boost::spirit 默认语义动作和字符串组合

Question

我有以下代码：

#include <gtest/gtest.h>
#include <boost/config/warning_disable.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/qi_eps.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <boost/spirit/include/phoenix_object.hpp>
#include <boost/spirit/include/phoenix_bind.hpp>
#include <boost/spirit/include/classic_core.hpp>
#include <boost/spirit/include/classic_confix.hpp>
#include <boost/spirit/include/classic_chset.hpp>
#include <boost/spirit/include/classic_utility.hpp>
#include <boost/fusion/include/cons.hpp>
#include <boost/fusion/include/at_c.hpp>
#include <boost/fusion/include/std_pair.hpp>
#include <boost/bind.hpp>
#include <boost/optional/optional_io.hpp>
#include <boost/variant.hpp>

namespace spi = boost::spirit;
namespace qi = boost::spirit::qi;

TEST(TestBoost, cpp_comment)
{
    using qi::char_;
    using qi::omit;
    using qi::eoi;
    typedef std::string::const_iterator iter;

    const std::string example = "/* this should be ignored */";
    auto b = std::begin(example);
    auto e = std::end(example);

    qi::rule<iter, std::string()> cpp_comment = char_('/') >> char_('/') >> *(char_ - '\n') >> (char_('\n') | omit[eoi]);
    qi::rule<iter, std::string()> c_comment = char_('/') >> char_('*') >> *(char_ - "*/") >> char_('*') >> char_('/');
    qi::rule<iter, std::string()> shell_comment = char_('#') >> *(char_ - '\n') >> (char_('\n') | omit[eoi]);
    qi::rule<iter, std::string()> comment = cpp_comment
            | c_comment
            | shell_comment
            ;

    std::string result;

    EXPECT_TRUE(qi::parse(b, e, comment, result));
    EXPECT_EQ(b, e);
    EXPECT_EQ(result, example);
}

失败并出现以下错误：

[----------] 1 test from TestBoost
[ RUN      ] TestBoost.cpp_comment
tests/spirit.cpp:56: Failure
      Expected: result
      Which is: "//* this should be ignored */"
To be equal to: example
      Which is: "/* this should be ignored */"
[  FAILED  ] TestBoost.cpp_comment (0 ms)
[----------] 1 test from TestBoost (0 ms total)

我不明白为什么。可能在 boost 文档中的某个地方提到了这种行为，但我找不到它。有人知道为什么会这样吗？

如果我这样写语义动作：

qi::rule<iter, std::string()> comment = cpp_comment[spi::_val = spi::_1]
            | c_comment[spi::_val = spi::_1]
            | shell_comment[spi::_val = spi::_1]
            ;

或者这个

qi::rule<iter, std::string()> comment = cpp_comment[spi::_val += spi::_1]
            | c_comment[spi::_val += spi::_1]
            | shell_comment[spi::_val += spi::_1]
            ;

它有效，但我真的很想知道为什么原始代码不起作用。

Answer 1

这是回溯容器属性的经典问题：

• boost::spirit::qi duplicate parsing on the output
• Parsing with Boost::Spirit (V2.4) into container

这里的想法是使用qi::hold，或者在这种情况下使用qi::raw 更好，因为看起来您想将整个匹配的输入序列公开为属性：

qi::rule<iter, std::string()>
      cpp_comment   = "//" >> *~char_('\n')   >> (eol|eoi),
      c_comment     = "/*" >> *(char_ - "*/") >> "*/",
      shell_comment = '#'  >> *~char_('\n')   >> (eol|eoi),
      comment       = qi::raw [ cpp_comment | c_comment | shell_comment ];

Live On Coliru

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

namespace qi = boost::spirit::qi;

void test() {
    using qi::char_;
    using qi::eol;
    using qi::eoi;

    std::string const example = "/* this should be ignored */";

    qi::rule<std::string::const_iterator, std::string()>
          cpp_comment   = "//" >> *~char_('\n')   >> (eol|eoi),
          c_comment     = "/*" >> *(char_ - "*/") >> "*/",
          shell_comment = '#'  >> *~char_('\n')   >> (eol|eoi),
          comment       = qi::raw [ cpp_comment | c_comment | shell_comment ];

    std::string result;

    bool ok = qi::parse(std::begin(example), std::end(example), comment >> eoi, result);
    assert(ok);

    std::cout << "expected: " << example << "\n";
    std::cout << "actual:   " << result << "\n";
    assert(result == example);
}

int main() {
    test();
}

打印

expected: /* this should be ignored */
actual:   /* this should be ignored */