我开始学习Boost.Spirit并完成阅读Qi - Writing Parsers部分。阅读时,一切都很容易理解。但是当我尝试做某事时,会出现很多错误,因为有太多的包含和命名空间,我需要知道何时包含/使用它们。作为练习,我想编写简单的INI解析器。
这是代码(包括来自Spirit lib中的一个示例,几乎所有其他内容):
#include <boost/config/warning_disable.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <boost/spirit/include/phoenix_stl.hpp>
#include <boost/fusion/adapted/std_pair.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/include/phoenix_object.hpp>
#include <iostream>
#include <string>
#include <vector>
#include <map>
namespace client
{
typedef std::map<std::string, std::string> key_value_map_t;
struct mini_ini
{
std::string name;
key_value_map_t key_values_map;
};
} // client
BOOST_FUSION_ADAPT_STRUCT(
client::mini_ini,
(std::string, name)
(client::key_value_map_t, key_values_map)
)
namespace client
{
namespace qi = boost::spirit::qi;
namespace ascii = boost::spirit::ascii;
namespace phoenix = boost::phoenix;
template <typename Iterator>
struct ini_grammar : qi::grammar<Iterator, mini_ini(), ascii::space_type>
{
ini_grammar() : ini_grammar::base_type(section_, "section")
{
using qi::char_;
using qi::on_error;
using qi::fail;
using namespace qi::labels;
using phoenix::construct;
using phoenix::val;
key_ = +char_("a-zA-Z_0-9");
pair_ = key_ >> '=' >> *char_;
section_ = '[' >> key_ >> ']' >> '\n' >> *(pair_ >> '\n');
key_.name("key");
pair_.name("pair");
section_.name("section");
on_error<fail>
(
section_
, std::cout
<< val("Error! Expecting ")
<< _4 // what failed?
<< val(" here: \"")
<< construct<std::string>(_3, _2) // iterators to error-pos, end
<< val("\"")
<< std::endl
);
}
qi::rule<Iterator, std::string(), ascii::space_type> key_;
qi::rule<Iterator, mini_ini(), ascii::space_type> section_;
qi::rule<Iterator, std::pair<std::string, std::string>(), ascii::space_type> pair_;
};
} // client
int
main()
{
std::string storage =
"[section]\n"
"key1=val1\n"
"key2=val2\n";
client::mini_ini ini;
typedef client::ini_grammar<std::string::const_iterator> ini_grammar;
ini_grammar grammar;
using boost::spirit::ascii::space;
std::string::const_iterator iter = storage.begin();
std::string::const_iterator end = storage.end();
bool r = phrase_parse(iter, end, grammar, space, ini);
if (r && iter == end)
{
std::cout << "-------------------------\n";
std::cout << "Parsing succeeded\n";
std::cout << "-------------------------\n";
return 0;
}
else
{
std::cout << "-------------------------\n";
std::cout << "Parsing failed\n";
std::cout << "-------------------------\n";
std::cout << std::string(iter, end) << "\n";
return 1;
}
return 0;
}
正如您所见,我想将下一个文本解析为mini_ini
struct:
"[section]"
"key1=val1"
"key2=val2";
我有失败,std::string(iter, end)
是完整的输入字符串。
我的问题:
on_error<fail>
处理程序?由于
答案 0 :(得分:2)
问。为什么我看到失败但没有看到on_error处理程序
on_error处理程序仅针对已注册的规则(section_)和expectation point is failed触发。
您的语法不包含期望点(仅使用>>
,而不是>
)。
问。你有什么建议如何学习Boost.Spirit(我在理论上对文档有很好的理解,但在实践中我有很多为什么?)
只需构建您需要的解析器。从文档和SO答案中复制好的约定。有很多。正如您所看到的,相当多的数据都包含Ini解析器的完整示例,其中包含不同级别的错误报告。
做更详细的状态报告:
bool ok = phrase_parse(iter, end, grammar, space, ini);
if (ok) {
std::cout << "Parse success\n";
} else {
std::cout << "Parse failure\n";
}
if (iter != end) {
std::cout << "Remaining unparsed: '" << std::string(iter, end) << "'\n";
}
return ok && (iter==end)? 0 : 1;
使用BOOST_SPIRIT_DEBUG:
#define BOOST_SPIRIT_DEBUG
// and later
BOOST_SPIRIT_DEBUG_NODES((key_)(pair_)(section_))
打印:
<section_>
<try>[section]\nkey1=val1\n</try>
<key_>
<try>section]\nkey1=val1\nk</try>
<success>]\nkey1=val1\nkey2=val</success>
<attributes>[[s, e, c, t, i, o, n]]</attributes>
</key_>
<fail/>
</section_>
Parse failure
Remaining unparsed: '[section]
key1=val1
key2=val2
'
您会注意到部分标题未被解析,因为换行符不匹配。您的船长(space_type
) 跳过 换行符,因此永远不会匹配:Boost spirit skipper issues
使用blank_type
作为船长时,您将获得成功的解析:
<section_>
<try>[section]\nkey1=val1\n</try>
<key_>
<try>section]\nkey1=val1\nk</try>
<success>]\nkey1=val1\nkey2=val</success>
<attributes>[[s, e, c, t, i, o, n]]</attributes>
</key_>
<pair_>
<try>key1=val1\nkey2=val2\n</try>
<key_>
<try>key1=val1\nkey2=val2\n</try>
<success>=val1\nkey2=val2\n</success>
<attributes>[[k, e, y, 1]]</attributes>
</key_>
<success></success>
<attributes>[[[k, e, y, 1], [v, a, l, 1,
, k, e, y, 2, =, v, a, l, 2,
]]]</attributes>
</pair_>
<success>key1=val1\nkey2=val2\n</success>
<attributes>[[[s, e, c, t, i, o, n], []]]</attributes>
</section_>
Parse success
Remaining unparsed: 'key1=val1
key2=val2
注意:解析成功,但没有做你想做的事。这是因为
*char_
包含换行符。那就做那个pair_ = key_ >> '=' >> *(char_ - qi::eol); // or pair_ = key_ >> '=' >> *~char_("\r\n"); // etc
<强> Live On Coliru 强>
#define BOOST_SPIRIT_DEBUG
#include <boost/config/warning_disable.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <boost/spirit/include/phoenix_stl.hpp>
#include <boost/fusion/adapted/std_pair.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/include/phoenix_object.hpp>
#include <iostream>
#include <string>
#include <vector>
#include <map>
namespace client
{
typedef std::map<std::string, std::string> key_value_map_t;
struct mini_ini
{
std::string name;
key_value_map_t key_values_map;
};
} // client
BOOST_FUSION_ADAPT_STRUCT(
client::mini_ini,
(std::string, name)
(client::key_value_map_t, key_values_map)
)
namespace client
{
namespace qi = boost::spirit::qi;
namespace ascii = boost::spirit::ascii;
namespace phoenix = boost::phoenix;
template <typename Iterator>
struct ini_grammar : qi::grammar<Iterator, mini_ini(), ascii::blank_type>
{
ini_grammar() : ini_grammar::base_type(section_, "section")
{
using qi::char_;
using qi::on_error;
using qi::fail;
using namespace qi::labels;
using phoenix::construct;
using phoenix::val;
key_ = +char_("a-zA-Z_0-9");
pair_ = key_ >> '=' >> *char_;
section_ = '[' >> key_ >> ']' >> '\n' >> *(pair_ >> '\n');
BOOST_SPIRIT_DEBUG_NODES((key_)(pair_)(section_))
on_error<fail>
(
section_
, std::cout
<< val("Error! Expecting ")
<< _4 // what failed?
<< val(" here: \"")
<< construct<std::string>(_3, _2) // iterators to error-pos, end
<< val("\"")
<< std::endl
);
}
qi::rule<Iterator, std::string(), ascii::blank_type> key_;
qi::rule<Iterator, mini_ini(), ascii::blank_type> section_;
qi::rule<Iterator, std::pair<std::string, std::string>(), ascii::blank_type> pair_;
};
} // client
int
main()
{
std::string storage =
"[section]\n"
"key1=val1\n"
"key2=val2\n";
client::mini_ini ini;
typedef client::ini_grammar<std::string::const_iterator> ini_grammar;
ini_grammar grammar;
using boost::spirit::ascii::blank;
std::string::const_iterator iter = storage.begin();
std::string::const_iterator end = storage.end();
bool ok = phrase_parse(iter, end, grammar, blank, ini);
if (ok) {
std::cout << "Parse success\n";
} else {
std::cout << "Parse failure\n";
}
if (iter != end) {
std::cout << "Remaining unparsed: '" << std::string(iter, end) << "'\n";
}
return ok && (iter==end)? 0 : 1;
}