编译原理：C语言词法分析器

标签：

编译原理的实验：完成对C语言的词法分析

先说一下整体框架：

基类：Base  封装了一些基础的字符判断函数，如下：

int charkind(char c);//判断字符类型
	int spaces(char c); //当前空格是否可以消除
	int characters(char c);//是否是字母
	int keyword(char str[]);//是否是关键字
	int signwords(char str[]);//是否是标识符
	int numbers(char c);//是否是数字
	int integers(char str[]);//是否是整数
	int floats(char str[]);//是否是浮点型

派生类 LexAn 继承Base并且封装了对行和单词处理的函数，如下：

void scanwords(); //处理每一行
		void clearnotes();//清除注释和多余的空格
		void getwords(int state);//处理出单词
		void wordkind(char str[]);//判断单词类型并且输出

函数之间调用关系如下：

好了，整体框架说完了，我们来说具体的实现：

（一）清除注释和多余的空格

（1）C语言的注释有//和/* 两种形式，所以如果当前读进的是 / 只需分情况判断下一个：

如果是/ 那么本行 //之后的肯定都是注释，只需要保存注释，更新当前行即可；

如果是* ,那么接着寻找直至 */位置，保存注释，更新当前行，然后继续这个操作（有可能有本行有多个 /* */）.

不足：不能处理跨行注释。

（2）处理多余的空格这里较为草率，只处理了形如if (    a    >=   b  )，即特殊符号和字母（数字）之间的空格；只要空格两端有特殊符号，那么去掉当前空格便不会造成错误。

void LexAn::clearnotes()
{
	int i, j, k;
	int noteCount = 0;
	int flag = 0;
	char note[100];

	/*注释*/
	for (i = 0; bufferin[buffernum][i] != '\0'; i++)
	{
		if (bufferin[buffernum][i] == '"')
		{
			flag = 1 - flag;
			continue;
		}
		if (bufferin[buffernum][i] == '/' && flag == 0)
		{
			if (bufferin[buffernum][i + 1] == '/')
			{
				for (j = i; bufferin[buffernum][j] != '\0'; j++)
				{
					note[noteCount++] = bufferin[buffernum][j];
				}
				note[noteCount] = '\0';
				noteCount = 0;
				fprintf(fout, "  [ %s ]  ----  [ 注释 ]\n", note);
				bufferin[buffernum][i] = '\0';
				break;
			}

			if (bufferin[buffernum][i + 1] == '*')
			{
				note[noteCount++] = '/';
				note[noteCount++] = '*';
				for (j = i + 2; bufferin[buffernum][j] != '\0'; j++)
				{
					note[noteCount++] = bufferin[buffernum][j];
					if (bufferin[buffernum][j] == '*' && bufferin[buffernum][j + 1] == '/')
					{
						j += 2;
						note[noteCount++] = bufferin[buffernum][j];
						note[noteCount] = '\0';
						noteCount = 0;
						fprintf(fout, "  [ %s ]  ----  [ 注释 ]\n", note);
						break;
					}
				}
				for (; bufferin[buffernum][j] != '\0'; j++, i++)
				{
					bufferin[buffernum][i] = bufferin[buffernum][j];
				}
				if (bufferin[buffernum][j] == '\0')
				{
					bufferin[buffernum][i] = '\0';
				}
			}
		}
	}

	//空格 
	for (i = 0, flag = 0; bufferin[buffernum][i] != '\0'; i++)
	{
		if (bufferin[buffernum][i] == '"')
		{
			flag = 1 - flag;
			continue;
		}
		if (bufferin[buffernum][i] == ' ' && flag == 0)
		{
			for (j = i + 1; bufferin[buffernum][j] != '\0' && bufferin[buffernum][j] == ' '; j++)
			{
			}
			if (bufferin[buffernum][j] == '\0')
			{
				bufferin[buffernum][i] = '\0';
				break;
			}
			if (bufferin[buffernum][j] != '\0' && ((spaces(bufferin[buffernum][j]) == 1) || (i > 0 && spaces(bufferin[buffernum][i - 1]) == 1)))
			{
				for (k = i; bufferin[buffernum][j] != '\0'; j++, k++)
				{
					bufferin[buffernum][k] = bufferin[buffernum][j];
				}
				bufferin[buffernum][k] = '\0';
				i--;
			}
		}
	}

	//制表符 
	for (i = 0, flag = 0; bufferin[buffernum][i] != '\0'; i++)
	{
		if (bufferin[buffernum][i] == '\t')
		{
			for (j = i; bufferin[buffernum][j] != '\0'; j++)
			{
				bufferin[buffernum][j] = bufferin[buffernum][j + 1];
			}
			i = -1;
		}
	}
}

画图不是很好话，我尽量用语言清除地描述，大家还需结合源码分析：

主要分为 <字母, 1> <数字,  2> <$ _ ,  3> <4 ,/ >(转义) < = ,5> <0,else >

state初始值设为0：

（1）如果首位字符是字母，那么只可能是标识符和关键字，之后遇到除 数字，字母，$，_，之外的字符结束，取出单词。

（2）如果首位字符是数字，那么只能是数字，即八进制，十六进制，. ，数字，$ ，之后遇到除上述之外的字符结束，取出单词。

（3）如果首位是$ _ ,那么只能是标识符，即字母，数字，$,之后遇到除上述之外的字符结束，取出单词。

（4）如果首位是特殊字符（" . () = 等），那么再分开处理，流程和上述的一致，遇到不可能的组合结束；这部分看代码吧。

//状态机
void LexAn::getwords(int state)
{
	char word[100];
	int charCount = 0;
	int finish = 0;
	int num;
	int i, j, k;
	for (i = 0; bufferscan[i] != '\0'; i++)
	{
		switch (state / 10)
		{
		case 0:
			switch (charkind(bufferscan[i]))
			{
			case 1:
				word[charCount++] = bufferscan[i];
				state = 10;
				break;
			case 2:
				word[charCount++] = bufferscan[i];
				state = 20;
				break;
			case 3:
				word[charCount++] = bufferscan[i];
				state = 30;
				break;
			case 0: case 5:
				word[charCount++] = bufferscan[i];
				switch (bufferscan[i])
				{
				case '"':
					state = 41;
					break;
				case '\'':
					state = 42;
					break;
				case '(': case ')': case '{': case '}': case '[': case ']': case ';': case ',': case '.':
					state = 50;
					word[charCount] = '\0';
					finish = 1;
					break;
				case '=':
					state = 43;
					break;
				default:
					state = 40;
					break;
				}
				break;
			default: word[charCount++] = bufferscan[i]; break;
			}
			break;
		case 1:
			switch (charkind(bufferscan[i]))
			{
			case 1:
				word[charCount++] = bufferscan[i];
				state = 10;
				break;
			case 2:
				word[charCount++] = bufferscan[i];
				state = 20;
				break;
			case 3:
				word[charCount++] = bufferscan[i];
				state = 30;
				break;
			case 0:case 5:
				word[charCount] = '\0';
				num = 0;
				while (word[num] != '\0')
					num++;

				<span style="color:#ff6600;">//长度的处理 ！！
				if (num>7)
					word[7] = '\0';</span>

				i--;
				finish = 1;
				state = 50;
				break;
			default: word[charCount++] = bufferscan[i]; break;
			}
			break;
		case 2:
			switch (charkind(bufferscan[i]))
			{
			case 1:
				word[charCount++] = bufferscan[i];
				state = 20;
				break;
			case 2:
				word[charCount++] = bufferscan[i];
				state = 20;
				break;
			case 3:
				word[charCount++] = bufferscan[i];
				state = 30;
				break;
			case 0:
				if (bufferscan[i] == '.')
				{
					word[charCount++] = bufferscan[i];
					state = 20;
					break;
				}
				word[charCount] = '\0';
				i--;
				finish = 1;
				state = 50;
				break;
			default: word[charCount++] = bufferscan[i]; break;
			}
			break;
		case 3:
			switch (charkind(bufferscan[i]))
			{
			case 1:
				word[charCount++] = bufferscan[i];
				state = 30;
				break;
			case 2:
				word[charCount++] = bufferscan[i];
				state = 30;
				break;
			case 3:
				word[charCount++] = bufferscan[i];
				state = 30;
				break;
			case 0:
				word[charCount] = '\0';
				i--;
				finish = 1;
				state = 50;
				break;
			default: word[charCount++] = bufferscan[i]; break;
			}
			break;
		case 4:
			switch (state)
			{
			case 40:
				switch (charkind(bufferscan[i]))
				{
				case 1:
					word[charCount] = '\0';
					i--;
					finish = 1;
					state = 50;
					break;
				case 2:
					word[charCount] = '\0';
					i--;
					finish = 1;
					state = 50;
					break;
				case 3:
					word[charCount] = '\0';
					i--;
					finish = 1;
					state = 50;
					break;
				case 0:
					word[charCount++] = bufferscan[i];
					state = 40;
					break;
				default: word[charCount++] = bufferscan[i]; break;
				}
				break;
			case 41:
				word[charCount++] = bufferscan[i];
				if (bufferscan[i] == '"')
				{
					if (charkind(bufferscan[i - 1]) == 4)
					{
					}
					else
					{
						word[charCount] = '\0';
						finish = 1;
						state = 50;
					}
				}
				break;
			case 42:
				word[charCount++] = bufferscan[i];
				if (bufferscan[i] == '\'')
				{
					word[charCount] = '\0';
					finish = 1;
					state = 50;
				}
				break;
			case 43:
				if (bufferscan[i] == '=')
				{
					word[charCount++] = bufferscan[i];
					state = 43;
				}
				else
				{
					word[charCount] = '\0';
					finish = 1;
					i--;
					state = 50;
				}
				break;
			default: word[charCount++] = bufferscan[i]; break;
			}
			break;
		case 5:
			finish = 0;
			state = 0;
			charCount = 0;
			i--;

			wordkind(word);
			break;
		default:break;
		}
		if (bufferscan[i + 1] == '\0')
		{
			word[charCount] = '\0';
			wordkind(word);
		}
	}
}

（三）效果截图：

本项目全部源码放在个人  Github 上，欢迎大家star和fork学习哈。

编译原理：C语言词法分析器

标签：

原文地址：http://blog.csdn.net/nk_test/article/details/51245559