Geek Answers Handbook

Using regex to replace matches in place

I am trying to execute a certain type of "row extension" in which I replace the keys with rows from the database. Tag format {$<key>}.

I use <regex>to try to do this, but I have a logistic problem. I want to be able to replace strings in a single pass, but changing the string ( s) may invalidate the iterators found in the objects smatch.

Here is more or less what I am trying to do:

#include <iostream>
#include <map>
#include <regex>

using namespace std;

int main()
{
    map<string, string> m;

    m.insert(make_pair("severity", "absolute"));
    m.insert(make_pair("experience", "nightmare"));

    string s = "This is an {$severity} {$experience}!";
    static regex e("\\{\\$(.*?)\\}");
    sregex_iterator next(s.begin(), s.end(), e);
    sregex_iterator end;

    for (; next != end; ++next)
    {
        auto m_itr = m.find(next->str(1));

        if (m_itr == m.end())
        {
            continue;
        }

        //TODO: replace expansion tags with strings somehow?

        cout << (*next).str(0) << ":" << m_itr->second << endl;
    }
}

The desired end result is that it sreads:

"This is an absolute nightmare!"

I know that I could do this type of thing in a few passes, but that seems a little rude.

- , boost::regex regex_replace, :

regex_replace(std::string&, regex, std::string(const smatch&))

(1.55) .

!

P.S. boost, std , , !

+4
1

, , 8 :

: Boost.Spirit, , .ini Boost , ,

. , ... , ?

, Boost ICL , .

(study):

template <
    typename InputRange,
    typename It = typename boost::range_iterator<InputRange const>::type,
    typename IntervalSet = boost::icl::interval_set<It> >
IntervalSet study(InputRange const& input) {
    using std::begin;
    using std::end;

    It first(begin(input)), last(end(input));

    using namespace boost::spirit::qi;
    using boost::spirit::repository::qi::seek;

    IntervalSet variables;

    parse(first, last, *seek [ raw [ "{$" >> +alnum >> "}" ] ], variables);

    return variables;
}

, - interval_set<It>, , . "", :

template <
    typename InputRange,
    typename Replacements,
    typename OutputIterator,
    typename StudyMap,
    typename It = typename boost::range_iterator<InputRange const>::type
>
OutputIterator perform_replacements(InputRange const& input, Replacements const& m, StudyMap const& wisdom, OutputIterator out) 
{
    using std::begin;
    using std::end;

    It current(begin(input));

    for (auto& replace : wisdom)
    {
        It l(lower(replace)),
        u(upper(replace));

        if (current < l)
            out = std::copy(current, l, out);

        auto match = m.find({l+2, u-1});
        if (match == m.end())
            out = std::copy(l, u, out);
        else
            out = std::copy(begin(match->second), end(match->second), out);

        current = u;
    }

    if (current!=end(input))
        out = std::copy(current, end(input), out);
    return out;
}

:

int main()
{
    using namespace std;
    string const input = "This {$oops} is an {$severity} {$experience}!\n";
    auto const wisdom = study(input);

    cout << "Wisdom: ";
    for(auto& entry : wisdom)
        cout << entry;

    auto m = map<string, string> {
            { "severity",   "absolute"  },
            { "OOPS",       "REALLY"    },
            { "experience", "nightmare" },
        };

    ostreambuf_iterator<char> out(cout);
    out = '\n';

    perform_replacements(input, m, wisdom, out);

    // now let use a case insensitive map, still with the same "study"
    map<string, string, ci_less> im { m.begin(), m.end() };
    im["eXperience"] = "joy";

    perform_replacements(input, im, wisdom, out);
}


Wisdom: {$oops}{$severity}{$experience}
This {$oops} is an absolute nightmare!
This REALLY is an absolute joy!

, unordered_map .. wisdom, .

Live On Coliru

#include <iostream>
#include <map>
#include <boost/regex.hpp>
#include <boost/icl/interval_set.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/repository/include/qi_seek.hpp>

namespace boost { namespace spirit { namespace traits {
    template <typename It>
        struct assign_to_attribute_from_iterators<icl::discrete_interval<It>, It, void> {
            template <typename ... T> static void call(It b, It e, icl::discrete_interval<It>& out) {
                out = icl::discrete_interval<It>::right_open(b, e);
            }
        };
} } }

template <
    typename InputRange,
    typename It = typename boost::range_iterator<InputRange const>::type,
    typename IntervalSet = boost::icl::interval_set<It> >
IntervalSet study(InputRange const& input) {
    using std::begin;
    using std::end;

    It first(begin(input)), last(end(input));

    using namespace boost::spirit::qi;
    using boost::spirit::repository::qi::seek;

    IntervalSet variables;    
    parse(first, last, *seek [ raw [ "{$" >> +alnum >> "}" ] ], variables);

    return variables;
}

template <
    typename InputRange,
    typename Replacements,
    typename OutputIterator,
    typename StudyMap,
    typename It = typename boost::range_iterator<InputRange const>::type
>
OutputIterator perform_replacements(InputRange const& input, Replacements const& m, StudyMap const& wisdom, OutputIterator out) 
{
    using std::begin;
    using std::end;

    It current(begin(input));

    for (auto& replace : wisdom)
    {
        It l(lower(replace)),
           u(upper(replace));

        if (current < l)
            out = std::copy(current, l, out);

        auto match = m.find({l+2, u-1});
        if (match == m.end())
            out = std::copy(l, u, out);
        else
            out = std::copy(begin(match->second), end(match->second), out);

        current = u;
    }

    if (current!=end(input))
        out = std::copy(current, end(input), out);
    return out;
}

template <
    typename InputRange,
    typename Replacements,
    typename OutputIterator,
    typename It = typename boost::range_iterator<InputRange const>::type
>
OutputIterator perform_replacements(InputRange const& input, Replacements const& m, OutputIterator out) {
    return perform_replacements(input, m, study(input), out);
}

// for demo program
#include <boost/algorithm/string.hpp>
struct ci_less {
    template <typename S>
    bool operator() (S const& a, S const& b) const {
        return boost::lexicographical_compare(a, b, boost::is_iless());
    }
};

namespace boost { namespace icl {
    template <typename It>
        static inline std::ostream& operator<<(std::ostream& os, discrete_interval<It> const& i) {
            return os << make_iterator_range(lower(i), upper(i));
        }
} }

int main()
{
    using namespace std;
    string const input = "This {$oops} is an {$severity} {$experience}!\n";
    auto const wisdom = study(input);

    cout << "Wisdom: ";
    for(auto& entry : wisdom)
        cout << entry;

    auto m = map<string, string> {
            { "severity",   "absolute"  },
            { "OOPS",       "REALLY"    },
            { "experience", "nightmare" },
        };

    ostreambuf_iterator<char> out(cout);
    out = '\n';

    perform_replacements(input, m, wisdom, out);

    // now let use a case insensitive map, still with the same "study"
    map<string, string, ci_less> im { m.begin(), m.end() };
    im["eXperience"] = "joy";

    perform_replacements(input, im, wisdom, out);
}

, {$pattern} ( ), input.begin() .

Live On Coliru

string input1 = "This {$803525c8-3ce4-423a-ad25-cc19bbe8422a} is an {$efa72abf-fe96-4983-b373-a35f70551e06} {$8a10abaa-cc0d-47bd-a8e1-34a8aa0ec1ef}!\n",
       input2 = input1;

auto m = map<string, string> {
        { "efa72abf-fe96-4983-b373-a35f70551e06", "absolute"  },
        { "803525C8-3CE4-423A-AD25-CC19BBE8422A", "REALLY"    },
        { "8a10abaa-cc0d-47bd-a8e1-34a8aa0ec1ef", "nightmare" },
    };

input1.erase(perform_replacements(input1, m, input1.begin()), input1.end());

map<string, string, ci_less> im { m.begin(), m.end() };
im["8a10abaa-cc0d-47bd-a8e1-34a8aa0ec1ef"] = "joy";

input2.erase(perform_replacements(input2, im, input2.begin()), input2.end());

std::cout << input1
          << input2;


This {$803525c8-3ce4-423a-ad25-cc19bbe8422a} is an absolute nightmare!
This REALLY is an absolute joy!

, () "" , .

+1

More articles:


All Articles