Skip to content

Commit

Permalink
[libc++] Fix wrong implementation of CityHash
Browse files Browse the repository at this point in the history
As PR56606 stated, the current implementation of CityHash in libc++
would drop some bits unintentionally. Cast the 32bit int to the 64bit
int to avoid this happened.

Reviewed By: ldionne, #libc

Differential Revision: https://reviews.llvm.org/D134124
  • Loading branch information
oToToT committed Oct 5, 2022
1 parent b61860e commit 0da59bb
Show file tree
Hide file tree
Showing 2 changed files with 37 additions and 1 deletion.
2 changes: 1 addition & 1 deletion libcxx/include/__functional/hash.h
Expand Up @@ -135,7 +135,7 @@ struct __murmur2_or_cityhash<_Size, 64>
if (__len >= 4) {
const uint32_t __a = __loadword<uint32_t>(__s);
const uint32_t __b = __loadword<uint32_t>(__s + __len - 4);
return __hash_len_16(__len + (__a << 3), __b);
return __hash_len_16(__len + (static_cast<_Size>(__a) << 3), __b);
}
if (__len > 0) {
const unsigned char __a = static_cast<unsigned char>(__s[0]);
Expand Down
@@ -0,0 +1,36 @@
//===----------------------------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//

// Test the CityHash implementation is correct.

// UNSUPPORTED: c++03

#include <cassert>
#include <string>
#include <utility>

#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
# define CHOOSE_BY_ENDIANESS(little, big) (little)
#else
# define CHOOSE_BY_ENDIANESS(little, big) (big)
#endif

int main(int, char**) {
const std::pair<std::string, uint64_t> TestCases[] = {
{"abcdefgh", CHOOSE_BY_ENDIANESS(0x4382a8d0fe8edb17ULL, 0xca84e809bef16fbcULL)},
{"abcDefgh", CHOOSE_BY_ENDIANESS(0xecefb080a6854061ULL, 0xd7feb824250272dcULL)},
{"CityHash", CHOOSE_BY_ENDIANESS(0x169ea3aebf908d6dULL, 0xea8cef3ca6f6e368ULL)},
{"CitYHash", CHOOSE_BY_ENDIANESS(0xe18298a2760f09faULL, 0xf33a7700bb7a94a8ULL)},
};

std::__murmur2_or_cityhash<uint64_t> h64;
for (const auto& test_case : TestCases) {
assert(h64(test_case.first.data(), test_case.first.size()) == test_case.second);
}
return 0;
}

0 comments on commit 0da59bb

Please sign in to comment.