我有一个记录解析器,它会抛出几个异常之一来指示哪个规则失败。
前面的事情:
#include <iostream>
#include <sstream>
#include <stdexcept>
#include <string>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/spirit/include/classic_position_iterator.hpp>
using namespace boost::spirit;
using namespace boost::spirit::ascii;
using namespace boost::spirit::qi;
using namespace boost::spirit::qi::labels;
using boost::phoenix::function;
using boost::phoenix::ref;
using boost::spirit::qi::eol;
using boost::spirit::qi::fail;
using boost::spirit::qi::lit;
using boost::spirit::qi::on_error;
using BOOST_SPIRIT_CLASSIC_NS::file_position;
using BOOST_SPIRIT_CLASSIC_NS::position_iterator;
我们使用position_iterator
中的Spirit.Classic,因此以下流插入运算符非常方便。
std::ostream&
operator<<(std::ostream& o, const file_position &fp)
{
o << fp.file << ": " << fp.line << ',' << fp.column;
return o;
}
模板err_t
会导致抛出与不同形式的解析失败相关的异常的样板。
template <typename Exception>
struct err_t {
template <typename, typename, typename>
struct result { typedef void type; };
template <typename Iterator>
void operator() (info const &what, Iterator errPos, Iterator last) const
{
std::stringstream ss;
ss << errPos.get_position()
<< ": expecting " << what
<< " near '" << std::string(errPos, last) << "'\n";
throw Exception(ss.str());
}
};
与err_t
包装器一起使用的例外:
class MissingA : public std::runtime_error {
public: MissingA(const std::string &s) : std::runtime_error(s) {}
};
class MissingB : public std::runtime_error {
public: MissingB(const std::string &s) : std::runtime_error(s) {}
};
class MissingC : public std::runtime_error {
public: MissingC(const std::string &s) : std::runtime_error(s) {}
};
function<err_t<MissingA> > const missingA = err_t<MissingA>();
function<err_t<MissingB> > const missingB = err_t<MissingB>();
function<err_t<MissingC> > const missingC = err_t<MissingC>();
function<err_t<std::runtime_error> > const other_error =
err_t<std::runtime_error>();
语法寻找简单的序列。如果没有eps
,则start
规则会在空输入上失败而不是a
。
template <typename Iterator, typename Skipper>
struct my_grammar
: grammar<Iterator, Skipper>
{
my_grammar(int &result)
: my_grammar::base_type(start)
, result(result)
{
a = eps > lit("Header A") > eol;
b = eps > lit("Header B") > eol;
c = eps > lit("C:") > int_[ref(result) = _1] > eol;
start = a > b > c;
a.name("A");
b.name("B");
c.name("C");
on_error<fail>(start, other_error(_4, _3, _2));
on_error<fail>(a, missingA(_4, _3, _2));
on_error<fail>(b, missingB(_4, _3, _2));
on_error<fail>(c, missingC(_4, _3, _2));
}
rule<Iterator, Skipper> start;
rule<Iterator, Skipper> a;
rule<Iterator, Skipper> b;
rule<Iterator, Skipper> c;
int &result;
};
在my_parse
中,我们会将流的内容转储到std::string
并使用position_iterator
来跟踪解析的位置。
int
my_parse(const std::string &path, std::istream &is)
{
std::string buf;
is.unsetf(std::ios::skipws);
std::copy(std::istream_iterator<char>(is),
std::istream_iterator<char>(),
std::back_inserter(buf));
typedef position_iterator<std::string::const_iterator> itertype;
typedef my_grammar<itertype, boost::spirit::ascii::space_type> grammar;
itertype it(buf.begin(), buf.end(), path);
itertype end;
int result;
grammar g(result);
bool r = phrase_parse(it, end, g, boost::spirit::ascii::space);
if (r && it == end) {
std::cerr << "success!\n";
return result;
}
else {
file_position fpos = it.get_position();
std::cerr << "parse failed at " << fpos << '\n';
return -9999;
}
}
最后,主程序
int main()
{
std::stringstream ss;
ss << "Header A\n"
<< "Header B\n"
<< "C: 3\n";
int val = my_parse("path", ss);
std::cout << "val = " << val << '\n';
return 0;
}
上面的代码抛出MissingA
:
terminate called after throwing an instance of 'MissingA' what(): path: 2,1: expecting near 'Header B C: 3 '
我认为船长可能已经使用了换行符,但尝试lexeme[eol]
却产生了相同的结果。
我必须遗漏一些明显的东西,因为这似乎是最难处理的解析器之一。我做错了什么?