_ignore_base.yml

---
general:
  name: Common ignore list.
  description: List of Latin strings not converted.
  version: 1.0.0
  date: 2025-12-03

roman_to_script:
  ignore:
    - "At head of title"
    - "at head of title"
    - "Colophon"
    - "colophon"
    - "Cover title"
    - "date of publication not identified"
    - "place of publication not identified"
    - "publisher not identified"
    - "and one other"
    - "and others"
    - "et al."
  ignore_ptn:
    - "and ([a-z0-9]+ )?others"

    # Incorrectly entered (but frequently found) Roman numerals.
    # 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.
    - "I{2,3}\\b"
    - "I(V|X)\\b"
    - "LI{,3}\\b"
    - "LI?(V|X)\\b"
    - "L(V|X{1,3})I{,3}\\b"
    - "LX{1,3}I?V\\b"
    - "LX{1,3}VI{,3}\\b"
    - "VI{1,3}\\b"
    - "X{1,3}I{1,3}\\b"
    - "X{1,3}I(V|X)\\b"
    - "X{1,3}VI{,3}\\b"

    # MARC sub-field markers.
    - "[\u2021\u01C2\\$][0-9a-z]\\b"