Question

我正在尝试进行某种类型的“字符串扩展”，其中我用数据库中的字符串替换键。标记的格式为{$<key>}。

我正在使用<regex>尝试完成此操作，但我遇到了一些后勤问题。我希望能够在一次传递中替换字符串，但修改字符串（s）可能会使smatch对象中的迭代器失效。

这或多或少是我正在尝试做的事情：

#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;
    }
}

期望的最终结果是s读取：

"This is an absolute nightmare!"

我知道我可以在多次通过中执行此类事情，但这似乎有点野蛮。

我在某处看到boost::regex有一些regex_replace的变体，允许以这种形式使用自定义替换函数：

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

但是，我当前的版本(1.55)没有这样的东西。

非常感谢任何帮助！

P.S。我可以使用boost或std，无论哪个都有效！

Answer 1

所以，除了我8小时前发表的评论：

或许相关：Compiling a simple parser with Boost.Spirit，replacing pieces of string，How to expand environment variables in .ini files using Boost，也许最有趣的是Fast multi-replacement into string

我看到了另外一个方法的空间。如果......您需要根据相同的文本模板进行许多替换，但使用不同的替换地图会怎样？

由于我最近发现了Boost ICL can be useful in mapping regions of input strings，我想在这里做同样的事情。

我使事情非常通用，并使用Spirit进行分析（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;
}

正如您所看到的，我们只返回interval_set<It>而不是进行任何替换，因此我们知道变量的位置。现在这是“智慧”，可用于从替换字符串的映射执行替换：

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;
}

现在，一个简单的测试程序将是这样的：

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's 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);
}

打印

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

你可以用输入字符串文字来调用它，使用unordered_map代替替换等。你可以省略wisdom，在这种情况下，实现将动态研究它。 / p>

完整计划

<强> 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's 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);
}

就地操作

只要确保替换字符串总是短于{$pattern}字符串（或等长），就可以使用input.begin()作为输出迭代器来调用此函数。

<强> 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;

打印

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

请注意，您可以（显然）不会再次在同一输入模板上重复使用相同的“智慧”，因为它会被修改。

使用正则表达式替换匹配

1 个答案:

完整计划

就地操作