Boost.Xpressiveの落書き

• boost::regexとboost::spiritをまとめて置きかえるライブラリであるらしい
• ヘッダーのみのライブラリでビルドは必要ない
• 正規表現を文字からではなく、オブジェクトから組み立てる(文字列の正規表現も扱える)

[]#include[][] "stdafx.h"[]
[]#include[][] <sstream>[]

[]#include[][] <iostream>[]

[]#include[][] <fstream>[]

[]#include[][] <cassert>[]

[]#include[][] <iterator>[]

[]#include[][] <boost/xpressive/xpressive_static.hpp>[]

[]namespace[] {

  []using[] []namespace[] []boost[]::[]xpressive[];
  []// regex[]

  []wsregex[] []re_cpp_comment[] = []L[][]"//"[] >> *~[]_n[];

  []wsregex[] []re_c_comment[] = []L[][]"/*"[] >> !*[]_[] >> []L[][]"*/"[];
  []wchar_t[] []sq[] = []L[][]'\''[];

  []wchar_t[] []dq[] = []L[][]'"'[];

  []wchar_t[] []em[] = []L[][]'\\'[];

  []wsregex[] []re_ec[] = []em[] >> []_[];

  []wsregex[] []re_char_literal[] = []sq[] >> *(~([]set[]=[]sq[],[]em[])|[]re_ec[]) >> []sq[];

  []wsregex[] []re_string_literal[] = []dq[] >> *(~([]set[]=[]dq[],[]em[])|[]re_ec[]) >> []dq[];
  []using[] []namespace[] []std[];
  []// format[]

  []wstring[] []fmt_whole[]([]L[][]"<pre class=cpp_source>$1</pre>"[]);
  []mark_tag[] []comment[](1), []string_literal[](2), []other[](3);

  []wstring[] []fmt_comment[]([]L[][]"<span class=cpp_comment>$1</span>"[]);

  []wstring[] []fmt_string_literal[]([]L[][]"<span class=cpp_string_literal>$1</span>"[]);


  []// grammer[]

  []wsregex[] []re_cpp_code[] =

    ( []comment[] = ([]re_cpp_comment[]) ) |

    ( []string_literal[] = ([]re_char_literal[]|[]re_string_literal[]) )

  ;

  

  []wstring[] []xml_escape_replace[]([]wstring[] []const[]& []src[]) {

    []wstring[] []out[] = []src[];

    []out[] = []regex_replace[]([]out[], []L[][]"&"[] >> []epsilon[], []wstring[]([]L[][]"&amp;"[]));

    []out[] = []regex_replace[]([]out[], []L[][]"<"[] >> []epsilon[], []wstring[]([]L[][]"&lt;"[]));

    []out[] = []regex_replace[]([]out[], []L[][]">"[] >> []epsilon[], []wstring[]([]L[][]"&gt;"[]));

    []out[] = []regex_replace[]([]out[], []L[][]"\""[] >> []epsilon[], []wstring[]([]L[][]"&quot;"[]));
    []out[] = []regex_replace[]([]out[], []L[][]"]"[] >> []epsilon[], []wstring[]([]L[][]"&#93;"[]));

    []out[] = []regex_replace[]([]out[], []L[][]"["[] >> []epsilon[], []wstring[]([]L[][]"&#91;"[]));

    []return[] []out[];

  }
  []// the parse[]

  []void[] []cpp_parse[]([]char[] []const[]* []filename[]) {

    []// open input file[]

    []wifstream[] []fin[]([]filename[]);

    []assert[]([]fin[].[]good[]());
    []wstring[] []in[];

    []getline[]([]fin[], []in[], []L[][]'\0'[]);
    []// wstring output = regex_replace(input, re_cpp_code, fmt_cpp_code);[]
    []wstringstream[] []out[];
    []wsregex_iterator[] []cur[]([]in[].[]begin[](), []in[].[]end[](), []re_cpp_code[]); []// trigger[]

    []wstring[]::[]const_iterator[] []first_pos[] = []in[].[]begin[]();

    []wsregex_iterator[] []end[];

    []for[]( ; []cur[] != []end[]; ++[]cur[])

    {

      []wsmatch[] []const[]& []what[] = *[]cur[];

      []// pass unmatched string to output[]

      []wstring[]::[]const_iterator[] []last_pos[] = []in[].[]begin[]();

      []advance[]([]last_pos[], []what[].[]position[](0));

      []out[] << []xml_escape_replace[]([]wstring[]([]first_pos[], []last_pos[]));

      []// update first_pos[]

      []first_pos[] = []last_pos[];

      []advance[]([]first_pos[], []what[].[]length[](0));
      []wstring[] []str[];

      []if[] ([]what[][[]comment[]]) {

        []// Note. I can't understand why format_first_only required...if you miss it,[]

        []//       ABC ---> <span>ABC</span><span></span>[]

        []str[] = []what[][[]comment[]].[]str[]();

        []str[] = []xml_escape_replace[]([]str[]);

        []str[] = []regex_replace[]([]str[], ([]s1[]=*[]_[]), []fmt_comment[], []regex_constants[]::[]format_first_only[]);

  

      } []else[] []if[] ([]what[][[]string_literal[]]) {

        []str[] = []what[][[]string_literal[]].[]str[]();

        []str[] = []xml_escape_replace[]([]str[]);

        []str[] = []regex_replace[]([]str[], ([]s1[]=*[]_[]), []fmt_string_literal[], []regex_constants[]::[]format_first_only[]);

      } []else[] {

        []assert[]([]false[]);

      }
      []out[] << []str[];

    }
    []out[] << []wstring[]( []first_pos[], []in[].[]end[]() );

  

    []wstring[] []result[] = []out[].[]str[]();

    []result[] = []regex_replace[]([]result[], ([]s1[]=*[]_[]), []fmt_whole[], []regex_constants[]::[]format_first_only[]);
    []// open output file[]

    []string[] []out_name[]([]filename[]);

    []out_name[] += []".html"[];

    []wofstream[] []fout[]([]out_name[].[]c_str[]());

    []assert[]([]fout[].[]good[]());

    []fout[] << []result[];

  }

}
[]int[] []main[]([]int[] []argc[], []char[]* []argv[][])

{

  []std[]::[]locale[]::[]global[]([]std[]::[]locale[]([]"ja"[]));
  []if[] ([]argc[] > 1) {

    []for[] ([]int[] []i[] = 1; []i[] < []argc[]; ++[]i[]) {

      []cout[] << []argv[][[]i[]] << []endl[];

      []cpp_parse[]([]argv[][[]i[]]);

    }

  } []else[] {

      []cerr[] << []"---NO FILENAME GIVEN---"[] << []endl[];

  }

  []wcin[].[]ignore[]();

  []return[] 0;

}