词法分析器

用C或C++语言编写一门语言的词法分析器

（1）阅读已有编译器的经典词法分析源程序。
选择一个编译器，如：TINY，其它编译器也可（需自备源代码）。阅读词法分析源程序，理解词法分析程序的手工构造方法——状态图代码化。尤其要求对相关函数与重要变量的作用与功能进行稍微详细的描述。若能加上学习心得则更好。TINY语言请参考《编译原理及实践》第2.5节（见压缩包里附带的文档）。
（2）确定今后其他实验中要设计编译器的语言，如TINY语言，又如更复杂的C－语言（其定义在《编译原理及实践》附录A中）。也可选择其它语言，不过要有该语言的详细定义（可仿照C－语言）。一旦选定，不能更改，因为要在以后继续实现编译器的其它部分。鼓励自己定义一门语言。
（3）根据该语言的关键词和识别的词法单元以及注释等，确定关键字表，画出所有词法单元和注释对应的DFA图。
（4）仿照前面学习的词法分析器，编写选定语言的词法分析器。
（5）准备2~3个测试用例，要求包含正例和反例，测试编译结果。

关键代码

void display(string str,int a,ofstream &output){
	
	output<<a<<": "<<str<<endl;
	string str1="";
	int count=0;
	int j=0;
	while(str[j]!='\0'){
		if(str[j]=='{'){
			flag=1; 
			num++;
		}
		if(flag==1){
			output<<"\t"<<a<<": ";
			while(str[j]!='}'){
				if(str[j+1]!='\0'){
					str1+=str[j];
				j++;
				}
				else break;
			}
			if(str[j]=='}'){
				str1+=str[j];
				output<<str1<<endl;
				str1="";
				flag=0;
				j++;
				num--;
			}
			else{
				if(str[j]!='\0'){
					str1+=str[j];
				}
				output<<str1<<endl;
				str1="";
				j++;
			}
		}
		else{
			while((str[j]>='a'&&str[j]<='z')||(str[j]>='A'&&str[j]<='Z')){
				if((str[j+1]>='a'&&str[j+1]<='z')||(str[j+1]>='A'&&str[j+1]<='Z')){
					str1+=str[j];
					j++;
				}/*else if(str[j+1]>='0'&&str[j+1]<='9'){
					output<<"\t"<<a<<": "<<"error, miss a ' ' "<<endl;
					str1="";
					j++;
				}*/else{
					str1+=str[j];
					if(save(str1)==1){
						output<<"\t"<<a<<": "<<"Reversed Word: "<<str1<<endl;
					}
					else{
						output<<"\t"<<a<<": "<<"ID, name= "<<str1<<endl;
					}
					str1="";
					j++;
				}
			}
			while(str[j]>='0'&&str[j]<='9'){
				if(str[j+1]>='0'&&str[j+1]<='9'){
					count=count*10+str[j]-'0';
					j++;
				}/*else if((str[j+1]>='a'&&str[j+1]<='z')||(str[j+1]>='A'&&str[j+1]<='Z')){
					output<<"\t"<<a<<": "<<"error, miss a ' ' "<<endl;
					count=0;
					j++;
				}*/
				else{
					count=count*10+str[j]-'0';
					output<<"\t"<<a<<": "<<"NUM, val= "<<count<<endl;
					j++;
					count=0;
				}
			}
			if(pluss(str[j])==1||reduce(str[j])==1||multiply(str[j])==1||division(str[j])==1||equal(str[j])==1||lesss(str[j])==1||LP(str[j])==1||RP(str[j])==1||semicolon(str[j])==1){
				output<<"\t"<<a<<": "<<str[j]<<endl;
				j++;
			}
			if(str[j]==':'){
				str1+=str[j];
				if(str[j+1]=='='){
					str1+=str[j+1];
					output<<"\t"<<a<<": "<<str1<<endl;
					j+=2;
					str1="";
				}
				else{
					output<<"\t"<<a<<": "<<"error, miss a '='"<<endl;
					str1="";
					j++;
				}
			}
			if(str[j]=='}'){
				output<<"\t"<<a<<": "<<str[j]<<endl;
				j++;
				num--;
				continue;
			}
			if(str[j]!='\0'){
				if(others(str[j])==1){
				output<<"\t"<<a<<": "<<"error, inavild"<<endl;
				j++;
			} 
			}
			
		}
	}
}

测试用例

{ Sample program
in TINY language -
computes factorial
}
read x; { input an integer }
if 0 < x then { don’t compute if x <= 0 }
fact := 1;
repeat
fact := fact * x;
x := x - 1
until x = 0;
write fact { output factorial of x }
and

输出结果

1: { Sample program
1: { Sample program
2: in TINY language -
2: in TINY language -
3: computes factorial
3: computes factorial
4: }
4: }
5: read x; { input an integer }
5: Reversed Word: read
5: ID, name= x
5: ;
5: { input an integer }
6: if 0 < x then { don’t compute if x <= 0 }
6: Reversed Word: if
6: NUM, val= 0
6: <
6: ID, name= x
6: Reversed Word: then
6: { don’t compute if x <= 0 }
7: fact := 1;
7: ID, name= fact
7: :=
7: NUM, val= 1
7: ;
8: repeat
8: Reversed Word: repeat
9: fact := fact * x;
9: ID, name= fact
9: :=
9: ID, name= fact
9: *
9: ID, name= x
9: ;
10: x := x - 1
10: ID, name= x
10: :=
10: ID, name= x
10: -
10: NUM, val= 1
11: until x = 0;
11: Reversed Word: until
11: ID, name= x
11: =
11: NUM, val= 0
11: ;
12: write fact { output factorial of x }
12: Reversed Word: write
12: ID, name= fact
12: { output factorial of x }
13: and
13: ID, name= and