Back to index

lightning-sunbird  0.9+nobinonly
nsCharSetProber.cpp
Go to the documentation of this file.
00001 /* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
00002 /* ***** BEGIN LICENSE BLOCK *****
00003  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
00004  *
00005  * The contents of this file are subject to the Mozilla Public License Version
00006  * 1.1 (the "License"); you may not use this file except in compliance with
00007  * the License. You may obtain a copy of the License at
00008  * http://www.mozilla.org/MPL/
00009  *
00010  * Software distributed under the License is distributed on an "AS IS" basis,
00011  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
00012  * for the specific language governing rights and limitations under the
00013  * License.
00014  *
00015  * The Original Code is Mozilla Universal charset detector code.
00016  *
00017  * The Initial Developer of the Original Code is
00018  * Netscape Communications Corporation.
00019  * Portions created by the Initial Developer are Copyright (C) 2001
00020  * the Initial Developer. All Rights Reserved.
00021  *
00022  * Contributor(s):
00023  *          Shy Shalom <shooshX@gmail.com>
00024  *
00025  * Alternatively, the contents of this file may be used under the terms of
00026  * either the GNU General Public License Version 2 or later (the "GPL"), or
00027  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
00028  * in which case the provisions of the GPL or the LGPL are applicable instead
00029  * of those above. If you wish to allow use of your version of this file only
00030  * under the terms of either the GPL or the LGPL, and not to allow others to
00031  * use your version of this file under the terms of the MPL, indicate your
00032  * decision by deleting the provisions above and replace them with the notice
00033  * and other provisions required by the GPL or the LGPL. If you do not delete
00034  * the provisions above, a recipient may use your version of this file under
00035  * the terms of any one of the MPL, the GPL or the LGPL.
00036  *
00037  * ***** END LICENSE BLOCK ***** */
00038  
00039 #include "nsCharSetProber.h"
00040 #include "prmem.h"
00041 
00042 //This filter applies to all scripts which do not use English characters
00043 PRBool nsCharSetProber::FilterWithoutEnglishLetters(const char* aBuf, PRUint32 aLen, char** newBuf, PRUint32& newLen)
00044 {
00045   char *newptr;
00046   char *prevPtr, *curPtr;
00047   
00048   PRBool meetMSB = PR_FALSE;   
00049   newptr = *newBuf = (char*)PR_Malloc(aLen);
00050   if (!newptr)
00051     return PR_FALSE;
00052 
00053   for (curPtr = prevPtr = (char*)aBuf; curPtr < aBuf+aLen; curPtr++)
00054   {
00055     if (*curPtr & 0x80)
00056     {
00057       meetMSB = PR_TRUE;
00058     }
00059     else if (*curPtr < 'A' || (*curPtr > 'Z' && *curPtr < 'a') || *curPtr > 'z') 
00060     {
00061       //current char is a symbol, most likely a punctuation. we treat it as segment delimiter
00062       if (meetMSB && curPtr > prevPtr) 
00063       //this segment contains more than single symbol, and it has upper ASCII, we need to keep it
00064       {
00065         while (prevPtr < curPtr) *newptr++ = *prevPtr++;  
00066         prevPtr++;
00067         *newptr++ = ' ';
00068         meetMSB = PR_FALSE;
00069       }
00070       else //ignore current segment. (either because it is just a symbol or just an English word)
00071         prevPtr = curPtr+1;
00072     }
00073   }
00074   if (meetMSB && curPtr > prevPtr) 
00075     while (prevPtr < curPtr) *newptr++ = *prevPtr++;  
00076 
00077   newLen = newptr - *newBuf;
00078 
00079   return PR_TRUE;
00080 }
00081 
00082 //This filter applies to all scripts which contain both English characters and upper ASCII characters.
00083 PRBool nsCharSetProber::FilterWithEnglishLetters(const char* aBuf, PRUint32 aLen, char** newBuf, PRUint32& newLen)
00084 {
00085   //do filtering to reduce load to probers
00086   char *newptr;
00087   char *prevPtr, *curPtr;
00088   PRBool isInTag = PR_FALSE;
00089 
00090   newptr = *newBuf = (char*)PR_Malloc(aLen);
00091   if (!newptr)
00092     return PR_FALSE;
00093 
00094   for (curPtr = prevPtr = (char*)aBuf; curPtr < aBuf+aLen; curPtr++)
00095   {
00096     if (*curPtr == '>')
00097       isInTag = PR_FALSE;
00098     else if (*curPtr == '<')
00099       isInTag = PR_TRUE;
00100 
00101     if (!(*curPtr & 0x80) &&
00102         (*curPtr < 'A' || (*curPtr > 'Z' && *curPtr < 'a') || *curPtr > 'z') )
00103     {
00104       if (curPtr > prevPtr && !isInTag) // Current segment contains more than just a symbol 
00105                                         // and it is not inside a tag, keep it.
00106       {
00107         while (prevPtr < curPtr) *newptr++ = *prevPtr++;  
00108         prevPtr++;
00109         *newptr++ = ' ';
00110       }
00111       else
00112         prevPtr = curPtr+1;
00113     }
00114   }
00115 
00116   // If the current segment contains more than just a symbol 
00117   // and it is not inside a tag then keep it.
00118   if (!isInTag)
00119     while (prevPtr < curPtr)
00120       *newptr++ = *prevPtr++;  
00121 
00122   newLen = newptr - *newBuf;
00123 
00124   return PR_TRUE;
00125 }