How do I tokenize a string in C++?

Question

Java has a convenient split method:

String str = "The quick brown fox";
String[] results = str.split(" ");

Is there an easy way to do this in C++?

Answer 1

I posted this answer for similar question.
Don't reinvent the wheel. I've used a number of libraries and the fastest and most flexible I have come across is: C++ String Toolkit Library.

Here is an example of how to use it that I've posted else where on the stackoverflow.

#include <iostream>
#include <vector>
#include <string>
#include <strtk.hpp>

const char *whitespace  = " \t\r\n\f";
const char *whitespace_and_punctuation  = " \t\r\n\f;,=";

int main()
{
    {   // normal parsing of a string into a vector of strings
       std::string s("Somewhere down the road");
       std::vector<std::string> result;
       if( strtk::parse( s, whitespace, result ) )
       {
           for(size_t i = 0; i < result.size(); ++i )
            std::cout << result[i] << std::endl;
       }
    }

    {  // parsing a string into a vector of floats with other separators
       // besides spaces

       std::string t("3.0, 3.14; 4.0");
       std::vector<float> values;
       if( strtk::parse( s, whitespace_and_punctuation, values ) )
       {
           for(size_t i = 0; i < values.size(); ++i )
            std::cout << values[i] << std::endl;
       }
    }

    {  // parsing a string into specific variables

       std::string u("angle = 45; radius = 9.9");
       std::string w1, w2;
       float v1, v2;
       if( strtk::parse( s, whitespace_and_punctuation, w1, v1, w2, v2) )
       {
           std::cout << "word " << w1 << ", value " << v1 << std::endl;
           std::cout << "word " << w2 << ", value " << v2 << std::endl;
       }
    }

    return 0;
}

Answer 2

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.

Basically one can replace the separator characters with string-terminating '\0'-characters and set pointers to the tokens withing the modified string. In the extreme case when the string consists only of separators, one gets string-length plus 1 resulting empty tokens. It is practical to duplicate the string to be modified.

Header file:

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 file:

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++ ] );
}

A scenario of usage would be:

// 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 ) );
}

output:

Item1

Item2
Item3

Answer 3

A solution using regex_token_iterators:

#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;
    }
}

Answer 4

you can take advantage of boost::make_find_iterator. Something similar to this:

template<typename CH>
inline vector< basic_string<CH> > tokenize(
    const basic_string<CH> &Input,
    const basic_string<CH> &Delimiter,
    bool remove_empty_token
    ) {

    typedef typename basic_string<CH>::const_iterator string_iterator_t;
    typedef boost::find_iterator< string_iterator_t > string_find_iterator_t;

    vector< basic_string<CH> > Result;
    string_iterator_t it = Input.begin();
    string_iterator_t it_end = Input.end();
    for(string_find_iterator_t i = boost::make_find_iterator(Input, boost::first_finder(Delimiter, boost::is_equal()));
        i != string_find_iterator_t();
        ++i) {
        if(remove_empty_token){
            if(it != i->begin())
                Result.push_back(basic_string<CH>(it,i->begin()));
        }
        else
            Result.push_back(basic_string<CH>(it,i->begin()));
        it = i->end();
    }
    if(it != it_end)
        Result.push_back(basic_string<CH>(it,it_end));

    return Result;
}

Answer 5

For simple stuff I just use the following:

unsigned TokenizeString(const std::string& i_source,
                        const std::string& i_seperators,
                        bool i_discard_empty_tokens,
                        std::vector<std::string>& o_tokens)
{
    unsigned prev_pos = 0;
    unsigned pos = 0;
    unsigned number_of_tokens = 0;
    o_tokens.clear();
    pos = i_source.find_first_of(i_seperators, pos);
    while (pos != std::string::npos)
    {
        std::string token = i_source.substr(prev_pos, pos - prev_pos);
        if (!i_discard_empty_tokens || token != "")
        {
            o_tokens.push_back(i_source.substr(prev_pos, pos - prev_pos));
            number_of_tokens++;
        }

        pos++;
        prev_pos = pos;
        pos = i_source.find_first_of(i_seperators, pos);
    }

    if (prev_pos < i_source.length())
    {
        o_tokens.push_back(i_source.substr(prev_pos));
        number_of_tokens++;
    }

    return number_of_tokens;
}

Cowardly disclaimer: I write real-time data processing software where the data comes in through binary files, sockets, or some API call (I/O cards, camera's). I never use this function for something more complicated or time-critical than reading external configuration files on startup.

Answer 6

Here is a sample tokenizer class that might do what you want

//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;
}

Example:

std::vector <std::string> v;
Tokenizer s("split this string", " ");
while (s.NextToken())
{
    v.push_back(s.GetToken());
}