cpp-peglib/grammar/cpp-peglib.peg

# Setup PEG syntax parser
Grammar <-  Spacing  Definition+  EndOfFile

Definition <-
	Ignore  IdentCont  Parameters  LEFTARROW Expression  Instruction?
	/ Ignore  Identifier  LEFTARROW  Expression Instruction?

Expression <-  Sequence  (SLASH  Sequence)*

Sequence <-  (CUT /  Prefix)*

Prefix <-  (AND /  NOT)?  SuffixWithLabel

SuffixWithLabel <- Suffix  (LABEL  Identifier)?

Suffix <-  Primary  Loop?

Loop <-  QUESTION /  STAR /  PLUS /  Repetition

Primary <-
	Ignore  IdentCont  Arguments !LEFTARROW
	/ Ignore  Identifier !(Parameters?  LEFTARROW)
	/ OPEN  Expression  CLOSE
	/ BeginTok  Expression  EndTok
	/ BeginCapScope  Expression  EndCapScope
	/ BeginCap  Expression  EndCap
	/ CapScope
	/ BackRef
	/ DictionaryI
	/ LiteralI
	/ Dictionary
	/ Literal
	/ NegatedClassI
	/ NegatedClass
	/ ClassI
	/ Class
	/ DOT

Identifier <-  IdentCont  Spacing

IdentCont <- <IdentStart  IdentRest*>

IdentStart <-  !"↑"  !"⇑" ([a-zA-Z_%] /  [\u0080-\uFFFF])

IdentRest <-  IdentStart /  [0-9]

Dictionary <-  LiteralD  (PIPE  LiteralD)+

DictionaryI <- LiteralID (PIPE LiteralID)*

lit_ope <-
	[']  <(![']  Char)*> [']  Spacing
	/ ["]  <(!["]  Char)*> ["]  Spacing

Literal <-  lit_ope

LiteralD <-  lit_ope

lit_case_ignore_ope <-
	[']  <(![']  Char)*>  "'i" Spacing
	/ ["]  <(!["]  Char)*>  '"i' Spacing

LiteralI <- lit_case_ignore_ope

LiteralID <- lit_case_ignore_ope

# NOTE: The original Brian Ford's paper uses 'zom' instead of 'oom'.
Class <-  '['  !'^' <(!']'  Range)+>  ']' Spacing
ClassI <-  '['  !'^' <(!']'  Range)+>  ']i' Spacing
NegatedClass <-  "[^" <(!']'  Range)+>  ']' Spacing
NegatedClassI <-  "[^" <(!']'  Range)+>  ']i' Spacing

Range <-  (Char  '-'  ! ']' Char) /  Char

Char <-
	'\\'  [nrt'\"[\]\\^]
	/ '\\'  [0-3]  [0-7]  [0-7]
	/ '\\'  [0-7]  [0-7]?
	/ "\\x"  [0-9a-fA-F]  [0-9a-fA-F]?
	/ "\\u" (((('0' [0-9a-fA-F]) / "10") [0-9a-fA-F]{4,4}) / [0-9a-fA-F]{4,5})
	/ !'\\'   .

Repetition <- BeginBracket  RepetitionRange  EndBracket

RepetitionRange <-
	Number  COMMA  Number
	/ Number  COMMA
	/  Number
	/ COMMA  Number

Number <-  [0-9]+  Spacing

CapScope <- BeginCapScope Expression EndCapScope

LEFTARROW <-  ("<-" / "←")  Spacing

~SLASH <-  '/'  Spacing
~PIPE <-  '|'  Spacing
AND <-  '&'  Spacing
NOT <-  '!'  Spacing
QUESTION <- '?'  Spacing
STAR <-  '*'  Spacing
PLUS <-  '+'  Spacing
~OPEN <-  '('  Spacing
~CLOSE <- ')'  Spacing
DOT <-  '.'  Spacing

CUT <-  "↑"  Spacing
~LABEL <-  ('^' /  "⇑")  Spacing

~Spacing <-  (Space /  Comment)*
Comment <- '#'  (!EndOfLine   . )*
Space <-  ' ' /  '\t' /  EndOfLine
EndOfLine <-  "\r\n" /  '\n' /  '\r'
EndOfFile <-  ! .

~BeginTok <-  '<'  Spacing
~EndTok <-  '>'  Spacing

~BeginCapScope <-  '$'  '('  Spacing
~EndCapScope <-  ')'  Spacing

BeginCap <-  '$'  <IdentCont>  '<'  Spacing
~EndCap <-  '>'  Spacing

BackRef <-  '$'  <IdentCont>  Spacing

IGNORE <-  '~'

Ignore <-  IGNORE?
Parameters <-  OPEN  Identifier (COMMA  Identifier)*  CLOSE
Arguments <-  OPEN  Expression (COMMA  Expression)*  CLOSE
~COMMA <-  ','  Spacing

# Instruction grammars
Instruction <-
	BeginBracket (InstructionItem  (InstructionItemSeparator InstructionItem)*)? EndBracket
InstructionItem <- PrecedenceClimbing /  ErrorMessage /  NoAstOpt
~InstructionItemSeparator <-  ';'  Spacing

~SpacesZom <-  Space*
~SpacesOom <-  Space+
~BeginBracket <-  '{'  Spacing
~EndBracket <-  '}'  Spacing

# PrecedenceClimbing instruction
PrecedenceClimbing <- "precedence"  SpacesOom  PrecedenceInfo (SpacesOom  PrecedenceInfo)*  SpacesZom
PrecedenceInfo <- PrecedenceAssoc (~SpacesOom  PrecedenceOpe)+
PrecedenceOpe <-
	['] <(!(Space /  ['])  Char)*> [']
	/ ["] <(!(Space /  ["])  Char)*> ["]
	/ <(!(PrecedenceAssoc /  Space /  '}')  . )+>
PrecedenceAssoc <-  [LR]

# Error message instruction
ErrorMessage <- "message"  SpacesOom  LiteralD  SpacesZom

# No Ast node optimization instruction
NoAstOpt <-  "no_ast_opt"  SpacesZom