使用精神以其他方式解析结构时混淆输出

时间:2015-10-26 02:32:54

标签: c++ parsing c++11 boost-spirit boost-spirit-qi

这是一个大大减少的事情我想尽可能以最好的方式做。 (当然,问题也在于,我试图了解如何最好地运用精神。)

我需要将数据解析为具有多个成员的结构。成员被简单地列为键值对,因此这很简单 - 但是,如果某些键不同,那么在我正在解析的数据中,稍后可能会出现不同的值,或者可能省略某些键。然而,我最终解析的数据结构有一个固定的形式。

在示例代码中,my_structstruct,如下所示:

struct my_struct {
  std::string a;
  std::string b;
  std::string c;
  std::string d;
};

grammar1是一种解析像这样的字符串的语法

"a: x b: y c: z d: w"

进入像这样的结构

my_struct{ "x", "y", "z", "w" }

我想另外解析这样的字符串:

"a: x b: y d-no-c: w"

进入像这样的结构

my_struct{ "x", "y", "", "w" }
理想情况下,我希望尽可能简单地做到这一点,而不必在此过程中制作不必要的字符串副本。

我的第一个想法是,主要规则应该被重写,以便它解析“a”和“b”,然后根据是否存在“c”在两个选项之间进行选择。这很容易理解为语法,但是当我们尝试使数据类型适合于它的属性语法部分时,我似乎无法使其工作。我尝试使用std::pair<std::string, std::string>fusion::vector作为替代类型,但这显然不能使用qi运算符<<流式传输到我的结构中。 (grammar2测试被注释掉,因为它没有编译。)

我的下一个想法是,我们可以简单地使用主要规则的两种替代形式,这些形式归因于类型my_struct,以确保归因解析成功。但令人惊讶的是,这个实现实际上已经被破坏 - 似乎当语法回溯时,它会复制结果结构中的ab字段。我没想到这一点,我不知道为什么会这样,你知道吗? (这是grammar3)。

grammar3有一个问题,即使它按照我认为的那样工作(测试通过),当替代部分回溯时,它必须重新分析ab这是一种效率低下的问题。如果我们愿意将目标结构从my_struct更改为不同的结构,那么我们可以使用grammar4,它具有与grammar2相同的计划,但是目标是一个结构,其中一个元素是std::pair。然后我们将这个临时结构中的所有字符串移动到我们真正想要的格式中。

所以,问题是

  • grammar4有效,但有没有办法按照grammar2的方式做一些事情,这可能会更有效率?
  • 为什么grammar3未通过测试?

完整列表:

#define SPIRIT_USE_PHOENIX_V3
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_fusion.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/fusion/adapted/struct/define_struct.hpp>
#include <boost/fusion/include/define_struct.hpp>
#include <boost/fusion/include/std_pair.hpp>

#include <iostream>
#include <string>
#include <utility>

namespace qi = boost::spirit::qi;

BOOST_FUSION_DEFINE_STRUCT(
 /**/
 ,
 my_struct,
 (std::string, a)
 (std::string, b)
 (std::string, c)
 (std::string, d))

template<typename Iterator>
class grammar1 : public qi::grammar<Iterator, my_struct()> {
public:
  qi::rule<Iterator, std::string()> id;
  qi::rule<Iterator, my_struct()> main;

  grammar1() : grammar1::base_type(main) {
    using qi::lit;
    using qi::char_;
    using qi::omit;
    using qi::space;
    id = omit[ *space ] >> *char_("A-Za-z_") >> omit [ *space ];
    main = lit("a:") >> id >> lit("b:") >> id >> lit("c:") >> id >> lit("d:") >> id;
  }
};


//typedef std::pair<std::string, std::string> second_part_type;
typedef boost::fusion::vector<std::string, std::string> second_part_type;

template<typename Iterator>
class grammar2 : public qi::grammar<Iterator, my_struct()> {
public:
  qi::rule<Iterator, std::string()> id;
  qi::rule<Iterator, second_part_type()> with_c;
  qi::rule<Iterator, second_part_type()> without_c;
  qi::rule<Iterator, my_struct()> main;

  grammar2() : grammar2::base_type(main) {
    using qi::lit;
    using qi::char_;
    using qi::omit;
    using qi::space;
    using qi::attr;
    id = omit[ *space ] >> *char_("A-Za-z_") >> omit [ *space ];
    with_c = lit("c:") >> id >> lit("d:") >> id;
    without_c = attr("") >> lit("d-no-c:") >> id;
    main = lit("a:") >> id >> lit("b:") >> id >> (with_c  | without_c);
  }
};


template<typename Iterator>
class grammar3 : public qi::grammar<Iterator, my_struct()> {
public:
  qi::rule<Iterator, std::string()> id;
  qi::rule<Iterator, my_struct()> with_c;
  qi::rule<Iterator, my_struct()> without_c;
  qi::rule<Iterator, my_struct()> main;

  grammar3() : grammar3::base_type(main) {
    using qi::lit;
    using qi::char_;
    using qi::omit;
    using qi::space;
    using qi::attr;
    id = omit[ *space ] >> *char_("A-Za-z_") >> omit [ *space ];
    with_c = lit("a:") >> id >> lit("b:") >> id >> lit("c:") >> id >> lit("d:") >> id;
    without_c = lit("a:") >> id >> lit("b:") >> id >> attr("") >> lit("d-no-c:") >> id;
    main = with_c | without_c;
  }
};

/***
 * Alternate approach
 */
typedef std::pair<std::string, std::string> spair;

BOOST_FUSION_DEFINE_STRUCT(
 /**/
 ,
 my_struct2,
 (std::string, a)
 (std::string, b)
 (spair, cd))

template<typename Iterator>
class grammar4 : public qi::grammar<Iterator, my_struct2()> {
public:
  qi::rule<Iterator, std::string()> id;
  qi::rule<Iterator, spair()> with_c;
  qi::rule<Iterator, spair()> without_c;
  qi::rule<Iterator, my_struct2()> main;

  grammar4() : grammar4::base_type(main) {
    using qi::lit;
    using qi::char_;
    using qi::omit;
    using qi::space;
    using qi::attr;
    id = omit[ *space ] >> *char_("A-Za-z_") >> omit [ *space ];
    with_c = lit("c:") >> id >> lit("d:") >> id;
    without_c = attr("") >> lit("d-no-c:") >> id;
    main = lit("a:") >> id >> lit("b:") >> id >> (with_c  | without_c);
  }
};

my_struct convert_struct(my_struct2 && s) {
  return { std::move(s.a), std::move(s.b), std::move(s.cd.first), std::move(s.cd.second) };
}

/***
 * Testing
 */
void check_strings_eq(const std::string & a, const std::string & b, const char * label, int line = 0) {
  if (a != b) {
    std::cerr << "Mismatch '" << label << "' ";
    if (line) { std::cerr << "at line " << line << " "; }
    std::cerr << "\"" << a << "\" != \"" << b << "\"\n";
  }
}

void check_eq(const my_struct & s, const my_struct & t, int line = 0) {
  check_strings_eq(s.a, t.a, "a", line);
  check_strings_eq(s.b, t.b, "b", line);
  check_strings_eq(s.c, t.c, "c", line);
  check_strings_eq(s.d, t.d, "d", line);
}

template<template<typename> class Grammar>
void test_grammar(const std::string & input, const my_struct & expected, int line = 0) {
  auto it = input.begin();
  auto end = input.end();
  Grammar<decltype(it)> grammar;
  my_struct result;
  if (!qi::parse(it, end, grammar, result)) {
    std::cerr << "Failed to parse! ";
    if (line) { std::cerr << "line = " << line; }
    std::cerr << "\n";
    std::cerr << "Stopped at:\n" << input << "\n";
    for (auto temp = input.begin(); temp != it; ++temp) { std::cerr << " "; }
    std::cerr << "^\n";
  } else {
    check_eq(result, expected, line);
  }
}

int main() {
  test_grammar<grammar1> ( "a: x    b: y   c: z   d: w",   my_struct{ "x",    "y",   "z",   "w" }, __LINE__);
  test_grammar<grammar1> ( "a: asdf b: jkl c: foo d: bar", my_struct{ "asdf", "jkl", "foo", "bar" }, __LINE__ );
  //test_grammar<grammar2> ( "a: asdf b: jkl c: foo d: bar", my_struct{ "asdf", "jkl", "foo", "bar" }, __LINE__ );
  //test_grammar<grammar2> ( "a: asdf b: jkl d-no-c: bar",   my_struct{ "asdf", "jkl", "", "bar" }, __LINE__ );
  test_grammar<grammar3> ( "a: asdf b: jkl c: foo d: bar", my_struct{ "asdf", "jkl", "foo", "bar" }, __LINE__);
  test_grammar<grammar3> ( "a: asdf b: jkl d-no-c: bar",   my_struct{ "asdf", "jkl", "", "bar" }, __LINE__ );

  // Test 4th grammar
  {
    std::string input = "a: asdf b: jkl c: foo d: bar";
    auto it = input.begin();
    auto end = input.end();
    grammar4<decltype(it)> grammar;
    my_struct2 result;
    if (!qi::parse(it, end, grammar, result)) {
      std::cerr << "Failed to parse! Line = " << __LINE__ << std::endl;
    } else {
      check_eq(convert_struct(std::move(result)),  my_struct{ "asdf", "jkl", "foo", "bar" }, __LINE__);
    }
  }
  {
    std::string input = "a: asdf b: jkl d-no-c: bar";
    auto it = input.begin();
    auto end = input.end();
    grammar4<decltype(it)> grammar;
    my_struct2 result;
    if (!qi::parse(it, end, grammar, result)) {
      std::cerr << "Failed to parse! Line = " << __LINE__ << std::endl;
    } else {
      check_eq(convert_struct(std::move(result)),  my_struct{ "asdf", "jkl", "", "bar" }, __LINE__);
    }
  }
}

1 个答案:

答案 0 :(得分:2)

我的建议是使用排列解析器。

虽然它更加灵活,但您可能希望在语义操作中添加验证约束:

<强> Live On Coliru

//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/tuple/tuple_comparison.hpp>

#include <iostream>
#include <string>

namespace qi = boost::spirit::qi;

struct my_struct {
    std::string a,b,c,d;
};

BOOST_FUSION_ADAPT_STRUCT(my_struct, a, b, c, d)

template<typename Iterator>
class grammar : public qi::grammar<Iterator, my_struct()> {
    public:
        grammar() : grammar::base_type(start) {
            using namespace qi;

            id    = +char_("A-Za-z_");
            part  = lexeme[lit(_r1) >> ':'] >> id;

            main  = part(+"a")
                  ^ part(+"b")
                  ^ part(+"c")
                  ^ (part(+"d") | part(+"d-no-c"));
                  ;

            start = skip(space) [ main ];

            BOOST_SPIRIT_DEBUG_NODES((main)(part))
        }
    private:
        qi::rule<Iterator, std::string()>                            id;
        qi::rule<Iterator, std::string(const char*), qi::space_type> part;
        qi::rule<Iterator, my_struct(), qi::space_type>              main;
        //
        qi::rule<Iterator, my_struct()> start;
};

/***
 * Testing
 */
void check_strings_eq(const std::string & a, const std::string & b, const char * label) {
    if (a != b) {
        std::cerr << "Mismatch '" << label << "' \"" << a << "\" != \"" << b << "\"\n";
    }
}

void check_eq(const my_struct & s, const my_struct & t) {
    check_strings_eq(s.a, t.a, "a");
    check_strings_eq(s.b, t.b, "b");
    check_strings_eq(s.c, t.c, "c");
    check_strings_eq(s.d, t.d, "d");
    if (boost::tie(s.a,s.b,s.c,s.d) == boost::tie(t.a,t.b,t.c,t.d))
        std::cerr << "struct data matches\n";
}

template<template<typename> class Grammar>
void test_grammar(const std::string &input, const my_struct &expected) {
    auto it  = input.begin();
    auto end = input.end();

    Grammar<decltype(it)> grammar;
    my_struct result;

    if (!qi::parse(it, end, grammar, result)) {
        std::cerr << "Failed to parse!\n";
        std::cerr << "Stopped at:\n" << input << "\n";

        for (auto temp = input.begin(); temp != it; ++temp) {
            std::cerr << " ";
        }

        std::cerr << "^\n";
    } else {
        check_eq(result, expected);
    }
}

int main() {
    for (auto&& p : std::vector<std::pair<std::string, my_struct> > {
            {"a: x b: y c: z d: w", my_struct{ "x", "y", "z", "w" }},
            {"a: x      c: z d: w", my_struct{ "x", "" , "z", "w" }},
            {"a: x      c: z"     , my_struct{ "x", "" , "z", ""  }},
            {"     b: y c: z d: w", my_struct{ "" , "y", "z", "w" }},
            {"b: y c: z a: x d: w", my_struct{ "x", "y", "z", "w" }},
            // if you really need:
            {"a: x b: y d-no-c: w", my_struct{ "x", "y", "" , "w" }},
        })
    {
        auto const& input    = p.first;
        auto const& expected = p.second;
        std::cout << "----\nParsing '" << input << "'\n";
        test_grammar<grammar> (input, expected);
    }
}

打印

----
Parsing 'a: x b: y c: z d: w'
struct data matches
----
Parsing 'a: x      c: z d: w'
struct data matches
----
Parsing 'a: x      c: z'
struct data matches
----
Parsing '     b: y c: z d: w'
struct data matches
----
Parsing 'b: y c: z a: x d: w'
struct data matches
----
Parsing 'a: x b: y d-no-c: w'
struct data matches