compiler-construction - 测试空白文件时的语法错误

问题描述

因此，基本上，每当我测试空文件或仅包含注释的文件时，都会出现语法错误。错误如下所示：

test01 只是一个空的 .c 文件

这是我的 Lex 文件：

%{
/*constants are defined outside of the l file in y.tab.h
*constants are defined from 257
*/

#include "y.tab.h"
int input_line_no = 1;
char the_tokens[1000];
char full_line[1000];
int lex_state = 0;

%}

whitespace         [ \t]
number             [0-9]
letter             [A-Za-z]
alfanum            [A-Za-z0-9_]
intcon             {number}+
id                 {letter}{alfanum}*
anything           .

%option noyywrap
 /*
 *Start conditions are specified to identify comments, 
 *literal strings, and literal chars. 
 */

%Start comment_in comment_out string_in char_in

%%

/*tokenization of special strings*/
"extern"        {return EXTERN;}
"if"            {return IF;}
"else"          {return ELSE;}
"void"          {return VOID;}
"char"          {return CHAR;}
"int"           {return INT;}



 /*line number is recorded*/
[\n]                        input_line_no++;

 /*identify comment*/
<INITIAL>"/""*"      {
                lex_state=1;
                                BEGIN(comment_in);
                 }
<comment_in>"*"      BEGIN(comment_out);
<comment_in>[^*]     ;
<comment_out>"*"     ;
<comment_out>"/"     {
            lex_state = 0;
                    BEGIN(INITIAL);
                 }
<comment_out>[^*/]   BEGIN(comment_in);

/*start tokenization of strings*/
<INITIAL>\"             {
            lex_state = 2;
                            BEGIN(string_in);

                    }
<string_in>[^"]     {
            return STRINGCON;
        }
<string_in>\"       {
            lex_state = 0;
            BEGIN(INITIAL);
        }
 /*tokenization of characters*/
<INITIAL>\' {
        lex_state = 3;
        BEGIN(char_in);
    }
<char_in>[^']
     {
         return CHARCON;
     }
<char_in>\' {
        lex_state = 0;
        BEGIN(INITIAL);
    }

{whitespace}    ;

 /*tokenization of numbers*/
{intcon}         {return(INTCON);}
{id}        {return ID;}

/*tokenization of operations*/
"=="        {return EQUALS;}
"!="        {return NOTEQU;}
">="        {return GREEQU;}
"<="        {return LESEQU;}
">"     {return GREATE;}
"<"     {return LESSTH;}

"&&"        {return ANDCOM;}
"||"        {return ORCOMP;}
"!"             {return ABANG;}

";"     {return SEMIC;}
","     {return COMMA;}
"("     {return LPAR;}
")"     {return RPAR;}      
"["     {return LBRAC;}
"]"     {return RBRAC;}
"{"     {return LCURL;}
"}"     {return RCURL;}

"+"     {return ADD;}
"-"     {return SUB;}
"*"     {return MUL;}
"/"     {return DIV;}
"="     {return EQUAL;}

 /*For strings that can not be identified by any patterns specified previously
 *lex returns the value of the character
 */

  {anything}     {return(OTHER);}

%%

这是我的 Yacc 文件：

    %{

#include <stdio.h>
#define YDEBUG
#ifndef YDEBUG

#define Y_DEBUG_PRINT(x)

#else

#define Y_DEBUG_PRINT(x) printf("Yout %s \n ",x)

#endif
int yydebug = 1; 

extern char the_token[]; 
 /* This is how I read tokens from lex... :) */
extern int input_line_no; 
 /* This is the current line number */
extern char *full_line; 
 /* This is the full line */
extern int lex_state;


%}

%token STRINGCON CHARCON INTCON EQUALS NOTEQU GREEQU LESEQU GREATE LESSTH
%token ANDCOM ORCOMP SEMIC COMMA LPAR RPAR LBRAC RBRAC LCURL RCURL ABANG
%token EQUAL ADD SUB MUL DIV ID EXTERN FOR WHILE RETURN IF ELSE 
%token VOID CHAR INT OTHER

%left ORCOMP
%left ANDCOM
%left EQUALS NOTEQU
%left LESSTH GREATE LESEQU GREEQU
%left ADD SUB
%left MUL DIV
%right UMINUS
%right ABANG

%start Assign
%%

prog: dcl SEMIC prog2 {Y_DEBUG_PRINT("prog-dcl-SEMIC-prog2");}
| Function prog2 {Y_DEBUG_PRINT("prog-Function-prog2");}

prog2: {Y_DEBUG_PRINT("prog2-EMPTY");}
| dcl SEMIC prog2 {Y_DEBUG_PRINT("prog2-dcl-SEMIC-prog2");}
| Function  prog2 {Y_DEBUG_PRINT("prog2-Function-prog2");}

dcl: VAR_list {Y_DEBUG_PRINT("dcl-VAR_list");}
| ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl-ID-LPAR-Param_types-RPAR-dcl2");}
| EXTERN ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl-EXTERN-ID-LPAR-Param_types-RPAR-dcl2");}
| EXTERN Type ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl-EXTERN-Type-ID-LPAR-Param_types-RPAR-dcl2");}
| EXTERN VOID ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl-EXTERN-VOID-ID-LPAR-Param_types-RPAR-dcl2");}
| Type ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl-Type-ID-LPAR-Param_types-RPAR-dcl2");}
| VOID ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl-VOID-ID-LPAR-Param_types-RPAR-dcl2");}

dcl2: {Y_DEBUG_PRINT("dcl2-EMPTY");}
| COMMA ID LPAR Param_types RPAR dcl2 {Y_DEBUG_PRINT("dcl2-COMMA-ID-LPAR-Param_types-RPAR-dcl2");}

Function: Functionhead LCURL Functionbody RCURL {Y_DEBUG_PRINT("Function-Functionhead-LCURL-Functionbody-RCURL");}
| VOID Functionhead LCURL Functionbody RCURL {Y_DEBUG_PRINT("Function-VOID-Functionhead-LCURL-Functionbody-RCURL");}
| Type Functionhead LCURL Functionbody RCURL {Y_DEBUG_PRINT("Function-Type-Functionhead-LCURL-Functionbody-RCURL");}

Functionhead: ID LPAR Param_types RPAR {Y_DEBUG_PRINT("Functionhead-ID-LPAR-Param_types-RPAR");}

Functionbody: VAR_list STMT_list {Y_DEBUG_PRINT("Functionbody-Varlist-Stmtlist");}

Param_types: VOID {Y_DEBUG_PRINT("Param_types-VOID");}
|Param_types1 {Y_DEBUG_PRINT("Param_types-Param_types1");}

Param_types1: Param_type1 {Y_DEBUG_PRINT("Param_types1-Param_type1");}
| Param_types1 COMMA Param_type1 {Y_DEBUG_PRINT("Param_types1-Param_types1-COMMA-Param_type1");}

Param_type1: Type ID Param_type11 {Y_DEBUG_PRINT("PARAM_type1-Type-ID-Param_type11");}

Param_type11: {Y_DEBUG_PRINT("Param_type11-EMPTY");}
| LBRAC RBRAC {Y_DEBUG_PRINT("Param_type11-LBRAC-RBRAC");}

VAR_list: Type VAR_list2 {Y_DEBUG_PRINT("VAR_list-Type-VAR_list2");}

VAR_list2: var_decl {Y_DEBUG_PRINT("VAR_list2-var_decl");}
| var_decl COMMA VAR_list2 {Y_DEBUG_PRINT("VAR_list2-var_decl-COMMA-VAR_list2");}

var_decl: ID {Y_DEBUG_PRINT("var_decl-ID");}
| ID LBRAC INTCON RBRAC {Y_DEBUG_PRINT("var-decl-ID-LBRAC-INTCON-RBRAC");}

Type: CHAR {Y_DEBUG_PRINT("Type-CHAR");}
|INT {Y_DEBUG_PRINT("Type-INT");}

STMT_list: STMT2 {Y_DEBUG_PRINT("STMT-list-STMT2");}

STMT2: STMT {Y_DEBUG_PRINT("STMT2-STMT");}
| STMT STMT2 {Y_DEBUG_PRINT("STMT2-STMT-STMT2");}

STMT : IF LPAR Expr RPAR STMT {Y_DEBUG_PRINT("IF-LPARN-Expr-RPARN-STMT");}
| IF LPAR Expr RPAR STMT ELSE STMT{Y_DEBUG_PRINT("IF-LPARN-Expr-RPARN-STMT-ELSE-STMT");}
 /*if cats) ERROR*/
| IF Expr RPAR STMT ELSE STMT {warn("STMT-IF: missing LPAR");}
 /*if (cats ERROR*/
| IF LPAR Expr STMT ELSE STMT {warn("STMT-IF: missing RPAR");}
 /*two elses ERROR*/
| IF LPAR Expr STMT ELSE ELSE STMT {warn(":too many elses");}
| WHILE LPAR Expr RPAR STMT{Y_DEBUG_PRINT("STMT-WHILE-LPAR-Expr-RPAR-STMT");}
 /*for(c=0;c<1;c++)*/
| FOR LPAR Assign SEMIC Expr SEMIC Assign RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-Assign-SEMIC-Expr-SEMIC-Assign-RPAR-STMT");}
 /*for(;c<1;c++)*/
| FOR LPAR SEMIC Expr SEMIC Assign RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-SEMIC-Expr-SEMIC-Assign-RPAR-STMT");}
 /*for(;;c++)*/
| FOR LPAR SEMIC SEMIC Assign RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-SEMIC-SEMIC-Assign-RPAR-STMT");}
 /*for(;;)*/
| FOR LPAR SEMIC SEMIC RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-SEMIC-SEMIC-RPAR-STMT");}
 /*for(c=0;;)*/
| FOR LPAR Assign SEMIC SEMIC RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-Assign-SEMIC-SEMIC-RPAR-STMT");}
 /*for(c=0;c<1;)*/
| FOR LPAR Assign SEMIC Expr SEMIC RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-Assign-SEMIC-Expr-Semic-RPAR-STMT");}
 /*for(c=0;;c++)*/
| FOR LPAR Assign SEMIC SEMIC Assign RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-Assign-SEMIC-SEMIC-ASSIGN-RPAR-STMT");}
 /*for(;c<1;)*/
| FOR LPAR SEMIC Expr SEMIC RPAR STMT {Y_DEBUG_PRINT("STMT-FOR-LPAR-SEMIC-Expr-SEMIC-RPAR-STMT");}
 /*for() ERROR*/
| FOR LPAR RPAR STMT {warn("STMT-FOR: empty statement");}
 /*for{;;;) ERROR*/
| FOR LPAR SEMIC SEMIC SEMIC RPAR {warn("STMT-FOR: too many semicolons");}
 /*for;;) ERROR*/
| FOR SEMIC SEMIC RPAR STMT {warn("STMT-FOR: missing LPAR");}
 /*for(;; ERROR*/   
| FOR LPAR SEMIC SEMIC STMT {warn("STMT-FOR: missing RPAR");}
| RETURN Expr SEMIC {Y_DEBUG_PRINT("STMT-RETURN-Expr-SEMIC");}
| RETURN SEMIC {Y_DEBUG_PRINT("STMT-RETURN-SEMIC");}
 /*return ERROR*/
| RETURN {warn("STMT-Return:missing semicolon");}
| Assign SEMIC {Y_DEBUG_PRINT("STMT-Assign-SEMIC");}
/*function call*/
| ID LPAR RPAR SEMIC {Y_DEBUG_PRINT("STMT-ID-LPAR-RPAR-SEMIC");}
| ID LPAR Expr Expr2 RPAR SEMIC {Y_DEBUG_PRINT("STMT-ID-LPAR-Expr-Expr2-RPAR-SEMIC");}
 /*No semic ERROR*/
| ID LPAR Expr Expr2 RPAR {warn(":missing semicolon");}  
| LCURL STMT2 RCURL {Y_DEBUG_PRINT("STMT-LCURL-STMT-RCURL");}
| LCURL RCURL {Y_DEBUG_PRINT("STMT-LCURL-RCURL");}
| SEMIC {Y_DEBUG_PRINT("STMT-SEMIC");}

Assign : ID Assign1 EQUAL Expr {Y_DEBUG_PRINT("Assign-1-ID-Assign1-EQUAL-Expr");}
 /*Error no semi*/
| Assign {warn( "Assign: missing semicolon on line");}

Assign1 : {Y_DEBUG_PRINT("Assign1-1-Empty"); }
| LBRAC Expr RBRAC {Y_DEBUG_PRINT("Assign1-2-LBRAC-Expr-RBRAC"); }
| LBRAC Expr error { warn("Assign1: missing RBRAC"); }
| error Expr RBRAC { warn("Assign1: missing LBRAC"); }
| LBRAC error RBRAC { warn("Assign1: Invalid array index"); }

Expr : SUB Expr %prec UMINUS {Y_DEBUG_PRINT("Expr-1-UMINUS Expr"); }
| ABANG Expr {Y_DEBUG_PRINT("Expr-2-ANABG Expr"); }
| Expr Binop Expr {Y_DEBUG_PRINT("Expr-3-Expr-Binop-Expr"); }
| Expr Relop Expr {Y_DEBUG_PRINT("Expr-4-Expr-Binop-Expr"); }
| Expr Logop Expr {Y_DEBUG_PRINT("Expr-5-Expr-Logop-Expr"); }
| ID {Y_DEBUG_PRINT("Expr-6-ID"); }
| ID LPAR RPAR {Y_DEBUG_PRINT("Expr-ID-LPAR-RPAR");} 
| ID LPAR Expr Expr2 RPAR {Y_DEBUG_PRINT("Expr-ID-LPAR-Expr-Expr2-RPAR");}
| ID LBRAC Expr RBRAC {Y_DEBUG_PRINT("Expr-ID-LBRAC-Expr-RBRAC");}
| LPAR Expr RPAR {Y_DEBUG_PRINT("Expr-7-LPARN-Expr-RPARN");} 
| INTCON { Y_DEBUG_PRINT("Expr-8-INTCON"); }
| CHARCON { Y_DEBUG_PRINT("Expr-9-CHARCON"); }
| STRINGCON { Y_DEBUG_PRINT("Expr-10-STRINGCON"); }
| Array {Y_DEBUG_PRINT("Expr-11-Array"); }
| error {warn("Expr: invalid expression "); }

/*top is for no expression 2*/
Expr2: {Y_DEBUG_PRINT("Expr2-Empty");}
| COMMA Expr {Y_DEBUG_PRINT("Expr2-COMMA-Expr");}
 /*recursively looks for another expression in function call (exp1,exp2,exp3,...*/
| COMMA Expr Expr2 {Y_DEBUG_PRINT("Expr2-COMMA-Expr-Expr2");}


Array : 
ID LBRAC Expr RBRAC {Y_DEBUG_PRINT("Array-1-ID-LBRAC-Expr-RBRAC"); }
| ID error RBRAC {warn( "Array: invalid array expression"); }

Binop : ADD {Y_DEBUG_PRINT("Binop-1-ADD"); }
| SUB {Y_DEBUG_PRINT("Binop-2-SUB"); }
| MUL {Y_DEBUG_PRINT("Binop-3-MUL"); }
| DIV {Y_DEBUG_PRINT("Binop-4-DIV"); }

Logop : ANDCOM {Y_DEBUG_PRINT("Logop-1-ANDCOM"); }
| ORCOMP {Y_DEBUG_PRINT("Logop-2-ORCOMP"); }

Relop : EQUALS { Y_DEBUG_PRINT("Relop-1-EQUALS"); }

| NOTEQU { Y_DEBUG_PRINT("Relop-2-NOTEQU"); }

| LESEQU { Y_DEBUG_PRINT("Relop-3-LESEQU"); }

| GREEQU { Y_DEBUG_PRINT("Relop-4-GREEQU"); }

| GREATE { Y_DEBUG_PRINT("Relop-5-GREATE"); }

| LESSTH { Y_DEBUG_PRINT("Relop-6-LESSTH"); }


%%

main()
{
int result = yyparse();
if (lex_state==1) {
yyerror("End of file within a comment");
}
if (lex_state==2) {
yyerror("End of file within a string");
}
return result;
} 
int yywrap(){
return 1;
}
yyerror(const char *s)
{
fprintf(stderr, "%s on line %d\n",s,input_line_no);
} 
warn(char *s)
{
fprintf(stderr, "%s\n", s);
}

基本上，这应该是编译器的词法分析器和解析器部分。由于 C- 语法规则，我正在尝试解析代码。我已经尝试向 Lexer 添加文件结束规则，但它只是产生了与以前相同的错误，所以我认为这不是问题所在。

有什么方法可以判断 Lexer 是否已将正确的标记传递给解析器？

另外，我被告知要检查 y.output 文件，以查看如何修复解析器的 shift/reduce 错误，但我查看了该文件，不知道如何判断错误在哪里。

我知道我的 Yacc 代码可能存在很多问题，但目前我只是试图修复这一个错误，以便我可以处理其他错误。任何帮助将不胜感激，谢谢。

标签： compiler-constructionsyntax-erroryacclex

compiler-construction - 测试空白文件时的语法错误 - LEX/YACC

问题描述

解决方案

推荐阅读