Composible parsers are indeed an open research problem, but it'd be wise to consider them more like the philosophers stone. Even humans find unambiguity in their languages which are quite well structured, yet some people are hanging onto the hope that a machine will be able to take arbitrary combinations of partially structured clauses and produce some kind of unambiguity. It isn't going to happen.

At least not with plain text. There's some terrfic research in composing languages - currently the best is Tratt and Diekmann's Language Boxes, which enable arbitrary syntax composition by means of the programmer specifying the syntax boundaries explicitly - which requires a more sophisticated editor than out plain text notepad variants.

With language boxes, and their prototype editor Eco, in the end, they're ultimately storing a tree of data in their own custom format - it doesn't matter what encoding is used, just as it doesn't matter whether lisp uses parens, braces or whitespace - what really matters is that you encode things deterministically into trees which can be easily reasoned about without requiring some "magic" (AI) which attempts to create a tree from a sequence of characters unambiguously, when the programmer knows and can specify exactly what he means.