Redy词法分析--注释的识别

返回文档首页

（一）简介

代码下载: git clone git://git.code.sf.net/p/redy/code redy-code

这一章内容有：

用状态矩阵的方法识别字符串

（二）注释的识别

在Redy中，注释是以符号'#'开头，后面可以接任意字符，直到这一行结束。

（１）状态机

　

（２）状态矩阵

对于注释来说，输入类型可以分为这么几种

1. 符号'#'　　　（Pound)
2. 换行符　　　（newline)
3. 除以上字符的所有字符　　（other)

其中 AnnoItem包括　Pound,other

状态矩阵为：

状态\输入	Other	Newlin	Pound
AnnotateBegin			Anotate
Anotate	Anotate	AnotateEnd	Anotate
AnotateEnd

其中开始状态为AnnotateBegin，终态为AnotateEnd

（3）程序数据

字符所属类型映射：

enum ANNO_INPUT_TYPTE
{
    ANNO_OTHER=0,
    ANNO_NEWLINE,
    ANNO_POUND,
    ANNO_INPUT_NUM,
};

char annotate_type_map[ASSIC_NUM]=
{
    0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0

};

状态矩阵：

#define ANNO_STATE_NUM 3
#define ANNO_BEGIN 0
#define ANNO_ANNOTATE 1
#define ANNO_END 2
/* Other | Newlin | Pound */
int annotate_automaton[ANNO_STATE_NUM*ANNO_INPUT_NUM]=
{
    LEX_ERR,LEX_ERR,ANNO_ANNOTATE,
    ANNO_ANNOTATE,ANNO_END,ANNO_ANNOTATE,
    LEX_ERR,LEX_ERR,LEX_ERR,
};

状态信息：

char anno_state[ANNO_STATE_NUM]={0,0,1};

然后再把这些信息集合起来，交结我们的驱动程序来处理，驱动程序与前面的介变量识别的一样，但是主函数有一点变化，因为要在输入的字符串包含换行符，所以不能用scanf函数，这里使用的时getline从标准输入中读取一行，主函数为：

int main()
{
    char* buf;
    int n;
    char buf_copy[2048];
    printf("input:__quit__ exit\n");
    printf("input:");

    getline(&buf,&n,stdin);
    while(strcmp(buf,"__quit__")!=0)
    {
        int ret=driver(&am_anno,buf);
        if(ret==-1)
        {
            printf("sorry,Not Anno\n");
        }
        else
        {
            memcpy(buf_copy,buf,ret+1);
            buf_copy[ret+1]='\0';
            printf("Recongise: %s\n",buf_copy);
            if(ret+1==strlen(buf))
            {
                printf("It's Anno\n");
            }
            else
            {
                printf("It's Not Anno\n");
            }
        }
        printf("\ninput:");
        getline(&buf,&n,stdin);
    }
    return 0;
}

（4）运行结果

关于注释识别的源程序，大家可以在tutorial/lexical/annotate下面找到

返回文档首页