实践说明

【题目要求】
编写C++程序分析当前目录下input.txt文件中的词法，以“(种别码,单词)”的形式输出，单词对应的种别码自拟，输出结果存放到当前目录下的output.txt文件中。

【可分析词法】
程序可识别64种词法，内容如下：
1、关键字：begin, void, int, char, main, if, scanf, printf, while, for, return, end
2、标识符（输出时前后会带上单引号）
3、十进制数字（输出时转换成二进制形式）
4、算术运算符：+, -, *, /, %, ++, –
5、关系运算符：==, !=, >, <, >=, <=
6、逻辑运算符：&&, ||, !
7、位运算符：&, |, ^, >>, <<
8、赋值运算符：=, +=, -=, =, /=, %=, >>=, <<=, &=, ^=, |=
9、注释：//, /, */
10、其他：., ->, ', ", , (, ), [, ], {, }, :, , ;, \n
注意，对于不存在于本词法中的输入X，本程序将输出：(-1,‘X’ does not exist in this lexical system)

【操作步骤】
1、在input.txt文件中输入或更改待分析的C源程序段（段末请以#结尾）。
2、双击程序exe文件即可完成词法分析程序的运行。
3、在output.txt文件中查看词法分析结果。

输入举例（input.txt）

begin
/* the main function */
void main()
{int i = 8 + 244 * 5 / 10 - 2;char _KEY_WORD_END = '\\';scanf("%[^end]s", ch); // get the stringif(i == 0){printf("good!, the result is:\n");for(; i != 128; -- i){while(i % 2 != 0 || (i < 61) && (i > 16)){oneWord -> value = ch[i ++];}}}return 0;
}$
end#

输出举例（output.txt）

Your words:-------------------------------
begin
/* the main function */
void main()
{int i = 8 + 244 * 5 / 10 - 2;char _KEY_WORD_END = '\\';scanf("%[^end]s", ch); // get the stringif(i == 0){printf("good!, the result is:\n");for(; i != 128; -- i){while(i % 2 != 0 || (i < 61) && (i > 16)){oneWord -> value = ch[i ++];}}}return 0;
}$
end
-------------------------------The result of lexical analyzer:(1,begin)
(20,\n)
(68,/*)
(69,*/)
(20,\n)
(2,void)
(5,main)
(56,()
(57,))
(20,\n)
(60,{)
(20,\n)
(3,int)
(13,'i')
(42,=)
(14,1000)
(21,+)
(14,11110100)
(23,*)
(14,101)
(24,/)
(14,1010)
(22,-)
(14,10)
(64,;)
(20,\n)
(4,char)
(13,'_KEY_WORD_END')
(42,=)
(65,')
(55,\)
(65,')
(64,;)
(20,\n)
(7,scanf)
(56,()
(66,")
(25,%)
(58,[)
(39,^)
(12,end)
(59,])
(13,'s')
(66,")
(63,,)
(13,'ch')
(57,))
(64,;)
(67,//)
(20,\n)
(6,if)
(56,()
(13,'i')
(28,==)
(14,0)
(57,))
(20,\n)
(60,{)
(20,\n)
(8,printf)
(56,()
(66,")
(13,'good')
(36,!)
(63,,)
(13,'the')
(13,'result')
(13,'is')
(62,:)
(20,\n)
(66,")
(57,))
(64,;)
(20,\n)
(10,for)
(56,()
(64,;)
(13,'i')
(29,!=)
(14,10000000)
(64,;)
(27,--)
(13,'i')
(57,))
(20,\n)
(60,{)
(20,\n)
(9,while)
(56,()
(13,'i')
(25,%)
(14,10)
(29,!=)
(14,0)
(35,||)
(56,()
(13,'i')
(31,<)
(14,111101)
(57,))
(34,&&)
(56,()
(13,'i')
(30,>)
(14,10000)
(57,))
(57,))
(20,\n)
(60,{)
(20,\n)
(13,'oneWord')
(54,->)
(13,'value')
(42,=)
(13,'ch')
(58,[)
(13,'i')
(26,++)
(59,])
(64,;)
(20,\n)
(61,})
(20,\n)
(61,})
(20,\n)
(61,})
(20,\n)
(11,return)
(14,0)
(64,;)
(20,\n)
(61,})
(-1,'$' does not exist in this lexical system)
(20,\n)
(12,end)

编程平台

CodeBlocks 10.05

代码实现

程序环境设置

#include <iostream>
#include <stdio.h>          /*包含库所用的某些宏和变量*/
#include <stdlib.h>         /*包含库*/
#include <string.h>         /*包含字符串处理库*/#define _KEY_WORD_END "waiting for your expanding" /*定义关键字结束标志*/using namespace std;typedef struct              /*单词二元组*/
{int categoryCode;       /*单词种别码*/char *value;            /*单词自身的值*/
}WORD;char inputBuffer[10000];    /*输入缓冲区*/
char wordBuffer[1000] = ""; /*单词缓冲区*/
int inputBufferIndex;       /*输入缓冲区下标*/
int wordBufferIndex;        /*单词缓冲区下标*/char ch;                    /*当前读入字符*/
char *rwtab[] = {"begin", "void", "int", "char", "main", "if", "scanf", "printf", "while", "for", "return", "end", _KEY_WORD_END};/*关键字数组*/WORD* scaner();             /*声明词法分析函数，获得一个单词*/
char getChar();             /*声明字符读取函数，从输入缓冲区读取一个字符*/
void removeBlankSymbol();   /*声明去掉空格和\t函数*/
void concatWord();          /*声明拼接单词函数*/
int isLetter();             /*声明判断是否字母函数*/
int isDigit();              /*声明判断是否数字函数*/
int retriveKeyword();       /*声明检索关键字数组函数，在字符数组rwtab中检索*/
void retractChar();         /*声明回退字符函数，回退一个字符*/
char* digitToBinary();      /*声明将十进制转换成二进制函数*/
char* changeWordFormation();/*声明更改单词的输出形式函数*/

主函数定义

int main()
{freopen("input.txt","r",stdin);    // 从input.txt获取输入freopen("output.txt","w",stdout);  // 输出到output.txt里int over = 1;                            // 判断是否出现#inputBufferIndex = 0;                    // 初始化输入缓冲区下标WORD *oneWord = new WORD;                // 关键字数组scanf("%[^#]s", inputBuffer);            // 读入源程序字符串到缓冲区，以#结束，允许多行输入，#不读入printf("Your words:\n\n");printf("-------------------------------\n");printf("%s\n", inputBuffer);printf("-------------------------------\n\n");printf("The result of lexical analyzer:\n\n");while (over < 1000)                      // 分析源程序直到出现结束符#{oneWord = scaner();                  // 获得一个新单词if (oneWord -> categoryCode < 1000)  // 本程序的种别码数量最多不超过1000个{printf("(%d,%s)\n", oneWord -> categoryCode, oneWord -> value);// 打印种别码和单词自身的值}over = oneWord -> categoryCode;}
}

单词获取

/*获取一个单词*/
WORD* scaner()
{WORD *myWord = new WORD;myWord -> categoryCode = 13;myWord -> value = "";wordBufferIndex = 0;getChar();           // 从输入缓冲区读取一个字符到ch中removeBlankSymbol(); // 去掉空格if(isLetter()) // 如果单词的第一个字符为字母，则说明该单词为变量{while(isLetter() || isDigit()) // 变量名可以有数字{concatWord(); // 拼接单词getChar();    // 从输入缓冲区读取下一个字符到ch中}retractChar(); // 回退一个字符if((myWord -> categoryCode = retriveKeyword()) == 13) // 说明不是关键字，需要加上引号后输出{myWord -> value = changeWordFormation();}else{myWord -> value = wordBuffer;}return myWord;}else if(isDigit()) // 如果单词的第一个字符为数字，则说明该单词为数字{while(isDigit()){concatWord(); // 拼接单词getChar();    // 从输入缓冲区读取下一个字符到ch中}retractChar(); // 回退一个字符myWord -> categoryCode = 14;myWord -> value = digitToBinary(); // 将数字转换成二进制数return myWord;}else // 说明单词为符号{switch(ch){case '+': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“+=”符号{myWord -> categoryCode = 43;myWord -> value = "+=";return myWord;}else if(ch == '+') // 是则说明是“++”符号{myWord -> categoryCode = 26;myWord -> value = "++";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 21;myWord -> value = "+";return myWord;break;case '-': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“-=”符号{myWord -> categoryCode = 44;myWord -> value = "-=";return myWord;}else if(ch == '-') // 是则说明是“--”符号{myWord -> categoryCode = 27;myWord -> value = "--";return myWord;}else if(ch == '>') // 是则说明是“->”符号{myWord -> categoryCode = 54;myWord -> value = "->";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 22;myWord -> value = "-";return myWord;break;case '*': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“*=”符号{myWord -> categoryCode = 45;myWord -> value = "*=";return myWord;}else if(ch == '/') // 是则说明是“*/”注释符号{myWord -> categoryCode = 69;myWord -> value = "*/";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 23;myWord -> value = "*";return myWord;break;case '/': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“/=”符号{myWord -> categoryCode = 46;myWord -> value = "/=";return myWord;}else if(ch == '/') // 是则说明是“//”注释符号{while(getChar()){if(ch == '\n'){retractChar(); // 回退一个字符break;}}myWord -> categoryCode = 67;myWord -> value = "//";return myWord;}else if(ch == '*') // 是则说明是“/*”注释符号{while(getChar()){if(ch == '*'){getChar();if(ch == '/'){retractChar(); // 回退一个字符retractChar(); // 回退一个字符break;}}}myWord -> categoryCode = 68;myWord -> value = "/*";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 24;myWord -> value = "/";return myWord;break;case '%': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“%=”符号{myWord -> categoryCode = 47;myWord -> value = "%=";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 25;myWord -> value = "%";return myWord;break;case '=': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“==”符号{myWord -> categoryCode = 28;myWord -> value = "==";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 42;myWord -> value = "=";return myWord;break;case '>': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“>=”符号{myWord -> categoryCode = 32;myWord -> value = ">=";return myWord;}else if(ch == '>') // 是则说明是“>>”符号{getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“>>=”符号{myWord -> categoryCode = 48;myWord -> value = ">>=";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 40;myWord -> value = ">>";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 30;myWord -> value = ">";return myWord;break;case '<': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“<=”符号{myWord -> categoryCode = 33;myWord -> value = "<=";return myWord;}else if(ch == '<') // 是则说明是“<<”符号{getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“<<=”符号{myWord -> categoryCode = 49;myWord -> value = "<<=";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 41;myWord -> value = "<<";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 31;myWord -> value = "<";return myWord;break;case '!': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“!=”符号{myWord -> categoryCode = 29;myWord -> value = "!=";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 36;myWord -> value = "!";return myWord;break;case '^': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“^=”符号{myWord -> categoryCode = 52;myWord -> value = "^=";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 39;myWord -> value = "^";return myWord;break;case '&': getChar(); // 再读入一个&字符if(ch == '=') // 是则说明是“&=”符号{myWord -> categoryCode = 50;myWord -> value = "&=";return myWord;}else if(ch == '&') // 是则说明是“&&”符号{myWord -> categoryCode = 34;myWord -> value = "&&";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 37;myWord -> value = "&";return myWord;break;case '|': getChar(); // 再获取一个字符if(ch == '=') // 是则说明是“|=”符号{myWord -> categoryCode = 51;myWord -> value = "|=";return myWord;}else if(ch == '|') // 是则说明是“||”符号{myWord -> categoryCode = 35;myWord -> value = "||";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 38;myWord -> value = "|";return myWord;break;case '.': myWord -> categoryCode = 53;myWord -> value = ".";return myWord;break;case '\\':getChar(); // 再获取一个字符if(ch == '\\') // 是则说明是“\”转义符号{myWord -> categoryCode = 55;myWord -> value = "\\";return myWord;}else if(ch == 'n'){myWord -> categoryCode = 20; // 换行符myWord -> value = "\\n";return myWord;}retractChar(); // 回退一个字符myWord -> categoryCode = 55;myWord -> value = "\\";return myWord;break;case '(': myWord -> categoryCode = 56;myWord -> value = "(";return myWord;break;case ')': myWord -> categoryCode = 57;myWord -> value = ")";return myWord;break;case '[': myWord -> categoryCode = 58;myWord -> value = "[";return myWord;break;case ']': myWord -> categoryCode = 59;myWord -> value = "]";return myWord;break;case '{': myWord -> categoryCode = 60;myWord -> value = "{";return myWord;break;case '}': myWord -> categoryCode = 61;myWord -> value = "}";return myWord;break;case ':': myWord -> categoryCode = 62;myWord -> value = ":";return myWord;break;case ',': myWord -> categoryCode = 63;myWord -> value = ",";return myWord;break;case ';': myWord -> categoryCode = 64;myWord -> value = ";";return myWord;break;case '\'':myWord -> categoryCode = 65;myWord -> value = "\'";return myWord;break;case '"': myWord -> categoryCode = 66;myWord -> value = "\"";return myWord;break;case 10:  myWord -> categoryCode = 20; // 换行符myWord -> value = "\\n";return myWord;break;case '\0':myWord -> categoryCode = 1000; // 此处即到了用户输入的#myWord -> value = "OVER";return myWord;break;default:  myWord -> categoryCode = -1;concatWord(); // 拼接单词changeWordFormation(); // 改变单词输出形式char reportError[] = " does not exist in this lexical system";for(int i = 0; reportError[i] != '\0' ; ++ i){wordBuffer[wordBufferIndex ++] = reportError[i];}wordBuffer[wordBufferIndex] = '\0';myWord -> value = wordBuffer;return myWord;}}
}

单词检索

/*从输入缓冲区读取一个字符到ch中*/
char getChar()
{ch = inputBuffer[inputBufferIndex];++ inputBufferIndex;return ch;
}/*去掉空格和\t*/
void removeBlankSymbol()
{while(ch == ' ' || ch == '\t'){ch = inputBuffer[inputBufferIndex];++ inputBufferIndex;}
}/*拼接单词*/
void concatWord()
{wordBuffer[wordBufferIndex] = ch;++ wordBufferIndex;wordBuffer[wordBufferIndex] = '\0';
}/*判断是否字母*/
int isLetter()
{if(ch >= 'a' && ch <= 'z' || ch >= 'A' && ch <= 'Z' || ch == '_') // 变量名可以有下划线{return 1;}return 0;
}/*判断是否数字*/
int isDigit()
{if(ch >= '0' && ch <= '9'){return 1;}return 0;
}/*检索关键字数组*/
int retriveKeyword()
{int i = 0;while(strcmp(rwtab[i], _KEY_WORD_END)){if(!strcmp(rwtab[i], wordBuffer)) // 相等时strcmp函数返回0，相等于false{return i + 1;}++ i;}return 13;
}/*回退一个字符*/
void retractChar()
{-- inputBufferIndex;
}

特殊词法处理

/*将十进制转换成二进制*/
char* digitToBinary()
{// 在<stdlib.h>头文件中有两个函数int atoi(char *p)和char *itoa(int value, char *string, int radix)；// 前者将装有整数的char数组转化为整数，后者将整数按位数分解依次存入char数组中。itoa(atoi(wordBuffer), wordBuffer, 2);return wordBuffer;
}/*更改单词的输出形式，让自定义变量或无法识别的单词能以'单词名'的形式输出，与关键字作区分*/
char* changeWordFormation()
{for(int i = wordBufferIndex - 1; i >= 0; -- i){wordBuffer[i + 1] = wordBuffer[i];}wordBuffer[0] = '\'';wordBuffer[++ wordBufferIndex] = '\'';wordBuffer[++ wordBufferIndex] = '\0';return wordBuffer;
}

如果文章内容出错或者您有更好的解决方法，欢迎到评论区指正和讨论！