在c++中进行不区分大小写字符串比较而不将字符串转换为全大写或全小写的最佳方法是什么?

请指出这些方法是否对unicode友好,以及它们的可移植性如何。


当前回答

我写了一个不区分大小写的char_traits版本,用于std::basic_string,以便在使用内置的std::basic_string成员函数进行比较、搜索等时生成一个不区分大小写的std::string。

换句话说,我想这样做。

std::string a = "Hello, World!";
std::string b = "hello, world!";

assert( a == b );

...这是std::string不能处理的。下面是我的新char_traits的用法:

std::istring a = "Hello, World!";
std::istring b = "hello, world!";

assert( a == b );

...这是它的实现:

/*  ---

        Case-Insensitive char_traits for std::string's

        Use:

            To declare a std::string which preserves case but ignores case in comparisons & search,
            use the following syntax:

                std::basic_string<char, char_traits_nocase<char> > noCaseString;

            A typedef is declared below which simplifies this use for chars:

                typedef std::basic_string<char, char_traits_nocase<char> > istring;

    --- */

    template<class C>
    struct char_traits_nocase : public std::char_traits<C>
    {
        static bool eq( const C& c1, const C& c2 )
        { 
            return ::toupper(c1) == ::toupper(c2); 
        }

        static bool lt( const C& c1, const C& c2 )
        { 
            return ::toupper(c1) < ::toupper(c2);
        }

        static int compare( const C* s1, const C* s2, size_t N )
        {
            return _strnicmp(s1, s2, N);
        }

        static const char* find( const C* s, size_t N, const C& a )
        {
            for( size_t i=0 ; i<N ; ++i )
            {
                if( ::toupper(s[i]) == ::toupper(a) ) 
                    return s+i ;
            }
            return 0 ;
        }

        static bool eq_int_type( const int_type& c1, const int_type& c2 )
        { 
            return ::toupper(c1) == ::toupper(c2) ; 
        }       
    };

    template<>
    struct char_traits_nocase<wchar_t> : public std::char_traits<wchar_t>
    {
        static bool eq( const wchar_t& c1, const wchar_t& c2 )
        { 
            return ::towupper(c1) == ::towupper(c2); 
        }

        static bool lt( const wchar_t& c1, const wchar_t& c2 )
        { 
            return ::towupper(c1) < ::towupper(c2);
        }

        static int compare( const wchar_t* s1, const wchar_t* s2, size_t N )
        {
            return _wcsnicmp(s1, s2, N);
        }

        static const wchar_t* find( const wchar_t* s, size_t N, const wchar_t& a )
        {
            for( size_t i=0 ; i<N ; ++i )
            {
                if( ::towupper(s[i]) == ::towupper(a) ) 
                    return s+i ;
            }
            return 0 ;
        }

        static bool eq_int_type( const int_type& c1, const int_type& c2 )
        { 
            return ::towupper(c1) == ::towupper(c2) ; 
        }       
    };

    typedef std::basic_string<char, char_traits_nocase<char> > istring;
    typedef std::basic_string<wchar_t, char_traits_nocase<wchar_t> > iwstring;

其他回答

bool insensitive_c_compare(char A, char B){
  static char mid_c = ('Z' + 'a') / 2 + 'Z';
  static char up2lo = 'A' - 'a'; /// the offset between upper and lowers

  if ('a' >= A and A >= 'z' or 'A' >= A and 'Z' >= A)
      if ('a' >= B and B >= 'z' or 'A' >= B and 'Z' >= B)
      /// check that the character is infact a letter
      /// (trying to turn a 3 into an E would not be pretty!)
      {
        if (A > mid_c and B > mid_c or A < mid_c and B < mid_c)
        {
          return A == B;
        }
        else
        {
          if (A > mid_c)
            A = A - 'a' + 'A'; 
          if (B > mid_c)/// convert all uppercase letters to a lowercase ones
            B = B - 'a' + 'A';
          /// this could be changed to B = B + up2lo;
          return A == B;
        }
      }
}

这可能会更有效,但这是一个笨重的版本,所有的比特都是空的。

不是所有的便携,但工作得很好,在我的电脑上(不知道,我是图片而不是文字)

支持unicode的Visual c++字符串函数:http://msdn.microsoft.com/en-us/library/cc194799.aspx

您可能正在寻找的是_wcsnicmp

只需使用strcmp()区分大小写,使用strcmpi()或stricmp()进行不区分大小写的比较。它们都在头文件<string.h>

格式:

int strcmp(const char*,const char*);    //for case sensitive
int strcmpi(const char*,const char*);   //for case insensitive

用法:

string a="apple",b="ApPlE",c="ball";
if(strcmpi(a.c_str(),b.c_str())==0)      //(if it is a match it will return 0)
    cout<<a<<" and "<<b<<" are the same"<<"\n";
if(strcmpi(a.c_str(),b.c_str()<0)
    cout<<a[0]<<" comes before ball "<<b[0]<<", so "<<a<<" comes before "<<b;

输出

apple和apple是一样的

A在b之前,所以苹果在球之前

又短又漂亮。没有其他依赖,除了扩展的std C库。

strcasecmp(str1.c_str(), str2.c_str()) == 0

如果str1和str2相等,则返回true。 Strcasecmp可能不存在,可能有类似的stricmp, strcmpi等。

示例代码:

#include <iostream>
#include <string>
#include <string.h> //For strcasecmp(). Also could be found in <mem.h>

using namespace std;

/// Simple wrapper
inline bool str_ignoreCase_cmp(std::string const& s1, std::string const& s2) {
    if(s1.length() != s2.length())
        return false;  // optimization since std::string holds length in variable.
    return strcasecmp(s1.c_str(), s2.c_str()) == 0;
}

/// Function object - comparator
struct StringCaseInsensetiveCompare {
    bool operator()(std::string const& s1, std::string const& s2) {
        if(s1.length() != s2.length())
            return false;  // optimization since std::string holds length in variable.
        return strcasecmp(s1.c_str(), s2.c_str()) == 0;
    }
    bool operator()(const char *s1, const char * s2){ 
        return strcasecmp(s1,s2)==0;
    }
};


/// Convert bool to string
inline char const* bool2str(bool b){ return b?"true":"false"; }

int main()
{
    cout<< bool2str(strcasecmp("asd","AsD")==0) <<endl;
    cout<< bool2str(strcasecmp(string{"aasd"}.c_str(),string{"AasD"}.c_str())==0) <<endl;
    StringCaseInsensetiveCompare cmp;
    cout<< bool2str(cmp("A","a")) <<endl;
    cout<< bool2str(cmp(string{"Aaaa"},string{"aaaA"})) <<endl;
    cout<< bool2str(str_ignoreCase_cmp(string{"Aaaa"},string{"aaaA"})) <<endl;
    return 0;
}

输出:

true
true
true
true
true

boost的问题在于,你必须与boost相关联并依赖于boost。在某些情况下并不容易(例如android)。

使用char_traits意味着所有的比较都是不区分大小写的,这通常不是你想要的。

这就足够了。它应该是相当有效的。它不处理unicode或任何东西。

bool iequals(const string& a, const string& b)
{
    unsigned int sz = a.size();
    if (b.size() != sz)
        return false;
    for (unsigned int i = 0; i < sz; ++i)
        if (tolower(a[i]) != tolower(b[i]))
            return false;
    return true;
}

更新:c++ 14版本(#include <算法>):

bool iequals(const string& a, const string& b)
{
    return std::equal(a.begin(), a.end(),
                      b.begin(), b.end(),
                      [](char a, char b) {
                          return tolower(a) == tolower(b);
                      });
}

c++ 20版本使用std::ranges:

#include <ranges>
#include <algorithm>
#include <string>

bool iequals(const std::string_view& lhs, const std::string_view& rhs) {
    auto to_lower{ std::ranges::views::transform(std::tolower) };
    return std::ranges::equal(lhs | to_lower, rhs | to_lower);
}