一個簡單C語言的詞法分析器

語言的詞法構成：

識別符號

id  同C語言識別符號

常量

num 數字  
ch  字元
str 字串

關鍵字

kw_int  int
kw_char char        
kw_void void        
kw_if   if      
kw_else else    
kw_switch   switch      
kw_case case    
kw_default  default     
kw_while    while   
kw_do   do      
kw_for  for 
kw_break
 
    break       
kw_continue continue        
kw_return   return      

運算子

add +       
sub -       
mul *       
div /
mod %
inc ++
dec --
not !
and &&
or  ||
assign  =
gt  >
ge  >=
lt  <
le  <=
equ ==
nequ    !=

分界符

comma   ,
colon   :
simcon  ;
lparen  (
rparen  )
lbrac
 
   {
rbrac   }

程式碼：

#include<stdio.h>
#include<string.h>

char input[200];//存放輸入字串
char token[10];//存放構成單詞符號的字串
char toke;
char ch;     //存放當前讀入字元
int fg;     //switch標記
int num;    //存放整形值
int p=0;//input[]下標

//二維字元陣列，存放關鍵字
char character[13][10]={"int","char","void","if","else","switch","case","default"
 
,"while","do","for","break","continue","return"};
//二維字元陣列，存放含義定義
char index[42][15]={"id","num","str","kw_int","kw_char","kw_void","kw_if","kw_else","kw_switch","kw_case","kw_default","kw_while","kw_do","kw_for","kw_break","kw_continue","kw_return","add","sub","mul","div","mod","inc","dec","not","and","or","assign","gt","ge","lt","le","equ","nequ","comma","colon","simcon","lparen","rparen","lbrac","rbrac","ch"};
main()
{
    printf("請輸入程式碼(結尾以'#'作為結束):\n");
    do
    {
        ch=getchar();
        input[p++]=ch;
    }while(ch!='#');
    p=0;
    do
    {
        scaner();
        switch(fg)
        {
            case 0:printf("** %s-->%s **\n",token,index[fg]);break;//識別符號
            case 1:printf("** %d-->%s **\n",num,index[fg]);break;//數字

            case 2:printf("** %s-->%s **\n",token,index[fg]);break;//字串

            case 3:printf("** %s-->%s **\n",token,index[fg]);break;//關鍵字
            case 4:printf("** %s-->%s **\n",token,index[fg]);break;
            case 5:printf("** %s-->%s **\n",token,index[fg]);break;
            case 6:printf("** %s-->%s **\n",token,index[fg]);break;
            case 7:printf("** %s-->%s **\n",token,index[fg]);break;
            case 8:printf("** %s-->%s **\n",token,index[fg]);break;
            case 9:printf("** %s-->%s **\n",token,index[fg]);break;
            case 10:printf("** %s-->%s **\n",token,index[fg]);break;
            case 11:printf("** %s-->%s **\n",token,index[fg]);break;
            case 12:printf("** %s-->%s **\n",token,index[fg]);break;
            case 13:printf("** %s-->%s **\n",token,index[fg]);break;
            case 14:printf("** %s-->%s **\n",token,index[fg]);break;
            case 15:printf("** %s-->%s **\n",token,index[fg]);break;
            case 16:printf("** %s-->%s **\n",token,index[fg]);break;

            case 17:printf("** %s-->%s **\n",token,index[fg]);break;//運算子
            case 18:printf("** %s-->%s **\n",token,index[fg]);break;
            case 19:printf("** %s-->%s **\n",token,index[fg]);break;
            case 20:printf("** %s-->%s **\n",token,index[fg]);break;
            case 21:printf("** %s-->%s **\n",token,index[fg]);break;
            case 22:printf("** %s-->%s **\n",token,index[fg]);break;
            case 23:printf("** %s-->%s **\n",token,index[fg]);break;
            case 24:printf("** %s-->%s **\n",token,index[fg]);break;
            case 25:printf("** %s-->%s **\n",token,index[fg]);break;
            case 26:printf("** %s-->%s **\n",token,index[fg]);break;
            case 27:printf("** %s-->%s **\n",token,index[fg]);break;
            case 28:printf("** %s-->%s **\n",token,index[fg]);break;
            case 29:printf("** %s-->%s **\n",token,index[fg]);break;
            case 30:printf("** %s-->%s **\n",token,index[fg]);break;
            case 31:printf("** %s-->%s **\n",token,index[fg]);break;
            case 32:printf("** %s-->%s **\n",token,index[fg]);break;
            case 33:printf("** %s-->%s **\n",token,index[fg]);break;
            case 34:printf("** %s-->%s **\n",token,index[fg]);break;
            case 35:printf("** %s-->%s **\n",token,index[fg]);break;
            case 36:printf("** %s-->%s **\n",token,index[fg]);break;
            case 37:printf("** %s-->%s **\n",token,index[fg]);break;
            case 39:printf("** %s-->%s **\n",token,index[fg]);break;
            case 40:printf("** %s-->%s **\n",token,index[fg]);break;

            case 41:printf("** %c-->%s **\n",toke,index[fg]);break;//字元

            case -1:printf("分析器不存在該詞法\n");  break;
        }
    }while(fg!=42);
    getch(); //用於讓程式停留在顯示頁面
}

scaner()
{//詞法掃描程式
    int m=0;//token[]下標
    int n;
    toke=NULL;
    //清空token[]
    for(n=0;n<5;n++)
        token[n]=NULL;
    //獲取第一個不為0字元
    ch=input[p++];
    while(ch==' ')ch=input[p++];
    while(ch=='\n')ch=input[p++];

    //數字處理
    if(ch<='9'&&ch>='0')
    {
        num=0;
        while(ch<='9'&&ch>='0')
        {
            num=num*10+ch-'0';
            ch=input[p++];
        }
        ch=input[--p];
        fg=1;
    }

    //關鍵字處理/識別符號處理
    else if((ch<='z'&&ch>='a')||(ch<='Z'&&ch>='A')||(ch=='_'))
    {
        int flag=0;
        while((ch<='z'&&ch>='a')||(ch<='Z'&&ch>='A')||(ch<='9'&&ch>='0')||(ch=='_'))
        {
            token[m++]=ch;
            ch=input[p++];
        }
        token[m++]='\0';
        ch=input[--p];

        for(n=0;n<14;n++)//關鍵字
        {
            if(strcmp(token,character[n])==0)//strcmp()比較兩個字串,相等返回0
            {
                flag=1;
                fg=n+3;
                break;

            }
       }
       if(flag==0)
       {
            fg=0;
       }
    }
    //運算子分界符處理
    else
    {
        switch(ch)
        {
            case '+':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='+')          //產生++
                {
                    fg=22;
                    token[m++]=ch;
                }
                else     //產生+
                {
                    fg=17;
                    ch=input[--p];
                }
                break;

            case '-':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='-')          //產生--
                {
                    fg=23;
                    token[m++]=ch;
                }
                else     //產生-
                {
                    fg=18;
                    ch=input[--p];
                }
                break;

            case '>':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='=')          //產生>=
                {
                    fg=29;
                    token[m++]=ch;
                }
                else     //產生>
                {
                    fg=28;
                    ch=input[--p];
                }
                break;


            case '<':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='=')          //產生<=
                {
                    fg=31;
                    token[m++]=ch;
                }
                else     //產生<
                {
                    fg=30;
                    ch=input[--p];
                }
                break;

            case '=':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='=')          //產生==
                {
                    fg=32;
                    token[m++]=ch;
                }
                else     //產生=
                {
                    fg=27;
                    ch=input[--p];
                }
                break;

            case '!':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='=')          //產生!=
                {
                    fg=33;
                    token[m++]=ch;
                }
                else     //產生!
                {
                    fg=24;
                    ch=input[--p];
                }
                break;

            case '&':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='&')          //產生&&
                {
                    fg=25;
                    token[m++]=ch;
                }
                else     //無產生
                {
                    fg=41;
                    ch=input[--p];
                }
                break;

            case '|':
                m=0;
                token[m++]=ch;
                ch=input[p++];
                if(ch=='|')          //產生||
                {
                    fg=26;
                    token[m++]=ch;
                }
                else     //無產生
                {
                    fg=41;
                    ch=input[--p];
                }
                break;

            case '*':fg=19;token[0]=ch;break;
            case '/':fg=20;token[0]=ch;break;
            case '%':fg=21;token[0]=ch;break;
            case ',':fg=34;token[0]=ch;break;
            case ':':fg=35;token[0]=ch;break;
            case ';':fg=36;token[0]=ch;break;
            case '(':fg=37;token[0]=ch;break;
            case ')':fg=38;token[0]=ch;break;
            case '{':fg=39;token[0]=ch;break;
            case '}':fg=40;token[0]=ch;break;

            case '"':
                ch=input[p++];
                m=0;
                token[m++]=ch;
                do
                {
                    ch=input[p++];
                    token[m++]=ch;
                }while(ch!='"');
                fg=2;
                break;
            case '\'':
                ch=input[p++];
                m=0;
                toke=ch;
                do
                {
                    ch=input[p++];
                    token[m++]=ch;
                }while(ch!='\'');
                if(token[0]=='\'')
                {
                    fg=41;
                }
                else
                {
                    fg=-1;
                }
                break;

            case '#':fg=42;break;
            default:fg=-1;
        }
    }
}

完成！