编译原理——扫描器设计与实现

改进了一下，加入了能够输出错误提示（注意：我们是用char接收的，但是遇到中文的时候因为码值的原因，一个中文字占三个char所以按照我们判断流程会输出三个错误提示，你们要是见意的话可以自行修改）

非常详细（包括跳过注释部分），不多说直接上代码（结合代码讲解）

#include<bits/stdc++.h>using namespace std;#define ARRAY_LENGTH(arr) (sizeof(arr) / sizeof(arr[0]))//关键词集合
string KEY_WORD[] = {"int","char","string","bool","float","double","true","false","return","if","else","while","for","default","do","public","static","switch","case","private","protected"};
//界符集合,我将'/'也加到界符表中用于判断是否是注释
char BOUND_CHAR[] = {',', ';', '(', ')', '{', '}', '[', ']', '\'', '\"', '/'};
int pos = 0;//当前读到的数的下标
short in_annotation = 0;//当前是否在注释的范围，1表示在并且是"//"这种类型，2表示在并且是"/**/"这种注释类型，默认不在（因为两种注释的退出条件不同）// 关键字,标识符,运算符,界符和常量
enum WordTypeKind{KEYWORD, IDENTIFIER, CONSTANT, OPERATOR, DELIMITER, ANNOTATION, ERROR, STOP
};//定义词
struct WORD {WordTypeKind wordType;string value;
};//读取文件中的内容
string openFile(string fileName) {ifstream readFile(fileName);//文件是否打开if(!readFile.is_open()) {cerr << "无法打开文件！" << '\n';return "";}string content, temp;while(getline(readFile, temp)) {// cout << content << endl;content += temp;content += '\n';}//关闭资源readFile.close();return content;
}//将字符串写入文件
bool writeFile(string fileName, string content) {ofstream writeFile(fileName);if(!writeFile.is_open()) {cerr << "无法打开文件！" << '\n';return false;}writeFile << content << endl;writeFile.close();return true;
}//判断一个单词是不是关键字，是返回true
bool isKeyWord(string word) {for(int i = 0; i < ARRAY_LENGTH(KEY_WORD); i++) {if(word == KEY_WORD[i]) return true;}return false;
}//分词器，将字符串分成最小单位（关键字,标识符,运算符,界符和常量），关键字我们可以自己根据使用的高级语句自定义
WORD getNextWord(string str) {string tempStr = "";//暂存这个单词WORD newWord;//返回的词newWord.wordType = STOP;//方便后续退出循环while (pos < str.length() && std::isspace(str[pos])) {if(in_annotation == 1 && str[pos] == '\n') in_annotation = 0;//退出注释状态++pos; // 跳过空白字符}if (pos >= str.length()) {return newWord; // 结束}if(pos < str.length()) {//不越界char c = str[pos++];tempStr += c;//标识符的命名规范：只能以字母或'_'开头if(isalpha(c) || c == '_') {//这个词是关键词或标识符// isalnum(str[pos])这个函数用来检查传递给它的字符是否是字母（isalpha）或者是数字（isdigit）while(pos < str.length() && (isalnum(str[pos]) || str[pos] == '_')) {tempStr += str[pos++];}//判断这个单词是标识符or关键字if(isKeyWord(tempStr)) {//是关键字newWord.wordType = KEYWORD;} else {//标识符newWord.wordType = IDENTIFIER;}} else if(isdigit(c)) {//数字开头只可能是常数，我们把所有数字读完while(pos < str.length() && isdigit(str[pos])) {tempStr += str[pos++];}newWord.wordType = CONSTANT;} else if(c >= 0 && c <= 127) {//只可能是运算符或界符for(int i = 0; i < ARRAY_LENGTH(BOUND_CHAR); i++) {//是不是界符if(c == BOUND_CHAR[i]) {//遇到'/'判断是不是注释和注释类型if(c == '/' && pos < str.length() && str[pos] == '/') {//是'//'类型in_annotation = 1; newWord.wordType = ANNOTATION;tempStr += str[pos++];newWord.value = tempStr;return newWord;} else if(c == '/' && pos < str.length() && str[pos] == '*') {//是'/**/'类型in_annotation = 2;newWord.wordType = ANNOTATION;tempStr += str[pos++];newWord.value = tempStr;return newWord;}newWord.wordType = DELIMITER;break;}}//是运算符,注意双目运算符（三目运算符我们就不考虑了）if(pos < str.length()) {//注意不要越界newWord.wordType = OPERATOR;char nextChar = str[pos];//特判一下'*/'的情况，因为这是第二种注释的退出标识if(c == '*' && nextChar == '/') {//退出注释状态，下面也不用看了in_annotation = 0;tempStr += nextChar;newWord.wordType = ANNOTATION;pos++;newWord.value = tempStr;return newWord;}//考虑一下所有的双目运算符if((c == '+' || c == '-' || c == '*' || c == '/' || c == '!' || c == '^' || c == '%' || c == '=' || c == '<' || c == '>') && nextChar == '=') {tempStr += nextChar;//更新一下nextCharpos++;}if(c == '+' && nextChar == '+') {tempStr += nextChar;//更新一下nextCharpos++;}if(c == '-' && nextChar == '-') {tempStr += nextChar;//更新一下nextCharpos++;}if(c == '&' && nextChar == '&') {tempStr += nextChar;//更新一下nextCharpos++;}if(c == '|' && nextChar == '|') {tempStr += nextChar;//更新一下nextCharpos++;}if(c == '<' && nextChar == '<') {tempStr += nextChar;//更新一下nextCharpos++;}if(c == '>' && nextChar == '>') {tempStr += nextChar;//更新一下nextCharpos++;}}} else {newWord.wordType = ERROR;}newWord.value = tempStr;}return newWord;
}//换行符占一个长度！！！int main() {//先读取txt文件string fileName = "E:\\program\\bianyiyuanli\\1.txt";string str = openFile(fileName);WORD word;while((word = getNextWord(str)).wordType != STOP) {if(word.wordType == ERROR && in_annotation == 0) cout << "出现ERROR!!!" << '\n';else if(word.wordType != ANNOTATION && in_annotation == 0) {//我们只有在词语不是注释类型和不在注释状态才输出它std::cout << "[" << word.wordType << ",   " << word.value << "]" << std::endl;}}return 1;
}