protobuf序列化编码实例分析

这几天把google protobuf官方文档通读了一遍, 总觉得对message序列化后的内容理解的不够透彻，因此动手操作一遍，分析一下message序列化后的内容。程序代码是官网的。

• proto文件内容

// file addressbook.proto
syntax = "proto3";
package tutorial;

message Person {
    string name = 1;
    int32 id = 2; // Unique ID number for this person.
    string email = 3;
    enum PhoneType {
        HOME = 0;
        MOBILE = 1;
        WORK = 2;
    }
    message PhoneNumber {
        string number = 1;
        PhoneType type = 2;
    }
    repeated PhoneNumber phone = 4;
}
message AddressBook {
    repeated Person person = 1;
}
service SearchService {
    rpc Search (Person) returns (Person);
}

• 序列化写入程序

#include <iostream>
#include <fstream>
#include <string>
#include "addressbook.pb.h"
using namespace std;

void PromptForAddress(tutorial::Person* person) {
    cout << "Enter person ID number: ";
    int id;
    cin >> id;
    person->set_id(id);
    cin.ignore(256, '\n');
    cout << "Enter name: ";
    getline(cin, *person->mutable_name());
    cout << "Enter email address (blank for none): ";
    string email;
    getline(cin, email);
    if (!email.empty()) {
        person->set_email(email);
    }
    while (true) {
        cout << "Enter a phone number (or leave blank to finish): ";
        string number;
        getline(cin, number);
        if (number.empty()) {
            break;
        }
        tutorial::Person::PhoneNumber* phone_number = person->add_phone();
        phone_number->set_number(number);

        cout << "Is this a mobile, home, or work phone? ";
        string type;
        getline(cin, type);
        if (type == "mobile") {
            phone_number->set_type(tutorial::Person::MOBILE);
        } else if (type == "home") {
            phone_number->set_type(tutorial::Person::HOME);
        } else if (type == "work") {
            phone_number->set_type(tutorial::Person::WORK);
        } else {
            cout << "Unknown phone type.  Using default." << endl;
        }
    }
}

int main(int argc, char* argv[]) {
    GOOGLE_PROTOBUF_VERIFY_VERSION;
    if (argc != 2) {
        cerr << "Usage:  " << argv[0] << " ADDRESS_BOOK_FILE" << endl;
        return -1;
    }
    tutorial::AddressBook address_book;
    {
        fstream input(argv[1], ios::in | ios::binary);
        if (!input) {
            cout << argv[1] << ": File not found.  Creating a new file." << endl;
        } else if (!address_book.ParseFromIstream(&input)) {
            cerr << "Failed to parse address book." << endl;
            return -1;
        }
    }
    PromptForAddress(address_book.add_person());
    {
        fstream output(argv[1], ios::out | ios::trunc | ios::binary);
        if (!address_book.SerializeToOstream(&output)) {
            cerr << "Failed to write address book." << endl;
            return -1;
        }
    }

    google::protobuf::ShutdownProtobufLibrary();

    return 0;
}

• 序列化读取程序

#include <iostream>
#include <fstream>
#include <string>
#include "addressbook.pb.h"

using namespace std;

void ListPeople(const tutorial::AddressBook& address_book) {
    for (int i = 0; i < address_book.person_size(); i++) {
        const tutorial::Person& person = address_book.person(i);
        cout << "Person ID: " << person.id() << endl;
        cout << "  Name: " << person.name() << endl;
        cout << "  E-mail address: " << person.email() << endl;
        for (int j = 0; j < person.phone_size(); j++) {
            const tutorial::Person::PhoneNumber& phone_number = person.phone(j);
            switch (phone_number.type()) {
                case tutorial::Person::MOBILE:
                    cout << "  Mobile phone #: ";
                    break;
                case tutorial::Person::HOME:
                    cout << "  Home phone #: ";
                    break;
                case tutorial::Person::WORK:
                    cout << "  Work phone #: ";
                    break;
            }
            cout << phone_number.number() << endl;
        }
    }
}

int main(int argc, char* argv[]) {
    GOOGLE_PROTOBUF_VERIFY_VERSION;
    if (argc != 2) {
        cerr << "Usage:  " << argv[0] << " ADDRESS_BOOK_FILE" << endl;
        return -1;
    }
    tutorial::AddressBook address_book;
    {
        fstream input(argv[1], ios::in | ios::binary);
        if (!address_book.ParseFromIstream(&input)) {
            cerr << "Failed to parse address book." << endl;
            return -1;
        }
    }

    ListPeople(address_book);

    google::protobuf::ShutdownProtobufLibrary();

    return 0;
}

执行写入程序:

root@instance-8alx1qc6-1:~/github/learning/protobuf/output# ./writer book
book: File not found.  Creating a new file.
Enter person ID number: 123
Enter name: ck
Enter email address (blank for none): ck@f.com
Enter a phone number (or leave blank to finish): 11
Is this a mobile, home, or work phone?
Unknown phone type.  Using default.
Enter a phone number (or leave blank to finish):

将message序列化到book文件里面，接下来我们看下book文件里面的内容：

root@instance-8alx1qc6-1:~/github/learning/protobuf/output# xxd -g 1 book
0000000: 0a 16 0a 02 63 6b 10 7b 1a 08 63 6b 40 66 2e 63  ....ck.{..ck@f.c
0000010: 6f 6d 22 04 0a 02 31 31                          om"...11

The available wire types are as follows:

我们逐个字节分析

0a: flag=1, wire type=2;
16: 22(也就是后面的所有内容长度)
0a: flag=1, wire type=2
02: 2(也就是后面字符串的长度为2)
63: 99，也就是c
6b: 107,也就是k
10: flag=2, wire type=0,也就是varint类型
7b: 123, 对应上id=123;
1a: flag=3, wire type=2
08: 8(也就是后面字符串的长度为8)
63 6b 40 66 2e 63 6f 6d: ck@f.com
22: flag=4, wire type=2
04: 4(后面内容的长度为4，也就是PhoneNumber的长度为4)
0a: flag=1, wire type=2;
02: 2(后面字符串的长度为2)
31 31: 11

在对字节和message各个字段的时候，一开始有个疑惑，为什么序列化的开头开头会有0a 16,想了好久，protobuf官网上也没找到相应的说明（或者我漏看了？），后来才发现0x16=22刚好是后面的字节总数,这是因为Person作为AddressBook的一个变量，作为变量的Message，外层将它作为Length-delimited类型看待。

参考

protobuf编码