词法分析

开发平台：
C/C++

2.c：源码内容
							#include<stdio.h>
#include<string.h>
#define   buf_s 2000 /*缓冲区长度*/  
#define   word_s  50 /*最大单词长度*/
/*单词种别*/
char *symbol[20]={"ERROR","IDN","INT8","INT10","INT16",
                "ADD","SUB","MUL","DIV","MORE","LESS","EQUAL",
				"LEFT","RIGHT","SEM",
				"IF","ELSE","THEN","WHILE","DO"};
/*关键字*/
char *key[5]={"if","else","then","while","do"};
/* 运算符、分隔符*/
char op_s[10]="+-*/><=();";
int scan(char*buf,char*word,int*symbol_number);
int main(){
	char buffer[buf_s];/*初始化缓冲区*/
	char finish_word[word_s]="";/*初始化单词为空*/
	int symbol_num=0;/*初始化单词种别值为0（错误）*/
	gets(buffer);/*读取程序*/
	while(scan(buffer,finish_word,&symbol_num))/*当到达程序结束，scan函数返回0，结束词法分析*/
		printf("%stt%sn",symbol[symbol_num],finish_word);/*打印单词种类、属性*/
	return 0;
}
/*scan分词函数（缓冲区地址，存放分隔单词地址，单词列别值地址）*/
int scan(char*buf,char*word,int*symbol_number){
	static int n=0;/*静态，记录当前缓冲区读取位置*/
	char ch;
	int word_n=0;/*单词尾部*/
	int key=0;/*关键字类别值的临时存放变量*/
	int op=0;/*运算符、分隔符类别值的临时存放变量*/
	ch=buf[n];/*取第一个字符*/
	
	while(ch==' '||ch=='n'){/*如果是换行符，或者空格，跳过，读取下一个字符*/
		n++;
		ch=buf[n];
	}
	
	if(ch=='0'){/*第一个字符为0，则为十进制0，十六进制，或者八进制*/
		word[word_n]=ch;/*ch-->word*/
		word_n++;
		n++; /*取下一个字符*/
		ch=buf[n];
		if(ch=='x'||ch=='X'){/*十六进制分支*/
			word[word_n]=ch;
			word_n++;
			n++;/*取下一个字符*/
			ch=buf[n];
			if(isdigit(ch)||(ch>='a'&&ch<='f')||(ch>='A'&&ch<='F')){
				word[word_n]=ch;
				word_n++;
				n++;
				ch=buf[n];
				while(isdigit(ch)||(ch>='a'&&ch<='f')||(ch>='A'&&ch<='F')){
					word[word_n]=ch;
					word_n++;
					n++;
					ch=buf[n];
				}
				word[word_n]='';
				*symbol_number=4;/*单词类别值设为4（十六进制）*/
			}
			else{/*当为“0x”+“非0-9，a-f,A-F”,出错*/
				word[word_n]='';
				*symbol_number=0;/*单词类别值设为0（出错）*/
			}
		}
		else if(ch>='0'&&ch<='7'){/*八进制分支*/
			word[word_n]=ch;
			word_n++;
			n++;
			ch=buf[n];
			while(ch>='0'&&ch<='7'){
					word[word_n]=ch;
					word_n++;
					n++;
					ch=buf[n];
				}
				word[word_n]='';
				*symbol_number=2;/*单词类别值设为2（八进制）*/
		}
		else{/*为十进制0*/
			word[word_n]='';
			*symbol_number=3;/*单词类别值设为3（十进制）*/
		}
	}
	else if(ch>='1'&&ch<='9'){/*十进制分支*/
		word[word_n]=ch;
		word_n++;
		n++;
		ch=buf[n];
		while(ch>='0'&&ch<='9'){
			word[word_n]=ch;
			word_n++;
			n++;
			ch=buf[n];
		}
		word[word_n]='';
		*symbol_number=3;/*单词类别值设为3（十进制）*/
	}
	else if(isalpha(ch)){/*标示符（IDN），或者关键字（key）分支*/ 
		word[word_n]=ch;
		word_n++;
		n++;
		ch=buf[n];
		while(isalpha(ch)||isdigit(ch)){
			word[word_n]=ch;
			word_n++;
			n++;
			ch=buf[n];
		}		
		word[word_n]='';
		if(key=iskeyword(word))/*是否为关键字*/
			*symbol_number=key;/*单词类别值设为key（关键字类别值）*/
		else *symbol_number=1;/*单词类别值设为1（标识符）*/
		
		
	}
	else if(op=isop_s(ch)){//运算或分隔符分枝
		word[word_n]=ch;
		word_n++;
		word[word_n]='';
		n++;
		*symbol_number=op;
	}else if(ch==''){/*结束符，退出scan程序*/
		return 0;
	}else{/*为非法字符*/
		word[word_n]=ch;
		word_n++;
		n++;
		word[word_n]='';
		*symbol_number=0;/*单词类别值设为0（非法字符）*/}
	return 1;
}
int isalpha(ch){//是否为字符
	if((ch>='a'&&ch<='z')||(ch>='A'&&ch<='Z'))
		return 1;
	else
		return 0;}
int isdigit(ch){//是否为数字
	if(ch>='0'&&ch<='9')
		return 1;
	else
		return 0;}
int iskeyword(char*w){//关键字
	int i;
	for(i=0;i<5;i++){
		if(strcmp(w,key[i])==0)
			return 15+i;/*返回关键字类别值*/
	}
	return 0;
}
int isop_s(char m){//运算或分隔符
	int i;
	for(i=0;i<10;i++){
		if(m==op_s[i])
			return 5+i;/*返回运算或分隔符类别值*/
	}
	return 0;
}

						