Question

我想编写一个解析特殊格式字符串语法的regularre表达式。它应该帮助我检测格式错误，并将格式字符串拆分为要处理的单独部分。

但是，尽管我努力尝试，但我无法按预期进行分裂。

根据我在文档中所读到的内容，＆＃39;（?:）＆＃39;语法应该定义一个非分裂组，而正常的括号表达式＆＃39;（）＆＃39;应该定义一个单独返回的子匹配。但它没有。

这是我的代码：

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

std::string parseCode( std::regex_constants::error_type etype);

int main()
{
   const std::string  regex_str( "(?:([^\\[]+)(\\[[^\\]]*\\])( +|\\n))");
   std::regex  atr;

   std::cout << "regex string = '" << regex_str << "'" << std::endl;

   try
   {
      atr.assign( regex_str);
   } catch (const std::regex_error& e)
   {
      std::cerr << "Error: " << e.what() << "; code: " << parseCode(e.code()) << std::endl;
      exit( EXIT_FAILURE);
   } // end try

   {
      const std::string  title( "First Title[]  Second Title[]   -Third Title[]");
      auto  regex_begin = std::sregex_iterator( title.begin(), title.end(), atr);

      for (std::sregex_iterator i = regex_begin; i != std::sregex_iterator(); ++i)
      {
         std::smatch  match = *i;
         std::cout << "got: '" << match.str() << "'" << std::endl;
      } // end for

      auto  subregex_begin = std::sregex_token_iterator( title.begin(),
         title.end(), atr, -1);

      for (std::sregex_token_iterator i = subregex_begin; i != std::sregex_token_iterator(); ++i)
      {
         std::cout << "got sub: '" << *i << "'" << std::endl;
      } // end for
   } // end scope

}

std::string parseCode( std::regex_constants::error_type etype)
{

   switch (etype)
   {
   case std::regex_constants::error_collate:
       return "error_collate: invalid collating element request";
   case std::regex_constants::error_ctype:
       return "error_ctype: invalid character class";
   case std::regex_constants::error_escape:
       return "error_escape: invalid escape character or trailing escape";
   case std::regex_constants::error_backref:
       return "error_backref: invalid back reference";
   case std::regex_constants::error_brack:
       return "error_brack: mismatched bracket([ or ])";
   case std::regex_constants::error_paren:
       return "error_paren: mismatched parentheses(( or ))";
   case std::regex_constants::error_brace:
       return "error_brace: mismatched brace({ or })";
   case std::regex_constants::error_badbrace:
       return "error_badbrace: invalid range inside a { }";
   case std::regex_constants::error_range:
       return "erro_range: invalid character range(e.g., [z-a])";
   case std::regex_constants::error_space:
       return "error_space: insufficient memory to handle this regular expression";
   case std::regex_constants::error_badrepeat:
       return "error_badrepeat: a repetition character (*, ?, +, or {) was not preceded by a valid regular expression";
   case std::regex_constants::error_complexity:
       return "error_complexity: the requested match is too complex";
   case std::regex_constants::error_stack:
       return "error_stack: insufficient memory to evaluate a match";
   default:
       return "";
   }
}

这是输出：

regex string = '(?:([^\[]+)(\[[^\]]*\])( +))'
got: 'First Title[]  '
got: 'Second Title[]   '
got sub: ''
got sub: ''
got sub: '-Third Title[]'

这就是我想要/期望的：

regex string = '(?:([^\[]+)(\[[^\]]*\])( +))'
got: 'First Title[]  '
got: 'Second Title[]   '
got: '-Third Title[]'
got sub: 'First  Title'
got sub: '[]'
got sub: '  '
got sub: 'Second  Title'
got sub: '[]'
got sub: '  '
got sub: '-Third Title'
got sub: '[]'

我在RHEL 7.2上使用g ++ 5.3.1 在IdeOne.com上使用g ++ 6.3获得了相同的结果：https://ideone.com/dj4Mqf

我做错了什么？

Answer 1

1）你的正则表达式与最后一部分不匹配，将其改为：

  const std::string  regex_str("([^\\[]+)(\\[[^\\]]*\\])(\\s+|\\n|$)");

2）match.str()返回整个匹配的字符串，以提取匹配的组，使用operator[]：

  std::smatch  match = *i;
  std::cout << "got: 1='" << match[1] << "' 2='" << match[2] << "' 3='" << match[3] << "'" << std::endl;

输出：

regex string = '([^\[]+)(\[[^\]]*\])(\s+|\n|$)'
got: 1='First Title' 2='[]' 3='  '
got: 1='Second Title' 2='[]' 3='   '
got: 1='-Third Title' 2='[]' 3=''

C ++ 11正则表达式不会按预期返回组

1 个答案: