利用C++开发一个protobuf动态解析工具

int DynamicParseFromPBFile(const std::string& file, const std::string& classname, 
      const std::string& pb_str) {
  // ...
  // 导入proto文件
  ::Google::protobuf::compiler::Importer importer(&sourceTree, NULL);
  importer.Import(file);

  // 找到要解析的message
  auto descriptor = importer.pool()->FindMessageTypeByName(classname);
  ::google::protobuf::DynamicMessageFactory factory;
  auto message = factory.GetPrototype(descriptor);

  // 动态创建message对象
  auto msg = message->New();
  msg->ParseFromString(pb_str);
  // msg即为解析到的结构
}

message MyMsg {
  optional uint64 id = 1;
  optional OtherMsg other = 2;
}

bool SourceTreeDescriptorDatabase::FindFileByName(const std::string& filename,
                                                  FileDescriptorProto* output) {
  // ...
  io::Tokenizer tokenizer(input.get(), &file_error_collector);
  
  Parser parser;
  
  // Parse it.
  output->set_name(filename);
  return parser.Parse(&tokenizer, output) && !file_error_collector.had_errors();
}

message FileDescriptorProto {
  optional string name = 1;     // file name, relative to root of source tree
  optional string package = 2;  // e.g. "foo", "foo.bar", etc.

  // All top-level definitions in this file.
  repeated DescriptorProto message_type = 4;
  repeated EnumDescriptorProto enum_type = 5;
  repeated ServiceDescriptorProto service = 6;
  repeated FieldDescriptorProto extension = 7;

  // ...
}

// proto输入
istringstream ss(proto);
istream* is = &ss;
io::IstreamInputStream input(is);

// 解析到FileDescriptorProto AST
io::Tokenizer tokenizer(&input, nullptr);
FileDescriptorProto output;
compiler::Parser parser;
if (!parser.Parse(&tokenizer, &output)) {
  err_msg = "parse proto failed";
  return -1;
}
output.set_name("proto");
output.clear_source_code_info();
printf("MSG: proto parsed output: %s\n", output.DebugString().c_str());

int ConvertUnknownType2Bytes(FileDescriptorProto& file_descriptor_proto) {
  // 找出所有给出定义的message类型名
  set<string> typename_set;
  for (auto const& msgtype : file_descriptor_proto.message_type()) {
    typename_set.insert(msgtype.name());
    // message内嵌套定义的message也要包含在内
    for (auto const& subtype : msgtype.nested_type()) {
      typename_set.insert(subtype.name());
    }
  }

  // 遍历所有field，检查其类型是否存在定义
  for (auto& msgtype : *file_descriptor_proto.mutable_message_type()) {
    for (auto& field : *msgtype.mutable_field()) {
      auto type_name = field.type_name();
      // 基本类型的type_name是空的
      if (!type_name.empty()) {
        // 如果typename_set中找不到该类型名，则转为bytes类型
        if (typename_set.find(type_name) == typename_set.end()) {
          field.clear_type_name();
          field.set_type(FieldDescriptorProto_Type_TYPE_BYTES);
        }
      }
    }
  }
  return 0;
}

// 解析proto并检查错误
SimpleDescriptorDatabase db;
db.Add(output);
DescriptorPool pool(&db);
auto descriptor = pool.FindMessageTypeByName(msg_type_name);
if (descriptor == nullptr) {
  // proto结构有错
  err_msg = "parse proto failed. FindMessageTypeByName result is null";
  return -1;
}

DynamicMessageFactory factory;
auto message = factory.GetPrototype(descriptor);
unique_ptr<Message> msg(message->New());

msg->ParseFromString(serilized_pb);
cout << "proto msg: " << msg->ShortDebugString().c_str() << endl;