diff options
Diffstat (limited to 'docs/SYNTAX.md')
| -rw-r--r-- | docs/SYNTAX.md | 184 |
1 files changed, 94 insertions, 90 deletions
diff --git a/docs/SYNTAX.md b/docs/SYNTAX.md index 49fdd59..a1c8bfb 100644 --- a/docs/SYNTAX.md +++ b/docs/SYNTAX.md @@ -1,37 +1,46 @@ # Syntax: A Casual and Formal Look -... - -## A Formal Look - -We now shall take a look at a more formal description of Puck's syntax. Syntax rules are described in extended Backus–Naur form (EBNF) - but most rules surrounding whitespace, and scope, and line breaks, are modified to how they would appear after a lexing step (whitespace is removed, line breaks are normalized, scope is switched to use `{` and `}`). +## Reserved Keywords + +The following keywords are reserved: +- variables: `let` `var` `const` +- control flow: `if` `elif` `else` +- pattern matching: `match` `of` +- loops: `loop` `while` `for` `in` +- blocks: `block` `break` `continue` `return` +- functions: `func` `mut` `static` `varargs` +- modules: `pub` `mod` `use` `as` +- error handling: `try` `catch` `finally` +- metaprogramming: `macro` `quote` `when` +- types: `type` `distinct` `ref` +- types: `struct` `tuple` `union` `enum` `interface` +- reserved: + - `impl` `object` `class` `concept` `auto` `empty` `effect` `case` `nil` + - `suspend` `resume` `spawn` `pool` `thread` `closure` + - `cyclic` `acyclic` `sink` `move` `destroy` `copy` `trace` `deepcopy` + +## A Formal Grammar + +We now shall take a look at a more formal description of Puck's syntax. Syntax rules are described in [extended Backus–Naur form](https://en.wikipedia.org/wiki/Extended_Backus–Naur_form) (EBNF): however, most rules surrounding whitespace, and scope, and line breaks, are modified to how they would appear after a lexing step. ### Identifiers ``` -IDENT ::= LETTER (LETTER | DIGIT | '_')* # todo: support _ -LETTER ::= 'A'..'Z' | 'a'..'z' | '\x80'..'\xff' # todo -DIGIT ::= '0'..'9' +Ident ::= (Letter | '_') (Letter | Digit | '_')* +Letter ::= 'A'..'Z' | 'a'..'z' | '\x80'..'\xff' # todo +Digit ::= '0'..'9' ``` ### Literals ``` -INT_LIT ::= '-'? (DEC_LIT | HEX_LIT | OCT_LIT | BIN_LIT) -BIN_LIT ::= '0b' BIN_DIGIT ('_'? BIN_DIGIT)* -OCT_LIT ::= '0o' OCT_DIGIT ('_'? OCT_DIGIT)* -HEX_LIT ::= '0x' HEX_DIGIT ('_'? HEX_DIGIT)* -DEC_LIT ::= DIGIT ('_'? DIGIT)* -BIN_DIGIT ::= '0'..'1' -OCT_DIGIT ::= '0'..'7' -HEX_DIGIT ::= DIGIT | 'A'..'F' | 'a'..'f' -``` - -### Operators -``` -OPERATOR ::= 'and' | 'or' | 'not' | 'xor' | 'shl' | 'shr' | # todo: more? - 'div' | 'mod' | 'rem' | 'is' | 'isnot' | OPR+ -OPR ::= '=' | '+' | '-' | '*' | '/' | '<' | '>' | # todo: more? - '@' | '$' | '~' | '&' | '%' | '|' | - '!' | '?' | '^' | '.' | ':' | '\\' +Int ::= '-'? (DecLit | HexLit | OctLit | BinLit) +Float ::= '-'? DecLit '.' DecLit +BinLit ::= '0b' BinDigit ('_'? BinDigit)* +OctLit ::= '0o' OctDigit ('_'? OctDigit)* +HexLit ::= '0x' HexDigit ('_'? HexDigit)* +DecLit ::= Digit ('_'? Digit)* +BinDigit ::= '0'..'1' +OctDigit ::= '0'..'7' +HexDigit ::= Digit | 'A'..'F' | 'a'..'f' ``` ### Chars, Strings, and Comments @@ -52,95 +61,90 @@ PRINT ::= LETTER | DIGIT | OPR | ### Values ``` -VALUE ::= INT_LIT | STRING | CHAR | LIST_DECL | ARRAY_DECL | TUPLE_DECL | STRUCT_DECL -LIST_DECL ::= '[' (EXPR (',' EXPR)*)? ']' -ARRAY_DECL ::= '[' (EXPR (',' EXPR)*)? ']' -TUPLE_DECL ::= '(' (IDENT '=')? EXPR (',' (IDENT '=')? EXPR)* ')' -STRUCT_DECL ::= '{' IDENT '=' EXPR (',' IDENT '=' EXPR)* '}' -# note: no union or enum. should struct exist? only in a structural system. +Value ::= Int | Float | String | Char | Array | Tuple | Struct +Array ::= '[' (Expr (',' Expr)*)? ']' +Tuple ::= '(' (Ident ':')? Expr (',' (Ident ':')? Expr)* ')' +Struct ::= '{' Ident ':' Expr (',' Ident ':' Expr)* '}' ``` ### Variables ``` -DECL ::= LET_DECL | VAR_DECL | CONST_DECL | FUNC_DECL | TYPE_DECL -LET_DECL ::= 'let' GROUP ANNOTATION? '=' EXPR -VAR_DECL ::= 'var' GROUP ANNOTATION? ('=' EXPR)? -CONST_DECL ::= 'pub'? 'const' GROUP ANNOTATION? '=' EXPR -GROUP ::= ('(' IDENT (',' IDENT)* ')') | IDENT +Decl ::= Let | Var | Const | Func | Type +Let ::= 'let' Pattern Annotation? '=' Expr +Var ::= 'var' Pattern Annotation? ('=' Expr)? +Const ::= 'pub'? 'const' Pattern Annotation? '=' Expr +Pattern ::= Char | String | Number | Float | Ident | '(' Pattern (',' Pattern)* ')' + Ident '(' Pattern (',' Pattern)* ')' ``` -### Functions +### Declarations ``` -FUNC_DECL ::= SIGNATURE '=' (EXPR | STMT) -SIGNATURE ::= 'pub'? ('pure' | 'yeet' | IDENT)? 'func' IDENT GENERICS? PARAMETERS? -PARAMETERS ::= '(' (PARAMETER (',' PARAMETER)?)? ')' -PARAMETER ::= ('var' | 'static')? IDENT ANNOTATION? -GENERICS ::= '[' IDENT ANNOTATION? (',' IDENT ANNOTATION?)* ']' -ANNOTATION ::= ':' TYPE_DESC +Func ::= 'pub'? 'func' Ident Generics? Parameters? Annotation? '=' Body +Macro ::= 'pub'? 'macro' Ident Generics? Parameters? Annotation? '=' Body +Generics ::= '[' Ident Annotation? (',' Ident Annotation?)* ']' +Parameters ::= '(' Ident Annotation? (',' Ident Annotation?)* ')' +Annotation ::= ':' Type ``` ### Types ``` -TYPE_DECL ::= 'pub'? 'type' IDENT GENERICS? '=' 'ref'? 'distinct'? TYPE_DESC -TYPE_DESC ::= TUPLE_TYPE | STRUCT_TYPE | UNION_TYPE | ENUM_TYPE | INTERFACE | IDENT | - (TYPE_DESC ('|' TYPE_DESC)+) -TUPLE_TYPE ::= 'tuple' '[' (IDENT ':')? TYPE_DESC (',' (IDENT ':')? TYPE_DESC)* ']' -STRUCT_TYPE ::= 'struct' '[' IDENT ANNOTATION (',' IDENT ANNOTATION)* ']' -UNION_TYPE ::= 'union' '[' IDENT ANNOTATION (',' IDENT ANNOTATION)* ']' -ENUM_TYPE ::= 'enum' '[' IDENT ('=' EXPR)? (',' IDENT ('=' EXPR)?)* ']' -FUNC_TYPE ::= 'func' GENERICS? PARAMETERS? ANNOTATION? -INTERFACE ::= 'interface' '[' SIGNATURE (',' SIGNATURE)* ('for' TYPE_DESC)? ']' +TypeDecl ::= 'pub'? 'type' Ident Generics? '=' Type +Type ::= StructType | TupleType | EnumType | UnionType | Interface | + (('distinct' | 'ref' | 'ptr' | 'mut' | 'static') (Type | ('[' Type ']'))?) +StructType ::= 'struct' ('[' Ident ':' Type (',' Ident ':' Type)* ']')? +UnionType ::= 'union' ('[' Ident ':' Type (',' Ident ':' Type)* ']')? +TupleType ::= 'tuple' ('[' (Ident ':')? Type (',' (Ident ':')? Type)* ']')? +EnumType ::= 'enum' ('[' Ident ('=' Expr)? (',' Ident ('=' Expr)?)* ']')? +Interface ::= 'interface' ('[' Signature (',' Signature)* ']')? +Signature ::= Ident Generics? ('(' Type (',' Type)* ')')? Annotation? ``` ## Control Flow ``` -IF_EXPR ::= 'if' EXPR '{' EXPR '}' ('elif' EXPR '{' EXPR '}')* 'else' '{' EXPR '}' -IF_STMT ::= 'if' EXPR '{' STMT '}' ('elif' EXPR '{' STMT '}')* ('else' '{' STMT '}')? -WHEN_EXPR ::= 'when' EXPR '{' EXPR '}' ('elif' EXPR '{' EXPR '}')* 'else' '{' EXPR '}' -WHEN_STMT ::= 'when' EXPR '{' STMT '}' ('elif' EXPR '{' EXPR '}')* ('else' '{' STMT '}')? -BLOCK_EXPR ::= 'block' IDENT? '{' EXPR '}' -BLOCK_STMT ::= 'block' IDENT? '{' STMT '}' -MATCH_EXPR ::= 'match' EXPR '{' - ('case' EXPR ('where' EXPR)? (',' EXPR ('where' EXPR)?)* '{' EXPR '}')+ '}' -MATCH_STMT ::= 'match' EXPR '{' - ('case' EXPR ('where' EXPR)? (',' EXPR ('where' EXPR)?)* '{' STMT '}')+ '}' -LOOP_STMT ::= 'loop' '{' STMT '}' -WHILE_STMT ::= 'while' EXPR '{' STMT '}' -FOR_STMT ::= 'for' GROUP 'in' EXPR '{' STMT '}' +If ::= 'if' Expr ':' Body ('elif' Expr ':' Body)* ('else' ':' Body)? +When ::= 'when' Expr ':' Body ('elif' Expr ':' Body)* ('else' ':' Body)? +Try ::= 'try' ':' Body + ('except' Ident ('as' Ident)? (',' Ident ('as' Ident)?)*) ':' Body)* + ('finally' ':' Body)? +Match ::= 'match' Expr ('of' Pattern (',' Pattern)* ('where' Expr)? ':' Body)+ +Block ::= 'block' Ident? ':' Body +Block ::= 'static' ':' Body +Loop ::= 'loop' ':' Body +While ::= 'while' Expr ':' Body +For ::= 'for' Pattern 'in' Expr Body ``` ## Modules ``` -IMPORT_STMT ::= 'import' IDENT_AS? - ('/' (IDENT_AS | '[' (IDENT_AS (',' IDENT_AS)*)? ']'))* -EXPORT_STMT ::= 'export' IDENT_AS? - ('/' (IDENT_AS | '[' (IDENT_AS (',' IDENT_AS)*)? ']'))* -MODULE_STMT ::= 'module' IDENT '{' STMT '}' -IDENT_AS ::= IDENT ('as' IDENT)? +Mod ::= 'pub'? 'mod' Ident ':' Body +Use ::= 'use' Ident ('/' Ident)* ('/' ('[' Ident (',' Ident)* ']'))? ``` -## Macros +### Operators ``` -MACRO_FUNC ::= IDENT '(' EXPR ')' -MACRO_BLOCK ::= IDENT '{' EXPR '}' # todo +Operator ::= 'and' | 'or' | 'not' | 'xor' | 'shl' | 'shr' | + 'div' | 'mod' | 'rem' | 'is' | 'in' | + Opr+ +Opr ::= '=' | '+' | '-' | '*' | '/' | '<' | '>' | + '@' | '$' | '~' | '&' | '%' | '|' | + '!' | '?' | '^' | '.' | ':' | '\\' ``` -## Calls, Statements, and Expressions +## Calls and Expressions ``` -OPERATION ::= EXPR OPERATOR EXPR -PREFIX ::= OPERATOR EXPR -SUFFIX ::= EXPR OPERATOR -APPLICATION ::= IDENT PARAMS? | IDENT EXPR | (APPLICATION | PREFIX | SUFFIX) '.' IDENT PARAMS? -PARAMS ::= '(' ((IDENT '=')? EXPR (',' (IDENT '=')? EXPR)*)? ')' +Call ::= Ident ('[' Call (',' Call)* ']')? ('(' (Ident '=')? Call (',' (Ident '=')? Call)* ')')? | + Ident Call (',' Call)* | + Call Operator Call? | + Call ':' Body +Expr ::= Let | Var | Const | Func | Type | Mod | Use | Block | Static | + For | While | Loop | If | When | Try | Match | Call +Body ::= Expr | ('{' Expr (';' Expr)* '}') ``` -``` -EXPR ::= IF_EXPR | WHEN_EXPR | BLOCK_EXPR | MATCH_EXPR | - MACRO_FUNC | MACRO_BLOCK | - APPLICATION | OPERATION | PREFIX | SUFFIX | - VALUE | (STMT EXPR) # todo -STMT ::= IF_STMT | WHEN_STMT | BLOCK_STMT | MATCH_STMT | - LOOP_STMT | WHILE_STMT | FOR_STMT | - IMPORT_STMT | EXPORT_STMT | MODULE_STMT | - ((APPLICATION | OPERATION | PREFIX | SUFFIX | DECL) ';') | (STMT+ STMT) -``` +--- + +References: +- https://www.joshwcomeau.com/javascript/statements-vs-expressions/ +- https://pgrandinetti.github.io/compilers/ +- https://docs.swift.org/swift-book/ReferenceManual/LexicalStructure.html +- https://nim-lang.github.io/Nim/manual.html |