Tiny C 语言编译程序实验一 Scanner

Tiny C语言编译程序实验一Scanner

要求：填写getToken( )函数，完成词法分析器scan.c。

约定：

?仅允许整数类型，不允许实数类型

?标识符由大小写英文字母组成，最多52个。其识别按最长匹配原则

?整数后紧跟非数字，或标识符后紧跟非字母认为是一个新Token开始

?由{ }括起来符号串都认为是注释部分，该部分在词法分析时被过滤掉

?识别出的Token由两个变量：currentToken，tokenString识别，其中currentToken

代表Token的类属，为一个名为TokenType的枚举类型，在文件globals.h中定义；

tokenString代表Token在程序中出现的形式，即其本来面目。例如整数10的

currentToken值为NUM，而tokenString值为‘10’；标识符i的currentToken值为

ID，而tokenString值为‘i’

typedef enum

{ ENDFILE,ERROR,

IF,THEN,ELSE,END,REPEAT,UNTIL,READ,WRITE, /* 保留字*/

ID,NUM,

ASSIGN,EQ,LT,PLUS,MINUS,TIMES,OVER,LPAREN,RPAREN,SEMI

:= = < + - * / ( ) ;

} TokenType;

画识别符合TINY C语言构词规则的DFA。然后用直接编码的方法构造词法分析器

/****************************************************/

/* File: scan.c */

/* The scanner implementation for the TINY compiler */

/****************************************************/

#include "globals.h"

#include "util.h"

#include "scan.h"

typedef enum

{START, INASSIGN, INCOMMENT, INNUM, INID, DONE } StateType;

char tokenString[MAXTOKENLEN+1];

static int getNextChar(void) //获得下一字符

static struct

{ char* str;

TokenType tok;

} reservedWords[MAXRESERVED]

= {{"if",IF},{"then",THEN},{"else",ELSE},{"end",END},

{"repeat",REPEA T},{"until",UNTIL},{"read",READ},

{"write",WRITE}}; //定义保留字表

static TokenType reservedLookup (char * s) //进行保留字的匹配

{实现请自己看scan.c文件}

/**********************************************/

/* the primary function of the scanner */

/* function getToken returns the next token in source file */

/**********************************************/

TokenType getToken(void)

{ int tokenStringIndex = 0;

TokenType currentToken; //保存被识别Token的类属

StateType state = START; //初始状态为START

int save; //标识当前字符是否保存，如空格，换行符\n、TAB符\t及注释中的任何字符while (state != DONE) //DONE状态表示已识别出一个Token

{ int c = getNextChar();

save = TRUE;

switch (state)

{ case START:

if (isdigit(c))

state = INNUM;

else if (isletter(c))

state=INID;

else if(c==':')

state=INASSIGN;

else if(c=='{')

state=INCOMMENT;

else

{

state=DONE;

currentToken=END;

}

break;

case INCOMMENT:

if(c=='}')

{

state=DONE;

currentToken=END;

}

break;

case INASSIGN:

if(c=='=')

{

state=DONE;

currentToken=ASSIGN;

}

else

{

error();

currentToken=ERROR

} ;/* 此处已填写完整 */

break;

case INNUM:

if (!isdigit(c))

{ /* backup in the input */

ungetNextChar();

save = FALSE;

state = DONE;

currentToken = NUM;

}

break;

case INID:

if (!isletter(c))

{ /* backup in the input */

ungetNextChar();

save = FALSE;

state = DONE;

currentToken =ID;

break;

case DONE: //不可能到

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);

}

} ---------end WHILE

if (TraceScan) {

fprintf(listing,"\t%d: ",lineno);

printToken(currentToken,tokenString);

}

return currentToken;

} /* end getToken */