Question

我想使用Boost.Spirit.Lex来提取二进制文件;为此我编写了以下程序（这是一个摘录）：

#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/support_multi_pass.hpp>
#include <boost/bind.hpp>
#include <boost/ref.hpp>
#include <fstream>
#include <iterator>
#include <string>

namespace spirit = boost::spirit;
namespace lex = spirit::lex;

#define X 1
#define Y 2
#define Z 3

template<typename L>
class word_count_tokens : public lex::lexer<L>
{
    public:
        word_count_tokens () {
            this->self.add
                ("[^ \t\n]+", X)
                ("\n", Y)
                (".", Z);
        }
};

class counter
{
    public:
        typedef bool result_type;

        template<typename T>
        bool operator () (const T &t, size_t &c, size_t &w, size_t &l) const {
            switch (t.id ()) {
               case X:
                   ++w; c += t.value ().size ();
                    break;
               case Y:
                   ++l; ++c;
                    break;
                case Z:
                    ++c;
                    break;
            }

            return true;
        }
};

int main (int argc, char **argv)
{
    std::ifstream ifs (argv[1], std::ios::in | std::ios::binary);
    auto first = spirit::make_default_multi_pass (std::istream_iterator<char> (ifs));
    auto last = spirit::make_default_multi_pass (std::istream_iterator<char> ());
    size_t w, c, l;
    word_count_tokens<lex::lexertl::lexer<>> word_count_functor;

    w = c = l = 0;

    bool r = lex::tokenize (first, last, word_count_functor, boost::bind (counter (), _1, boost::ref (c), boost::ref (w), boost::ref (l)));

    ifs.close ();

    if (r) {
        std::cout << l << ", " << w << ", " << c << std::endl;
    }

    return 0;
}

构建返回以下错误：

lexer.hpp:390:46: error: non-const lvalue reference to type 'const char *' cannot bind to a value of unrelated type

现在，错误是由具体词法分析器lex::lexer<>的定义引起的;实际上它的第一个参数默认为const char *。如果我使用spirit::istream_iterator或spirit::make_default_multi_pass (.....)，我也会收到同样的错误但是，如果我指定lex::lexer<>的正确模板参数，我会收到大量错误！

解决方案？

更新

我已经推出了所有源文件;这是word_counter网站的例子。

Answer 1

我认为真正的问题没有显示出来。您没有显示first或last，我觉得您可能会有临时工作。

这是我提出的一个验证样本，或许你可以看到它在做什么 - 错误---不同：）

Live on Coliru （内存映射字节向量，通过const char*）
And this alternative （使用spirit::istream_iterator）

#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/qi.hpp>
#include <fstream>
#ifdef MEMORY_MAPPED
#   include <boost/iostreams/device/mapped_file.hpp>
#endif

namespace /*anon*/
{
    namespace qi =boost::spirit::qi;
    namespace lex=boost::spirit::lex;

    template <typename Lexer>
        struct mylexer_t : lex::lexer<Lexer>
    {
        mylexer_t()
        {
            fileheader = "hello";

            this->self = fileheader
                | space [ lex::_pass = lex::pass_flags::pass_ignore ];
        }

        lex::token_def<lex::omit>
            fileheader, space;
    };

    template <typename Iterator> struct my_grammar_t
        : public qi::grammar<Iterator>
    {
        template <typename TokenDef>
            my_grammar_t(TokenDef const& tok) 
                : my_grammar_t::base_type(header)
        {
            header = tok.fileheader;
            BOOST_SPIRIT_DEBUG_NODE(header);
        }

      private:
        qi::rule<Iterator> header;
    };
}

namespace /* */ {

    std::string safechar(char ch) {
        switch (ch) {
            case '\t': return "\\t"; break;
            case '\0': return "\\0"; break;
            case '\r': return "\\r"; break;
            case '\n': return "\\n"; break;
        }
        return std::string(1, ch); 
    }

    template <typename It>
        std::string showtoken(const boost::iterator_range<It>& range)
        {
            std::ostringstream oss;
            oss << '[';
            std::transform(range.begin(), range.end(), std::ostream_iterator<std::string>(oss), safechar);
            oss << ']';
            return oss.str();
        }
}

bool parsefile(const std::string& spec)
{
#ifdef MEMORY_MAPPED
    typedef char const* It;
    boost::iostreams::mapped_file mmap(spec.c_str(), boost::iostreams::mapped_file::readonly);
    char const *first = mmap.const_data();
    char const *last = first + mmap.size();
#else
    typedef char const* It;
    std::ifstream in(spec.c_str());
    in.unsetf(std::ios::skipws);

    std::string v(std::istreambuf_iterator<char>(in.rdbuf()), std::istreambuf_iterator<char>());
    It first = &v[0];
    It last = first+v.size();
#endif

    typedef lex::lexertl::token<It  /*, boost::mpl::vector<char, unsigned int, std::string> */> token_type;
    typedef lex::lexertl::actor_lexer<token_type> lexer_type;

    typedef mylexer_t<lexer_type>::iterator_type iterator_type;
    try
    {
        static mylexer_t<lexer_type> mylexer;
        static my_grammar_t<iterator_type> parser(mylexer);

        auto iter = mylexer.begin(first, last);
        auto end  = mylexer.end();

        bool r = qi::parse(iter, end, parser);

        r = r && (iter == end);

        if (!r)
            std::cerr << spec << ": parsing failed at: \"" << std::string(first, last) << "\"\n";
        return r;
    }
    catch (const qi::expectation_failure<iterator_type>& e)
    {
        std::cerr << "FIXME: expected " << e.what_ << ", got '";
        for (auto it=e.first; it!=e.last; it++)
            std::cerr << showtoken(it->value());
        std::cerr << "'" << std::endl;
        return false;
    }
}

int main()
{
    if (parsefile("input.bin"))
        return 0;
    return 1;
}

对于变体：

typedef boost::spirit::istream_iterator It;
std::ifstream in(spec.c_str());
in.unsetf(std::ios::skipws);

It first(in), last;

Answer 2

好的，既然问题已经改变，这里有一个新答案，用完整的代码示例解决了一些问题。

首先，您需要使用自定义令牌类型。即

word_count_tokens<lex::lexertl::lexer<lex::lexertl::token<boost::spirit::istream_iterator>>> word_count_functor;
// instead of:
// word_count_tokens<lex::lexertl::lexer<>> word_count_functor;

显然，习惯使用typedef lex::lexertl::token<boost::spirit::istream_iterator>

您需要使用min_token_id而不是令牌ID 1,2,3。另外，请将其作为易于维护的枚举：
```
enum token_ids {
    X = lex::min_token_id + 1,
    Y,
    Z,
};
```
您不能再在默认令牌.size()上使用value()，因为迭代器范围不再是RandomAccessRange。相反，请使用专门用于boost::distance()的{{1}}：
```
iterator_range
```

合并这些修补程序： Live On Coliru

        ++w; c += boost::distance(t.value()); // t.value ().size ();

自行运行时，打印

#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/support_istream_iterator.hpp>
#include <boost/bind.hpp>
#include <fstream>

namespace spirit = boost::spirit;
namespace lex    = spirit::lex;

enum token_ids {
    X = lex::min_token_id + 1,
    Y,
    Z,
};

template<typename L>
class word_count_tokens : public lex::lexer<L>
{
    public:
        word_count_tokens () {
            this->self.add
                ("[^ \t\n]+", X)
                ("\n"       , Y)
                ("."        , Z);
        }
};

struct counter
{
    typedef bool result_type;

    template<typename T>
    bool operator () (const T &t, size_t &c, size_t &w, size_t &l) const {
        switch (t.id ()) {
            case X:
                ++w; c += boost::distance(t.value()); // t.value ().size ();
                break;
            case Y:
                ++l; ++c;
                break;
            case Z:
                ++c;
                break;
        }

        return true;
    }
};

int main (int argc, char **argv)
{
    std::ifstream ifs (argv[1], std::ios::in | std::ios::binary);
    ifs >> std::noskipws;
    boost::spirit::istream_iterator first(ifs), last;
    word_count_tokens<lex::lexertl::lexer<lex::lexertl::token<boost::spirit::istream_iterator>>> word_count_functor;

    size_t w = 0, c = 0, l = 0;
    bool r = lex::tokenize (first, last, word_count_functor, 
            boost::bind (counter (), _1, boost::ref (c), boost::ref (w), boost::ref (l)));

    ifs.close ();

    if (r) {
        std::cout << l << ", " << w << ", " << c << std::endl;
    }
}

使用Boost.Spirit.Lex和流迭代器

2 个答案: