Mercurial > hg
view contrib/fuzz/xdiff.cc @ 40978:42f59d3f714d
delta: exclude base candidate much smaller than the target
If a revision's full text is that much bigger than a base candidate full text,
we no longer consider that candidate.
This solves a pathological case we encountered on a very specify repository.
It contains a long series of changesets with a very small manifest (one file)
co-existing with others changesets using a very large manifest.
Without this filtering, we ended up considering a large number of tiny full
snapshots as a potential base. It resulted in very large delta (the size of
the full text) and mercurial spending 99% of its time compressing these
deltas.
The timing of a commit moved from about 400s to about 10s (still slow, but not
ridiculously slow).
author | Boris Feld <boris.feld@octobus.net> |
---|---|
date | Mon, 17 Dec 2018 10:42:19 +0100 |
parents | fa0ddd5e8fff |
children | 2e60a77b7058 |
line wrap: on
line source
/* * xdiff.cc - fuzzer harness for thirdparty/xdiff * * Copyright 2018, Google Inc. * * This software may be used and distributed according to the terms of * the GNU General Public License, incorporated herein by reference. */ #include "thirdparty/xdiff/xdiff.h" #include <inttypes.h> #include <stdlib.h> #include "fuzzutil.h" extern "C" { int hunk_consumer(long a1, long a2, long b1, long b2, void *priv) { // TODO: probably also test returning -1 from this when things break? return 0; } int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size) { auto maybe_inputs = SplitInputs(Data, Size); if (!maybe_inputs) { return 0; } auto inputs = std::move(maybe_inputs.value()); mmfile_t a, b; a.ptr = inputs.left.get(); a.size = inputs.left_size; b.ptr = inputs.right.get(); b.size = inputs.right_size; xpparam_t xpp = { XDF_INDENT_HEURISTIC, /* flags */ }; xdemitconf_t xecfg = { XDL_EMIT_BDIFFHUNK, /* flags */ hunk_consumer, /* hunk_consume_func */ }; xdemitcb_t ecb = { NULL, /* priv */ }; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; // Non-zero return values are reserved for future use. } #ifdef HG_FUZZER_INCLUDE_MAIN int main(int argc, char **argv) { const char data[] = "asdf"; return LLVMFuzzerTestOneInput((const uint8_t *)data, 4); } #endif } // extern "C"