我是 Boost Spirit 的新手，正在努力创建一个正确的表达式来解析以下输入(实际上是某些命令的标准输出的结果):

^+ line-17532.dyn.kponet.fi      2   7   377     1   +1503us[+9103us] +/-   55ms

我需要将其解析为一组字符串和整数并记录在变量中。该行的大部分内容应该被解析为适当类型(字符串或整数)的变量。所以最后，我得到:

string:  "^+", "line-17532.dyn.kponet.fi", "+1503us", "+9103us", "55ms"
int   :   2, 7, 377, 1 

一对

+1503us[+9103us] 

也可以带空格

+503us[ +103us] 

我需要将方括号之前和方括号中的内容放在单独的字符串中。

此外，时间指定可以表示为

ns, ms, us, s

我很欣赏有关如何处理它的示例，因为可用的文档非常稀疏且不连贯。

大块日志，以及描述各个字段的标题:

MS Name/IP address         Stratum Poll Reach LastRx Last sample               
===============================================================================
^+ ns2.sdi.fi                    2   9   377   381  -1476us[-1688us] +/-   72ms
^+ line-17532.dyn.kponet.fi      2  10   377   309   +302us[ +302us] +/-   59ms
^* heh.fi                        2  10   377   319  -1171us[-1387us] +/-   50ms
^+ stara.mulimuli.fi             3  10   377   705  -1253us[-1446us] +/-   73ms

最佳答案

一如既往，我从绘制有用的 AST 开始:

namespace AST {
    using clock = std::chrono::high_resolution_clock;

    struct TimeSample {
        enum Direction { up, down } direction; // + or -
        clock::duration value;
    };

    struct Record {
        std::string prefix; // "^+"
        std::string fqdn;   // "line-17532.dyn.kponet.fi"
        int a, b, c, d;     // 2, 7, 377, 1
        TimeSample primary, braced;
        clock::duration tolerance;
    };
}

现在我们知道我们想要解析什么，我们主要只是用规则模仿 AST，有点:

using namespace qi;

start     = skip(blank) [record_];

record_   = prefix_ >> fqdn_ >> int_ >> int_ >> int_ >> int_ >> sample_ >> '[' >> sample_ >> ']' >> tolerance_;

prefix_   = string("^+"); // or whatever you need to match here
fqdn_     = +graph; // or whatever additional constraints you have
sample_   = direction_ >> duration_;
duration_ = (long_ >> units_) [ _val = _1 * _2 ];
tolerance_= "+/-" >> duration_;

当然，有趣的是单位和方向:

struct directions : qi::symbols<char, AST::TimeSample::Direction> {
    directions() { add("+", AST::TimeSample::up)("-", AST::TimeSample::down); }
} direction_;
struct units : qi::symbols<char, AST::clock::duration> {
    units() {
        using namespace std::literals::chrono_literals;
        add("s", 1s)("ms", 1ms)("us", 1us)("µs", 1us)("ns", 1ns);
    }
} units_;

空白接受由 skipper 管理；我为非词素规则选择了qi::blank_type:

using Skipper = qi::blank_type;
qi::rule<It, AST::Record()> start;
qi::rule<It, AST::Record(), Skipper> record_;
qi::rule<It, AST::TimeSample(), Skipper> sample_;
qi::rule<It, AST::clock::duration(), Skipper> duration_, tolerance_;
// lexemes:
qi::rule<It, std::string()> prefix_;
qi::rule<It, std::string()> fqdn_;

演示

把它们放在一起，使用它:

int main() {
    std::istringstream iss(R"(^+ line-17532.dyn.kponet.fi      2   7   377     1   +1503us[+9103us] +/-   55ms
)");

    std::string line;

    while (getline(iss, line)) {
        auto f = line.cbegin(), l = line.cend();
        AST::Record record;
        if (parse(f, l, parser<>{}, record))
            std::cout << "parsed: " << boost::fusion::as_vector(record) << "\n";
        else
            std::cout << "parse error\n";

        if (f!=l)
            std::cout << "remaining unparsed input: '" << std::string(f,l) << "'\n";
    }
}

打印: Live On Coliru

parsed: (^+ line-17532.dyn.kponet.fi 2 7 377 1 +0.001503s +0.009103s 0.055s)

(下面的调试输出)

完整代码:

Live On Coliru

#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/fusion/adapted.hpp>
#include <sstream>
#include <chrono>

namespace std { namespace chrono {
    // for debug
    std::ostream& operator<<(std::ostream& os, duration<double> d) { return os << d.count() << "s"; }
} }

namespace AST {
    using clock = std::chrono::high_resolution_clock;

    struct TimeSample {
        enum Direction { up, down } direction; // + or -
        clock::duration value;

        // for debug:
        friend std::ostream& operator<<(std::ostream& os, Direction d) {
            char const* signs[] = {"+","-"};
            return os << signs[d];
        }
        friend std::ostream& operator<<(std::ostream& os, TimeSample const& sample) {
            return os << sample.direction << std::chrono::duration<double>(sample.value).count() << "s";
        }
    };

    struct Record {
        std::string prefix; // "^+"
        std::string fqdn;   // "line-17532.dyn.kponet.fi"
        int a, b, c, d;     // 2, 7, 377, 1
        TimeSample primary, braced;
        clock::duration tolerance;
    };
}

BOOST_FUSION_ADAPT_STRUCT(AST::Record, prefix, fqdn, a, b, c, d, primary, braced, tolerance)
BOOST_FUSION_ADAPT_STRUCT(AST::TimeSample, direction, value)

namespace qi = boost::spirit::qi;

template <typename It = std::string::const_iterator>
struct parser : qi::grammar<It, AST::Record()> {
    parser() : parser::base_type(start) {
        using namespace qi;

        start     = skip(blank) [record_];

        record_   = prefix_ >> fqdn_ >> int_ >> int_ >> int_ >> int_ >> sample_ >> '[' >> sample_ >> ']' >> tolerance_;

        prefix_   = string("^+"); // or whatever you need to match here
        fqdn_     = +graph; // or whatever additional constraints you have
        sample_   = direction_ >> duration_;
        duration_ = (long_ >> units_) [ _val = _1 * _2 ];
        tolerance_= "+/-" >> duration_;

        BOOST_SPIRIT_DEBUG_NODES(
                (start)(record_)
                (prefix_)(fqdn_)(sample_)(duration_)(tolerance_)
            )
    }
  private:
    struct directions : qi::symbols<char, AST::TimeSample::Direction> {
        directions() { add("+", AST::TimeSample::up)("-", AST::TimeSample::down); }
    } direction_;
    struct units : qi::symbols<char, AST::clock::duration> {
        units() {
            using namespace std::literals::chrono_literals;
            add("s", 1s)("ms", 1ms)("us", 1us)("µs", 1us)("ns", 1ns);
        }
    } units_;

    using Skipper = qi::blank_type;
    qi::rule<It, AST::Record()> start;
    qi::rule<It, AST::Record(), Skipper> record_;
    qi::rule<It, AST::TimeSample(), Skipper> sample_;
    qi::rule<It, AST::clock::duration(), Skipper> duration_, tolerance_;
    // lexemes:
    qi::rule<It, std::string()> prefix_;
    qi::rule<It, std::string()> fqdn_;
};

int main() {
    std::istringstream iss(R"(^+ line-17532.dyn.kponet.fi      2   7   377     1   +1503us[+9103us] +/-   55ms
)");

    std::string line;

    while (getline(iss, line)) {
        auto f = line.cbegin(), l = line.cend();
        AST::Record record;
        if (parse(f, l, parser<>{}, record))
            std::cout << "parsed: " << boost::fusion::as_vector(record) << "\n";
        else
            std::cout << "parse error\n";

        if (f!=l)
            std::cout << "remaining unparsed input: '" << std::string(f,l) << "'\n";
    }
}

调试输出

<start>
  <try>^+ line-17532.dyn.kp</try>
  <record_>
    <try>^+ line-17532.dyn.kp</try>
    <prefix_>
      <try>^+ line-17532.dyn.kp</try>
      <success> line-17532.dyn.kpon</success>
      <attributes>[[^, +]]</attributes>
    </prefix_>
    <fqdn_>
      <try>line-17532.dyn.kpone</try>
      <success>      2   7   377   </success>
      <attributes>[[l, i, n, e, -, 1, 7, 5, 3, 2, ., d, y, n, ., k, p, o, n, e, t, ., f, i]]</attributes>
    </fqdn_>
    <sample_>
      <try>   +1503us[+9103us] </try>
      <duration_>
        <try>1503us[+9103us] +/- </try>
        <success>[+9103us] +/-   55ms</success>
        <attributes>[0.001503s]</attributes>
      </duration_>
      <success>[+9103us] +/-   55ms</success>
      <attributes>[[+, 0.001503s]]</attributes>
    </sample_>
    <sample_>
      <try>+9103us] +/-   55ms</try>
      <duration_>
        <try>9103us] +/-   55ms</try>
        <success>] +/-   55ms</success>
        <attributes>[0.009103s]</attributes>
      </duration_>
      <success>] +/-   55ms</success>
      <attributes>[[+, 0.009103s]]</attributes>
    </sample_>
    <tolerance_>
      <try> +/-   55ms</try>
      <duration_>
        <try>   55ms</try>
        <success></success>
        <attributes>[0.055s]</attributes>
      </duration_>
      <success></success>
      <attributes>[0.055s]</attributes>
    </tolerance_>
    <success></success>
    <attributes>[[[^, +], [l, i, n, e, -, 1, 7, 5, 3, 2, ., d, y, n, ., k, p, o, n, e, t, ., f, i], 2, 7, 377, 1, [+, 0.001503s], [+, 0.009103s], 0.055s]]</attributes>
  </record_>
  <success></success>
  <attributes>[[[^, +], [l, i, n, e, -, 1, 7, 5, 3, 2, ., d, y, n, ., k, p, o, n, e, t, ., f, i], 2, 7, 377, 1, [+, 0.001503s], [+, 0.009103s], 0.055s]]</attributes>
</start>

关于c++ - 使用 Boost Spirit Qi 解析特定字符串，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/42888172/