scriptshifter/scriptshifter/tables/data/_ignore_base.yml

general:
  name: Common ignore list.

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-z0-9]+ )?others"
    - "et al."

script_to_roman:
  ignore:
    - " "