【编译原理】一个词法分析器源码的剖析

一，词法分析器

        作用：读取源程序的输入字符、将他们组成词素，生成并输出一个词法单元序列

二，设计原理

        1）C程序语言的符号分类：关键字、标识符、常数、运算符、界符

        2）词法分析器的二元输出：<单词种别，单词符号属性值>

        3）正规式和状态转换图

 

           4）程序说明：

                               1>main 中打开源码文件，从第一个字符流读取

                               2>如果第一个是字符，则交给letterprocess(str); 处理

                               3>如果第一个是数字，则交给numberprocess(str); 处理

                               4>如果第一个是数字，则交给otherprocess(str); 处理

                               5>注意上述过程中，File *fp每读取一个词素，fp都会移动到下一个词素。对于空格的处理：isspace（ch）检查参数c是否为空格字符，也就是判断是否为空格('')、定位字符

　　('\t')、CR('\r')、换行('\n')、垂直定位字符('\v')或翻页('\f')的情况

                 这个程序输出结果情况汇总：关键字、算术运算符、关系运算符、分割符号、特殊符号、注释符号、逻辑运算符、非法符号

三，程序源码

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <malloc.h>
#include <conio.h>
#define NULL 0
FILE *fp;
char ch;
char *keyword[34]={"auto","break","case","char","const","continue","default","do","double",
"else","enum","extern","float","for","goto","if","int","long","register",
"return","short","signed","sizeof","static","struct","switch","typedef", "printf",
"union","unsigned","void","volatile","while","main"};
char *operatornum[6]={"+","-","*","/","++","--"};
char *comparison[8]={"<","<=","=",">",">=","<>","==","!="};
char *interpunction[8]={",",";",":=",".","(",")","{","}"};
char *biaoshifu[6]={"%","$","^","&","_","#"};//特殊标识符
char *zhushifu[3]={"//","/*","*/"};//注释符
char *luoji[3]={"&&","||","!"};//逻辑运算符


bool search(char searchstr[],int wordtype)//符号匹配
{
    int i;
    switch (wordtype)
    {
        case 1:
            for(i=0;i<=33;i++)
            {
                if(strcmp(keyword[i],searchstr)==0)
                return(true);
            }
            break;
        case 2:
            for(i=0;i<=5;i++)
            {
                if(strcmp(operatornum[i],searchstr)==0)
                return(true);
            }
         break;

        case 3:
            for(i=0;i<=7;i++)
            {
             if(strcmp(comparison[i],searchstr)==0)
                return(true);
            }
            break;

        case 4:
            for(i=0;i<=7;i++)
            {
                if(strcmp(interpunction[i],searchstr)==0)
                return(true);
            }

            break;
        case 5:
            for(i=0;i<=5;i++)
            {
                if(strcmp(biaoshifu[i],searchstr)==0)
                    return(true);
            }
            break;
        case 6:
             for(i=0;i<=2;i++)
             {
                if(strcmp(zhushifu[i],searchstr)==0)
                    return(true);
            }
            break;
        case 7:
            for(i=0;i<=2;i++)
            {
                if(strcmp(luoji[i],searchstr)==0)
                    return(true);
            }
        break;
    }

    return false;
}

char letterprocess (char ch)//字母处理函数
{
    int i=-1;
    char letter[20];
    while (isalnum(ch)!=0)
    {
        letter[++i]=ch;
        ch=fgetc(fp);
    }
    letter[i+1]='\0';
    if (search(letter,1))
    {
        printf("<%s,关键字>\n",letter);
        //strcat(letter,"\n");
        //fputs('<' letter '>\n',outp);
    }
    else
    {
        printf("<%s,自定义变量>\n",letter);
        //strcat(letter,"\n");
        //fputs(letter,outp);
    }

    return(ch);
}

char numberprocess(char ch)//数字处理程序
{
    int i=-1;
    char num[20];
    while (isdigit(ch)!=0)
    {
        num[++i]=ch;
        ch=fgetc(fp);
    }
    if(isalpha(ch)!=0)//数字后面是字符
    {
        while(isspace(ch)==0)
        {
            num[++i]=ch;
            ch=fgetc(fp);
        }
        num[i+1]='\0';
        printf("错误！非法标识符：%s\n",num);
    goto u;
    }
    num[i+1]='\0';
    printf("<%s,数字>\n",num);

    u: return(ch);
}

char otherprocess(char ch)//其他处理程序
{
    int i=-1;
    char other[20];
    if (isspace(ch)!=0)
    {
        ch=fgetc(fp);
        goto u;
    }
    while ((isspace(ch)==0)&&(isalnum(ch)==0))
    {
        other[++i]=ch;
        ch=fgetc(fp);
    }
    other[i+1]='\0';
    if (search(other,2))
        printf("<%s,算数运算符>\n",other);
    else if (search(other,3))
        printf("<%s,关系运算符号>\n",other);
    else if (search(other,4))
        printf("<%s,分隔符号>\n",other);
    else if (search(other,5))
        printf("<%s,特殊标识符号>\n",other);
    else if (search(other,6))
        printf("<%s,注释符号>\n",other);
    else if (search(other,7))
        printf("<%s,逻辑运算符号>\n",other);
    else
        printf("错误！非法字符：%s\n",other);
    u: return (ch);
}

int main ()
{
    char str;
    printf("**********************************词法分析器************************************\n");
    if ((fp=fopen("源程序.txt","r"))==NULL)
        printf("源程序无法打开！\n");
    else
    {
        str =fgetc(fp);//从流中读取字符
        while (str!=EOF)
        {
            if (isalpha(str)!=0)//如果是字符    isalpha包含在#include <cctype>
                str=letterprocess(str);
            else
            {
                if (isdigit(str)!=0)
                    str=numberprocess(str);
                else
                    str=otherprocess(str);
            }

        };
     printf("词法分析结束，谢谢使用！\n");
     //printf("点任意键退出!\n");
   }
   //c=getch();

   return 0;
}