parser/html/nsHtml5MetaScannerCppSupplement.h

   1 /* ***** BEGIN LICENSE BLOCK *****
   2  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   3  *
   4  * The contents of this file are subject to the Mozilla Public License Version
   5  * 1.1 (the "License"); you may not use this file except in compliance with
   6  * the License. You may obtain a copy of the License at
   7  * http://www.mozilla.org/MPL/
   8  *
   9  * Software distributed under the License is distributed on an "AS IS" basis,
  10  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  11  * for the specific language governing rights and limitations under the
  12  * License.
  13  *
  14  * The Original Code is HTML Parser C++ Translator code.
  15  *
  16  * The Initial Developer of the Original Code is
  17  * Mozilla Foundation.
  18  * Portions created by the Initial Developer are Copyright (C) 2009
  19  * the Initial Developer. All Rights Reserved.
  20  *
  21  * Contributor(s):
  22  *   Henri Sivonen <hsivonen@iki.fi>
  23  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either the GNU General Public License Version 2 or later (the "GPL"), or
  26  * 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 #include "nsICharsetConverterManager.h"
  39 #include "nsServiceManagerUtils.h"
  40 #include "nsICharsetAlias.h"
  41 #include "nsEncoderDecoderUtils.h"
  42 #include "nsTraceRefcnt.h"
  43
  44 static NS_DEFINE_CID(kCharsetAliasCID, NS_CHARSETALIAS_CID);
  45
  46 void
  47 nsHtml5MetaScanner::sniff(nsHtml5ByteReadable* bytes, nsIUnicodeDecoder** decoder, nsACString& charset)
  48 {
  49   readable = bytes;
  50   stateLoop(stateSave);
  51   readable = nsnull;
  52   if (mUnicodeDecoder) {
  53     mUnicodeDecoder.forget(decoder);
  54     charset.Assign(mCharset);
  55   }
  56 }
  57
  58 PRBool
  59 nsHtml5MetaScanner::tryCharset(nsString* charset)
  60 {
  61   // This code needs to stay in sync with
  62   // nsHtml5StreamParser::internalEncodingDeclaration. Unfortunately, the
  63   // trickery with member fields here leads to some copy-paste reuse. :-(
  64   nsresult res = NS_OK;
  65   nsCOMPtr<nsICharsetConverterManager> convManager = do_GetService(NS_CHARSETCONVERTERMANAGER_CONTRACTID, &res);
  66   if (NS_FAILED(res)) {
  67     NS_ERROR("Could not get CharsetConverterManager service.");
  68     return PR_FALSE;
  69   }
  70   nsCAutoString encoding;
  71   CopyUTF16toUTF8(*charset, encoding);
  72   encoding.Trim(" \t\r\n\f");
  73   if (encoding.LowerCaseEqualsLiteral("utf-16") ||
  74       encoding.LowerCaseEqualsLiteral("utf-16be") ||
  75       encoding.LowerCaseEqualsLiteral("utf-16le")) {
  76     mCharset.Assign("UTF-8");
  77     res = convManager->GetUnicodeDecoderRaw(mCharset.get(), getter_AddRefs(mUnicodeDecoder));
  78     if (NS_FAILED(res)) {
  79       NS_ERROR("Could not get decoder for UTF-8.");
  80       return PR_FALSE;
  81     }
  82     return PR_TRUE;
  83   }
  84   nsCAutoString preferred;
  85   nsCOMPtr<nsICharsetAlias> calias(do_GetService(kCharsetAliasCID, &res));
  86   if (NS_FAILED(res)) {
  87     NS_ERROR("Could not get CharsetAlias service.");
  88     return PR_FALSE;
  89   }
  90   res = calias->GetPreferred(encoding, preferred);
  91   if (NS_FAILED(res)) {
  92     return PR_FALSE;
  93   }
  94   if (preferred.LowerCaseEqualsLiteral("utf-16") ||
  95       preferred.LowerCaseEqualsLiteral("utf-16be") ||
  96       preferred.LowerCaseEqualsLiteral("utf-16le") ||
  97       preferred.LowerCaseEqualsLiteral("utf-32") ||
  98       preferred.LowerCaseEqualsLiteral("utf-32be") ||
  99       preferred.LowerCaseEqualsLiteral("utf-32le") ||
 100       preferred.LowerCaseEqualsLiteral("utf-7") ||
 101       preferred.LowerCaseEqualsLiteral("jis_x0212-1990") ||
 102       preferred.LowerCaseEqualsLiteral("x-jis0208") ||
 103       preferred.LowerCaseEqualsLiteral("x-imap4-modified-utf7") ||
 104       preferred.LowerCaseEqualsLiteral("x-user-defined")) {
 105     return PR_FALSE;
 106   }
 107   res = convManager->GetUnicodeDecoderRaw(preferred.get(), getter_AddRefs(mUnicodeDecoder));
 108   if (res == NS_ERROR_UCONV_NOCONV) {
 109     return PR_FALSE;
 110   } else if (NS_FAILED(res)) {
 111     NS_ERROR("Getting an encoding decoder failed in a bad way.");
 112     mUnicodeDecoder = nsnull;
 113     return PR_FALSE;
 114   } else {
 115     NS_ASSERTION(mUnicodeDecoder, "Getter nsresult and object don't match.");
 116     mCharset.Assign(preferred);
 117     return PR_TRUE;
 118   }
 119 }