intl/lwbrk/src/nsSampleWordBreaker.cpp

   1 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* ***** BEGIN LICENSE BLOCK *****
   3  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License. You may obtain a copy of the License at
   8  * http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Original Code is mozilla.org code.
  16  *
  17  * The Initial Developer of the Original Code is
  18  * Netscape Communications Corporation.
  19  * Portions created by the Initial Developer are Copyright (C) 1998
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either of the GNU General Public License Version 2 or later (the "GPL"),
  26  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  27  * in which case the provisions of the GPL or the LGPL are applicable instead
  28  * of those above. If you wish to allow use of your version of this file only
  29  * under the terms of either the GPL or the LGPL, and not to allow others to
  30  * use your version of this file under the terms of the MPL, indicate your
  31  * decision by deleting the provisions above and replace them with the notice
  32  * and other provisions required by the GPL or the LGPL. If you do not delete
  33  * the provisions above, a recipient may use your version of this file under
  34  * the terms of any one of the MPL, the GPL or the LGPL.
  35  *
  36  * ***** END LICENSE BLOCK ***** */
  37
  38
  39 #include "nsSampleWordBreaker.h"
  40
  41 #include "pratom.h"
  42 #include "nsLWBRKDll.h"
  43 nsSampleWordBreaker::nsSampleWordBreaker()
  44 {
  45 }
  46 nsSampleWordBreaker::~nsSampleWordBreaker()
  47 {
  48 }
  49
  50 NS_IMPL_ISUPPORTS1(nsSampleWordBreaker, nsIWordBreaker)
  51
  52 PRBool nsSampleWordBreaker::BreakInBetween(
  53   const PRUnichar* aText1 , PRUint32 aTextLen1,
  54   const PRUnichar* aText2 , PRUint32 aTextLen2)
  55 {
  56   NS_PRECONDITION( nsnull != aText1, "null ptr");
  57   NS_PRECONDITION( nsnull != aText2, "null ptr");
  58
  59   if(!aText1 || !aText2 || (0 == aTextLen1) || (0 == aTextLen2))
  60     return PR_FALSE;
  61
  62   return (this->GetClass(aText1[aTextLen1-1]) != this->GetClass(aText2[0]));
  63 }
  64
  65
  66 #define IS_ASCII(c)            (0 == ( 0xFF80 & (c)))
  67 #define ASCII_IS_ALPHA(c)         ((( 'a' <= (c)) && ((c) <= 'z')) || (( 'A' <= (c)) && ((c) <= 'Z')))
  68 #define ASCII_IS_DIGIT(c)         (( '0' <= (c)) && ((c) <= '9'))
  69 #define ASCII_IS_SPACE(c)         (( ' ' == (c)) || ( '\t' == (c)) || ( '\r' == (c)) || ( '\n' == (c)))
  70 #define IS_ALPHABETICAL_SCRIPT(c) ((c) < 0x2E80)
  71
  72 // we change the beginning of IS_HAN from 0x4e00 to 0x3400 to relfect Unicode 3.0
  73 #define IS_HAN(c)              (( 0x3400 <= (c)) && ((c) <= 0x9fff))||(( 0xf900 <= (c)) && ((c) <= 0xfaff))
  74 #define IS_KATAKANA(c)         (( 0x30A0 <= (c)) && ((c) <= 0x30FF))
  75 #define IS_HIRAGANA(c)         (( 0x3040 <= (c)) && ((c) <= 0x309F))
  76 #define IS_HALFWIDTHKATAKANA(c)         (( 0xFF60 <= (c)) && ((c) <= 0xFF9F))
  77 #define IS_THAI(c)         (0x0E00 == (0xFF80 & (c) )) // Look at the higest 9 bits
  78
  79 PRUint8 nsSampleWordBreaker::GetClass(PRUnichar c)
  80 {
  81   // begin of the hack
  82
  83   if (IS_ALPHABETICAL_SCRIPT(c))  {
  84           if(IS_ASCII(c))  {
  85                   if(ASCII_IS_SPACE(c)) {
  86                           return kWbClassSpace;
  87                   } else if(ASCII_IS_ALPHA(c) || ASCII_IS_DIGIT(c)) {
  88                           return kWbClassAlphaLetter;
  89                   } else {
  90                           return kWbClassPunct;
  91                   }
  92           } else if(IS_THAI(c)) {
  93                   return kWbClassThaiLetter;
  94           } else if (c == 0x00A0/*NBSP*/) {
  95       return kWbClassSpace;
  96     } else {
  97                   return kWbClassAlphaLetter;
  98           }
  99   }  else {
 100           if(IS_HAN(c)) {
 101                   return kWbClassHanLetter;
 102           } else if(IS_KATAKANA(c))   {
 103                   return kWbClassKatakanaLetter;
 104           } else if(IS_HIRAGANA(c))   {
 105                   return kWbClassHiraganaLetter;
 106           } else if(IS_HALFWIDTHKATAKANA(c))  {
 107                   return kWbClassHWKatakanaLetter;
 108           } else  {
 109                   return kWbClassAlphaLetter;
 110           }
 111   }
 112   return 0;
 113 }
 114
 115 nsWordRange nsSampleWordBreaker::FindWord(
 116   const PRUnichar* aText , PRUint32 aTextLen,
 117   PRUint32 aOffset)
 118 {
 119   nsWordRange range;
 120   NS_PRECONDITION( nsnull != aText, "null ptr");
 121   NS_PRECONDITION( 0 != aTextLen, "len = 0");
 122   NS_PRECONDITION( aOffset <= aTextLen, "aOffset > aTextLen");
 123
 124   range.mBegin = aTextLen + 1;
 125   range.mEnd = aTextLen + 1;
 126
 127   if(!aText || aOffset > aTextLen)
 128     return range;
 129
 130   PRUint8 c = this->GetClass(aText[aOffset]);
 131   PRUint32 i;
 132   // Scan forward
 133   range.mEnd--;
 134   for(i = aOffset +1;i <= aTextLen; i++)
 135   {
 136      if( c != this->GetClass(aText[i]))
 137      {
 138        range.mEnd = i;
 139        break;
 140      }
 141   }
 142
 143   // Scan backward
 144   range.mBegin = 0;
 145   for(i = aOffset ;i > 0; i--)
 146   {
 147      if( c != this->GetClass(aText[i-1]))
 148      {
 149        range.mBegin = i;
 150        break;
 151      }
 152   }
 153   if(kWbClassThaiLetter == c)
 154   {
 155         // need to call Thai word breaker from here
 156         // we should pass the whole Thai segment to the thai word breaker to find a shorter answer
 157   }
 158   return range;
 159 }
 160
 161 PRInt32 nsSampleWordBreaker::NextWord(
 162   const PRUnichar* aText, PRUint32 aLen, PRUint32 aPos)
 163 {
 164   PRInt8 c1, c2;
 165   PRUint32 cur = aPos;
 166   if (cur == aLen)
 167     return NS_WORDBREAKER_NEED_MORE_TEXT;
 168   c1 = this->GetClass(aText[cur]);
 169
 170   for(cur++; cur <aLen; cur++)
 171   {
 172      c2 = this->GetClass(aText[cur]);
 173      if(c2 != c1)
 174        break;
 175   }
 176   if(kWbClassThaiLetter == c1)
 177   {
 178         // need to call Thai word breaker from here
 179         // we should pass the whole Thai segment to the thai word breaker to find a shorter answer
 180   }
 181   if (cur == aLen)
 182     return NS_WORDBREAKER_NEED_MORE_TEXT;
 183   return cur;
 184 }
 185
 186 PRInt32 nsSampleWordBreaker::PrevWord(
 187   const PRUnichar* aText, PRUint32 aLen, PRUint32 aPos)
 188 {
 189   PRInt8 c1, c2;
 190   PRUint32 cur = aPos;
 191   if (cur == aLen) {
 192     if (cur == 0)
 193       return NS_WORDBREAKER_NEED_MORE_TEXT;
 194     --cur;
 195   }
 196   c1 = this->GetClass(aText[cur]);
 197
 198   for(; cur > 0; cur--)
 199   {
 200      c2 = this->GetClass(aText[cur-1]);
 201      if(c2 != c1)
 202        break;
 203   }
 204   if(kWbClassThaiLetter == c1)
 205   {
 206         // need to call Thai word breaker from here
 207         // we should pass the whole Thai segment to the thai word breaker to find a shorter answer
 208   }
 209   if (!cur)
 210     return NS_WORDBREAKER_NEED_MORE_TEXT;
 211   return cur;
 212 }