scan.c

1.小型编译器 2。支持整数

/****************************************************/
/* 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,INEQ,INNEQ,INLE,INGE,INAND,INOR }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
{ 
	const char* str;
  	TokenType tok;
} reservedWords[MAXRESERVED]
= {{"if",IF},{"else",ELSE},{"while",WHILE},{"return",RETURN},
	{"break",BREAK},{"continue",CONTINUE},{"int",NUM},
	{"char",SCHAR},{"void",VOID},{"double",DNUM}};

/* 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)
   	{ 
   		int c = getNextChar();
		
		//多取一位
		int	d = getNextChar();
		ungetNextChar();
		
     	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 == '=')
           			state = INEQ;
				else if (c == '|')
           			state = INOR;
         		else if ((c == ' ') || (c == '\t') || (c == '\n'))
           			save = FALSE;
         		else
         		{ 
         			state = DONE;
           			switch (c)
           			{ 
           				case EOF:
               				save = FALSE;
               				currentToken = ENDFILE;
               				break;
             			case '<':
							if(d == '='){
								state = INLE;
							}else {
               					currentToken = LT;
							}
               				break;
						case '>':
							if(d == '='){
								state = INGE;
							}else {
               					currentToken = GT;
							}
               				break;
						case '&':
							if(d == '&'){
								state = INAND;
							}else {
								//取地址
               					//currentToken = GT;
               					currentToken = ERROR;
							}
               				break;
             			case '+':
               				currentToken = PLUS;
               				break;
             			case '-':
               				currentToken = SUB;
               				break;
             			case '*':
               				currentToken = MUT;
              				break;
             			case '/':
               				currentToken = DIV;
               				break;
             			case '(':
               				currentToken = LP;
               				break;
             			case ')':
               				currentToken = RP;
               				break;
						case '{':
               				currentToken = LFP;
               				break;
             			case '}':
               				currentToken = RFP;
               				break;
						case '!':
							if(d == '='){
								state = INNEQ;
							}else {
               					currentToken = NOT;
							}
               				break;
             			case ';':
               				currentToken = SEMI;
               				break;
						case ',':
               				currentToken = COMMA;
               				break;
             			default:
               				currentToken = ERROR;
               				break;
           			}
         		}
         		break;

			case INLE:
				state = DONE;
         		if (c == '=')
           			currentToken = LE;
         		else
         		{ /* backup in the input */
           			ungetNextChar();
           			save = FALSE;
           			currentToken = ERROR;
         		}
         		break;
			case INGE:
				state = DONE;
         		if (c == '=')
           			currentToken = GE;
         		else
         		{ /* backup in the input */
           			ungetNextChar();
           			save = FALSE;
           			currentToken = ERROR;
         		}
         		break;
			case INEQ:
				state = DONE;
         		if (c == '=')
           			currentToken = EQ;
         		else
         		{ /* backup in the input */
           			ungetNextChar();
           			save = FALSE;
           			currentToken = ERROR;
         		}
         		break;
			case INNEQ:
				state = DONE;
         		if (c == '=')
           			currentToken = NEQ;
         		else
         		{ /* backup in the input */
           			ungetNextChar();
           			save = FALSE;
           			currentToken = ERROR;
         		}
         		break;
			case INOR:
				state = DONE;
         		if (c == '|')
           			currentToken = NOT;
         		else
         		{ /* backup in the input */
           			ungetNextChar();
           			save = FALSE;
           			currentToken = ERROR;
         		}
         		break;
			case INAND:
				state = DONE;
         		if (c == '|')
           			currentToken = AND;
         		else
         		{ /* backup in the input */
           			ungetNextChar();
           			save = FALSE;
           			currentToken = ERROR;
         		}
         		break;
				
       		case INCOMMENT:
         		save = FALSE;
         		if (c == EOF)
         		{ 
         			state = DONE;
           			currentToken = ENDFILE;
         		}
         		else if (c == '}') 
					state = START;
         		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))
         		{ /* 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;
         		break;
     	}
     	if ((save) && (tokenStringIndex <= MAXTOKENLEN))
       		tokenString[tokenStringIndex++] = (char) c;
     	if (state == DONE)
     	{ 
     		tokenString[tokenStringIndex] = '\0';
       		if (currentToken == ID)
         		currentToken = reservedLookup(tokenString);
     	}
   	}
   	if (TraceScan) {
     	fprintf(listing,"\t%d: ",lineno);
     	printToken(currentToken,tokenString);
   	}
   	return currentToken;
} /* end getToken */