this is an issue that we are currently thinking about and working on. It would, of course, be very desirable to implement, but we haven’t decided yet on how to do so best. Particularly for the interactions it may be complex. But, for the ‘regular’ weighted effect coding (=without interaction), it should be easy to implement, for instance as follows:

library(questionr)
contr.wecw <- function (x, omitted, w)
{
frequencies <- wtd.table(x, weights=w)
n.cat <- length(table(x))
omitted <- which(levels(x) == omitted)
new.contrasts <- contr.treatment(n.cat, base = omitted)
new.contrasts[omitted, ] <- -1 * frequencies[-omitted]/frequencies[omitted]
colnames(new.contrasts) <- names(frequencies[-omitted])
return(new.contrasts)
}