What does the protobuf text format look like?

Done myself:

test.proto

enum MyEnum
{
    Default = 0;
    Variant1 = 1;
    Variant100 = 100;
}

message Test {
    required string f1 = 1;
    required int64 f2 = 2;
    repeated uint64 fa = 3;
    repeated int32 fb = 4;
    repeated int32 fc = 5 [packed = true];
    repeated Pair pairs = 6;
    optional bytes bbbb = 7;

    extensions 100 to max;
}

message Pair {
    required string key = 1;
    optional string value = 2;
}



extend Test {
    optional bool gtt = 100;
    optional double gtg = 101;
    repeated MyEnum someEnum = 102;
}

example output:

f1: "dsfadsafsaf"
f2: 234
fa: 2342134
fa: 2342135
fa: 2342136
fb: -2342134
fb: -2342135
fb: -2342136
fc: 4
fc: 7
fc: -12
fc: 4
fc: 7
fc: -3
fc: 4
fc: 7
fc: 0
pairs {
  key: "sdfff"
  value: "q\"qq\\q\n"
}
pairs {
  key: "   sdfff2  \321\202\320\265\321\201\321\202 "
  value: "q\tqq<>q2&\001\377"
}
bbbb: "\000\001\002\377\376\375"
[gtt]: true
[gtg]: 20.0855369
[someEnum]: Variant1

the program:

#include <google/protobuf/text_format.h>

#include <stdio.h>
#include "test.pb.h"

int main() {
    Test t;
    t.set_f1("dsfadsafsaf");
    t.set_f2(234);
    t.add_fa(2342134);
    t.add_fa(2342135);
    t.add_fa(2342136);
    t.add_fb(-2342134);
    t.add_fb(-2342135);
    t.add_fb(-2342136);
    t.add_fc(4);
    t.add_fc(7);
    t.add_fc(-12);
    t.add_fc(4);
    t.add_fc(7);
    t.add_fc(-3);
    t.add_fc(4);
    t.add_fc(7);
    t.add_fc(0);
    t.set_bbbb("\x00\x01\x02\xff\xfe\xfd",6);

    Pair *p1 = t.add_pairs(), *p2 = t.add_pairs();
    p1->set_key("sdfff");
    p1->set_value("q\"qq\\q\n");
    p2->set_key("   sdfff2  ั‚ะตัั‚ ");
    p2->set_value("q\tqq<>q2&\x01\xff");

    t.SetExtension(gtt, true);
    t.SetExtension(gtg, 20.0855369);
    t.AddExtension(someEnum, Variant1);

    std::string str;
    google::protobuf::TextFormat::PrintToString(t, &str);
    printf("%s", str.c_str());

    return 0;
}

Binary protobuf of this sample (for completeness):

00000000  0a 0b 64 73 66 61 64 73  61 66 73 61 66 10 ea 01  |..dsfadsafsaf...|
00000010  18 f6 f9 8e 01 18 f7 f9  8e 01 18 f8 f9 8e 01 20  |............... |
00000020  8a 86 f1 fe ff ff ff ff  ff 01 20 89 86 f1 fe ff  |.......... .....|
00000030  ff ff ff ff 01 20 88 86  f1 fe ff ff ff ff ff 01  |..... ..........|
00000040  2a 1b 04 07 f4 ff ff ff  ff ff ff ff ff 01 04 07  |*...............|
00000050  fd ff ff ff ff ff ff ff  ff 01 04 07 00 32 10 0a  |.............2..|
00000060  05 73 64 66 66 66 12 07  71 22 71 71 5c 71 0a 32  |.sdfff..q"qq\q.2|
00000070  23 0a 14 20 20 20 73 64  66 66 66 32 20 20 d1 82  |#..   sdfff2  ..|
00000080  d0 b5 d1 81 d1 82 20 12  0b 71 09 71 71 3c 3e 71  |...... ..q.qq<>q|
00000090  32 26 01 ff 3a 06 00 01  02 ff fe fd a0 06 01 a9  |2&..:...........|
000000a0  06 ea 19 0c bf e5 15 34  40 b0 06 01              |.......4@...|
000000ac

Note that it’s the sample is not completely OK: libprotobuf ERROR google/protobuf/wire_format.cc:1059] Encountered string containing invalid UTF-8 data while parsing protocol buffer. Strings must contain only UTF-8; use the 'bytes' type for raw bytes.

Note that protoc tool also can decode messages to text, both with the proto file and without:

$ protoc --decode=Test test.proto < test.bin 
[libprotobuf ERROR google/protobuf/wire_format.cc:1091] String field 'value' contains invalid UTF-8 data when parsing a protocol buffer. Use the 'bytes' type if you intend to send raw bytes. 
f1: "dsfadsafsaf"
f2: 234
fa: 2342134
fa: 2342135
fa: 2342136
fb: -2342134
fb: -2342135
fb: -2342136
fc: 4
fc: 7
fc: -12
fc: 4
fc: 7
fc: -3
fc: 4
fc: 7
fc: 0
pairs {
  key: "sdfff"
  value: "q\"qq\\q\n"
}
pairs {
  key: "   sdfff2  \321\202\320\265\321\201\321\202 "
  value: "q\tqq<>q2&\001\377"
}
bbbb: "\000\001\002\377\376\375"
[gtt]: true
[gtg]: 20.0855369
[someEnum]: Variant1
$ protoc --decode_raw  < test.bin 
1: "dsfadsafsaf"
2: 234
3: 2342134
3: 2342135
3: 2342136
4: 18446744073707209482
4: 18446744073707209481
4: 18446744073707209480
5: "\004\007\364\377\377\377\377\377\377\377\377\001\004\007\375\377\377\377\377\377\377\377\377\001\004\007\000"
6 {
  1: "sdfff"
  2: "q\"qq\\q\n"
}
6 {
  1: "   sdfff2  \321\202\320\265\321\201\321\202 "
  2: "q\tqq<>q2&\001\377"
}
7: "\000\001\002\377\376\375"
100: 1
101: 0x403415e5bf0c19ea
102: 1

Leave a Comment