Boost::Spirit struggle with parsing a String

China☆狼群 提交于 2021-02-10 06:11:38

问题


I'm trying to Parse a String with Boost::Spirit, but i just cannot get it to work. I have no experience with Boost::Spirit since today.

The string is composed of commands separated by an ';'. The commands are

"INC someInteger"

"BOMB firstInteger secondInteger"

"MOVE firstInteger secondInteger thirdInteger"

"MSG someString"

"WAIT"

I Managed to get this far:

#include <boost/spirit/include/qi.hpp>
#include <boost/phoenix/phoenix.hpp>

using namespace boost::spirit;

int main() {    
    std::string testInput = "MOVE 1 2 43;BOMB 0 3;INC 6;MOVE 2 3 99;MOVE 1 2 6";

    typedef std::string::iterator iter;
    using boost::phoenix::ref;

    iter start = testInput.begin();

    std::vector<int> IncCommands;
    std::vector<std::pair<int, int>> BombCommands;
    std::vector<std::tuple<int, int, int>> MoveCommands;

    qi::rule<iter, std::vector<int>(), ascii::space_type> nextIncrease = ("INC " >> qi::int_);
    //qi::rule<iter, std::vector<std::pair<int, int>>(), ascii::space_type> nextBomb = ("BOMB " >> qi::int_ >> qi::int_);
    //qi::rule<iter, std::vector<int>(), ascii::space_type> nextMove = ("MOVE " >> qi::int_ >> qi::int_ >> qi::int_);

    //qi::rule<iter, std::string, ascii::space_type> nextAction = (nextMove | nextBomb | nextIncrease) % ';';

    bool match = qi::phrase_parse(
        start,
        testInput.end(),
        nextIncrease,
        ascii::space,
        IncCommands
    );

    return 0;
}

The Problems that i have now:

  1. I don't know how i can extract more than 1 integer

  2. I don't know how i can merge everything into a proper grammar so that everything is parsed into several vectors.

  3. I didn't consider MSG and WAIT yet.


回答1:


I'd suggest starting out with the desired AST as always.

Spirit works well with static polymorphism, so I'd use a variant to represent commands:

namespace AST {
    namespace Cmd {
        struct Move { int x,y,z;  };
        struct Bomb { int x,y;    };
        struct Inc  { int amount; };
        struct Msg  { std::string text; };
        struct Wait {};
    }

    using Command = boost::variant<Cmd::Move, Cmd::Bomb, Cmd::Inc, Cmd::Msg, Cmd::Wait>;
    using Commands = std::vector<Command>;
}

Now, write the most straight-forward grammar to match it:

template <typename It>
struct ScriptGrammar : qi::grammar<It, AST::Commands()>
{
    ScriptGrammar() : ScriptGrammar::base_type(start) {
        using namespace qi;
        start   = skip(space) [ script ];
        script  = command % ";";
        command = move|bomb|inc|msg|wait;

        move = "MOVE" >> int_ >> int_ >> int_;
        bomb = "BOMB" >> int_ >> int_;
        inc  = "INC"  >> int_;
        msg  = "MSG"  >> text;
        wait = "WAIT" >> qi::attr(AST::Cmd::Wait{});

        text  = +~char_(";");
        BOOST_SPIRIT_DEBUG_NODES((start)(script)(command)(move)(bomb)(inc)(msg)(wait)(text))
    }
  private:
    using Skipper = qi::space_type;
    qi::rule<It, AST::Commands(), Skipper>  script;
    qi::rule<It, AST::Command(), Skipper>   command;
    qi::rule<It, AST::Cmd::Move(), Skipper> move;
    qi::rule<It, AST::Cmd::Bomb(), Skipper> bomb;
    qi::rule<It, AST::Cmd::Inc(), Skipper>  inc;
    qi::rule<It, AST::Cmd::Msg(), Skipper>  msg;
    qi::rule<It, AST::Cmd::Wait(), Skipper> wait;
    // lexeme
    qi::rule<It, AST::Commands()>  start;
    qi::rule<It, std::string()>  text;
};

Add in some glue for debug (Fusion adaptation and output streaming), and we have a working sample:

Live On Coliru

#define BOOST_SPIRIT_DEBUG
#include <iostream>
#include <vector>
#include <string>
#include <iterator>
#include <iomanip>
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/phoenix/phoenix.hpp>

namespace AST {
    namespace Cmd {
        struct Move { int x,y,z;  };
        struct Bomb { int x,y;    };
        struct Inc  { int amount; };
        struct Msg  { std::string text; };
        struct Wait {};
    }

    using Command = boost::variant<Cmd::Move, Cmd::Bomb, Cmd::Inc, Cmd::Msg, Cmd::Wait>;
    using Commands = std::vector<Command>;
}

BOOST_FUSION_ADAPT_STRUCT(AST::Cmd::Move, x,y,z)
BOOST_FUSION_ADAPT_STRUCT(AST::Cmd::Bomb, x,y)
BOOST_FUSION_ADAPT_STRUCT(AST::Cmd::Inc, amount)
BOOST_FUSION_ADAPT_STRUCT(AST::Cmd::Msg, text)
BOOST_FUSION_ADAPT_STRUCT(AST::Cmd::Wait)

namespace AST { namespace Cmd { // For demo/debug
    std::ostream& operator<<(std::ostream& os, Move const& cmd) { return os << "MOVE " << boost::fusion::as_vector(cmd); } 
    std::ostream& operator<<(std::ostream& os, Bomb const& cmd) { return os << "BOMB " << boost::fusion::as_vector(cmd); } 
    std::ostream& operator<<(std::ostream& os, Inc const& cmd)  { return os << "INC " << boost::fusion::as_vector(cmd);  } 
    std::ostream& operator<<(std::ostream& os, Msg const& cmd)  { return os << "MSG " << boost::fusion::as_vector(cmd);  } 
    std::ostream& operator<<(std::ostream& os, Wait const& cmd) { return os << "WAIT " << boost::fusion::as_vector(cmd); } 
} }

namespace qi = boost::spirit::qi;

template <typename It>
struct ScriptGrammar : qi::grammar<It, AST::Commands()>
{
    ScriptGrammar() : ScriptGrammar::base_type(start) {
        using namespace qi;
        start   = skip(space) [ script ];
        script  = command % ";";
        command = move|bomb|inc|msg|wait;

        move = "MOVE" >> int_ >> int_ >> int_;
        bomb = "BOMB" >> int_ >> int_;
        inc  = "INC"  >> int_;
        msg  = "MSG"  >> text;
        wait = "WAIT" >> qi::attr(AST::Cmd::Wait{});

        text  = +~char_(";");
        BOOST_SPIRIT_DEBUG_NODES((start)(script)(command)(move)(bomb)(inc)(msg)(wait)(text))
    }
  private:
    using Skipper = qi::space_type;
    qi::rule<It, AST::Commands(), Skipper>  script;
    qi::rule<It, AST::Command(), Skipper>   command;
    qi::rule<It, AST::Cmd::Move(), Skipper> move;
    qi::rule<It, AST::Cmd::Bomb(), Skipper> bomb;
    qi::rule<It, AST::Cmd::Inc(), Skipper>  inc;
    qi::rule<It, AST::Cmd::Msg(), Skipper>  msg;
    qi::rule<It, AST::Cmd::Wait(), Skipper> wait;
    // lexeme
    qi::rule<It, AST::Commands()>  start;
    qi::rule<It, std::string()>  text;
};

int main() {    
    std::string const testInput = "MOVE 1 2 43;BOMB 0 3;INC 6;MOVE 2 3 99;MSG MOVE ZIG;WAIT;MSG FOR GREAT JUSTICE!;MOVE 1 2 6";

    typedef std::string::const_iterator iter;

    iter start = testInput.begin(), end = testInput.end();

    AST::Commands script;

    bool match = qi::parse(start, testInput.end(), ScriptGrammar<iter>(), script);

    if (match) {
        std::cout << "Parsed " << script.size() << " commands\n";
        std::copy(script.begin(), script.end(), std::ostream_iterator<AST::Command>(std::cout, ";"));
    } else {
        std::cout << "Parse failed\n";
    }

    if (start != end)
        std::cout << "Remaining unparsed input: '" << std::string(start, end) << "'\n";
}

Which prints:

Parsed 8 commands
MOVE (1 2 43);BOMB (0 3);INC (6);MOVE (2 3 99);MSG (MOVE ZIG);WAIT ();MSG (FOR GREAT JUSTICE!);MOVE (1 2 6);

And optionally the BOOST_SPIRIT_DEBUG output:

<start>
  <try>MOVE 1 2 43;BOMB 0 3</try>
  <script>
    <try>MOVE 1 2 43;BOMB 0 3</try>
    <command>
      <try>MOVE 1 2 43;BOMB 0 3</try>
      <move>
        <try>MOVE 1 2 43;BOMB 0 3</try>
        <success>;BOMB 0 3;INC 6;MOVE</success>
        <attributes>[[1, 2, 43]]</attributes>
      </move>
      <success>;BOMB 0 3;INC 6;MOVE</success>
      <attributes>[[1, 2, 43]]</attributes>
    </command>
    <command>
      <try>BOMB 0 3;INC 6;MOVE </try>
      <move>
        <try>BOMB 0 3;INC 6;MOVE </try>
        <fail/>
      </move>
      <bomb>
        <try>BOMB 0 3;INC 6;MOVE </try>
        <success>;INC 6;MOVE 2 3 99;M</success>
        <attributes>[[0, 3]]</attributes>
      </bomb>
      <success>;INC 6;MOVE 2 3 99;M</success>
      <attributes>[[0, 3]]</attributes>
    </command>
    <command>
      <try>INC 6;MOVE 2 3 99;MS</try>
      <move>
        <try>INC 6;MOVE 2 3 99;MS</try>
        <fail/>
      </move>
      <bomb>
        <try>INC 6;MOVE 2 3 99;MS</try>
        <fail/>
      </bomb>
      <inc>
        <try>INC 6;MOVE 2 3 99;MS</try>
        <success>;MOVE 2 3 99;MSG MOV</success>
        <attributes>[[6]]</attributes>
      </inc>
      <success>;MOVE 2 3 99;MSG MOV</success>
      <attributes>[[6]]</attributes>
    </command>
    <command>
      <try>MOVE 2 3 99;MSG MOVE</try>
      <move>
        <try>MOVE 2 3 99;MSG MOVE</try>
        <success>;MSG MOVE ZIG;WAIT;M</success>
        <attributes>[[2, 3, 99]]</attributes>
      </move>
      <success>;MSG MOVE ZIG;WAIT;M</success>
      <attributes>[[2, 3, 99]]</attributes>
    </command>
    <command>
      <try>MSG MOVE ZIG;WAIT;MS</try>
      <move>
        <try>MSG MOVE ZIG;WAIT;MS</try>
        <fail/>
      </move>
      <bomb>
        <try>MSG MOVE ZIG;WAIT;MS</try>
        <fail/>
      </bomb>
      <inc>
        <try>MSG MOVE ZIG;WAIT;MS</try>
        <fail/>
      </inc>
      <msg>
        <try>MSG MOVE ZIG;WAIT;MS</try>
        <text>
          <try>MOVE ZIG;WAIT;MSG FO</try>
          <success>;WAIT;MSG FOR GREAT </success>
          <attributes>[[M, O, V, E,  , Z, I, G]]</attributes>
        </text>
        <success>;WAIT;MSG FOR GREAT </success>
        <attributes>[[[M, O, V, E,  , Z, I, G]]]</attributes>
      </msg>
      <success>;WAIT;MSG FOR GREAT </success>
      <attributes>[[[M, O, V, E,  , Z, I, G]]]</attributes>
    </command>
    <command>
      <try>WAIT;MSG FOR GREAT J</try>
      <move>
        <try>WAIT;MSG FOR GREAT J</try>
        <fail/>
      </move>
      <bomb>
        <try>WAIT;MSG FOR GREAT J</try>
        <fail/>
      </bomb>
      <inc>
        <try>WAIT;MSG FOR GREAT J</try>
        <fail/>
      </inc>
      <msg>
        <try>WAIT;MSG FOR GREAT J</try>
        <fail/>
      </msg>
      <wait>
        <try>WAIT;MSG FOR GREAT J</try>
        <success>;MSG FOR GREAT JUSTI</success>
        <attributes>[[]]</attributes>
      </wait>
      <success>;MSG FOR GREAT JUSTI</success>
      <attributes>[[]]</attributes>
    </command>
    <command>
      <try>MSG FOR GREAT JUSTIC</try>
      <move>
        <try>MSG FOR GREAT JUSTIC</try>
        <fail/>
      </move>
      <bomb>
        <try>MSG FOR GREAT JUSTIC</try>
        <fail/>
      </bomb>
      <inc>
        <try>MSG FOR GREAT JUSTIC</try>
        <fail/>
      </inc>
      <msg>
        <try>MSG FOR GREAT JUSTIC</try>
        <text>
          <try>FOR GREAT JUSTICE!;M</try>
          <success>;MOVE 1 2 6</success>
          <attributes>[[F, O, R,  , G, R, E, A, T,  , J, U, S, T, I, C, E, !]]</attributes>
        </text>
        <success>;MOVE 1 2 6</success>
        <attributes>[[[F, O, R,  , G, R, E, A, T,  , J, U, S, T, I, C, E, !]]]</attributes>
      </msg>
      <success>;MOVE 1 2 6</success>
      <attributes>[[[F, O, R,  , G, R, E, A, T,  , J, U, S, T, I, C, E, !]]]</attributes>
    </command>
    <command>
      <try>MOVE 1 2 6</try>
      <move>
        <try>MOVE 1 2 6</try>
        <success></success>
        <attributes>[[1, 2, 6]]</attributes>
      </move>
      <success></success>
      <attributes>[[1, 2, 6]]</attributes>
    </command>
    <success></success>
    <attributes>[[[1, 2, 43], [0, 3], [6], [2, 3, 99], [[M, O, V, E,  , Z, I, G]], [], [[F, O, R,  , G, R, E, A, T,  , J, U, S, T, I, C, E, !]], [1, 2, 6]]]</attributes>
  </script>
  <success></success>
  <attributes>[[[1, 2, 43], [0, 3], [6], [2, 3, 99], [[M, O, V, E,  , Z, I, G]], [], [[F, O, R,  , G, R, E, A, T,  , J, U, S, T, I, C, E, !]], [1, 2, 6]]]</attributes>
</start>


来源:https://stackoverflow.com/questions/42811884/boostspirit-struggle-with-parsing-a-string

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!