# A customized type mapping for WordDelimiterFilter
# the allowable types are: LOWER, UPPER, ALPHA, DIGIT, ALPHANUM, SUBWORD_DELIM
# 
# the default for any character without a mapping is always computed from 
# Unicode character properties

# Map the $, %, '.', and ',' characters to DIGIT 
# This might be useful for financial data.
$ => DIGIT
% => DIGIT
. => DIGIT
\u002C => DIGIT
# _ => SUBWORD_DELIM 
# / => DIGIT
# - => DIGIT


# in some cases you might not want to split on ZWJ
# this also tests the case where we need a bigger byte[]
# see http://en.wikipedia.org/wiki/Zero-width_joiner
\u200D => ALPHANUM