/****************************************************/
/* 文件：scan.c                                     */
/* TINY掃描程序的執行代碼							*/
/****************************************************/

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

/* 掃描程序有限自動機的狀態 */
typedef enum
   { START,INASSIGN,INCOMMENT,INNUM,INID,DONE }
   StateType;

/* 用來保存當前保留字或者標識符 */
char tokenString[MAXTOKENLEN+1];

/* BUFLEN定義源文件行中的最大字符數 */
#define BUFLEN 256

static char lineBuf[BUFLEN]; /* 保留當前行 */
static int linepos = 0; /* 保存LineBuf中的當前位置 */
static int bufsize = 0; /* 當前緩存中保存的字符數 */
static int EOF_flag = FALSE; /* 當遇到EOF（文件結束符）調整ungetNextChar的操作 */

/* getNextCharlineBuf取得下一個非空格的字符。如果讀完了緩存中的全部字符，
   就把新的一行讀入緩存 */
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把一個字符退回到lineBuf緩存中 */
static void ungetNextChar(void)
{ if (!EOF_flag) linepos-- ;}

/* 保留字表*/
static struct
    { char* str;
      TokenType tok;
    } reservedWords[MAXRESERVED]
   = {{"if",IF},{"then",THEN},{"else",ELSE},{"end",END},
      {"repeat",REPEAT},{"until",UNTIL},{"read",READ},
      {"write",WRITE}};

/* T I N Y對保留字的識別是通過首先將它們看作是標識符，
 * 之后再在保留字表中查找它們來完成的。
 * 我們的掃描程序使用了一種非常簡便的方法—線性搜索，
 * 即按順序從開頭到結尾搜索表格。這對于小型表格不成問題。
 */

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;
}

/****************************************/
/* 分析程序的主函數  */
/****************************************/
/* 耗輸入字符并根據圖8.2.1
 * 中的DFA返回下一個被識別的記號
 */
TokenType getToken(void)
{  /* tokenString的引索 */
   int tokenStringIndex = 0;
   /* 保存當前要返回的記號 */
   TokenType currentToken;
   /* 當前的狀態－總是從START開始 */
   StateType state = START;
   /* 是否保存到tokenString的標記 */
   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 == ' ') || (c == '\t') || (c == '\n'))
           save = FALSE;
         else if (c == '{')
         { save = FALSE;
           state = INCOMMENT;
         }
         else
         { state = DONE;
           switch (c)
           { case EOF:
               save = FALSE;
               currentToken = ENDFILE;
               break;
             case '=':
               currentToken = EQ;
               break;
             case '<':
               currentToken = LT;
               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;
               break;
           }
         }
         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
		   /*退回到緩存中 */
           ungetNextChar();
           save = FALSE;
           currentToken = ERROR;
         }
         break;
       case INNUM:
         if (!isdigit(c))
         { /* 退回到緩存中 */
           ungetNextChar();
           save = FALSE;
           state = DONE;
           currentToken = NUM;
         }
         break;
       case INID:
         if (!isalpha(c))
         { /* 退回到緩存中 */
           ungetNextChar();
           save = FALSE;
           state = DONE;
           currentToken = ID;
         }
         break;
       case DONE:
       default: 
         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;
}