text-validator.toml

["text_validator.plugins.whitespace"]
CHECK_CRLF = true
CHECK_TABS = true
CHECK_TRAILING_WHITESPACE = true
CHECK_NO_EOF_NEWLINE = true

["text_validator.plugins.unicode"]
CONFIRM_UTF_8_NFC = true

["text_validator.plugins.ref_line_format"]
REF_REGEX = "(\\d+\\.\\d+$|p\\d+\\.head+$|p\\d+\\.subscript+$|\\d+\\.head+$||\\d+\\.note+$|\\d+\\.\\d+\\.\\d+a$)"

["text_validator.plugins.characters"]
REPLACE_CHARS = [
    # bad character, suggested replacement
    ["\u02BC", "\u2019"],
    ["\u1FBF", "\u2019"],
    ["\u037E", "\u003B"],
    ["\u0387", "\u00B7"],
    ["\u0374", "\u02B9"],
    ["\u03D5", "\u03C6"],
    ["\u03D1", "\u03B8"],
]
TOKEN_REGEXES = [
    # each whitespace-separated token must match one of these regexes
    "\\d+\\.\\d+\\.\\d+$",
    "\\d+.[A-F]\\.\\d+$",
    "\\d+\\.\\d+\\.\\d+[a-z]$",
    "\\d+\\.\\d+\\.\\d+\\-\\d+$",
    "\\d+\\.title$",
    "\\d+\\.note$",
    "title\\.0$",
    "[\u201C(]*[A-Za-z\u2019\\-]+[.,:;)\u201D]?$",
    "[«(\u201C\u2019]*[\u0370-\u03FF\u1F00-\u1FFF]+\u2019?[.,:;»)·\u2014\u201D]*$",
    "\u2014$",
    "\\([A-Za-z]\\)$",
    "ξβʹ$",
    "εʹ$",
    "ιʹ$",
]