Created
January 23, 2012 16:36
-
-
Save hecomi/1664139 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <iostream> | |
#include <string> | |
#include <boost/spirit/include/qi.hpp> | |
#include <boost/spirit/include/phoenix.hpp> | |
#include <boost/spirit/include/phoenix_stl.hpp> | |
#include <boost/format.hpp> | |
namespace qi = boost::spirit::qi; | |
namespace phx = boost::phoenix; | |
namespace sw = qi::standard_wide; | |
// 結果を格納する型(2次元 string テーブル) | |
typedef std::vector<std::vector<std::string>> str_2d_array; | |
/* ------------------------------------------------------------------------- */ | |
// Parser | |
// string: "(a|b|c)d(e|f)g" --> str_2d_array: { {a,b,c}, d, {e,f}, g} | |
/* ------------------------------------------------------------------------- */ | |
template <typename Iterator> | |
bool command_parse(Iterator first, Iterator last, str_2d_array& result) | |
{ | |
using sw::char_; | |
using qi::_1; | |
using qi::lit; | |
qi::rule<Iterator, std::string(), sw::space_type> word, words, sentence; | |
std::vector<std::string> buf; | |
word = +( char_ - '(' - '|' - ')' ); | |
words = -lit('(') | |
>> ( word [phx::push_back(phx::ref(buf), _1)] % '|' ) | |
>> -lit("|)") [phx::push_back(phx::ref(buf), "")] | |
>> -lit(')'); | |
sentence = *( | |
words | |
[phx::push_back(phx::ref(result), phx::ref(buf))] | |
[phx::clear(phx::ref(buf))] | |
) | |
>> qi::eol; | |
bool r = qi::phrase_parse(first, last, sentence, sw::space); | |
if (!r || first != last) { | |
return false; | |
} | |
return true; | |
} | |
/* ------------------------------------------------------------------------- */ | |
// main 関数(テスト用) | |
/* ------------------------------------------------------------------------- */ | |
int main(int argc, char const* argv[]) | |
{ | |
std::string str = "(電気|ライト)(を|)(オン|オフ|つけて|消して)"; | |
std::string::const_iterator iter = str.begin(), end = str.end(); | |
str_2d_array sentences; | |
if (command_parse(iter, end, sentences)) { | |
std::cout << "failed" << std::endl; | |
return 1; | |
} | |
std::cout << "kaden.grammar" << std::endl; | |
std::cout << "S\t: NS_B "; | |
for (size_t i = 0; i < sentences.size(); ++i) { | |
std::cout << boost::format("WORD%1% ") % i; | |
} | |
std::cout << "NS_E\n\n"; | |
std::cout << "kaden.voca" << std::endl; | |
int n = 0; | |
for (const auto& sentence : sentences) { | |
std::cout << boost::format("%% WORD%1%\n") % n++; | |
for (const auto& x : sentence) { | |
std::cout << boost::format("%1%\t%2%\n") % ( (x=="") ? "<sp>" : x ) % "d u m m y"; | |
} | |
} | |
std::cout << | |
"% NS_B\n" | |
"<s>\tsilB\n" | |
"% NS_E\n" | |
"<s>\tsilE\n"; | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
kaden.grammar
S : NS_B WORD0 WORD1 WORD2 NS_E
kaden.voca
% WORD0
電気 d u m m y
ライト d u m m y
% WORD1
を d u m m y
<sp> d u m m y
% WORD2
オン d u m m y
オフ d u m m y
つけて d u m m y
消して d u m m y
% NS_B
<s>silB
% NS_E
<s>silE