scan.c

小型编译器,可以用于测试使用

/****************************************************/
/* File: scan.c                                     */
/* The scanner implementation for the TINY compiler */
/* Compiler Construction: Principles and Practice   */
/* Kenneth C. Louden                                */
/****************************************************/

#include "globals.h"
#include "util.h"
#include "scan.h"

/* states in scanner DFA */
typedef enum
   { START,INASSIGN,INCOMMENT,INNUM,INID,DONE,
   INSTR,INLE,INGE }//修改
   StateType;

/* lexeme of identifier or reserved word */
char tokenString[MAXTOKENLEN+1];

/* BUFLEN = length of the input buffer for
   source code lines */
#define BUFLEN 256

static char lineBuf[BUFLEN]; /* holds the current line */
static int linepos = 0; /* current position in LineBuf */
static int bufsize = 0; /* current size of buffer string */
static int EOF_flag = FALSE; /* corrects ungetNextChar behavior on EOF */

/* getNextChar fetches the next non-blank character
   from lineBuf, reading in a new line if lineBuf is
   exhausted */
static int getNextChar(void)
{ if (!(linepos < bufsize))
  { lineno++;
    if (fgets(lineBuf,BUFLEN-1,source))
    { if (EchoSource) fprintf(listing,"%4d: %s",lineno,lineBuf);
      bufsize = strlen(lineBuf);
      linepos = 0;
      return lineBuf[linepos++];
    }
    else
    { EOF_flag = TRUE;
      return EOF;
    }
  }
  else return lineBuf[linepos++];
}

/* ungetNextChar backtracks one character
   in lineBuf */
static void ungetNextChar(void)
{ if (!EOF_flag) linepos-- ;}

/* lookup table of reserved words */
static struct
    { char* str;
      TokenType tok;
    } reservedWords[MAXRESERVED]
   = {{"if",IF},{"then",THEN},{"else",ELSE},{"end",END},
      {"repeat",REPEAT},{"until",UNTIL},{"read",READ},
      {"write",WRITE},
	{"true",BTRUE},{"false",BFALSE},{"or",OR},{"and",AND},{"not",NOT},{"int",INT},{"bool",BOOL},
	{"string",STRING},{"while",WHILE},{"do",DO}};//修改

/* lookup an identifier to see if it is a reserved word */
/* uses linear search */
static TokenType reservedLookup (char * s)
{ int i;
  for (i=0;i<MAXRESERVED;i++)
    if (!strcmp(s,reservedWords[i].str))
      return reservedWords[i].tok;
  return ID;
}

/****************************************/
/* the primary function of the scanner  */
/****************************************/
/* function getToken returns the 
 * next token in source file
 */
TokenType getToken(void)
{  /* index for storing into tokenString */
   int tokenStringIndex = 0;
   /* holds current token to be returned */
   TokenType currentToken;
   /* current state - always begins at START */
   StateType state = START;
   /* flag to indicate save to tokenString */
   int save;
   while (state != DONE)
   { char c = getNextChar();
     save = TRUE;
     switch (state)
     { case START:
         if (isdigit(c))
           state = INNUM;
         else if (isalpha(c))
           state = INID;
         else if (c == ':')
           state = INASSIGN;
         else if ((c == ' ') || (c == '\t') || (c == '\n'))
           save = FALSE;
         else if (c == '{')
         { save = FALSE;
           state = INCOMMENT;
         }
		 else if (c == '\'')//修改
		 {
			 save=FALSE;
			 state = INSTR;
		 }
		 else if (c == '<')//修改
			 state = INLE;
		 else if (c == '>')//修改
			 state = INGE;
		 else
         { state = DONE;
           switch (c)
           { case EOF:
               save = FALSE;
               currentToken = ENDFILE;
               break;
             case '=':
               currentToken = EQ;
               break;
             case ','://修改
				 currentToken = COMMA;
				 break;
             case '+':
               currentToken = PLUS;
               break;
             case '-':
               currentToken = MINUS;
               break;
             case '*':
               currentToken = TIMES;
               break;
             case '/':
               currentToken = OVER;
               break;
             case '(':
               currentToken = LPAREN;
               break;
             case ')':
               currentToken = RPAREN;
               break;
             case ';':
               currentToken = SEMI;
               break;
             default:
               currentToken = ERROR;
			   errortype = 1;
               break;
           }
         }
         break;
       case INCOMMENT:
         save =FALSE;
         if (c == EOF )		//缺少右括号 可以换行
         { 
			 state = DONE;
           currentToken = ERROR;
		   errortype = 2;
         }
         else if (c == '}') state = START;
         break;
	   case INSTR://修改
         save=TRUE;
		 if (c == '\'')
		 {
			 save = FALSE;
			 state = DONE;
			 currentToken = STR;
		 }
		 else if ( c == '\n' || c == EOF )//缺少右引号错误
		 {
			 save = FALSE;
			 currentToken = ERROR;
			 errortype = 3;
			 state = DONE;
		 }
         break;
	   case INLE://修改
		   state = DONE;
		   if (c == '=')
			   currentToken = LE;
		   else
		   {
			   ungetNextChar();
			   save = FALSE;
			   currentToken = LT;
		   }
		   break;
	   case INGE://修改
		   state = DONE;
		   if (c == '=')
			   currentToken = GE;
		   else
		   {
			   ungetNextChar();
			   save = FALSE;
			   currentToken = GT;
		   }
		   break;
       case INASSIGN:
         state = DONE;
         if (c == '=')
           currentToken = ASSIGN;
         else
         { /* backup in the input */
           ungetNextChar();
           save = FALSE;
           currentToken = ERROR;
         }
         break;
       case INNUM:
         if (!isdigit(c))
         { /* backup in the input */
           ungetNextChar();
           save = FALSE;
           state = DONE;
           currentToken = NUM;
         }
         break;
       case INID:
         if (!isalpha(c) && !isdigit(c))//修改
         { /* backup in the input */
           ungetNextChar();
           save = FALSE;
           state = DONE;
           currentToken = ID;
         }
         break;
       case DONE:
       default: /* should never happen */
         fprintf(listing,"Scanner Bug: state= %d\n",state);
         state = DONE;
         currentToken = ERROR;
		 errortype = 4;
         break;
     }
     if ((save) && (tokenStringIndex <= MAXTOKENLEN))
       tokenString[tokenStringIndex++] = (char) c;
     if (state == DONE)
     { tokenString[tokenStringIndex] = '\0';
       if (currentToken == ID)
         currentToken = reservedLookup(tokenString);
     }
   }
   if (TraceScan && currentToken!=ENDFILE) {//修改
     fprintf(listing,"\t%d: ",lineno);
     printToken(currentToken,tokenString);
   }

   return currentToken;
} /* end getToken */