编译原理实验3 词法分析

【任务介绍】根据给定源语言的构词规则，从任意字符串中识别出该语言所有的合法的单词符号，并以等长的二元组形式输出。
【输入】字符串形式的源程序。
【输出】单词符号所构成的串（流），单词以等长的二元组形式呈现。
【题目】设计一个程序，根据给定源语言的构词规则，从任意字符串中识别出该语言所有的合法的单词符号，并以等长的二元组形式输出。

#include <iostream>
#include <string.h>
using namespace std;

// 全局变量，关键字表【c语言的32个关键字】
// 种别码：<auto, 1>...<while, 32>
static char keyword[32][10] = {
	"auto", "break", "case", "char", "const", "continue", "default", "do", "double", "else", "enum", "extern",
	"float", "for", "goto", "if", "int", "long", "register", "return", "short", "signed", "sizeof", "static", 
	"struct", "switch", "typedef", "union", "unsigned", "void", "volatile", "while"
};
// 界符，运算符表【36个， 可继续添加】
/*编码
<+，33> <-,34> <*,35> </,36> <<,37> <<=,38> <>,39> <>=,40> <=,41> <==,42> <!=,43> <;,44> <(,45> <),46>
<^,47> <,,48> <",49> <',50> <#,51> <&,52> <&&,53> <|,54> <||,55> <%,56> <~,57> <<<,58>左移 <>>,59>右移 
<[,60> <],61> <{,62> <},63> <\,64> <.,65> <?,66> <:,67> <!,68> "[","]","{","}"
*/
static char operatorOrDelimiter[36][10] = {
	"+", "-", "*", "/", "<", "<=", ">", ">=", "=", "==", "!=", ";", "(", ")", "^", ",", "\"", "\'", "#", "&",
	"&&", "|", "||", "%", "~", "<<", ">>", "[", "]", "{", "}", "\\", ".", "\?", ":", "!"
};
// 常数		<常数， 99>
// 标识符表	<标识符, 100>
static char identifier[1000][40] = {""};

//查找关键字
int searchKeyword(char keyword[][10], char s[])
{
	for (int i = 0; i < 32; i++)
	{
		if (strcmp(keyword[i], s) == 0)
		{
			return i + 1;		// 匹配则返回种别码，关键字种别码 1-32
		}
	}
	return -1;	//查找不成功，为标识符
}

//判断是否为字母
bool isLetter(char letter)
{
	// a-z && A-Z && _
	if (letter >= 'a' && letter <= 'z' || letter >= 'A' && letter <= 'Z' || letter == '_')
		return true;
	else
		return false;
}

//判断是否为数字
bool isDigit(char digit)
{
	if (digit >= '0' && digit <= '9')
		return true;
	else
		return false;
}


//读入分析,核心部分（根据状态转化图）
void scanner(int &syn, char resourceCode[], char token[], int &p)
{
	char ch;
	int count = 0;	//count指示token[]，存入有用字符
	ch = resourceCode[p];
	while (ch == ' ' || ch == '\n' || ch == '\t')	// 跳过空格和回车（结果因为tab(\t)找了好久的错误）
	{
		p++;
		ch = resourceCode[p];
	}
	for (int i = 0; i < 20; i++)
	{
		token[i] = '\0';	// 每次收集前先清零
	}

	// 开头为字母
	if (isLetter(resourceCode[p]))
	{
		token[count++] = resourceCode[p];	//写入token[]中
		p++;
		while (isLetter(resourceCode[p]) || isDigit(resourceCode[p]))
		{
			token[count++] = resourceCode[p];	// 后跟字母或数字继续写入token
			p++;
		}
		token[count] = '\0';
		syn = searchKeyword(keyword, token);	// 查找种别码
		if (syn == -1)	// 若非关键字即为标识符
		{
			syn = 100;	// 标识符种别码
		}
		return;
	}
	else if (ch == '-')	// 如果是负数
	{
		token[count++] = resourceCode[p];
		p++;
		ch = resourceCode[p];
		while (isDigit(resourceCode[p]))
		{
			token[count++] = resourceCode[p];
			p++;	//多读了一个字符既是下次将要开始的指针位置
		}
		token[count] = '\0';
		syn = 99;	//常数种别码99
	}
	else if (isDigit(resourceCode[p]))	// 正数-起始字母为数字
	{
		while (isDigit(resourceCode[p]))
		{
			token[count++] = resourceCode[p];
			p++;
		}
		token[count] = '\0';
		syn = 99;
	}
	else if (ch == '+' || ch == '-' || ch == '*' || ch == '/' || ch == ';' || ch == '(' || ch == ')' 
		|| ch == '^' || ch == ',' || ch == '\"' || ch == '\'' || ch == '~' || ch == '#' || ch == '%' 
		|| ch == '[' || ch == ']' || ch == '{' || ch == '}' || ch == '\\' || ch == '.' || ch == '\?' 
		|| ch == ':')
	{
		// 若为运算符或者界符，查表得到结果，单字符
		token[0] = resourceCode[p];
		token[1] = '\0';	// 形成单字符
		for (int i = 0; i < 36; i++)
		{
			if (strcmp(token, operatorOrDelimiter[i]) == 0)
			{
				syn = 33 + i;	// 获得种别码
				break;	// 查到后退出
			}
		}
		p++;
		return;
	}
	// 多目运算
	else if (resourceCode[p] == '<')	// <,<=,<<
	{
		p++;
		if (resourceCode[p] == '=')
		{
			syn = 38;
		}
		else if (resourceCode[p] == '<')
		{
			p--;
			syn = 58;
		}
		else
		{
			p--;
			syn = 37;
		}
		p++;
		return;
	}
	else if (resourceCode[p] == '>')	// >,>=,>>
	{
		p++;
		if (resourceCode[p] == '=')
			syn = 40;
		else if (resourceCode[p] == '>')
		{
			p--;
			syn = 59;
		}
		else
		{
			p--;
			syn = 39;
		}
		p++;
		return;
	}
	else if (resourceCode[p] == '=')
	{
		p++;
		if (resourceCode[p] == '=')
			syn = 42;	// ==
		else
		{
			p--;
			syn = 41;	// =
		}
		p++;
		return;
	}
	else if (resourceCode[p] == '!')
	{
		p++;
		if (resourceCode[p] == '=')	// !=
			syn = 43;
		else
		{
			syn = 68;		// !
			p--;
		}
		p++;
		return;
	}
	else if (resourceCode[p] == '&')
	{
		p++;
		if (resourceCode[p] == '&')	// &&
			syn = 53;
		else
		{
			syn = 52;		// &
			p--;
		}
		p++;
		return;
	}
	else if (resourceCode[p] == '|')
	{
		p++;
		if (resourceCode[p] == '|')
			syn = 55;		// ||
		else
		{
			syn = 54;
			p--;
		}
		p++;
		return;
	}
	else if (resourceCode[p] == '$')	// 结束符
		syn = 0;	// 种别码为0
	else
	{
		cout << "无法识别的字符>>>>> %c" << ch << endl;
		exit(0);
	}
}


int main(void)
{
	char resourceCode[10000];	// 用于存入源码的数组
	char token[20] = { 0 };		// 生成序列
	int syn = -1;	// 初始化
	int p = 0;	// 源程序指针

	FILE *fp1, *fp2;
	if ((fp1 = fopen("input.txt", "r")) == NULL)
	{
		cout << "无法打开文件！" << endl;
		exit(0);
	}
	resourceCode[p] = fgetc(fp1);
	// 将源程序读入数组,输出到屏幕
	while (resourceCode[p] != '$')
	{
		p++;
		resourceCode[p] = fgetc(fp1);
	}
	resourceCode[++p] = '\0';
	cout << "input.txt 源程序为:" << endl;
	cout << resourceCode << endl;

	if ((fp2 = fopen("output.txt", "w+")) == NULL)
	{
		cout << "无法写入！" << endl;
		exit(0);
	}

	// 指针复位，从头开始读
	p = 0;
	while (syn != 0)
	{
		// 启动扫描
		scanner(syn, resourceCode, token, p);
		if (syn == 100)		// 标识符
		{
			for (int i = 0; i < 1000; i++)		// 插入标识符表中
			{
				if (strcmp(identifier[i], token) == 0)
					break;		//已经在表中
				if (strcmp(identifier[i], "") == 0)
				{
					// 查找空间
					strcpy(identifier[i], token);
					break;
				}
			}
			cout << "<" << syn << ", " << token << ">" << endl;
			fprintf(fp2, "<%d, %s>\n", syn, token);
		}
		else if (syn >= 1 && syn <= 32)	// keyword
		{
			cout << "<" << syn << ", " << keyword[syn - 1] << ">" << endl;
			fprintf(fp2, "<%d, %s>\n", syn, keyword[syn - 1]);
		}
		else if (syn >= 33 && syn <= 68)
		{
			cout << "<" << syn << ", " << operatorOrDelimiter[syn - 33] << ">" << endl;
			fprintf(fp2, "<%d, %s>\n", syn, operatorOrDelimiter[syn - 33]);
		}
		else if (syn == 99)		// 常数
		{
			cout << "<" << syn << ", " << token << ">" << endl;
			fprintf(fp2, "<%d, %s>\n", syn, token);
		}
	}

	system("pause");
	return 0;
}

运行结果展示

处理后（部分截图）