编译原理——词法分析器

1.词法分析器的主要工作

2.单词的基本分类

3.有限状态机

4.程序流程图

5.以下为完整代码

//compiler
#include<iostream>
#include<ctype.h>
#include<cstring>
#include<cstdio>
using namespace std;

const char *k[12] = {"for","if","else","do","while","return","int","char","short","float","double","string"};
char instring[80];
char outtoken[10];
//char id[10] = {'\0'};
//int ci[10];
int m;
//int num = 0;
int t;
int p;
char ch;
int row = 1,col = 0;
int j = 0;
void scan()
{
ch = instring[p ++];
m = -1;
for(int i = 0; i < 10; i ++)
outtoken[i] = '\0';
if(ch == ' ')ch = instring[p ++];
if(ch == '\n'){
ch = instring[p ++];
row = row + 1;
col = 0;
}
if(isalpha(ch)){
while(isalpha(ch)||isdigit(ch)){
outtoken[++ m] = ch;
ch = instring[p ++];
}
outtoken[++ m] = '\0';
ch = instring[p --];
int flag = 0;
for(int n = 0; n < 12; n++){
if(strcmp(outtoken,k
) == 0){
t = 1;
flag = 1;
break;
}
}
if(flag == 0){
//strcpy(id,outtoken);
t = 6;
}
col = col + 1;
}
else if(isdigit(ch)){
while(isdigit(ch) || ch == '.'){
m = m + 1;
outtoken[m] = ch;
//num = num * 10 + ch - '0';
ch = instring[p ++];
}
//cout<<m<<endl;当时写出这个语句，是为了检测m的值，以判断程序是否有bug
for(int num = 0; num < m; num ++){
if(outtoken[num] == '.')
j = j + 1;//判断是否有多个“.”，如果有多个就说明该数字是错误的，如：1.2.2
}
int tag = 0;//设立标志
if(j > 1){
outtoken[++ m] = '\0';
ch = instring[p --];
t = -1;//t=-1，报错。
tag = 1;//tag置1
}
if(isalpha(ch)){
outtoken[++ m] = ch;
outtoken[++ m] = '\0';
t = -1;
}
else if(tag == 0){//执行了第一个if语句，就一定不会执行这句。
outtoken[++ m] = '\0';
ch = instring[p --];
t = 5;
}
col = col + 1;
}
else{
switch(ch){
case '+':
outtoken[++ m] = ch;
ch = instring[p ++];
if(ch == '+')
outtoken[++ m] = ch;
else
ch = instring[p --];
case '-':

case '*':   case '/':t = 3;col = col + 1;break;
case ',':   case ';':
case '(':   case ')':
case '{':   case '}':
case '[':   case ']':t = 2;outtoken[0] = ch;col = col + 1;break;
case '#':
t = 0;outtoken[++ m] = ch;break;
case '=':
outtoken[++ m] = ch;
ch = instring[p ++];
if(ch == '='){
outtoken[++ m] = ch;
t = 4;

}
else{
ch = instring[p --];
t = 4;
}
col = col + 1;
break;
case '<':
outtoken[++ m] = ch;
ch = instring[p ++];
if(ch == '='||ch == '>'){
outtoken[++ m] = ch;
t = 4;
}
else{
t = 4;
ch = instring [p --];
}
col = col + 1;
break;
case '>':
outtoken[++ m] = ch;
ch = instring[p ++];
if(ch == '='){
outtoken[++ m] = ch;
t = 4;
}
else{
t = 4;
ch = instring[p --];
}
col = col + 1;
break;
default:
outtoken[0] = ch;
t = -1;
col = col + 1;
break;
}
}
}

int main()
{
cout<<"请输入要进行词法分析的代码块（C++）:\n";
p = -1;
do{
ch = getchar();
instring[p ++] = ch;
}while(ch != '#');
p = -1;
//ch = instring[p ];
cout<<"单词\t二元序列\t类型\t\t位置（行，列）"<<endl<<endl;
do{
scan();
switch(t){
case 1:
cout<<outtoken<<"\t"<<"("<<1<<","
<<outtoken<<")\t\t"<<"关键字\t\t"
<<"("<<row<<","<<col<<")"<<endl;
break;
case 2:
cout<<outtoken<<"\t"<<"("<<2<<","
<<outtoken<<")\t\t"<<"分界符\t\t"
<<"("<<row<<","<<col<<")"<<endl;
break;
case 3:
cout<<outtoken<<"\t"<<"("<<3<<","
<<outtoken<<")\t\t"<<"算术运算符\t"
<<"("<<row<<","<<col<<")"<<endl;
break;
case 4:
cout<<outtoken<<"\t"<<"("<<4<<","
<<outtoken<<")\t\t"<<"关系运算符\t"
<<"("<<row<<","<<col<<")"<<endl;
break;
case 5:
cout<<outtoken<<"\t"<<"("<<5<<","
<<outtoken<<")\t\t"<<"常量\t\t"
<<"("<<row<<","<<col<<")"<<endl;
break;
case 6:
cout<<outtoken<<"\t"<<"("<<6<<","
<<outtoken<<")\t\t"<<"标识符\t\t"
<<"("<<row<<","<<col<<")"<<endl;
break;
case -1:
cout<<outtoken<<"\t\t\t"<<"Error!\t\t"
<<"("<<row<<","<<col<<")"<<endl;
case 0:
break;
}
}while(t != 0);
return 0;
}

6.运行结果

7.说明

if(condition1){...}

if(condition2){...}

else {...}