/****************************************************/
/* File: scan.c                                     */
/* Main program for c- compiler                     */
/* Compiler Construction: Principles and Practice   */
/* Maker:Liukai                                     */
/****************************************************/
#include "globals.h"
#include "util.h"
#include "scan.h"

/* states in scanner DFA */
typedef enum
   { START , INASSIGN , INCOMMENT1 , INCOMMENT2 , INCOMMENT3 , INCOMMENT4 , INNUM , INID , INLT ,  INMT , INNEQ , DONE }
   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},{"else",ELSE},{"while",WHILE},
      {"int",INT},{"return",RETURN},{"void",VOID},
     };

/* 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();
     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 = INLT;
		 else if (c == '>')
           state = INMT;
		 else if (c == '!')
           state = INNEQ;
         else if ((c == ' ') || (c == '\t') || (c == '\n'))
           save = FALSE;
         else if (c == '/')
         { save = FALSE;
           state = INCOMMENT1;
         }
         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 = OVER;
               break;
			   */
             case '(':
               currentToken = LPAREN;
               break;
             case ')':
               currentToken = RPAREN;
               break;
             case ';':
				 currentToken = SEMI;
				 break;
			 case ',':
				 currentToken = DOUHAO;
				 break;
			 case '[':
				 currentToken = ZLPAREN;
				 break;
			 case ']':
				 currentToken = ZRPAREN;
				 break;
			 case '{':
				 currentToken = DLPAREN;
				 break;
			 case '}':
				 currentToken = DRPAREN;
				 break;
             default:
				 currentToken = ERROR;
				 break;
           }
         }
         break;
	 case INCOMMENT1:
		 save = false;
	//	 c = getNextChar();
		 if (c == '*') 
			 state = INCOMMENT2;
		 else
		 {
			  ungetNextChar();
			 ungetNextChar();
			 ungetNextChar();
			 ungetNextChar();
			 state = INCOMMENT4;
			 c = getNextChar();
		}
			
		
		 /*        if (c == EOF)
         { state = DONE;
		 currentToken = ENDFILE;
         }
		 */
		 
         break;
	 case INCOMMENT2:
		 save = false;
		 if(c == '*')
		 {
			 state = INCOMMENT3;
		 }
		 break;	
	 case INCOMMENT4:
		 save = true ;
		 c = getNextChar();
		 
			 state = DONE;
			 currentToken = OVER;

		
		 break;
	case INCOMMENT3:
		save = false ;
		if(c == '/')
		{
			state = START ;
			currentToken = OVER;
		}
		
		else
		{
			state = INCOMMENT2;
		}
		break;

		
	case INLT:
		state = DONE;
		if (c == '=')
			currentToken = LET;
		else
		{ /* backup in the input */
			ungetNextChar();
			save = false ;
			currentToken = LT;
		}
		break;
	case INMT:
		state = DONE;
		if (c == '=')
			currentToken = MET;
		else
		{ /* backup in the input */
			ungetNextChar();
			save = false ;
			currentToken = MT;
		}
		break;
	case INNEQ:
		state = DONE;
		if (c == '=')
			currentToken = NEQ;
		else
		{ /* backup in the input */
			ungetNextChar();
			save = false ;
			currentToken = ERROR;
		}
		break;
	case INASSIGN:
		state = DONE;
		if (c == '=')
			currentToken = EQ;
		else
		{ /* backup in the input */
			ungetNextChar();
			save = false ;
			currentToken = ASSIGN;
		}
		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 */