On Mon, 12 Feb 2024, Stephen J. Turnbull wrote:
...snip...
Otherwise, not generically, short of plugging in a well-trained LLM. The problem is that quoting conventions etc differ across mail clients, as do signature blocks. If the signature appears below the quoted footer, it will become quite complex to decide how much to remove, especially since some "modern" (aka nonconformant) clients don't conform to the traditional signature inclusion conventions.
That's just silly: We've had "diff" for over THREE full decades now, to say nothing of the variants.
A VERY straight-forward strategy would be to diff the current inbound against the previous one it was in reply to - using threading as already cited. No LLM is needed, well trained or otherwise, and neither is it "quite complex." It's surely far easier than spam detection!
Richard