fuzz: clean out most of fuzzutil

It's now a header-only setup that just selects absl:: or std::
versions of things as needed, and a logging helper. There's some room
for future cleanups here: we could move to just requiring a C++17
compiler and get rid of the absl stuff. Also, the mpatch parser has a
fair amount of parsing the input string into char* blocks that we can
and probably should fix that up to use FuzzedDataProvider as well.

Differential Revision: https://phab.mercurial-scm.org/D7370

contrib/fuzz/Makefile

@@ -1,184 +1,175 b''
 CC = clang
 CXX = clang++
 
 all: bdiff mpatch xdiff
 
-fuzzutil.o: fuzzutil.cc fuzzutil.h
-	$(CXX) $(CXXFLAGS) -g -O1 \
-	  -std=c++17 \
-	  -I../../mercurial -c -o fuzzutil.o fuzzutil.cc
-
-fuzzutil-oss-fuzz.o: fuzzutil.cc fuzzutil.h
-	$(CXX) $(CXXFLAGS) -std=c++17 \
-	  -I../../mercurial -c -o fuzzutil-oss-fuzz.o fuzzutil.cc
-
 pyutil.o: pyutil.cc pyutil.h
 	$(CXX) $(CXXFLAGS) -g -O1 \
 	  `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial -c -o pyutil.o pyutil.cc
 
 bdiff.o: ../../mercurial/bdiff.c
 	$(CC) $(CFLAGS) -fsanitize=fuzzer-no-link,address -c -o bdiff.o \
 	  ../../mercurial/bdiff.c
 
-bdiff: bdiff.cc bdiff.o fuzzutil.o
+bdiff: bdiff.cc bdiff.o 
 	$(CXX) $(CXXFLAGS) -DHG_FUZZER_INCLUDE_MAIN=1 -g -O1 -fsanitize=fuzzer-no-link,address \
 	  -std=c++17 \
-	  -I../../mercurial bdiff.cc bdiff.o fuzzutil.o -o bdiff
+	  -I../../mercurial bdiff.cc bdiff.o -o bdiff
 
 bdiff-oss-fuzz.o: ../../mercurial/bdiff.c
 	$(CC) $(CFLAGS) -c -o bdiff-oss-fuzz.o ../../mercurial/bdiff.c
 
-bdiff_fuzzer: bdiff.cc bdiff-oss-fuzz.o fuzzutil-oss-fuzz.o
+bdiff_fuzzer: bdiff.cc bdiff-oss-fuzz.o
 	$(CXX) $(CXXFLAGS) -std=c++17 -I../../mercurial bdiff.cc \
-	  bdiff-oss-fuzz.o fuzzutil-oss-fuzz.o -lFuzzingEngine -o \
+	  bdiff-oss-fuzz.o -lFuzzingEngine -o \
 	  $$OUT/bdiff_fuzzer
 
 mpatch.o: ../../mercurial/mpatch.c
 	$(CC) -g -O1 -fsanitize=fuzzer-no-link,address -c -o mpatch.o \
 	  ../../mercurial/mpatch.c
 
 mpatch: CXXFLAGS += -std=c++17
-mpatch: mpatch.cc mpatch.o fuzzutil.o
+mpatch: mpatch.cc mpatch.o
 	$(CXX) $(CXXFLAGS) -DHG_FUZZER_INCLUDE_MAIN=1 -g -O1 -fsanitize=fuzzer-no-link,address \
-	  -I../../mercurial mpatch.cc mpatch.o fuzzutil.o -o mpatch
+	  -I../../mercurial mpatch.cc mpatch.o -o mpatch
 
 mpatch-oss-fuzz.o: ../../mercurial/mpatch.c
 	$(CC) $(CFLAGS) -c -o mpatch-oss-fuzz.o ../../mercurial/mpatch.c
 
-mpatch_fuzzer: mpatch.cc mpatch-oss-fuzz.o fuzzutil-oss-fuzz.o
+mpatch_fuzzer: mpatch.cc mpatch-oss-fuzz.o 
 	$(CXX) $(CXXFLAGS) -std=c++17 -I../../mercurial mpatch.cc \
-	  mpatch-oss-fuzz.o fuzzutil-oss-fuzz.o -lFuzzingEngine -o \
+	  mpatch-oss-fuzz.o -lFuzzingEngine -o \
 	  $$OUT/mpatch_fuzzer
 
 mpatch_corpus.zip:
 	python mpatch_corpus.py $$OUT/mpatch_fuzzer_seed_corpus.zip
 
 x%.o: ../../mercurial/thirdparty/xdiff/x%.c ../../mercurial/thirdparty/xdiff/*.h
 	$(CC) -g -O1 -fsanitize=fuzzer-no-link,address -c \
 	  -o $@ \
 	  $<
 
 xdiff: CXXFLAGS += -std=c++17
-xdiff: xdiff.cc xdiffi.o xprepare.o xutils.o fuzzutil.o
+xdiff: xdiff.cc xdiffi.o xprepare.o xutils.o 
 	$(CXX) $(CXXFLAGS) -DHG_FUZZER_INCLUDE_MAIN=1 -g -O1 -fsanitize=fuzzer-no-link,address \
 	  -I../../mercurial xdiff.cc \
-	  xdiffi.o xprepare.o xutils.o fuzzutil.o -o xdiff
+	  xdiffi.o xprepare.o xutils.o -o xdiff
 
 fuzz-x%.o: ../../mercurial/thirdparty/xdiff/x%.c ../../mercurial/thirdparty/xdiff/*.h
 	$(CC) $(CFLAGS) -c \
 	  -o $@ \
 	  $<
 
-xdiff_fuzzer: xdiff.cc fuzz-xdiffi.o fuzz-xprepare.o fuzz-xutils.o fuzzutil-oss-fuzz.o
+xdiff_fuzzer: xdiff.cc fuzz-xdiffi.o fuzz-xprepare.o fuzz-xutils.o 
 	$(CXX) $(CXXFLAGS) -std=c++17 -I../../mercurial xdiff.cc \
-	  fuzz-xdiffi.o fuzz-xprepare.o fuzz-xutils.o fuzzutil-oss-fuzz.o \
+	  fuzz-xdiffi.o fuzz-xprepare.o fuzz-xutils.o \
 	  -lFuzzingEngine -o $$OUT/xdiff_fuzzer
 
 manifest.o: ../../mercurial/cext/manifest.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o manifest.o ../../mercurial/cext/manifest.c
 
 charencode.o: ../../mercurial/cext/charencode.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o charencode.o ../../mercurial/cext/charencode.c
 
 parsers.o: ../../mercurial/cext/parsers.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o parsers.o ../../mercurial/cext/parsers.c
 
 dirs.o: ../../mercurial/cext/dirs.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o dirs.o ../../mercurial/cext/dirs.c
 
 pathencode.o: ../../mercurial/cext/pathencode.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o pathencode.o ../../mercurial/cext/pathencode.c
 
 revlog.o: ../../mercurial/cext/revlog.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o revlog.o ../../mercurial/cext/revlog.c
 
 dirs_fuzzer: dirs.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial dirs.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/dirs_fuzzer
 
 fncache_fuzzer: fncache.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial fncache.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/fncache_fuzzer
 
 jsonescapeu8fast_fuzzer: jsonescapeu8fast.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial jsonescapeu8fast.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/jsonescapeu8fast_fuzzer
 
 manifest_corpus.zip:
 	python manifest_corpus.py $$OUT/manifest_fuzzer_seed_corpus.zip
 
 manifest_fuzzer: manifest.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial manifest.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/manifest_fuzzer
 
 revlog_fuzzer: revlog.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial revlog.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/revlog_fuzzer
 
 revlog_corpus.zip:
 	python revlog_corpus.py $$OUT/revlog_fuzzer_seed_corpus.zip
 
 dirstate_fuzzer: dirstate.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial dirstate.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/dirstate_fuzzer
 
 dirstate_corpus.zip:
 	python dirstate_corpus.py $$OUT/dirstate_fuzzer_seed_corpus.zip
 
 fm1readmarkers_fuzzer: fm1readmarkers.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial fm1readmarkers.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/fm1readmarkers_fuzzer
 
 fm1readmarkers_corpus.zip:
 	python fm1readmarkers_corpus.py $$OUT/fm1readmarkers_fuzzer_seed_corpus.zip
 
 clean:
 	$(RM) *.o *_fuzzer \
 	  bdiff \
 	  mpatch \
 	  xdiff
 
 oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer dirs_fuzzer fncache_fuzzer jsonescapeu8fast_fuzzer manifest_fuzzer manifest_corpus.zip revlog_fuzzer revlog_corpus.zip dirstate_fuzzer dirstate_corpus.zip fm1readmarkers_fuzzer fm1readmarkers_corpus.zip
 
 .PHONY: all clean oss-fuzz

contrib/fuzz/fuzzutil.h

@@ -1,47 +1,37 b''
 #ifndef CONTRIB_FUZZ_FUZZUTIL_H
 #define CONTRIB_FUZZ_FUZZUTIL_H
 #include <iostream>
 #include <memory>
 #include <stdint.h>
 
 /* Try and use std::optional, but failing that assume we'll have a
  * workable https://abseil.io/ install on the include path to get
  * their backport of std::optional. */
 #ifdef __has_include
 #if __has_include(<optional>) && __cplusplus >= 201703L
 #include <optional>
 #define CONTRIB_FUZZ_HAVE_STD_OPTIONAL
 #endif
 #endif
 #ifdef CONTRIB_FUZZ_HAVE_STD_OPTIONAL
 namespace contrib
 {
 using std::nullopt;
 using std::optional;
 } /* namespace contrib */
 #else
 #include "third_party/absl/types/optional.h"
 namespace contrib
 {
 using absl::nullopt;
 using absl::optional;
 } /* namespace contrib */
 #endif
 
 /* set DEBUG to 1 for a few debugging prints, or 2 for a lot */
 #define DEBUG 0
 #define LOG(level)                                                             \
 	if (level <= DEBUG)                                                    \
 	std::cout
 
-struct two_inputs {
-	std::unique_ptr<char[]> right;
-	size_t right_size;
-	std::unique_ptr<char[]> left;
-	size_t left_size;
-};
-
-/* Split a non-zero-length input into two inputs. */
-contrib::optional<two_inputs> SplitInputs(const uint8_t *Data, size_t Size);
-
 #endif /* CONTRIB_FUZZ_FUZZUTIL_H */