aeb78354be
- Fix determinization (NFA->DFA subset construction) in Automata - Implement RegularAutomata longest-match tokenizer - Implement ContextFreeCompiler: canonical LR(1) tables with %left/%right precedence - Implement ContextFreeAutomata shift/reduce DPDA with AST build - Split regex (RG+CFG) and epsilon transitions in RegularCompiler - Add UnifiedGrammarFormat (header + source): defines the .g grammar syntax and the inline regex syntax via the C++ grammar API, and translates a parsed .g AST into target RE + CFG grammars (bootstrap) - SimpleParser: bootstrap .g grammar files -> RE + LALR tables -> parse input - Fix Map iterator off-by-one (last bucket never visited) - Tests: compile a .g grammar and parse a program to a valid AST
93 lines
1.6 KiB
C++
93 lines
1.6 KiB
C++
|
|
#pragma once
|
|
|
|
#include "SimpleParser.hpp"
|
|
|
|
const char* gGrammar = R"(
|
|
oscript {
|
|
%whitespace "[ \t\r\n]+" ;
|
|
%left '(' ')' ;
|
|
%left '+' '-' ;
|
|
%left '*' '/' ;
|
|
%left '.' '=' ;
|
|
%left '==' '>' '<' '>=' '<=' '!=' '!' ;
|
|
%left ';' ;
|
|
|
|
script : stmts | ;
|
|
|
|
scope : '{' stmts '}' | '{' '}' ;
|
|
|
|
stmts : stmts stmt | stmt ;
|
|
|
|
stmt : stm_var_def_new_type ';'
|
|
| stm_var_def_assign ';'
|
|
| stm_log ';'
|
|
| stm_assign ';'
|
|
| stm_while
|
|
| stm_return ';'
|
|
| stm_break ';'
|
|
| stm_if
|
|
| stm_def_class
|
|
| stm_def_method
|
|
| stm_ignore ';' ;
|
|
|
|
stm_def_method : 'method' id '(' id_list ')' scope ;
|
|
stm_def_class : 'class' id scope ;
|
|
|
|
stm_if : 'if' '(' expr ')' scope
|
|
| 'if' '(' expr ')' scope 'else' scope ;
|
|
|
|
stm_break : 'break' ;
|
|
stm_return : 'return' expr | 'return' ;
|
|
stm_while : 'while' '(' expr ')' scope ;
|
|
stm_var_def_new_type : 'var' id ':' id ;
|
|
stm_var_def_assign : 'var' id '=' expr ;
|
|
stm_log : 'print' expr ;
|
|
stm_assign : expr '=' expr ;
|
|
stm_ignore : expr ;
|
|
|
|
expr_list : expr_list ',' expr ',' | expr | ;
|
|
|
|
id_list : id_list ',' id ',' | id | ;
|
|
|
|
expr : id '(' expr_list ')'
|
|
| expr '.' id '(' expr_list ')'
|
|
| expr '.' id
|
|
| expr '==' expr
|
|
| '!' expr
|
|
| expr '!=' expr
|
|
| expr '>' expr
|
|
| expr '<' expr
|
|
| expr '>=' expr
|
|
| expr '<=' expr
|
|
| expr '+' expr
|
|
| expr '-' expr
|
|
| expr '*' expr
|
|
| expr '/' expr
|
|
| '(' expr ')'
|
|
| boolean
|
|
| integer
|
|
| id ;
|
|
|
|
id : "[a-zA-Z]+" ;
|
|
boolean : "true|false" ;
|
|
integer : "[0-9]+" ;
|
|
}
|
|
)";
|
|
|
|
const char* gSentence = R"(
|
|
method main ( ) {
|
|
var i = 10 ;
|
|
|
|
if ( i == 10 ) {
|
|
while ( i > 0 ) {
|
|
print i ;
|
|
i = i - 1 ;
|
|
}
|
|
} else {
|
|
print i ;
|
|
}
|
|
}
|
|
|
|
main ( ) ;
|
|
)";
|