词法分析器C语言编译原理实验

#include <iostream> #include <ctype.h> #include <string.h> #include <conio.h> #include <stdlib.h> #include<fstream> using namespace std; #define KEYWORD_LEN 32 //保留字个数 #define STR_MAX_LEN 300 //标识符最大长度 #define PRO_MAX_LEN 20480 //源程序最大长度 #define STB_MAX_LEN 1000 //符号表最大容量 #define CTB_MAX_LEN 1000 //常数表最大容量 #define ERROR 0 //错误 #define ID (KEYWORD_LEN+1) //标识符 #define CONST (KEYWORD_LEN+2) //常量 #define OPERAT (KEYWORD_LEN+3) //运算符 #define DIVIDE (KEYWORD_LEN+4) //界符 char proBuffer[PRO_MAX_LEN] = ""; //存储程序代码的全局缓冲区 char ch; //读出来的当前字符 char word[STR_MAX_LEN]; //标识符 或 常量 int point = 0; //源程序当前位置指针 char signTab[STB_MAX_LEN][STR_MAX_LEN]; //符号表 int pointSTB = 0; //符号表指针 char constTab[CTB_MAX_LEN][STR_MAX_LEN]; //常量表 int pointCTB = 0; //常数表指针 int Line=0; char kwTab[KEYWORD_LEN][10]={ //保留字表 C语言一共有32个保留字[关键字] "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"}; typedef struct Duality { int kind; int value; int order; }*pD, Dua; //函数声明 bool Getchar(); //获得一个字符不包括结束标记 bool GetBC(); //获得一个非空白字符 void Concat(char *str); //将ch连接到str后 int Reserve(char *str); //对str字符串查找保留字表 若是一个保留字-返回其编码 否则返回0 void Retract(); //将搜索指示器回调一个字符位置 int InsertId(char *str);//将str串以标识符插入符号表，并返回符号表指针 int InsertConst(char *str); //将str串以常数插入符号表，并返回常数表指针 bool wordAnalyse(pD pDu); //词法分析 true正常 bool Getchar()//获得一个字符 { if(point < PRO_MAX_LEN && proBuffer[point] != '\0')//如果当前下标合法且当前字符为结束标记则取字符增游标 { ch = proBuffer[point++]; if (ch == '\n') Line ++; return true; } ch = '\0'; return false; } //获得一个非空白字符 bool GetBC() { do { if(!Getchar()) //获取字符失败 { ch = '\0'; return false; } }while(isspace(ch)); //直到获得一个非空白字符 return true; } //将ch连接到str后 void Concat(char *str) { int i; for(i=0; str[i]; ++i); str[i] = ch; str[i+1] = '\0'; } //对str字符串查找保留字表 若是一个保留字-返回其编码 否则返回0 int Reserve(char *str) { int i; for(i=0; i<KEYWORD_LEN; ++i) //从保留字表中查找str串 { if(0 == strcmp(kwTab[i], str)) return i+1; //注意，这里加一原因是0值被错误标记占用 } return 0; } //将搜索指示器回调一个字符位置 void Retract()///char *ch { if(proBuffer[point] == '\n' && Line > 0) Line --; point --; } //将str串以标识符插入符号表，并返回符号表指针 int InsertId(char *str) { int i; for(i=0; i < pointSTB; ++i) if(0 == strcmp(signTab[i], str)) return i; strcpy(signTab[pointSTB++], str); return (pointSTB-1); } //将str串以常数插入常量表，并返回常数表指针 /*int InsertConst(char *str) { int i; for(i=0; i < pointCTB; ++i) if(0 == strcmp(constTab[i], str)) return i; strcpy(constTab[pointCTB++], str); return (pointCTB-1); }*/ //词法分析 false--分析结束 bool wordAnalyse(pD pDu) { int code, value; char judge; //这里有个技巧 借用此变量巧妙的运用SWITCH结构 int i = 0; //辅助 GetBC(); judge = ch; if (isalpha(ch) || ch == '_') judge='L'; if (isdigit(ch)) judge='D'; switch(judge) { case 'L': while(isalnum(ch) || ch == '_') { //标识符 word[i++] = ch; Getchar(); } word[i] = '\0'; Retract(); //回退一个字符 code = Reserve(word); if(code == 0) { value = InsertId(word); pDu->kind = ID; pDu->value = value; } else { pDu->kind = code; pDu->value = -1; } return true; case 'D': while(isdigit(ch)) { word[i++] = ch; Getchar(); } word[i] = '\0'; Retract(); // value = InsertConst(word); pDu->kind = CONST; // pDu->value= value; return true; case '"': //字符串常量 do { word[i++] = ch; Getchar(); }while(ch != '"' && ch != '\0'); word[i++] = ch; word[i] = '\0'; if(ch == '\0') { // cout<<word; pDu->kind = ERROR; pDu->value = 0; } else { // value = InsertConst(word); pDu->kind = CONST; // pDu->value = value; } return true; //字符常量 case '\'': word[i++] = ch; // ' Getchar(); word[i++] = ch; if(ch == '\\') // '\n' {//如果是转义字符则要多接收一个字符 Getchar(); // ch = ' word[i++] = ch; } Getchar(); word[i++] = ch; word[i] = '\0'; if(ch != '\'') {//'\b' cout<<word; // ProcError(2); pDu->kind = ERROR; pDu->value = 0; } else { // value = InsertConst(word); pDu->kind = CONST; // pDu->value = value; } return true; case '(': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=1; return true; case ')': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=2; return true; case '[': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=3; return true; case ']': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=4; return true; case '.': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=5; return true; case ',': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=6; return true; case '~': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=7; return true; case '?': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=8; return true; case ':': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=9; return true; case ';': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=10; return true; case '{': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=11; return true; case '}': word[i++] = ch; word[i] = '\0'; pDu->kind = DIVIDE; //界符 pDu->value = -1; pDu->order=12; ret