From 0d25c6e70407a7e37cc4e12ce39bf5e3a2e78c96 Mon Sep 17 00:00:00 2001
From: Marcus Holland-Moritz <github@mhxnet.de>
Date: Tue, 18 Jul 2023 20:14:33 +0200
Subject: [PATCH] Basic categorizer fuzzer

---
 CMakeLists.txt             |  7 +++++
 test/fuzz_categorizers.cpp | 58 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+)
 create mode 100644 test/fuzz_categorizers.cpp

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 03a058c0..2db2ec42 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -29,6 +29,7 @@ include(CheckCXXSourceCompiles)
 
 option(WITH_TESTS "build with tests" OFF)
 option(WITH_BENCHMARKS "build with benchmarks" OFF)
+option(WITH_FUZZ "build with fuzzing binaries" OFF)
 option(ENABLE_PERFMON "enable performance monitor in all tools" ON)
 if(WIN32)
   set(PREFER_SYSTEM_LIBFMT ON)
@@ -586,6 +587,12 @@ if(WITH_BENCHMARKS)
   list(APPEND BINARY_TARGETS dwarfs_benchmark)
 endif()
 
+if(WITH_FUZZ)
+  add_executable(fuzz_categorizers test/fuzz_categorizers.cpp)
+  target_link_libraries(fuzz_categorizers "$<LINK_LIBRARY:WHOLE_ARCHIVE,dwarfs_categorizer>")
+  list(APPEND BINARY_TARGETS fuzz_categorizers)
+endif()
+
 if(WITH_MAN_PAGES)
   list(REMOVE_DUPLICATES MAN_DIRS)
   add_custom_target(manpages ALL DEPENDS ${MAN_PAGES})
diff --git a/test/fuzz_categorizers.cpp b/test/fuzz_categorizers.cpp
new file mode 100644
index 00000000..97349326
--- /dev/null
+++ b/test/fuzz_categorizers.cpp
@@ -0,0 +1,58 @@
+/* vim:set ts=2 sw=2 sts=2 et: */
+/**
+ * \author     Marcus Holland-Moritz (github@mhxnet.de)
+ * \copyright  Copyright (c) Marcus Holland-Moritz
+ *
+ * This file is part of dwarfs.
+ *
+ * dwarfs is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * dwarfs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with dwarfs.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <filesystem>
+
+#include <boost/program_options.hpp>
+
+#include "dwarfs/categorizer.h"
+#include "dwarfs/logger.h"
+#include "dwarfs/mmap.h"
+
+using namespace dwarfs;
+
+int main(int argc, char** argv) {
+  if (argc < 2) {
+    return 1;
+  }
+
+  stream_logger lgr(std::cerr);
+
+  auto& catreg = categorizer_registry::instance();
+  auto catmgr = std::make_shared<categorizer_manager>(lgr);
+
+  boost::program_options::variables_map vm;
+  catmgr->add(catreg.create(lgr, "pcmaudio", vm));
+
+#ifdef __AFL_LOOP
+  while (__AFL_LOOP(10000))
+#endif
+  {
+    std::filesystem::path p(argv[1]);
+    auto mm = mmap(p);
+    auto job = catmgr->job(p);
+    job.set_total_size(mm.size());
+    job.categorize_random_access(mm.span());
+    auto res [[maybe_unused]] = job.result();
+  }
+
+  return 0;
+}