scriptshifter/transliterator/tables/data/_cyrillic_base.yml

general:
  name: Cyrillic base
  notes: >
    copied from Russian .cfg file and stripped
    off language-specific tokens. Russian ignore list
    has been left here on purpose, assuming it's valid
    for all child languages.

roman_to_script:
  ignore:
    - "at head of title"
    - "colophon"
    - "date of publication not identified"
    - "place of publication not identified"
    - "publisher not identified"
    # NOTE There is ambiguity about ignoring these
    # words. Note that the single-character Roman
    # numerals are not included on purpose.
    # Ideally the source editors should use the
    # dedicated U+2160÷U+216F (uppercase Roman
    # numerals) and/or U+2170÷U+217F (lower case Roman
    # numerals) ranges to avoid this ambiguity.
    # TODO implement regular expressions for ignore patterns.
    #- re: "I{2,3}"
    #- re: "I(V|X)"
    #- re: "LI{,3}"
    #- re: "LI?(V|X)"
    #- re: "L(V|X{1,3})I{,3}"
    #- re: "LX{1,3}I?V"
    #- re: "LX{1,3}VI{,3}"
    #- re: "(V|X{1,3})I{,3}"
    #- re: "X{1,3}I{,3}"
    #- re: "X{1,3}I(V|X)"
    #- re: "X{1,3}VI{,3}"
    - "II"
    - "III"
    - "IV"
    - "IX"
    - "LI"
    - "LII"
    - "LIII"
    - "LIV"
    - "LIX"
    - "LV"
    - "LVI"
    - "LVII"
    - "LVIII"
    - "LX"
    - "LXI"
    - "LXII"
    - "LXIII"
    - "LXIV"
    - "LXIX"
    - "LXV"
    - "LXVI"
    - "LXVII"
    - "LXVIII"
    - "LXX"
    - "LXXI"
    - "LXXII"
    - "LXXIII"
    - "LXXIV"
    - "LXXIX"
    - "LXXV"
    - "LXXVI"
    - "LXXVII"
    - "LXXVIII"
    - "LXXX"
    - "LXXXI"
    - "LXXXII"
    - "LXXXIII"
    - "LXXXIV"
    - "LXXXIX"
    - "LXXXV"
    - "LXXXVI"
    - "LXXXVII"
    - "LXXXVIII"
    - "VI"
    - "VII"
    - "VIII"
    - "XI"
    - "XII"
    - "XIII"
    - "XIV"
    - "XIX"
    - "XL"
    - "XLI"
    - "XLII"
    - "XLIII"
    - "XLIV"
    - "XLIX"
    - "XLV"
    - "XLVI"
    - "XLVII"
    - "XLVIII"
    - "XV"
    - "XVI"
    - "XVII"
    - "XVIII"
    - "XX"
    - "XXI"
    - "XXII"
    - "XXIII"
    - "XXIV"
    - "XXIX"
    - "XXV"
    - "XXVI"
    - "XXVII"
    - "XXVIII"
    - "XXX"
    - "XXXI"
    - "XXXII"
    - "XXXIII"
    - "XXXIV"
    - "XXXIX"
    - "XXXV"
    - "XXXVI"
    - "XXXVII"
    - "XXXVIII"
    - "and one other"
    #- re: "and ([a-z]+ )?others"
    - "et al."

  map:
    "A": "\u0410"
    "a": "\u0430"
    "B": "\u0411"
    "b": "\u0431"
    "V": "\u0412"
    "v": "\u0432"
    "D": "\u0414"
    "d": "\u0434"
    "E": "\u0415"
    "e": "\u0435"
    # this conversion shouldn't be needed, but does no harm
    "Z": "\u0417"
    "z": "\u0437"
    "I\u0306": "\u0419"
    # this conversion shouldn't be needed, but does no harm
    "I\uFE20U\uFE21": "\u042E"
    # this conversion shouldn't be needed, but does no harm
    "I\uFE20u\uFE21": "\u042E"
    "I\uFE20A\uFE21": "\u042F"
    # this conversion shouldn't be needed, but does no harm
    "I\uFE20a\uFE21": "\u042F"
    "i\u0306": "\u0439"
    "i\uFE20u\uFE21": "\u044E"
    "i\uFE20a\uFE21": "\u044F"
    # this conversion shouldn't be needed, but does no harm
    "KH": "\u0425"
    "Kh": "\u0425"
    "K": "\u041A"
    "kh": "\u0445"
    "k": "\u043A"
    "L": "\u041B"
    "l": "\u043B"
    "M": "\u041C"
    "m": "\u043C"
    "N": "\u041D"
    "n": "\u043D"
    "O": "\u041E"
    "o": "\u043E"
    "P": "\u041F"
    "p": "\u043F"
    "R": "\u0420"
    "r": "\u0440"
    # this conversion shouldn't be needed, but does no harm
    # this conversion shouldn't be needed, but does no harm
    "SH": "\u0428"
    "Sh": "\u0428"
    "S": "\u0421"
    "sh": "\u0448"
    "s": "\u0441"
    # this conversion shouldn't be needed, but does no harm
    "T": "\u0422"
    "t": "\u0442"
    "U": "\u0423"
    "u": "\u0443"
    "F": "\u0424"
    "f": "\u0444"
    # this conversion shouldn't be needed, but does no harm
    "CH": "\u0427"
    "Ch": "\u0427"
    "ch": "\u0447"
    # this conversion shouldn't be needed, but does no harm
    "\uFE20": ""
    # this conversion shouldn't be needed, but does no harm
    "\uFE21": ""
    # this conversion is ambiguous - \u042C is also theoretically possible
    "\u02B9": "\u044C"

script_to_roman:
  map:
    "\u0404": "I\uFE20E\uFE21"
    "\u0407": "I\u0308"
    "\u0410": "A"
    "\u0411": "B"
    "\u0412": "V"
    "\u0414": "D"
    "\u0415": "E"
    "\u0417": "Z"
    "\u0419": "I\u0306"
    "\u041A": "K"
    "\u041B": "L"
    "\u041C": "M"
    "\u041D": "N"
    "\u041E": "O"
    "\u041F": "P"
    "\u0420": "R"
    "\u0421": "S"
    "\u0422": "T"
    "\u0423": "U"
    "\u0424": "F"
    "\u0425": "Kh"
    "\u0427": "Ch"
    "\u0428": "Sh"
    "\u0429": "Shch"
    "\u042C": "\u02B9"
    "\u042E": "I\uFE20U\uFE21"
    "\u042F": "I\uFE20A\uFE21"
    "\u0430": "a"
    "\u0431": "b"
    "\u0432": "v"
    "\u0434": "d"
    "\u0435": "e"
    "\u0437": "z"
    "\u0439": "i\u0306"
    "\u043A": "k"
    "\u043B": "l"
    "\u043C": "m"
    "\u043D": "n"
    "\u043E": "o"
    "\u043F": "p"
    "\u0440": "r"
    "\u0441": "s"
    "\u0442": "t"
    "\u0443": "u"
    "\u0444": "f"
    "\u0445": "kh"
    "\u0447": "ch"
    "\u0448": "sh"
    "\u0449": "shch"
    "\u044C": "\u02B9"
    "\u044E": "i\uFE20u\uFE21"
    "\u044F": "i\uFE20a\uFE21"