自己编程实现对C语言的词法分析程序，加深对词法分析原理的理解。1、 C语言分为关键字、标识符、数字、运算符、界符五类。自己设置单词符号对应的种别码

好的，下面是一份简单的C语言词法分析程序示例，使用了C++语言编写，并设置了对应的种别码：

#include <iostream>
#include <string>
#include <unordered_map>
#include <regex>

using namespace std;

// 定义单词种别码
enum Token {
    ERROR = -1,
    KEYWORD = 1,
    IDENTIFIER = 2,
    NUMBER = 3,
    OPERATOR = 4,
    DELIMITER = 5
};

// 定义关键字和对应的种别码
const unordered_map<string, int> keywords = {
    {"auto", KEYWORD},
    {"break", KEYWORD},
    {"case", KEYWORD},
    {"char", KEYWORD},
    {"const", KEYWORD},
    {"continue", KEYWORD},
    {"default", KEYWORD},
    {"do", KEYWORD},
    {"double", KEYWORD},
    {"else", KEYWORD},
    {"enum", KEYWORD},
    {"extern", KEYWORD},
    {"float", KEYWORD},
    {"for", KEYWORD},
    {"goto", KEYWORD},
    {"if", KEYWORD},
    {"int", KEYWORD},
    {"long", KEYWORD},
    {"register", KEYWORD},
    {"return", KEYWORD},
    {"short", KEYWORD},
    {"signed", KEYWORD},
    {"sizeof", KEYWORD},
    {"static", KEYWORD},
    {"struct", KEYWORD},
    {"switch", KEYWORD},
    {"typedef", KEYWORD},
    {"union", KEYWORD},
    {"unsigned", KEYWORD},
    {"void", KEYWORD},
    {"volatile", KEYWORD},
    {"while", KEYWORD}
};

// 定义运算符和对应的种别码
const unordered_map<string, int> operators = {
    {"+", OPERATOR},
    {"-", OPERATOR},
    {"*", OPERATOR},
    {"/", OPERATOR},
    {"%", OPERATOR},
    {"++", OPERATOR},
    {"--", OPERATOR},
    {"==", OPERATOR},
    {"!=", OPERATOR},
    {"<", OPERATOR},
    {">", OPERATOR},
    {"<=", OPERATOR},
    {">=", OPERATOR},
    {"&&", OPERATOR},
    {"||", OPERATOR},
    {"!", OPERATOR},
    {"&", OPERATOR},
    {"|", OPERATOR},
    {"^", OPERATOR},
    {"~", OPERATOR},
    {"<<", OPERATOR},
    {">>", OPERATOR},
    {"=", OPERATOR},
    {"+=", OPERATOR},
    {"-=", OPERATOR},
    {"*=", OPERATOR},
    {"/=", OPERATOR},
    {"%=", OPERATOR},
    {"&=", OPERATOR},
    {"|=", OPERATOR},
    {"^=", OPERATOR},
    {"<<=", OPERATOR},
    {">>=", OPERATOR}
};

// 定义界符和对应的种别码
const unordered_map<string, int> delimiters = {
    {"(", DELIMITER},
    {")", DELIMITER},
    {"[", DELIMITER},
    {"]", DELIMITER},
    {"{", DELIMITER},
    {"}", DELIMITER},
    {",", DELIMITER},
    {";", DELIMITER},
    {":", DELIMITER},
    {"?", DELIMITER},
    {"#", DELIMITER},
    {"\\", DELIMITER}
};

// 判断是否为数字
bool isNumber(const string& str) {
    regex reg("\\d+");
    return regex_match(str, reg);
}

// 判断是否为标识符
bool isIdentifier(const string& str) {
    regex reg("[a-zA-Z_]+[a-zA-Z0-9_]*");
    return regex_match(str, reg);
}

// 分析单词
int analyzeToken(const string& word) {
    if (keywords.count(word)) {
        return keywords.at(word);
    } else if (isNumber(word)) {
        return NUMBER;
    } else if (isIdentifier(word)) {
        return IDENTIFIER;
    } else if (operators.count(word)) {
        return operators.at(word);
    } else if (delimiters.count(word)) {
        return delimiters.at(word);
    } else {
        return ERROR;
    }
}

int main() {
    string code = "int main() { int a = 1; int b = 2; int c = a + b; return c; }";
    string word = "";
    int token = 0;
    int index = 0;
    int lineNumber = 1;

    while (index < code.size()) {
        char c = code[index];
        if (c == '\n') {
            lineNumber++;
        } else if (isspace(c)) {
            // 忽略空格、制表符等空白字符
        } else {
            word += c;
            auto nextToken = analyzeToken(word);
            if (nextToken == ERROR) {
                // 如果分析出错，输出错误信息
                cout << "Error: invalid token \"" << word << "\" at line " << lineNumber << endl;
                return 0;
            } else if (nextToken != OPERATOR) {
                // 如果遇到运算符，先输出前面的单词
                if (token != 0) {
                    cout << "Token " << token << ": " << word.substr(0, word.size() - 1) << endl;
                }
                token = nextToken;
                word = "";
            }
        }
        index++;
    }

    // 输出最后一个单词
    if (token != 0) {
        cout << "Token " << token << ": " << word << endl;
    } else {
        auto finalToken = analyzeToken(word);
        cout << "Token " << finalToken << ": " << word << endl;
    }

    return 0;
}

在上面的代码中，我们通过定义三个unordered_map来存储关键字、运算符和界符，并分别设置了对应的种别码。在analyzeToken函数中，我们根据输入的单词判断其种别，并返回对应的种别码。

在主函数中，我们依次读取源代码中的每个字符，并用isNumber和isIdentifier函数判断当前单词是否为数字或标识符。如果是，则直接进行下一个字符的读取；如果不是，则调用analyzeToken函数对其进行分析，并输出对应的种别码和单词内容。

需要注意的是，在遇到运算符时，我们先输出前面的单词，并将当前单词的种别码保存下来，以便后续输出。这是因为运算符可能会包含多个字符，如"++"和">=", 如果不先输出前面的单词，会导致输出结果出错。

最后，我们输出最后一个单词，并结束程序的执行。