语义分析

【实验目的】

 

通过上机实验，加深对语法制导翻译的理解，掌握将语法分析所识别的语法成分变换为中间代码的语义翻译方法。

 

【实验内容】

对给定的程序通过语义分析器能够判断语句串是否正确。正确则输出三地址指令形式的四元式代码，错误则抛出错误信息。

 

【设计思想】

（1）输入待分析的字符串。

语法如下：

a.关键字：begin,if,then,while,do,end.

b.运算符和界符：:= + - * / < <= > >= <> = ; ( ) #

c.其他单词是标识符(ID)和整形常数(NUM)：ID=letter(letter|digit)*，NUM=digitdigit*

d.空格由空白、制表符和换行符组成。空格一般用来分隔ID、NUM、运算符、界符和关键字，词法分析阶段通常被忽略。

（2）扫描字符串，采用递归向下进行分析。

主要函数如下：

a.scaner()//词法分析函数，char token[8]用来存放构成单词符号的字符串;

b.parser()//语法分析，在语法分析的基础上插入相应的语义动作：将输入串翻译成四元式序列。只对表达式、赋值语句进行翻译。

c.emit(char *result,char *arg1,char *op,char *ag2)//该函数功能是生成一个三地址语句返回四元式表中。

d.char *newtemp()//该函数返回一个新的临时变量名，临时变量名产生的顺序为T1,T2,…。

【实验要求】

四元式表的结构如下：

struct {char result[8];

char ag1[8];

char op[8];

char ag2[8];

}quad[20];

（3）输出为三地址指令形式的四元式序列。

例如：语句串begin  a:=2+3*4;x:=(a+b)/c;end#，

输出的三地址指令如下：

t1=3*4

t2=2+t1

a=t2

t3=a+b

t4=t3/c

x=t4

 

代码：

 

#include "stdio.h"

#include "string.h"

char prog[100], token[8], ch;

char *rwtab[6] = { "begin", "if", "then", "while", "do", "end" };

int syn, p, m, n, sum, q;

int kk;

struct {

char result1[8];

char ag11[8];

char op1[8];

char ag21[8];

} quad[20];

char *factor();

char *expression();

int yucu();

char *term();

int statement();

int lrparser();

char *newtemp();

scaner();

emit(char *result, char *ag1, char*op, char *ag2);

 

main()

{

int j;

q = p = kk = 0;

printf("\n**************************************");

printf("\nplease input a string (end with'#'): ");

do

{

scanf_s("%c", &ch);

prog[p++] = ch;

} while (ch != '#');

p = 0;

scaner();

lrparser();

if (q>19)printf(" too longsentense!\n");

else for (j = 0; j<q; j++)printf("   %s = %s%s %s \n\n", quad[j].result1, quad[j].ag11, quad[j].op1, quad[j].ag21);

getchar();

}

 

int lrparser()

{

int schain = 0;

kk = 0;

if (syn == 1)

{

scaner();

schain = yucu();

if (syn == 6)

{

scaner();

if ((syn == 0) && (kk == 0)) printf("Success!\n");

}

else {

if (kk != 1)printf("short of 'end'!\n");

kk = 1;

getchar();

exit(0);

}

}

else {

printf("short of 'begin' !\n");

kk = 1;

getchar();

exit(0);

}

return (schain);

}

 

int yucu()

{

int schain = 0;

schain = statement();

while (syn == 26)

{

scaner();

schain = statement();

}

return (schain);

}

 

int statement()

{

char tt[8], eplace[8];

int schain = 0;

if (syn == 10)

{

strcpy_s(tt, 255, token);

scaner();

if (syn == 18)

{

scaner();

strcpy_s(eplace, 255, expression());

emit(tt, eplace, "", "");

schain = 0;

}

else {

printf("short of sign ':='!\n");

kk = 1;

getchar();

exit(0);

}

return (schain);

}

}

 

char *expression()

{

char *tp, *ep2, *eplace, *tt;

tp = (char *)malloc(12);

ep2 = (char *)malloc(12);

eplace = (char *)malloc(12);

tt = (char *)malloc(12);

strcpy_s(eplace, 255, term());

while ((syn == 13) || (syn == 14))

{

if (syn == 13)strcpy_s(tt, 255, "+");

else strcpy_s(tt, 255, "-");

scaner();

strcpy_s(ep2, 255, term());

strcpy_s(tp, 255, newtemp());

emit(tp, eplace, tt, ep2);

strcpy_s(eplace, 255, tp);

}

return (eplace);

}

 

char *term()

{

char *tp, *ep2, *eplace, *tt;

tp = (char *)malloc(12);

ep2 = (char *)malloc(12);

eplace = (char *)malloc(12);

tt = (char *)malloc(12);

strcpy_s(eplace, 255, factor());

while ((syn == 15) || (syn == 16))

{

if (syn == 15)strcpy_s(tt, 255, "*");

else strcpy_s(tt, 255, "/");

scaner();

strcpy_s(ep2, 255, factor());

strcpy_s(tp, 255, newtemp());

emit(tp, eplace, tt, ep2);

strcpy_s(eplace, 255, tp);

}

return (eplace);

}

 

char *factor()

{

char *fplace;

fplace = (char *)malloc(12);

strcpy_s(fplace, 255, "");

if (syn == 10)

{

strcpy_s(fplace, 255, token);

scaner();

}

else if (syn == 11)

{

itoa(sum, fplace, 10);

scaner();

}

else if (syn == 27)

{

scaner();

fplace = expression();

if (syn == 28) scaner();

else {

printf("error on ')'!\n");

kk = 1;

getchar();

exit(0);

}

}

else {

printf("error on '(' !\n");

kk = 1;

getchar();

exit(0);

}

return (fplace);

}

 

char *newtemp()

{

char *p;

char m[8];

p = (char *)malloc(8);

kk++;

itoa(kk, m, 10);

strcpy_s(p + 1, 255, m);

p[0] = 't';

return(p);

}

 

scaner()

{

sum = 0;

for (m = 0; m<8; m++)token[m++] = NULL;

m = 0;

ch = prog[p++];

while (ch == ' ')ch = prog[p++];

if (((ch <= 'z') && (ch >= 'a')) || ((ch <= 'Z') && (ch >= 'A')))

{

while (((ch <= 'z') && (ch >= 'a')) || ((ch <= 'Z') && (ch >= 'A')) || ((ch >= '0') && (ch <= '9')))

{

token[m++] = ch;

ch = prog[p++];

}

p--;

syn = 10;

token[m++] = '\0';

for (n = 0; n<6; n++)

if (strcmp(token, rwtab[n]) == 0)

{

syn = n + 1;

break;

}

}

else if ((ch >= '0') && (ch <= '9'))

{

while ((ch >= '0') && (ch <= '9'))

{

sum = sum * 10 + ch - '0';

ch = prog[p++];

}

p--;

syn = 11;

}

else switch (ch)

{

case '<':m = 0;

ch = prog[p++];

if (ch == '>')

{

syn = 21;

 

}

else if (ch == '=')

{

syn = 22;

}

else

{

syn = 20;

p--;

}

break;

case '>':m = 0;

ch = prog[p++];

if (ch == '=')

{

syn = 24;

}

else

{

syn = 23;

p--;

}

break;

case ':':m = 0;

ch = prog[p++];

if (ch == '=')

{

syn = 18;

}

else

{

syn = 17;

p--;

}

break;

case '+': syn = 13; break;

case '-': syn = 14; break;

case '*': syn = 15; break;

case '/': syn = 16; break;

case '(': syn = 27; break;

case ')': syn = 28; break;

case '=': syn = 25; break;

case ';': syn = 26; break;

case '#': syn = 0; break;

default: syn = -1; break;

 

}

}

 

emit(char *result, char *ag1, char*op, char *ag2)

{

strcpy_s(quad[q].result1, 255, result);

strcpy_s(quad[q].ag11, 255, ag1);

strcpy_s(quad[q].op1, 255, op);

strcpy_s(quad[q].ag21, 255, ag2);

q++;

}

　　

运行截图：