博客

注：需在txt文件中以’#’键结尾。代码已在vs2019中运行成功。

#include <iostream>
#include <fstream>
#include <cstring>
using namespace std;

#define max 1000
char ch;//用于取单个字符
char token[max][100];//存放字符
int ptoken = 0;

//关键字
const char* pkeyword[] = { "if", "else", "while", "int", "main", "switch", "case", "return",
						  "break","char","const","default","do","double","for","float",
						   "static","struct","switch","void" };
//识别字母
int letter()
{
	if (ch >= 'a' && ch <= 'z' || ch >= 'A' && ch <= 'Z')
		return 1;
	else
		return 0;
}
//识别数字
int digit()
{
	if (ch >= '0' && ch <= '9')
		return 1;
	else
		return 0;
}
//识别关键字
int reserve()
{
	for (int i = 0; i < 20; i++)
	{
		if (strcmp(token[ptoken], pkeyword[i]) == 0)
			return i;
	}
	return 20;
}

void scanning(ifstream* pfile)
{
	pfile->get(ch);
	while (1)
	{
		//识别关键字和标识符
		if (letter())
		{
			int i = 0;
			token[ptoken][i] = ch;
			while (pfile->get(ch) && (letter() || digit()))//识别字母和数字
			{

				i++;
				token[ptoken][i] = ch;
			}
			int check = reserve();//识别关键字
			if (check < 20)
				cout << pkeyword[check] << "\t" << "关键字" << endl;
			else
				cout << token[ptoken] << "\t" << "标识符" << endl;
			ptoken++;//为下一次识别准备
		}
		//识别数字
		else if (digit())
		{
			int i = 0;
			token[ptoken][i] = ch;
			pfile->get(ch);
			while (digit())
			{
				i++;
				token[ptoken][i] = ch;
				pfile->get(ch);
			}
			cout << token[ptoken] << "\t" << "数字" << endl;
			ptoken++;
		}
		//过滤注释
		else if (ch == '/')
		{
			token[ptoken][0] = ch;
			pfile->get(ch);
			if (ch == '/')
			{
				token[ptoken][1] = ch;
				cout << token[ptoken] << "\t" << "注释" << endl;
				while (pfile->get(ch) && ch != '\n') {}//过滤掉'//'之后一行的字符
			}
			/*if (ch == '*')
			{
				token[ptoken][1] == ch;
				cout << token[ptoken] << "\t" << "注释" << endl;
				pfile->get(ch);
				ptoken++;
				if (ch == '*')
				{
					token[ptoken][0] = ch;
					pfile->get(ch);
					if (ch == '/')
					{
						token[ptoken][1] = ch;
						cout<<token[ptoken] << "\t" << "注释" << endl;
					}

				}
			}*/
			else
			{
				cout << token[ptoken] << "\t" << "运算符" << endl;
			}
			ptoken++;
		}
		//过滤空格、换行符、制表符
		else if (ch == ' ' || ch == '\n' || ch == '\t')
			pfile->get(ch);
		//结束
		else if (ch == '#')
			break;
		//特殊字符
		else
		{
			switch (ch)
			{
			case '+':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '-':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '*':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '=':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '(':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case ')':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '{':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '}':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '[':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case ']':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case ':':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '.':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '\\':
				token[ptoken][0] = ch;
				pfile->get(ch);
				if (ch == '\\')
				{
					token[ptoken][1] = ch;
					cout << token[ptoken] << "\t" << "界符" << endl;
					pfile->get(ch);
				}
				else {
					cout << token[ptoken] << "\t" << "界符" << endl;
				}
				ptoken++;
				break;
			case '"':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '\'':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case ';':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '!':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case ',':
				token[ptoken][0] = ch;
				cout << token[ptoken] << "\t" << "界符" << endl;
				ptoken++;
				pfile->get(ch);
				break;
			case '&':
				token[ptoken][0] = ch;
				pfile->get(ch);
				if (ch == '&')
				{
					token[ptoken][1] = ch;
					cout << token[ptoken] << "\t" << "运算符" << endl;
					pfile->get(ch);
				}
				else
					cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				break;
			case '<':
				token[ptoken][0] = ch;
				pfile->get(ch);
				if (ch == '=')
				{
					token[ptoken][1] = ch;
					cout << token[ptoken] << "\t" << "运算符" << endl;
					pfile->get(ch);
				}
				if (ch == '<')
				{
					token[ptoken][1] = ch;
					cout << token[ptoken] << "\t" << "运算符" << endl;
					pfile->get(ch);
				}
				else
					cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				break;
			case '>':
				token[ptoken][0] = ch;
				pfile->get(ch);
				if (ch == '=')
				{
					token[ptoken][1] = ch;
					cout << token[ptoken] << "\t" << "运算符" << endl;
					pfile->get(ch);
				}
				else
					cout << token[ptoken] << "\t" << "运算符" << endl;
				ptoken++;
				break;
			default:
				//				cout << "暂时无法识别:" << "\t" << ch << endl;
				pfile->get(ch);
				break;
			}
		}
	}
}

int main()
{
	ifstream infile("F:\\test.txt", ios::in);
	if (!infile)
	{
		cout << "file could not be open" << endl;
		return 0;
	}
	cout<< "单词"<<'\t'<< "类别" << endl;
	scanning(&infile);
	infile.close();
	return 1;

}

txt文件举例：

运行结果：