From 3e60d7f515a919d2514a299aee8596e0d117b03c Mon Sep 17 00:00:00 2001 From: Dayanne Fernandes Date: Sat, 17 Oct 2020 12:01:53 -0300 Subject: [PATCH] inital parser --- .gitignore | 4 +- src/Makefile | 15 + src/README.md | 51 +- src/ast.c | 32 + src/ast.h | 31 + src/build.sh | 5 - src/cppython.lex | 195 ++-- src/cppython.y | 52 + src/{lex.yy.c => lexer.c} | 425 +++---- src/lexer.h | 474 ++++++++ src/main.c | 22 + src/parser.c | 1597 +++++++++++++++++++++++++++ src/parser.h | 83 ++ src/parser.output | 177 +++ src/sym_tab.c | 34 + src/sym_tab.h | 19 + src/tests/{ => lexer}/invalid_1.ppy | 0 src/tests/{ => lexer}/invalid_2.ppy | 0 src/tests/{ => lexer}/valid_1.ppy | 0 src/tests/{ => lexer}/valid_2.ppy | 0 src/tests/parser/invalid_1.ppy | 1 + src/tests/parser/invalid_2.ppy | 2 + src/tests/parser/valid_1.ppy | 1 + src/tests/parser/valid_2.ppy | 1 + 24 files changed, 2814 insertions(+), 407 deletions(-) create mode 100644 src/Makefile create mode 100644 src/ast.c create mode 100644 src/ast.h delete mode 100755 src/build.sh create mode 100644 src/cppython.y rename src/{lex.yy.c => lexer.c} (84%) create mode 100644 src/lexer.h create mode 100644 src/main.c create mode 100644 src/parser.c create mode 100644 src/parser.h create mode 100644 src/parser.output create mode 100644 src/sym_tab.c create mode 100644 src/sym_tab.h rename src/tests/{ => lexer}/invalid_1.ppy (100%) rename src/tests/{ => lexer}/invalid_2.ppy (100%) rename src/tests/{ => lexer}/valid_1.ppy (100%) rename src/tests/{ => lexer}/valid_2.ppy (100%) create mode 100644 src/tests/parser/invalid_1.ppy create mode 100644 src/tests/parser/invalid_2.ppy create mode 100644 src/tests/parser/valid_1.ppy create mode 100644 src/tests/parser/valid_2.ppy diff --git a/.gitignore b/.gitignore index b682d41..790dad5 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1,3 @@ -cppython \ No newline at end of file +cppython +*.tab.* +*.yy.* \ No newline at end of file diff --git a/src/Makefile b/src/Makefile new file mode 100644 index 0000000..d0b775f --- /dev/null +++ b/src/Makefile @@ -0,0 +1,15 @@ +FILES = parser.c lexer.c ast.c sym_tab.c main.c +CFLAGS = -g -Wall -pedantic -x c +CC = gcc + +cppython: $(FILES) ast.h sym_tab.h + $(CC) $(CFLAGS) $(FILES) -o cppython -lfl + +lexer.c: cppython.lex + flex cppython.lex + +parser.c: cppython.y + bison -d -v cppython.y + +clean: + rm -f *.o *~ lexer.c lexer.h parser.c parser.h parser.output cppython diff --git a/src/README.md b/src/README.md index c133f4b..81c33cc 100644 --- a/src/README.md +++ b/src/README.md @@ -3,46 +3,63 @@ ## Requirements - Flex 2.6.4 +- Bison 3.5.1 - GCC 9.3.0 ## Usage ```bash -$ chmod +x build.sh -$ ./build.sh -$ ./cppython tests/valid_1.ppy # for valid test -$ ./cppython tests/incorrect_1.ppy # for invalid test +$ make +$ ./cppython tests/parser/valid_1.ppy # for valid test +$ ./cppython tests/parser/invalid_1.ppy # for invalid test ``` ## Output examples - Valid input 1: - - Commands: ./build.sh && ./cppython tests/valid_1.ppy + - Commands: ./cppython tests/parser/valid_1.ppy - Output: ```bash - CPPython interpreter: + Welcome to CPPython interpreter: + Lexer/parser: - line 1. - line 2. - line 3. + line 1. Token: + + Creating integer expression node: 1 + Token: + Assign expression. + Token: + + Creating integer expression node: 1 + + line 2. + Assign expression. + + Creating binary expression node: 1 + 1 + 1 + + AST created. + + Lexer and parser finished. ``` - Invalid input 2: - - Commands: ./build.sh && ./cppython tests/invalid_1.ppy + - Commands: ./cppython tests/parser/invalid_1.ppy - Output: ```bash - CPPython interpreter: + Welcome to CPPython interpreter: + Lexer/parser: + + line 1. Token: + + Creating integer expression node: 1 - line 1. - line 2. - line 3. - line 4. +#include +#include "ast.h" + +ast_node* create_bin_expr(char *operator, ast_node* left, ast_node* right) { + printf("\nCreating binary expression node: %d %s %d\n", + left->op.integer_expr, operator, right->op.integer_expr); + ast_node* expr = (ast_node*) malloc(sizeof(ast_node)); + expr->op.binary_expr.operator = operator; + expr->op.binary_expr.left = left; + expr->op.binary_expr.right = right; + return expr; +} + +ast_node* create_int_expr(int value) { + printf("\n\nCreating integer expression node: %d\n", value); + ast_node* expr = (ast_node*) malloc(sizeof(ast_node)); + expr->op.integer_expr = value; + return expr; +} + +void create_ast(ast_node* expression) { + ast* ast_obj = (ast*) malloc(sizeof(ast)); + ast_obj->head = expression; + ast_obj->next = NULL; + printf("\nAST created.\n"); +} + +ast_node* show(ast_node* expression) { + printf("\nAssign expression.\n"); + return expression; +} \ No newline at end of file diff --git a/src/ast.h b/src/ast.h new file mode 100644 index 0000000..c56ff7f --- /dev/null +++ b/src/ast.h @@ -0,0 +1,31 @@ +#ifndef __AST_H__ +#define __AST_H__ + +int line, column; + +typedef struct exp { + union { + int integer_expr; + char *string_expr; + char *variable_expr; + struct { + char *operator; + struct exp* left; + struct exp* right; + } binary_expr; + } op; +} ast_node; + +typedef struct expr_list { + ast_node* head; + struct expr_list* next; +} ast; + +void create_ast(ast_node* expression); +ast_node* show(ast_node* expression); +ast_node* create_int_expr(int value); +ast_node* create_bin_expr(char *operator, ast_node* left, ast_node* right); + +void handle_token(int token); + +#endif // __AST_H__ \ No newline at end of file diff --git a/src/build.sh b/src/build.sh deleted file mode 100755 index a8bc7b4..0000000 --- a/src/build.sh +++ /dev/null @@ -1,5 +0,0 @@ -#!/bin/bash - -rm -f cppython lex.yy.c -flex cppython.lex -gcc lex.yy.c -lfl -o cppython \ No newline at end of file diff --git a/src/cppython.lex b/src/cppython.lex index e7659ea..ee56e15 100644 --- a/src/cppython.lex +++ b/src/cppython.lex @@ -2,74 +2,44 @@ %{ #include - #include "uthash.h" + #include "sym_tab.h" + #include "ast.h" + #include "parser.h" enum TOKENS{ - ERROR=1, - NEWLINE, - WHITESPACE, - ID, - KEYWORD, - INTEGER, - FLOAT, - OPERATOR, - DELIMITER, - BOOLEAN, - BOOLEAN_OP, - STRING, - COMMENT + ERROR_TOK=1, + NEWLINE_TOK, + WHITESPACE_TOK, + ID_TOK, + KEYWORD_TOK, + FLOAT_TOK, + DELIMITER_TOK, + BOOLEAN_TOK, + BOOLEAN_OP_TOK, + STRING_TOK, + COMMENT_TOK, + INTEGER_TOK, + ADD_TOK, + SUB_TOK, + MULT_TOK, + DIV_TOK }; - - int line, column; - - struct word { - int key; - char name[50]; - UT_hash_handle hh; /* makes this structure hashable */ - }; - - struct word *symbol_table = NULL; - - void add_word(int key, char *name) { - struct word *s; - HASH_FIND_INT(symbol_table, &key, s); - if (s == NULL) { - s = (struct word *) malloc(sizeof *s); - s->key = key; - HASH_ADD_INT(symbol_table, key, s); - } - strcpy(s->name, name); - } - - struct word *find_word(int word_key) { - struct word *s; - - HASH_FIND_INT(symbol_table, &word_key, s); - return s; - } - - void delete_word(struct word *s) { - HASH_DEL(symbol_table, s); - free(s); - } - - void delete_all() { - struct word *cur_word, *tmp; - - HASH_ITER(hh, symbol_table, cur_word, tmp) { - HASH_DEL(symbol_table, cur_word); - free(cur_word); - } - } - %} +%option outfile="lexer.c" header-file="lexer.h" +%option nounput +%option noinput + /* regex and token definition */ DIGIT [0-9] NDIGIT [1-9] LETTER [a-zA-Z] -OPERATOR ("-"|"+"|"*"|"/") +SUB ("-") +ADD ("+") +MULT ("*") +DIV ("/") +OPERATOR (ADD|SUB|MULT|DIV) BOOLEAN_OP ("=="|"<="|">="|"!="|"<"|">"|"~"|"|"|"&"|"and"|"or"|"not") DELIMITER ("="|"("|")"|"["|"]"|";"|","|"."|":") BOOLEAN ("True"|"False") @@ -86,31 +56,34 @@ NUMBER ({INTEGER}|{FLOAT}) /* reserved keywords */ -("input"|"print"|"if"|"elif"|"else"|"return"|"def"|"for"|"while") return KEYWORD; +("input"|"print"|"if"|"elif"|"else"|"return"|"def"|"for"|"while") ; - /* arithmetics expressions */ + /* arithmetic expressions */ -{INTEGER} return INTEGER; -{FLOAT} return FLOAT; -{OPERATOR} return OPERATOR; -{DELIMITER} return DELIMITER; +{INTEGER} { handle_token(INTEGER_TOK); return INTEGER; }; +{FLOAT} ; +{SUB} { handle_token(SUB_TOK); return SUB; }; +{ADD} { handle_token(ADD_TOK); return ADD; }; +{MULT} { handle_token(MULT_TOK); return MULT; }; +{DIV} { handle_token(DIV_TOK); return DIV; }; +{DELIMITER} ; /* conditional and booleans expressions */ -{BOOLEAN} return BOOLEAN; -{BOOLEAN_OP} return BOOLEAN_OP; +{BOOLEAN} ; +{BOOLEAN_OP} ; /* structure helpers */ -#.*{NEWLINE} return COMMENT; -{STRING} return STRING; +#.*{NEWLINE} ; +{STRING} ; /* general */ -{NEWLINE} return NEWLINE; -{WHITESPACE} return WHITESPACE; -{VAR} return ID; -. return ERROR; /* any character but newline */ +{NEWLINE} { handle_token(NEWLINE_TOK); }; +{WHITESPACE} ; +{VAR} ; +. { handle_token(ERROR_TOK); }; /* any character but newline */ %% @@ -120,69 +93,39 @@ NUMBER ({INTEGER}|{FLOAT}) - Output: */ -void switcher(int token) { +void handle_token(int token) { switch (token) { - case ERROR: - printf("\nLexerError: line %d, column %d, token '%s' is not recognized\n", line, column, yytext); - break; - case NEWLINE: - line += 1; - column = 0; // reset column index - printf("\nline %d. ", line); - break; - case WHITESPACE: - break; // ignore - case ID: ; - int cur_key = HASH_COUNT(symbol_table) + 1; - add_word(cur_key, yytext); - printf(" ", cur_key); + case INTEGER_TOK: + printf("Token: ", yytext); + yylval.value = atoi(yytext); break; - case KEYWORD: - printf(" ", yytext); + case SUB_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case STRING: - printf(" ", yytext); + case ADD_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case DELIMITER: - printf(" ", yytext); + case MULT_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case OPERATOR: - printf(" ", yytext); + case DIV_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case BOOLEAN: - printf(" ", yytext); - break; - case BOOLEAN_OP: - printf(" ", yytext); - break; - case INTEGER: - printf(" ", yytext); - break; - case FLOAT: - printf(" ", yytext); - break; - case COMMENT: ; - char *comment = yytext; - comment[strlen(comment) - 1] = 0; - printf(" ", comment); + case NEWLINE_TOK: line += 1; column = 0; // reset column index printf("\nline %d. ", line); break; + case ERROR_TOK: + printf("\nLexerError: line %d, column %d, token '%s' is not recognized\n", + line, column, yytext); + exit(1); default: - printf("\nUndefined error.\n"); - } + break; // ignore + } column += strlen(yytext); -} - -int main (int argc, char *argv[]) { - line = column = 1; - printf("CPPython interpreter:\n"); - yyin = fopen(argv[1], "r"); - int token; - printf("\nline %d. ", line); - while ((token = yylex()) != 0) switcher(token); - fclose(yyin); - printf("\n"); - return 0; -} +} \ No newline at end of file diff --git a/src/cppython.y b/src/cppython.y new file mode 100644 index 0000000..38c8e9e --- /dev/null +++ b/src/cppython.y @@ -0,0 +1,52 @@ +%{ + #include + #include "ast.h" + + int yylex(); + void yyerror(char *s); +%} + +%output "parser.c" +%defines "parser.h" +%define lr.type ielr + +%start input + +%union { + int value; + char* op; + ast_node* expression; +} + +%token ADD SUB MULT DIV +%token INTEGER + +%left ADD SUB +%left MULT DIV + +%type expr term factor + +%% + +input : /* empty */ + | expr { create_ast($1); } + ; + +expr : term[L] ADD[C] term[R] { $$ = create_bin_expr($C, $L, $R); } + | term[L] SUB[C] term[R] { $$ = create_bin_expr($C, $L, $R); } + | term[U] { $$ = show($U); } + ; + +term : factor[L] MULT[C] factor[R] { $$ = create_bin_expr($C, $L, $R); } + | factor[L] DIV[C] factor[R] { $$ = create_bin_expr($C, $L, $R); } + | factor[U] { $$ = show($U); } + ; + +factor : INTEGER[U] { $$ = create_int_expr($U); } + ; + +%% + +void yyerror(char *s) { + printf("%s\n", s); +} diff --git a/src/lex.yy.c b/src/lexer.c similarity index 84% rename from src/lex.yy.c rename to src/lexer.c index b2756b6..713724f 100644 --- a/src/lex.yy.c +++ b/src/lexer.c @@ -1,5 +1,6 @@ +#line 2 "lexer.c" -#line 3 "lex.yy.c" +#line 4 "lexer.c" #define YY_INT_ALIGNED short int @@ -351,8 +352,8 @@ static void yynoreturn yy_fatal_error ( const char* msg ); (yy_hold_char) = *yy_cp; \ *yy_cp = '\0'; \ (yy_c_buf_p) = yy_cp; -#define YY_NUM_RULES 14 -#define YY_END_OF_BUFFER 15 +#define YY_NUM_RULES 17 +#define YY_END_OF_BUFFER 18 /* This struct is not used in this scanner, but its presence is necessary. */ struct yy_trans_info @@ -360,16 +361,16 @@ struct yy_trans_info flex_int32_t yy_verify; flex_int32_t yy_nxt; }; -static const flex_int16_t yy_accept[78] = +static const flex_int16_t yy_accept[80] = { 0, - 0, 0, 15, 13, 11, 10, 13, 13, 13, 7, - 13, 5, 4, 4, 2, 2, 7, 5, 7, 12, - 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, - 12, 12, 12, 13, 11, 7, 0, 9, 0, 8, - 0, 9, 0, 3, 0, 2, 12, 12, 12, 12, - 12, 12, 12, 1, 12, 12, 7, 12, 12, 12, - 3, 12, 12, 12, 12, 12, 12, 12, 12, 12, - 6, 12, 12, 12, 12, 12, 0 + 0, 0, 18, 16, 14, 13, 16, 16, 16, 10, + 16, 8, 6, 5, 4, 7, 2, 2, 10, 8, + 10, 15, 15, 15, 15, 15, 15, 15, 15, 15, + 15, 15, 15, 15, 15, 16, 14, 10, 0, 12, + 0, 11, 0, 12, 0, 3, 0, 2, 15, 15, + 15, 15, 15, 15, 15, 1, 15, 15, 10, 15, + 15, 15, 3, 15, 15, 15, 15, 15, 15, 15, + 15, 15, 9, 15, 15, 15, 15, 15, 0 } ; static const YY_CHAR yy_ec[256] = @@ -413,53 +414,53 @@ static const YY_CHAR yy_meta[49] = 3, 3, 3, 3, 3, 1, 1, 1 } ; -static const flex_int16_t yy_base[82] = +static const flex_int16_t yy_base[84] = { 0, 0, 0, 130, 131, 127, 131, 106, 122, 123, 131, - 117, 131, 131, 109, 34, 38, 101, 100, 99, 0, - 105, 88, 35, 80, 84, 79, 76, 20, 75, 72, - 71, 78, 75, 94, 106, 131, 102, 101, 102, 131, - 96, 95, 42, 131, 46, 50, 0, 65, 57, 68, - 65, 30, 57, 0, 57, 53, 0, 59, 51, 57, - 52, 50, 58, 56, 56, 44, 49, 42, 47, 45, - 0, 32, 31, 32, 38, 24, 131, 76, 79, 82, - 54 + 117, 131, 131, 109, 131, 131, 34, 38, 101, 100, + 99, 0, 105, 88, 35, 80, 84, 79, 76, 20, + 75, 72, 71, 78, 75, 94, 106, 131, 102, 101, + 102, 131, 96, 95, 42, 131, 46, 50, 0, 65, + 57, 68, 65, 30, 57, 0, 57, 53, 0, 59, + 51, 57, 52, 50, 58, 56, 56, 44, 49, 42, + 47, 45, 0, 32, 31, 32, 38, 24, 131, 76, + 79, 82, 54 } ; -static const flex_int16_t yy_def[82] = +static const flex_int16_t yy_def[84] = { 0, - 77, 1, 77, 77, 77, 77, 77, 78, 79, 77, - 80, 77, 77, 77, 77, 77, 77, 77, 77, 81, - 81, 81, 81, 81, 81, 81, 81, 81, 81, 81, - 81, 81, 81, 77, 77, 77, 78, 78, 79, 77, - 80, 80, 77, 77, 77, 77, 81, 81, 81, 81, - 81, 81, 81, 81, 81, 81, 81, 81, 81, 81, - 77, 81, 81, 81, 81, 81, 81, 81, 81, 81, - 81, 81, 81, 81, 81, 81, 0, 77, 77, 77, - 77 + 79, 1, 79, 79, 79, 79, 79, 80, 81, 79, + 82, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 83, 83, 83, 83, 83, 83, 83, 83, 83, + 83, 83, 83, 83, 83, 79, 79, 79, 80, 80, + 81, 79, 82, 82, 79, 79, 79, 79, 83, 83, + 83, 83, 83, 83, 83, 83, 83, 83, 83, 83, + 83, 83, 79, 83, 83, 83, 83, 83, 83, 83, + 83, 83, 83, 83, 83, 83, 83, 83, 0, 79, + 79, 79, 79 } ; static const flex_int16_t yy_nxt[180] = { 0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 12, - 13, 14, 12, 13, 12, 13, 15, 16, 12, 12, - 17, 18, 19, 20, 21, 22, 23, 12, 12, 20, - 24, 25, 26, 27, 20, 28, 20, 29, 30, 31, - 32, 20, 20, 20, 33, 34, 10, 10, 44, 43, - 45, 45, 44, 54, 46, 46, 47, 55, 61, 61, - 44, 54, 45, 45, 44, 64, 46, 46, 61, 61, - 54, 65, 76, 54, 54, 49, 37, 71, 37, 39, - 39, 39, 41, 75, 41, 74, 73, 72, 54, 54, - 71, 70, 69, 68, 67, 57, 66, 54, 54, 57, - - 63, 62, 42, 42, 40, 38, 38, 35, 43, 60, - 59, 58, 57, 56, 53, 52, 51, 50, 48, 43, - 36, 36, 36, 43, 42, 40, 38, 36, 35, 77, - 3, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77 + 13, 14, 12, 15, 12, 16, 17, 18, 12, 12, + 19, 20, 21, 22, 23, 24, 25, 12, 12, 22, + 26, 27, 28, 29, 22, 30, 22, 31, 32, 33, + 34, 22, 22, 22, 35, 36, 10, 10, 46, 45, + 47, 47, 46, 56, 48, 48, 49, 57, 63, 63, + 46, 56, 47, 47, 46, 66, 48, 48, 63, 63, + 56, 67, 78, 56, 56, 51, 39, 73, 39, 41, + 41, 41, 43, 77, 43, 76, 75, 74, 56, 56, + 73, 72, 71, 70, 69, 59, 68, 56, 56, 59, + + 65, 64, 44, 44, 42, 40, 40, 37, 45, 62, + 61, 60, 59, 58, 55, 54, 53, 52, 50, 45, + 38, 38, 38, 45, 44, 42, 40, 38, 37, 79, + 3, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79 } ; static const flex_int16_t yy_chk[180] = @@ -468,21 +469,21 @@ static const flex_int16_t yy_chk[180] = 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1, 1, 1, 1, 1, 15, 23, - 15, 15, 16, 28, 16, 16, 81, 28, 43, 43, - 45, 76, 45, 45, 46, 52, 46, 46, 61, 61, - 75, 52, 74, 73, 72, 23, 78, 70, 78, 79, - 79, 79, 80, 69, 80, 68, 67, 66, 65, 64, - 63, 62, 60, 59, 58, 56, 55, 53, 51, 50, - - 49, 48, 42, 41, 39, 38, 37, 35, 34, 33, - 32, 31, 30, 29, 27, 26, 25, 24, 22, 21, - 19, 18, 17, 14, 11, 9, 8, 7, 5, 3, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, - 77, 77, 77, 77, 77, 77, 77, 77, 77 + 1, 1, 1, 1, 1, 1, 1, 1, 17, 25, + 17, 17, 18, 30, 18, 18, 83, 30, 45, 45, + 47, 78, 47, 47, 48, 54, 48, 48, 63, 63, + 77, 54, 76, 75, 74, 25, 80, 72, 80, 81, + 81, 81, 82, 71, 82, 70, 69, 68, 67, 66, + 65, 64, 62, 61, 60, 58, 57, 55, 53, 52, + + 51, 50, 44, 43, 41, 40, 39, 37, 36, 35, + 34, 33, 32, 31, 29, 28, 27, 26, 24, 23, + 21, 20, 19, 14, 11, 9, 8, 7, 5, 3, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, + 79, 79, 79, 79, 79, 79, 79, 79, 79 } ; static yy_state_type yy_last_accepting_state; @@ -503,70 +504,33 @@ char *yytext; /* tokens mapping */ #line 4 "cppython.lex" #include - #include "uthash.h" + #include "sym_tab.h" + #include "ast.h" + #include "parser.h" enum TOKENS{ - ERROR=1, - NEWLINE, - WHITESPACE, - ID, - KEYWORD, - INTEGER, - FLOAT, - OPERATOR, - DELIMITER, - BOOLEAN, - BOOLEAN_OP, - STRING, - COMMENT + ERROR_TOK=1, + NEWLINE_TOK, + WHITESPACE_TOK, + ID_TOK, + KEYWORD_TOK, + FLOAT_TOK, + DELIMITER_TOK, + BOOLEAN_TOK, + BOOLEAN_OP_TOK, + STRING_TOK, + COMMENT_TOK, + INTEGER_TOK, + ADD_TOK, + SUB_TOK, + MULT_TOK, + DIV_TOK }; - - int line, column; - - struct word { - int key; - char name[50]; - UT_hash_handle hh; /* makes this structure hashable */ - }; - - struct word *symbol_table = NULL; - - void add_word(int key, char *name) { - struct word *s; - HASH_FIND_INT(symbol_table, &key, s); - if (s == NULL) { - s = (struct word *) malloc(sizeof *s); - s->key = key; - HASH_ADD_INT(symbol_table, key, s); - } - strcpy(s->name, name); - } - - struct word *find_word(int word_key) { - struct word *s; - - HASH_FIND_INT(symbol_table, &word_key, s); - return s; - } - - void delete_word(struct word *s) { - HASH_DEL(symbol_table, s); - free(s); - } - - void delete_all() { - struct word *cur_word, *tmp; - - HASH_ITER(hh, symbol_table, cur_word, tmp) { - HASH_DEL(symbol_table, cur_word); - free(cur_word); - } - } - -#line 567 "lex.yy.c" -#line 68 "cppython.lex" +#line 530 "lexer.c" +#define YY_NO_INPUT 1 +#line 34 "cppython.lex" /* regex and token definition */ -#line 570 "lex.yy.c" +#line 534 "lexer.c" #define INITIAL 0 @@ -627,8 +591,6 @@ extern int yywrap ( void ); #ifndef YY_NO_UNPUT - static void yyunput ( int c, char *buf_ptr ); - #endif #ifndef yytext_ptr @@ -783,12 +745,12 @@ YY_DECL } { -#line 86 "cppython.lex" +#line 56 "cppython.lex" /* reserved keywords */ -#line 792 "lex.yy.c" +#line 754 "lexer.c" while ( /*CONSTCOND*/1 ) /* loops until end-of-file is reached */ { @@ -815,7 +777,7 @@ YY_DECL while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state ) { yy_current_state = (int) yy_def[yy_current_state]; - if ( yy_current_state >= 78 ) + if ( yy_current_state >= 80 ) yy_c = yy_meta[yy_c]; } yy_current_state = yy_nxt[yy_base[yy_current_state] + yy_c]; @@ -847,81 +809,96 @@ YY_DECL case 1: YY_RULE_SETUP -#line 90 "cppython.lex" -return KEYWORD; +#line 60 "cppython.lex" +; YY_BREAK -/* arithmetics expressions */ +/* arithmetic expressions */ case 2: YY_RULE_SETUP -#line 94 "cppython.lex" -return INTEGER; +#line 64 "cppython.lex" +{ handle_token(INTEGER_TOK); return INTEGER; }; YY_BREAK case 3: YY_RULE_SETUP -#line 95 "cppython.lex" -return FLOAT; +#line 65 "cppython.lex" +; YY_BREAK case 4: YY_RULE_SETUP -#line 96 "cppython.lex" -return OPERATOR; +#line 66 "cppython.lex" +{ handle_token(SUB_TOK); return SUB; }; YY_BREAK case 5: YY_RULE_SETUP -#line 97 "cppython.lex" -return DELIMITER; +#line 67 "cppython.lex" +{ handle_token(ADD_TOK); return ADD; }; YY_BREAK -/* conditional and booleans expressions */ case 6: YY_RULE_SETUP -#line 101 "cppython.lex" -return BOOLEAN; +#line 68 "cppython.lex" +{ handle_token(MULT_TOK); return MULT; }; YY_BREAK case 7: YY_RULE_SETUP -#line 102 "cppython.lex" -return BOOLEAN_OP; +#line 69 "cppython.lex" +{ handle_token(DIV_TOK); return DIV; }; YY_BREAK -/* structure helpers */ case 8: -/* rule 8 can match eol */ YY_RULE_SETUP -#line 106 "cppython.lex" -return COMMENT; +#line 70 "cppython.lex" +; YY_BREAK +/* conditional and booleans expressions */ case 9: YY_RULE_SETUP -#line 107 "cppython.lex" -return STRING; +#line 74 "cppython.lex" +; YY_BREAK -/* general */ case 10: -/* rule 10 can match eol */ YY_RULE_SETUP -#line 111 "cppython.lex" -return NEWLINE; +#line 75 "cppython.lex" +; YY_BREAK +/* structure helpers */ case 11: +/* rule 11 can match eol */ YY_RULE_SETUP -#line 112 "cppython.lex" -return WHITESPACE; +#line 79 "cppython.lex" +; YY_BREAK case 12: YY_RULE_SETUP -#line 113 "cppython.lex" -return ID; +#line 80 "cppython.lex" +; YY_BREAK +/* general */ case 13: +/* rule 13 can match eol */ YY_RULE_SETUP -#line 114 "cppython.lex" -return ERROR; /* any character but newline */ +#line 84 "cppython.lex" +{ handle_token(NEWLINE_TOK); }; YY_BREAK case 14: YY_RULE_SETUP -#line 116 "cppython.lex" +#line 85 "cppython.lex" +; + YY_BREAK +case 15: +YY_RULE_SETUP +#line 86 "cppython.lex" +; + YY_BREAK +case 16: +YY_RULE_SETUP +#line 87 "cppython.lex" +{ handle_token(ERROR_TOK); }; /* any character but newline */ + YY_BREAK +case 17: +YY_RULE_SETUP +#line 89 "cppython.lex" ECHO; YY_BREAK -#line 925 "lex.yy.c" +#line 902 "lexer.c" case YY_STATE_EOF(INITIAL): yyterminate(); @@ -1218,7 +1195,7 @@ static int yy_get_next_buffer (void) while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state ) { yy_current_state = (int) yy_def[yy_current_state]; - if ( yy_current_state >= 78 ) + if ( yy_current_state >= 80 ) yy_c = yy_meta[yy_c]; } yy_current_state = yy_nxt[yy_base[yy_current_state] + yy_c]; @@ -1246,54 +1223,17 @@ static int yy_get_next_buffer (void) while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state ) { yy_current_state = (int) yy_def[yy_current_state]; - if ( yy_current_state >= 78 ) + if ( yy_current_state >= 80 ) yy_c = yy_meta[yy_c]; } yy_current_state = yy_nxt[yy_base[yy_current_state] + yy_c]; - yy_is_jam = (yy_current_state == 77); + yy_is_jam = (yy_current_state == 79); return yy_is_jam ? 0 : yy_current_state; } #ifndef YY_NO_UNPUT - static void yyunput (int c, char * yy_bp ) -{ - char *yy_cp; - - yy_cp = (yy_c_buf_p); - - /* undo effects of setting up yytext */ - *yy_cp = (yy_hold_char); - - if ( yy_cp < YY_CURRENT_BUFFER_LVALUE->yy_ch_buf + 2 ) - { /* need to shift things up to make room */ - /* +2 for EOB chars. */ - int number_to_move = (yy_n_chars) + 2; - char *dest = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[ - YY_CURRENT_BUFFER_LVALUE->yy_buf_size + 2]; - char *source = - &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]; - - while ( source > YY_CURRENT_BUFFER_LVALUE->yy_ch_buf ) - *--dest = *--source; - - yy_cp += (int) (dest - source); - yy_bp += (int) (dest - source); - YY_CURRENT_BUFFER_LVALUE->yy_n_chars = - (yy_n_chars) = (int) YY_CURRENT_BUFFER_LVALUE->yy_buf_size; - - if ( yy_cp < YY_CURRENT_BUFFER_LVALUE->yy_ch_buf + 2 ) - YY_FATAL_ERROR( "flex scanner push-back overflow" ); - } - - *--yy_cp = (char) c; - - (yytext_ptr) = yy_bp; - (yy_hold_char) = *yy_cp; - (yy_c_buf_p) = yy_cp; -} - #endif #ifndef YY_NO_INPUT @@ -1926,7 +1866,7 @@ void yyfree (void * ptr ) #define YYTABLES_NAME "yytables" -#line 116 "cppython.lex" +#line 89 "cppython.lex" /* @@ -1935,70 +1875,39 @@ void yyfree (void * ptr ) - Output: */ -void switcher(int token) { +void handle_token(int token) { switch (token) { - case ERROR: - printf("\nLexerError: line %d, column %d, token '%s' is not recognized\n", line, column, yytext); + case INTEGER_TOK: + printf("Token: ", yytext); + yylval.value = atoi(yytext); break; - case NEWLINE: - line += 1; - column = 0; // reset column index - printf("\nline %d. ", line); - break; - case WHITESPACE: - break; // ignore - case ID: ; - int cur_key = HASH_COUNT(symbol_table) + 1; - add_word(cur_key, yytext); - printf(" ", cur_key); - break; - case KEYWORD: - printf(" ", yytext); - break; - case STRING: - printf(" ", yytext); - break; - case DELIMITER: - printf(" ", yytext); + case SUB_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case OPERATOR: - printf(" ", yytext); + case ADD_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case BOOLEAN: - printf(" ", yytext); + case MULT_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case BOOLEAN_OP: - printf(" ", yytext); + case DIV_TOK: + printf("Token: ", yytext); + yylval.op = yytext; break; - case INTEGER: - printf(" ", yytext); - break; - case FLOAT: - printf(" ", yytext); - break; - case COMMENT: ; - char *comment = yytext; - comment[strlen(comment) - 1] = 0; - printf(" ", comment); + case NEWLINE_TOK: line += 1; column = 0; // reset column index printf("\nline %d. ", line); break; + case ERROR_TOK: + printf("\nLexerError: line %d, column %d, token '%s' is not recognized\n", + line, column, yytext); + exit(1); default: - printf("\nUndefined error.\n"); - } + break; // ignore + } column += strlen(yytext); } - -int main (int argc, char *argv[]) { - line = column = 1; - printf("CPPython interpreter:\n"); - yyin = fopen(argv[1], "r"); - int token; - printf("\nline %d. ", line); - while ((token = yylex()) != 0) switcher(token); - fclose(yyin); - printf("\n"); - return 0; -} - diff --git a/src/lexer.h b/src/lexer.h new file mode 100644 index 0000000..c2d5b6b --- /dev/null +++ b/src/lexer.h @@ -0,0 +1,474 @@ +#ifndef yyHEADER_H +#define yyHEADER_H 1 +#define yyIN_HEADER 1 + +#line 6 "lexer.h" + +#line 8 "lexer.h" + +#define YY_INT_ALIGNED short int + +/* A lexical scanner generated by flex */ + +#define FLEX_SCANNER +#define YY_FLEX_MAJOR_VERSION 2 +#define YY_FLEX_MINOR_VERSION 6 +#define YY_FLEX_SUBMINOR_VERSION 4 +#if YY_FLEX_SUBMINOR_VERSION > 0 +#define FLEX_BETA +#endif + +/* First, we deal with platform-specific or compiler-specific issues. */ + +/* begin standard C headers. */ +#include +#include +#include +#include + +/* end standard C headers. */ + +/* flex integer type definitions */ + +#ifndef FLEXINT_H +#define FLEXINT_H + +/* C99 systems have . Non-C99 systems may or may not. */ + +#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + +/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h, + * if you want the limit (max/min) macros for int types. + */ +#ifndef __STDC_LIMIT_MACROS +#define __STDC_LIMIT_MACROS 1 +#endif + +#include +typedef int8_t flex_int8_t; +typedef uint8_t flex_uint8_t; +typedef int16_t flex_int16_t; +typedef uint16_t flex_uint16_t; +typedef int32_t flex_int32_t; +typedef uint32_t flex_uint32_t; +#else +typedef signed char flex_int8_t; +typedef short int flex_int16_t; +typedef int flex_int32_t; +typedef unsigned char flex_uint8_t; +typedef unsigned short int flex_uint16_t; +typedef unsigned int flex_uint32_t; + +/* Limits of integral types. */ +#ifndef INT8_MIN +#define INT8_MIN (-128) +#endif +#ifndef INT16_MIN +#define INT16_MIN (-32767-1) +#endif +#ifndef INT32_MIN +#define INT32_MIN (-2147483647-1) +#endif +#ifndef INT8_MAX +#define INT8_MAX (127) +#endif +#ifndef INT16_MAX +#define INT16_MAX (32767) +#endif +#ifndef INT32_MAX +#define INT32_MAX (2147483647) +#endif +#ifndef UINT8_MAX +#define UINT8_MAX (255U) +#endif +#ifndef UINT16_MAX +#define UINT16_MAX (65535U) +#endif +#ifndef UINT32_MAX +#define UINT32_MAX (4294967295U) +#endif + +#ifndef SIZE_MAX +#define SIZE_MAX (~(size_t)0) +#endif + +#endif /* ! C99 */ + +#endif /* ! FLEXINT_H */ + +/* begin standard C++ headers. */ + +/* TODO: this is always defined, so inline it */ +#define yyconst const + +#if defined(__GNUC__) && __GNUC__ >= 3 +#define yynoreturn __attribute__((__noreturn__)) +#else +#define yynoreturn +#endif + +/* Size of default input buffer. */ +#ifndef YY_BUF_SIZE +#ifdef __ia64__ +/* On IA-64, the buffer size is 16k, not 8k. + * Moreover, YY_BUF_SIZE is 2*YY_READ_BUF_SIZE in the general case. + * Ditto for the __ia64__ case accordingly. + */ +#define YY_BUF_SIZE 32768 +#else +#define YY_BUF_SIZE 16384 +#endif /* __ia64__ */ +#endif + +#ifndef YY_TYPEDEF_YY_BUFFER_STATE +#define YY_TYPEDEF_YY_BUFFER_STATE +typedef struct yy_buffer_state *YY_BUFFER_STATE; +#endif + +#ifndef YY_TYPEDEF_YY_SIZE_T +#define YY_TYPEDEF_YY_SIZE_T +typedef size_t yy_size_t; +#endif + +extern int yyleng; + +extern FILE *yyin, *yyout; + +#ifndef YY_STRUCT_YY_BUFFER_STATE +#define YY_STRUCT_YY_BUFFER_STATE +struct yy_buffer_state + { + FILE *yy_input_file; + + char *yy_ch_buf; /* input buffer */ + char *yy_buf_pos; /* current position in input buffer */ + + /* Size of input buffer in bytes, not including room for EOB + * characters. + */ + int yy_buf_size; + + /* Number of characters read into yy_ch_buf, not including EOB + * characters. + */ + int yy_n_chars; + + /* Whether we "own" the buffer - i.e., we know we created it, + * and can realloc() it to grow it, and should free() it to + * delete it. + */ + int yy_is_our_buffer; + + /* Whether this is an "interactive" input source; if so, and + * if we're using stdio for input, then we want to use getc() + * instead of fread(), to make sure we stop fetching input after + * each newline. + */ + int yy_is_interactive; + + /* Whether we're considered to be at the beginning of a line. + * If so, '^' rules will be active on the next match, otherwise + * not. + */ + int yy_at_bol; + + int yy_bs_lineno; /**< The line count. */ + int yy_bs_column; /**< The column count. */ + + /* Whether to try to fill the input buffer when we reach the + * end of it. + */ + int yy_fill_buffer; + + int yy_buffer_status; + + }; +#endif /* !YY_STRUCT_YY_BUFFER_STATE */ + +void yyrestart ( FILE *input_file ); +void yy_switch_to_buffer ( YY_BUFFER_STATE new_buffer ); +YY_BUFFER_STATE yy_create_buffer ( FILE *file, int size ); +void yy_delete_buffer ( YY_BUFFER_STATE b ); +void yy_flush_buffer ( YY_BUFFER_STATE b ); +void yypush_buffer_state ( YY_BUFFER_STATE new_buffer ); +void yypop_buffer_state ( void ); + +YY_BUFFER_STATE yy_scan_buffer ( char *base, yy_size_t size ); +YY_BUFFER_STATE yy_scan_string ( const char *yy_str ); +YY_BUFFER_STATE yy_scan_bytes ( const char *bytes, int len ); + +void *yyalloc ( yy_size_t ); +void *yyrealloc ( void *, yy_size_t ); +void yyfree ( void * ); + +/* Begin user sect3 */ + +extern int yylineno; + +extern char *yytext; +#ifdef yytext_ptr +#undef yytext_ptr +#endif +#define yytext_ptr yytext + +#ifdef YY_HEADER_EXPORT_START_CONDITIONS +#define INITIAL 0 + +#endif + +#ifndef YY_NO_UNISTD_H +/* Special case for "unistd.h", since it is non-ANSI. We include it way + * down here because we want the user's section 1 to have been scanned first. + * The user has a chance to override it with an option. + */ +#include +#endif + +#ifndef YY_EXTRA_TYPE +#define YY_EXTRA_TYPE void * +#endif + +/* Accessor methods to globals. + These are made visible to non-reentrant scanners for convenience. */ + +int yylex_destroy ( void ); + +int yyget_debug ( void ); + +void yyset_debug ( int debug_flag ); + +YY_EXTRA_TYPE yyget_extra ( void ); + +void yyset_extra ( YY_EXTRA_TYPE user_defined ); + +FILE *yyget_in ( void ); + +void yyset_in ( FILE * _in_str ); + +FILE *yyget_out ( void ); + +void yyset_out ( FILE * _out_str ); + + int yyget_leng ( void ); + +char *yyget_text ( void ); + +int yyget_lineno ( void ); + +void yyset_lineno ( int _line_number ); + +/* Macros after this point can all be overridden by user definitions in + * section 1. + */ + +#ifndef YY_SKIP_YYWRAP +#ifdef __cplusplus +extern "C" int yywrap ( void ); +#else +extern int yywrap ( void ); +#endif +#endif + +#ifndef yytext_ptr +static void yy_flex_strncpy ( char *, const char *, int ); +#endif + +#ifdef YY_NEED_STRLEN +static int yy_flex_strlen ( const char * ); +#endif + +#ifndef YY_NO_INPUT + +#endif + +/* Amount of stuff to slurp up with each read. */ +#ifndef YY_READ_BUF_SIZE +#ifdef __ia64__ +/* On IA-64, the buffer size is 16k, not 8k */ +#define YY_READ_BUF_SIZE 16384 +#else +#define YY_READ_BUF_SIZE 8192 +#endif /* __ia64__ */ +#endif + +/* Number of entries by which start-condition stack grows. */ +#ifndef YY_START_STACK_INCR +#define YY_START_STACK_INCR 25 +#endif + +/* Default declaration of generated scanner - a define so the user can + * easily add parameters. + */ +#ifndef YY_DECL +#define YY_DECL_IS_OURS 1 + +extern int yylex (void); + +#define YY_DECL int yylex (void) +#endif /* !YY_DECL */ + +/* yy_get_previous_state - get the state just before the EOB char was reached */ + +#undef YY_NEW_FILE +#undef YY_FLUSH_BUFFER +#undef yy_set_bol +#undef yy_new_buffer +#undef yy_set_interactive +#undef YY_DO_BEFORE_ACTION + +#ifdef YY_DECL_IS_OURS +#undef YY_DECL_IS_OURS +#undef YY_DECL +#endif + +#ifndef yy_create_buffer_ALREADY_DEFINED +#undef yy_create_buffer +#endif +#ifndef yy_delete_buffer_ALREADY_DEFINED +#undef yy_delete_buffer +#endif +#ifndef yy_scan_buffer_ALREADY_DEFINED +#undef yy_scan_buffer +#endif +#ifndef yy_scan_string_ALREADY_DEFINED +#undef yy_scan_string +#endif +#ifndef yy_scan_bytes_ALREADY_DEFINED +#undef yy_scan_bytes +#endif +#ifndef yy_init_buffer_ALREADY_DEFINED +#undef yy_init_buffer +#endif +#ifndef yy_flush_buffer_ALREADY_DEFINED +#undef yy_flush_buffer +#endif +#ifndef yy_load_buffer_state_ALREADY_DEFINED +#undef yy_load_buffer_state +#endif +#ifndef yy_switch_to_buffer_ALREADY_DEFINED +#undef yy_switch_to_buffer +#endif +#ifndef yypush_buffer_state_ALREADY_DEFINED +#undef yypush_buffer_state +#endif +#ifndef yypop_buffer_state_ALREADY_DEFINED +#undef yypop_buffer_state +#endif +#ifndef yyensure_buffer_stack_ALREADY_DEFINED +#undef yyensure_buffer_stack +#endif +#ifndef yylex_ALREADY_DEFINED +#undef yylex +#endif +#ifndef yyrestart_ALREADY_DEFINED +#undef yyrestart +#endif +#ifndef yylex_init_ALREADY_DEFINED +#undef yylex_init +#endif +#ifndef yylex_init_extra_ALREADY_DEFINED +#undef yylex_init_extra +#endif +#ifndef yylex_destroy_ALREADY_DEFINED +#undef yylex_destroy +#endif +#ifndef yyget_debug_ALREADY_DEFINED +#undef yyget_debug +#endif +#ifndef yyset_debug_ALREADY_DEFINED +#undef yyset_debug +#endif +#ifndef yyget_extra_ALREADY_DEFINED +#undef yyget_extra +#endif +#ifndef yyset_extra_ALREADY_DEFINED +#undef yyset_extra +#endif +#ifndef yyget_in_ALREADY_DEFINED +#undef yyget_in +#endif +#ifndef yyset_in_ALREADY_DEFINED +#undef yyset_in +#endif +#ifndef yyget_out_ALREADY_DEFINED +#undef yyget_out +#endif +#ifndef yyset_out_ALREADY_DEFINED +#undef yyset_out +#endif +#ifndef yyget_leng_ALREADY_DEFINED +#undef yyget_leng +#endif +#ifndef yyget_text_ALREADY_DEFINED +#undef yyget_text +#endif +#ifndef yyget_lineno_ALREADY_DEFINED +#undef yyget_lineno +#endif +#ifndef yyset_lineno_ALREADY_DEFINED +#undef yyset_lineno +#endif +#ifndef yyget_column_ALREADY_DEFINED +#undef yyget_column +#endif +#ifndef yyset_column_ALREADY_DEFINED +#undef yyset_column +#endif +#ifndef yywrap_ALREADY_DEFINED +#undef yywrap +#endif +#ifndef yyget_lval_ALREADY_DEFINED +#undef yyget_lval +#endif +#ifndef yyset_lval_ALREADY_DEFINED +#undef yyset_lval +#endif +#ifndef yyget_lloc_ALREADY_DEFINED +#undef yyget_lloc +#endif +#ifndef yyset_lloc_ALREADY_DEFINED +#undef yyset_lloc +#endif +#ifndef yyalloc_ALREADY_DEFINED +#undef yyalloc +#endif +#ifndef yyrealloc_ALREADY_DEFINED +#undef yyrealloc +#endif +#ifndef yyfree_ALREADY_DEFINED +#undef yyfree +#endif +#ifndef yytext_ALREADY_DEFINED +#undef yytext +#endif +#ifndef yyleng_ALREADY_DEFINED +#undef yyleng +#endif +#ifndef yyin_ALREADY_DEFINED +#undef yyin +#endif +#ifndef yyout_ALREADY_DEFINED +#undef yyout +#endif +#ifndef yy_flex_debug_ALREADY_DEFINED +#undef yy_flex_debug +#endif +#ifndef yylineno_ALREADY_DEFINED +#undef yylineno +#endif +#ifndef yytables_fload_ALREADY_DEFINED +#undef yytables_fload +#endif +#ifndef yytables_destroy_ALREADY_DEFINED +#undef yytables_destroy +#endif +#ifndef yyTABLES_NAME_ALREADY_DEFINED +#undef yyTABLES_NAME +#endif + +#line 89 "cppython.lex" + + +#line 473 "lexer.h" +#undef yyIN_HEADER +#endif /* yyHEADER_H */ diff --git a/src/main.c b/src/main.c new file mode 100644 index 0000000..f964360 --- /dev/null +++ b/src/main.c @@ -0,0 +1,22 @@ +#include +#include "ast.h" +#include "lexer.h" +#include "parser.h" + +int main (int argc, char *argv[]) { + printf("Welcome to CPPython interpreter:\n"); + + // init lexer and parser + printf("Lexer/parser:\n"); + line = column = 1; + yyin = fopen(argv[1], "r"); + printf("\nline %d. ", line); + do { + yyparse(); + } while (!feof(yyin)); + fclose(yyin); + printf("\n"); + printf("Lexer and parser finished.\n\n"); + + return 0; +} diff --git a/src/parser.c b/src/parser.c new file mode 100644 index 0000000..7ff1d51 --- /dev/null +++ b/src/parser.c @@ -0,0 +1,1597 @@ +/* A Bison parser, made by GNU Bison 3.5.1. */ + +/* Bison implementation for Yacc-like parsers in C + + Copyright (C) 1984, 1989-1990, 2000-2015, 2018-2020 Free Software Foundation, + Inc. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . */ + +/* As a special exception, you may create a larger work that contains + part or all of the Bison parser skeleton and distribute that work + under terms of your choice, so long as that work isn't itself a + parser generator using the skeleton or a modified version thereof + as a parser skeleton. Alternatively, if you modify or redistribute + the parser skeleton itself, you may (at your option) remove this + special exception, which will cause the skeleton and the resulting + Bison output files to be licensed under the GNU General Public + License without this special exception. + + This special exception was added by the Free Software Foundation in + version 2.2 of Bison. */ + +/* C LALR(1) parser skeleton written by Richard Stallman, by + simplifying the original so-called "semantic" parser. */ + +/* All symbols defined below should begin with yy or YY, to avoid + infringing on user name space. This should be done even for local + variables, as they might otherwise be expanded by user macros. + There are some unavoidable exceptions within include files to + define necessary library symbols; they are noted "INFRINGES ON + USER NAME SPACE" below. */ + +/* Undocumented macros, especially those whose name start with YY_, + are private implementation details. Do not rely on them. */ + +/* Identify Bison output. */ +#define YYBISON 1 + +/* Bison version. */ +#define YYBISON_VERSION "3.5.1" + +/* Skeleton name. */ +#define YYSKELETON_NAME "yacc.c" + +/* Pure parsers. */ +#define YYPURE 0 + +/* Push parsers. */ +#define YYPUSH 0 + +/* Pull parsers. */ +#define YYPULL 1 + + + + +/* First part of user prologue. */ +#line 1 "cppython.y" + + #include + #include "ast.h" + + int yylex(); + void yyerror(char *s); + +#line 78 "parser.c" + +# ifndef YY_CAST +# ifdef __cplusplus +# define YY_CAST(Type, Val) static_cast (Val) +# define YY_REINTERPRET_CAST(Type, Val) reinterpret_cast (Val) +# else +# define YY_CAST(Type, Val) ((Type) (Val)) +# define YY_REINTERPRET_CAST(Type, Val) ((Type) (Val)) +# endif +# endif +# ifndef YY_NULLPTR +# if defined __cplusplus +# if 201103L <= __cplusplus +# define YY_NULLPTR nullptr +# else +# define YY_NULLPTR 0 +# endif +# else +# define YY_NULLPTR ((void*)0) +# endif +# endif + +/* Enabling verbose error messages. */ +#ifdef YYERROR_VERBOSE +# undef YYERROR_VERBOSE +# define YYERROR_VERBOSE 1 +#else +# define YYERROR_VERBOSE 0 +#endif + +/* Use api.header.include to #include this header + instead of duplicating it here. */ +#ifndef YY_YY_PARSER_H_INCLUDED +# define YY_YY_PARSER_H_INCLUDED +/* Debug traces. */ +#ifndef YYDEBUG +# define YYDEBUG 0 +#endif +#if YYDEBUG +extern int yydebug; +#endif + +/* Token type. */ +#ifndef YYTOKENTYPE +# define YYTOKENTYPE + enum yytokentype + { + ADD = 258, + SUB = 259, + MULT = 260, + DIV = 261, + INTEGER = 262 + }; +#endif + +/* Value type. */ +#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED +union YYSTYPE +{ +#line 15 "cppython.y" + + int value; + char* op; + ast_node* expression; + +#line 144 "parser.c" + +}; +typedef union YYSTYPE YYSTYPE; +# define YYSTYPE_IS_TRIVIAL 1 +# define YYSTYPE_IS_DECLARED 1 +#endif + + +extern YYSTYPE yylval; + +int yyparse (void); + +#endif /* !YY_YY_PARSER_H_INCLUDED */ + + + +#ifdef short +# undef short +#endif + +/* On compilers that do not define __PTRDIFF_MAX__ etc., make sure + and (if available) are included + so that the code can choose integer types of a good width. */ + +#ifndef __PTRDIFF_MAX__ +# include /* INFRINGES ON USER NAME SPACE */ +# if defined __STDC_VERSION__ && 199901 <= __STDC_VERSION__ +# include /* INFRINGES ON USER NAME SPACE */ +# define YY_STDINT_H +# endif +#endif + +/* Narrow types that promote to a signed type and that can represent a + signed or unsigned integer of at least N bits. In tables they can + save space and decrease cache pressure. Promoting to a signed type + helps avoid bugs in integer arithmetic. */ + +#ifdef __INT_LEAST8_MAX__ +typedef __INT_LEAST8_TYPE__ yytype_int8; +#elif defined YY_STDINT_H +typedef int_least8_t yytype_int8; +#else +typedef signed char yytype_int8; +#endif + +#ifdef __INT_LEAST16_MAX__ +typedef __INT_LEAST16_TYPE__ yytype_int16; +#elif defined YY_STDINT_H +typedef int_least16_t yytype_int16; +#else +typedef short yytype_int16; +#endif + +#if defined __UINT_LEAST8_MAX__ && __UINT_LEAST8_MAX__ <= __INT_MAX__ +typedef __UINT_LEAST8_TYPE__ yytype_uint8; +#elif (!defined __UINT_LEAST8_MAX__ && defined YY_STDINT_H \ + && UINT_LEAST8_MAX <= INT_MAX) +typedef uint_least8_t yytype_uint8; +#elif !defined __UINT_LEAST8_MAX__ && UCHAR_MAX <= INT_MAX +typedef unsigned char yytype_uint8; +#else +typedef short yytype_uint8; +#endif + +#if defined __UINT_LEAST16_MAX__ && __UINT_LEAST16_MAX__ <= __INT_MAX__ +typedef __UINT_LEAST16_TYPE__ yytype_uint16; +#elif (!defined __UINT_LEAST16_MAX__ && defined YY_STDINT_H \ + && UINT_LEAST16_MAX <= INT_MAX) +typedef uint_least16_t yytype_uint16; +#elif !defined __UINT_LEAST16_MAX__ && USHRT_MAX <= INT_MAX +typedef unsigned short yytype_uint16; +#else +typedef int yytype_uint16; +#endif + +#ifndef YYPTRDIFF_T +# if defined __PTRDIFF_TYPE__ && defined __PTRDIFF_MAX__ +# define YYPTRDIFF_T __PTRDIFF_TYPE__ +# define YYPTRDIFF_MAXIMUM __PTRDIFF_MAX__ +# elif defined PTRDIFF_MAX +# ifndef ptrdiff_t +# include /* INFRINGES ON USER NAME SPACE */ +# endif +# define YYPTRDIFF_T ptrdiff_t +# define YYPTRDIFF_MAXIMUM PTRDIFF_MAX +# else +# define YYPTRDIFF_T long +# define YYPTRDIFF_MAXIMUM LONG_MAX +# endif +#endif + +#ifndef YYSIZE_T +# ifdef __SIZE_TYPE__ +# define YYSIZE_T __SIZE_TYPE__ +# elif defined size_t +# define YYSIZE_T size_t +# elif defined __STDC_VERSION__ && 199901 <= __STDC_VERSION__ +# include /* INFRINGES ON USER NAME SPACE */ +# define YYSIZE_T size_t +# else +# define YYSIZE_T unsigned +# endif +#endif + +#define YYSIZE_MAXIMUM \ + YY_CAST (YYPTRDIFF_T, \ + (YYPTRDIFF_MAXIMUM < YY_CAST (YYSIZE_T, -1) \ + ? YYPTRDIFF_MAXIMUM \ + : YY_CAST (YYSIZE_T, -1))) + +#define YYSIZEOF(X) YY_CAST (YYPTRDIFF_T, sizeof (X)) + +/* Stored state numbers (used for stacks). */ +typedef yytype_int8 yy_state_t; + +/* State numbers in computations. */ +typedef int yy_state_fast_t; + +#ifndef YY_ +# if defined YYENABLE_NLS && YYENABLE_NLS +# if ENABLE_NLS +# include /* INFRINGES ON USER NAME SPACE */ +# define YY_(Msgid) dgettext ("bison-runtime", Msgid) +# endif +# endif +# ifndef YY_ +# define YY_(Msgid) Msgid +# endif +#endif + +#ifndef YY_ATTRIBUTE_PURE +# if defined __GNUC__ && 2 < __GNUC__ + (96 <= __GNUC_MINOR__) +# define YY_ATTRIBUTE_PURE __attribute__ ((__pure__)) +# else +# define YY_ATTRIBUTE_PURE +# endif +#endif + +#ifndef YY_ATTRIBUTE_UNUSED +# if defined __GNUC__ && 2 < __GNUC__ + (7 <= __GNUC_MINOR__) +# define YY_ATTRIBUTE_UNUSED __attribute__ ((__unused__)) +# else +# define YY_ATTRIBUTE_UNUSED +# endif +#endif + +/* Suppress unused-variable warnings by "using" E. */ +#if ! defined lint || defined __GNUC__ +# define YYUSE(E) ((void) (E)) +#else +# define YYUSE(E) /* empty */ +#endif + +#if defined __GNUC__ && ! defined __ICC && 407 <= __GNUC__ * 100 + __GNUC_MINOR__ +/* Suppress an incorrect diagnostic about yylval being uninitialized. */ +# define YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN \ + _Pragma ("GCC diagnostic push") \ + _Pragma ("GCC diagnostic ignored \"-Wuninitialized\"") \ + _Pragma ("GCC diagnostic ignored \"-Wmaybe-uninitialized\"") +# define YY_IGNORE_MAYBE_UNINITIALIZED_END \ + _Pragma ("GCC diagnostic pop") +#else +# define YY_INITIAL_VALUE(Value) Value +#endif +#ifndef YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN +# define YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN +# define YY_IGNORE_MAYBE_UNINITIALIZED_END +#endif +#ifndef YY_INITIAL_VALUE +# define YY_INITIAL_VALUE(Value) /* Nothing. */ +#endif + +#if defined __cplusplus && defined __GNUC__ && ! defined __ICC && 6 <= __GNUC__ +# define YY_IGNORE_USELESS_CAST_BEGIN \ + _Pragma ("GCC diagnostic push") \ + _Pragma ("GCC diagnostic ignored \"-Wuseless-cast\"") +# define YY_IGNORE_USELESS_CAST_END \ + _Pragma ("GCC diagnostic pop") +#endif +#ifndef YY_IGNORE_USELESS_CAST_BEGIN +# define YY_IGNORE_USELESS_CAST_BEGIN +# define YY_IGNORE_USELESS_CAST_END +#endif + + +#define YY_ASSERT(E) ((void) (0 && (E))) + +#if ! defined yyoverflow || YYERROR_VERBOSE + +/* The parser invokes alloca or malloc; define the necessary symbols. */ + +# ifdef YYSTACK_USE_ALLOCA +# if YYSTACK_USE_ALLOCA +# ifdef __GNUC__ +# define YYSTACK_ALLOC __builtin_alloca +# elif defined __BUILTIN_VA_ARG_INCR +# include /* INFRINGES ON USER NAME SPACE */ +# elif defined _AIX +# define YYSTACK_ALLOC __alloca +# elif defined _MSC_VER +# include /* INFRINGES ON USER NAME SPACE */ +# define alloca _alloca +# else +# define YYSTACK_ALLOC alloca +# if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS +# include /* INFRINGES ON USER NAME SPACE */ + /* Use EXIT_SUCCESS as a witness for stdlib.h. */ +# ifndef EXIT_SUCCESS +# define EXIT_SUCCESS 0 +# endif +# endif +# endif +# endif +# endif + +# ifdef YYSTACK_ALLOC + /* Pacify GCC's 'empty if-body' warning. */ +# define YYSTACK_FREE(Ptr) do { /* empty */; } while (0) +# ifndef YYSTACK_ALLOC_MAXIMUM + /* The OS might guarantee only one guard page at the bottom of the stack, + and a page size can be as small as 4096 bytes. So we cannot safely + invoke alloca (N) if N exceeds 4096. Use a slightly smaller number + to allow for a few compiler-allocated temporary stack slots. */ +# define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */ +# endif +# else +# define YYSTACK_ALLOC YYMALLOC +# define YYSTACK_FREE YYFREE +# ifndef YYSTACK_ALLOC_MAXIMUM +# define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM +# endif +# if (defined __cplusplus && ! defined EXIT_SUCCESS \ + && ! ((defined YYMALLOC || defined malloc) \ + && (defined YYFREE || defined free))) +# include /* INFRINGES ON USER NAME SPACE */ +# ifndef EXIT_SUCCESS +# define EXIT_SUCCESS 0 +# endif +# endif +# ifndef YYMALLOC +# define YYMALLOC malloc +# if ! defined malloc && ! defined EXIT_SUCCESS +void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */ +# endif +# endif +# ifndef YYFREE +# define YYFREE free +# if ! defined free && ! defined EXIT_SUCCESS +void free (void *); /* INFRINGES ON USER NAME SPACE */ +# endif +# endif +# endif +#endif /* ! defined yyoverflow || YYERROR_VERBOSE */ + + +#if (! defined yyoverflow \ + && (! defined __cplusplus \ + || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL))) + +/* A type that is properly aligned for any stack member. */ +union yyalloc +{ + yy_state_t yyss_alloc; + YYSTYPE yyvs_alloc; +}; + +/* The size of the maximum gap between one aligned stack and the next. */ +# define YYSTACK_GAP_MAXIMUM (YYSIZEOF (union yyalloc) - 1) + +/* The size of an array large to enough to hold all stacks, each with + N elements. */ +# define YYSTACK_BYTES(N) \ + ((N) * (YYSIZEOF (yy_state_t) + YYSIZEOF (YYSTYPE)) \ + + YYSTACK_GAP_MAXIMUM) + +# define YYCOPY_NEEDED 1 + +/* Relocate STACK from its old location to the new one. The + local variables YYSIZE and YYSTACKSIZE give the old and new number of + elements in the stack, and YYPTR gives the new location of the + stack. Advance YYPTR to a properly aligned location for the next + stack. */ +# define YYSTACK_RELOCATE(Stack_alloc, Stack) \ + do \ + { \ + YYPTRDIFF_T yynewbytes; \ + YYCOPY (&yyptr->Stack_alloc, Stack, yysize); \ + Stack = &yyptr->Stack_alloc; \ + yynewbytes = yystacksize * YYSIZEOF (*Stack) + YYSTACK_GAP_MAXIMUM; \ + yyptr += yynewbytes / YYSIZEOF (*yyptr); \ + } \ + while (0) + +#endif + +#if defined YYCOPY_NEEDED && YYCOPY_NEEDED +/* Copy COUNT objects from SRC to DST. The source and destination do + not overlap. */ +# ifndef YYCOPY +# if defined __GNUC__ && 1 < __GNUC__ +# define YYCOPY(Dst, Src, Count) \ + __builtin_memcpy (Dst, Src, YY_CAST (YYSIZE_T, (Count)) * sizeof (*(Src))) +# else +# define YYCOPY(Dst, Src, Count) \ + do \ + { \ + YYPTRDIFF_T yyi; \ + for (yyi = 0; yyi < (Count); yyi++) \ + (Dst)[yyi] = (Src)[yyi]; \ + } \ + while (0) +# endif +# endif +#endif /* !YYCOPY_NEEDED */ + +/* YYFINAL -- State number of the termination state. */ +#define YYFINAL 6 +/* YYLAST -- Last index in YYTABLE. */ +#define YYLAST 10 + +/* YYNTOKENS -- Number of terminals. */ +#define YYNTOKENS 8 +/* YYNNTS -- Number of nonterminals. */ +#define YYNNTS 5 +/* YYNRULES -- Number of rules. */ +#define YYNRULES 10 +/* YYNSTATES -- Number of states. */ +#define YYNSTATES 15 + +#define YYUNDEFTOK 2 +#define YYMAXUTOK 262 + + +/* YYTRANSLATE(TOKEN-NUM) -- Symbol number corresponding to TOKEN-NUM + as returned by yylex, with out-of-bounds checking. */ +#define YYTRANSLATE(YYX) \ + (0 <= (YYX) && (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK) + +/* YYTRANSLATE[TOKEN-NUM] -- Symbol number corresponding to TOKEN-NUM + as returned by yylex. */ +static const yytype_int8 yytranslate[] = +{ + 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 1, 2, 3, 4, + 5, 6, 7 +}; + +#if YYDEBUG + /* YYRLINE[YYN] -- Source line where rule number YYN was defined. */ +static const yytype_int8 yyrline[] = +{ + 0, 31, 31, 32, 35, 36, 37, 40, 41, 42, + 45 +}; +#endif + +#if YYDEBUG || YYERROR_VERBOSE || 0 +/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM. + First, the terminals, then, starting at YYNTOKENS, nonterminals. */ +static const char *const yytname[] = +{ + "$end", "error", "$undefined", "ADD", "SUB", "MULT", "DIV", "INTEGER", + "$accept", "input", "expr", "term", "factor", YY_NULLPTR +}; +#endif + +# ifdef YYPRINT +/* YYTOKNUM[NUM] -- (External) token number corresponding to the + (internal) symbol number NUM (which must be that of a token). */ +static const yytype_int16 yytoknum[] = +{ + 0, 256, 257, 258, 259, 260, 261, 262 +}; +# endif + +#define YYPACT_NINF (-6) + +#define yypact_value_is_default(Yyn) \ + ((Yyn) == YYPACT_NINF) + +#define YYTABLE_NINF (-1) + +#define yytable_value_is_error(Yyn) \ + 0 + + /* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing + STATE-NUM. */ +static const yytype_int8 yypact[] = +{ + -5, -6, 5, -6, -3, -2, -6, -5, -5, -5, + -5, -6, -6, -6, -6 +}; + + /* YYDEFACT[STATE-NUM] -- Default reduction number in state STATE-NUM. + Performed when YYTABLE does not specify something else to do. Zero + means the default is an error. */ +static const yytype_int8 yydefact[] = +{ + 2, 10, 0, 3, 6, 9, 1, 0, 0, 0, + 0, 4, 5, 7, 8 +}; + + /* YYPGOTO[NTERM-NUM]. */ +static const yytype_int8 yypgoto[] = +{ + -6, -6, -6, -1, 0 +}; + + /* YYDEFGOTO[NTERM-NUM]. */ +static const yytype_int8 yydefgoto[] = +{ + -1, 2, 3, 4, 5 +}; + + /* YYTABLE[YYPACT[STATE-NUM]] -- What to do in state STATE-NUM. If + positive, shift that token. If negative, reduce the rule whose + number is the opposite. If YYTABLE_NINF, syntax error. */ +static const yytype_int8 yytable[] = +{ + 7, 8, 1, 9, 10, 6, 11, 12, 0, 13, + 14 +}; + +static const yytype_int8 yycheck[] = +{ + 3, 4, 7, 5, 6, 0, 7, 8, -1, 9, + 10 +}; + + /* YYSTOS[STATE-NUM] -- The (internal number of the) accessing + symbol of state STATE-NUM. */ +static const yytype_int8 yystos[] = +{ + 0, 7, 9, 10, 11, 12, 0, 3, 4, 5, + 6, 11, 11, 12, 12 +}; + + /* YYR1[YYN] -- Symbol number of symbol that rule YYN derives. */ +static const yytype_int8 yyr1[] = +{ + 0, 8, 9, 9, 10, 10, 10, 11, 11, 11, + 12 +}; + + /* YYR2[YYN] -- Number of symbols on the right hand side of rule YYN. */ +static const yytype_int8 yyr2[] = +{ + 0, 2, 0, 1, 3, 3, 1, 3, 3, 1, + 1 +}; + + +#define yyerrok (yyerrstatus = 0) +#define yyclearin (yychar = YYEMPTY) +#define YYEMPTY (-2) +#define YYEOF 0 + +#define YYACCEPT goto yyacceptlab +#define YYABORT goto yyabortlab +#define YYERROR goto yyerrorlab + + +#define YYRECOVERING() (!!yyerrstatus) + +#define YYBACKUP(Token, Value) \ + do \ + if (yychar == YYEMPTY) \ + { \ + yychar = (Token); \ + yylval = (Value); \ + YYPOPSTACK (yylen); \ + yystate = *yyssp; \ + goto yybackup; \ + } \ + else \ + { \ + yyerror (YY_("syntax error: cannot back up")); \ + YYERROR; \ + } \ + while (0) + +/* Error token number */ +#define YYTERROR 1 +#define YYERRCODE 256 + + + +/* Enable debugging if requested. */ +#if YYDEBUG + +# ifndef YYFPRINTF +# include /* INFRINGES ON USER NAME SPACE */ +# define YYFPRINTF fprintf +# endif + +# define YYDPRINTF(Args) \ +do { \ + if (yydebug) \ + YYFPRINTF Args; \ +} while (0) + +/* This macro is provided for backward compatibility. */ +#ifndef YY_LOCATION_PRINT +# define YY_LOCATION_PRINT(File, Loc) ((void) 0) +#endif + + +# define YY_SYMBOL_PRINT(Title, Type, Value, Location) \ +do { \ + if (yydebug) \ + { \ + YYFPRINTF (stderr, "%s ", Title); \ + yy_symbol_print (stderr, \ + Type, Value); \ + YYFPRINTF (stderr, "\n"); \ + } \ +} while (0) + + +/*-----------------------------------. +| Print this symbol's value on YYO. | +`-----------------------------------*/ + +static void +yy_symbol_value_print (FILE *yyo, int yytype, YYSTYPE const * const yyvaluep) +{ + FILE *yyoutput = yyo; + YYUSE (yyoutput); + if (!yyvaluep) + return; +# ifdef YYPRINT + if (yytype < YYNTOKENS) + YYPRINT (yyo, yytoknum[yytype], *yyvaluep); +# endif + YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN + YYUSE (yytype); + YY_IGNORE_MAYBE_UNINITIALIZED_END +} + + +/*---------------------------. +| Print this symbol on YYO. | +`---------------------------*/ + +static void +yy_symbol_print (FILE *yyo, int yytype, YYSTYPE const * const yyvaluep) +{ + YYFPRINTF (yyo, "%s %s (", + yytype < YYNTOKENS ? "token" : "nterm", yytname[yytype]); + + yy_symbol_value_print (yyo, yytype, yyvaluep); + YYFPRINTF (yyo, ")"); +} + +/*------------------------------------------------------------------. +| yy_stack_print -- Print the state stack from its BOTTOM up to its | +| TOP (included). | +`------------------------------------------------------------------*/ + +static void +yy_stack_print (yy_state_t *yybottom, yy_state_t *yytop) +{ + YYFPRINTF (stderr, "Stack now"); + for (; yybottom <= yytop; yybottom++) + { + int yybot = *yybottom; + YYFPRINTF (stderr, " %d", yybot); + } + YYFPRINTF (stderr, "\n"); +} + +# define YY_STACK_PRINT(Bottom, Top) \ +do { \ + if (yydebug) \ + yy_stack_print ((Bottom), (Top)); \ +} while (0) + + +/*------------------------------------------------. +| Report that the YYRULE is going to be reduced. | +`------------------------------------------------*/ + +static void +yy_reduce_print (yy_state_t *yyssp, YYSTYPE *yyvsp, int yyrule) +{ + int yylno = yyrline[yyrule]; + int yynrhs = yyr2[yyrule]; + int yyi; + YYFPRINTF (stderr, "Reducing stack by rule %d (line %d):\n", + yyrule - 1, yylno); + /* The symbols being reduced. */ + for (yyi = 0; yyi < yynrhs; yyi++) + { + YYFPRINTF (stderr, " $%d = ", yyi + 1); + yy_symbol_print (stderr, + yystos[+yyssp[yyi + 1 - yynrhs]], + &yyvsp[(yyi + 1) - (yynrhs)] + ); + YYFPRINTF (stderr, "\n"); + } +} + +# define YY_REDUCE_PRINT(Rule) \ +do { \ + if (yydebug) \ + yy_reduce_print (yyssp, yyvsp, Rule); \ +} while (0) + +/* Nonzero means print parse trace. It is left uninitialized so that + multiple parsers can coexist. */ +int yydebug; +#else /* !YYDEBUG */ +# define YYDPRINTF(Args) +# define YY_SYMBOL_PRINT(Title, Type, Value, Location) +# define YY_STACK_PRINT(Bottom, Top) +# define YY_REDUCE_PRINT(Rule) +#endif /* !YYDEBUG */ + + +/* YYINITDEPTH -- initial size of the parser's stacks. */ +#ifndef YYINITDEPTH +# define YYINITDEPTH 200 +#endif + +/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only + if the built-in stack extension method is used). + + Do not make this value too large; the results are undefined if + YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH) + evaluated with infinite-precision integer arithmetic. */ + +#ifndef YYMAXDEPTH +# define YYMAXDEPTH 10000 +#endif + + +#if YYERROR_VERBOSE + +# ifndef yystrlen +# if defined __GLIBC__ && defined _STRING_H +# define yystrlen(S) (YY_CAST (YYPTRDIFF_T, strlen (S))) +# else +/* Return the length of YYSTR. */ +static YYPTRDIFF_T +yystrlen (const char *yystr) +{ + YYPTRDIFF_T yylen; + for (yylen = 0; yystr[yylen]; yylen++) + continue; + return yylen; +} +# endif +# endif + +# ifndef yystpcpy +# if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE +# define yystpcpy stpcpy +# else +/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in + YYDEST. */ +static char * +yystpcpy (char *yydest, const char *yysrc) +{ + char *yyd = yydest; + const char *yys = yysrc; + + while ((*yyd++ = *yys++) != '\0') + continue; + + return yyd - 1; +} +# endif +# endif + +# ifndef yytnamerr +/* Copy to YYRES the contents of YYSTR after stripping away unnecessary + quotes and backslashes, so that it's suitable for yyerror. The + heuristic is that double-quoting is unnecessary unless the string + contains an apostrophe, a comma, or backslash (other than + backslash-backslash). YYSTR is taken from yytname. If YYRES is + null, do not copy; instead, return the length of what the result + would have been. */ +static YYPTRDIFF_T +yytnamerr (char *yyres, const char *yystr) +{ + if (*yystr == '"') + { + YYPTRDIFF_T yyn = 0; + char const *yyp = yystr; + + for (;;) + switch (*++yyp) + { + case '\'': + case ',': + goto do_not_strip_quotes; + + case '\\': + if (*++yyp != '\\') + goto do_not_strip_quotes; + else + goto append; + + append: + default: + if (yyres) + yyres[yyn] = *yyp; + yyn++; + break; + + case '"': + if (yyres) + yyres[yyn] = '\0'; + return yyn; + } + do_not_strip_quotes: ; + } + + if (yyres) + return yystpcpy (yyres, yystr) - yyres; + else + return yystrlen (yystr); +} +# endif + +/* Copy into *YYMSG, which is of size *YYMSG_ALLOC, an error message + about the unexpected token YYTOKEN for the state stack whose top is + YYSSP. + + Return 0 if *YYMSG was successfully written. Return 1 if *YYMSG is + not large enough to hold the message. In that case, also set + *YYMSG_ALLOC to the required number of bytes. Return 2 if the + required number of bytes is too large to store. */ +static int +yysyntax_error (YYPTRDIFF_T *yymsg_alloc, char **yymsg, + yy_state_t *yyssp, int yytoken) +{ + enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 }; + /* Internationalized format string. */ + const char *yyformat = YY_NULLPTR; + /* Arguments of yyformat: reported tokens (one for the "unexpected", + one per "expected"). */ + char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM]; + /* Actual size of YYARG. */ + int yycount = 0; + /* Cumulated lengths of YYARG. */ + YYPTRDIFF_T yysize = 0; + + /* There are many possibilities here to consider: + - If this state is a consistent state with a default action, then + the only way this function was invoked is if the default action + is an error action. In that case, don't check for expected + tokens because there are none. + - The only way there can be no lookahead present (in yychar) is if + this state is a consistent state with a default action. Thus, + detecting the absence of a lookahead is sufficient to determine + that there is no unexpected or expected token to report. In that + case, just report a simple "syntax error". + - Don't assume there isn't a lookahead just because this state is a + consistent state with a default action. There might have been a + previous inconsistent state, consistent state with a non-default + action, or user semantic action that manipulated yychar. + - Of course, the expected token list depends on states to have + correct lookahead information, and it depends on the parser not + to perform extra reductions after fetching a lookahead from the + scanner and before detecting a syntax error. Thus, state merging + (from LALR or IELR) and default reductions corrupt the expected + token list. However, the list is correct for canonical LR with + one exception: it will still contain any token that will not be + accepted due to an error action in a later state. + */ + if (yytoken != YYEMPTY) + { + int yyn = yypact[+*yyssp]; + YYPTRDIFF_T yysize0 = yytnamerr (YY_NULLPTR, yytname[yytoken]); + yysize = yysize0; + yyarg[yycount++] = yytname[yytoken]; + if (!yypact_value_is_default (yyn)) + { + /* Start YYX at -YYN if negative to avoid negative indexes in + YYCHECK. In other words, skip the first -YYN actions for + this state because they are default actions. */ + int yyxbegin = yyn < 0 ? -yyn : 0; + /* Stay within bounds of both yycheck and yytname. */ + int yychecklim = YYLAST - yyn + 1; + int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS; + int yyx; + + for (yyx = yyxbegin; yyx < yyxend; ++yyx) + if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR + && !yytable_value_is_error (yytable[yyx + yyn])) + { + if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM) + { + yycount = 1; + yysize = yysize0; + break; + } + yyarg[yycount++] = yytname[yyx]; + { + YYPTRDIFF_T yysize1 + = yysize + yytnamerr (YY_NULLPTR, yytname[yyx]); + if (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM) + yysize = yysize1; + else + return 2; + } + } + } + } + + switch (yycount) + { +# define YYCASE_(N, S) \ + case N: \ + yyformat = S; \ + break + default: /* Avoid compiler warnings. */ + YYCASE_(0, YY_("syntax error")); + YYCASE_(1, YY_("syntax error, unexpected %s")); + YYCASE_(2, YY_("syntax error, unexpected %s, expecting %s")); + YYCASE_(3, YY_("syntax error, unexpected %s, expecting %s or %s")); + YYCASE_(4, YY_("syntax error, unexpected %s, expecting %s or %s or %s")); + YYCASE_(5, YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s")); +# undef YYCASE_ + } + + { + /* Don't count the "%s"s in the final size, but reserve room for + the terminator. */ + YYPTRDIFF_T yysize1 = yysize + (yystrlen (yyformat) - 2 * yycount) + 1; + if (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM) + yysize = yysize1; + else + return 2; + } + + if (*yymsg_alloc < yysize) + { + *yymsg_alloc = 2 * yysize; + if (! (yysize <= *yymsg_alloc + && *yymsg_alloc <= YYSTACK_ALLOC_MAXIMUM)) + *yymsg_alloc = YYSTACK_ALLOC_MAXIMUM; + return 1; + } + + /* Avoid sprintf, as that infringes on the user's name space. + Don't have undefined behavior even if the translation + produced a string with the wrong number of "%s"s. */ + { + char *yyp = *yymsg; + int yyi = 0; + while ((*yyp = *yyformat) != '\0') + if (*yyp == '%' && yyformat[1] == 's' && yyi < yycount) + { + yyp += yytnamerr (yyp, yyarg[yyi++]); + yyformat += 2; + } + else + { + ++yyp; + ++yyformat; + } + } + return 0; +} +#endif /* YYERROR_VERBOSE */ + +/*-----------------------------------------------. +| Release the memory associated to this symbol. | +`-----------------------------------------------*/ + +static void +yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep) +{ + YYUSE (yyvaluep); + if (!yymsg) + yymsg = "Deleting"; + YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp); + + YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN + YYUSE (yytype); + YY_IGNORE_MAYBE_UNINITIALIZED_END +} + + + + +/* The lookahead symbol. */ +int yychar; + +/* The semantic value of the lookahead symbol. */ +YYSTYPE yylval; +/* Number of syntax errors so far. */ +int yynerrs; + + +/*----------. +| yyparse. | +`----------*/ + +int +yyparse (void) +{ + yy_state_fast_t yystate; + /* Number of tokens to shift before error messages enabled. */ + int yyerrstatus; + + /* The stacks and their tools: + 'yyss': related to states. + 'yyvs': related to semantic values. + + Refer to the stacks through separate pointers, to allow yyoverflow + to reallocate them elsewhere. */ + + /* The state stack. */ + yy_state_t yyssa[YYINITDEPTH]; + yy_state_t *yyss; + yy_state_t *yyssp; + + /* The semantic value stack. */ + YYSTYPE yyvsa[YYINITDEPTH]; + YYSTYPE *yyvs; + YYSTYPE *yyvsp; + + YYPTRDIFF_T yystacksize; + + int yyn; + int yyresult; + /* Lookahead token as an internal (translated) token number. */ + int yytoken = 0; + /* The variables used to return semantic value and location from the + action routines. */ + YYSTYPE yyval; + +#if YYERROR_VERBOSE + /* Buffer for error messages, and its allocated size. */ + char yymsgbuf[128]; + char *yymsg = yymsgbuf; + YYPTRDIFF_T yymsg_alloc = sizeof yymsgbuf; +#endif + +#define YYPOPSTACK(N) (yyvsp -= (N), yyssp -= (N)) + + /* The number of symbols on the RHS of the reduced rule. + Keep to zero when no symbol should be popped. */ + int yylen = 0; + + yyssp = yyss = yyssa; + yyvsp = yyvs = yyvsa; + yystacksize = YYINITDEPTH; + + YYDPRINTF ((stderr, "Starting parse\n")); + + yystate = 0; + yyerrstatus = 0; + yynerrs = 0; + yychar = YYEMPTY; /* Cause a token to be read. */ + goto yysetstate; + + +/*------------------------------------------------------------. +| yynewstate -- push a new state, which is found in yystate. | +`------------------------------------------------------------*/ +yynewstate: + /* In all cases, when you get here, the value and location stacks + have just been pushed. So pushing a state here evens the stacks. */ + yyssp++; + + +/*--------------------------------------------------------------------. +| yysetstate -- set current state (the top of the stack) to yystate. | +`--------------------------------------------------------------------*/ +yysetstate: + YYDPRINTF ((stderr, "Entering state %d\n", yystate)); + YY_ASSERT (0 <= yystate && yystate < YYNSTATES); + YY_IGNORE_USELESS_CAST_BEGIN + *yyssp = YY_CAST (yy_state_t, yystate); + YY_IGNORE_USELESS_CAST_END + + if (yyss + yystacksize - 1 <= yyssp) +#if !defined yyoverflow && !defined YYSTACK_RELOCATE + goto yyexhaustedlab; +#else + { + /* Get the current used size of the three stacks, in elements. */ + YYPTRDIFF_T yysize = yyssp - yyss + 1; + +# if defined yyoverflow + { + /* Give user a chance to reallocate the stack. Use copies of + these so that the &'s don't force the real ones into + memory. */ + yy_state_t *yyss1 = yyss; + YYSTYPE *yyvs1 = yyvs; + + /* Each stack pointer address is followed by the size of the + data in use in that stack, in bytes. This used to be a + conditional around just the two extra args, but that might + be undefined if yyoverflow is a macro. */ + yyoverflow (YY_("memory exhausted"), + &yyss1, yysize * YYSIZEOF (*yyssp), + &yyvs1, yysize * YYSIZEOF (*yyvsp), + &yystacksize); + yyss = yyss1; + yyvs = yyvs1; + } +# else /* defined YYSTACK_RELOCATE */ + /* Extend the stack our own way. */ + if (YYMAXDEPTH <= yystacksize) + goto yyexhaustedlab; + yystacksize *= 2; + if (YYMAXDEPTH < yystacksize) + yystacksize = YYMAXDEPTH; + + { + yy_state_t *yyss1 = yyss; + union yyalloc *yyptr = + YY_CAST (union yyalloc *, + YYSTACK_ALLOC (YY_CAST (YYSIZE_T, YYSTACK_BYTES (yystacksize)))); + if (! yyptr) + goto yyexhaustedlab; + YYSTACK_RELOCATE (yyss_alloc, yyss); + YYSTACK_RELOCATE (yyvs_alloc, yyvs); +# undef YYSTACK_RELOCATE + if (yyss1 != yyssa) + YYSTACK_FREE (yyss1); + } +# endif + + yyssp = yyss + yysize - 1; + yyvsp = yyvs + yysize - 1; + + YY_IGNORE_USELESS_CAST_BEGIN + YYDPRINTF ((stderr, "Stack size increased to %ld\n", + YY_CAST (long, yystacksize))); + YY_IGNORE_USELESS_CAST_END + + if (yyss + yystacksize - 1 <= yyssp) + YYABORT; + } +#endif /* !defined yyoverflow && !defined YYSTACK_RELOCATE */ + + if (yystate == YYFINAL) + YYACCEPT; + + goto yybackup; + + +/*-----------. +| yybackup. | +`-----------*/ +yybackup: + /* Do appropriate processing given the current state. Read a + lookahead token if we need one and don't already have one. */ + + /* First try to decide what to do without reference to lookahead token. */ + yyn = yypact[yystate]; + if (yypact_value_is_default (yyn)) + goto yydefault; + + /* Not known => get a lookahead token if don't already have one. */ + + /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol. */ + if (yychar == YYEMPTY) + { + YYDPRINTF ((stderr, "Reading a token: ")); + yychar = yylex (); + } + + if (yychar <= YYEOF) + { + yychar = yytoken = YYEOF; + YYDPRINTF ((stderr, "Now at end of input.\n")); + } + else + { + yytoken = YYTRANSLATE (yychar); + YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc); + } + + /* If the proper action on seeing token YYTOKEN is to reduce or to + detect an error, take that action. */ + yyn += yytoken; + if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken) + goto yydefault; + yyn = yytable[yyn]; + if (yyn <= 0) + { + if (yytable_value_is_error (yyn)) + goto yyerrlab; + yyn = -yyn; + goto yyreduce; + } + + /* Count tokens shifted since error; after three, turn off error + status. */ + if (yyerrstatus) + yyerrstatus--; + + /* Shift the lookahead token. */ + YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc); + yystate = yyn; + YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN + *++yyvsp = yylval; + YY_IGNORE_MAYBE_UNINITIALIZED_END + + /* Discard the shifted token. */ + yychar = YYEMPTY; + goto yynewstate; + + +/*-----------------------------------------------------------. +| yydefault -- do the default action for the current state. | +`-----------------------------------------------------------*/ +yydefault: + yyn = yydefact[yystate]; + if (yyn == 0) + goto yyerrlab; + goto yyreduce; + + +/*-----------------------------. +| yyreduce -- do a reduction. | +`-----------------------------*/ +yyreduce: + /* yyn is the number of a rule to reduce with. */ + yylen = yyr2[yyn]; + + /* If YYLEN is nonzero, implement the default value of the action: + '$$ = $1'. + + Otherwise, the following line sets YYVAL to garbage. + This behavior is undocumented and Bison + users should not rely upon it. Assigning to YYVAL + unconditionally makes the parser a bit smaller, and it avoids a + GCC warning that YYVAL may be used uninitialized. */ + yyval = yyvsp[1-yylen]; + + + YY_REDUCE_PRINT (yyn); + switch (yyn) + { + case 3: +#line 32 "cppython.y" + { create_ast((yyvsp[0].expression)); } +#line 1315 "parser.c" + break; + + case 4: +#line 35 "cppython.y" + { (yyval.expression) = create_bin_expr((yyvsp[-1].op), (yyvsp[-2].expression), (yyvsp[0].expression)); } +#line 1321 "parser.c" + break; + + case 5: +#line 36 "cppython.y" + { (yyval.expression) = create_bin_expr((yyvsp[-1].op), (yyvsp[-2].expression), (yyvsp[0].expression)); } +#line 1327 "parser.c" + break; + + case 6: +#line 37 "cppython.y" + { (yyval.expression) = show((yyvsp[0].expression)); } +#line 1333 "parser.c" + break; + + case 7: +#line 40 "cppython.y" + { (yyval.expression) = create_bin_expr((yyvsp[-1].op), (yyvsp[-2].expression), (yyvsp[0].expression)); } +#line 1339 "parser.c" + break; + + case 8: +#line 41 "cppython.y" + { (yyval.expression) = create_bin_expr((yyvsp[-1].op), (yyvsp[-2].expression), (yyvsp[0].expression)); } +#line 1345 "parser.c" + break; + + case 9: +#line 42 "cppython.y" + { (yyval.expression) = show((yyvsp[0].expression)); } +#line 1351 "parser.c" + break; + + case 10: +#line 45 "cppython.y" + { (yyval.expression) = create_int_expr((yyvsp[0].value)); } +#line 1357 "parser.c" + break; + + +#line 1361 "parser.c" + + default: break; + } + /* User semantic actions sometimes alter yychar, and that requires + that yytoken be updated with the new translation. We take the + approach of translating immediately before every use of yytoken. + One alternative is translating here after every semantic action, + but that translation would be missed if the semantic action invokes + YYABORT, YYACCEPT, or YYERROR immediately after altering yychar or + if it invokes YYBACKUP. In the case of YYABORT or YYACCEPT, an + incorrect destructor might then be invoked immediately. In the + case of YYERROR or YYBACKUP, subsequent parser actions might lead + to an incorrect destructor call or verbose syntax error message + before the lookahead is translated. */ + YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc); + + YYPOPSTACK (yylen); + yylen = 0; + YY_STACK_PRINT (yyss, yyssp); + + *++yyvsp = yyval; + + /* Now 'shift' the result of the reduction. Determine what state + that goes to, based on the state we popped back to and the rule + number reduced by. */ + { + const int yylhs = yyr1[yyn] - YYNTOKENS; + const int yyi = yypgoto[yylhs] + *yyssp; + yystate = (0 <= yyi && yyi <= YYLAST && yycheck[yyi] == *yyssp + ? yytable[yyi] + : yydefgoto[yylhs]); + } + + goto yynewstate; + + +/*--------------------------------------. +| yyerrlab -- here on detecting error. | +`--------------------------------------*/ +yyerrlab: + /* Make sure we have latest lookahead translation. See comments at + user semantic actions for why this is necessary. */ + yytoken = yychar == YYEMPTY ? YYEMPTY : YYTRANSLATE (yychar); + + /* If not already recovering from an error, report this error. */ + if (!yyerrstatus) + { + ++yynerrs; +#if ! YYERROR_VERBOSE + yyerror (YY_("syntax error")); +#else +# define YYSYNTAX_ERROR yysyntax_error (&yymsg_alloc, &yymsg, \ + yyssp, yytoken) + { + char const *yymsgp = YY_("syntax error"); + int yysyntax_error_status; + yysyntax_error_status = YYSYNTAX_ERROR; + if (yysyntax_error_status == 0) + yymsgp = yymsg; + else if (yysyntax_error_status == 1) + { + if (yymsg != yymsgbuf) + YYSTACK_FREE (yymsg); + yymsg = YY_CAST (char *, YYSTACK_ALLOC (YY_CAST (YYSIZE_T, yymsg_alloc))); + if (!yymsg) + { + yymsg = yymsgbuf; + yymsg_alloc = sizeof yymsgbuf; + yysyntax_error_status = 2; + } + else + { + yysyntax_error_status = YYSYNTAX_ERROR; + yymsgp = yymsg; + } + } + yyerror (yymsgp); + if (yysyntax_error_status == 2) + goto yyexhaustedlab; + } +# undef YYSYNTAX_ERROR +#endif + } + + + + if (yyerrstatus == 3) + { + /* If just tried and failed to reuse lookahead token after an + error, discard it. */ + + if (yychar <= YYEOF) + { + /* Return failure if at end of input. */ + if (yychar == YYEOF) + YYABORT; + } + else + { + yydestruct ("Error: discarding", + yytoken, &yylval); + yychar = YYEMPTY; + } + } + + /* Else will try to reuse lookahead token after shifting the error + token. */ + goto yyerrlab1; + + +/*---------------------------------------------------. +| yyerrorlab -- error raised explicitly by YYERROR. | +`---------------------------------------------------*/ +yyerrorlab: + /* Pacify compilers when the user code never invokes YYERROR and the + label yyerrorlab therefore never appears in user code. */ + if (0) + YYERROR; + + /* Do not reclaim the symbols of the rule whose action triggered + this YYERROR. */ + YYPOPSTACK (yylen); + yylen = 0; + YY_STACK_PRINT (yyss, yyssp); + yystate = *yyssp; + goto yyerrlab1; + + +/*-------------------------------------------------------------. +| yyerrlab1 -- common code for both syntax error and YYERROR. | +`-------------------------------------------------------------*/ +yyerrlab1: + yyerrstatus = 3; /* Each real token shifted decrements this. */ + + for (;;) + { + yyn = yypact[yystate]; + if (!yypact_value_is_default (yyn)) + { + yyn += YYTERROR; + if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR) + { + yyn = yytable[yyn]; + if (0 < yyn) + break; + } + } + + /* Pop the current state because it cannot handle the error token. */ + if (yyssp == yyss) + YYABORT; + + + yydestruct ("Error: popping", + yystos[yystate], yyvsp); + YYPOPSTACK (1); + yystate = *yyssp; + YY_STACK_PRINT (yyss, yyssp); + } + + YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN + *++yyvsp = yylval; + YY_IGNORE_MAYBE_UNINITIALIZED_END + + + /* Shift the error token. */ + YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp); + + yystate = yyn; + goto yynewstate; + + +/*-------------------------------------. +| yyacceptlab -- YYACCEPT comes here. | +`-------------------------------------*/ +yyacceptlab: + yyresult = 0; + goto yyreturn; + + +/*-----------------------------------. +| yyabortlab -- YYABORT comes here. | +`-----------------------------------*/ +yyabortlab: + yyresult = 1; + goto yyreturn; + + +#if !defined yyoverflow || YYERROR_VERBOSE +/*-------------------------------------------------. +| yyexhaustedlab -- memory exhaustion comes here. | +`-------------------------------------------------*/ +yyexhaustedlab: + yyerror (YY_("memory exhausted")); + yyresult = 2; + /* Fall through. */ +#endif + + +/*-----------------------------------------------------. +| yyreturn -- parsing is finished, return the result. | +`-----------------------------------------------------*/ +yyreturn: + if (yychar != YYEMPTY) + { + /* Make sure we have latest lookahead translation. See comments at + user semantic actions for why this is necessary. */ + yytoken = YYTRANSLATE (yychar); + yydestruct ("Cleanup: discarding lookahead", + yytoken, &yylval); + } + /* Do not reclaim the symbols of the rule whose action triggered + this YYABORT or YYACCEPT. */ + YYPOPSTACK (yylen); + YY_STACK_PRINT (yyss, yyssp); + while (yyssp != yyss) + { + yydestruct ("Cleanup: popping", + yystos[+*yyssp], yyvsp); + YYPOPSTACK (1); + } +#ifndef yyoverflow + if (yyss != yyssa) + YYSTACK_FREE (yyss); +#endif +#if YYERROR_VERBOSE + if (yymsg != yymsgbuf) + YYSTACK_FREE (yymsg); +#endif + return yyresult; +} +#line 48 "cppython.y" + + +void yyerror(char *s) { + printf("%s\n", s); +} diff --git a/src/parser.h b/src/parser.h new file mode 100644 index 0000000..776de16 --- /dev/null +++ b/src/parser.h @@ -0,0 +1,83 @@ +/* A Bison parser, made by GNU Bison 3.5.1. */ + +/* Bison interface for Yacc-like parsers in C + + Copyright (C) 1984, 1989-1990, 2000-2015, 2018-2020 Free Software Foundation, + Inc. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . */ + +/* As a special exception, you may create a larger work that contains + part or all of the Bison parser skeleton and distribute that work + under terms of your choice, so long as that work isn't itself a + parser generator using the skeleton or a modified version thereof + as a parser skeleton. Alternatively, if you modify or redistribute + the parser skeleton itself, you may (at your option) remove this + special exception, which will cause the skeleton and the resulting + Bison output files to be licensed under the GNU General Public + License without this special exception. + + This special exception was added by the Free Software Foundation in + version 2.2 of Bison. */ + +/* Undocumented macros, especially those whose name start with YY_, + are private implementation details. Do not rely on them. */ + +#ifndef YY_YY_PARSER_H_INCLUDED +# define YY_YY_PARSER_H_INCLUDED +/* Debug traces. */ +#ifndef YYDEBUG +# define YYDEBUG 0 +#endif +#if YYDEBUG +extern int yydebug; +#endif + +/* Token type. */ +#ifndef YYTOKENTYPE +# define YYTOKENTYPE + enum yytokentype + { + ADD = 258, + SUB = 259, + MULT = 260, + DIV = 261, + INTEGER = 262 + }; +#endif + +/* Value type. */ +#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED +union YYSTYPE +{ +#line 15 "cppython.y" + + int value; + char* op; + ast_node* expression; + +#line 71 "parser.h" + +}; +typedef union YYSTYPE YYSTYPE; +# define YYSTYPE_IS_TRIVIAL 1 +# define YYSTYPE_IS_DECLARED 1 +#endif + + +extern YYSTYPE yylval; + +int yyparse (void); + +#endif /* !YY_YY_PARSER_H_INCLUDED */ diff --git a/src/parser.output b/src/parser.output new file mode 100644 index 0000000..7135396 --- /dev/null +++ b/src/parser.output @@ -0,0 +1,177 @@ +Grammar + + 0 $accept: input $end + + 1 input: %empty + 2 | expr + + 3 expr: term ADD term + 4 | term SUB term + 5 | term + + 6 term: factor MULT factor + 7 | factor DIV factor + 8 | factor + + 9 factor: INTEGER + + +Terminals, with rules where they appear + + $end (0) 0 + error (256) + ADD (258) 3 + SUB (259) 4 + MULT (260) 6 + DIV (261) 7 + INTEGER (262) 9 + + +Nonterminals, with rules where they appear + + $accept (8) + on left: 0 + input (9) + on left: 1 2 + on right: 0 + expr (10) + on left: 3 4 5 + on right: 2 + term (11) + on left: 6 7 8 + on right: 3 4 5 + factor (12) + on left: 9 + on right: 6 7 8 + + +State 0 + + 0 $accept: . input $end + + INTEGER shift, and go to state 1 + + $default reduce using rule 1 (input) + + input go to state 2 + expr go to state 3 + term go to state 4 + factor go to state 5 + + +State 1 + + 9 factor: INTEGER . + + $default reduce using rule 9 (factor) + + +State 2 + + 0 $accept: input . $end + + $end shift, and go to state 6 + + +State 3 + + 2 input: expr . + + $default reduce using rule 2 (input) + + +State 4 + + 3 expr: term . ADD term + 4 | term . SUB term + 5 | term . + + ADD shift, and go to state 7 + SUB shift, and go to state 8 + + $default reduce using rule 5 (expr) + + +State 5 + + 6 term: factor . MULT factor + 7 | factor . DIV factor + 8 | factor . + + MULT shift, and go to state 9 + DIV shift, and go to state 10 + + $default reduce using rule 8 (term) + + +State 6 + + 0 $accept: input $end . + + $default accept + + +State 7 + + 3 expr: term ADD . term + + INTEGER shift, and go to state 1 + + term go to state 11 + factor go to state 5 + + +State 8 + + 4 expr: term SUB . term + + INTEGER shift, and go to state 1 + + term go to state 12 + factor go to state 5 + + +State 9 + + 6 term: factor MULT . factor + + INTEGER shift, and go to state 1 + + factor go to state 13 + + +State 10 + + 7 term: factor DIV . factor + + INTEGER shift, and go to state 1 + + factor go to state 14 + + +State 11 + + 3 expr: term ADD term . + + $default reduce using rule 3 (expr) + + +State 12 + + 4 expr: term SUB term . + + $default reduce using rule 4 (expr) + + +State 13 + + 6 term: factor MULT factor . + + $default reduce using rule 6 (term) + + +State 14 + + 7 term: factor DIV factor . + + $default reduce using rule 7 (term) diff --git a/src/sym_tab.c b/src/sym_tab.c new file mode 100644 index 0000000..546bd66 --- /dev/null +++ b/src/sym_tab.c @@ -0,0 +1,34 @@ +#include "sym_tab.h" + + +void add_word(int key, char *name) { + struct word *s; + HASH_FIND_INT(symbol_table, &key, s); + if (s == NULL) { + s = (struct word *) malloc(sizeof *s); + s->key = key; + HASH_ADD_INT(symbol_table, key, s); + } + strcpy(s->name, name); +} + +struct word *find_word(int word_key) { + struct word *s; + + HASH_FIND_INT(symbol_table, &word_key, s); + return s; +} + +void delete_word(struct word *s) { + HASH_DEL(symbol_table, s); + free(s); +} + +void delete_all() { + struct word *cur_word, *tmp; + + HASH_ITER(hh, symbol_table, cur_word, tmp) { + HASH_DEL(symbol_table, cur_word); + free(cur_word); + } +} \ No newline at end of file diff --git a/src/sym_tab.h b/src/sym_tab.h new file mode 100644 index 0000000..8e9422c --- /dev/null +++ b/src/sym_tab.h @@ -0,0 +1,19 @@ +#ifndef __SYM_TAB_H__ +#define __SYM_TAB_H__ + +#include "uthash.h" + +struct word { + int key; + char name[50]; + UT_hash_handle hh; /* makes this structure hashable */ +}; + +struct word *symbol_table; + +void add_word(int key, char *name); +struct word *find_word(int word_key); +void delete_word(struct word *s); +void delete_all(); + +#endif // __SYM_TAB_H__ \ No newline at end of file diff --git a/src/tests/invalid_1.ppy b/src/tests/lexer/invalid_1.ppy similarity index 100% rename from src/tests/invalid_1.ppy rename to src/tests/lexer/invalid_1.ppy diff --git a/src/tests/invalid_2.ppy b/src/tests/lexer/invalid_2.ppy similarity index 100% rename from src/tests/invalid_2.ppy rename to src/tests/lexer/invalid_2.ppy diff --git a/src/tests/valid_1.ppy b/src/tests/lexer/valid_1.ppy similarity index 100% rename from src/tests/valid_1.ppy rename to src/tests/lexer/valid_1.ppy diff --git a/src/tests/valid_2.ppy b/src/tests/lexer/valid_2.ppy similarity index 100% rename from src/tests/valid_2.ppy rename to src/tests/lexer/valid_2.ppy diff --git a/src/tests/parser/invalid_1.ppy b/src/tests/parser/invalid_1.ppy new file mode 100644 index 0000000..b297393 --- /dev/null +++ b/src/tests/parser/invalid_1.ppy @@ -0,0 +1 @@ +1 ^ diff --git a/src/tests/parser/invalid_2.ppy b/src/tests/parser/invalid_2.ppy new file mode 100644 index 0000000..f673cd9 --- /dev/null +++ b/src/tests/parser/invalid_2.ppy @@ -0,0 +1,2 @@ +1 + 1 +@ diff --git a/src/tests/parser/valid_1.ppy b/src/tests/parser/valid_1.ppy new file mode 100644 index 0000000..8d2f097 --- /dev/null +++ b/src/tests/parser/valid_1.ppy @@ -0,0 +1 @@ +1 + 1 diff --git a/src/tests/parser/valid_2.ppy b/src/tests/parser/valid_2.ppy new file mode 100644 index 0000000..30ec71b --- /dev/null +++ b/src/tests/parser/valid_2.ppy @@ -0,0 +1 @@ +5 - 1