词法分析程序的设计与实现

词法分析程序（Lexical Analyzer）要求：

- 从左至右扫描构成源程序的字符流

-  识别出有词法意义的单词（Lexemes）

-  返回单词记录（单词类别，单词本身）

-  滤掉空格

-  跳过注释

-  发现词法错误

程序结构：

输入：字符流（什么输入方式，什么数据结构保存）

处理：

–遍历（什么遍历方式）

–词法规则

输出：单词流（什么输出形式）

–二元组

源程序如下：

#include<stdio.h>
#include<conio.h>
#include<math.h>
#include<string.h>
#include<stdlib.h>

int i, row = 0, line = 0;
char test[1000];  //test文件中的字符 
int number[100];    //常数表 
char mark[100][5];   //标识符表

//词法分析
int wordanalysis()
{
    //标识符和保留字
    if ((test[i] >= 'A'&&test[i] <= 'Z')||(test[i]>='a'&&test[i]<='z'))  
    {
        char word[10];
        //保留字表
        char pro[100][100] = { "PROGRAM", "BEGIN", "END", "VAR", "INTEGER", "WHILE",
                                 "IF", "THEN", "ELSE", "DO", "PROCEDURE" ,"char",
                                "int","if","else","var" ,"return","break",
                                "do","while","for","double","float","short"}; 

        int n = 0;
        word[n++] = test[i++];
        while ((test[i] >= 'A'&&test[i] <= 'Z') || (test[i] >= '0' && test[i] <= '9')||(test[i]>='a'&&test[i]<='z'))
        {
            word[n++] = test[i++];
        }
        word[n] = '';
        i--;

        //判断该标识符是否为保留字
        for (n = 0; n < 100; n++)
        {
            if (strcmp(word, pro[n]) == 0)
            {
                printf(">> %s	(%d,-) 保留字
", pro[n], n + 1);
                return 3;
            }
        }

        //判断该标识符是否在标识符表中
        int m = 0;
        if (line != 0)
        {
            int q = 0;
            while (q<line)
            {
                if (strcmp(word, mark[q++]) == 0)
                {
                    printf(">> %s	(10,%d) 标识符
", word, q);
                    return 3;
                }
            }

        }

        //将该标识符保存到标识符表中
        strcpy(mark[line], word);
        
        printf(">> %s	(10, %d) 标识符
", word, line + 1);
        line++;
        return 3;

    }
    //数字 
    else if (test[i] >= '0' && test[i] <= '9')  
    {
        char x[100];
        int n = 0;
        x[n++] = test[i++];
        
        while (test[i] >= '0' && test[i] <= '9')
        {
            x[n++] = test[i++];
        }
        x[n] = '';
        i--;
        int num = atoi(x); //将字符串转换成int型
        
        //判断该常数是否存在于常数表中
        if (row != 0)
        {   
            
            for(int y=0;y<row;y++)
            {
                if(number[y]==num)
                {
                    printf(">> %d	(11,%d)
", num, y + 1);
                    return 3;
                }
            }
        }
        
        //将该常数保存到标识符表中
        number[row]=num;
        

        int line = row;
        printf(">> %d	(11,%d)
", num, line + 1);
        row++;

        return 3;
    }
    
    //各种符号
    else                      
        switch (test[i])
    {
        case ' ':
        case '
':
            return -1;
        case '#': return 0;
        case '=':printf(">> =	(25,-)
"); return 3;
        case '<':
            i++;
            if (test[i] == '=')
            {
                printf(">> <= 	(21,-)
");
                return 3;
            }
            else if (test[i] == '>')
            {
                printf(">> <>	(22,-)
");
                return 3;
            }
            else
            {
                i--;
                printf(">> <	(20,-)
");
                return 3;
            }
        case '>':
            i++;
            if (test[i] == '=')
            {
                printf(">> >=	(24,-)
");
                return 3;
            }
            else
            {
                i--;
                printf(">> >	(23,-)
");
                return 3;
            }
        case '+': printf(">> +	(13,-)
"); return 3;
        case '-': printf(">> -	(14,-)
"); return 3;
        case '*': printf(">> *	(15,-)
"); return 3;
        case '/': 
            i++;
            if(test[i]!='/'){
                i--;
                printf(">> /	(16,-)
"); return 3;
            }

            else{

                while(1){
                    if(test[i++]=='
')
                        return -1;
                }
                printf(">> //	(37,-)
");return 3;

            }

        case ':': printf(">> :	(17,-)
"); return 3;
        case ';': printf(">> ;	(26,-)
"); return 3;
        case '(': printf(">> (	(27,-)
"); return 3;
        case ')': printf(">> )	(28,-)
"); return 3;

    }

}

int main()
{

    int c = 0;
    int m;
    i = 0;
    FILE *fp;
    fp=fopen(".\test.txt","r");
    if (fp == NULL)
    {
        printf("can't open file!
");
        exit(0);
    }

    while (!feof(fp))
    {
        test[c++] = fgetc(fp);
    }
    test[c] = '#';
    do
    {
        m = wordanalysis();

        switch (m)
        {
        case -1:i++; break;
        case 0: i++; break;
        case 3: i++; break;
        }
    } while (m != 0);


    return 0;
}

 测试代码文件如下：

include <stdio.h>
int main(void)
{
	int a[3][4]={{1,3,5,7},
	{9,11,13,15},
	{17,19,21,23}
	
	};
	
int *p,line;

for(line=0;line<3;line++)
{
	for(p=a[line];p<a[line]+4;p++)
		printf("%4d",*p);
	putchar('
');
}
return 0;
} 

　　

 运行结果：