词法分析程序实验

一、词法分析程序的功能

输入一段字符串，从字符串表示的源程序中识别出具有独立意义的单词符号，根据扫描到单词符号的第一个字符的种类，拼出相应的单词符号。

二、符号与种别码对照表

单词符号	种别码	单词符号	种别码
begin	1	:	17
if	2	:=	18
then	3	<	20
while	4	<=	21
do	5	<>	22
end	6	>	23
l(l|d)*	10	>=	24
dd*	11	=	25
+	13	;	26
-	14	(	27
*	15	)	28
/	16	#	0

三、用文法描述词法规则

<字母>：A→a|b|c|…|X|Y|Z
<数字>：B→0|1|2|…|9
<整数常数>：Z→C|ZC

                   C→0|1|2|...|9
<标识符>: I→X|IX|ID
X→a|b|c|…|X|Y|Z|_

D→0|1|2|...|9
<关键字>: K→const|var|procedure|begin|end|odd|if|then|call|while|do|read|write
<运算符>: Y→+|-|*|/|=|#|<|<=|>|>=|!=
<界符>: J→(|)|,|;|.

四、c语言源代码和运行结果截图

#include<stdio.h>
#include<string.h>
#include<math.h>
char prog[80]; 
char token[8]; 
char ch; 
int syn,p,m,n; 
double sum;     
int count;

int isSignal; 

int isDecimal;
double decimal; 
int isExp;  
int index;  
int isNegative; 
double temp;
int temp2;

void scanner();

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

void main()
{
    p=0;
    count=0;
    isDecimal=0;
    index=0;
    printf("请输入字符串:
");
    do{
        ch=getchar();
        prog[p++]=ch;
    }while(ch!='#'); 

    p=0;
    do{
        scanner(); 
        switch(syn)
        {
        case 11:
            if(isDecimal==0)
            {
                printf("(%2d,%8d)
",syn,(int)sum);
                break;
            }
            else if(isExp==1)
            {
                printf("(%2d,%10.5e)
",syn,sum);
                isExp=0;
                isDecimal=0;
                break;
            }
            else if(isDecimal==1)
            {
                printf("(%2d,%8.4f)
",syn,sum);
                isDecimal=0;
                break;
            }
        case -1:
            printf("input error
");
            break;
        default:
            printf("(%2d,%8s)
",syn,token);
        }
    }while(syn!=0);
}

void scanner()
{
    sum=0;
    decimal=0;
    m=0;

    for(n=0;n<8;n++)
        token[n]=NULL;
    ch=prog[p++]; 
    while(ch==' ')  
        ch=prog[p++];

    if(((ch>='a')&&(ch<='z'))||((ch>='A')&&(ch<='Z')))
    {
        while(((ch>='a')&&(ch<='z'))||((ch>='A')&&(ch<='Z'))||((ch>='0')&&(ch<='9')))
        {
            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    if((ch>='0')&&(ch<='9'))
    {
IsNum:
   if(isSignal==1)
   {
       
   }
        while((ch>='0')&&(ch<='9'))
        {
            sum=sum*10+ch-'0'; 
            ch=prog[p++];
        }
        if(ch=='.')
        {
            isDecimal=1;
            ch=prog[p++];
            while((ch>='0')&&(ch<='9'))
            {
                
                temp=(ch-'0')*pow(0.1,++count);
                decimal=decimal+temp;
                
                ch=prog[p++];
            }
            sum=sum+decimal;
        }
        if(ch=='e'||ch=='E')
        {
            isExp=1;
            ch=prog[p++];
            if(ch=='-')
            {
                isNegative=1;
                ch=prog[p++];
            }
            while((ch>='0')&&(ch<='9'))
            {
                
                index=index*10+ch-'0';
                ch=prog[p++];
            }
            if(isNegative)
                sum=sum*pow(0.1,index);
            else
                sum=sum*pow(10,index);

        }
        if(isSignal==1)
        {
            sum=-sum;
            isSignal=0;
        }
        p--;
        syn=11;
    }

    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=20;
                p--;
            }
            break;

        case '>':
            m=0;
            token[m++]=ch;
            ch=prog[p++];
            if(ch=='=')
            {
                syn=24;
                token[m++]=ch;
            }
            else
            {
                syn=23;
                p--;
            }
            break;

        case ':':
            m=0;
            token[m++]=ch;
            ch=prog[p++];
            if(ch=='=')
            {
                syn=18;
                token[m++]=ch;
            }
            else
            {
                syn=17;
                p--;
            }
            break;

        case '+':
            temp2=prog[p];
            if((temp2>='0')&&(temp2<='9'))
            {
                isSignal=2;
                ch=prog[p++];
                goto IsNum;
            }
            syn=13;
            token[m++]=ch;
            break;
        case '-':
            temp2=prog[p];
            if((temp2>='0')&&(temp2<='9'))
            {
                isSignal=1;
                ch=prog[p++];
                goto IsNum;  
            }
            syn=14;
            token[m++]=ch;
            break;
        case '*':
            syn=15;
            token[m++]=ch;
            break;
        case '/':
            syn=16;
            token[m++]=ch;
            break;
        case '=':
            syn=25;
            token[m++]=ch;
            break;
        case ';':
            syn=26;
            token[m++]=ch;
            break;
        case '(':
            syn=27;
            token[m++]=ch;
            break;
        case ')':
            syn=28;
            token[m++]=ch;
            break;
        case'#':
            syn=0;
            token[m++]=ch;
            break;
        default:
            syn=-1;
    }
}