "Allah" # See note 5
-    sub space + "\u0627\u0644\u0644\u0651\u064e\u0647", "ollah" # NOTE 9
-
-    sub "\u0652", "" # ْ sokoon
-    sub "\u0659", "ê"
-
-    sub "\u064e\u064a\u0652", "ay" # ـَيْ
-    sub "\u0649\u0670", "á" # ىٰ
-    sub "\u0674", "-e" # ٴ
-    sub "\u0654", "-e" #  ٔ
-    # - '-ye'
-
-
-    # ta' marboota
-    sub "\u0629", "eh"
-
-
-
-    sub "\u0626", "’" # ئ
-    sub "\u0624", "’" # ؤ
-    sub "\u0623", "" # أ
-    sub "\u0625", "" # إ
-
-    # See note B
-    sub boundary + "\u0627\u0644", "al " # ال
-    sub boundary + "\u0622\u0644", "Al " # ‫آل‬
-    # '\uFE8E' : ''  # ﺎ
-
-    # Sun letters
-    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
-    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "as s" # الث
-    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
-    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az z" # الذ
-    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
-    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
-    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
-    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ash sh" # الش
-    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "as s" # الص
-    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "az z" # الض
-    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "at t" # الط
-    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az z" # الظ
-    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
-    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
-
-    # Farsi Vowel (Pointing)
-    sub "\u0622", "a" # آ alef maddeh
-    sub "\u064e", "a" # َ fatha
-    sub "\u0627", "", before: "\u064e" # ا
-    sub "\u0627", "a", not_before: boundary # ا
-    sub boundary + "\u0627\u064e", "a" # ا initial followed by fatha
-    sub boundary + "\u0627\u064f", "o" # ا initial followed by damma
-    sub boundary + "\u0627\u0650", "e" # ِ ا initial followed by kasra
-
-    sub "\u064f", "o" # damma
-    sub "\u064f\u0648", "u" # ـُو damma followed by و
-    # '\u064e\u0648' : 'ow'  # ـَو
-    # '\u064e\u0648\u0652' : 'aw'  # ـَوْ
-
-
-    sub "\u0650", "e" # kasra
-    sub "\u0650\u064a", "i" # ـِي kasra followed by ي
-    sub "\u0650\u06cc", "i" # ـِي kasra followed by ي
-    sub "\u0650\u064a\u0651\u064e", "iy" # ـِيَّ
-    sub "\u0650\u06cc\u0651\u064e", "iy" # ـِيَّ
-    sub "\u0650\u064a", "iy", after: any(["\u064e", "u064f"]) # ـِي kasra followed by ي
-    # '\u064e\u064a' : 'aī'  # ـَي
-    # '\u064e\u06cc' : 'aī'  # ـَي
-    # '\u064e\u0649' : 'ay'  # ـَى fatha followed by ى which is ا not ي
-
-    # additional symbols
-
-    # shadda
-
-    sub "\u0628\u0651", "bb" # ب
-    sub "\u062a\u0651", "tt" # ت
-    sub "\u062b\u0651", "ss" # ث
-    sub "\u062c\u0651", "jj" # ج
-    sub "\u062d\u0651", "hh" # ح
-    sub "\u062e\u0651", "kh" # خ
-    sub "\u062f\u0651", "dd" # د
-    sub "\u0630\u0651", "zz" # ذ
-    sub "\u0631\u0651", "rr" # ر
-    sub "\u0632\u0651", "zz" # ز
-    sub "\u0633\u0651", "ss" # س
-    sub "\u0634\u0651", "sh" # ش
-    sub "\u0635\u0651", "ss" # ص
-    sub "\u0636\u0651", "zz" # ض
-    sub "\u0637\u0651", "tt" # ط
-    sub "\u0638\u0651", "zz" # ظ
-    sub "\u063a\u0651", "gh" # غ
-    sub "\u0641\u0651", "ff" # ف
-    sub "\u0642\u0651", "gh" # ق
-    sub "\u0643\u0651", "kk" # ك
-    sub "\u0644\u0651", "ll" # ل
-    sub "\u0645\u0651", "mm" # م
-    sub "\u0646\u0651", "nn" # ن
-    sub "\u0647\u0651", "hh" # ه
-    sub "\u0648\u0651", "vv" # و
-    sub "\u064a\u0651", "yy" # ي
-
-    sub "\u0621", "", before: boundary # ء
-    sub "\u0621", "’" # ء
-
-    # FROM NOTES
-
-    sub "\u064e\u0649", "a" # ـَى fatha followed by ى which is ا not ي
-    sub "\u0649", "a" # ى alef maqsura NOTE-1
-
-    sub "\u064a\u064a", "’i" # NOTE 4 (2)
-    sub "\u06cc\u06cc", "’i"
-
-    sub "\u0627\u064a" + boundary, "’i" # NOTE 4 (3)
-    sub "\u0627\u06cc" + boundary, "’i"
-
-    # Farsi consonant characters
-
-    sub "\u0628", "b" # ب
-    sub "\u067E", "p" # پ
-    sub "\u062a", "t" # ت
-    sub "\u062B", "s" # ث
-    sub "\u062c", "j" # ج
-    sub "\u0686", "ch" # ‫چ‬
-    sub "\u062d", "h" # ح
-    sub "\u062e", "kh" # خ
-    sub "\u062f", "d" # د
-    sub "\u0630", "z" # ذ
-    sub "\u0631", "r" # ر
-    sub "\u0632", "z" # ز
-    sub "\u0698", "zh" # ‫ژ‬
-    sub "\u0633", "s" # س
-    sub "\u0634", "sh" # ش
-    sub "\u0635", "s" # ص
-    sub "\u0636", "z" # ض
-    sub "\u0637", "t" # ط
-    sub "\u0638", "z" # ظ
-    sub "\u0639", "‘" # ع
-    sub "\u0639", "", before: boundary # ع not represented initially
-    sub "\u063a", "gh" # غ
-    sub "\u0641", "f" # ف
-    sub "\u0642", "gh" # ق
-    sub "\u0643", "k" # ك
-    sub "\u06A9", "k" # ک
-    sub "\u06AF", "g" # ‫گ‬
-    sub "\u0644", "l" # ل
-    sub "\u0645", "m" # م
-    sub "\u0646", "n" # ن
-    sub "\u0647", "h" # ه
-    sub "\u0648", "v" # و
-    sub "\u064a", "y" # ي
-    sub "\u0649", "y" # ي
-    sub "\u06D0", "ē" # ې
-    sub "\u06CD", "êy" # ‫ۍ‬
-  }
-
-}