diff --git a/src/doc/grammar.md b/src/doc/grammar.md index ee9135b6578f6..4501d74073e90 100644 --- a/src/doc/grammar.md +++ b/src/doc/grammar.md @@ -1,812 +1,7 @@ % Grammar -# Introduction +The Rust grammar may now be found in the [reference]. Additionally, the [grammar +working group] is working on producing a testable grammar. -This document is the primary reference for the Rust programming language grammar. It -provides only one kind of material: - - - Chapters that formally define the language grammar. - -This document does not serve as an introduction to the language. Background -familiarity with the language is assumed. A separate [guide] is available to -help acquire such background. - -This document also does not serve as a reference to the [standard] library -included in the language distribution. Those libraries are documented -separately by extracting documentation attributes from their source code. Many -of the features that one might expect to be language features are library -features in Rust, so what you're looking for may be there, not here. - -[guide]: guide.html -[standard]: std/index.html - -# Notation - -Rust's grammar is defined over Unicode codepoints, each conventionally denoted -`U+XXXX`, for 4 or more hexadecimal digits `X`. _Most_ of Rust's grammar is -confined to the ASCII range of Unicode, and is described in this document by a -dialect of Extended Backus-Naur Form (EBNF), specifically a dialect of EBNF -supported by common automated LL(k) parsing tools such as `llgen`, rather than -the dialect given in ISO 14977. The dialect can be defined self-referentially -as follows: - -```antlr -grammar : rule + ; -rule : nonterminal ':' productionrule ';' ; -productionrule : production [ '|' production ] * ; -production : term * ; -term : element repeats ; -element : LITERAL | IDENTIFIER | '[' productionrule ']' ; -repeats : [ '*' | '+' ] NUMBER ? | NUMBER ? | '?' ; -``` - -Where: - -- Whitespace in the grammar is ignored. -- Square brackets are used to group rules. -- `LITERAL` is a single printable ASCII character, or an escaped hexadecimal - ASCII code of the form `\xQQ`, in single quotes, denoting the corresponding - Unicode codepoint `U+00QQ`. -- `IDENTIFIER` is a nonempty string of ASCII letters and underscores. -- The `repeat` forms apply to the adjacent `element`, and are as follows: - - `?` means zero or one repetition - - `*` means zero or more repetitions - - `+` means one or more repetitions - - NUMBER trailing a repeat symbol gives a maximum repetition count - - NUMBER on its own gives an exact repetition count - -This EBNF dialect should hopefully be familiar to many readers. - -## Unicode productions - -A few productions in Rust's grammar permit Unicode codepoints outside the ASCII -range. We define these productions in terms of character properties specified -in the Unicode standard, rather than in terms of ASCII-range codepoints. The -section [Special Unicode Productions](#special-unicode-productions) lists these -productions. - -## String table productions - -Some rules in the grammar — notably [unary -operators](#unary-operator-expressions), [binary -operators](#binary-operator-expressions), and [keywords](#keywords) — are -given in a simplified form: as a listing of a table of unquoted, printable -whitespace-separated strings. These cases form a subset of the rules regarding -the [token](#tokens) rule, and are assumed to be the result of a -lexical-analysis phase feeding the parser, driven by a DFA, operating over the -disjunction of all such string table entries. - -When such a string enclosed in double-quotes (`"`) occurs inside the grammar, -it is an implicit reference to a single member of such a string table -production. See [tokens](#tokens) for more information. - -# Lexical structure - -## Input format - -Rust input is interpreted as a sequence of Unicode codepoints encoded in UTF-8. -Most Rust grammar rules are defined in terms of printable ASCII-range -codepoints, but a small number are defined in terms of Unicode properties or -explicit codepoint lists. [^inputformat] - -[^inputformat]: Substitute definitions for the special Unicode productions are - provided to the grammar verifier, restricted to ASCII range, when verifying the - grammar in this document. - -## Special Unicode Productions - -The following productions in the Rust grammar are defined in terms of Unicode -properties: `ident`, `non_null`, `non_eol`, `non_single_quote` and -`non_double_quote`. - -### Identifiers - -The `ident` production is any nonempty Unicode string of -the following form: - -- The first character is in one of the following ranges `U+0041` to `U+005A` -("A" to "Z"), `U+0061` to `U+007A` ("a" to "z"), or `U+005F` ("\_"). -- The remaining characters are in the range `U+0030` to `U+0039` ("0" to "9"), -or any of the prior valid initial characters. - -as long as the identifier does _not_ occur in the set of [keywords](#keywords). - -### Delimiter-restricted productions - -Some productions are defined by exclusion of particular Unicode characters: - -- `non_null` is any single Unicode character aside from `U+0000` (null) -- `non_eol` is any single Unicode character aside from `U+000A` (`'\n'`) -- `non_single_quote` is any single Unicode character aside from `U+0027` (`'`) -- `non_double_quote` is any single Unicode character aside from `U+0022` (`"`) - -## Comments - -```antlr -comment : block_comment | line_comment ; -block_comment : "/*" block_comment_body * "*/" ; -block_comment_body : [block_comment | character] * ; -line_comment : "//" non_eol * ; -``` - -**FIXME:** add doc grammar? - -## Whitespace - -```antlr -whitespace_char : '\x20' | '\x09' | '\x0a' | '\x0d' ; -whitespace : [ whitespace_char | comment ] + ; -``` - -## Tokens - -```antlr -simple_token : keyword | unop | binop ; -token : simple_token | ident | literal | symbol | whitespace token ; -``` - -### Keywords - -

- -| | | | | | -|----------|----------|----------|----------|----------| -| _ | abstract | alignof | as | become | -| box | break | const | continue | crate | -| do | else | enum | extern | false | -| final | fn | for | if | impl | -| in | let | loop | macro | match | -| mod | move | mut | offsetof | override | -| priv | proc | pub | pure | ref | -| return | Self | self | sizeof | static | -| struct | super | trait | true | type | -| typeof | unsafe | unsized | use | virtual | -| where | while | yield | | | - - -Each of these keywords has special meaning in its grammar, and all of them are -excluded from the `ident` rule. - -Not all of these keywords are used by the language. Some of them were used -before Rust 1.0, and were left reserved once their implementations were -removed. Some of them were reserved before 1.0 to make space for possible -future features. - -### Literals - -```antlr -lit_suffix : ident; -literal : [ string_lit | char_lit | byte_string_lit | byte_lit | num_lit | bool_lit ] lit_suffix ?; -``` - -The optional `lit_suffix` production is only used for certain numeric literals, -but is reserved for future extension. That is, the above gives the lexical -grammar, but a Rust parser will reject everything but the 12 special cases -mentioned in [Number literals](reference/tokens.html#number-literals) in the -reference. - -#### Character and string literals - -```antlr -char_lit : '\x27' char_body '\x27' ; -string_lit : '"' string_body * '"' | 'r' raw_string ; - -char_body : non_single_quote - | '\x5c' [ '\x27' | common_escape | unicode_escape ] ; - -string_body : non_double_quote - | '\x5c' [ '\x22' | common_escape | unicode_escape ] ; -raw_string : '"' raw_string_body '"' | '#' raw_string '#' ; - -common_escape : '\x5c' - | 'n' | 'r' | 't' | '0' - | 'x' hex_digit 2 -unicode_escape : 'u' '{' hex_digit+ 6 '}'; - -hex_digit : 'a' | 'b' | 'c' | 'd' | 'e' | 'f' - | 'A' | 'B' | 'C' | 'D' | 'E' | 'F' - | dec_digit ; -oct_digit : '0' | '1' | '2' | '3' | '4' | '5' | '6' | '7' ; -dec_digit : '0' | nonzero_dec ; -nonzero_dec: '1' | '2' | '3' | '4' - | '5' | '6' | '7' | '8' | '9' ; -``` - -#### Byte and byte string literals - -```antlr -byte_lit : "b\x27" byte_body '\x27' ; -byte_string_lit : "b\x22" string_body * '\x22' | "br" raw_byte_string ; - -byte_body : ascii_non_single_quote - | '\x5c' [ '\x27' | common_escape ] ; - -byte_string_body : ascii_non_double_quote - | '\x5c' [ '\x22' | common_escape ] ; -raw_byte_string : '"' raw_byte_string_body '"' | '#' raw_byte_string '#' ; - -``` - -#### Number literals - -```antlr -num_lit : nonzero_dec [ dec_digit | '_' ] * float_suffix ? - | '0' [ [ dec_digit | '_' ] * float_suffix ? - | 'b' [ '1' | '0' | '_' ] + - | 'o' [ oct_digit | '_' ] + - | 'x' [ hex_digit | '_' ] + ] ; - -float_suffix : [ exponent | '.' dec_lit exponent ? ] ? ; - -exponent : ['E' | 'e'] ['-' | '+' ] ? dec_lit ; -dec_lit : [ dec_digit | '_' ] + ; -``` - -#### Boolean literals - -```antlr -bool_lit : [ "true" | "false" ] ; -``` - -The two values of the boolean type are written `true` and `false`. - -### Symbols - -```antlr -symbol : "::" | "->" - | '#' | '[' | ']' | '(' | ')' | '{' | '}' - | ',' | ';' ; -``` - -Symbols are a general class of printable [tokens](#tokens) that play structural -roles in a variety of grammar productions. They are cataloged here for -completeness as the set of remaining miscellaneous printable tokens that do not -otherwise appear as [unary operators](#unary-operator-expressions), [binary -operators](#binary-operator-expressions), or [keywords](#keywords). - -## Paths - -```antlr -expr_path : [ "::" ] ident [ "::" expr_path_tail ] + ; -expr_path_tail : '<' type_expr [ ',' type_expr ] + '>' - | expr_path ; - -type_path : ident [ type_path_tail ] + ; -type_path_tail : '<' type_expr [ ',' type_expr ] + '>' - | "::" type_path ; -``` - -# Syntax extensions - -## Macros - -```antlr -expr_macro_rules : "macro_rules" '!' ident '(' macro_rule * ')' ';' - | "macro_rules" '!' ident '{' macro_rule * '}' ; -macro_rule : '(' matcher * ')' "=>" '(' transcriber * ')' ';' ; -matcher : '(' matcher * ')' | '[' matcher * ']' - | '{' matcher * '}' | '$' ident ':' ident - | '$' '(' matcher * ')' sep_token? [ '*' | '+' ] - | non_special_token ; -transcriber : '(' transcriber * ')' | '[' transcriber * ']' - | '{' transcriber * '}' | '$' ident - | '$' '(' transcriber * ')' sep_token? [ '*' | '+' ] - | non_special_token ; -``` - -# Crates and source files - -**FIXME:** grammar? What production covers #![crate_id = "foo"] ? - -# Items and attributes - -**FIXME:** grammar? - -## Items - -```antlr -item : vis ? mod_item | fn_item | type_item | struct_item | enum_item - | const_item | static_item | trait_item | impl_item | extern_block_item ; -``` - -### Type Parameters - -**FIXME:** grammar? - -### Modules - -```antlr -mod_item : "mod" ident ( ';' | '{' mod '}' ); -mod : [ view_item | item ] * ; -``` - -#### View items - -```antlr -view_item : extern_crate_decl | use_decl ';' ; -``` - -##### Extern crate declarations - -```antlr -extern_crate_decl : "extern" "crate" crate_name -crate_name: ident | ( ident "as" ident ) -``` - -##### Use declarations - -```antlr -use_decl : vis ? "use" [ path "as" ident - | path_glob ] ; - -path_glob : ident [ "::" [ path_glob - | '*' ] ] ? - | '{' path_item [ ',' path_item ] * '}' ; - -path_item : ident | "self" ; -``` - -### Functions - -**FIXME:** grammar? - -#### Generic functions - -**FIXME:** grammar? - -#### Unsafety - -**FIXME:** grammar? - -##### Unsafe functions - -**FIXME:** grammar? - -##### Unsafe blocks - -**FIXME:** grammar? - -#### Diverging functions - -**FIXME:** grammar? - -### Type definitions - -**FIXME:** grammar? - -### Structures - -**FIXME:** grammar? - -### Enumerations - -**FIXME:** grammar? - -### Constant items - -```antlr -const_item : "const" ident ':' type '=' expr ';' ; -``` - -### Static items - -```antlr -static_item : "static" ident ':' type '=' expr ';' ; -``` - -#### Mutable statics - -**FIXME:** grammar? - -### Traits - -**FIXME:** grammar? - -### Implementations - -**FIXME:** grammar? - -### External blocks - -```antlr -extern_block_item : "extern" '{' extern_block '}' ; -extern_block : [ foreign_fn ] * ; -``` - -## Visibility and Privacy - -```antlr -vis : "pub" ; -``` -### Re-exporting and Visibility - -See [Use declarations](#use-declarations). - -## Attributes - -```antlr -attribute : '#' '!' ? '[' meta_item ']' ; -meta_item : ident [ '=' literal - | '(' meta_seq ')' ] ? ; -meta_seq : meta_item [ ',' meta_seq ] ? ; -``` - -# Statements and expressions - -## Statements - -```antlr -stmt : decl_stmt | expr_stmt | ';' ; -``` - -### Declaration statements - -```antlr -decl_stmt : item | let_decl ; -``` - -#### Item declarations - -See [Items](#items). - -#### Variable declarations - -```antlr -let_decl : "let" pat [':' type ] ? [ init ] ? ';' ; -init : [ '=' ] expr ; -``` - -### Expression statements - -```antlr -expr_stmt : expr ';' ; -``` - -## Expressions - -```antlr -expr : literal | path | tuple_expr | unit_expr | struct_expr - | block_expr | method_call_expr | field_expr | array_expr - | idx_expr | range_expr | unop_expr | binop_expr - | paren_expr | call_expr | lambda_expr | while_expr - | loop_expr | break_expr | continue_expr | for_expr - | if_expr | match_expr | if_let_expr | while_let_expr - | return_expr ; -``` - -#### Lvalues, rvalues and temporaries - -**FIXME:** grammar? - -#### Moved and copied types - -**FIXME:** Do we want to capture this in the grammar as different productions? - -### Literal expressions - -See [Literals](#literals). - -### Path expressions - -See [Paths](#paths). - -### Tuple expressions - -```antlr -tuple_expr : '(' [ expr [ ',' expr ] * | expr ',' ] ? ')' ; -``` - -### Unit expressions - -```antlr -unit_expr : "()" ; -``` - -### Structure expressions - -```antlr -struct_expr_field_init : ident | ident ':' expr ; -struct_expr : expr_path '{' struct_expr_field_init - [ ',' struct_expr_field_init ] * - [ ".." expr ] '}' | - expr_path '(' expr - [ ',' expr ] * ')' | - expr_path ; -``` - -### Block expressions - -```antlr -block_expr : '{' [ stmt | item ] * - [ expr ] '}' ; -``` - -### Method-call expressions - -```antlr -method_call_expr : expr '.' ident paren_expr_list ; -``` - -### Field expressions - -```antlr -field_expr : expr '.' ident ; -``` - -### Array expressions - -```antlr -array_expr : '[' "mut" ? array_elems? ']' ; - -array_elems : [expr [',' expr]*] | [expr ';' expr] ; -``` - -### Index expressions - -```antlr -idx_expr : expr '[' expr ']' ; -``` - -### Range expressions - -```antlr -range_expr : expr ".." expr | - expr ".." | - ".." expr | - ".." ; -``` - -### Unary operator expressions - -```antlr -unop_expr : unop expr ; -unop : '-' | '*' | '!' ; -``` - -### Binary operator expressions - -```antlr -binop_expr : expr binop expr | type_cast_expr - | assignment_expr | compound_assignment_expr ; -binop : arith_op | bitwise_op | lazy_bool_op | comp_op -``` - -#### Arithmetic operators - -```antlr -arith_op : '+' | '-' | '*' | '/' | '%' ; -``` - -#### Bitwise operators - -```antlr -bitwise_op : '&' | '|' | '^' | "<<" | ">>" ; -``` - -#### Lazy boolean operators - -```antlr -lazy_bool_op : "&&" | "||" ; -``` - -#### Comparison operators - -```antlr -comp_op : "==" | "!=" | '<' | '>' | "<=" | ">=" ; -``` - -#### Type cast expressions - -```antlr -type_cast_expr : value "as" type ; -``` - -#### Assignment expressions - -```antlr -assignment_expr : expr '=' expr ; -``` - -#### Compound assignment expressions - -```antlr -compound_assignment_expr : expr [ arith_op | bitwise_op ] '=' expr ; -``` - -### Grouped expressions - -```antlr -paren_expr : '(' expr ')' ; -``` - -### Call expressions - -```antlr -expr_list : [ expr [ ',' expr ]* ] ? ; -paren_expr_list : '(' expr_list ')' ; -call_expr : expr paren_expr_list ; -``` - -### Lambda expressions - -```antlr -ident_list : [ ident [ ',' ident ]* ] ? ; -lambda_expr : '|' ident_list '|' expr ; -``` - -### While loops - -```antlr -while_expr : [ lifetime ':' ] ? "while" no_struct_literal_expr '{' block '}' ; -``` - -### Infinite loops - -```antlr -loop_expr : [ lifetime ':' ] ? "loop" '{' block '}'; -``` - -### Break expressions - -```antlr -break_expr : "break" [ lifetime ] ?; -``` - -### Continue expressions - -```antlr -continue_expr : "continue" [ lifetime ] ?; -``` - -### For expressions - -```antlr -for_expr : [ lifetime ':' ] ? "for" pat "in" no_struct_literal_expr '{' block '}' ; -``` - -### If expressions - -```antlr -if_expr : "if" no_struct_literal_expr '{' block '}' - else_tail ? ; - -else_tail : "else" [ if_expr | if_let_expr - | '{' block '}' ] ; -``` - -### Match expressions - -```antlr -match_expr : "match" no_struct_literal_expr '{' match_arm * '}' ; - -match_arm : attribute * match_pat "=>" [ expr "," | '{' block '}' ] ; - -match_pat : pat [ '|' pat ] * [ "if" expr ] ? ; -``` - -### If let expressions - -```antlr -if_let_expr : "if" "let" pat '=' expr '{' block '}' - else_tail ? ; -``` - -### While let loops - -```antlr -while_let_expr : [ lifetime ':' ] ? "while" "let" pat '=' expr '{' block '}' ; -``` - -### Return expressions - -```antlr -return_expr : "return" expr ? ; -``` - -# Type system - -**FIXME:** is this entire chapter relevant here? Or should it all have been covered by some production already? - -## Types - -### Primitive types - -**FIXME:** grammar? - -#### Machine types - -**FIXME:** grammar? - -#### Machine-dependent integer types - -**FIXME:** grammar? - -### Textual types - -**FIXME:** grammar? - -### Tuple types - -**FIXME:** grammar? - -### Array, and Slice types - -**FIXME:** grammar? - -### Structure types - -**FIXME:** grammar? - -### Enumerated types - -**FIXME:** grammar? - -### Pointer types - -**FIXME:** grammar? - -### Function types - -**FIXME:** grammar? - -### Closure types - -```antlr -closure_type := [ 'unsafe' ] [ '<' lifetime-list '>' ] '|' arg-list '|' - [ ':' bound-list ] [ '->' type ] -lifetime-list := lifetime | lifetime ',' lifetime-list -arg-list := ident ':' type | ident ':' type ',' arg-list -``` - -### Never type -An empty type - -```antlr -never_type : "!" ; -``` - -### Object types - -**FIXME:** grammar? - -### Type parameters - -**FIXME:** grammar? - -### Type parameter bounds - -```antlr -bound-list := bound | bound '+' bound-list '+' ? -bound := ty_bound | lt_bound -lt_bound := lifetime -ty_bound := ty_bound_noparen | (ty_bound_noparen) -ty_bound_noparen := [?] [ for ] simple_path -``` - -### Self types - -**FIXME:** grammar? - -## Type kinds - -**FIXME:** this is probably not relevant to the grammar... - -# Memory and concurrency models - -**FIXME:** is this entire chapter relevant here? Or should it all have been covered by some production already? - -## Memory model - -### Memory allocation and lifetime - -### Memory ownership - -### Variables - -### Boxes - -## Threads - -### Communication between threads - -### Thread lifecycle +[reference]: https://doc.rust-lang.org/reference/ +[grammar working group]: https://github.com/rust-lang/wg-grammar diff --git a/src/grammar/.gitignore b/src/grammar/.gitignore deleted file mode 100644 index 3e4498759434f..0000000000000 --- a/src/grammar/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -*.class -*.java -*.tokens diff --git a/src/grammar/lexer.l b/src/grammar/lexer.l deleted file mode 100644 index 1feb781b2b39f..0000000000000 --- a/src/grammar/lexer.l +++ /dev/null @@ -1,350 +0,0 @@ -%{ -#include -#include - -static int num_hashes; -static int end_hashes; -static int saw_non_hash; - -%} - -%option stack -%option yylineno - -%x str -%x rawstr -%x rawstr_esc_begin -%x rawstr_esc_body -%x rawstr_esc_end -%x byte -%x bytestr -%x rawbytestr -%x rawbytestr_nohash -%x pound -%x shebang_or_attr -%x ltorchar -%x linecomment -%x doc_line -%x blockcomment -%x doc_block -%x suffix - -ident [a-zA-Z\x80-\xff_][a-zA-Z0-9\x80-\xff_]* - -%% - -{ident} { BEGIN(INITIAL); } -(.|\n) { yyless(0); BEGIN(INITIAL); } - -[ \n\t\r] { } - -\xef\xbb\xbf { - // UTF-8 byte order mark (BOM), ignore if in line 1, error otherwise - if (yyget_lineno() != 1) { - return -1; - } -} - -\/\/(\/|\!) { BEGIN(doc_line); yymore(); } -\n { BEGIN(INITIAL); - yyleng--; - yytext[yyleng] = 0; - return ((yytext[2] == '!') ? INNER_DOC_COMMENT : OUTER_DOC_COMMENT); - } -[^\n]* { yymore(); } - -\/\/|\/\/\/\/ { BEGIN(linecomment); } -\n { BEGIN(INITIAL); } -[^\n]* { } - -\/\*(\*|\!)[^*] { yy_push_state(INITIAL); yy_push_state(doc_block); yymore(); } -\/\* { yy_push_state(doc_block); yymore(); } -\*\/ { - yy_pop_state(); - if (yy_top_state() == doc_block) { - yymore(); - } else { - return ((yytext[2] == '!') ? INNER_DOC_COMMENT : OUTER_DOC_COMMENT); - } -} -(.|\n) { yymore(); } - -\/\* { yy_push_state(blockcomment); } -\/\* { yy_push_state(blockcomment); } -\*\/ { yy_pop_state(); } -(.|\n) { } - -_ { return UNDERSCORE; } -abstract { return ABSTRACT; } -alignof { return ALIGNOF; } -as { return AS; } -become { return BECOME; } -box { return BOX; } -break { return BREAK; } -catch { return CATCH; } -const { return CONST; } -continue { return CONTINUE; } -crate { return CRATE; } -default { return DEFAULT; } -do { return DO; } -else { return ELSE; } -enum { return ENUM; } -extern { return EXTERN; } -false { return FALSE; } -final { return FINAL; } -fn { return FN; } -for { return FOR; } -if { return IF; } -impl { return IMPL; } -in { return IN; } -let { return LET; } -loop { return LOOP; } -macro { return MACRO; } -match { return MATCH; } -mod { return MOD; } -move { return MOVE; } -mut { return MUT; } -offsetof { return OFFSETOF; } -override { return OVERRIDE; } -priv { return PRIV; } -proc { return PROC; } -pure { return PURE; } -pub { return PUB; } -ref { return REF; } -return { return RETURN; } -self { return SELF; } -sizeof { return SIZEOF; } -static { return STATIC; } -struct { return STRUCT; } -super { return SUPER; } -trait { return TRAIT; } -true { return TRUE; } -type { return TYPE; } -typeof { return TYPEOF; } -union { return UNION; } -unsafe { return UNSAFE; } -unsized { return UNSIZED; } -use { return USE; } -virtual { return VIRTUAL; } -where { return WHERE; } -while { return WHILE; } -yield { return YIELD; } - -{ident} { return IDENT; } - -0x[0-9a-fA-F_]+ { BEGIN(suffix); return LIT_INTEGER; } -0o[0-7_]+ { BEGIN(suffix); return LIT_INTEGER; } -0b[01_]+ { BEGIN(suffix); return LIT_INTEGER; } -[0-9][0-9_]* { BEGIN(suffix); return LIT_INTEGER; } -[0-9][0-9_]*\.(\.|[a-zA-Z]) { yyless(yyleng - 2); BEGIN(suffix); return LIT_INTEGER; } - -[0-9][0-9_]*\.[0-9_]*([eE][-\+]?[0-9_]+)? { BEGIN(suffix); return LIT_FLOAT; } -[0-9][0-9_]*(\.[0-9_]*)?[eE][-\+]?[0-9_]+ { BEGIN(suffix); return LIT_FLOAT; } - -; { return ';'; } -, { return ','; } -\.\.\. { return DOTDOTDOT; } -\.\. { return DOTDOT; } -\. { return '.'; } -\( { return '('; } -\) { return ')'; } -\{ { return '{'; } -\} { return '}'; } -\[ { return '['; } -\] { return ']'; } -@ { return '@'; } -# { BEGIN(pound); yymore(); } -\! { BEGIN(shebang_or_attr); yymore(); } -\[ { - BEGIN(INITIAL); - yyless(2); - return SHEBANG; -} -[^\[\n]*\n { - // Since the \n was eaten as part of the token, yylineno will have - // been incremented to the value 2 if the shebang was on the first - // line. This yyless undoes that, setting yylineno back to 1. - yyless(yyleng - 1); - if (yyget_lineno() == 1) { - BEGIN(INITIAL); - return SHEBANG_LINE; - } else { - BEGIN(INITIAL); - yyless(2); - return SHEBANG; - } -} -. { BEGIN(INITIAL); yyless(1); return '#'; } - -\~ { return '~'; } -:: { return MOD_SEP; } -: { return ':'; } -\$ { return '$'; } -\? { return '?'; } - -== { return EQEQ; } -=> { return FAT_ARROW; } -= { return '='; } -\!= { return NE; } -\! { return '!'; } -\<= { return LE; } -\<\< { return SHL; } -\<\<= { return SHLEQ; } -\< { return '<'; } -\>= { return GE; } -\>\> { return SHR; } -\>\>= { return SHREQ; } -\> { return '>'; } - -\x27 { BEGIN(ltorchar); yymore(); } -static { BEGIN(INITIAL); return STATIC_LIFETIME; } -{ident} { BEGIN(INITIAL); return LIFETIME; } -\\[nrt\\\x27\x220]\x27 { BEGIN(suffix); return LIT_CHAR; } -\\x[0-9a-fA-F]{2}\x27 { BEGIN(suffix); return LIT_CHAR; } -\\u\{([0-9a-fA-F]_*){1,6}\}\x27 { BEGIN(suffix); return LIT_CHAR; } -.\x27 { BEGIN(suffix); return LIT_CHAR; } -[\x80-\xff]{2,4}\x27 { BEGIN(suffix); return LIT_CHAR; } -<> { BEGIN(INITIAL); return -1; } - -b\x22 { BEGIN(bytestr); yymore(); } -\x22 { BEGIN(suffix); return LIT_BYTE_STR; } - -<> { return -1; } -\\[n\nrt\\\x27\x220] { yymore(); } -\\x[0-9a-fA-F]{2} { yymore(); } -\\u\{([0-9a-fA-F]_*){1,6}\} { yymore(); } -\\[^n\nrt\\\x27\x220] { return -1; } -(.|\n) { yymore(); } - -br\x22 { BEGIN(rawbytestr_nohash); yymore(); } -\x22 { BEGIN(suffix); return LIT_BYTE_STR_RAW; } -(.|\n) { yymore(); } -<> { return -1; } - -br/# { - BEGIN(rawbytestr); - yymore(); - num_hashes = 0; - saw_non_hash = 0; - end_hashes = 0; -} -# { - if (!saw_non_hash) { - num_hashes++; - } else if (end_hashes != 0) { - end_hashes++; - if (end_hashes == num_hashes) { - BEGIN(INITIAL); - return LIT_BYTE_STR_RAW; - } - } - yymore(); -} -\x22# { - end_hashes = 1; - if (end_hashes == num_hashes) { - BEGIN(INITIAL); - return LIT_BYTE_STR_RAW; - } - yymore(); -} -(.|\n) { - if (!saw_non_hash) { - saw_non_hash = 1; - } - if (end_hashes != 0) { - end_hashes = 0; - } - yymore(); -} -<> { return -1; } - -b\x27 { BEGIN(byte); yymore(); } -\\[nrt\\\x27\x220]\x27 { BEGIN(INITIAL); return LIT_BYTE; } -\\x[0-9a-fA-F]{2}\x27 { BEGIN(INITIAL); return LIT_BYTE; } -\\u([0-9a-fA-F]_*){4}\x27 { BEGIN(INITIAL); return LIT_BYTE; } -\\U([0-9a-fA-F]_*){8}\x27 { BEGIN(INITIAL); return LIT_BYTE; } -.\x27 { BEGIN(INITIAL); return LIT_BYTE; } -<> { BEGIN(INITIAL); return -1; } - -r\x22 { BEGIN(rawstr); yymore(); } -\x22 { BEGIN(suffix); return LIT_STR_RAW; } -(.|\n) { yymore(); } -<> { return -1; } - -r/# { - BEGIN(rawstr_esc_begin); - yymore(); - num_hashes = 0; - saw_non_hash = 0; - end_hashes = 0; -} - -# { - num_hashes++; - yymore(); -} -\x22 { - BEGIN(rawstr_esc_body); - yymore(); -} -(.|\n) { return -1; } - -\x22/# { - BEGIN(rawstr_esc_end); - yymore(); - } -(.|\n) { - yymore(); - } - -# { - end_hashes++; - if (end_hashes == num_hashes) { - BEGIN(INITIAL); - return LIT_STR_RAW; - } - yymore(); - } -[^#] { - end_hashes = 0; - BEGIN(rawstr_esc_body); - yymore(); - } - -<> { return -1; } - -\x22 { BEGIN(str); yymore(); } -\x22 { BEGIN(suffix); return LIT_STR; } - -<> { return -1; } -\\[n\nr\rt\\\x27\x220] { yymore(); } -\\x[0-9a-fA-F]{2} { yymore(); } -\\u\{([0-9a-fA-F]_*){1,6}\} { yymore(); } -\\[^n\nrt\\\x27\x220] { return -1; } -(.|\n) { yymore(); } - -\<- { return LARROW; } --\> { return RARROW; } -- { return '-'; } --= { return MINUSEQ; } -&& { return ANDAND; } -& { return '&'; } -&= { return ANDEQ; } -\|\| { return OROR; } -\| { return '|'; } -\|= { return OREQ; } -\+ { return '+'; } -\+= { return PLUSEQ; } -\* { return '*'; } -\*= { return STAREQ; } -\/ { return '/'; } -\/= { return SLASHEQ; } -\^ { return '^'; } -\^= { return CARETEQ; } -% { return '%'; } -%= { return PERCENTEQ; } - -<> { return 0; } - -%% diff --git a/src/grammar/parser-lalr-main.c b/src/grammar/parser-lalr-main.c deleted file mode 100644 index 6348190cc140b..0000000000000 --- a/src/grammar/parser-lalr-main.c +++ /dev/null @@ -1,193 +0,0 @@ -#include -#include -#include -#include - -extern int yylex(); -extern int rsparse(); - -#define PUSHBACK_LEN 4 - -static char pushback[PUSHBACK_LEN]; -static int verbose; - -void print(const char* format, ...) { - va_list args; - va_start(args, format); - if (verbose) { - vprintf(format, args); - } - va_end(args); -} - -// If there is a non-null char at the head of the pushback queue, -// dequeue it and shift the rest of the queue forwards. Otherwise, -// return the token from calling yylex. -int rslex() { - if (pushback[0] == '\0') { - return yylex(); - } else { - char c = pushback[0]; - memmove(pushback, pushback + 1, PUSHBACK_LEN - 1); - pushback[PUSHBACK_LEN - 1] = '\0'; - return c; - } -} - -// Note: this does nothing if the pushback queue is full. As long as -// there aren't more than PUSHBACK_LEN consecutive calls to push_back -// in an action, this shouldn't be a problem. -void push_back(char c) { - for (int i = 0; i < PUSHBACK_LEN; ++i) { - if (pushback[i] == '\0') { - pushback[i] = c; - break; - } - } -} - -extern int rsdebug; - -struct node { - struct node *next; - struct node *prev; - int own_string; - char const *name; - int n_elems; - struct node *elems[]; -}; - -struct node *nodes = NULL; -int n_nodes; - -struct node *mk_node(char const *name, int n, ...) { - va_list ap; - int i = 0; - unsigned sz = sizeof(struct node) + (n * sizeof(struct node *)); - struct node *nn, *nd = (struct node *)malloc(sz); - - print("# New %d-ary node: %s = %p\n", n, name, nd); - - nd->own_string = 0; - nd->prev = NULL; - nd->next = nodes; - if (nodes) { - nodes->prev = nd; - } - nodes = nd; - - nd->name = name; - nd->n_elems = n; - - va_start(ap, n); - while (i < n) { - nn = va_arg(ap, struct node *); - print("# arg[%d]: %p\n", i, nn); - print("# (%s ...)\n", nn->name); - nd->elems[i++] = nn; - } - va_end(ap); - n_nodes++; - return nd; -} - -struct node *mk_atom(char *name) { - struct node *nd = mk_node((char const *)strdup(name), 0); - nd->own_string = 1; - return nd; -} - -struct node *mk_none() { - return mk_atom(""); -} - -struct node *ext_node(struct node *nd, int n, ...) { - va_list ap; - int i = 0, c = nd->n_elems + n; - unsigned sz = sizeof(struct node) + (c * sizeof(struct node *)); - struct node *nn; - - print("# Extending %d-ary node by %d nodes: %s = %p", - nd->n_elems, c, nd->name, nd); - - if (nd->next) { - nd->next->prev = nd->prev; - } - if (nd->prev) { - nd->prev->next = nd->next; - } - nd = realloc(nd, sz); - nd->prev = NULL; - nd->next = nodes; - nodes->prev = nd; - nodes = nd; - - print(" ==> %p\n", nd); - - va_start(ap, n); - while (i < n) { - nn = va_arg(ap, struct node *); - print("# arg[%d]: %p\n", i, nn); - print("# (%s ...)\n", nn->name); - nd->elems[nd->n_elems++] = nn; - ++i; - } - va_end(ap); - return nd; -} - -int const indent_step = 4; - -void print_indent(int depth) { - while (depth) { - if (depth-- % indent_step == 0) { - print("|"); - } else { - print(" "); - } - } -} - -void print_node(struct node *n, int depth) { - int i = 0; - print_indent(depth); - if (n->n_elems == 0) { - print("%s\n", n->name); - } else { - print("(%s\n", n->name); - for (i = 0; i < n->n_elems; ++i) { - print_node(n->elems[i], depth + indent_step); - } - print_indent(depth); - print(")\n"); - } -} - -int main(int argc, char **argv) { - if (argc == 2 && strcmp(argv[1], "-v") == 0) { - verbose = 1; - } else { - verbose = 0; - } - int ret = 0; - struct node *tmp; - memset(pushback, '\0', PUSHBACK_LEN); - ret = rsparse(); - print("--- PARSE COMPLETE: ret:%d, n_nodes:%d ---\n", ret, n_nodes); - if (nodes) { - print_node(nodes, 0); - } - while (nodes) { - tmp = nodes; - nodes = tmp->next; - if (tmp->own_string) { - free((void*)tmp->name); - } - free(tmp); - } - return ret; -} - -void rserror(char const *s) { - fprintf(stderr, "%s\n", s); -} diff --git a/src/grammar/parser-lalr.y b/src/grammar/parser-lalr.y deleted file mode 100644 index 5585c95a5a63a..0000000000000 --- a/src/grammar/parser-lalr.y +++ /dev/null @@ -1,1982 +0,0 @@ -%{ -#define YYERROR_VERBOSE -#define YYSTYPE struct node * -struct node; -extern int yylex(); -extern void yyerror(char const *s); -extern struct node *mk_node(char const *name, int n, ...); -extern struct node *mk_atom(char *text); -extern struct node *mk_none(); -extern struct node *ext_node(struct node *nd, int n, ...); -extern void push_back(char c); -extern char *yytext; -%} -%debug - -%token SHL -%token SHR -%token LE -%token EQEQ -%token NE -%token GE -%token ANDAND -%token OROR -%token SHLEQ -%token SHREQ -%token MINUSEQ -%token ANDEQ -%token OREQ -%token PLUSEQ -%token STAREQ -%token SLASHEQ -%token CARETEQ -%token PERCENTEQ -%token DOTDOT -%token DOTDOTDOT -%token MOD_SEP -%token RARROW -%token LARROW -%token FAT_ARROW -%token LIT_BYTE -%token LIT_CHAR -%token LIT_INTEGER -%token LIT_FLOAT -%token LIT_STR -%token LIT_STR_RAW -%token LIT_BYTE_STR -%token LIT_BYTE_STR_RAW -%token IDENT -%token UNDERSCORE -%token LIFETIME - -// keywords -%token SELF -%token STATIC -%token ABSTRACT -%token ALIGNOF -%token AS -%token BECOME -%token BREAK -%token CATCH -%token CRATE -%token DO -%token ELSE -%token ENUM -%token EXTERN -%token FALSE -%token FINAL -%token FN -%token FOR -%token IF -%token IMPL -%token IN -%token LET -%token LOOP -%token MACRO -%token MATCH -%token MOD -%token MOVE -%token MUT -%token OFFSETOF -%token OVERRIDE -%token PRIV -%token PUB -%token PURE -%token REF -%token RETURN -%token SIZEOF -%token STRUCT -%token SUPER -%token UNION -%token UNSIZED -%token TRUE -%token TRAIT -%token TYPE -%token UNSAFE -%token VIRTUAL -%token YIELD -%token DEFAULT -%token USE -%token WHILE -%token CONTINUE -%token PROC -%token BOX -%token CONST -%token WHERE -%token TYPEOF -%token INNER_DOC_COMMENT -%token OUTER_DOC_COMMENT - -%token SHEBANG -%token SHEBANG_LINE -%token STATIC_LIFETIME - - /* - Quoting from the Bison manual: - - "Finally, the resolution of conflicts works by comparing the precedence - of the rule being considered with that of the lookahead token. If the - token's precedence is higher, the choice is to shift. If the rule's - precedence is higher, the choice is to reduce. If they have equal - precedence, the choice is made based on the associativity of that - precedence level. The verbose output file made by ‘-v’ (see Invoking - Bison) says how each conflict was resolved" - */ - -// We expect no shift/reduce or reduce/reduce conflicts in this grammar; -// all potential ambiguities are scrutinized and eliminated manually. -%expect 0 - -// fake-precedence symbol to cause '|' bars in lambda context to parse -// at low precedence, permit things like |x| foo = bar, where '=' is -// otherwise lower-precedence than '|'. Also used for proc() to cause -// things like proc() a + b to parse as proc() { a + b }. -%precedence LAMBDA - -%precedence SELF - -// MUT should be lower precedence than IDENT so that in the pat rule, -// "& MUT pat" has higher precedence than "binding_mode ident [@ pat]" -%precedence MUT - -// IDENT needs to be lower than '{' so that 'foo {' is shifted when -// trying to decide if we've got a struct-construction expr (esp. in -// contexts like 'if foo { .') -// -// IDENT also needs to be lower precedence than '<' so that '<' in -// 'foo:bar . <' is shifted (in a trait reference occurring in a -// bounds list), parsing as foo:(bar) rather than (foo:bar). -%precedence IDENT - // Put the weak keywords that can be used as idents here as well -%precedence CATCH -%precedence DEFAULT -%precedence UNION - -// A couple fake-precedence symbols to use in rules associated with + -// and < in trailing type contexts. These come up when you have a type -// in the RHS of operator-AS, such as "foo as bar". The "<" there -// has to be shifted so the parser keeps trying to parse a type, even -// though it might well consider reducing the type "bar" and then -// going on to "<" as a subsequent binop. The "+" case is with -// trailing type-bounds ("foo as bar:A+B"), for the same reason. -%precedence SHIFTPLUS - -%precedence MOD_SEP -%precedence RARROW ':' - -// In where clauses, "for" should have greater precedence when used as -// a higher ranked constraint than when used as the beginning of a -// for_in_type (which is a ty) -%precedence FORTYPE -%precedence FOR - -// Binops & unops, and their precedences -%precedence '?' -%precedence BOX -%nonassoc DOTDOT - -// RETURN needs to be lower-precedence than tokens that start -// prefix_exprs -%precedence RETURN YIELD - -%right '=' SHLEQ SHREQ MINUSEQ ANDEQ OREQ PLUSEQ STAREQ SLASHEQ CARETEQ PERCENTEQ -%right LARROW -%left OROR -%left ANDAND -%left EQEQ NE -%left '<' '>' LE GE -%left '|' -%left '^' -%left '&' -%left SHL SHR -%left '+' '-' -%precedence AS -%left '*' '/' '%' -%precedence '!' - -%precedence '{' '[' '(' '.' - -%precedence RANGE - -%start crate - -%% - -//////////////////////////////////////////////////////////////////////// -// Part 1: Items and attributes -//////////////////////////////////////////////////////////////////////// - -crate -: maybe_shebang inner_attrs maybe_mod_items { mk_node("crate", 2, $2, $3); } -| maybe_shebang maybe_mod_items { mk_node("crate", 1, $2); } -; - -maybe_shebang -: SHEBANG_LINE -| %empty -; - -maybe_inner_attrs -: inner_attrs -| %empty { $$ = mk_none(); } -; - -inner_attrs -: inner_attr { $$ = mk_node("InnerAttrs", 1, $1); } -| inner_attrs inner_attr { $$ = ext_node($1, 1, $2); } -; - -inner_attr -: SHEBANG '[' meta_item ']' { $$ = mk_node("InnerAttr", 1, $3); } -| INNER_DOC_COMMENT { $$ = mk_node("InnerAttr", 1, mk_node("doc-comment", 1, mk_atom(yytext))); } -; - -maybe_outer_attrs -: outer_attrs -| %empty { $$ = mk_none(); } -; - -outer_attrs -: outer_attr { $$ = mk_node("OuterAttrs", 1, $1); } -| outer_attrs outer_attr { $$ = ext_node($1, 1, $2); } -; - -outer_attr -: '#' '[' meta_item ']' { $$ = $3; } -| OUTER_DOC_COMMENT { $$ = mk_node("doc-comment", 1, mk_atom(yytext)); } -; - -meta_item -: ident { $$ = mk_node("MetaWord", 1, $1); } -| ident '=' lit { $$ = mk_node("MetaNameValue", 2, $1, $3); } -| ident '(' meta_seq ')' { $$ = mk_node("MetaList", 2, $1, $3); } -| ident '(' meta_seq ',' ')' { $$ = mk_node("MetaList", 2, $1, $3); } -; - -meta_seq -: %empty { $$ = mk_none(); } -| meta_item { $$ = mk_node("MetaItems", 1, $1); } -| meta_seq ',' meta_item { $$ = ext_node($1, 1, $3); } -; - -maybe_mod_items -: mod_items -| %empty { $$ = mk_none(); } -; - -mod_items -: mod_item { $$ = mk_node("Items", 1, $1); } -| mod_items mod_item { $$ = ext_node($1, 1, $2); } -; - -attrs_and_vis -: maybe_outer_attrs visibility { $$ = mk_node("AttrsAndVis", 2, $1, $2); } -; - -mod_item -: attrs_and_vis item { $$ = mk_node("Item", 2, $1, $2); } -; - -// items that can appear outside of a fn block -item -: stmt_item -| item_macro -; - -// items that can appear in "stmts" -stmt_item -: item_static -| item_const -| item_type -| block_item -| view_item -; - -item_static -: STATIC ident ':' ty '=' expr ';' { $$ = mk_node("ItemStatic", 3, $2, $4, $6); } -| STATIC MUT ident ':' ty '=' expr ';' { $$ = mk_node("ItemStatic", 3, $3, $5, $7); } -; - -item_const -: CONST ident ':' ty '=' expr ';' { $$ = mk_node("ItemConst", 3, $2, $4, $6); } -; - -item_macro -: path_expr '!' maybe_ident parens_delimited_token_trees ';' { $$ = mk_node("ItemMacro", 3, $1, $3, $4); } -| path_expr '!' maybe_ident braces_delimited_token_trees { $$ = mk_node("ItemMacro", 3, $1, $3, $4); } -| path_expr '!' maybe_ident brackets_delimited_token_trees ';'{ $$ = mk_node("ItemMacro", 3, $1, $3, $4); } -; - -view_item -: use_item -| extern_fn_item -| EXTERN CRATE ident ';' { $$ = mk_node("ViewItemExternCrate", 1, $3); } -| EXTERN CRATE ident AS ident ';' { $$ = mk_node("ViewItemExternCrate", 2, $3, $5); } -; - -extern_fn_item -: EXTERN maybe_abi item_fn { $$ = mk_node("ViewItemExternFn", 2, $2, $3); } -; - -use_item -: USE view_path ';' { $$ = mk_node("ViewItemUse", 1, $2); } -; - -view_path -: path_no_types_allowed { $$ = mk_node("ViewPathSimple", 1, $1); } -| path_no_types_allowed MOD_SEP '{' '}' { $$ = mk_node("ViewPathList", 2, $1, mk_atom("ViewPathListEmpty")); } -| MOD_SEP '{' '}' { $$ = mk_node("ViewPathList", 1, mk_atom("ViewPathListEmpty")); } -| path_no_types_allowed MOD_SEP '{' idents_or_self '}' { $$ = mk_node("ViewPathList", 2, $1, $4); } -| MOD_SEP '{' idents_or_self '}' { $$ = mk_node("ViewPathList", 1, $3); } -| path_no_types_allowed MOD_SEP '{' idents_or_self ',' '}' { $$ = mk_node("ViewPathList", 2, $1, $4); } -| MOD_SEP '{' idents_or_self ',' '}' { $$ = mk_node("ViewPathList", 1, $3); } -| path_no_types_allowed MOD_SEP '*' { $$ = mk_node("ViewPathGlob", 1, $1); } -| MOD_SEP '*' { $$ = mk_atom("ViewPathGlob"); } -| '*' { $$ = mk_atom("ViewPathGlob"); } -| '{' '}' { $$ = mk_atom("ViewPathListEmpty"); } -| '{' idents_or_self '}' { $$ = mk_node("ViewPathList", 1, $2); } -| '{' idents_or_self ',' '}' { $$ = mk_node("ViewPathList", 1, $2); } -| path_no_types_allowed AS ident { $$ = mk_node("ViewPathSimple", 2, $1, $3); } -; - -block_item -: item_fn -| item_unsafe_fn -| item_mod -| item_foreign_mod { $$ = mk_node("ItemForeignMod", 1, $1); } -| item_struct -| item_enum -| item_union -| item_trait -| item_impl -; - -maybe_ty_ascription -: ':' ty_sum { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -maybe_init_expr -: '=' expr { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -// structs -item_struct -: STRUCT ident generic_params maybe_where_clause struct_decl_args -{ - $$ = mk_node("ItemStruct", 4, $2, $3, $4, $5); -} -| STRUCT ident generic_params struct_tuple_args maybe_where_clause ';' -{ - $$ = mk_node("ItemStruct", 4, $2, $3, $4, $5); -} -| STRUCT ident generic_params maybe_where_clause ';' -{ - $$ = mk_node("ItemStruct", 3, $2, $3, $4); -} -; - -struct_decl_args -: '{' struct_decl_fields '}' { $$ = $2; } -| '{' struct_decl_fields ',' '}' { $$ = $2; } -; - -struct_tuple_args -: '(' struct_tuple_fields ')' { $$ = $2; } -| '(' struct_tuple_fields ',' ')' { $$ = $2; } -; - -struct_decl_fields -: struct_decl_field { $$ = mk_node("StructFields", 1, $1); } -| struct_decl_fields ',' struct_decl_field { $$ = ext_node($1, 1, $3); } -| %empty { $$ = mk_none(); } -; - -struct_decl_field -: attrs_and_vis ident ':' ty_sum { $$ = mk_node("StructField", 3, $1, $2, $4); } -; - -struct_tuple_fields -: struct_tuple_field { $$ = mk_node("StructFields", 1, $1); } -| struct_tuple_fields ',' struct_tuple_field { $$ = ext_node($1, 1, $3); } -| %empty { $$ = mk_none(); } -; - -struct_tuple_field -: attrs_and_vis ty_sum { $$ = mk_node("StructField", 2, $1, $2); } -; - -// enums -item_enum -: ENUM ident generic_params maybe_where_clause '{' enum_defs '}' { $$ = mk_node("ItemEnum", 0); } -| ENUM ident generic_params maybe_where_clause '{' enum_defs ',' '}' { $$ = mk_node("ItemEnum", 0); } -; - -enum_defs -: enum_def { $$ = mk_node("EnumDefs", 1, $1); } -| enum_defs ',' enum_def { $$ = ext_node($1, 1, $3); } -| %empty { $$ = mk_none(); } -; - -enum_def -: attrs_and_vis ident enum_args { $$ = mk_node("EnumDef", 3, $1, $2, $3); } -; - -enum_args -: '{' struct_decl_fields '}' { $$ = mk_node("EnumArgs", 1, $2); } -| '{' struct_decl_fields ',' '}' { $$ = mk_node("EnumArgs", 1, $2); } -| '(' maybe_ty_sums ')' { $$ = mk_node("EnumArgs", 1, $2); } -| '=' expr { $$ = mk_node("EnumArgs", 1, $2); } -| %empty { $$ = mk_none(); } -; - -// unions -item_union -: UNION ident generic_params maybe_where_clause '{' struct_decl_fields '}' { $$ = mk_node("ItemUnion", 0); } -| UNION ident generic_params maybe_where_clause '{' struct_decl_fields ',' '}' { $$ = mk_node("ItemUnion", 0); } - -item_mod -: MOD ident ';' { $$ = mk_node("ItemMod", 1, $2); } -| MOD ident '{' maybe_mod_items '}' { $$ = mk_node("ItemMod", 2, $2, $4); } -| MOD ident '{' inner_attrs maybe_mod_items '}' { $$ = mk_node("ItemMod", 3, $2, $4, $5); } -; - -item_foreign_mod -: EXTERN maybe_abi '{' maybe_foreign_items '}' { $$ = mk_node("ItemForeignMod", 1, $4); } -| EXTERN maybe_abi '{' inner_attrs maybe_foreign_items '}' { $$ = mk_node("ItemForeignMod", 2, $4, $5); } -; - -maybe_abi -: str -| %empty { $$ = mk_none(); } -; - -maybe_foreign_items -: foreign_items -| %empty { $$ = mk_none(); } -; - -foreign_items -: foreign_item { $$ = mk_node("ForeignItems", 1, $1); } -| foreign_items foreign_item { $$ = ext_node($1, 1, $2); } -; - -foreign_item -: attrs_and_vis STATIC item_foreign_static { $$ = mk_node("ForeignItem", 2, $1, $3); } -| attrs_and_vis item_foreign_fn { $$ = mk_node("ForeignItem", 2, $1, $2); } -| attrs_and_vis UNSAFE item_foreign_fn { $$ = mk_node("ForeignItem", 2, $1, $3); } -; - -item_foreign_static -: maybe_mut ident ':' ty ';' { $$ = mk_node("StaticItem", 3, $1, $2, $4); } -; - -item_foreign_fn -: FN ident generic_params fn_decl_allow_variadic maybe_where_clause ';' { $$ = mk_node("ForeignFn", 4, $2, $3, $4, $5); } -; - -fn_decl_allow_variadic -: fn_params_allow_variadic ret_ty { $$ = mk_node("FnDecl", 2, $1, $2); } -; - -fn_params_allow_variadic -: '(' ')' { $$ = mk_none(); } -| '(' params ')' { $$ = $2; } -| '(' params ',' ')' { $$ = $2; } -| '(' params ',' DOTDOTDOT ')' { $$ = $2; } -; - -visibility -: PUB { $$ = mk_atom("Public"); } -| %empty { $$ = mk_atom("Inherited"); } -; - -idents_or_self -: ident_or_self { $$ = mk_node("IdentsOrSelf", 1, $1); } -| idents_or_self AS ident { $$ = mk_node("IdentsOrSelf", 2, $1, $3); } -| idents_or_self ',' ident_or_self { $$ = ext_node($1, 1, $3); } -; - -ident_or_self -: ident -| SELF { $$ = mk_atom(yytext); } -; - -item_type -: TYPE ident generic_params maybe_where_clause '=' ty_sum ';' { $$ = mk_node("ItemTy", 4, $2, $3, $4, $6); } -; - -for_sized -: FOR '?' ident { $$ = mk_node("ForSized", 1, $3); } -| FOR ident '?' { $$ = mk_node("ForSized", 1, $2); } -| %empty { $$ = mk_none(); } -; - -item_trait -: maybe_unsafe TRAIT ident generic_params for_sized maybe_ty_param_bounds maybe_where_clause '{' maybe_trait_items '}' -{ - $$ = mk_node("ItemTrait", 7, $1, $3, $4, $5, $6, $7, $9); -} -; - -maybe_trait_items -: trait_items -| %empty { $$ = mk_none(); } -; - -trait_items -: trait_item { $$ = mk_node("TraitItems", 1, $1); } -| trait_items trait_item { $$ = ext_node($1, 1, $2); } -; - -trait_item -: trait_const -| trait_type -| trait_method -| maybe_outer_attrs item_macro { $$ = mk_node("TraitMacroItem", 2, $1, $2); } -; - -trait_const -: maybe_outer_attrs CONST ident maybe_ty_ascription maybe_const_default ';' { $$ = mk_node("ConstTraitItem", 4, $1, $3, $4, $5); } -; - -maybe_const_default -: '=' expr { $$ = mk_node("ConstDefault", 1, $2); } -| %empty { $$ = mk_none(); } -; - -trait_type -: maybe_outer_attrs TYPE ty_param ';' { $$ = mk_node("TypeTraitItem", 2, $1, $3); } -; - -maybe_unsafe -: UNSAFE { $$ = mk_atom("Unsafe"); } -| %empty { $$ = mk_none(); } -; - -maybe_default_maybe_unsafe -: DEFAULT UNSAFE { $$ = mk_atom("DefaultUnsafe"); } -| DEFAULT { $$ = mk_atom("Default"); } -| UNSAFE { $$ = mk_atom("Unsafe"); } -| %empty { $$ = mk_none(); } - -trait_method -: type_method { $$ = mk_node("Required", 1, $1); } -| method { $$ = mk_node("Provided", 1, $1); } -; - -type_method -: maybe_outer_attrs maybe_unsafe FN ident generic_params fn_decl_with_self_allow_anon_params maybe_where_clause ';' -{ - $$ = mk_node("TypeMethod", 6, $1, $2, $4, $5, $6, $7); -} -| maybe_outer_attrs CONST maybe_unsafe FN ident generic_params fn_decl_with_self_allow_anon_params maybe_where_clause ';' -{ - $$ = mk_node("TypeMethod", 6, $1, $3, $5, $6, $7, $8); -} -| maybe_outer_attrs maybe_unsafe EXTERN maybe_abi FN ident generic_params fn_decl_with_self_allow_anon_params maybe_where_clause ';' -{ - $$ = mk_node("TypeMethod", 7, $1, $2, $4, $6, $7, $8, $9); -} -; - -method -: maybe_outer_attrs maybe_unsafe FN ident generic_params fn_decl_with_self_allow_anon_params maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("Method", 7, $1, $2, $4, $5, $6, $7, $8); -} -| maybe_outer_attrs CONST maybe_unsafe FN ident generic_params fn_decl_with_self_allow_anon_params maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("Method", 7, $1, $3, $5, $6, $7, $8, $9); -} -| maybe_outer_attrs maybe_unsafe EXTERN maybe_abi FN ident generic_params fn_decl_with_self_allow_anon_params maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("Method", 8, $1, $2, $4, $6, $7, $8, $9, $10); -} -; - -impl_method -: attrs_and_vis maybe_default maybe_unsafe FN ident generic_params fn_decl_with_self maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("Method", 8, $1, $2, $3, $5, $6, $7, $8, $9); -} -| attrs_and_vis maybe_default CONST maybe_unsafe FN ident generic_params fn_decl_with_self maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("Method", 8, $1, $2, $4, $6, $7, $8, $9, $10); -} -| attrs_and_vis maybe_default maybe_unsafe EXTERN maybe_abi FN ident generic_params fn_decl_with_self maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("Method", 9, $1, $2, $3, $5, $7, $8, $9, $10, $11); -} -; - -// There are two forms of impl: -// -// impl (<...>)? TY { ... } -// impl (<...>)? TRAIT for TY { ... } -// -// Unfortunately since TY can begin with '<' itself -- as part of a -// TyQualifiedPath type -- there's an s/r conflict when we see '<' after IMPL: -// should we reduce one of the early rules of TY (such as maybe_once) -// or shall we continue shifting into the generic_params list for the -// impl? -// -// The production parser disambiguates a different case here by -// permitting / requiring the user to provide parens around types when -// they are ambiguous with traits. We do the same here, regrettably, -// by splitting ty into ty and ty_prim. -item_impl -: maybe_default_maybe_unsafe IMPL generic_params ty_prim_sum maybe_where_clause '{' maybe_inner_attrs maybe_impl_items '}' -{ - $$ = mk_node("ItemImpl", 6, $1, $3, $4, $5, $7, $8); -} -| maybe_default_maybe_unsafe IMPL generic_params '(' ty ')' maybe_where_clause '{' maybe_inner_attrs maybe_impl_items '}' -{ - $$ = mk_node("ItemImpl", 6, $1, $3, 5, $6, $9, $10); -} -| maybe_default_maybe_unsafe IMPL generic_params trait_ref FOR ty_sum maybe_where_clause '{' maybe_inner_attrs maybe_impl_items '}' -{ - $$ = mk_node("ItemImpl", 6, $3, $4, $6, $7, $9, $10); -} -| maybe_default_maybe_unsafe IMPL generic_params '!' trait_ref FOR ty_sum maybe_where_clause '{' maybe_inner_attrs maybe_impl_items '}' -{ - $$ = mk_node("ItemImplNeg", 7, $1, $3, $5, $7, $8, $10, $11); -} -| maybe_default_maybe_unsafe IMPL generic_params trait_ref FOR DOTDOT '{' '}' -{ - $$ = mk_node("ItemImplDefault", 3, $1, $3, $4); -} -| maybe_default_maybe_unsafe IMPL generic_params '!' trait_ref FOR DOTDOT '{' '}' -{ - $$ = mk_node("ItemImplDefaultNeg", 3, $1, $3, $4); -} -; - -maybe_impl_items -: impl_items -| %empty { $$ = mk_none(); } -; - -impl_items -: impl_item { $$ = mk_node("ImplItems", 1, $1); } -| impl_item impl_items { $$ = ext_node($1, 1, $2); } -; - -impl_item -: impl_method -| attrs_and_vis item_macro { $$ = mk_node("ImplMacroItem", 2, $1, $2); } -| impl_const -| impl_type -; - -maybe_default -: DEFAULT { $$ = mk_atom("Default"); } -| %empty { $$ = mk_none(); } -; - -impl_const -: attrs_and_vis maybe_default item_const { $$ = mk_node("ImplConst", 3, $1, $2, $3); } -; - -impl_type -: attrs_and_vis maybe_default TYPE ident generic_params '=' ty_sum ';' { $$ = mk_node("ImplType", 5, $1, $2, $4, $5, $7); } -; - -item_fn -: FN ident generic_params fn_decl maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("ItemFn", 5, $2, $3, $4, $5, $6); -} -| CONST FN ident generic_params fn_decl maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("ItemFn", 5, $3, $4, $5, $6, $7); -} -; - -item_unsafe_fn -: UNSAFE FN ident generic_params fn_decl maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("ItemUnsafeFn", 5, $3, $4, $5, $6, $7); -} -| CONST UNSAFE FN ident generic_params fn_decl maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("ItemUnsafeFn", 5, $4, $5, $6, $7, $8); -} -| UNSAFE EXTERN maybe_abi FN ident generic_params fn_decl maybe_where_clause inner_attrs_and_block -{ - $$ = mk_node("ItemUnsafeFn", 6, $3, $5, $6, $7, $8, $9); -} -; - -fn_decl -: fn_params ret_ty { $$ = mk_node("FnDecl", 2, $1, $2); } -; - -fn_decl_with_self -: fn_params_with_self ret_ty { $$ = mk_node("FnDecl", 2, $1, $2); } -; - -fn_decl_with_self_allow_anon_params -: fn_anon_params_with_self ret_ty { $$ = mk_node("FnDecl", 2, $1, $2); } -; - -fn_params -: '(' maybe_params ')' { $$ = $2; } -; - -fn_anon_params -: '(' anon_param anon_params_allow_variadic_tail ')' { $$ = ext_node($2, 1, $3); } -| '(' ')' { $$ = mk_none(); } -; - -fn_params_with_self -: '(' maybe_mut SELF maybe_ty_ascription maybe_comma_params ')' { $$ = mk_node("SelfLower", 3, $2, $4, $5); } -| '(' '&' maybe_mut SELF maybe_ty_ascription maybe_comma_params ')' { $$ = mk_node("SelfRegion", 3, $3, $5, $6); } -| '(' '&' lifetime maybe_mut SELF maybe_ty_ascription maybe_comma_params ')' { $$ = mk_node("SelfRegion", 4, $3, $4, $6, $7); } -| '(' maybe_params ')' { $$ = mk_node("SelfStatic", 1, $2); } -; - -fn_anon_params_with_self -: '(' maybe_mut SELF maybe_ty_ascription maybe_comma_anon_params ')' { $$ = mk_node("SelfLower", 3, $2, $4, $5); } -| '(' '&' maybe_mut SELF maybe_ty_ascription maybe_comma_anon_params ')' { $$ = mk_node("SelfRegion", 3, $3, $5, $6); } -| '(' '&' lifetime maybe_mut SELF maybe_ty_ascription maybe_comma_anon_params ')' { $$ = mk_node("SelfRegion", 4, $3, $4, $6, $7); } -| '(' maybe_anon_params ')' { $$ = mk_node("SelfStatic", 1, $2); } -; - -maybe_params -: params -| params ',' -| %empty { $$ = mk_none(); } -; - -params -: param { $$ = mk_node("Args", 1, $1); } -| params ',' param { $$ = ext_node($1, 1, $3); } -; - -param -: pat ':' ty_sum { $$ = mk_node("Arg", 2, $1, $3); } -; - -inferrable_params -: inferrable_param { $$ = mk_node("InferrableParams", 1, $1); } -| inferrable_params ',' inferrable_param { $$ = ext_node($1, 1, $3); } -; - -inferrable_param -: pat maybe_ty_ascription { $$ = mk_node("InferrableParam", 2, $1, $2); } -; - -maybe_comma_params -: ',' { $$ = mk_none(); } -| ',' params { $$ = $2; } -| ',' params ',' { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -maybe_comma_anon_params -: ',' { $$ = mk_none(); } -| ',' anon_params { $$ = $2; } -| ',' anon_params ',' { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -maybe_anon_params -: anon_params -| anon_params ',' -| %empty { $$ = mk_none(); } -; - -anon_params -: anon_param { $$ = mk_node("Args", 1, $1); } -| anon_params ',' anon_param { $$ = ext_node($1, 1, $3); } -; - -// anon means it's allowed to be anonymous (type-only), but it can -// still have a name -anon_param -: named_arg ':' ty { $$ = mk_node("Arg", 2, $1, $3); } -| ty -; - -anon_params_allow_variadic_tail -: ',' DOTDOTDOT { $$ = mk_none(); } -| ',' anon_param anon_params_allow_variadic_tail { $$ = mk_node("Args", 2, $2, $3); } -| %empty { $$ = mk_none(); } -; - -named_arg -: ident -| UNDERSCORE { $$ = mk_atom("PatWild"); } -| '&' ident { $$ = $2; } -| '&' UNDERSCORE { $$ = mk_atom("PatWild"); } -| ANDAND ident { $$ = $2; } -| ANDAND UNDERSCORE { $$ = mk_atom("PatWild"); } -| MUT ident { $$ = $2; } -; - -ret_ty -: RARROW '!' { $$ = mk_none(); } -| RARROW ty { $$ = mk_node("ret-ty", 1, $2); } -| %prec IDENT %empty { $$ = mk_none(); } -; - -generic_params -: '<' '>' { $$ = mk_node("Generics", 2, mk_none(), mk_none()); } -| '<' lifetimes '>' { $$ = mk_node("Generics", 2, $2, mk_none()); } -| '<' lifetimes ',' '>' { $$ = mk_node("Generics", 2, $2, mk_none()); } -| '<' lifetimes SHR { push_back('>'); $$ = mk_node("Generics", 2, $2, mk_none()); } -| '<' lifetimes ',' SHR { push_back('>'); $$ = mk_node("Generics", 2, $2, mk_none()); } -| '<' lifetimes ',' ty_params '>' { $$ = mk_node("Generics", 2, $2, $4); } -| '<' lifetimes ',' ty_params ',' '>' { $$ = mk_node("Generics", 2, $2, $4); } -| '<' lifetimes ',' ty_params SHR { push_back('>'); $$ = mk_node("Generics", 2, $2, $4); } -| '<' lifetimes ',' ty_params ',' SHR { push_back('>'); $$ = mk_node("Generics", 2, $2, $4); } -| '<' ty_params '>' { $$ = mk_node("Generics", 2, mk_none(), $2); } -| '<' ty_params ',' '>' { $$ = mk_node("Generics", 2, mk_none(), $2); } -| '<' ty_params SHR { push_back('>'); $$ = mk_node("Generics", 2, mk_none(), $2); } -| '<' ty_params ',' SHR { push_back('>'); $$ = mk_node("Generics", 2, mk_none(), $2); } -| %empty { $$ = mk_none(); } -; - -maybe_where_clause -: %empty { $$ = mk_none(); } -| where_clause -; - -where_clause -: WHERE where_predicates { $$ = mk_node("WhereClause", 1, $2); } -| WHERE where_predicates ',' { $$ = mk_node("WhereClause", 1, $2); } -; - -where_predicates -: where_predicate { $$ = mk_node("WherePredicates", 1, $1); } -| where_predicates ',' where_predicate { $$ = ext_node($1, 1, $3); } -; - -where_predicate -: maybe_for_lifetimes lifetime ':' bounds { $$ = mk_node("WherePredicate", 3, $1, $2, $4); } -| maybe_for_lifetimes ty ':' ty_param_bounds { $$ = mk_node("WherePredicate", 3, $1, $2, $4); } -; - -maybe_for_lifetimes -: FOR '<' lifetimes '>' { $$ = mk_none(); } -| %prec FORTYPE %empty { $$ = mk_none(); } - -ty_params -: ty_param { $$ = mk_node("TyParams", 1, $1); } -| ty_params ',' ty_param { $$ = ext_node($1, 1, $3); } -; - -// A path with no type parameters; e.g. `foo::bar::Baz` -// -// These show up in 'use' view-items, because these are processed -// without respect to types. -path_no_types_allowed -: ident { $$ = mk_node("ViewPath", 1, $1); } -| MOD_SEP ident { $$ = mk_node("ViewPath", 1, $2); } -| SELF { $$ = mk_node("ViewPath", 1, mk_atom("Self")); } -| MOD_SEP SELF { $$ = mk_node("ViewPath", 1, mk_atom("Self")); } -| SUPER { $$ = mk_node("ViewPath", 1, mk_atom("Super")); } -| MOD_SEP SUPER { $$ = mk_node("ViewPath", 1, mk_atom("Super")); } -| path_no_types_allowed MOD_SEP ident { $$ = ext_node($1, 1, $3); } -; - -// A path with a lifetime and type parameters, with no double colons -// before the type parameters; e.g. `foo::bar<'a>::Baz` -// -// These show up in "trait references", the components of -// type-parameter bounds lists, as well as in the prefix of the -// path_generic_args_and_bounds rule, which is the full form of a -// named typed expression. -// -// They do not have (nor need) an extra '::' before '<' because -// unlike in expr context, there are no "less-than" type exprs to -// be ambiguous with. -path_generic_args_without_colons -: %prec IDENT - ident { $$ = mk_node("components", 1, $1); } -| %prec IDENT - ident generic_args { $$ = mk_node("components", 2, $1, $2); } -| %prec IDENT - ident '(' maybe_ty_sums ')' ret_ty { $$ = mk_node("components", 2, $1, $3); } -| %prec IDENT - path_generic_args_without_colons MOD_SEP ident { $$ = ext_node($1, 1, $3); } -| %prec IDENT - path_generic_args_without_colons MOD_SEP ident generic_args { $$ = ext_node($1, 2, $3, $4); } -| %prec IDENT - path_generic_args_without_colons MOD_SEP ident '(' maybe_ty_sums ')' ret_ty { $$ = ext_node($1, 2, $3, $5); } -; - -generic_args -: '<' generic_values '>' { $$ = $2; } -| '<' generic_values SHR { push_back('>'); $$ = $2; } -| '<' generic_values GE { push_back('='); $$ = $2; } -| '<' generic_values SHREQ { push_back('>'); push_back('='); $$ = $2; } -// If generic_args starts with "<<", the first arg must be a -// TyQualifiedPath because that's the only type that can start with a -// '<'. This rule parses that as the first ty_sum and then continues -// with the rest of generic_values. -| SHL ty_qualified_path_and_generic_values '>' { $$ = $2; } -| SHL ty_qualified_path_and_generic_values SHR { push_back('>'); $$ = $2; } -| SHL ty_qualified_path_and_generic_values GE { push_back('='); $$ = $2; } -| SHL ty_qualified_path_and_generic_values SHREQ { push_back('>'); push_back('='); $$ = $2; } -; - -generic_values -: maybe_ty_sums_and_or_bindings { $$ = mk_node("GenericValues", 1, $1); } -; - -maybe_ty_sums_and_or_bindings -: ty_sums -| ty_sums ',' -| ty_sums ',' bindings { $$ = mk_node("TySumsAndBindings", 2, $1, $3); } -| bindings -| bindings ',' -| %empty { $$ = mk_none(); } -; - -maybe_bindings -: ',' bindings { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -//////////////////////////////////////////////////////////////////////// -// Part 2: Patterns -//////////////////////////////////////////////////////////////////////// - -pat -: UNDERSCORE { $$ = mk_atom("PatWild"); } -| '&' pat { $$ = mk_node("PatRegion", 1, $2); } -| '&' MUT pat { $$ = mk_node("PatRegion", 1, $3); } -| ANDAND pat { $$ = mk_node("PatRegion", 1, mk_node("PatRegion", 1, $2)); } -| '(' ')' { $$ = mk_atom("PatUnit"); } -| '(' pat_tup ')' { $$ = mk_node("PatTup", 1, $2); } -| '[' pat_vec ']' { $$ = mk_node("PatVec", 1, $2); } -| lit_or_path -| lit_or_path DOTDOTDOT lit_or_path { $$ = mk_node("PatRange", 2, $1, $3); } -| path_expr '{' pat_struct '}' { $$ = mk_node("PatStruct", 2, $1, $3); } -| path_expr '(' ')' { $$ = mk_node("PatEnum", 2, $1, mk_none()); } -| path_expr '(' pat_tup ')' { $$ = mk_node("PatEnum", 2, $1, $3); } -| path_expr '!' maybe_ident delimited_token_trees { $$ = mk_node("PatMac", 3, $1, $3, $4); } -| binding_mode ident { $$ = mk_node("PatIdent", 2, $1, $2); } -| ident '@' pat { $$ = mk_node("PatIdent", 3, mk_node("BindByValue", 1, mk_atom("MutImmutable")), $1, $3); } -| binding_mode ident '@' pat { $$ = mk_node("PatIdent", 3, $1, $2, $4); } -| BOX pat { $$ = mk_node("PatUniq", 1, $2); } -| '<' ty_sum maybe_as_trait_ref '>' MOD_SEP ident { $$ = mk_node("PatQualifiedPath", 3, $2, $3, $6); } -| SHL ty_sum maybe_as_trait_ref '>' MOD_SEP ident maybe_as_trait_ref '>' MOD_SEP ident -{ - $$ = mk_node("PatQualifiedPath", 3, mk_node("PatQualifiedPath", 3, $2, $3, $6), $7, $10); -} -; - -pats_or -: pat { $$ = mk_node("Pats", 1, $1); } -| pats_or '|' pat { $$ = ext_node($1, 1, $3); } -; - -binding_mode -: REF { $$ = mk_node("BindByRef", 1, mk_atom("MutImmutable")); } -| REF MUT { $$ = mk_node("BindByRef", 1, mk_atom("MutMutable")); } -| MUT { $$ = mk_node("BindByValue", 1, mk_atom("MutMutable")); } -; - -lit_or_path -: path_expr { $$ = mk_node("PatLit", 1, $1); } -| lit { $$ = mk_node("PatLit", 1, $1); } -| '-' lit { $$ = mk_node("PatLit", 1, $2); } -; - -pat_field -: ident { $$ = mk_node("PatField", 1, $1); } -| binding_mode ident { $$ = mk_node("PatField", 2, $1, $2); } -| BOX ident { $$ = mk_node("PatField", 2, mk_atom("box"), $2); } -| BOX binding_mode ident { $$ = mk_node("PatField", 3, mk_atom("box"), $2, $3); } -| ident ':' pat { $$ = mk_node("PatField", 2, $1, $3); } -| binding_mode ident ':' pat { $$ = mk_node("PatField", 3, $1, $2, $4); } -| LIT_INTEGER ':' pat { $$ = mk_node("PatField", 2, mk_atom(yytext), $3); } -; - -pat_fields -: pat_field { $$ = mk_node("PatFields", 1, $1); } -| pat_fields ',' pat_field { $$ = ext_node($1, 1, $3); } -; - -pat_struct -: pat_fields { $$ = mk_node("PatStruct", 2, $1, mk_atom("false")); } -| pat_fields ',' { $$ = mk_node("PatStruct", 2, $1, mk_atom("false")); } -| pat_fields ',' DOTDOT { $$ = mk_node("PatStruct", 2, $1, mk_atom("true")); } -| DOTDOT { $$ = mk_node("PatStruct", 1, mk_atom("true")); } -| %empty { $$ = mk_node("PatStruct", 1, mk_none()); } -; - -pat_tup -: pat_tup_elts { $$ = mk_node("PatTup", 2, $1, mk_none()); } -| pat_tup_elts ',' { $$ = mk_node("PatTup", 2, $1, mk_none()); } -| pat_tup_elts DOTDOT { $$ = mk_node("PatTup", 2, $1, mk_none()); } -| pat_tup_elts ',' DOTDOT { $$ = mk_node("PatTup", 2, $1, mk_none()); } -| pat_tup_elts DOTDOT ',' pat_tup_elts { $$ = mk_node("PatTup", 2, $1, $4); } -| pat_tup_elts DOTDOT ',' pat_tup_elts ',' { $$ = mk_node("PatTup", 2, $1, $4); } -| pat_tup_elts ',' DOTDOT ',' pat_tup_elts { $$ = mk_node("PatTup", 2, $1, $5); } -| pat_tup_elts ',' DOTDOT ',' pat_tup_elts ',' { $$ = mk_node("PatTup", 2, $1, $5); } -| DOTDOT ',' pat_tup_elts { $$ = mk_node("PatTup", 2, mk_none(), $3); } -| DOTDOT ',' pat_tup_elts ',' { $$ = mk_node("PatTup", 2, mk_none(), $3); } -| DOTDOT { $$ = mk_node("PatTup", 2, mk_none(), mk_none()); } -; - -pat_tup_elts -: pat { $$ = mk_node("PatTupElts", 1, $1); } -| pat_tup_elts ',' pat { $$ = ext_node($1, 1, $3); } -; - -pat_vec -: pat_vec_elts { $$ = mk_node("PatVec", 2, $1, mk_none()); } -| pat_vec_elts ',' { $$ = mk_node("PatVec", 2, $1, mk_none()); } -| pat_vec_elts DOTDOT { $$ = mk_node("PatVec", 2, $1, mk_none()); } -| pat_vec_elts ',' DOTDOT { $$ = mk_node("PatVec", 2, $1, mk_none()); } -| pat_vec_elts DOTDOT ',' pat_vec_elts { $$ = mk_node("PatVec", 2, $1, $4); } -| pat_vec_elts DOTDOT ',' pat_vec_elts ',' { $$ = mk_node("PatVec", 2, $1, $4); } -| pat_vec_elts ',' DOTDOT ',' pat_vec_elts { $$ = mk_node("PatVec", 2, $1, $5); } -| pat_vec_elts ',' DOTDOT ',' pat_vec_elts ',' { $$ = mk_node("PatVec", 2, $1, $5); } -| DOTDOT ',' pat_vec_elts { $$ = mk_node("PatVec", 2, mk_none(), $3); } -| DOTDOT ',' pat_vec_elts ',' { $$ = mk_node("PatVec", 2, mk_none(), $3); } -| DOTDOT { $$ = mk_node("PatVec", 2, mk_none(), mk_none()); } -| %empty { $$ = mk_node("PatVec", 2, mk_none(), mk_none()); } -; - -pat_vec_elts -: pat { $$ = mk_node("PatVecElts", 1, $1); } -| pat_vec_elts ',' pat { $$ = ext_node($1, 1, $3); } -; - -//////////////////////////////////////////////////////////////////////// -// Part 3: Types -//////////////////////////////////////////////////////////////////////// - -ty -: ty_prim -| ty_closure -| '<' ty_sum maybe_as_trait_ref '>' MOD_SEP ident { $$ = mk_node("TyQualifiedPath", 3, $2, $3, $6); } -| SHL ty_sum maybe_as_trait_ref '>' MOD_SEP ident maybe_as_trait_ref '>' MOD_SEP ident { $$ = mk_node("TyQualifiedPath", 3, mk_node("TyQualifiedPath", 3, $2, $3, $6), $7, $10); } -| '(' ty_sums ')' { $$ = mk_node("TyTup", 1, $2); } -| '(' ty_sums ',' ')' { $$ = mk_node("TyTup", 1, $2); } -| '(' ')' { $$ = mk_atom("TyNil"); } -; - -ty_prim -: %prec IDENT path_generic_args_without_colons { $$ = mk_node("TyPath", 2, mk_node("global", 1, mk_atom("false")), $1); } -| %prec IDENT MOD_SEP path_generic_args_without_colons { $$ = mk_node("TyPath", 2, mk_node("global", 1, mk_atom("true")), $2); } -| %prec IDENT SELF MOD_SEP path_generic_args_without_colons { $$ = mk_node("TyPath", 2, mk_node("self", 1, mk_atom("true")), $3); } -| %prec IDENT path_generic_args_without_colons '!' maybe_ident delimited_token_trees { $$ = mk_node("TyMacro", 3, $1, $3, $4); } -| %prec IDENT MOD_SEP path_generic_args_without_colons '!' maybe_ident delimited_token_trees { $$ = mk_node("TyMacro", 3, $2, $4, $5); } -| BOX ty { $$ = mk_node("TyBox", 1, $2); } -| '*' maybe_mut_or_const ty { $$ = mk_node("TyPtr", 2, $2, $3); } -| '&' ty { $$ = mk_node("TyRptr", 2, mk_atom("MutImmutable"), $2); } -| '&' MUT ty { $$ = mk_node("TyRptr", 2, mk_atom("MutMutable"), $3); } -| ANDAND ty { $$ = mk_node("TyRptr", 1, mk_node("TyRptr", 2, mk_atom("MutImmutable"), $2)); } -| ANDAND MUT ty { $$ = mk_node("TyRptr", 1, mk_node("TyRptr", 2, mk_atom("MutMutable"), $3)); } -| '&' lifetime maybe_mut ty { $$ = mk_node("TyRptr", 3, $2, $3, $4); } -| ANDAND lifetime maybe_mut ty { $$ = mk_node("TyRptr", 1, mk_node("TyRptr", 3, $2, $3, $4)); } -| '[' ty ']' { $$ = mk_node("TyVec", 1, $2); } -| '[' ty ',' DOTDOT expr ']' { $$ = mk_node("TyFixedLengthVec", 2, $2, $5); } -| '[' ty ';' expr ']' { $$ = mk_node("TyFixedLengthVec", 2, $2, $4); } -| TYPEOF '(' expr ')' { $$ = mk_node("TyTypeof", 1, $3); } -| UNDERSCORE { $$ = mk_atom("TyInfer"); } -| ty_bare_fn -| for_in_type -; - -ty_bare_fn -: FN ty_fn_decl { $$ = $2; } -| UNSAFE FN ty_fn_decl { $$ = $3; } -| EXTERN maybe_abi FN ty_fn_decl { $$ = $4; } -| UNSAFE EXTERN maybe_abi FN ty_fn_decl { $$ = $5; } -; - -ty_fn_decl -: generic_params fn_anon_params ret_ty { $$ = mk_node("TyFnDecl", 3, $1, $2, $3); } -; - -ty_closure -: UNSAFE '|' anon_params '|' maybe_bounds ret_ty { $$ = mk_node("TyClosure", 3, $3, $5, $6); } -| '|' anon_params '|' maybe_bounds ret_ty { $$ = mk_node("TyClosure", 3, $2, $4, $5); } -| UNSAFE OROR maybe_bounds ret_ty { $$ = mk_node("TyClosure", 2, $3, $4); } -| OROR maybe_bounds ret_ty { $$ = mk_node("TyClosure", 2, $2, $3); } -; - -for_in_type -: FOR '<' maybe_lifetimes '>' for_in_type_suffix { $$ = mk_node("ForInType", 2, $3, $5); } -; - -for_in_type_suffix -: ty_bare_fn -| trait_ref -| ty_closure -; - -maybe_mut -: MUT { $$ = mk_atom("MutMutable"); } -| %prec MUT %empty { $$ = mk_atom("MutImmutable"); } -; - -maybe_mut_or_const -: MUT { $$ = mk_atom("MutMutable"); } -| CONST { $$ = mk_atom("MutImmutable"); } -| %empty { $$ = mk_atom("MutImmutable"); } -; - -ty_qualified_path_and_generic_values -: ty_qualified_path maybe_bindings -{ - $$ = mk_node("GenericValues", 3, mk_none(), mk_node("TySums", 1, mk_node("TySum", 1, $1)), $2); -} -| ty_qualified_path ',' ty_sums maybe_bindings -{ - $$ = mk_node("GenericValues", 3, mk_none(), mk_node("TySums", 2, $1, $3), $4); -} -; - -ty_qualified_path -: ty_sum AS trait_ref '>' MOD_SEP ident { $$ = mk_node("TyQualifiedPath", 3, $1, $3, $6); } -| ty_sum AS trait_ref '>' MOD_SEP ident '+' ty_param_bounds { $$ = mk_node("TyQualifiedPath", 3, $1, $3, $6); } -; - -maybe_ty_sums -: ty_sums -| ty_sums ',' -| %empty { $$ = mk_none(); } -; - -ty_sums -: ty_sum { $$ = mk_node("TySums", 1, $1); } -| ty_sums ',' ty_sum { $$ = ext_node($1, 1, $3); } -; - -ty_sum -: ty_sum_elt { $$ = mk_node("TySum", 1, $1); } -| ty_sum '+' ty_sum_elt { $$ = ext_node($1, 1, $3); } -; - -ty_sum_elt -: ty -| lifetime -; - -ty_prim_sum -: ty_prim_sum_elt { $$ = mk_node("TySum", 1, $1); } -| ty_prim_sum '+' ty_prim_sum_elt { $$ = ext_node($1, 1, $3); } -; - -ty_prim_sum_elt -: ty_prim -| lifetime -; - -maybe_ty_param_bounds -: ':' ty_param_bounds { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -ty_param_bounds -: boundseq -| %empty { $$ = mk_none(); } -; - -boundseq -: polybound -| boundseq '+' polybound { $$ = ext_node($1, 1, $3); } -; - -polybound -: FOR '<' maybe_lifetimes '>' bound { $$ = mk_node("PolyBound", 2, $3, $5); } -| bound -| '?' FOR '<' maybe_lifetimes '>' bound { $$ = mk_node("PolyBound", 2, $4, $6); } -| '?' bound { $$ = $2; } -; - -bindings -: binding { $$ = mk_node("Bindings", 1, $1); } -| bindings ',' binding { $$ = ext_node($1, 1, $3); } -; - -binding -: ident '=' ty { mk_node("Binding", 2, $1, $3); } -; - -ty_param -: ident maybe_ty_param_bounds maybe_ty_default { $$ = mk_node("TyParam", 3, $1, $2, $3); } -| ident '?' ident maybe_ty_param_bounds maybe_ty_default { $$ = mk_node("TyParam", 4, $1, $3, $4, $5); } -; - -maybe_bounds -: %prec SHIFTPLUS - ':' bounds { $$ = $2; } -| %prec SHIFTPLUS %empty { $$ = mk_none(); } -; - -bounds -: bound { $$ = mk_node("bounds", 1, $1); } -| bounds '+' bound { $$ = ext_node($1, 1, $3); } -; - -bound -: lifetime -| trait_ref -; - -maybe_ltbounds -: %prec SHIFTPLUS - ':' ltbounds { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -ltbounds -: lifetime { $$ = mk_node("ltbounds", 1, $1); } -| ltbounds '+' lifetime { $$ = ext_node($1, 1, $3); } -; - -maybe_ty_default -: '=' ty_sum { $$ = mk_node("TyDefault", 1, $2); } -| %empty { $$ = mk_none(); } -; - -maybe_lifetimes -: lifetimes -| lifetimes ',' -| %empty { $$ = mk_none(); } -; - -lifetimes -: lifetime_and_bounds { $$ = mk_node("Lifetimes", 1, $1); } -| lifetimes ',' lifetime_and_bounds { $$ = ext_node($1, 1, $3); } -; - -lifetime_and_bounds -: LIFETIME maybe_ltbounds { $$ = mk_node("lifetime", 2, mk_atom(yytext), $2); } -| STATIC_LIFETIME { $$ = mk_atom("static_lifetime"); } -; - -lifetime -: LIFETIME { $$ = mk_node("lifetime", 1, mk_atom(yytext)); } -| STATIC_LIFETIME { $$ = mk_atom("static_lifetime"); } -; - -trait_ref -: %prec IDENT path_generic_args_without_colons -| %prec IDENT MOD_SEP path_generic_args_without_colons { $$ = $2; } -; - -//////////////////////////////////////////////////////////////////////// -// Part 4: Blocks, statements, and expressions -//////////////////////////////////////////////////////////////////////// - -inner_attrs_and_block -: '{' maybe_inner_attrs maybe_stmts '}' { $$ = mk_node("ExprBlock", 2, $2, $3); } -; - -block -: '{' maybe_stmts '}' { $$ = mk_node("ExprBlock", 1, $2); } -; - -maybe_stmts -: stmts -| stmts nonblock_expr { $$ = ext_node($1, 1, $2); } -| nonblock_expr -| %empty { $$ = mk_none(); } -; - -// There are two sub-grammars within a "stmts: exprs" derivation -// depending on whether each stmt-expr is a block-expr form; this is to -// handle the "semicolon rule" for stmt sequencing that permits -// writing -// -// if foo { bar } 10 -// -// as a sequence of two stmts (one if-expr stmt, one lit-10-expr -// stmt). Unfortunately by permitting juxtaposition of exprs in -// sequence like that, the non-block expr grammar has to have a -// second limited sub-grammar that excludes the prefix exprs that -// are ambiguous with binops. That is to say: -// -// {10} - 1 -// -// should parse as (progn (progn 10) (- 1)) not (- (progn 10) 1), that -// is to say, two statements rather than one, at least according to -// the mainline rust parser. -// -// So we wind up with a 3-way split in exprs that occur in stmt lists: -// block, nonblock-prefix, and nonblock-nonprefix. -// -// In non-stmts contexts, expr can relax this trichotomy. - -stmts -: stmt { $$ = mk_node("stmts", 1, $1); } -| stmts stmt { $$ = ext_node($1, 1, $2); } -; - -stmt -: maybe_outer_attrs let { $$ = $2; } -| stmt_item -| PUB stmt_item { $$ = $2; } -| outer_attrs stmt_item { $$ = $2; } -| outer_attrs PUB stmt_item { $$ = $3; } -| full_block_expr -| maybe_outer_attrs block { $$ = $2; } -| nonblock_expr ';' -| outer_attrs nonblock_expr ';' { $$ = $2; } -| ';' { $$ = mk_none(); } -; - -maybe_exprs -: exprs -| exprs ',' -| %empty { $$ = mk_none(); } -; - -maybe_expr -: expr -| %empty { $$ = mk_none(); } -; - -exprs -: expr { $$ = mk_node("exprs", 1, $1); } -| exprs ',' expr { $$ = ext_node($1, 1, $3); } -; - -path_expr -: path_generic_args_with_colons -| MOD_SEP path_generic_args_with_colons { $$ = $2; } -| SELF MOD_SEP path_generic_args_with_colons { $$ = mk_node("SelfPath", 1, $3); } -; - -// A path with a lifetime and type parameters with double colons before -// the type parameters; e.g. `foo::bar::<'a>::Baz::` -// -// These show up in expr context, in order to disambiguate from "less-than" -// expressions. -path_generic_args_with_colons -: ident { $$ = mk_node("components", 1, $1); } -| SUPER { $$ = mk_atom("Super"); } -| path_generic_args_with_colons MOD_SEP ident { $$ = ext_node($1, 1, $3); } -| path_generic_args_with_colons MOD_SEP SUPER { $$ = ext_node($1, 1, mk_atom("Super")); } -| path_generic_args_with_colons MOD_SEP generic_args { $$ = ext_node($1, 1, $3); } -; - -// the braces-delimited macro is a block_expr so it doesn't appear here -macro_expr -: path_expr '!' maybe_ident parens_delimited_token_trees { $$ = mk_node("MacroExpr", 3, $1, $3, $4); } -| path_expr '!' maybe_ident brackets_delimited_token_trees { $$ = mk_node("MacroExpr", 3, $1, $3, $4); } -; - -nonblock_expr -: lit { $$ = mk_node("ExprLit", 1, $1); } -| %prec IDENT - path_expr { $$ = mk_node("ExprPath", 1, $1); } -| SELF { $$ = mk_node("ExprPath", 1, mk_node("ident", 1, mk_atom("self"))); } -| macro_expr { $$ = mk_node("ExprMac", 1, $1); } -| path_expr '{' struct_expr_fields '}' { $$ = mk_node("ExprStruct", 2, $1, $3); } -| nonblock_expr '?' { $$ = mk_node("ExprTry", 1, $1); } -| nonblock_expr '.' path_generic_args_with_colons { $$ = mk_node("ExprField", 2, $1, $3); } -| nonblock_expr '.' LIT_INTEGER { $$ = mk_node("ExprTupleIndex", 1, $1); } -| nonblock_expr '[' maybe_expr ']' { $$ = mk_node("ExprIndex", 2, $1, $3); } -| nonblock_expr '(' maybe_exprs ')' { $$ = mk_node("ExprCall", 2, $1, $3); } -| '[' vec_expr ']' { $$ = mk_node("ExprVec", 1, $2); } -| '(' maybe_exprs ')' { $$ = mk_node("ExprParen", 1, $2); } -| CONTINUE { $$ = mk_node("ExprAgain", 0); } -| CONTINUE lifetime { $$ = mk_node("ExprAgain", 1, $2); } -| RETURN { $$ = mk_node("ExprRet", 0); } -| RETURN expr { $$ = mk_node("ExprRet", 1, $2); } -| BREAK { $$ = mk_node("ExprBreak", 0); } -| BREAK lifetime { $$ = mk_node("ExprBreak", 1, $2); } -| YIELD { $$ = mk_node("ExprYield", 0); } -| YIELD expr { $$ = mk_node("ExprYield", 1, $2); } -| nonblock_expr '=' expr { $$ = mk_node("ExprAssign", 2, $1, $3); } -| nonblock_expr SHLEQ expr { $$ = mk_node("ExprAssignShl", 2, $1, $3); } -| nonblock_expr SHREQ expr { $$ = mk_node("ExprAssignShr", 2, $1, $3); } -| nonblock_expr MINUSEQ expr { $$ = mk_node("ExprAssignSub", 2, $1, $3); } -| nonblock_expr ANDEQ expr { $$ = mk_node("ExprAssignBitAnd", 2, $1, $3); } -| nonblock_expr OREQ expr { $$ = mk_node("ExprAssignBitOr", 2, $1, $3); } -| nonblock_expr PLUSEQ expr { $$ = mk_node("ExprAssignAdd", 2, $1, $3); } -| nonblock_expr STAREQ expr { $$ = mk_node("ExprAssignMul", 2, $1, $3); } -| nonblock_expr SLASHEQ expr { $$ = mk_node("ExprAssignDiv", 2, $1, $3); } -| nonblock_expr CARETEQ expr { $$ = mk_node("ExprAssignBitXor", 2, $1, $3); } -| nonblock_expr PERCENTEQ expr { $$ = mk_node("ExprAssignRem", 2, $1, $3); } -| nonblock_expr OROR expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiOr"), $1, $3); } -| nonblock_expr ANDAND expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiAnd"), $1, $3); } -| nonblock_expr EQEQ expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiEq"), $1, $3); } -| nonblock_expr NE expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiNe"), $1, $3); } -| nonblock_expr '<' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiLt"), $1, $3); } -| nonblock_expr '>' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiGt"), $1, $3); } -| nonblock_expr LE expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiLe"), $1, $3); } -| nonblock_expr GE expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiGe"), $1, $3); } -| nonblock_expr '|' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitOr"), $1, $3); } -| nonblock_expr '^' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitXor"), $1, $3); } -| nonblock_expr '&' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitAnd"), $1, $3); } -| nonblock_expr SHL expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiShl"), $1, $3); } -| nonblock_expr SHR expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiShr"), $1, $3); } -| nonblock_expr '+' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiAdd"), $1, $3); } -| nonblock_expr '-' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiSub"), $1, $3); } -| nonblock_expr '*' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiMul"), $1, $3); } -| nonblock_expr '/' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiDiv"), $1, $3); } -| nonblock_expr '%' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiRem"), $1, $3); } -| nonblock_expr DOTDOT { $$ = mk_node("ExprRange", 2, $1, mk_none()); } -| nonblock_expr DOTDOT expr { $$ = mk_node("ExprRange", 2, $1, $3); } -| DOTDOT expr { $$ = mk_node("ExprRange", 2, mk_none(), $2); } -| DOTDOT { $$ = mk_node("ExprRange", 2, mk_none(), mk_none()); } -| nonblock_expr AS ty { $$ = mk_node("ExprCast", 2, $1, $3); } -| nonblock_expr ':' ty { $$ = mk_node("ExprTypeAscr", 2, $1, $3); } -| BOX expr { $$ = mk_node("ExprBox", 1, $2); } -| expr_qualified_path -| nonblock_prefix_expr -; - -expr -: lit { $$ = mk_node("ExprLit", 1, $1); } -| %prec IDENT - path_expr { $$ = mk_node("ExprPath", 1, $1); } -| SELF { $$ = mk_node("ExprPath", 1, mk_node("ident", 1, mk_atom("self"))); } -| macro_expr { $$ = mk_node("ExprMac", 1, $1); } -| path_expr '{' struct_expr_fields '}' { $$ = mk_node("ExprStruct", 2, $1, $3); } -| expr '?' { $$ = mk_node("ExprTry", 1, $1); } -| expr '.' path_generic_args_with_colons { $$ = mk_node("ExprField", 2, $1, $3); } -| expr '.' LIT_INTEGER { $$ = mk_node("ExprTupleIndex", 1, $1); } -| expr '[' maybe_expr ']' { $$ = mk_node("ExprIndex", 2, $1, $3); } -| expr '(' maybe_exprs ')' { $$ = mk_node("ExprCall", 2, $1, $3); } -| '(' maybe_exprs ')' { $$ = mk_node("ExprParen", 1, $2); } -| '[' vec_expr ']' { $$ = mk_node("ExprVec", 1, $2); } -| CONTINUE { $$ = mk_node("ExprAgain", 0); } -| CONTINUE ident { $$ = mk_node("ExprAgain", 1, $2); } -| RETURN { $$ = mk_node("ExprRet", 0); } -| RETURN expr { $$ = mk_node("ExprRet", 1, $2); } -| BREAK { $$ = mk_node("ExprBreak", 0); } -| BREAK ident { $$ = mk_node("ExprBreak", 1, $2); } -| YIELD { $$ = mk_node("ExprYield", 0); } -| YIELD expr { $$ = mk_node("ExprYield", 1, $2); } -| expr '=' expr { $$ = mk_node("ExprAssign", 2, $1, $3); } -| expr SHLEQ expr { $$ = mk_node("ExprAssignShl", 2, $1, $3); } -| expr SHREQ expr { $$ = mk_node("ExprAssignShr", 2, $1, $3); } -| expr MINUSEQ expr { $$ = mk_node("ExprAssignSub", 2, $1, $3); } -| expr ANDEQ expr { $$ = mk_node("ExprAssignBitAnd", 2, $1, $3); } -| expr OREQ expr { $$ = mk_node("ExprAssignBitOr", 2, $1, $3); } -| expr PLUSEQ expr { $$ = mk_node("ExprAssignAdd", 2, $1, $3); } -| expr STAREQ expr { $$ = mk_node("ExprAssignMul", 2, $1, $3); } -| expr SLASHEQ expr { $$ = mk_node("ExprAssignDiv", 2, $1, $3); } -| expr CARETEQ expr { $$ = mk_node("ExprAssignBitXor", 2, $1, $3); } -| expr PERCENTEQ expr { $$ = mk_node("ExprAssignRem", 2, $1, $3); } -| expr OROR expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiOr"), $1, $3); } -| expr ANDAND expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiAnd"), $1, $3); } -| expr EQEQ expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiEq"), $1, $3); } -| expr NE expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiNe"), $1, $3); } -| expr '<' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiLt"), $1, $3); } -| expr '>' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiGt"), $1, $3); } -| expr LE expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiLe"), $1, $3); } -| expr GE expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiGe"), $1, $3); } -| expr '|' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitOr"), $1, $3); } -| expr '^' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitXor"), $1, $3); } -| expr '&' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitAnd"), $1, $3); } -| expr SHL expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiShl"), $1, $3); } -| expr SHR expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiShr"), $1, $3); } -| expr '+' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiAdd"), $1, $3); } -| expr '-' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiSub"), $1, $3); } -| expr '*' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiMul"), $1, $3); } -| expr '/' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiDiv"), $1, $3); } -| expr '%' expr { $$ = mk_node("ExprBinary", 3, mk_atom("BiRem"), $1, $3); } -| expr DOTDOT { $$ = mk_node("ExprRange", 2, $1, mk_none()); } -| expr DOTDOT expr { $$ = mk_node("ExprRange", 2, $1, $3); } -| DOTDOT expr { $$ = mk_node("ExprRange", 2, mk_none(), $2); } -| DOTDOT { $$ = mk_node("ExprRange", 2, mk_none(), mk_none()); } -| expr AS ty { $$ = mk_node("ExprCast", 2, $1, $3); } -| expr ':' ty { $$ = mk_node("ExprTypeAscr", 2, $1, $3); } -| BOX expr { $$ = mk_node("ExprBox", 1, $2); } -| expr_qualified_path -| block_expr -| block -| nonblock_prefix_expr -; - -expr_nostruct -: lit { $$ = mk_node("ExprLit", 1, $1); } -| %prec IDENT - path_expr { $$ = mk_node("ExprPath", 1, $1); } -| SELF { $$ = mk_node("ExprPath", 1, mk_node("ident", 1, mk_atom("self"))); } -| macro_expr { $$ = mk_node("ExprMac", 1, $1); } -| expr_nostruct '?' { $$ = mk_node("ExprTry", 1, $1); } -| expr_nostruct '.' path_generic_args_with_colons { $$ = mk_node("ExprField", 2, $1, $3); } -| expr_nostruct '.' LIT_INTEGER { $$ = mk_node("ExprTupleIndex", 1, $1); } -| expr_nostruct '[' maybe_expr ']' { $$ = mk_node("ExprIndex", 2, $1, $3); } -| expr_nostruct '(' maybe_exprs ')' { $$ = mk_node("ExprCall", 2, $1, $3); } -| '[' vec_expr ']' { $$ = mk_node("ExprVec", 1, $2); } -| '(' maybe_exprs ')' { $$ = mk_node("ExprParen", 1, $2); } -| CONTINUE { $$ = mk_node("ExprAgain", 0); } -| CONTINUE ident { $$ = mk_node("ExprAgain", 1, $2); } -| RETURN { $$ = mk_node("ExprRet", 0); } -| RETURN expr { $$ = mk_node("ExprRet", 1, $2); } -| BREAK { $$ = mk_node("ExprBreak", 0); } -| BREAK ident { $$ = mk_node("ExprBreak", 1, $2); } -| YIELD { $$ = mk_node("ExprYield", 0); } -| YIELD expr { $$ = mk_node("ExprYield", 1, $2); } -| expr_nostruct '=' expr_nostruct { $$ = mk_node("ExprAssign", 2, $1, $3); } -| expr_nostruct SHLEQ expr_nostruct { $$ = mk_node("ExprAssignShl", 2, $1, $3); } -| expr_nostruct SHREQ expr_nostruct { $$ = mk_node("ExprAssignShr", 2, $1, $3); } -| expr_nostruct MINUSEQ expr_nostruct { $$ = mk_node("ExprAssignSub", 2, $1, $3); } -| expr_nostruct ANDEQ expr_nostruct { $$ = mk_node("ExprAssignBitAnd", 2, $1, $3); } -| expr_nostruct OREQ expr_nostruct { $$ = mk_node("ExprAssignBitOr", 2, $1, $3); } -| expr_nostruct PLUSEQ expr_nostruct { $$ = mk_node("ExprAssignAdd", 2, $1, $3); } -| expr_nostruct STAREQ expr_nostruct { $$ = mk_node("ExprAssignMul", 2, $1, $3); } -| expr_nostruct SLASHEQ expr_nostruct { $$ = mk_node("ExprAssignDiv", 2, $1, $3); } -| expr_nostruct CARETEQ expr_nostruct { $$ = mk_node("ExprAssignBitXor", 2, $1, $3); } -| expr_nostruct PERCENTEQ expr_nostruct { $$ = mk_node("ExprAssignRem", 2, $1, $3); } -| expr_nostruct OROR expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiOr"), $1, $3); } -| expr_nostruct ANDAND expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiAnd"), $1, $3); } -| expr_nostruct EQEQ expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiEq"), $1, $3); } -| expr_nostruct NE expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiNe"), $1, $3); } -| expr_nostruct '<' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiLt"), $1, $3); } -| expr_nostruct '>' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiGt"), $1, $3); } -| expr_nostruct LE expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiLe"), $1, $3); } -| expr_nostruct GE expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiGe"), $1, $3); } -| expr_nostruct '|' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitOr"), $1, $3); } -| expr_nostruct '^' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitXor"), $1, $3); } -| expr_nostruct '&' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiBitAnd"), $1, $3); } -| expr_nostruct SHL expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiShl"), $1, $3); } -| expr_nostruct SHR expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiShr"), $1, $3); } -| expr_nostruct '+' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiAdd"), $1, $3); } -| expr_nostruct '-' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiSub"), $1, $3); } -| expr_nostruct '*' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiMul"), $1, $3); } -| expr_nostruct '/' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiDiv"), $1, $3); } -| expr_nostruct '%' expr_nostruct { $$ = mk_node("ExprBinary", 3, mk_atom("BiRem"), $1, $3); } -| expr_nostruct DOTDOT %prec RANGE { $$ = mk_node("ExprRange", 2, $1, mk_none()); } -| expr_nostruct DOTDOT expr_nostruct { $$ = mk_node("ExprRange", 2, $1, $3); } -| DOTDOT expr_nostruct { $$ = mk_node("ExprRange", 2, mk_none(), $2); } -| DOTDOT { $$ = mk_node("ExprRange", 2, mk_none(), mk_none()); } -| expr_nostruct AS ty { $$ = mk_node("ExprCast", 2, $1, $3); } -| expr_nostruct ':' ty { $$ = mk_node("ExprTypeAscr", 2, $1, $3); } -| BOX expr { $$ = mk_node("ExprBox", 1, $2); } -| expr_qualified_path -| block_expr -| block -| nonblock_prefix_expr_nostruct -; - -nonblock_prefix_expr_nostruct -: '-' expr_nostruct { $$ = mk_node("ExprUnary", 2, mk_atom("UnNeg"), $2); } -| '!' expr_nostruct { $$ = mk_node("ExprUnary", 2, mk_atom("UnNot"), $2); } -| '*' expr_nostruct { $$ = mk_node("ExprUnary", 2, mk_atom("UnDeref"), $2); } -| '&' maybe_mut expr_nostruct { $$ = mk_node("ExprAddrOf", 2, $2, $3); } -| ANDAND maybe_mut expr_nostruct { $$ = mk_node("ExprAddrOf", 1, mk_node("ExprAddrOf", 2, $2, $3)); } -| lambda_expr_nostruct -| MOVE lambda_expr_nostruct { $$ = $2; } -; - -nonblock_prefix_expr -: '-' expr { $$ = mk_node("ExprUnary", 2, mk_atom("UnNeg"), $2); } -| '!' expr { $$ = mk_node("ExprUnary", 2, mk_atom("UnNot"), $2); } -| '*' expr { $$ = mk_node("ExprUnary", 2, mk_atom("UnDeref"), $2); } -| '&' maybe_mut expr { $$ = mk_node("ExprAddrOf", 2, $2, $3); } -| ANDAND maybe_mut expr { $$ = mk_node("ExprAddrOf", 1, mk_node("ExprAddrOf", 2, $2, $3)); } -| lambda_expr -| MOVE lambda_expr { $$ = $2; } -; - -expr_qualified_path -: '<' ty_sum maybe_as_trait_ref '>' MOD_SEP ident maybe_qpath_params -{ - $$ = mk_node("ExprQualifiedPath", 4, $2, $3, $6, $7); -} -| SHL ty_sum maybe_as_trait_ref '>' MOD_SEP ident maybe_as_trait_ref '>' MOD_SEP ident -{ - $$ = mk_node("ExprQualifiedPath", 3, mk_node("ExprQualifiedPath", 3, $2, $3, $6), $7, $10); -} -| SHL ty_sum maybe_as_trait_ref '>' MOD_SEP ident generic_args maybe_as_trait_ref '>' MOD_SEP ident -{ - $$ = mk_node("ExprQualifiedPath", 3, mk_node("ExprQualifiedPath", 4, $2, $3, $6, $7), $8, $11); -} -| SHL ty_sum maybe_as_trait_ref '>' MOD_SEP ident maybe_as_trait_ref '>' MOD_SEP ident generic_args -{ - $$ = mk_node("ExprQualifiedPath", 4, mk_node("ExprQualifiedPath", 3, $2, $3, $6), $7, $10, $11); -} -| SHL ty_sum maybe_as_trait_ref '>' MOD_SEP ident generic_args maybe_as_trait_ref '>' MOD_SEP ident generic_args -{ - $$ = mk_node("ExprQualifiedPath", 4, mk_node("ExprQualifiedPath", 4, $2, $3, $6, $7), $8, $11, $12); -} - -maybe_qpath_params -: MOD_SEP generic_args { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -maybe_as_trait_ref -: AS trait_ref { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -lambda_expr -: %prec LAMBDA - OROR ret_ty expr { $$ = mk_node("ExprFnBlock", 3, mk_none(), $2, $3); } -| %prec LAMBDA - '|' '|' ret_ty expr { $$ = mk_node("ExprFnBlock", 3, mk_none(), $3, $4); } -| %prec LAMBDA - '|' inferrable_params '|' ret_ty expr { $$ = mk_node("ExprFnBlock", 3, $2, $4, $5); } -| %prec LAMBDA - '|' inferrable_params OROR lambda_expr_no_first_bar { $$ = mk_node("ExprFnBlock", 3, $2, mk_none(), $4); } -; - -lambda_expr_no_first_bar -: %prec LAMBDA - '|' ret_ty expr { $$ = mk_node("ExprFnBlock", 3, mk_none(), $2, $3); } -| %prec LAMBDA - inferrable_params '|' ret_ty expr { $$ = mk_node("ExprFnBlock", 3, $1, $3, $4); } -| %prec LAMBDA - inferrable_params OROR lambda_expr_no_first_bar { $$ = mk_node("ExprFnBlock", 3, $1, mk_none(), $3); } -; - -lambda_expr_nostruct -: %prec LAMBDA - OROR expr_nostruct { $$ = mk_node("ExprFnBlock", 2, mk_none(), $2); } -| %prec LAMBDA - '|' '|' ret_ty expr_nostruct { $$ = mk_node("ExprFnBlock", 3, mk_none(), $3, $4); } -| %prec LAMBDA - '|' inferrable_params '|' expr_nostruct { $$ = mk_node("ExprFnBlock", 2, $2, $4); } -| %prec LAMBDA - '|' inferrable_params OROR lambda_expr_nostruct_no_first_bar { $$ = mk_node("ExprFnBlock", 3, $2, mk_none(), $4); } -; - -lambda_expr_nostruct_no_first_bar -: %prec LAMBDA - '|' ret_ty expr_nostruct { $$ = mk_node("ExprFnBlock", 3, mk_none(), $2, $3); } -| %prec LAMBDA - inferrable_params '|' ret_ty expr_nostruct { $$ = mk_node("ExprFnBlock", 3, $1, $3, $4); } -| %prec LAMBDA - inferrable_params OROR lambda_expr_nostruct_no_first_bar { $$ = mk_node("ExprFnBlock", 3, $1, mk_none(), $3); } -; - -vec_expr -: maybe_exprs -| exprs ';' expr { $$ = mk_node("VecRepeat", 2, $1, $3); } -; - -struct_expr_fields -: field_inits -| field_inits ',' -| maybe_field_inits default_field_init { $$ = ext_node($1, 1, $2); } -| %empty { $$ = mk_none(); } -; - -maybe_field_inits -: field_inits -| field_inits ',' -| %empty { $$ = mk_none(); } -; - -field_inits -: field_init { $$ = mk_node("FieldInits", 1, $1); } -| field_inits ',' field_init { $$ = ext_node($1, 1, $3); } -; - -field_init -: ident { $$ = mk_node("FieldInit", 1, $1); } -| ident ':' expr { $$ = mk_node("FieldInit", 2, $1, $3); } -| LIT_INTEGER ':' expr { $$ = mk_node("FieldInit", 2, mk_atom(yytext), $3); } -; - -default_field_init -: DOTDOT expr { $$ = mk_node("DefaultFieldInit", 1, $2); } -; - -block_expr -: expr_match -| expr_if -| expr_if_let -| expr_while -| expr_while_let -| expr_loop -| expr_for -| UNSAFE block { $$ = mk_node("UnsafeBlock", 1, $2); } -| path_expr '!' maybe_ident braces_delimited_token_trees { $$ = mk_node("Macro", 3, $1, $3, $4); } -; - -full_block_expr -: block_expr -| block_expr_dot -; - -block_expr_dot -: block_expr '.' path_generic_args_with_colons %prec IDENT { $$ = mk_node("ExprField", 2, $1, $3); } -| block_expr_dot '.' path_generic_args_with_colons %prec IDENT { $$ = mk_node("ExprField", 2, $1, $3); } -| block_expr '.' path_generic_args_with_colons '[' maybe_expr ']' { $$ = mk_node("ExprIndex", 3, $1, $3, $5); } -| block_expr_dot '.' path_generic_args_with_colons '[' maybe_expr ']' { $$ = mk_node("ExprIndex", 3, $1, $3, $5); } -| block_expr '.' path_generic_args_with_colons '(' maybe_exprs ')' { $$ = mk_node("ExprCall", 3, $1, $3, $5); } -| block_expr_dot '.' path_generic_args_with_colons '(' maybe_exprs ')' { $$ = mk_node("ExprCall", 3, $1, $3, $5); } -| block_expr '.' LIT_INTEGER { $$ = mk_node("ExprTupleIndex", 1, $1); } -| block_expr_dot '.' LIT_INTEGER { $$ = mk_node("ExprTupleIndex", 1, $1); } -; - -expr_match -: MATCH expr_nostruct '{' '}' { $$ = mk_node("ExprMatch", 1, $2); } -| MATCH expr_nostruct '{' match_clauses '}' { $$ = mk_node("ExprMatch", 2, $2, $4); } -| MATCH expr_nostruct '{' match_clauses nonblock_match_clause '}' { $$ = mk_node("ExprMatch", 2, $2, ext_node($4, 1, $5)); } -| MATCH expr_nostruct '{' nonblock_match_clause '}' { $$ = mk_node("ExprMatch", 2, $2, mk_node("Arms", 1, $4)); } -; - -match_clauses -: match_clause { $$ = mk_node("Arms", 1, $1); } -| match_clauses match_clause { $$ = ext_node($1, 1, $2); } -; - -match_clause -: nonblock_match_clause ',' -| block_match_clause -| block_match_clause ',' -; - -nonblock_match_clause -: maybe_outer_attrs pats_or maybe_guard FAT_ARROW nonblock_expr { $$ = mk_node("ArmNonblock", 4, $1, $2, $3, $5); } -| maybe_outer_attrs pats_or maybe_guard FAT_ARROW block_expr_dot { $$ = mk_node("ArmNonblock", 4, $1, $2, $3, $5); } -; - -block_match_clause -: maybe_outer_attrs pats_or maybe_guard FAT_ARROW block { $$ = mk_node("ArmBlock", 4, $1, $2, $3, $5); } -| maybe_outer_attrs pats_or maybe_guard FAT_ARROW block_expr { $$ = mk_node("ArmBlock", 4, $1, $2, $3, $5); } -; - -maybe_guard -: IF expr_nostruct { $$ = $2; } -| %empty { $$ = mk_none(); } -; - -expr_if -: IF expr_nostruct block { $$ = mk_node("ExprIf", 2, $2, $3); } -| IF expr_nostruct block ELSE block_or_if { $$ = mk_node("ExprIf", 3, $2, $3, $5); } -; - -expr_if_let -: IF LET pat '=' expr_nostruct block { $$ = mk_node("ExprIfLet", 3, $3, $5, $6); } -| IF LET pat '=' expr_nostruct block ELSE block_or_if { $$ = mk_node("ExprIfLet", 4, $3, $5, $6, $8); } -; - -block_or_if -: block -| expr_if -| expr_if_let -; - -expr_while -: maybe_label WHILE expr_nostruct block { $$ = mk_node("ExprWhile", 3, $1, $3, $4); } -; - -expr_while_let -: maybe_label WHILE LET pat '=' expr_nostruct block { $$ = mk_node("ExprWhileLet", 4, $1, $4, $6, $7); } -; - -expr_loop -: maybe_label LOOP block { $$ = mk_node("ExprLoop", 2, $1, $3); } -; - -expr_for -: maybe_label FOR pat IN expr_nostruct block { $$ = mk_node("ExprForLoop", 4, $1, $3, $5, $6); } -; - -maybe_label -: lifetime ':' -| %empty { $$ = mk_none(); } -; - -let -: LET pat maybe_ty_ascription maybe_init_expr ';' { $$ = mk_node("DeclLocal", 3, $2, $3, $4); } -; - -//////////////////////////////////////////////////////////////////////// -// Part 5: Macros and misc. rules -//////////////////////////////////////////////////////////////////////// - -lit -: LIT_BYTE { $$ = mk_node("LitByte", 1, mk_atom(yytext)); } -| LIT_CHAR { $$ = mk_node("LitChar", 1, mk_atom(yytext)); } -| LIT_INTEGER { $$ = mk_node("LitInteger", 1, mk_atom(yytext)); } -| LIT_FLOAT { $$ = mk_node("LitFloat", 1, mk_atom(yytext)); } -| TRUE { $$ = mk_node("LitBool", 1, mk_atom(yytext)); } -| FALSE { $$ = mk_node("LitBool", 1, mk_atom(yytext)); } -| str -; - -str -: LIT_STR { $$ = mk_node("LitStr", 1, mk_atom(yytext), mk_atom("CookedStr")); } -| LIT_STR_RAW { $$ = mk_node("LitStr", 1, mk_atom(yytext), mk_atom("RawStr")); } -| LIT_BYTE_STR { $$ = mk_node("LitByteStr", 1, mk_atom(yytext), mk_atom("ByteStr")); } -| LIT_BYTE_STR_RAW { $$ = mk_node("LitByteStr", 1, mk_atom(yytext), mk_atom("RawByteStr")); } -; - -maybe_ident -: %empty { $$ = mk_none(); } -| ident -; - -ident -: IDENT { $$ = mk_node("ident", 1, mk_atom(yytext)); } -// Weak keywords that can be used as identifiers -| CATCH { $$ = mk_node("ident", 1, mk_atom(yytext)); } -| DEFAULT { $$ = mk_node("ident", 1, mk_atom(yytext)); } -| UNION { $$ = mk_node("ident", 1, mk_atom(yytext)); } -; - -unpaired_token -: SHL { $$ = mk_atom(yytext); } -| SHR { $$ = mk_atom(yytext); } -| LE { $$ = mk_atom(yytext); } -| EQEQ { $$ = mk_atom(yytext); } -| NE { $$ = mk_atom(yytext); } -| GE { $$ = mk_atom(yytext); } -| ANDAND { $$ = mk_atom(yytext); } -| OROR { $$ = mk_atom(yytext); } -| LARROW { $$ = mk_atom(yytext); } -| SHLEQ { $$ = mk_atom(yytext); } -| SHREQ { $$ = mk_atom(yytext); } -| MINUSEQ { $$ = mk_atom(yytext); } -| ANDEQ { $$ = mk_atom(yytext); } -| OREQ { $$ = mk_atom(yytext); } -| PLUSEQ { $$ = mk_atom(yytext); } -| STAREQ { $$ = mk_atom(yytext); } -| SLASHEQ { $$ = mk_atom(yytext); } -| CARETEQ { $$ = mk_atom(yytext); } -| PERCENTEQ { $$ = mk_atom(yytext); } -| DOTDOT { $$ = mk_atom(yytext); } -| DOTDOTDOT { $$ = mk_atom(yytext); } -| MOD_SEP { $$ = mk_atom(yytext); } -| RARROW { $$ = mk_atom(yytext); } -| FAT_ARROW { $$ = mk_atom(yytext); } -| LIT_BYTE { $$ = mk_atom(yytext); } -| LIT_CHAR { $$ = mk_atom(yytext); } -| LIT_INTEGER { $$ = mk_atom(yytext); } -| LIT_FLOAT { $$ = mk_atom(yytext); } -| LIT_STR { $$ = mk_atom(yytext); } -| LIT_STR_RAW { $$ = mk_atom(yytext); } -| LIT_BYTE_STR { $$ = mk_atom(yytext); } -| LIT_BYTE_STR_RAW { $$ = mk_atom(yytext); } -| IDENT { $$ = mk_atom(yytext); } -| UNDERSCORE { $$ = mk_atom(yytext); } -| LIFETIME { $$ = mk_atom(yytext); } -| SELF { $$ = mk_atom(yytext); } -| STATIC { $$ = mk_atom(yytext); } -| ABSTRACT { $$ = mk_atom(yytext); } -| ALIGNOF { $$ = mk_atom(yytext); } -| AS { $$ = mk_atom(yytext); } -| BECOME { $$ = mk_atom(yytext); } -| BREAK { $$ = mk_atom(yytext); } -| CATCH { $$ = mk_atom(yytext); } -| CRATE { $$ = mk_atom(yytext); } -| DEFAULT { $$ = mk_atom(yytext); } -| DO { $$ = mk_atom(yytext); } -| ELSE { $$ = mk_atom(yytext); } -| ENUM { $$ = mk_atom(yytext); } -| EXTERN { $$ = mk_atom(yytext); } -| FALSE { $$ = mk_atom(yytext); } -| FINAL { $$ = mk_atom(yytext); } -| FN { $$ = mk_atom(yytext); } -| FOR { $$ = mk_atom(yytext); } -| IF { $$ = mk_atom(yytext); } -| IMPL { $$ = mk_atom(yytext); } -| IN { $$ = mk_atom(yytext); } -| LET { $$ = mk_atom(yytext); } -| LOOP { $$ = mk_atom(yytext); } -| MACRO { $$ = mk_atom(yytext); } -| MATCH { $$ = mk_atom(yytext); } -| MOD { $$ = mk_atom(yytext); } -| MOVE { $$ = mk_atom(yytext); } -| MUT { $$ = mk_atom(yytext); } -| OFFSETOF { $$ = mk_atom(yytext); } -| OVERRIDE { $$ = mk_atom(yytext); } -| PRIV { $$ = mk_atom(yytext); } -| PUB { $$ = mk_atom(yytext); } -| PURE { $$ = mk_atom(yytext); } -| REF { $$ = mk_atom(yytext); } -| RETURN { $$ = mk_atom(yytext); } -| STRUCT { $$ = mk_atom(yytext); } -| SIZEOF { $$ = mk_atom(yytext); } -| SUPER { $$ = mk_atom(yytext); } -| TRUE { $$ = mk_atom(yytext); } -| TRAIT { $$ = mk_atom(yytext); } -| TYPE { $$ = mk_atom(yytext); } -| UNION { $$ = mk_atom(yytext); } -| UNSAFE { $$ = mk_atom(yytext); } -| UNSIZED { $$ = mk_atom(yytext); } -| USE { $$ = mk_atom(yytext); } -| VIRTUAL { $$ = mk_atom(yytext); } -| WHILE { $$ = mk_atom(yytext); } -| YIELD { $$ = mk_atom(yytext); } -| CONTINUE { $$ = mk_atom(yytext); } -| PROC { $$ = mk_atom(yytext); } -| BOX { $$ = mk_atom(yytext); } -| CONST { $$ = mk_atom(yytext); } -| WHERE { $$ = mk_atom(yytext); } -| TYPEOF { $$ = mk_atom(yytext); } -| INNER_DOC_COMMENT { $$ = mk_atom(yytext); } -| OUTER_DOC_COMMENT { $$ = mk_atom(yytext); } -| SHEBANG { $$ = mk_atom(yytext); } -| STATIC_LIFETIME { $$ = mk_atom(yytext); } -| ';' { $$ = mk_atom(yytext); } -| ',' { $$ = mk_atom(yytext); } -| '.' { $$ = mk_atom(yytext); } -| '@' { $$ = mk_atom(yytext); } -| '#' { $$ = mk_atom(yytext); } -| '~' { $$ = mk_atom(yytext); } -| ':' { $$ = mk_atom(yytext); } -| '$' { $$ = mk_atom(yytext); } -| '=' { $$ = mk_atom(yytext); } -| '?' { $$ = mk_atom(yytext); } -| '!' { $$ = mk_atom(yytext); } -| '<' { $$ = mk_atom(yytext); } -| '>' { $$ = mk_atom(yytext); } -| '-' { $$ = mk_atom(yytext); } -| '&' { $$ = mk_atom(yytext); } -| '|' { $$ = mk_atom(yytext); } -| '+' { $$ = mk_atom(yytext); } -| '*' { $$ = mk_atom(yytext); } -| '/' { $$ = mk_atom(yytext); } -| '^' { $$ = mk_atom(yytext); } -| '%' { $$ = mk_atom(yytext); } -; - -token_trees -: %empty { $$ = mk_node("TokenTrees", 0); } -| token_trees token_tree { $$ = ext_node($1, 1, $2); } -; - -token_tree -: delimited_token_trees -| unpaired_token { $$ = mk_node("TTTok", 1, $1); } -; - -delimited_token_trees -: parens_delimited_token_trees -| braces_delimited_token_trees -| brackets_delimited_token_trees -; - -parens_delimited_token_trees -: '(' token_trees ')' -{ - $$ = mk_node("TTDelim", 3, - mk_node("TTTok", 1, mk_atom("(")), - $2, - mk_node("TTTok", 1, mk_atom(")"))); -} -; - -braces_delimited_token_trees -: '{' token_trees '}' -{ - $$ = mk_node("TTDelim", 3, - mk_node("TTTok", 1, mk_atom("{")), - $2, - mk_node("TTTok", 1, mk_atom("}"))); -} -; - -brackets_delimited_token_trees -: '[' token_trees ']' -{ - $$ = mk_node("TTDelim", 3, - mk_node("TTTok", 1, mk_atom("[")), - $2, - mk_node("TTTok", 1, mk_atom("]"))); -} -; diff --git a/src/grammar/raw-string-literal-ambiguity.md b/src/grammar/raw-string-literal-ambiguity.md deleted file mode 100644 index c909f2333148a..0000000000000 --- a/src/grammar/raw-string-literal-ambiguity.md +++ /dev/null @@ -1,64 +0,0 @@ -Rust's lexical grammar is not context-free. Raw string literals are the source -of the problem. Informally, a raw string literal is an `r`, followed by `N` -hashes (where N can be zero), a quote, any characters, then a quote followed -by `N` hashes. Critically, once inside the first pair of quotes, -another quote cannot be followed by `N` consecutive hashes. e.g. -`r###""###"###` is invalid. - -This grammar describes this as best possible: - - R -> 'r' S - S -> '"' B '"' - S -> '#' S '#' - B -> . B - B -> ε - -Where `.` represents any character, and `ε` the empty string. Consider the -string `r#""#"#`. This string is not a valid raw string literal, but can be -accepted as one by the above grammar, using the derivation: - - R : #""#"# - S : ""#" - S : "# - B : # - B : ε - -(Where `T : U` means the rule `T` is applied, and `U` is the remainder of the -string.) The difficulty arises from the fact that it is fundamentally -context-sensitive. In particular, the context needed is the number of hashes. - -To prove that Rust's string literals are not context-free, we will use -the fact that context-free languages are closed under intersection with -regular languages, and the -[pumping lemma for context-free languages](https://en.wikipedia.org/wiki/Pumping_lemma_for_context-free_languages). - -Consider the regular language `R = r#+""#*"#+`. If Rust's raw string literals are -context-free, then their intersection with `R`, `R'`, should also be context-free. -Therefore, to prove that raw string literals are not context-free, -it is sufficient to prove that `R'` is not context-free. - -The language `R'` is `{r#^n""#^m"#^n | m < n}`. - -Assume `R'` *is* context-free. Then `R'` has some pumping length `p > 0` for which -the pumping lemma applies. Consider the following string `s` in `R'`: - -`r#^p""#^{p-1}"#^p` - -e.g. for `p = 2`: `s = r##""#"##` - -Then `s = uvwxy` for some choice of `uvwxy` such that `vx` is non-empty, -`|vwx| < p+1`, and `uv^iwx^iy` is in `R'` for all `i >= 0`. - -Neither `v` nor `x` can contain a `"` or `r`, as the number of these characters -in any string in `R'` is fixed. So `v` and `x` contain only hashes. -Consequently, of the three sequences of hashes, `v` and `x` combined -can only pump two of them. -If we ever choose the central sequence of hashes, then one of the outer sequences -will not grow when we pump, leading to an imbalance between the outer sequences. -Therefore, we must pump both outer sequences of hashes. However, -there are `p+2` characters between these two sequences of hashes, and `|vwx|` must -be less than `p+1`. Therefore we have a contradiction, and `R'` must not be -context-free. - -Since `R'` is not context-free, it follows that the Rust's raw string literals -must not be context-free. diff --git a/src/grammar/testparser.py b/src/grammar/testparser.py deleted file mode 100755 index 4b5a7fb9e10b5..0000000000000 --- a/src/grammar/testparser.py +++ /dev/null @@ -1,66 +0,0 @@ -#!/usr/bin/env python - -# ignore-tidy-linelength - -import sys - -import os -import subprocess -import argparse - -# usage: testparser.py [-h] [-p PARSER [PARSER ...]] -s SOURCE_DIR - -# Parsers should read from stdin and return exit status 0 for a -# successful parse, and nonzero for an unsuccessful parse - -parser = argparse.ArgumentParser() -parser.add_argument('-p', '--parser', nargs='+') -parser.add_argument('-s', '--source-dir', nargs=1, required=True) -args = parser.parse_args(sys.argv[1:]) - -total = 0 -ok = {} -bad = {} -for parser in args.parser: - ok[parser] = 0 - bad[parser] = [] -devnull = open(os.devnull, 'w') -print("\n") - -for base, dirs, files in os.walk(args.source_dir[0]): - for f in filter(lambda p: p.endswith('.rs'), files): - p = os.path.join(base, f) - parse_fail = 'parse-fail' in p - if sys.version_info.major == 3: - lines = open(p, encoding='utf-8').readlines() - else: - lines = open(p).readlines() - if any('ignore-test' in line or 'ignore-lexer-test' in line for line in lines): - continue - total += 1 - for parser in args.parser: - if subprocess.call(parser, stdin=open(p), stderr=subprocess.STDOUT, stdout=devnull) == 0: - if parse_fail: - bad[parser].append(p) - else: - ok[parser] += 1 - else: - if parse_fail: - ok[parser] += 1 - else: - bad[parser].append(p) - parser_stats = ', '.join(['{}: {}'.format(parser, ok[parser]) for parser in args.parser]) - sys.stdout.write("\033[K\r total: {}, {}, scanned {}" - .format(total, os.path.relpath(parser_stats), os.path.relpath(p))) - -devnull.close() - -print("\n") - -for parser in args.parser: - filename = os.path.basename(parser) + '.bad' - print("writing {} files that did not yield the correct result with {} to {}".format(len(bad[parser]), parser, filename)) - with open(filename, "w") as f: - for p in bad[parser]: - f.write(p) - f.write("\n") diff --git a/src/grammar/tokens.h b/src/grammar/tokens.h deleted file mode 100644 index 297e3dc841e87..0000000000000 --- a/src/grammar/tokens.h +++ /dev/null @@ -1,99 +0,0 @@ -enum Token { - SHL = 257, // Parser generators reserve 0-256 for char literals - SHR, - LE, - EQEQ, - NE, - GE, - ANDAND, - OROR, - SHLEQ, - SHREQ, - MINUSEQ, - ANDEQ, - OREQ, - PLUSEQ, - STAREQ, - SLASHEQ, - CARETEQ, - PERCENTEQ, - DOTDOT, - DOTDOTDOT, - MOD_SEP, - LARROW, - RARROW, - FAT_ARROW, - LIT_BYTE, - LIT_CHAR, - LIT_INTEGER, - LIT_FLOAT, - LIT_STR, - LIT_STR_RAW, - LIT_BYTE_STR, - LIT_BYTE_STR_RAW, - IDENT, - UNDERSCORE, - LIFETIME, - - // keywords - SELF, - STATIC, - ABSTRACT, - ALIGNOF, - AS, - BECOME, - BREAK, - CATCH, - CRATE, - DEFAULT, - DO, - ELSE, - ENUM, - EXTERN, - FALSE, - FINAL, - FN, - FOR, - IF, - IMPL, - IN, - LET, - LOOP, - MACRO, - MATCH, - MOD, - MOVE, - MUT, - OFFSETOF, - OVERRIDE, - PRIV, - PUB, - PURE, - REF, - RETURN, - SIZEOF, - STRUCT, - SUPER, - UNION, - TRUE, - TRAIT, - TYPE, - UNSAFE, - UNSIZED, - USE, - VIRTUAL, - WHILE, - YIELD, - CONTINUE, - PROC, - BOX, - CONST, - WHERE, - TYPEOF, - INNER_DOC_COMMENT, - OUTER_DOC_COMMENT, - - SHEBANG, - SHEBANG_LINE, - STATIC_LIFETIME -};