#include<stdio.h> //包含库所用的某些宏和变量 #include<stdlib.h> //包含库 #include<string.h> //包含字符串处理库 #define _KEY_WORD_END "waiting for your expanding" //定义关键字结束标志 typedef struct { int typenum; char * word; }WORD; char input[255]; //输入换缓冲区 char token[255]=""; //单词缓冲区 int p_input; //输入换缓冲区指针 int p_token; //单词缓冲区指针 char ch; //当前所读的字符 char *rwtab[]={"begin","if","then","while","do","end",_KEY_WORD_END}; //C语言关键字 WORD * scaner(); //词法扫描函数,获得关键字 main() { int over=1; WORD *oneword; oneword=(WORD *)malloc(sizeof(WORD)); printf("Input your code(end with #):"); //读入源程序字符串到缓冲区,以#结束,允许多行输入 scanf("%[^#]s",input); p_input=0; printf("The code is:\n%s\n\n",input); while(over<1000&&over!=-1) { oneword=scaner(); printf("(%d,%s)\n",oneword->typenum,oneword->word); over=oneword->typenum; } } //需要用到的自编函数参考实现 //从输入缓冲区读取一个字符到ch中 char m_getch() { ch=input[p_input]; p_input=p_input+1; return (ch); } //去掉空白字符 void getbc() { while(ch==' '||ch==10) { ch=input[p_input]; p_input=p_input+1; } } //拼接单词 void concat() { token[p_token]=ch; p_token=p_token+1; token[p_token]='\0'; } //判断是否字母 int letter() { if(ch>='a'&&ch<='z'||ch>='A'&&ch<='Z') return 1; else return 0; } //判断是否数字 int digit() { if(ch>='0'&&ch<='9') return 1; else return 0; } //检索关键字表格 int reserve() { int i=0; while(strcmp(rwtab[i],_KEY_WORD_END)) //数组中的单词跟输入的单词比较 { if(!strcmp(rwtab[i],token)) { return i+1; } i=i+1; } return 10; } //回退一个字符 void retract() { p_input=p_input-1; } WORD *scaner()//扫描单词 { WORD *myword; myword=(WORD *)malloc(sizeof(WORD)); myword->typenum=10; myword->word=""; p_token=0; m_getch(); getbc(); if(letter()) { while(letter()||digit()) { concat(); m_getch(); } retract(); myword->typenum=reserve(); myword->word=token; return(myword); } else if(digit()) { while(digit()) { concat(); m_getch(); } retract(); myword->typenum=11; myword->word=token; return(myword); } else { switch(ch) { case'+': myword->typenum=13; myword->word="+"; return(myword); break; case'-': myword->typenum=14; myword->word="-"; return(myword); break; case'*': myword->typenum=15; myword->word="*"; return(myword); break; case'/': myword->typenum=16; myword->word="/"; return(myword); break; case':': m_getch(); if(ch=='=') { myword->typenum=18; myword->word=":="; return(myword); } retract(); myword->typenum=17; myword->word=":"; return(myword); break; case'<': m_getch(); if(ch=='=') { myword->typenum=21; myword->word="<="; return(myword); } else if(ch=='>') { myword->typenum=22; myword->word="<>"; return(myword); } retract(); myword->typenum=20; myword->word="<"; return(myword); break; case'>': m_getch(); if(ch=='=') { myword->typenum=24; myword->word=">="; return(myword); } retract(); myword->typenum=23; myword->word=">"; return(myword); break; case'=': myword->typenum=25; myword->word="="; return(myword); break; case';': myword->typenum=26; myword->word=";"; return(myword); break; case '(': myword->typenum=27; myword->word="("; return(myword); break; case ')': myword->typenum=28; myword->word=")"; return(myword); break; case '#': myword->typenum=0; myword->word="OVER"; return(myword); break; case '\0': myword->typenum=1000; myword->word="#"; return(myword); break; default: myword->typenum=-1; myword->word="ERROR"; return(myword); } } }
![](https://images2015.cnblogs.com/blog/808508/201510/808508-20151029151727904-944315525.png)