annotate contrib/fuzz/xdiff.cc @ 43813:5a9e2ae9899b

fuzz: use a more standard approach to allow local builds of fuzzers

This is taken from the (improved since we started fuzzing) guide on ideal
integrations. Rather than have our own wonky targets for building outside the
fuzzer universe, we have a driver program we carry along and use when we're
not using LibFuzzer. This will let us jettison a fair amount of goo.

contrib/fuzz/standalone_fuzz_target_runner.cc is
https://github.com/google/oss-fuzz/ file
projects/example/my-api-repo/standalone from git revision
c4579d9358a73ea5dbcc99cb985de1f2bf76dcf7, reformatted with out
clang-format settings and a no-check-code comment added. It allows
running a single test input through a fuzzer, rather than performing
ongoing fuzzing as libfuzzer would.

contrib/fuzz/FuzzedDataProvider.h is
https://github.com/llvm/llvm-project/ file
/compiler-rt/include/fuzzer/FuzzedDataProvider.h from git revision
a44ef027ebca1598892ea9b104d6189aeb3bc2f0, reformatted with our
clang-format settings and a no-check-code comment added. We can
discard this if we instead want to add an hghave check for a new
enough llvm that includes FuzzedDataProvder.h in the fuzzer headers.

Differential Revision: https://phab.mercurial-scm.org/D7564

/*
 * 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 "FuzzedDataProvider.h"

extern "C" {

int LLVMFuzzerInitialize(int *argc, char ***argv)
{
	return 0;
}

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)
{
	// Don't allow fuzzer inputs larger than 100k, since we'll just bog
	// down and not accomplish much.
	if (Size > 100000) {
		return 0;
	}
	FuzzedDataProvider provider(Data, Size);
	std::string left = provider.ConsumeRandomLengthString(Size);
	std::string right = provider.ConsumeRemainingBytesAsString();
	mmfile_t a, b;

	a.ptr = (char *)left.c_str();
	a.size = left.size();
	b.ptr = (char *)right.c_str();
	b.size = 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"