protocompile
protocompile copied to clipboard
bufbuild
Grammar railroad diagram
I've just added this project grammar to https://mingodad.github.io/parsertl-playground/playground/ an Yacc/Lex compatible online editor/tester (select Protocompile parser from Examples then click Parse to see a parse tree for the content in Input Source), it also generate an EBNF understood by (IPV4) https://rr.red-dove.com/ui or (IPV6) https://www.bottlecaps.de/rr/ui to generate a nice navigable railroad diagram (see instruction bellow at the top).
I hope it can help develop/debug/document this project grammar.
//
// EBNF to be viewd at
// (IPV6) https://www.bottlecaps.de/rr/ui
// (IPV4) https://rr.red-dove.com/ui
//
// Copy and paste this at one of the urls shown above in the 'Edit Grammar' tab
// then click the 'View Diagram' tab.
//
file::=
syntaxDecl
| editionDecl
| fileBody
| syntaxDecl fileBody
| editionDecl fileBody
| /*%empty*/
fileBody::=
semicolons fileElements
fileElements::=
fileElements fileElement
| fileElement
fileElement::=
importDecl
| packageDecl
| optionDecl
| messageDecl
| enumDecl
| extensionDecl
| serviceDecl
semicolonList::=
';'
| semicolonList ';'
semicolons::=
semicolonList
| /*%empty*/
semicolon::=
';'
| /*%empty*/
syntaxDecl::=
_SYNTAX '=' stringLit ';'
editionDecl::=
_EDITION '=' stringLit ';'
importDecl::=
_IMPORT stringLit semicolons
| _IMPORT _WEAK stringLit semicolons
| _IMPORT _PUBLIC stringLit semicolons
packageDecl::=
_PACKAGE qualifiedIdentifier semicolons
qualifiedIdentifier::=
identifier
| qualifiedIdentifier '.' identifier
qualifiedIdentifierDot::=
qualifiedIdentifierFinal
| qualifiedIdentifierLeading qualifiedIdentifierFinal
qualifiedIdentifierLeading::=
qualifiedIdentifierEntry
| qualifiedIdentifierLeading qualifiedIdentifierEntry
qualifiedIdentifierFinal::=
identifier
| qualifiedIdentifierEntry
qualifiedIdentifierEntry::=
identifier '.'
msgElementIdent::=
msgElementName
| msgElementIdent '.' identifier
extElementIdent::=
extElementName
| extElementIdent '.' identifier
oneofElementIdent::=
oneofElementName
| oneofElementIdent '.' identifier
notGroupElementIdent::=
notGroupElementName
| notGroupElementIdent '.' identifier
mtdElementIdent::=
mtdElementIdentFinal
| mtdElementIdentLeading mtdElementIdentFinal
mtdElementIdentLeading::=
mtdElementIdentEntry
| mtdElementIdentLeading mtdElementIdentEntry
mtdElementIdentFinal::=
mtdElementName
| mtdElementIdentEntry
mtdElementIdentEntry::=
mtdElementName '.'
oneofOptionDecl::=
_OPTION optionName '=' optionValue semicolon
optionDecl::=
_OPTION optionName '=' optionValue semicolons
optionNamePart::=
identifier
| extensionName
optionNameEntry::=
optionNamePart '.'
optionNameFinal::=
optionNamePart
| optionNameEntry
optionNameLeading::=
optionNameEntry
| optionNameLeading optionNameEntry
optionName::=
optionNameFinal
| optionNameLeading optionNameFinal
extensionName::=
'(' typeName ')'
optionValue::=
scalarValue
| messageLiteralWithBraces
scalarValue::=
stringLit
| numLit
| specialFloatLit
| identifier
numLit::=
_FLOAT_LIT
| '-' _FLOAT_LIT
| _INT_LIT
| '-' _INT_LIT
specialFloatLit::=
'-' _INF
| '-' _NAN
stringLit::=
_STRING_LIT
| stringLit _STRING_LIT
messageLiteralWithBraces::=
'{' messageTextFormat '}'
| '{' '}'
messageTextFormat::=
messageLiteralFields
messageLiteralFields::=
messageLiteralFieldEntry
| messageLiteralFieldEntry messageLiteralFields
messageLiteralFieldEntry::=
messageLiteralField
| messageLiteralField ','
| messageLiteralField ';'
messageLiteralField::=
messageLiteralFieldName ':' fieldValue
| messageLiteralFieldName messageValue
messageLiteralFieldName::=
identifier
| '[' qualifiedIdentifierDot ']'
| '[' qualifiedIdentifierDot '/' qualifiedIdentifierDot ']'
fieldValue::=
fieldScalarValue
| messageLiteral
| listLiteral
fieldScalarValue::=
stringLit
| numLit
| '-' identifier
| identifier
messageValue::=
messageLiteral
| listOfMessagesLiteral
messageLiteral::=
messageLiteralWithBraces
| '<' messageTextFormat '>'
| '<' '>'
listLiteral::=
'[' listElements ']'
| '[' ']'
listElements::=
listElement
| listElements ',' listElement
listElement::=
fieldScalarValue
| messageLiteral
listOfMessagesLiteral::=
'[' messageLiterals ']'
| '[' ']'
messageLiterals::=
messageLiteral
| messageLiterals ',' messageLiteral
typeName::=
qualifiedIdentifierDot
| '.' qualifiedIdentifierDot
msgElementTypeIdent::=
msgElementIdent
| '.' qualifiedIdentifier
extElementTypeIdent::=
extElementIdent
| '.' qualifiedIdentifier
oneofElementTypeIdent::=
oneofElementIdent
| '.' qualifiedIdentifier
notGroupElementTypeIdent::=
notGroupElementIdent
| '.' qualifiedIdentifier
mtdElementTypeIdent::=
mtdElementIdent
| '.' qualifiedIdentifierDot
fieldCardinality::=
_REQUIRED
| _OPTIONAL
| _REPEATED
compactOptions::=
'[' compactOptionDecls ']'
| '[' ']'
compactOptionDecls::=
compactOptionFinal
| compactOptionLeadingDecls compactOptionFinal
compactOptionLeadingDecls::=
compactOptionEntry
| compactOptionLeadingDecls compactOptionEntry
compactOptionFinal::=
compactOption
| compactOptionEntry
compactOptionEntry::=
compactOption ','
compactOption::=
optionName '=' optionValue
| optionName
groupDecl::=
fieldCardinality _GROUP identifier '=' _INT_LIT '{' messageBody '}'
| fieldCardinality _GROUP identifier '=' _INT_LIT compactOptions '{' messageBody '}'
messageGroupDecl::=
fieldCardinality _GROUP identifier '=' _INT_LIT '{' messageBody '}' semicolons
| fieldCardinality _GROUP identifier '=' _INT_LIT compactOptions '{' messageBody '}' semicolons
| fieldCardinality _GROUP identifier '{' messageBody '}' semicolons
| fieldCardinality _GROUP identifier compactOptions '{' messageBody '}' semicolons
oneofDecl::=
_ONEOF identifier '{' oneofBody '}' semicolons
oneofBody::=
/*%empty*/
| oneofElements
oneofElements::=
oneofElements oneofElement
| oneofElement
oneofElement::=
oneofOptionDecl
| oneofFieldDecl
| oneofGroupDecl
oneofFieldDecl::=
oneofElementTypeIdent identifier '=' _INT_LIT semicolon
| oneofElementTypeIdent identifier '=' _INT_LIT compactOptions semicolon
| oneofElementTypeIdent identifier semicolon
| oneofElementTypeIdent identifier compactOptions semicolon
oneofGroupDecl::=
_GROUP identifier '=' _INT_LIT '{' messageBody '}'
| _GROUP identifier '=' _INT_LIT compactOptions '{' messageBody '}'
| _GROUP identifier '{' messageBody '}'
| _GROUP identifier compactOptions '{' messageBody '}'
mapFieldDecl::=
mapType identifier '=' _INT_LIT semicolons
| mapType identifier '=' _INT_LIT compactOptions semicolons
| mapType identifier semicolons
| mapType identifier compactOptions semicolons
mapType::=
_MAP '<' mapKeyType ',' typeName '>'
mapKeyType::=
_INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
extensionRangeDecl::=
_EXTENSIONS tagRanges ';' semicolons
| _EXTENSIONS tagRanges compactOptions semicolons
tagRanges::=
tagRange
| tagRanges ',' tagRange
tagRange::=
_INT_LIT
| _INT_LIT _TO _INT_LIT
| _INT_LIT _TO _MAX
enumValueRanges::=
enumValueRange
| enumValueRanges ',' enumValueRange
enumValueRange::=
enumValueNumber
| enumValueNumber _TO enumValueNumber
| enumValueNumber _TO _MAX
enumValueNumber::=
_INT_LIT
| '-' _INT_LIT
msgReserved::=
_RESERVED tagRanges ';' semicolons
| reservedNames
enumReserved::=
_RESERVED enumValueRanges ';' semicolons
| reservedNames
reservedNames::=
_RESERVED fieldNameStrings semicolons
| _RESERVED fieldNameIdents semicolons
fieldNameStrings::=
stringLit
| fieldNameStrings ',' stringLit
fieldNameIdents::=
identifier
| fieldNameIdents ',' identifier
enumDecl::=
_ENUM identifier '{' enumBody '}' semicolons
enumBody::=
semicolons
| semicolons enumElements
enumElements::=
enumElements enumElement
| enumElement
enumElement::=
optionDecl
| enumValueDecl
| enumReserved
enumValueDecl::=
enumValueName '=' enumValueNumber semicolons
| enumValueName '=' enumValueNumber compactOptions semicolons
messageDecl::=
_MESSAGE identifier '{' messageBody '}' semicolons
messageBody::=
semicolons
| semicolons messageElements
messageElements::=
messageElements messageElement
| messageElement
messageElement::=
messageFieldDecl
| enumDecl
| messageDecl
| extensionDecl
| extensionRangeDecl
| messageGroupDecl
| optionDecl
| oneofDecl
| mapFieldDecl
| msgReserved
messageFieldDecl::=
fieldCardinality notGroupElementTypeIdent identifier '=' _INT_LIT semicolons
| fieldCardinality notGroupElementTypeIdent identifier '=' _INT_LIT compactOptions semicolons
| msgElementTypeIdent identifier '=' _INT_LIT semicolons
| msgElementTypeIdent identifier '=' _INT_LIT compactOptions semicolons
| fieldCardinality notGroupElementTypeIdent identifier semicolons
| fieldCardinality notGroupElementTypeIdent identifier compactOptions semicolons
| msgElementTypeIdent identifier semicolons
| msgElementTypeIdent identifier compactOptions semicolons
extensionDecl::=
_EXTEND typeName '{' extensionBody '}' semicolons
extensionBody::=
/*%empty*/
| extensionElements
extensionElements::=
extensionElements extensionElement
| extensionElement
extensionElement::=
extensionFieldDecl
| groupDecl
extensionFieldDecl::=
fieldCardinality notGroupElementTypeIdent identifier '=' _INT_LIT semicolon
| fieldCardinality notGroupElementTypeIdent identifier '=' _INT_LIT compactOptions semicolon
| extElementTypeIdent identifier '=' _INT_LIT semicolon
| extElementTypeIdent identifier '=' _INT_LIT compactOptions semicolon
serviceDecl::=
_SERVICE identifier '{' serviceBody '}' semicolons
serviceBody::=
semicolons
| semicolons serviceElements
serviceElements::=
serviceElements serviceElement
| serviceElement
serviceElement::=
optionDecl
| methodDecl
methodDecl::=
_RPC identifier methodMessageType _RETURNS methodMessageType semicolons
| _RPC identifier methodMessageType _RETURNS methodMessageType '{' methodBody '}' semicolons
methodMessageType::=
'(' _STREAM typeName ')'
| '(' mtdElementTypeIdent ')'
methodBody::=
semicolons
| semicolons methodElements
methodElements::=
methodElements methodElement
| methodElement
methodElement::=
optionDecl
msgElementName::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _TRUE
| _FALSE
| _INF
| _NAN
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _MAP
| _TO
| _MAX
| _SERVICE
| _RPC
| _STREAM
| _RETURNS
extElementName::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _OPTION
| _TRUE
| _FALSE
| _INF
| _NAN
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _ONEOF
| _MAP
| _EXTENSIONS
| _TO
| _MAX
| _RESERVED
| _ENUM
| _MESSAGE
| _EXTEND
| _SERVICE
| _RPC
| _STREAM
| _RETURNS
enumValueName::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _TRUE
| _FALSE
| _INF
| _NAN
| _REPEATED
| _OPTIONAL
| _REQUIRED
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _GROUP
| _ONEOF
| _MAP
| _EXTENSIONS
| _TO
| _MAX
| _ENUM
| _MESSAGE
| _EXTEND
| _SERVICE
| _RPC
| _STREAM
| _RETURNS
oneofElementName::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _TRUE
| _FALSE
| _INF
| _NAN
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _ONEOF
| _MAP
| _EXTENSIONS
| _TO
| _MAX
| _RESERVED
| _ENUM
| _MESSAGE
| _EXTEND
| _SERVICE
| _RPC
| _STREAM
| _RETURNS
notGroupElementName::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _OPTION
| _TRUE
| _FALSE
| _INF
| _NAN
| _REPEATED
| _OPTIONAL
| _REQUIRED
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _ONEOF
| _MAP
| _EXTENSIONS
| _TO
| _MAX
| _RESERVED
| _ENUM
| _MESSAGE
| _EXTEND
| _SERVICE
| _RPC
| _STREAM
| _RETURNS
mtdElementName::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _OPTION
| _TRUE
| _FALSE
| _INF
| _NAN
| _REPEATED
| _OPTIONAL
| _REQUIRED
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _GROUP
| _ONEOF
| _MAP
| _EXTENSIONS
| _TO
| _MAX
| _RESERVED
| _ENUM
| _MESSAGE
| _EXTEND
| _SERVICE
| _RPC
| _RETURNS
identifier::=
_NAME
| _SYNTAX
| _EDITION
| _IMPORT
| _WEAK
| _PUBLIC
| _PACKAGE
| _OPTION
| _TRUE
| _FALSE
| _INF
| _NAN
| _REPEATED
| _OPTIONAL
| _REQUIRED
| _DOUBLE
| _FLOAT
| _INT32
| _INT64
| _UINT32
| _UINT64
| _SINT32
| _SINT64
| _FIXED32
| _FIXED64
| _SFIXED32
| _SFIXED64
| _BOOL
| _STRING
| _BYTES
| _GROUP
| _ONEOF
| _MAP
| _EXTENSIONS
| _TO
| _MAX
| _RESERVED
| _ENUM
| _MESSAGE
| _EXTEND
| _SERVICE
| _RPC
| _STREAM
| _RETURNS
//Tokens
_BOOL ::= "bool"
_BYTES ::= "bytes"
_DOUBLE ::= "double"
_EDITION ::= "edition"
_ENUM ::= "enum"
_EXTEND ::= "extend"
_EXTENSIONS ::= "extensions"
_FALSE ::= "false"
_FIXED32 ::= "fixed32"
_FIXED64 ::= "fixed64"
_FLOAT ::= "float"
_GROUP ::= "group"
_IMPORT ::= "import"
_INF ::= "inf"
_INT32 ::= "int32"
_INT64 ::= "int64"
_MAP ::= "map"
_MAX ::= "max"
_MESSAGE ::= "message"
_NAN ::= "nan"
_ONEOF ::= "oneof"
_OPTIONAL ::= "optional"
_OPTION ::= "option"
_PACKAGE ::= "package"
_PUBLIC ::= "public"
_REPEATED ::= "repeated"
_REQUIRED ::= "required"
_RESERVED ::= "reserved"
_RETURNS ::= "returns"
_RPC ::= "rpc"
_SERVICE ::= "service"
_SFIXED32 ::= "sfixed32"
_SFIXED64 ::= "sfixed64"
_SINT32 ::= "sint32"
_SINT64 ::= "sint64"
_STREAM ::= "stream"
_STRING ::= "string"
_SYNTAX ::= "syntax"
_TO ::= "to"
_TRUE ::= "true"
_UINT32 ::= "uint32"
_UINT64 ::= "uint64"
_WEAK ::= "weak"
@mingodad, FWIW, we've written a specification for the Protobuf language, and that also includes a grammar that is intended to be human-readable: https://protobuf.com/docs/language-spec
@jhump thank you for reply ! Would be nice to have the full grammar in one place there too (instead/plus of piece-wise that's there now) !
The site that hosts the language spec also contains some other parser examples, including an ANTLR grammar configuration: https://protobuf.com/docs/examples
Thank you again !
I see now that I've used the grammar from https://github.com/bufbuild/protocompile/blob/v0.2.0/parser/proto.y on my Yacc/Lex playground.
The last released version is https://github.com/bufbuild/protocompile/releases/tag/v0.14.1 so the parsers/grammars you have on those links seem to be outdated.
@mingodad, thanks for pointing that out. I've updated the site so it now points to the latest release instead (0.14.1).
Hello @jhump I'm not sure that it's right because comparing the content of the links there is no difference. Does that mean that the version has changed but the grammar/parser continues the same.
There over ~1400 lines changed, just in the file proto.y, between the two versions:
https://github.com/bufbuild/protocompile/compare/v0.2.0..v0.14.1#diff-cbe13169fa724e83181b277eea5d1e7c0b7b7647441f3330ddb73abf446f0aee
If you are referring to changes between that latest version and the railroad diagram you created above, it appears you are correct that there is no difference. It looks like you made that diagram based on the latest version, not based on the very old version that was previously linked from the protobuf.com page.
FWIW, the grammar in the protobuf.com site, and in the other example grammars, is much more accurate. The proto.y grammar in protocompile is very lenient and allows several things that the actual protobuf language forbids. This is done specifically so that we can get an AST for a file, even when the source is invalid; this was intended to aid the implementation of a language server (see LSP), where it is common for files to be incomplete/in the process of being edited, and thus to contain transient syntax errors. Note that we are in the process of implementing a new parser (which will temporarily live in an experimental folder, until it's mature enough to replace the existing parser). That one will be even more lenient, specifically for better error recovery and diagnostics for a language server.
@jhump thank you again for reply ! It seems that you are right about the grammar version that I've used (somehow I've got confused).
Now I've got the spec here https://github.com/bufbuild/protobuf-language-spec/blob/main/language-spec.md?plain=1 and manually separated the ebnf parts and converted to an EBNF understood by https://github.com/GuntherRademacher/rr (see bellow instructions at the top).
//
// EBNF to be viewd at
// (IPV6) https://www.bottlecaps.de/rr/ui
// (IPV4) https://rr.red-dove.com/ui
//
// Copy and paste this at one of the urls shown above in the 'Edit Grammar' tab
// then click the 'View Diagram' tab.
//
//From: https://github.com/bufbuild/protobuf-language-spec/blob/0df02baa0678241fca35704da220ae699de79144/language-spec.md?plain=1
start ::= File //to make easy for navigation
//Whitespace and Comments
whitespace ::= " " | "\n" | "\r" | "\t" | "\f" | "\v"
comment ::= line_comment | block_comment
line_comment ::= "//" ( [^#x10#x00] )*
block_comment ::= "/*" block_comment_rest
block_comment_rest ::= "*" block_comment_tail |
[^*#x00] block_comment_rest
block_comment_tail ::= "/" |
"*" block_comment_tail |
[^*/#x00] block_comment_rest
//Character Classes
letter ::= [A-Za-z_]
decimal_digit ::= [0-9]
octal_digit ::= [0-7]
hex_digit ::= [0-9A-Fa-f]
byte_order_mark ::= "\xEF\xBB\xBF"
//Identifiers and Keywords
identifier ::= letter ( letter | decimal_digit )*
syntax ::= "syntax"
float ::= "float" .
oneof ::= "oneof"
import ::= "import"
double ::= "double"
map ::= "map"
weak ::= "weak"
int32 ::= "int32"
extensions ::= "extensions"
public ::= "public"
int64 ::= "int64"
to ::= "to"
package ::= "package"
uint32 ::= "uint32"
max ::= "max"
option ::= "option"
uint64 ::= "uint64"
reserved ::= "reserved"
inf ::= "inf"
sint32 ::= "sint32"
enum ::= "enum"
repeated ::= "repeated"
sint64 ::= "sint64"
message ::= "message"
optional ::= "optional"
fixed32 ::= "fixed32"
extend ::= "extend"
required ::= "required"
fixed64 ::= "fixed64"
service ::= "service"
bool ::= "bool"
sfixed32 ::= "sfixed32"
rpc ::= "rpc"
string ::= "string"
sfixed64 ::= "sfixed64"
stream ::= "stream"
bytes ::= "bytes"
group ::= "group"
returns ::= "returns"
//Numeric Literals
numeric_literal ::= "."? decimal_digit digit_point_or_exp*
digit_point_or_exp ::= "." | decimal_digit | ( "e" | "E" ) ( "+" | "-" )? | letter
int_literal ::= decimal_literal | octal_literal | hex_literal
decimal_literal ::= "0" | [1-9] decimal_digits?
octal_literal ::= "0" octal_digits
hex_literal ::= "0" ( "x" | "X" ) hex_digits
decimal_digits ::= decimal_digit decimal_digit*
octal_digits ::= octal_digit octal_digit*
hex_digits ::= hex_digit hex_digit*
float_literal ::= decimal_digits "." decimal_digits? decimal_exponent? |
decimal_digits decimal_exponent |
"." decimal_digits decimal_exponent?
decimal_exponent ::= ( "e" | "E" ) ( "+" | "-" )? decimal_digits
//String Literals
string_literal ::= single_quoted_string_literal | double_quoted_string_literal
single_quoted_string_literal ::= "'" ( [^#x10#x00'\] | rune_escape_seq )* "'"
double_quoted_string_literal ::= '"' ( [^#x10#x00"\] | rune_escape_seq )* '"'
rune_escape_seq ::= simple_escape_seq | hex_escape_seq | octal_escape_seq | unicode_escape_seq
simple_escape_seq ::= '\' ( "a" | "b" | "f" | "n" | "r" | "t" | "v" | '\' | "'" | '"' | "?" )
hex_escape_seq ::= '\' ( "x" | "X" ) hex_digit hex_digit?
octal_escape_seq ::= '\' octal_digit ( octal_digit octal_digit? )?
unicode_escape_seq ::= "\u" hex_digit hex_digit hex_digit hex_digit |
"\U" hex_digit hex_digit hex_digit hex_digit
hex_digit hex_digit hex_digit hex_digit
//Punctuation and Operators
semicolon ::= ";"
colon ::= ":"
l_paren ::= "("
l_bracket ::= "["
comma ::= ","
equals ::= "="
r_paren ::= ")"
r_bracket ::= "]"
dot ::= "."
minus ::= "-"
l_brace ::= "{"
l_angle ::= "<"
slash ::= "/"
plus ::= "+"
r_brace ::= "}"
r_angle ::= ">"
//Syntax
//Source File Organization
File ::= byte_order_mark? SyntaxDecl? FileElement*
FileElement ::= ImportDecl |
PackageDecl |
OptionDecl |
MessageDecl |
EnumDecl |
ExtensionDecl |
ServiceDecl |
EmptyDecl
//Declaration Types
EmptyDecl ::= semicolon
//Syntax Declaration
SyntaxDecl ::= syntax equals SyntaxLevel semicolon
SyntaxLevel ::= StringLiteral
StringLiteral ::= string_literal string_literal*
PackageDecl ::= package PackageName semicolon
PackageName ::= QualifiedIdentifier
//Imports
ImportDecl ::= import ( weak | public )? ImportedFileName semicolon
ImportedFileName ::= StringLiteral
//Type References
TypeName ::= dot? QualifiedIdentifier
QualifiedIdentifier ::= identifier dot identifier*
//Options
OptionDecl ::= option OptionName equals OptionValue semicolon
CompactOptions ::= l_bracket CompactOption ( comma CompactOption )* r_bracket
CompactOption ::= OptionName equals OptionValue
//Option Names
OptionName ::= ( SimpleName | ExtensionName ) ( dot OptionName )?
SimpleName ::= identifier
ExtensionName ::= l_paren TypeName r_paren
//Option Values
OptionValue ::= ScalarValue | MessageLiteralWithBraces
ScalarValue ::= StringLiteral | UintLiteral | IntLiteral | FloatLiteral | identifier
UintLiteral ::= plus? int_literal
IntLiteral ::= minus int_literal
FloatLiteral ::= ( minus | plus )? ( float_literal | inf )
MessageLiteralWithBraces ::= l_brace MessageTextFormat r_brace
//Protobuf Text Format
MessageTextFormat ::= ( MessageLiteralField ( comma | semicolon )? )*
MessageLiteralField ::= MessageLiteralFieldName colon Value |
MessageLiteralFieldName MessageValue
MessageLiteralFieldName ::= FieldName |
l_bracket SpecialFieldName r_bracket
SpecialFieldName ::= ExtensionFieldName | TypeURL
ExtensionFieldName ::= QualifiedIdentifier
TypeURL ::= QualifiedIdentifier slash QualifiedIdentifier
Value ::= ScalarValue | MessageLiteral | ListLiteral
MessageValue ::= MessageLiteral | ListOfMessagesLiteral
MessageLiteral ::= MessageLiteralWithBraces |
l_angle MessageTextFormat r_angle
ListLiteral ::= l_bracket ( ListElement ( comma ListElement )* )? r_bracket
ListElement ::= ScalarValue | MessageLiteral
ListOfMessagesLiteral ::= l_bracket ( MessageLiteral ( comma MessageLiteral )* )? r_bracket
//Messages
MessageDecl ::= message MessageName l_brace MessageElement* r_brace
MessageName ::= identifier
MessageElement ::= FieldDecl |
MapFieldDecl |
GroupDecl |
OneofDecl |
OptionDecl |
ExtensionRangeDecl |
MessageReservedDecl |
MessageDecl |
EnumDecl |
ExtensionDecl |
EmptyDecl
//Fields
FieldDecl ::= FieldCardinality? TypeName FieldName equals FieldNumber
CompactOptions? semicolon
FieldCardinality ::= required | optional | repeated
FieldName ::= identifier
FieldNumber ::= int_literal
//Maps
MapFieldDecl ::= MapType FieldName equals FieldNumber CompactOptions? semicolon
MapType ::= map l_angle MapKeyType comma MapValueType r_angle
MapKeyType ::= int32 | int64 | uint32 | uint64 | sint32 | sint64 |
fixed32 | fixed64 | sfixed32 | sfixed64 | bool | string
MapValueType ::= TypeName
//Groups
GroupDecl ::= FieldCardinality? group FieldName equals FieldNumber
CompactOptions? l_brace MessageElement* r_brace
//Oneofs
OneofDecl ::= oneof OneofName l_brace OneofElement* r_brace
OneofName ::= identifier
OneofElement ::= OptionDecl |
OneofFieldDecl |
OneofGroupDecl
OneofFieldDecl ::= TypeName FieldName equals FieldNumber
CompactOptions? semicolon
OneofGroupDecl ::= group FieldName equals FieldNumber
CompactOptions? l_brace MessageElement* r_brace
//Extension Ranges
ExtensionRangeDecl ::= extensions TagRanges CompactOptions? semicolon
TagRanges ::= TagRange ( comma TagRange )*
TagRange ::= TagRangeStart ( to TagRangeEnd )?
TagRangeStart ::= FieldNumber
TagRangeEnd ::= FieldNumber | max
//Reserved Names and Numbers
MessageReservedDecl ::= reserved ( TagRanges | Names ) semicolon
Names ::= StringLiteral ( comma StringLiteral )*
//Enums
EnumDecl ::= enum EnumName l_brace EnumElement* r_brace
EnumName ::= identifier
EnumElement ::= OptionDecl |
EnumValueDecl |
EnumReservedDecl |
EmptyDecl
//Enum Values
EnumValueDecl ::= EnumValueName equals EnumValueNumber CompactOptions? semicolon
EnumValueName ::= identifier
EnumValueNumber ::= minus? int_literal
//Reserved Names and Numbers
EnumReservedDecl ::= reserved ( EnumValueRanges | Names ) semicolon
EnumValueRanges ::= EnumValueRange ( comma EnumValueRange )*
EnumValueRange ::= EnumValueRangeStart ( to EnumValueRangeEnd )?
EnumValueRangeStart ::= EnumValueNumber
EnumValueRangeEnd ::= EnumValueNumber | max
//Extensions
ExtensionDecl ::= extend ExtendedMessage l_brace ExtensionElement* r_brace
ExtendedMessage ::= TypeName
ExtensionElement ::= FieldDecl |
GroupDecl
//Services
ServiceDecl ::= service ServiceName l_brace ServiceElement* r_brace
ServiceName ::= identifier
ServiceElement ::= OptionDecl |
MethodDecl |
EmptyDecl
//Methods
MethodDecl ::= rpc MethodName InputType returns OutputType semicolon |
rpc MethodName InputType returns OutputType l_brace MethodElement* r_brace
MethodName ::= identifier
InputType ::= MessageType
OutputType ::= MessageType
MethodElement ::= OptionDecl |
EmptyDecl
MessageType ::= l_paren stream? TypeName r_paren