icu.cpp

来自「Boost provides free peer-reviewed portab」· C++ 代码 · 共 496 行 · 第 1/2 页

/*
 *
 * Copyright (c) 2004
 * John Maddock
 *
 * Use, modification and distribution are subject to the 
 * Boost Software License, Version 1.0. (See accompanying file 
 * LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
 *
 */

 /*
  *   LOCATION:    see http://www.boost.org for most recent version.
  *   FILE         icu.cpp
  *   VERSION      see <boost/version.hpp>
  *   DESCRIPTION: Unicode regular expressions on top of the ICU Library.
  */
#define BOOST_REGEX_SOURCE

#include <boost/regex/config.hpp>
#ifdef BOOST_HAS_ICU
#define BOOST_REGEX_ICU_INSTANTIATE
#include <boost/regex/icu.hpp>

namespace boost{

namespace re_detail{

icu_regex_traits_implementation::string_type icu_regex_traits_implementation::do_transform(const char_type* p1, const char_type* p2, const U_NAMESPACE_QUALIFIER Collator* pcoll) const
{
   // TODO make thread safe!!!! :
   typedef u32_to_u16_iterator<const char_type*, ::UChar> itt;
   itt i(p1), j(p2);
#ifndef BOOST_NO_TEMPLATED_ITERATOR_CONSTRUCTORS
   std::vector< ::UChar> t(i, j);
#else
   std::vector< ::UChar> t;
   while(i != j)
      t.push_back(*i++);
#endif
   ::uint8_t result[100];
   ::int32_t len;
   if(t.size())
      len = pcoll->getSortKey(&*t.begin(), static_cast< ::int32_t>(t.size()), result, sizeof(result));
   else
      len = pcoll->getSortKey(static_cast<UChar const*>(0), static_cast< ::int32_t>(0), result, sizeof(result));
   if(std::size_t(len) > sizeof(result))
   {
      scoped_array< ::uint8_t> presult(new ::uint8_t[len+1]);
      if(t.size())
         len = pcoll->getSortKey(&*t.begin(), static_cast< ::int32_t>(t.size()), presult.get(), len+1);
      else
         len = pcoll->getSortKey(static_cast<UChar const*>(0), static_cast< ::int32_t>(0), presult.get(), len+1);
      if((0 == presult[len-1]) && (len > 1))
         --len;
#ifndef BOOST_NO_TEMPLATED_ITERATOR_CONSTRUCTORS
      return string_type(presult.get(), presult.get()+len);
#else
      string_type sresult;
      ::uint8_t const* ia = presult.get();
      ::uint8_t const* ib = presult.get()+len;
      while(ia != ib)
         sresult.push_back(*ia++);
      return sresult;
#endif
   }
   if((0 == result[len-1]) && (len > 1))
      --len;
#ifndef BOOST_NO_TEMPLATED_ITERATOR_CONSTRUCTORS
   return string_type(result, result+len);
#else
   string_type sresult;
   ::uint8_t const* ia = result;
   ::uint8_t const* ib = result+len;
   while(ia != ib)
      sresult.push_back(*ia++);
   return sresult;
#endif
}

}

icu_regex_traits::size_type icu_regex_traits::length(const char_type* p)
{
   size_type result = 0;
   while(*p)
   {
      ++p;
      ++result;
   }
   return result;
}

//
// define our bitmasks:
//
const icu_regex_traits::char_class_type icu_regex_traits::mask_blank = icu_regex_traits::char_class_type(1) << offset_blank;
const icu_regex_traits::char_class_type icu_regex_traits::mask_space = icu_regex_traits::char_class_type(1) << offset_space;
const icu_regex_traits::char_class_type icu_regex_traits::mask_xdigit = icu_regex_traits::char_class_type(1) << offset_xdigit;
const icu_regex_traits::char_class_type icu_regex_traits::mask_underscore = icu_regex_traits::char_class_type(1) << offset_underscore;
const icu_regex_traits::char_class_type icu_regex_traits::mask_unicode = icu_regex_traits::char_class_type(1) << offset_unicode;
const icu_regex_traits::char_class_type icu_regex_traits::mask_any = icu_regex_traits::char_class_type(1) << offset_any;
const icu_regex_traits::char_class_type icu_regex_traits::mask_ascii = icu_regex_traits::char_class_type(1) << offset_ascii;

icu_regex_traits::char_class_type icu_regex_traits::lookup_icu_mask(const ::UChar32* p1, const ::UChar32* p2)
{
   static const ::UChar32 prop_name_table[] = {
      /* any */  'a', 'n', 'y', 
      /* ascii */  'a', 's', 'c', 'i', 'i', 
      /* assigned */  'a', 's', 's', 'i', 'g', 'n', 'e', 'd', 
      /* c* */  'c', '*', 
      /* cc */  'c', 'c', 
      /* cf */  'c', 'f', 
      /* closepunctuation */  'c', 'l', 'o', 's', 'e', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* cn */  'c', 'n', 
      /* co */  'c', 'o', 
      /* connectorpunctuation */  'c', 'o', 'n', 'n', 'e', 'c', 't', 'o', 'r', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* control */  'c', 'o', 'n', 't', 'r', 'o', 'l', 
      /* cs */  'c', 's', 
      /* currencysymbol */  'c', 'u', 'r', 'r', 'e', 'n', 'c', 'y', 's', 'y', 'm', 'b', 'o', 'l', 
      /* dashpunctuation */  'd', 'a', 's', 'h', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* decimaldigitnumber */  'd', 'e', 'c', 'i', 'm', 'a', 'l', 'd', 'i', 'g', 'i', 't', 'n', 'u', 'm', 'b', 'e', 'r', 
      /* enclosingmark */  'e', 'n', 'c', 'l', 'o', 's', 'i', 'n', 'g', 'm', 'a', 'r', 'k', 
      /* finalpunctuation */  'f', 'i', 'n', 'a', 'l', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* format */  'f', 'o', 'r', 'm', 'a', 't', 
      /* initialpunctuation */  'i', 'n', 'i', 't', 'i', 'a', 'l', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* l* */  'l', '*', 
      /* letter */  'l', 'e', 't', 't', 'e', 'r', 
      /* letternumber */  'l', 'e', 't', 't', 'e', 'r', 'n', 'u', 'm', 'b', 'e', 'r', 
      /* lineseparator */  'l', 'i', 'n', 'e', 's', 'e', 'p', 'a', 'r', 'a', 't', 'o', 'r', 
      /* ll */  'l', 'l', 
      /* lm */  'l', 'm', 
      /* lo */  'l', 'o', 
      /* lowercaseletter */  'l', 'o', 'w', 'e', 'r', 'c', 'a', 's', 'e', 'l', 'e', 't', 't', 'e', 'r', 
      /* lt */  'l', 't', 
      /* lu */  'l', 'u', 
      /* m* */  'm', '*', 
      /* mark */  'm', 'a', 'r', 'k', 
      /* mathsymbol */  'm', 'a', 't', 'h', 's', 'y', 'm', 'b', 'o', 'l', 
      /* mc */  'm', 'c', 
      /* me */  'm', 'e', 
      /* mn */  'm', 'n', 
      /* modifierletter */  'm', 'o', 'd', 'i', 'f', 'i', 'e', 'r', 'l', 'e', 't', 't', 'e', 'r', 
      /* modifiersymbol */  'm', 'o', 'd', 'i', 'f', 'i', 'e', 'r', 's', 'y', 'm', 'b', 'o', 'l', 
      /* n* */  'n', '*', 
      /* nd */  'n', 'd', 
      /* nl */  'n', 'l', 
      /* no */  'n', 'o', 
      /* nonspacingmark */  'n', 'o', 'n', 's', 'p', 'a', 'c', 'i', 'n', 'g', 'm', 'a', 'r', 'k', 
      /* notassigned */  'n', 'o', 't', 'a', 's', 's', 'i', 'g', 'n', 'e', 'd', 
      /* number */  'n', 'u', 'm', 'b', 'e', 'r', 
      /* openpunctuation */  'o', 'p', 'e', 'n', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* other */  'o', 't', 'h', 'e', 'r', 
      /* otherletter */  'o', 't', 'h', 'e', 'r', 'l', 'e', 't', 't', 'e', 'r', 
      /* othernumber */  'o', 't', 'h', 'e', 'r', 'n', 'u', 'm', 'b', 'e', 'r', 
      /* otherpunctuation */  'o', 't', 'h', 'e', 'r', 'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* othersymbol */  'o', 't', 'h', 'e', 'r', 's', 'y', 'm', 'b', 'o', 'l', 
      /* p* */  'p', '*', 
      /* paragraphseparator */  'p', 'a', 'r', 'a', 'g', 'r', 'a', 'p', 'h', 's', 'e', 'p', 'a', 'r', 'a', 't', 'o', 'r', 
      /* pc */  'p', 'c', 
      /* pd */  'p', 'd', 
      /* pe */  'p', 'e', 
      /* pf */  'p', 'f', 
      /* pi */  'p', 'i', 
      /* po */  'p', 'o', 
      /* privateuse */  'p', 'r', 'i', 'v', 'a', 't', 'e', 'u', 's', 'e', 
      /* ps */  'p', 's', 
      /* punctuation */  'p', 'u', 'n', 'c', 't', 'u', 'a', 't', 'i', 'o', 'n', 
      /* s* */  's', '*', 
      /* sc */  's', 'c', 
      /* separator */  's', 'e', 'p', 'a', 'r', 'a', 't', 'o', 'r', 
      /* sk */  's', 'k', 
      /* sm */  's', 'm', 
      /* so */  's', 'o', 
      /* spaceseparator */  's', 'p', 'a', 'c', 'e', 's', 'e', 'p', 'a', 'r', 'a', 't', 'o', 'r', 
      /* spacingcombiningmark */  's', 'p', 'a', 'c', 'i', 'n', 'g', 'c', 'o', 'm', 'b', 'i', 'n', 'i', 'n', 'g', 'm', 'a', 'r', 'k', 
      /* surrogate */  's', 'u', 'r', 'r', 'o', 'g', 'a', 't', 'e', 
      /* symbol */  's', 'y', 'm', 'b', 'o', 'l', 
      /* titlecase */  't', 'i', 't', 'l', 'e', 'c', 'a', 's', 'e', 
      /* titlecaseletter */  't', 'i', 't', 'l', 'e', 'c', 'a', 's', 'e', 'l', 'e', 't', 't', 'e', 'r', 
      /* uppercaseletter */  'u', 'p', 'p', 'e', 'r', 'c', 'a', 's', 'e', 'l', 'e', 't', 't', 'e', 'r', 
      /* z* */  'z', '*', 
      /* zl */  'z', 'l', 
      /* zp */  'z', 'p', 
      /* zs */  'z', 's', 
   };

   static const re_detail::character_pointer_range< ::UChar32> range_data[] = {
      { prop_name_table+0, prop_name_table+3, }, // any
      { prop_name_table+3, prop_name_table+8, }, // ascii
      { prop_name_table+8, prop_name_table+16, }, // assigned
      { prop_name_table+16, prop_name_table+18, }, // c*
      { prop_name_table+18, prop_name_table+20, }, // cc
      { prop_name_table+20, prop_name_table+22, }, // cf
      { prop_name_table+22, prop_name_table+38, }, // closepunctuation
      { prop_name_table+38, prop_name_table+40, }, // cn
      { prop_name_table+40, prop_name_table+42, }, // co
      { prop_name_table+42, prop_name_table+62, }, // connectorpunctuation
      { prop_name_table+62, prop_name_table+69, }, // control
      { prop_name_table+69, prop_name_table+71, }, // cs
      { prop_name_table+71, prop_name_table+85, }, // currencysymbol
      { prop_name_table+85, prop_name_table+100, }, // dashpunctuation
      { prop_name_table+100, prop_name_table+118, }, // decimaldigitnumber
      { prop_name_table+118, prop_name_table+131, }, // enclosingmark
      { prop_name_table+131, prop_name_table+147, }, // finalpunctuation
      { prop_name_table+147, prop_name_table+153, }, // format
      { prop_name_table+153, prop_name_table+171, }, // initialpunctuation
      { prop_name_table+171, prop_name_table+173, }, // l*
      { prop_name_table+173, prop_name_table+179, }, // letter
      { prop_name_table+179, prop_name_table+191, }, // letternumber
      { prop_name_table+191, prop_name_table+204, }, // lineseparator
      { prop_name_table+204, prop_name_table+206, }, // ll
      { prop_name_table+206, prop_name_table+208, }, // lm
      { prop_name_table+208, prop_name_table+210, }, // lo
      { prop_name_table+210, prop_name_table+225, }, // lowercaseletter
      { prop_name_table+225, prop_name_table+227, }, // lt
      { prop_name_table+227, prop_name_table+229, }, // lu
      { prop_name_table+229, prop_name_table+231, }, // m*
      { prop_name_table+231, prop_name_table+235, }, // mark
      { prop_name_table+235, prop_name_table+245, }, // mathsymbol
      { prop_name_table+245, prop_name_table+247, }, // mc
      { prop_name_table+247, prop_name_table+249, }, // me
      { prop_name_table+249, prop_name_table+251, }, // mn
      { prop_name_table+251, prop_name_table+265, }, // modifierletter
      { prop_name_table+265, prop_name_table+279, }, // modifiersymbol
      { prop_name_table+279, prop_name_table+281, }, // n*
      { prop_name_table+281, prop_name_table+283, }, // nd
      { prop_name_table+283, prop_name_table+285, }, // nl
      { prop_name_table+285, prop_name_table+287, }, // no
      { prop_name_table+287, prop_name_table+301, }, // nonspacingmark
      { prop_name_table+301, prop_name_table+312, }, // notassigned
      { prop_name_table+312, prop_name_table+318, }, // number
      { prop_name_table+318, prop_name_table+333, }, // openpunctuation
      { prop_name_table+333, prop_name_table+338, }, // other
      { prop_name_table+338, prop_name_table+349, }, // otherletter
      { prop_name_table+349, prop_name_table+360, }, // othernumber
      { prop_name_table+360, prop_name_table+376, }, // otherpunctuation
      { prop_name_table+376, prop_name_table+387, }, // othersymbol
      { prop_name_table+387, prop_name_table+389, }, // p*
      { prop_name_table+389, prop_name_table+407, }, // paragraphseparator
      { prop_name_table+407, prop_name_table+409, }, // pc
      { prop_name_table+409, prop_name_table+411, }, // pd
      { prop_name_table+411, prop_name_table+413, }, // pe
      { prop_name_table+413, prop_name_table+415, }, // pf
      { prop_name_table+415, prop_name_table+417, }, // pi
      { prop_name_table+417, prop_name_table+419, }, // po
      { prop_name_table+419, prop_name_table+429, }, // privateuse
      { prop_name_table+429, prop_name_table+431, }, // ps