Java有一个方便的分割方法:
String str = "The quick brown fox";
String[] results = str.split(" ");
在c++中有简单的方法来做到这一点吗?
Java有一个方便的分割方法:
String str = "The quick brown fox";
String[] results = str.split(" ");
在c++中有简单的方法来做到这一点吗?
当前回答
在我看来很奇怪的是,SO网站上有这么多注重速度的书呆子,却没有人给出一个使用编译时生成的分隔符查找表的版本(下面是示例实现)。使用查找表和迭代器应该在效率上击败std::regex,如果你不需要击败regex,就使用它,它是c++ 11的标准,超级灵活。
有些人已经建议使用正则表达式,但对于新手来说,这里有一个打包的示例,应该完全符合OP的期望:
std::vector<std::string> split(std::string::const_iterator it, std::string::const_iterator end, std::regex e = std::regex{"\\w+"}){
std::smatch m{};
std::vector<std::string> ret{};
while (std::regex_search (it,end,m,e)) {
ret.emplace_back(m.str());
std::advance(it, m.position() + m.length()); //next start position = match position + match length
}
return ret;
}
std::vector<std::string> split(const std::string &s, std::regex e = std::regex{"\\w+"}){ //comfort version calls flexible version
return split(s.cbegin(), s.cend(), std::move(e));
}
int main ()
{
std::string str {"Some people, excluding those present, have been compile time constants - since puberty."};
auto v = split(str);
for(const auto&s:v){
std::cout << s << std::endl;
}
std::cout << "crazy version:" << std::endl;
v = split(str, std::regex{"[^e]+"}); //using e as delim shows flexibility
for(const auto&s:v){
std::cout << s << std::endl;
}
return 0;
}
如果我们需要更快并接受所有字符必须为8位的约束,我们可以在编译时使用元编程创建一个查找表:
template<bool...> struct BoolSequence{}; //just here to hold bools
template<char...> struct CharSequence{}; //just here to hold chars
template<typename T, char C> struct Contains; //generic
template<char First, char... Cs, char Match> //not first specialization
struct Contains<CharSequence<First, Cs...>,Match> :
Contains<CharSequence<Cs...>, Match>{}; //strip first and increase index
template<char First, char... Cs> //is first specialization
struct Contains<CharSequence<First, Cs...>,First>: std::true_type {};
template<char Match> //not found specialization
struct Contains<CharSequence<>,Match>: std::false_type{};
template<int I, typename T, typename U>
struct MakeSequence; //generic
template<int I, bool... Bs, typename U>
struct MakeSequence<I,BoolSequence<Bs...>, U>: //not last
MakeSequence<I-1, BoolSequence<Contains<U,I-1>::value,Bs...>, U>{};
template<bool... Bs, typename U>
struct MakeSequence<0,BoolSequence<Bs...>,U>{ //last
using Type = BoolSequence<Bs...>;
};
template<typename T> struct BoolASCIITable;
template<bool... Bs> struct BoolASCIITable<BoolSequence<Bs...>>{
/* could be made constexpr but not yet supported by MSVC */
static bool isDelim(const char c){
static const bool table[256] = {Bs...};
return table[static_cast<int>(c)];
}
};
using Delims = CharSequence<'.',',',' ',':','\n'>; //list your custom delimiters here
using Table = BoolASCIITable<typename MakeSequence<256,BoolSequence<>,Delims>::Type>;
有了这些,创建getNextToken函数就很容易了:
template<typename T_It>
std::pair<T_It,T_It> getNextToken(T_It begin,T_It end){
begin = std::find_if(begin,end,std::not1(Table{})); //find first non delim or end
auto second = std::find_if(begin,end,Table{}); //find first delim or end
return std::make_pair(begin,second);
}
使用它也很简单:
int main() {
std::string s{"Some people, excluding those present, have been compile time constants - since puberty."};
auto it = std::begin(s);
auto end = std::end(s);
while(it != std::end(s)){
auto token = getNextToken(it,end);
std::cout << std::string(token.first,token.second) << std::endl;
it = token.second;
}
return 0;
}
这里有一个生动的例子:http://ideone.com/GKtkLQ
其他回答
下面是一个示例标记器类,它可以实现您想要的功能
//Header file
class Tokenizer
{
public:
static const std::string DELIMITERS;
Tokenizer(const std::string& str);
Tokenizer(const std::string& str, const std::string& delimiters);
bool NextToken();
bool NextToken(const std::string& delimiters);
const std::string GetToken() const;
void Reset();
protected:
size_t m_offset;
const std::string m_string;
std::string m_token;
std::string m_delimiters;
};
//CPP file
const std::string Tokenizer::DELIMITERS(" \t\n\r");
Tokenizer::Tokenizer(const std::string& s) :
m_string(s),
m_offset(0),
m_delimiters(DELIMITERS) {}
Tokenizer::Tokenizer(const std::string& s, const std::string& delimiters) :
m_string(s),
m_offset(0),
m_delimiters(delimiters) {}
bool Tokenizer::NextToken()
{
return NextToken(m_delimiters);
}
bool Tokenizer::NextToken(const std::string& delimiters)
{
size_t i = m_string.find_first_not_of(delimiters, m_offset);
if (std::string::npos == i)
{
m_offset = m_string.length();
return false;
}
size_t j = m_string.find_first_of(delimiters, i);
if (std::string::npos == j)
{
m_token = m_string.substr(i);
m_offset = m_string.length();
return true;
}
m_token = m_string.substr(i, j - i);
m_offset = j;
return true;
}
例子:
std::vector <std::string> v;
Tokenizer s("split this string", " ");
while (s.NextToken())
{
v.push_back(s.GetToken());
}
我以前只用标准库做了一个lexer/tokenizer。代码如下:
#include <iostream>
#include <string>
#include <vector>
#include <sstream>
using namespace std;
string seps(string& s) {
if (!s.size()) return "";
stringstream ss;
ss << s[0];
for (int i = 1; i < s.size(); i++) {
ss << '|' << s[i];
}
return ss.str();
}
void Tokenize(string& str, vector<string>& tokens, const string& delimiters = " ")
{
seps(str);
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
int main(int argc, char *argv[])
{
vector<string> t;
string s = "Tokens for everyone!";
Tokenize(s, t, "|");
for (auto c : t)
cout << c << endl;
system("pause");
return 0;
}
使用regex_token_iterators的解决方案:
#include <iostream>
#include <regex>
#include <string>
using namespace std;
int main()
{
string str("The quick brown fox");
regex reg("\\s+");
sregex_token_iterator iter(str.begin(), str.end(), reg, -1);
sregex_token_iterator end;
vector<string> vec(iter, end);
for (auto a : vec)
{
cout << a << endl;
}
}
If the maximum length of the input string to be tokenized is known, one can exploit this and implement a very fast version. I am sketching the basic idea below, which was inspired by both strtok() and the "suffix array"-data structure described Jon Bentley's "Programming Perls" 2nd edition, chapter 15. The C++ class in this case only gives some organization and convenience of use. The implementation shown can be easily extended for removing leading and trailing whitespace characters in the tokens.
基本上,可以将分隔符替换为以字符串结束的'\0'字符,并设置指向修改后字符串中的标记的指针。在极端情况下,当字符串仅由分隔符组成时,将得到字符串长度加1个空标记。复制要修改的字符串是可行的。
头文件:
class TextLineSplitter
{
public:
TextLineSplitter( const size_t max_line_len );
~TextLineSplitter();
void SplitLine( const char *line,
const char sep_char = ',',
);
inline size_t NumTokens( void ) const
{
return mNumTokens;
}
const char * GetToken( const size_t token_idx ) const
{
assert( token_idx < mNumTokens );
return mTokens[ token_idx ];
}
private:
const size_t mStorageSize;
char *mBuff;
char **mTokens;
size_t mNumTokens;
inline void ResetContent( void )
{
memset( mBuff, 0, mStorageSize );
// mark all items as empty:
memset( mTokens, 0, mStorageSize * sizeof( char* ) );
// reset counter for found items:
mNumTokens = 0L;
}
};
Implementattion文件:
TextLineSplitter::TextLineSplitter( const size_t max_line_len ):
mStorageSize ( max_line_len + 1L )
{
// allocate memory
mBuff = new char [ mStorageSize ];
mTokens = new char* [ mStorageSize ];
ResetContent();
}
TextLineSplitter::~TextLineSplitter()
{
delete [] mBuff;
delete [] mTokens;
}
void TextLineSplitter::SplitLine( const char *line,
const char sep_char /* = ',' */,
)
{
assert( sep_char != '\0' );
ResetContent();
strncpy( mBuff, line, mMaxLineLen );
size_t idx = 0L; // running index for characters
do
{
assert( idx < mStorageSize );
const char chr = line[ idx ]; // retrieve current character
if( mTokens[ mNumTokens ] == NULL )
{
mTokens[ mNumTokens ] = &mBuff[ idx ];
} // if
if( chr == sep_char || chr == '\0' )
{ // item or line finished
// overwrite separator with a 0-terminating character:
mBuff[ idx ] = '\0';
// count-up items:
mNumTokens ++;
} // if
} while( line[ idx++ ] );
}
使用的场景是:
// create an instance capable of splitting strings up to 1000 chars long:
TextLineSplitter spl( 1000 );
spl.SplitLine( "Item1,,Item2,Item3" );
for( size_t i = 0; i < spl.NumTokens(); i++ )
{
printf( "%s\n", spl.GetToken( i ) );
}
输出:
Item1
Item2
Item3
使用strtok。在我看来,没有必要围绕标记化构建类,除非strtok不能提供您所需要的东西。可能不会,但在用C和c++编写各种解析代码的15年多时间里,我一直在使用strtok。这里有一个例子
char myString[] = "The quick brown fox";
char *p = strtok(myString, " ");
while (p) {
printf ("Token: %s\n", p);
p = strtok(NULL, " ");
}
一些注意事项(可能不适合您的需要)。该字符串在该过程中被“销毁”,这意味着EOS字符内联放置在分隔符点中。正确的用法可能需要创建字符串的非const版本。还可以在解析过程中更改分隔符列表。
在我看来,上面的代码比为它单独编写一个类要简单得多,也更容易使用。对我来说,这是语言提供的功能之一,而且它做得很好,很干净。这只是一个“基于C”的解决方案。它很合适,很简单,而且你不需要写很多额外的代码:-)