boost::spirit::qi::parse 语法没有按预期工作
boost::spirit::qi::parse grammar not working as expected
我尝试编写一个语法来解析以下语法:
// - command
// - command value0 ... valueN
// - command -arg0 ... -argN
// - command -arg0 value0 ... valueN ... -argN value0 ... valueN
- 每个元素都应解释为一个字符串
- 在字符串中允许所有符号
- 命令、参数和值之间允许有多个空格
- 参数总是以“-”开头
结果应存储在结构中:
struct Data
{
std::string m_command;
std::map< std::string, std::vector< std::string > m_arg;
}
- m_command 应存储已解析的命令
- m_arg 应将解析的参数和相应的值存储在向量中
我在一个简短的示例中添加了我当前的语法 here
我的问题:
矢量包含的条目多于可用值,因为空白也被解释为值
不太清楚你希望语法如何运作¹,但从目标数据结构来看,我觉得事情可以通过
大大简化
- 使用船长(背景见Boost spirit skipper issues)
使用自动属性传播而不是 phoenix(另请参阅 Boost Spirit: "Semantic actions are evil"?)。
token = +~char_("\r\n -");
values = +token;
//
entry = (lexeme['-' >> token] >> -values | attr("empty") >> values);
args = *entry;
//
data = skip(qi::blank) [ token >> args ];
在下面的示例中,我使用 Fusion 适配来启用自动属性传播(它立即启用调试输出
#define BOOST_SPIRIT_DEBUG
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <map>
#include <string>
#include <vector>
// Structure stores the parsed command line information:
struct CmdData
{
typedef std::string Name;
typedef std::string ArgName;
typedef std::string Value;
typedef std::vector<Value> Values; // Type defines a list of values:
typedef std::map<ArgName, Values> Args; // Type defines a map storing the relation between a argument and the corresponding values:
Name cmd; // Stores the command name as a string.
Args arg; // Stores the arguments and the corresponding values as strings.
};
BOOST_FUSION_ADAPT_STRUCT(CmdData, (CmdData::Name, cmd)(CmdData::Args, arg))
namespace Grammar
{
namespace qi = boost::spirit::qi;
// This class implements the grammar used to parse a command line.
// The expected format is as follows:
// - command
// - command value0 ... valueN
// - command -arg0 ... -argN
// - command -arg0 value0 ... valueN ... -argN value0 ... valueN
template <typename It>
struct decode : qi::grammar<It, CmdData()>
{
decode() : decode::base_type(data)
{
using namespace qi;
token = +~char_("\r\n -");
values = +token;
//
entry = (lexeme['-' >> token] >> -values | attr("empty") >> values);
args = *entry;
//
data = skip(qi::blank) [ token >> args ];
BOOST_SPIRIT_DEBUG_NODES( (token)(values)(entry)(args)(data) )
}
private:
qi::rule<It, CmdData()> data;
// The following variables define the rules used within this grammar:
typedef std::pair<CmdData::ArgName, CmdData::Values> Entry;
qi::rule<It, CmdData::Values(), qi::blank_type> values;
qi::rule<It, Entry(), qi::blank_type> entry;
qi::rule<It, CmdData::Args(), qi::blank_type> args;
// lexemes
qi::rule<It, std::string()> token;
};
} // namespace
bool parse(const std::string& in)
{
CmdData data;
// Create an instance of the used grammar:
Grammar::decode<std::string::const_iterator> gr;
// Try to parse the data stored within the stream according the grammar and store the result in the tag variable:
bool b = boost::spirit::qi::parse(in.begin(), in.end(), gr, data);
std::cout << "Parsing: '" << in << "' ok: " << std::boolalpha << b << "\n";
if (b)
std::cout << "Entries parsed: " << data.arg.size() << "\n";
return b;
}
int main()
{
parse(" cmd0");
parse(" cmd0 -23.0 value0 value1 value2");
parse(" cmd0 -arg0 -arg1 -arg2");
parse(" cmd0 -arg0 value0 -arg1 value0 value1 -arg2 value0 value1 value2");
}
版画
Parsing: ' cmd0' ok: true
Entries parsed: 0
Parsing: ' cmd0 -23.0 value0 value1 value2' ok: true
Entries parsed: 1
Parsing: ' cmd0 -arg0 -arg1 -arg2' ok: true
Entries parsed: 3
Parsing: ' cmd0 -arg0 value0 -arg1 value0 value1 -arg2 value0 value1 value2' ok: true
Entries parsed: 3
(禁用调试输出)
¹(例如 -23.0
是否明确表示为一个选项)
我尝试编写一个语法来解析以下语法:
// - command
// - command value0 ... valueN
// - command -arg0 ... -argN
// - command -arg0 value0 ... valueN ... -argN value0 ... valueN
- 每个元素都应解释为一个字符串
- 在字符串中允许所有符号
- 命令、参数和值之间允许有多个空格
- 参数总是以“-”开头
结果应存储在结构中:
struct Data { std::string m_command; std::map< std::string, std::vector< std::string > m_arg; }
- m_command 应存储已解析的命令
- m_arg 应将解析的参数和相应的值存储在向量中
我在一个简短的示例中添加了我当前的语法 here
我的问题:
矢量包含的条目多于可用值,因为空白也被解释为值
不太清楚你希望语法如何运作¹,但从目标数据结构来看,我觉得事情可以通过
大大简化- 使用船长(背景见Boost spirit skipper issues)
使用自动属性传播而不是 phoenix(另请参阅 Boost Spirit: "Semantic actions are evil"?)。
token = +~char_("\r\n -"); values = +token; // entry = (lexeme['-' >> token] >> -values | attr("empty") >> values); args = *entry; // data = skip(qi::blank) [ token >> args ];
在下面的示例中,我使用 Fusion 适配来启用自动属性传播(它立即启用调试输出
#define BOOST_SPIRIT_DEBUG
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <map>
#include <string>
#include <vector>
// Structure stores the parsed command line information:
struct CmdData
{
typedef std::string Name;
typedef std::string ArgName;
typedef std::string Value;
typedef std::vector<Value> Values; // Type defines a list of values:
typedef std::map<ArgName, Values> Args; // Type defines a map storing the relation between a argument and the corresponding values:
Name cmd; // Stores the command name as a string.
Args arg; // Stores the arguments and the corresponding values as strings.
};
BOOST_FUSION_ADAPT_STRUCT(CmdData, (CmdData::Name, cmd)(CmdData::Args, arg))
namespace Grammar
{
namespace qi = boost::spirit::qi;
// This class implements the grammar used to parse a command line.
// The expected format is as follows:
// - command
// - command value0 ... valueN
// - command -arg0 ... -argN
// - command -arg0 value0 ... valueN ... -argN value0 ... valueN
template <typename It>
struct decode : qi::grammar<It, CmdData()>
{
decode() : decode::base_type(data)
{
using namespace qi;
token = +~char_("\r\n -");
values = +token;
//
entry = (lexeme['-' >> token] >> -values | attr("empty") >> values);
args = *entry;
//
data = skip(qi::blank) [ token >> args ];
BOOST_SPIRIT_DEBUG_NODES( (token)(values)(entry)(args)(data) )
}
private:
qi::rule<It, CmdData()> data;
// The following variables define the rules used within this grammar:
typedef std::pair<CmdData::ArgName, CmdData::Values> Entry;
qi::rule<It, CmdData::Values(), qi::blank_type> values;
qi::rule<It, Entry(), qi::blank_type> entry;
qi::rule<It, CmdData::Args(), qi::blank_type> args;
// lexemes
qi::rule<It, std::string()> token;
};
} // namespace
bool parse(const std::string& in)
{
CmdData data;
// Create an instance of the used grammar:
Grammar::decode<std::string::const_iterator> gr;
// Try to parse the data stored within the stream according the grammar and store the result in the tag variable:
bool b = boost::spirit::qi::parse(in.begin(), in.end(), gr, data);
std::cout << "Parsing: '" << in << "' ok: " << std::boolalpha << b << "\n";
if (b)
std::cout << "Entries parsed: " << data.arg.size() << "\n";
return b;
}
int main()
{
parse(" cmd0");
parse(" cmd0 -23.0 value0 value1 value2");
parse(" cmd0 -arg0 -arg1 -arg2");
parse(" cmd0 -arg0 value0 -arg1 value0 value1 -arg2 value0 value1 value2");
}
版画
Parsing: ' cmd0' ok: true
Entries parsed: 0
Parsing: ' cmd0 -23.0 value0 value1 value2' ok: true
Entries parsed: 1
Parsing: ' cmd0 -arg0 -arg1 -arg2' ok: true
Entries parsed: 3
Parsing: ' cmd0 -arg0 value0 -arg1 value0 value1 -arg2 value0 value1 value2' ok: true
Entries parsed: 3
(禁用调试输出)
¹(例如 -23.0
是否明确表示为一个选项)