We were consuming certain symbols after `\uNNNN` during tokenization. This led to an *extra* character being consumed as the "fallback," so letters went missing after encoded unicode characters. Closes #11981.
363 B
363 B
% pandoc -f native -t rtf | pandoc -f rtf -t native
[ Para [ Str "abc\8217def" ]
, Para [ Str "\8220abc\8221" , Space , Str "\8216abc\8217" ]
, Para [ Str "abc\8217def" ]
, Para [ Str "abc\8212def" ]
]
^D
[ Para [ Str "abc\8217def" ]
, Para [ Str "\8220abc\8221" , Space , Str "\8216abc\8217" ]
, Para [ Str "abc\8217def" ]
, Para [ Str "abc\8212def" ]
]