From 6ea4f43f35747fd373b3940d984e94a89b9d8eec Mon Sep 17 00:00:00 2001 From: Shankar Date: Mon, 29 Jul 2019 20:26:45 +0530 Subject: [proto/en] Adding Protocol Buffer 3 --- protocol-buffer-3.html.markdown | 247 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 247 insertions(+) create mode 100644 protocol-buffer-3.html.markdown (limited to 'protocol-buffer-3.html.markdown') diff --git a/protocol-buffer-3.html.markdown b/protocol-buffer-3.html.markdown new file mode 100644 index 00000000..46065536 --- /dev/null +++ b/protocol-buffer-3.html.markdown @@ -0,0 +1,247 @@ +--- +language: protocol-buffers +filename: protocol-buffers.proto +contributors: + - ["Shankar Shastri", "https://github.com/shankarshastri"] +--- +# Protocol Buffers + +## Why Protocol Buffers + +Protocol buffers are Google's language-neutral, platform-neutral, extensible mechanism for serializing structured data – think XML, but smaller, faster, and simpler. +You define how you want your data to be structured once, then you can use special generated source code to easily write and read your structured data to and from a variety of data streams and using a variety of languages. +Protocol Buffers are Schema Of Messages. They are language agnostic. +They can be converted to binary and converted back to message formats using the code generated by the protoc compiler for various languages. + +``` +/* +* Language Syntax +*/ + +/* +* Specifying Syntax Of Protocol Buffer Version +* Specifying Which Protocol Buffer Version To Use +* It can be usually proto3 or proto2 +*/ +syntax = "proto3"; + +/* +* Declaring Message In Protocol Buffer: +* As you can see, each field in the message definition has a unique number. +* These field numbers are used to identify your fields in the message binary format, +* and should not be changed once your message type is in use. +* Note that field numbers in the range 1 through 15 take one byte to encode, including the field number and the field's type (you can find out more about this in Protocol Buffer Encoding). +* Field numbers in the range 16 through 2047 take two bytes. So you should reserve the numbers 1 through 15 for very frequently occurring message elements. +* Remember to leave some room for frequently occurring elements that might be added in the future. +* The smallest field number you can specify is 1, and the largest is 2^29 - 1, or 536,870,911. +* You also cannot use the numbers 19000 through 19999 (FieldDescriptor::kFirstReservedNumber through FieldDescriptor::kLastReservedNumber), +* as they are reserved for the Protocol Buffers implementation - the protocol buffer compiler will complain if you use one of these reserved numbers in your .proto. +* Similarly, you cannot use any previously reserved field numbers. +* +*/ + +/* +Syntax For Declaring Message: + message ${MessageName} { + ${Scalar Value Type} ${FieldName1} = ${Tag Number1}; + . + . + . + ${Scalar Value Type} ${FieldNameN} = ${Tag NumberN}; + } + +Default Values Will be applied any case if the message doesn't contain a existing field defined +in the message definition +*/ + +message MessageTypes { + /* + * Scalar Value Types + */ + string stringType = 1; // A string must always contain UTF-8 encoded or 7-bit ASCII text. Default value = "" + + // Number Types, Default Value = 0 + int32 int32Type = 2; // Uses Variable Length Encoding. Inefficient For Negative Numbers, Instead Use sint32. + int64 int64Type = 3; // Uses Variable Length Encoding. Inefficient For Negative Numbers, Instead Use sint64. + uint32 uInt32Type = 4; // Uses Variable Length Encoding + uint64 uInt64Type = 5; // Uses Variable Length Encoding + sint32 sInt32Type = 6; // Uses Variable Length Encoding. They are efficient in encoding for negative numbers. + // Use this instead of int32 for negative numbers + sint64 sInt64Type = 7; // Uses Variable Length Encoding. They are efficient in encoding for negative numbers. + // Use this instead of int64 for negative numbers. + + fixed32 fixed32Type = 8; // Always four bytes. More efficient than uint32 if values are often greater than 2^28. + fixed64 fixed64Type = 9; // Always eight bytes. More efficient than uint64 if values are often greater than 2^56 + + sfixed32 sfixed32Type = 10; // Always four bytes. + sfixed64 sfixed64Type = 11; // Always Eight bytes. + + bool boolType = 12; // Boolean Type. Default Value = false + + bytes bytesType = 13; // May contain any arbitrary sequence of bytes. Default Value = Empty Bytes + + double doubleType = 14; + float floatType = 15; + + enum Week { + UNDEFINED = 0; // Tag 0 is always used as default in case of enum + SUNDAY = 1; + MONDAY = 2; + TUESDAY = 3; + WEDNESDAY = 4; + THURSDAY = 5; + FRIDAY = 6; + SATURDAY = 7; + } + Week wkDayType = 16; + + /* + * Defining Collection Of Scalar Value Type + * Syntax: repeated ${ScalarType} ${name} = TagValue + */ + repeated string listOfString = 17; // List[String] +} + +/* +* Defining Defined Message Types In Other Message Definition +*/ +message Person { + string fname = 1; + string sname = 2; +} + +message City { + Person p = 1; +} + +/* +* Nested Message Definitions +*/ + +message NestedMessages { + message FirstLevelNestedMessage { + string firstString = 1; + message SecondLevelNestedMessage { + string secondString = 2; + } + } + FirstLevelNestedMessage msg = 1; + FirstLevelNestedMessage.SecondLevelNestedMessage msg2 = 2; +} + +/* +* Importing Message From A File +*/ + +// one.proto +// message One { +// string oneMsg = 1; +// } + +// two.proto +// import "myproject/one.proto" +// message Two { +// string twoMsg = 2; +// } + + +/* +* Advanced Topics +*/ + +/* +* Handling Message Type Changes: +* Never Change/Use The TagNumber Of A Message Field Which Was Removed +* We should use reserved in case of message definition update. +* (https://developers.google.com/protocol-buffers/docs/proto3#updating) +*/ + +/* +* Reserved Fields +* It's used in case if we need to add/remove new fields into message. +* Using Reserved Backward and Forward Compatibility Of Messages can be achieved +*/ + + +message ReservedMessage { + reserved 0, 1, 2, 3 to 10; // Set Of Tag Numbers Which Can't be reused. + reserved "firstMsg", "secondMsg", "thirdMsg"; // Set Of Labels Which Can't Be reused. +} + +/* +* Any +* The Any message type lets you use messages as embedded types without having their .proto definition. +* An Any contains an arbitrary serialized message as bytes, +* along with a URL that acts as a globally unique identifier for and resolves to that message's type. +* For Any to work we need to import it as shown below. +*/ +/* + import "google/protobuf/any.proto"; + message AnySampleMessage { + repeated google.protobuf.Any.details = 1; + } + +*/ + + +/* +* OneOf +* There are cases, wherein only one field at-most might be present as part of the message. +* Note: OneOf messages can't be repeated. +*/ + +message OneOfMessage { + oneof msg { + string fname = 1; + string sname = 2; + }; +} + +/* +* Maps +* Map fields cannot be repeated. +* Ordering Of A Map Is Not Guaranteed. +*/ + +message MessageWithMaps { + map mapOfMessages = 1; +} + + +/* +* Packages +* Used for preventing name clashes between protocol message types +* Syntax: + package ${packageName}; + + To Access the package; + ${packageName}.${messageName} = ${tagNumber}; +*/ + +/* +* Services +* Message Types Defined For Using In RPC system. +* When protoc compiler generates for various languages it generates stub methods for the services. +*/ + +message SearchRequest { + string queryString = 1; +} + +message SearchResponse { + string queryResponse = 1; +} +service SearchService { + rpc Search (SearchRequest) returns (SearchResponse); +} +``` + +## Generating Classes In Various Languages For Protocol Buffers + +```shell +protoc --proto_path=IMPORT_PATH --cpp_out=DST_DIR --java_out=DST_DIR --python_out=DST_DIR --go_out=DST_DIR --ruby_out=DST_DIR --objc_out=DST_DIR --csharp_out=DST_DIR path/to/file.proto +``` + +## References + +[Google Protocol Buffers](https://developers.google.com/protocol-buffers/) -- cgit v1.2.3