在进行 url 编码时，std::regex_replace 对于字符“+”不能正常工作

Posted 2023-02-21

【中文标题】在进行 url 编码时，std::regex_replace 对于字符“+”不能正常工作

【英文标题】：While doing url encoding, the std::regex_replace doesn't work properly for character "+"

【发布时间】：2018-05-16 06:46:11

【问题描述】：

下面是sn-p代码，regex_replace不能正常处理字符“+”，我不应该对字符使用特殊处理，但它应该可以正常工作。

/*All headerfiles are available.*/



std::string charToHex(unsigned char c, bool bUpperCase);
std::string urlEncode(const std::string& toEncode, bool bEncodeForwardSlash);
std::string getEncodedUrl(const std::string& url)
std::string bktObjKey = "";

std::string urlEnc = url;

boost::regex expression("^(([^:/?#]+):)?(//([^/?#:]*)(:\\d+)?)?([^?#]*)((\\?[^#]*))?(#(.*))?");

std::string::const_iterator start=url.begin(), end = url.end();
boost::match_results<std::string::const_iterator> what;
boost::match_flag_type flags = boost::match_default;
if (regex_search(url.begin(), url.end(), what, expression, flags)) 
  std::cout<<"Matched"<<std::endl;
  bktObjKey.insert(bktObjKey.begin(), what[6].first, what[6].second);

  std::regex fobj(bktObjKey);
  /*std::string fobj = bktObjKey;*/

  /*auto pos = url.find(bktObjKey);*/
  bktObjKey = urlEncode(bktObjKey, false);
  std::cout<<"bktObjKey :"<<bktObjKey.c_str()<<" urlEnc: "<<urlEnc.c_str()<<std::endl;

  urlEnc = std::regex_replace(url, fobj, bktObjKey);
  std::cout<<" urlEnc: "<<urlEnc.c_str()<<std::endl;

  return urlEnc;

std::string urlEncode(const std::string& toEncode, bool bEncodeForwardSlash)  
  std::ostringstream out;

  std::cout<<"inside encode"<<std::endl;
  for(std::string::size_type i=0; i < toEncode.length(); ++i) 
    char ch = toEncode.at(i);
    if ((ch >= 'A' && ch <= 'Z') ||
        (ch >= 'a' && ch <= 'z') ||
        (ch >= '0' && ch <= '9') ||
        (ch == '_' || ch == '-' || ch == '~' || ch == '.') ||
        (ch == '/' && !bEncodeForwardSlash)) 
      out << ch;
      std::cout<<out.str()<<" Is not coded to HEX"<<std::endl;
    
    else 
      out << "%" <<  charToHex(ch, true);
      std::cout<<out.str()<<" Is coded to HEX"<<std::endl;
    
  
  std::cout<<"Return :"<<out.str()<<std::endl;
  return out.str();


std::string charToHex(unsigned char c, bool bUpperCase) 
  short i = c;
  std::stringstream s;
  s << std::setw(2) << std::setfill('0') << std::hex << i;
  return s.str();


int main() 

std::string url1 ="http://10.130.0.36/rbkt10/+";
std::string out1 = getEncodedUrl(url1);
std::cout<<"Encoded URL1=:"<<out1<<std::endl;

return 0;

输出： 编码 URL1=:http://10.130.0.36/rbkt10/%2b+

所以输出变成“++”。它应该只有“+”。我怎样才能让它完美地工作？

【问题讨论】：

代码是供人阅读的。格式化很重要

【参考方案1】：

您将原始字符串解释为正则表达式。 + 在正则表达式中是特殊的¹。

您应该简单地使用std::string::replace，因为您不需要正则表达式替换功能：

boost::smatch what;
if (regex_search(url.cbegin(), url.cend(), what, expression)) 
    boost::ssub_match query = what[6];
    url.replace(query.first, query.second, urlEncode(query.str(), false));

像这样复杂、分散的代码： 可能只是：

std::string bktObjKey = what[6].str();

复杂的循环

for (std::string::size_type i = 0; i < toEncode.length(); ++i) 
     char ch = toEncode.at(i);

可能是

for (char ch : toEncode) 

charToHex 每次都会创建一个新的 2 字符字符串，每次都使用另一个字符串流，将结果从字符串流中复制出来等。相反，只需写入您拥有的字符串流并避免所有低效率：

void writeHex(std::ostream& os, unsigned char c, bool uppercase) 
    os << std::setfill('0') << std::hex;
    if (uppercase) 
        os << std::uppercase;
    os << std::setw(2) << static_cast<int>(c);

请注意，这也解决了您忘记使用 bUppercase 的事实

查看<cctype> 以获得对字符进行分类的帮助。

使用原始文字书写

boost::regex expression("^(([^:/?#]+):)?(//([^/?#:]*)(:\\d+)?)?([^?#]*)((\\?[^#]*))?(#(.*))?");

改为：

boost::regex expression(R"(^(([^:/?#]+):)?(//([^/?#:]*)(:\d+)?)?([^?#]*)((\?[^#]*))?(#(.*))?)");

（无需双重转义\d 和\?）

要么删除所有多余的子组

boost::regex expression(R"(^([^:/?#]+:)?(//[^/?#:]*(:\d+)?)?[^?#]*(\?[^#]*)?(#.*)?)");

或者使它们可维护和有用²：

boost::regex uri_regex(
    R"(^((?<scheme>[^:/?#]+):)?)"
    R"((?<authority>//(\?<host>[^/?#:]*)(:(?<port>\d+))?)?)"
    R"((?<path>[^?#]*))"
    R"((\?(?<query>([^#]*)))?)"
    R"((#(?<fragment>.*))?)");

现在您可以访问 URI 的逻辑组件，应用它以更好地了解何时何地进行编码：

    std::string escaped = 
       what["scheme"].str() + 
       what["authority"].str() +
       urlEncode(what["path"].str(), false);

    if (query.matched) 
        escaped += '?';
        escaped.append(urlEncode(query, true));
    

    if (fragment.matched) 
        escaped += '#';
        escaped.append(urlEncode(fragment, true));
    

重载 urlEncode，它采用现有的 ostream 引用，而不是始终创建自己的引用：

std::ostringstream out;
out << what["scheme"] << what["authority"];
urlEncode(out, what["path"], false);

if (query.matched)
    urlEncode(out << '?', query, true);

if (fragment.matched)
    urlEncode(out << '#', fragment, true);

审查后的代码

Live On Coliru

#include <boost/regex.hpp>
#include <iostream>
#include <iomanip>

void writeHex(std::ostream& os, unsigned char c, bool uppercase) 
    os << std::setfill('0') << std::hex;
    if (uppercase) 
        os << std::uppercase;
    os << '%' << std::setw(2) << static_cast<int>(c);


void urlEncode(std::ostream& os, const std::string &toEncode, bool bEncodeForwardSlash) 
    auto is_safe = [=](uint8_t ch) 
        return std::isalnum(ch) ||
            (ch == '/' && !bEncodeForwardSlash) ||
            std::strchr("_-~.", ch);
    ;

    for (char ch : toEncode) 
        if (is_safe(ch))
            os << ch;
        else
            writeHex(os, ch, true);
    


std::string urlEncode(const std::string &toEncode, bool bEncodeForwardSlash) 
    std::ostringstream out;
    urlEncode(out, toEncode, bEncodeForwardSlash);
    return out.str();


std::string getEncodedUrl(std::string url) 

    boost::regex uri_regex(
        R"(^((?<scheme>[^:/?#]+):)?)"
        R"((?<authority>//(\?<host>[^/?#:]*)(:(?<port>\d+))?)?)"
        R"((?<path>[^?#]*))"
        R"((\?(?<query>([^#]*)))?)"
        R"((#(?<fragment>.*))?)");

    boost::match_results<std::string::iterator> what;
    //boost::smatch what;
    if (regex_search(url.begin(), url.end(), what, uri_regex)) 
        auto& full     = what[0];
        auto& query    = what["query"];
        auto& fragment = what["fragment"];

        std::ostringstream out;
        out << what["scheme"] << what["authority"];
        urlEncode(out, what["path"], false);

        if (query.matched)
            urlEncode(out << '?', query, true);

        if (fragment.matched)
            urlEncode(out << '#', fragment, true);

        url.replace(full.begin(), full.end(), out.str());
    
    return url;


int main() 
    for (std::string url :  
            "http://10.130.0.36/rbkt10/+",
            "//10.130.0.36/rbkt10/+",
            "//localhost:443/rbkt10/+",
            "https:/rbkt10/+",
            "https:/rbkt10/+?in_params='please do escape / (forward slash)'&more#also=in/fragment",
            "match inside text http://10.130.0.36/rbkt10/+ is a bit fuzzy",
          ) 
        std::cout << "Encoded URL: " << getEncodedUrl(url) << std::endl;
    

打印

Encoded URL: http//10.130.0.36/rbkt10/%2B
Encoded URL: //10.130.0.36/rbkt10/%2B
Encoded URL: //localhost%3A443/rbkt10/%2B
Encoded URL: https/rbkt10/%2B
Encoded URL: https/rbkt10/%2B?in_params%3D%27please%20do%20escape%20%2F%20%28forward%20slash%29%27%26more#also%3Din%2Ffragment
Encoded URL: match inside text http//10.130.0.36/rbkt10/%2B%20is%20a%20bit%20fuzzy

注意

请注意，代码仍然不符合规范：

这就是您使用库的原因。

---

¹（这会导致输入中留下 +。它不是“重复”的，只是没有被替换，因为 /+ 表示 1 个或多个 /）。

² 见https://en.wikipedia.org/wiki/Uniform_Resource_Identifier#Generic_syntax