c++ - 如何根据空格标记特殊字符（< >

问题描述

我发现了一个几年前完成的项目，在这里找到了一些简单的命令行解析。虽然我真的很喜欢它的功能，但它不支持解析特殊字符，例如 <、>、& 等。我继续尝试通过添加一些与现有代码相同的条件来添加一些功能来专门解析这些字符用于查找空格、转义字符和引号：

bool _isQuote(char c) {
    if (c == '\"')
            return true;
    else if (c == '\'')
            return true;

    return false;
}

bool _isEscape(char c) {
    if (c == '\\')
        return true;

    return false;
}

bool _isWhitespace(char c) {
    if (c == ' ')
        return true;
    else if(c == '\t')
        return true;

    return false;
}
.
.
.

我添加的内容：

bool _isLeftCarrot(char c) {
    if (c == '<')
        return true;

    return false;
}

bool _isRightCarrot(char c) {
    if (c == '>')
        return true;

    return false;
}

其余的特殊字符依此类推。

我还尝试了与方法中现有代码相同的parse方法：

std::list<string> parse(const std::string& args) {

    std::stringstream ain(args);            // iterates over the input string
    ain >> std::noskipws;                   // ensures not to skip whitespace
    std::list<std::string> oargs;           // list of strings where we will store the tokens

    std::stringstream currentArg("");
    currentArg >> std::noskipws;

    // current state
    enum State {
            InArg,          // scanning the string currently
            InArgQuote,     // scanning the string that started with a quote currently 
            OutOfArg        // not scanning the string currently
    };
    State currentState = OutOfArg;

    char currentQuoteChar = '\0';   // used to differentiate between ' and "
                                    // ex. "sample'text" 

    char c;
    std::stringstream ss;
    std::string s;
    // iterate character by character through input string
    while(!ain.eof() && (ain >> c)) {

            // if current character is a quote
            if(_isQuote(c)) {
                    switch(currentState) {
                            case OutOfArg:
                                    currentArg.str(std::string());
                            case InArg:
                                    currentState = InArgQuote;
                                    currentQuoteChar = c;
                                    break;
                            case InArgQuote:
                                    if (c == currentQuoteChar)
                                            currentState = InArg;
                                    else
                                            currentArg << c;
                                    break;
                    }
            }
            // if current character is whitespace
            else if (_isWhitespace(c)) {
                        switch(currentState) {
                            case InArg:
                                    oargs.push_back(currentArg.str());
                                    currentState = OutOfArg;
                                    break;
                            case InArgQuote:
                                    currentArg << c;
                                    break;
                            case OutOfArg:
                                    // nothing
                                    break;
                    }
            }
            // if current character is escape character
            else if (_isEscape(c)) {
                    switch(currentState) {
                            case OutOfArg:
                                    currentArg.str(std::string());
                                    currentState = InArg;
                            case InArg:
                            case InArgQuote:
                                    if (ain.eof())
                                    {
                                            currentArg << c;
                                            throw(std::runtime_error("Found Escape Character at end of file."));
                                    }
                                    else {
                                            char c1 = c;
                                            ain >> c;
                                            if (c != '\"')
                                                    currentArg << c1;
                                            ain.unget();
                                            ain >> c;
                                            currentArg << c;
                                    }
                                    break;
                    }
            }

我在parse方法中添加的内容：

            // if current character is left carrot (<)
            else if(_isLeftCarrot(c)) {
                    // convert from char to string and push onto list
                    ss << c;
                    ss >> s;
                    oargs.push_back(s);
            }
            // if current character is right carrot (>)
            else if(_isRightCarrot(c)) {
                    ss << c;
                    ss >> s;
                    oargs.push_back(s);
            }
.
.
.
            else {
                    switch(currentState) {
                            case InArg:
                            case InArgQuote:
                                    currentArg << c;
                                    break;
                            case OutOfArg:
                                    currentArg.str(std::string());
                                    currentArg << c;
                                    currentState = InArg;
                                    break;
                    }
            }
    }

    if (currentState == InArg) {
            oargs.push_back(currentArg.str());
            s.clear();
    }
    else if (currentState == InArgQuote)
            throw(std::runtime_error("Starting quote has no ending quote."));

    return oargs;
}

parse将返回令牌字符串列表。

但是，当特殊字符附加到输入的末尾时，我遇到了特定测试用例的问题。例如，输入

foo-bar&

将返回此列表：[{&},{foo-bar}]而不是我想要的：[{foo-bar},{&}]

我正在努力解决这个问题。我是 C++ 新手，所以任何建议以及一些解释都会有很大帮助。

标签： c++parsingtokenize

c++ - 如何根据空格标记特殊字符（< > | & 等）

问题描述

解决方案

推荐阅读