%***************************************************************************%
% %
% Copyright (C) 2005, 2006 Sampo Pyysalo, Sophie Aubin %
% Copyright (C) 2009, 2012 Linas Vepstas %
% See file "LICENSE" for information about commercial use of this system %
% %
%***************************************************************************%
% We demand that these end with an alphanumeric, i.e. explicitly
% reject punctuation. We don't want this regex to "swallow" any trailing
% commas, colons, or periods/question-marks at the end of sentences.
% In addition, this must not swallow words ending in 's 'll etc.
% (... any affix, for that matter ...) and so no embedded apostrophe
CAPITALIZED-WORDS: /^[[:upper:]][^'’]*[^[:punct:]]$/
% Look for at least four in a row.
%<UNKNOWN-WORD>: /^[.,-]{4}[.,-]*$/