软件构造——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> 
#include<iostream> 
#include<stdlib.h> 
using namespace std;
struct {
    char result[12];
    char ag1[12];
    char op[12];
    char ag2[12];
}quad;
//变量的定义
char prog[80], token[12];
char ch; int syn, p, m = 0, n, sum = 0, kk; //p 是缓冲区 prog 的指针， m 是 token 的指针
char *rwtab[6] = { "begin", "if", "then", "while", "do", "end" };
void scaner();
char *factor(void);
char *term(void);
char *expression(void);
int yucu();
void emit(char *result, char *ag1, char *op, char *ag2);
char *newtemp();
int statement();
int k = 0;
void emit(char *result, char *ag1, char *op, char *ag2) {
    strcpy(quad.result, result);
    strcpy(quad.ag1, ag1);
    strcpy(quad.op, op);
    strcpy(quad.ag2, ag2);
    //cout<<quad.result<<"="<<quad.ag1<<quad.op<<quad.ag2<<endl; 
    cout << "( " << quad.op << ", " << "entry(" << quad.ag1 << "), " << "entry(" << quad.ag2 << "), " << quad.result << ")
" << endl;
    //cout<<"entry("<<quad.ag1<<"entry("<<quad.op<<quad.ag2<<endl; 
}
char *newtemp() {
    char *p;
    char m[12];
    p = (char *)malloc(12);
    k++;
    _itoa_s(k, m, 10);
    strcpy(p + 1, m);
    p[0] = 't';
    return (p);
}
//对字符的扫描
void scaner() {
    for (n = 0; n<8; n++)
        token[n] = NULL;
    ch = prog[p++];
    while (ch == ' ') {
        ch = prog[p];
        p++;
    }
    if ((ch >= 'a'&&ch <= 'z') || (ch >= 'A'&&ch <= 'Z')) {
        if ((ch >= 'a'&&ch <= 'c') || (ch >= 'A'&&ch <= 'C')){
            m = 0;
            while ((ch >= '0'&&ch <= '9') || (ch >= 'a'&&ch <= 'z') || (ch >= 'A'&&ch <= 'Z')) {
                token[m++] = ch;
                ch = prog[p++];
            }
            token[m++] = '';
            p--;
            syn = 10;
            for (n = 0; n<6; n++) {
                if (strcmp(token, rwtab[n]) == 0) {
                    syn = n + 1;
                    break;
                }
            }
        }
        else
            cout << "Error!" << endl;
    }
    else if ((ch >= '0'&&ch <= '9')) {
        {
            sum = 0;
            while ((ch >= '0'&&ch <= '9')) {
                sum = sum * 10 + ch - '0';
                ch = prog[p++];
            }
        }
        p--;
        syn = 11;
        if (sum>32767)
            syn = -1;
    }
    else switch (ch)
    {
    case'<':
        m = 0;
        token[m++] = ch;
        ch = prog[p++];
        if (ch == '>') {
            syn = 21;
            token[m++] = ch;
        }
        else if (ch == '=')
        {
            syn = 22;
            token[m++] = ch;
        }
        else {
            syn = 23;
            p--;
        }
        break;
    case'>':
        m = 0;
        token[m++] = ch;
        ch = prog[p++];
        if (ch == '=') {
            syn = 24;
            token[m++] = ch;
        }
        else {
            syn = 20;
            p--;
        }
        break;
    case':':
        m = 0; token[m++] = ch;
        ch = prog[p++];
        if (ch == '=') {
            syn = 18;
            token[m++] = ch;
        }
        else {
            syn = 17;
            p--;
        }
        break;
    case'*':
        syn = 13;
        token[0] = ch;
        break;
    case'/':
        syn = 14;
        token[0] = ch;
        break;
    case'+':
        syn = 15;
        token[0] = ch;
        break;
    case'-':
        syn = 16;
        token[0] = ch;
        break;
    case'=':
        syn = 25;
        token[0] = ch;
        break;
    case';':
        syn = 26;
        token[0] = ch;
        break;
    case'(':
        syn = 27;
        token[0] = ch;
        break;
    case')':
        syn = 28;
        token[0] = ch;
        break;
    case'#':
        syn = 0;
        token[0] = ch;
        break;
    default:
        syn = -1;
        break;
    }
}
int lrparser()
{
    //cout<<" 调用 lrparser"<<endl; 
    int schain = 0;
    kk = 0;
    if (syn == 1) {
        scaner();
        schain = yucu();
        //cout<<"SYN= "<<syn<<endl; 
        if (syn == 6) {
            scaner();
            if (syn == 0 && (kk == 0))
                cout << "success!" << endl;
        }
        /* else
        {
        if(kk!=1)
        cout<<"缺 end!"<<endl;
        kk=1;
        } */
    }
    else
    {
        cout << "Error!" << endl;
        kk = 1;
    }
    return(schain);
}
int yucu() { // cout<<" 调用 yucu"<<endl; 
    int schain = 0;
    schain = statement();
    while (syn == 26) {
        scaner();
        schain = statement();
    }
    return(schain);
}
int statement()
{
    //cout<<" 调用 statement"<<endl; 
    char *eplace, *tt;
    eplace = (char *)malloc(12);
    tt = (char *)malloc(12);
    int schain = 0;
    switch (syn) {
    case 10:
        strcpy(tt, token);
        scaner();
        // if(syn==18) { 
        scaner();
        strcpy(eplace, expression());
        emit(tt, eplace, "", "");
        schain = 0;
        /* }
        else { cout<<"缺少赋值符 !"<<endl;
        kk=1;
        } */
        return (schain);
        break;
    }
    return (schain);
}
char *expression(void) {
    char *tp, *ep2, *eplace, *tt;
    tp = (char *)malloc(12);
    ep2 = (char *)malloc(12);
    eplace = (char *)malloc(12);
    tt = (char *)malloc(12);
    strcpy(eplace, term()); //调用 term 分析产生表达式计算的第一项 eplace 
    while ((syn == 15) || (syn == 16)) {
        if (syn == 15)
            strcpy(tt, "+");
        else
            strcpy(tt, "-");
        scaner();
        strcpy(ep2, term()); //调用 term 分析产生表达式计算的第二项 ep2 
        strcpy(tp, newtemp()); // 调用 newtemp 产生临时变量 tp 存储计算结果
        emit(tp, eplace, tt, ep2); //生成四元式送入四元式表
        strcpy(eplace, tp);
    }
    return(eplace);
}
char *term(void) {
    // cout<<" 调用 term"<<endl; 
    char *tp, *ep2, *eplace, *tt;
    tp = (char *)malloc(12);
    ep2 = (char *)malloc(12);
    eplace = (char *)malloc(12);
    tt = (char *)malloc(12);
    strcpy(eplace, factor());
    while ((syn == 13) || (syn == 14)) {
        if (syn == 13)strcpy(tt, "*");
        else strcpy(tt, "/");
        scaner(); strcpy(ep2, factor()); // 调用 factor 分析产生表达式计算的第二项 ep2 
        strcpy(tp, newtemp());
        //调用 newtemp产生临时变量 tp 存储计算结果 emit(tp,eplace,tt,ep2); //生成四元式送入四元式表
        strcpy(eplace, tp);
    }
    return(eplace);
}
char *factor(void) {
    char *fplace;
    fplace = (char *)malloc(12);
    strcpy(fplace, "");
    if (syn == 10) {
        strcpy(fplace, token);
        scaner();
    }
    else if (syn == 11) {
        itoa(sum, fplace, 10);
        scaner();
    }
    else if (syn == 27) {
        scaner();
        fplace = expression(); //调用 expression分析返回表达式的值
        if (syn == 28)
            scaner();
        else {
            cout << "缺)错误 !" << endl;
            kk = 1;
        }
    }
    else {
        cout << "缺(错误 !" << endl;
        kk = 1;
    }
    return(fplace);
}
int main(void) {
    cout << "这是周博的语义分析器；" << endl;
    for (int i = 0; i < 10; i++)
    {
        cout << "*************";
    }
    cout << endl;
    p = 0;
    cout << "请输入一个字符串（以#结束）:" << endl;
    do {
        cin.get(ch);
        prog[p++] = ch;
    } while (ch != '#');
    p = 0;
    scaner();
    lrparser();
    for (int i = 0; i < 10; i++)
    {
        cout << "*************";
    }
    return 0;

实验截图：