mirror of
https://github.com/carbon-language/carbon-lang.git
synced 2026-09-24 22:02:23 +01:00
Jon Ross-Perkins
2de746e83c
I've been mulling this mainly for the parameter complexity of check/lower, but doing lex/parse for symmetry. I'm motivated by the plan to move dumping for all of them into the respective functions, because of discussion about llvm-verifier. That basically would add another bool parameter (or more) to each of these. My instinct is we're going to probably accrue a little more over time, so I'm suggesting this as maybe adding the boundary a little simpler and/or easier to read. Note it may make sense to refactor a little further, e.g. maybe Lower::Context could receive the full set of options and pick out what it wants, but I figured creating the struct itself would be a decent start. I'm trying to put things into options when we can produce a reasonable default if the user doesn't assign a value. I'm using an explicit constructor so that values can be added without affecting every caller. A different factoring would be to pass in everything through the param struct, but that just felt weird when I was trying it out. Removing `inst_namer` and `module_name` from `LowerToLLVM` params -- both of these can be inferred from `sem_ir`, and I'm not seeing a particular reason to maintain them at the call site.
62 lines
2.3 KiB
C++
62 lines
2.3 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 <cstring>
|
|
|
|
#include "common/check.h"
|
|
#include "llvm/ADT/StringRef.h"
|
|
#include "testing/fuzzing/libfuzzer.h"
|
|
#include "toolchain/base/shared_value_stores.h"
|
|
#include "toolchain/diagnostics/null_diagnostics.h"
|
|
#include "toolchain/lex/lex.h"
|
|
|
|
namespace Carbon::Testing {
|
|
|
|
// NOLINTNEXTLINE: Match the documented fuzzer entry point declaration style.
|
|
extern "C" int LLVMFuzzerTestOneInput(const unsigned char* data, 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/parse_fuzzer.cpp.
|
|
if (size > 100000) {
|
|
return 0;
|
|
}
|
|
static constexpr llvm::StringLiteral TestFileName = "test.carbon";
|
|
llvm::vfs::InMemoryFileSystem fs;
|
|
llvm::StringRef data_ref(reinterpret_cast<const char*>(data), size);
|
|
CARBON_CHECK(fs.addFile(
|
|
TestFileName, /*ModificationTime=*/0,
|
|
llvm::MemoryBuffer::getMemBuffer(data_ref, /*BufferName=*/TestFileName,
|
|
/*RequiresNullTerminator=*/false)));
|
|
auto source =
|
|
SourceBuffer::MakeFromFile(fs, TestFileName, Diagnostics::NullConsumer());
|
|
|
|
SharedValueStores value_stores;
|
|
Lex::LexOptions options;
|
|
options.consumer = &Diagnostics::NullConsumer();
|
|
auto buffer = Lex::Lex(value_stores, *source, options);
|
|
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 (Lex::TokenIndex 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
|