com.c

这是一个功能比较完善的词法分析器

/****************************************************/
/* File: c.c                                     */
/* The scanner implementation for the C-Minus compiler */
/* Compiler Construction: Principles a*/
/****************************************************/

#include "GLOBALS2.H"
#include "UTIL.H"
#include "scan.h"

/* states in scanner DFA */
typedef enum
   { START,INID,INNUM,Done,Inassign,Incomment1,Incomment2,M,N}
   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[MAXTOKENLEN]
   = {{"if",IF},{"else",ELSE},{"int",INT},{"return",RETURN},{"void",VOID},{"while",WHILE}};

/* 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<MAXTOKENLEN;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 includes：START,ASSIGN,EQ,LT,PLUS,MINUS,TIMES,OVER,LPAREN,RPAREN,SEMI
   */StateType state = START;
   /* flag to indicate save to tokenString */
   int save;
   int judge;
   while (state != DONE)
   { int c = getNextChar();
     save = TRUE;

     switch (state)
     { case START:
         if (isdigit(c))
           state = INNUM;
         else if (isalpha(c))
           state = INID;
         else if (c == '!')
           state = M; 
		 else if ((c == ' ') || (c == '\t') || (c == '\n'))
           save = FALSE;
         else if (( c== '<')||(c == '>') ||(c == '='))
		 {
			judge = c;
			state = Inassign;
		 }
         else if (c == '/')
           state = N;
       
         else
         { state = DONE;
           switch (c)
           { case EOF:
               save = FALSE;
               currentToken = ENDFILE;
               break;
             case '+':
               currentToken = PLUS;
               break;
             case '-':
               currentToken = MINUS;
               break;
             case '*':
               currentToken = TIMES;
               break;
             case '(':
               currentToken = LPAREN;
               break;
             case ')':
               currentToken = RPAREN;
               break;
             case '{':
               currentToken = BL;
               break;
             case '}':
               currentToken = BR;
               break;
             case '[':
               currentToken = ML;
               break;
             case ']':
               currentToken = MR;
               break;
             case ';':
               currentToken = SEMI;
               break;
             case ',':
               currentToken = COMMA;
               break;
			 
             default:
               currentToken = ERROR;
               break;
		   }
         }
		 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 N:
         if (c == EOF)
         { state = DONE;
		   save = FALSE;
           currentToken = ENDFILE;
         }
         else if (c == '*') 
		 { save = FALSE;
		   state = INCOMMENT1;
		 }
         else 
		 { currentToken = OVER;
		   state = DONE;
		 }
		 break;

       case INCOMMENT1:
		 if (c == '*') state = INCOMMENT2;
         else state = INCOMMENT1;
		 break;
   
       case INCOMMENT2:
         if (c == '*') state = INCOMMENT2;
         else if (c == '/') 
		 {  state = DONE;
		    currentToken = INC;
		 }
         else state = INCOMMENT1;
		 break;

       case M:
         state = DONE;
         if (c == '=')
           currentToken = UN;
         else
         { /* backup in the input*/
           ungetNextChar();
           save = FALSE;
           state = DONE;
           currentToken = ERROR;
         }
         break;

        case Inassign:
          state = DONE;
          if(c=='=')
        {
          if(judge=='>')
          currentToken=MORETHAN_EQ;       
          if(judge=='=')
          currentToken=EQ;
          if(judge=='<')
          currentToken=LESSTHAN_EQ;
        }
        else
         {if(judge=='>')
          currentToken=MORETHAN;
          if(judge=='=')
          currentToken=E;
          if(judge=='<')
          currentToken=LESSTHAN;

       }
         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);
     }
   }
   //如果跟踪词法分析的结果则打印相应的信息
   if (TraceScan) {
     fprintf(listing,"\t%d: ",lineno);
     printToken(currentToken,tokenString);
   }
   return currentToken;
 /* end getToken */
}