Home | History | Annotate | Download | only in strings
      1 /* Copyright 2018 The TensorFlow Authors. All Rights Reserved.
      2 
      3 Licensed under the Apache License, Version 2.0 (the "License");
      4 you may not use this file except in compliance with the License.
      5 You may obtain a copy of the License at
      6 
      7     http://www.apache.org/licenses/LICENSE-2.0
      8 
      9 Unless required by applicable law or agreed to in writing, software
     10 distributed under the License is distributed on an "AS IS" BASIS,
     11 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     12 See the License for the specific language governing permissions and
     13 limitations under the License.
     14 ==============================================================================*/
     15 #include "tensorflow/core/lib/strings/proto_serialization.h"
     16 
     17 #include <cstring>
     18 #include "absl/memory/memory.h"
     19 #include "absl/strings/string_view.h"
     20 #include "tensorflow/core/lib/gtl/inlined_vector.h"
     21 #include "tensorflow/core/lib/hash/hash.h"
     22 #include "tensorflow/core/platform/logging.h"
     23 #include "tensorflow/core/platform/macros.h"
     24 
     25 namespace tensorflow {
     26 namespace {
     27 static const int kInlinedBufferSize = 256;
     28 }  // namespace
     29 
     30 bool SerializeToStringDeterministic(const protobuf::MessageLite& msg,
     31                                     string* result) {
     32   const size_t size = msg.ByteSizeLong();
     33   DCHECK_LE(size, static_cast<size_t>(INT_MAX));
     34   *result = string(size, '\0');
     35   return SerializeToBufferDeterministic(msg, const_cast<char*>(result->data()),
     36                                         result->size());
     37 }
     38 
     39 bool SerializeToBufferDeterministic(const protobuf::MessageLite& msg,
     40                                     char* buffer, size_t size) {
     41   DCHECK(msg.ByteSizeLong() == size && size <= static_cast<size_t>(INT_MAX));
     42   protobuf::io::ArrayOutputStream array_stream(buffer, size);
     43   protobuf::io::CodedOutputStream output_stream(&array_stream);
     44   output_stream.SetSerializationDeterministic(true);
     45   msg.SerializeWithCachedSizes(&output_stream);
     46   return !output_stream.HadError() && size == output_stream.ByteCount();
     47 }
     48 
     49 bool AreSerializedProtosEqual(const protobuf::MessageLite& x,
     50                               const protobuf::MessageLite& y) {
     51   const size_t size = x.ByteSizeLong();
     52   if (size != y.ByteSizeLong()) return false;
     53   if (size == 0) return true;
     54   gtl::InlinedVector<char, kInlinedBufferSize> x_serialized(size);
     55   bool success_x = SerializeToBufferDeterministic(x, x_serialized.data(), size);
     56   DCHECK(success_x);
     57   gtl::InlinedVector<char, kInlinedBufferSize> y_serialized(size);
     58   bool success_y = SerializeToBufferDeterministic(y, y_serialized.data(), size);
     59   DCHECK(success_y);
     60   return memcmp(x_serialized.data(), y_serialized.data(), size) == 0;
     61 }
     62 
     63 uint64 DeterministicProtoHash64(const protobuf::MessageLite& proto,
     64                                 uint64 seed) {
     65   const size_t size = proto.ByteSizeLong();
     66   gtl::InlinedVector<char, kInlinedBufferSize> serialized(size);
     67   SerializeToBufferDeterministic(proto, serialized.data(), size);
     68   return Hash64(serialized.data(), size, seed);
     69 }
     70 
     71 uint64 DeterministicProtoHash64(const protobuf::MessageLite& proto) {
     72   const size_t size = proto.ByteSizeLong();
     73   gtl::InlinedVector<char, kInlinedBufferSize> serialized(size);
     74   SerializeToBufferDeterministic(proto, serialized.data(), size);
     75   return Hash64(serialized.data(), size);
     76 }
     77 
     78 }  // namespace tensorflow
     79