| 1 | // Licensed to the Apache Software Foundation (ASF) under one |
| 2 | // or more contributor license agreements. See the NOTICE file |
| 3 | // distributed with this work for additional information |
| 4 | // regarding copyright ownership. The ASF licenses this file |
| 5 | // to you under the Apache License, Version 2.0 (the |
| 6 | // "License"); you may not use this file except in compliance |
| 7 | // with the License. You may obtain a copy of the License at |
| 8 | // |
| 9 | // http://www.apache.org/licenses/LICENSE-2.0 |
| 10 | // |
| 11 | // Unless required by applicable law or agreed to in writing, |
| 12 | // software distributed under the License is distributed on an |
| 13 | // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 14 | // KIND, either express or implied. See the License for the |
| 15 | // specific language governing permissions and limitations |
| 16 | // under the License. |
| 17 | |
| 18 | //----------------------------------------------------------------------------- |
| 19 | // MurmurHash3 was written by Austin Appleby, and is placed in the public |
| 20 | // domain. The author hereby disclaims copyright to this source code. |
| 21 | |
| 22 | #ifndef PARQUET_MURMURHASH3_H_ |
| 23 | #define PARQUET_MURMURHASH3_H_ |
| 24 | |
| 25 | #include <cstdint> |
| 26 | |
| 27 | #include "parquet/hasher.h" |
| 28 | #include "parquet/platform.h" |
| 29 | #include "parquet/types.h" |
| 30 | |
| 31 | namespace parquet { |
| 32 | |
| 33 | /// Source: |
| 34 | /// https://github.com/aappleby/smhasher/blob/master/src/MurmurHash3.cpp |
| 35 | /// (Modified to adapt to coding conventions and to inherit the Hasher abstract class) |
| 36 | class PARQUET_EXPORT MurmurHash3 : public Hasher { |
| 37 | public: |
| 38 | MurmurHash3() : seed_(DEFAULT_SEED) {} |
| 39 | uint64_t Hash(int32_t value) const override; |
| 40 | uint64_t Hash(int64_t value) const override; |
| 41 | uint64_t Hash(float value) const override; |
| 42 | uint64_t Hash(double value) const override; |
| 43 | uint64_t Hash(const Int96* value) const override; |
| 44 | uint64_t Hash(const ByteArray* value) const override; |
| 45 | uint64_t Hash(const FLBA* val, uint32_t len) const override; |
| 46 | |
| 47 | private: |
| 48 | // Default seed for hash which comes from Bloom filter in parquet-mr, it is generated |
| 49 | // by System.nanoTime() of java. |
| 50 | static constexpr int DEFAULT_SEED = 1361930890; |
| 51 | |
| 52 | uint32_t seed_; |
| 53 | }; |
| 54 | |
| 55 | } // namespace parquet |
| 56 | |
| 57 | #endif // PARQUET_MURMURHASH3_H_ |
| 58 | |