Files
carbon-lang/toolchain/lexer/tokenized_buffer_fuzzer.cpp
T
Jon Meow af694b97cb Prefix most macro names with CARBON_ (#1232)
I'm doing this to avoid macro name conflicts, following https://google.github.io/styleguide/cppguide.html#Preprocessor_Macros: "If you do export a macro from a header, it must have a globally unique name. To achieve this, it must be named with a prefix consisting of your project's namespace name (but upper case)."

Commands run:

```
sed -i 's/\(DCHECK\|CHECK\|FATAL\|MAKE_UNIQUE_NAME\|MAKE_UNIQUE_NAME_IMPL\|RAW_EXITING_STREAM\|RETURN_IF_ERROR\|RETURN_IF_ERROR_IMPL\|ASSIGN_OR_RETURN\|ASSIGN_OR_RETURN_IMPL\|DIAGNOSTIC_KIND\|RETURN_IF_STACK_LIMITED\)(/CARBON_\1(/g' $(git ls-files *.cpp *.h *.lpp *.ypp *.def ':!third_party')
sed -i 's/#undef DIAGNOSTIC_KIND/#undef CARBON_DIAGNOSTIC_KIND/' toolchain/diagnostics/diagnostic_registry.def
```

Note this isn't *quite* everything, but it's intended to be a large pass at everything:

```
╚╡git grep '#define ' *.cpp *.h *.lpp *.ypp *.def ':!third_party' | grep -v '#define CARBON' | grep -v _H_
explorer/syntax/lexer.lpp:  #define YY_USER_ACTION                                             \
explorer/syntax/lexer.lpp:  #define SIMPLE_TOKEN(name) \
explorer/syntax/lexer.lpp:  #define ARG_TOKEN(name, arg) \
explorer/syntax/parse_and_lex_context.h:#define YY_DECL                                                         \
migrate_cpp/cpp_refactoring/var_decl.cpp:#define ABSTRACT_TYPE(Class, Base)
migrate_cpp/cpp_refactoring/var_decl.cpp:#define TYPE(Class, Base)     \
```

We may in particular want to do a pass to clean up #ifdef guards and make them be CARBON_ rooted.
2022-05-06 15:30:25 -07:00

53 lines
1.9 KiB
C++

// Part of the Carbon Language project, under the Apache License v2.0 with LLVM
// Exceptions. See /LICENSE for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#include <cstdint>
#include <cstring>
#include "common/check.h"
#include "llvm/ADT/StringRef.h"
#include "toolchain/diagnostics/diagnostic_emitter.h"
#include "toolchain/diagnostics/null_diagnostics.h"
#include "toolchain/lexer/tokenized_buffer.h"
namespace Carbon::Testing {
// NOLINTNEXTLINE: Match the documented fuzzer entry point declaration style.
extern "C" int LLVMFuzzerTestOneInput(const unsigned char* data,
std::size_t size) {
// Ignore large inputs.
// TODO: Investigate replacement with an error limit. Content with errors on
// escaped quotes (`\"` repeated) have O(M * N) behavior for M errors in a
// file length N, so either that will need to also be fixed or M will need to
// shrink for large (1MB+) inputs.
// This also affects parse_tree_fuzzer.cpp.
if (size > 100000) {
return 0;
}
auto source = SourceBuffer::CreateFromText(
llvm::StringRef(reinterpret_cast<const char*>(data), size));
auto buffer = TokenizedBuffer::Lex(*source, NullDiagnosticConsumer());
if (buffer.has_errors()) {
return 0;
}
// Walk the lexed and tokenized buffer to ensure it isn't corrupt in some way.
//
// TODO: We should enhance this to do more sanity checks on the resulting
// token stream.
for (TokenizedBuffer::Token token : buffer.tokens()) {
int line_number = buffer.GetLineNumber(token);
CARBON_CHECK(line_number > 0) << "Invalid line number!";
CARBON_CHECK(line_number < INT_MAX) << "Invalid line number!";
int column_number = buffer.GetColumnNumber(token);
CARBON_CHECK(column_number > 0) << "Invalid line number!";
CARBON_CHECK(column_number < INT_MAX) << "Invalid line number!";
}
return 0;
}
} // namespace Carbon::Testing