lang-bootstrap/06/zig.peg
Dawid Sobczak e6b88d5a0f Add stage 06: Lua bootstrap
The goal of stage 06 is to try parse zig synax in lua. I pulled in
lpeglable 1.2.0 and parser-gen off github to get started. All of this
needs to be cleaned up rather soon.

Lua boostraps using tcc and musl from the previous stage. Since musl
0.6.0 doesn't support dynamic linking this build of lua doesn't support
shared libraries. I couldn't easily patch musl with dlopen and friends
so instead I link statically and call deps with c api.
2023-07-06 12:32:47 +01:00

518 lines
No EOL
16 KiB
Text

Root <- skip container_doc_comment? ContainerMembers eof
ContainerMembers <- ContainerDeclarations (ContainerField COMMA)* (ContainerField / ContainerDeclarations)
ContainerDeclarations
<- TestDecl ContainerDeclarations
/ TopLevelComptime ContainerDeclarations
/ doc_comment? KEYWORD_pub? TopLevelDecl ContainerDeclarations
TestDecl <- doc_comment? KEYWORD_test STRINGLITERALSINGLE? Block
TopLevelComptime <- doc_comment? KEYWORD_comptime BlockExpr
TopLevelDecl
<- (KEYWORD_export / KEYWORD_extern STRINGLITERALSINGLE? / (KEYWORD_inline / KEYWORD_noinline))? FnProto (SEMICOLON / Block)
/ (KEYWORD_export / KEYWORD_extern STRINGLITERALSINGLE?)? KEYWORD_threadlocal? VarDecl
/ KEYWORD_usingnamespace Expr SEMICOLON
FnProto <- KEYWORD_fn IDENTIFIER? LPAREN ParamDeclList RPAREN ByteAlign? LinkSection? CallConv? EXCLAMATIONMARK? TypeExpr
VarDecl <- (KEYWORD_const / KEYWORD_var) IDENTIFIER (COLON TypeExpr)? ByteAlign? LinkSection? (EQUAL Expr)? SEMICOLON
ContainerField <- doc_comment? KEYWORD_comptime? IDENTIFIER (COLON (KEYWORD_anytype / TypeExpr) ByteAlign?)? (EQUAL Expr)?
Statement
<- KEYWORD_comptime? VarDecl
/ KEYWORD_comptime BlockExprStatement
/ KEYWORD_nosuspend BlockExprStatement
/ KEYWORD_suspend BlockExprStatement
/ KEYWORD_defer BlockExprStatement
/ KEYWORD_errdefer Payload? BlockExprStatement
/ IfStatement
/ LabeledStatement
/ SwitchExpr
/ AssignExpr SEMICOLON
IfStatement
<- IfPrefix BlockExpr ( KEYWORD_else Payload? Statement )?
/ IfPrefix AssignExpr ( SEMICOLON / KEYWORD_else Payload? Statement )
LabeledStatement <- BlockLabel? (Block / LoopStatement)
LoopStatement <- KEYWORD_inline? (ForStatement / WhileStatement)
ForStatement
<- ForPrefix BlockExpr ( KEYWORD_else Statement )?
/ ForPrefix AssignExpr ( SEMICOLON / KEYWORD_else Statement )
WhileStatement
<- WhilePrefix BlockExpr ( KEYWORD_else Payload? Statement )?
/ WhilePrefix AssignExpr ( SEMICOLON / KEYWORD_else Payload? Statement )
BlockExprStatement
<- BlockExpr
/ AssignExpr SEMICOLON
BlockExpr <- BlockLabel? Block
AssignExpr <- Expr (AssignOp Expr)?
Expr <- BoolOrExpr
BoolOrExpr <- BoolAndExpr (KEYWORD_or BoolAndExpr)*
BoolAndExpr <- CompareExpr (KEYWORD_and CompareExpr)*
CompareExpr <- BitwiseExpr (CompareOp BitwiseExpr)?
BitwiseExpr <- BitShiftExpr (BitwiseOp BitShiftExpr)*
BitShiftExpr <- AdditionExpr (BitShiftOp AdditionExpr)*
AdditionExpr <- MultiplyExpr (AdditionOp MultiplyExpr)*
MultiplyExpr <- PrefixExpr (MultiplyOp PrefixExpr)*
PrefixExpr <- PrefixOp* PrimaryExpr
PrimaryExpr
<- AsmExpr
/ IfExpr
/ KEYWORD_break BreakLabel? Expr?
/ KEYWORD_comptime Expr
/ KEYWORD_nosuspend Expr
/ KEYWORD_continue BreakLabel?
/ KEYWORD_resume Expr
/ KEYWORD_return Expr?
/ BlockLabel? LoopExpr
/ Block
/ CurlySuffixExpr
IfExpr <- IfPrefix Expr (KEYWORD_else Payload? Expr)?
Block <- LBRACE Statement* RBRACE
LoopExpr <- KEYWORD_inline? (ForExpr / WhileExpr)
ForExpr <- ForPrefix Expr (KEYWORD_else Expr)?
WhileExpr <- WhilePrefix Expr (KEYWORD_else Payload? Expr)?
CurlySuffixExpr <- TypeExpr InitList?
InitList
<- LBRACE FieldInit (COMMA FieldInit)* COMMA? RBRACE
/ LBRACE Expr (COMMA Expr)* COMMA? RBRACE
/ LBRACE RBRACE
TypeExpr <- PrefixTypeOp* ErrorUnionExpr
ErrorUnionExpr <- SuffixExpr (EXCLAMATIONMARK TypeExpr)?
SuffixExpr
<- KEYWORD_async PrimaryTypeExpr SuffixOp* FnCallArguments
/ PrimaryTypeExpr (SuffixOp / FnCallArguments)*
PrimaryTypeExpr
<- BUILTINIDENTIFIER FnCallArguments
/ CHAR_LITERAL
/ ContainerDecl
/ DOT IDENTIFIER
/ DOT InitList
/ ErrorSetDecl
/ FLOAT
/ FnProto
/ GroupedExpr
/ LabeledTypeExpr
/ IDENTIFIER
/ IfTypeExpr
/ INTEGER
/ KEYWORD_comptime TypeExpr
/ KEYWORD_error DOT IDENTIFIER
/ KEYWORD_anyframe
/ KEYWORD_unreachable
/ STRINGLITERAL
/ SwitchExpr
ContainerDecl <- (KEYWORD_extern / KEYWORD_packed)? ContainerDeclAuto
ErrorSetDecl <- KEYWORD_error LBRACE IdentifierList RBRACE
GroupedExpr <- LPAREN Expr RPAREN
IfTypeExpr <- IfPrefix TypeExpr (KEYWORD_else Payload? TypeExpr)?
LabeledTypeExpr
<- BlockLabel Block
/ BlockLabel? LoopTypeExpr
LoopTypeExpr <- KEYWORD_inline? (ForTypeExpr / WhileTypeExpr)
ForTypeExpr <- ForPrefix TypeExpr (KEYWORD_else TypeExpr)?
WhileTypeExpr <- WhilePrefix TypeExpr (KEYWORD_else Payload? TypeExpr)?
SwitchExpr <- KEYWORD_switch LPAREN Expr RPAREN LBRACE SwitchProngList RBRACE
AsmExpr <- KEYWORD_asm KEYWORD_volatile? LPAREN Expr AsmOutput? RPAREN
AsmOutput <- COLON AsmOutputList AsmInput?
AsmOutputItem <- LBRACKET IDENTIFIER RBRACKET STRINGLITERAL LPAREN (MINUSRARROW TypeExpr / IDENTIFIER) RPAREN
AsmInput <- COLON AsmInputList AsmClobbers?
AsmInputItem <- LBRACKET IDENTIFIER RBRACKET STRINGLITERAL LPAREN Expr RPAREN
AsmClobbers <- COLON StringList
BreakLabel <- COLON IDENTIFIER
BlockLabel <- IDENTIFIER COLON
FieldInit <- DOT IDENTIFIER EQUAL Expr
WhileContinueExpr <- COLON LPAREN AssignExpr RPAREN
LinkSection <- KEYWORD_linksection LPAREN Expr RPAREN
CallConv <- KEYWORD_callconv LPAREN Expr RPAREN
ParamDecl
<- doc_comment? (KEYWORD_noalias / KEYWORD_comptime)? (IDENTIFIER COLON)? ParamType
/ DOT3
ParamType
<- KEYWORD_anytype
/ TypeExpr
IfPrefix <- KEYWORD_if LPAREN Expr RPAREN PtrPayload?
WhilePrefix <- KEYWORD_while LPAREN Expr RPAREN PtrPayload? WhileContinueExpr?
ForPrefix <- KEYWORD_for LPAREN Expr RPAREN PtrIndexPayload
Payload <- PIPE IDENTIFIER PIPE
PtrPayload <- PIPE ASTERISK? IDENTIFIER PIPE
PtrIndexPayload <- PIPE ASTERISK? IDENTIFIER (COMMA IDENTIFIER)? PIPE
SwitchProng <- SwitchCase EQUALRARROW PtrPayload? AssignExpr
SwitchCase
<- SwitchItem (COMMA SwitchItem)* COMMA?
/ KEYWORD_else
SwitchItem <- Expr (DOT3 Expr)?
AssignOp
<- ASTERISKEQUAL
/ SLASHEQUAL
/ PERCENTEQUAL
/ PLUSEQUAL
/ MINUSEQUAL
/ LARROW2EQUAL
/ RARROW2EQUAL
/ AMPERSANDEQUAL
/ CARETEQUAL
/ PIPEEQUAL
/ ASTERISKPERCENTEQUAL
/ PLUSPERCENTEQUAL
/ MINUSPERCENTEQUAL
/ EQUAL
CompareOp
<- EQUALEQUAL
/ EXCLAMATIONMARKEQUAL
/ LARROW
/ RARROW
/ LARROWEQUAL
/ RARROWEQUAL
BitwiseOp
<- AMPERSAND
/ CARET
/ PIPE
/ KEYWORD_orelse
/ KEYWORD_catch Payload?
BitShiftOp
<- LARROW2
/ RARROW2
AdditionOp
<- PLUS
/ MINUS
/ PLUS2
/ PLUSPERCENT
/ MINUSPERCENT
MultiplyOp
<- PIPE2
/ ASTERISK
/ SLASH
/ PERCENT
/ ASTERISK2
/ ASTERISKPERCENT
PrefixOp
<- EXCLAMATIONMARK
/ MINUS
/ TILDE
/ MINUSPERCENT
/ AMPERSAND
/ KEYWORD_try
/ KEYWORD_await
PrefixTypeOp
<- QUESTIONMARK
/ KEYWORD_anyframe MINUSRARROW
/ SliceTypeStart (ByteAlign / KEYWORD_const / KEYWORD_volatile / KEYWORD_allowzero)*
/ PtrTypeStart (KEYWORD_align LPAREN Expr (COLON INTEGER COLON INTEGER)? RPAREN / KEYWORD_const / KEYWORD_volatile / KEYWORD_allowzero)*
/ ArrayTypeStart
SuffixOp
<- LBRACKET Expr (DOT2 (Expr? (COLON Expr)?)?)? RBRACKET
/ DOT IDENTIFIER
/ DOTASTERISK
/ DOTQUESTIONMARK
FnCallArguments <- LPAREN ExprList RPAREN
SliceTypeStart <- LBRACKET (COLON Expr)? RBRACKET
PtrTypeStart
<- ASTERISK
/ ASTERISK2
/ LBRACKET ASTERISK (LETTERC / COLON Expr)? RBRACKET
ArrayTypeStart <- LBRACKET Expr (COLON Expr)? RBRACKET
ContainerDeclAuto <- ContainerDeclType LBRACE container_doc_comment? ContainerMembers RBRACE
ContainerDeclType
<- KEYWORD_struct
/ KEYWORD_opaque
/ KEYWORD_enum (LPAREN Expr RPAREN)?
/ KEYWORD_union (LPAREN (KEYWORD_enum (LPAREN Expr RPAREN)? / Expr) RPAREN)?
ByteAlign <- KEYWORD_align LPAREN Expr RPAREN
IdentifierList <- (doc_comment? IDENTIFIER COMMA)* (doc_comment? IDENTIFIER)?
SwitchProngList <- (SwitchProng COMMA)* SwitchProng?
AsmOutputList <- (AsmOutputItem COMMA)* AsmOutputItem?
AsmInputList <- (AsmInputItem COMMA)* AsmInputItem?
StringList <- (STRINGLITERAL COMMA)* STRINGLITERAL?
ParamDeclList <- (ParamDecl COMMA)* ParamDecl?
ExprList <- (Expr COMMA)* Expr?
eof <- !.
bin <- [01]
bin_ <- '_'? bin
oct <- [0-7]
oct_ <- '_'? oct
hex <- [0-9a-fA-F]
hex_ <- '_'? hex
dec <- [0-9]
dec_ <- '_'? dec
bin_int <- bin bin_*
oct_int <- oct oct_*
dec_int <- dec dec_*
hex_int <- hex hex_*
ox80_oxBF <- [\200-\277]
oxF4 <- '\364'
ox80_ox8F <- [\200-\217]
oxF1_oxF3 <- [\361-\363]
oxF0 <- '\360'
ox90_0xBF <- [\220-\277]
oxEE_oxEF <- [\356-\357]
oxED <- '\355'
ox80_ox9F <- [\200-\237]
oxE1_oxEC <- [\341-\354]
oxE0 <- '\340'
oxA0_oxBF <- [\240-\277]
oxC2_oxDF <- [\302-\337]
mb_utf8_literal <-
oxF4 ox80_ox8F ox80_oxBF ox80_oxBF
/ oxF1_oxF3 ox80_oxBF ox80_oxBF ox80_oxBF
/ oxF0 ox90_0xBF ox80_oxBF ox80_oxBF
/ oxEE_oxEF ox80_oxBF ox80_oxBF
/ oxED ox80_ox9F ox80_oxBF
/ oxE1_oxEC ox80_oxBF ox80_oxBF
/ oxE0 oxA0_oxBF ox80_oxBF
/ oxC2_oxDF ox80_oxBF
ascii_char_not_nl_slash_squote <- [\000-\011\013-\046-\050-\133\135-\177]
char_escape
<- "\\x" hex hex
/ "\\u{" hex+ "}"
/ "\\" [nr\\t'"]
char_char
<- mb_utf8_literal
/ char_escape
/ ascii_char_not_nl_slash_squote
string_char
<- char_escape
/ [^\\"\n]
container_doc_comment <- ('//!' [^\n]* [ \n]*)+
doc_comment <- ('///' [^\n]* [ \n]*)+
line_comment <- '//' ![!/][^\n]* / '////' [^\n]*
line_string <- ("\\\\" [^\n]* [ \n]*)+
skip <- ([ \n] / line_comment)*
CHAR_LITERAL <- "'" char_char "'" skip
FLOAT
<- "0x" hex_int "." hex_int ([pP] [-+]? dec_int)? skip
/ dec_int "." dec_int ([eE] [-+]? dec_int)? skip
/ "0x" hex_int [pP] [-+]? dec_int skip
/ dec_int [eE] [-+]? dec_int skip
INTEGER
<- "0b" bin_int skip
/ "0o" oct_int skip
/ "0x" hex_int skip
/ dec_int skip
STRINGLITERALSINGLE <- "\"" string_char* "\"" skip
STRINGLITERAL
<- STRINGLITERALSINGLE
/ (line_string skip)+
IDENTIFIER
<- !keyword [A-Za-z_] [A-Za-z0-9_]* skip
/ "@\"" string_char* "\"" skip
BUILTINIDENTIFIER <- "@"[A-Za-z_][A-Za-z0-9_]* skip
AMPERSAND <- '&' ![=] skip
AMPERSANDEQUAL <- '&=' skip
ASTERISK <- '*' ![*%=] skip
ASTERISK2 <- '**' skip
ASTERISKEQUAL <- '*=' skip
ASTERISKPERCENT <- '*%' ![=] skip
ASTERISKPERCENTEQUAL <- '*%=' skip
CARET <- '^' ![=] skip
CARETEQUAL <- '^=' skip
COLON <- ':' skip
COMMA <- ',' skip
DOT <- '.' ![*.?] skip
DOT2 <- '..' ![.] skip
DOT3 <- '...' skip
DOTASTERISK <- '.*' skip
DOTQUESTIONMARK <- '.?' skip
EQUAL <- '=' ![>=] skip
EQUALEQUAL <- '==' skip
EQUALRARROW <- '=>' skip
EXCLAMATIONMARK <- '!' ![=] skip
EXCLAMATIONMARKEQUAL <- '!=' skip
LARROW <- '<' ![<=] skip
LARROW2 <- '<<' ![=] skip
LARROW2EQUAL <- '<<=' skip
LARROWEQUAL <- '<=' skip
LBRACE <- '{' skip
LBRACKET <- '[' skip
LPAREN <- '(' skip
MINUS <- '-' ![%=>] skip
MINUSEQUAL <- '-=' skip
MINUSPERCENT <- '-%' ![=] skip
MINUSPERCENTEQUAL <- '-%=' skip
MINUSRARROW <- '->' skip
PERCENT <- '%' ![=] skip
PERCENTEQUAL <- '%=' skip
PIPE <- '|' ![|=] skip
PIPE2 <- '||' skip
PIPEEQUAL <- '|=' skip
PLUS <- '+' ![%+=] skip
PLUS2 <- '++' skip
PLUSEQUAL <- '+=' skip
PLUSPERCENT <- '+%' ![=] skip
PLUSPERCENTEQUAL <- '+%=' skip
LETTERC <- 'c' skip
QUESTIONMARK <- '?' skip
RARROW <- '>' ![>=] skip
RARROW2 <- '>>' ![=] skip
RARROW2EQUAL <- '>>=' skip
RARROWEQUAL <- '>=' skip
RBRACE <- '}' skip
RBRACKET <- ']' skip
RPAREN <- ')' skip
SEMICOLON <- ';' skip
SLASH <- '/' ![=] skip
SLASHEQUAL <- '/=' skip
TILDE <- '~' skip
end_of_word <- ![a-zA-Z0-9_] skip
KEYWORD_align <- 'align' end_of_word
KEYWORD_allowzero <- 'allowzero' end_of_word
KEYWORD_and <- 'and' end_of_word
KEYWORD_anyframe <- 'anyframe' end_of_word
KEYWORD_anytype <- 'anytype' end_of_word
KEYWORD_asm <- 'asm' end_of_word
KEYWORD_async <- 'async' end_of_word
KEYWORD_await <- 'await' end_of_word
KEYWORD_break <- 'break' end_of_word
KEYWORD_callconv <- 'callconv' end_of_word
KEYWORD_catch <- 'catch' end_of_word
KEYWORD_comptime <- 'comptime' end_of_word
KEYWORD_const <- 'const' end_of_word
KEYWORD_continue <- 'continue' end_of_word
KEYWORD_defer <- 'defer' end_of_word
KEYWORD_else <- 'else' end_of_word
KEYWORD_enum <- 'enum' end_of_word
KEYWORD_errdefer <- 'errdefer' end_of_word
KEYWORD_error <- 'error' end_of_word
KEYWORD_export <- 'export' end_of_word
KEYWORD_extern <- 'extern' end_of_word
KEYWORD_fn <- 'fn' end_of_word
KEYWORD_for <- 'for' end_of_word
KEYWORD_if <- 'if' end_of_word
KEYWORD_inline <- 'inline' end_of_word
KEYWORD_noalias <- 'noalias' end_of_word
KEYWORD_nosuspend <- 'nosuspend' end_of_word
KEYWORD_noinline <- 'noinline' end_of_word
KEYWORD_opaque <- 'opaque' end_of_word
KEYWORD_or <- 'or' end_of_word
KEYWORD_orelse <- 'orelse' end_of_word
KEYWORD_packed <- 'packed' end_of_word
KEYWORD_pub <- 'pub' end_of_word
KEYWORD_resume <- 'resume' end_of_word
KEYWORD_return <- 'return' end_of_word
KEYWORD_linksection <- 'linksection' end_of_word
KEYWORD_struct <- 'struct' end_of_word
KEYWORD_suspend <- 'suspend' end_of_word
KEYWORD_switch <- 'switch' end_of_word
KEYWORD_test <- 'test' end_of_word
KEYWORD_threadlocal <- 'threadlocal' end_of_word
KEYWORD_try <- 'try' end_of_word
KEYWORD_union <- 'union' end_of_word
KEYWORD_unreachable <- 'unreachable' end_of_word
KEYWORD_usingnamespace <- 'usingnamespace' end_of_word
KEYWORD_var <- 'var' end_of_word
KEYWORD_volatile <- 'volatile' end_of_word
KEYWORD_while <- 'while' end_of_word
keyword <- KEYWORD_align / KEYWORD_allowzero / KEYWORD_and / KEYWORD_anyframe
/ KEYWORD_anytype / KEYWORD_asm / KEYWORD_async / KEYWORD_await
/ KEYWORD_break / KEYWORD_callconv / KEYWORD_catch / KEYWORD_comptime
/ KEYWORD_const / KEYWORD_continue / KEYWORD_defer / KEYWORD_else
/ KEYWORD_enum / KEYWORD_errdefer / KEYWORD_error / KEYWORD_export
/ KEYWORD_extern / KEYWORD_fn / KEYWORD_for / KEYWORD_if
/ KEYWORD_inline / KEYWORD_noalias / KEYWORD_nosuspend / KEYWORD_noinline
/ KEYWORD_opaque / KEYWORD_or / KEYWORD_orelse / KEYWORD_packed
/ KEYWORD_pub / KEYWORD_resume / KEYWORD_return / KEYWORD_linksection
/ KEYWORD_struct / KEYWORD_suspend / KEYWORD_switch / KEYWORD_test
/ KEYWORD_threadlocal / KEYWORD_try / KEYWORD_union / KEYWORD_unreachable
/ KEYWORD_usingnamespace / KEYWORD_var / KEYWORD_volatile / KEYWORD_while