#include<stdio.h> #include<stdlib.h> #include<string.h> #define _KEY_WOED_END "waiting for your expanding" //關鍵字結束標誌 typedef struct { int typenum; char * word; }WORD; char input[255]; //輸入換緩衝區 char token[255]=""; //單詞緩衝區 int p_input; //輸入換緩衝區指標 int p_token; //單詞緩衝區指標 char ch; //當前所讀的字元 char *rwtab[]={"begin","if","then","while","do","end",_KEY_WOED_END}; //C語言關鍵字 WORD * scaner(); //詞法掃描函式,獲得關鍵字 main() { int over=1; WORD *oneword; oneword=(WORD *)malloc(sizeof(WORD)); printf("請輸入您的字串(以#作為結束標誌):"); scanf("%[^#]s",input); //讀入源程式字串到緩衝區,以#結束,允許多行輸入 p_input=0; printf("您輸入的字串是:%s\n\n",input); while(over<1000&&over!=-1) { oneword=scaner(); printf("(%d,%s)\n",oneword->typenum,oneword->word); over=oneword->typenum; } printf("\n\n備註:數字10代表所輸入的不是關鍵詞,只是普通詞\n"); printf(" 數字20代表您輸入的是數字\n"); printf(" 數字1000是結束標誌\n\n"); } //需要用到的自編函式參考實現 //從輸入緩衝區讀取一個字元到ch中 char m_getch(){ ch=input[p_input]; p_input=p_input+1; return (ch); } //去掉空白字元 void getbc() { while(ch==' '||ch==10){ ch=input[p_input]; p_input=p_input+1; } } //拼接單詞 void concat() { token[p_token]=ch; p_token=p_token+1; token[p_token]='\0'; } //判斷是否字母 int letter() { if(ch>='a'&&ch<='z'||ch>='A'&&ch<='Z')return 1; else return 0; } //判斷是否數字 int digit() { if(ch>='0'&&ch<='9') return 1; else return 0; } //檢索關鍵字表格 int reserve() { int i=0; for(i=0;i<7;i++) { if(!strcmp(rwtab[i],token)) { return i+1; } i=i+1; } return 10; } //回退一個字元 void retract() { p_input=p_input-1; } WORD *scaner() { 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=20; myword->word=token; return(myword); } else { switch(ch) { case '=':m_getch(); if(ch=='=') { myword->typenum=39; myword->word="=="; return(myword); } retract(); myword->typenum=21; myword->word="="; return(myword); break; case '+': myword->typenum=22; myword->word="+"; return(myword); break; case '-': myword->typenum=23; myword->word="-"; return(myword); break; case '*': myword->typenum=24; 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=29; myword->word="]"; return(myword); break; case '{': myword->typenum=30; myword->word="{"; return(myword); break; case '}': myword->typenum=31; myword->word="}"; return(myword); break; case ',': myword->typenum=32; myword->word=","; return(myword); break; case ':': myword->typenum=33; myword->word=":"; return(myword); break; case ';': myword->typenum=34; myword->word=";"; return(myword); break; case '>': myword->typenum=35; myword->word=">"; return(myword); break; case '<': myword->typenum=36; myword->word="<"; return(myword); break; case '!': m_getch(); if(ch=='=') { myword->typenum=40; myword->word="!="; return(myword); } retract(); myword->typenum=-1; myword->word="ERROR"; return(myword); break; case '\0': myword->typenum=1000; myword->word="OVER"; return(myword); break; default: myword->typenum=-1; myword->word="ERROR"; return(myword); } } }