intl/uconv/src/nsUTF8ConverterService.cpp

   1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* vim:expandtab:shiftwidth=2:tabstop=4:
   3  */
   4 /* ***** BEGIN LICENSE BLOCK *****
   5  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   6  *
   7  * The contents of this file are subject to the Mozilla Public License Version
   8  * 1.1 (the "License"); you may not use this file except in compliance with
   9  * the License. You may obtain a copy of the License at
  10  * http://www.mozilla.org/MPL/
  11  *
  12  * Software distributed under the License is distributed on an "AS IS" basis,
  13  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  14  * for the specific language governing rights and limitations under the
  15  * License.
  16  *
  17  * The Original Code is mozilla.org code.
  18  *
  19  * The Initial Developers of the Original Code are
  20  * Naoki Hotta <nhotta@netscape.com> and Jungshik Shin <jshin@mailaps.org>.
  21  * Portions created by the Initial Developer are Copyright (C) 2002, 2003
  22  * the Initial Developers. All Rights Reserved.
  23  *
  24  * Contributor(s):
  25  *
  26  * Alternatively, the contents of this file may be used under the terms of
  27  * either the GNU General Public License Version 2 or later (the "GPL"), or
  28  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  29  * in which case the provisions of the GPL or the LGPL are applicable instead
  30  * of those above. If you wish to allow use of your version of this file only
  31  * under the terms of either the GPL or the LGPL, and not to allow others to
  32  * use your version of this file under the terms of the MPL, indicate your
  33  * decision by deleting the provisions above and replace them with the notice
  34  * and other provisions required by the GPL or the LGPL. If you do not delete
  35  * the provisions above, a recipient may use your version of this file under
  36  * the terms of any one of the MPL, the GPL or the LGPL.
  37  *
  38  * ***** END LICENSE BLOCK ***** */
  39 #include "nsString.h"
  40 #include "nsIUnicodeEncoder.h"
  41 #include "nsICharsetConverterManager.h"
  42 #include "nsReadableUtils.h"
  43 #include "nsIServiceManager.h"
  44 #include "nsUConvDll.h"
  45 #include "prmem.h"
  46 #include "nsUTF8ConverterService.h"
  47 #include "nsEscape.h"
  48 #include "nsAutoPtr.h"
  49
  50 NS_IMPL_ISUPPORTS1(nsUTF8ConverterService, nsIUTF8ConverterService)
  51
  52 static nsresult
  53 ToUTF8(const nsACString &aString, const char *aCharset, nsACString &aResult)
  54 {
  55   nsresult rv;
  56   if (!aCharset || !*aCharset)
  57     return NS_ERROR_INVALID_ARG;
  58
  59   nsCOMPtr<nsICharsetConverterManager> ccm;
  60
  61   ccm = do_GetService(NS_CHARSETCONVERTERMANAGER_CONTRACTID, &rv);
  62   NS_ENSURE_SUCCESS(rv, rv);
  63
  64   nsCOMPtr<nsIUnicodeDecoder> unicodeDecoder;
  65   rv = ccm->GetUnicodeDecoder(aCharset,
  66                               getter_AddRefs(unicodeDecoder));
  67   NS_ENSURE_SUCCESS(rv, rv);
  68
  69   PRInt32 srcLen = aString.Length();
  70   PRInt32 dstLen;
  71   const nsAFlatCString& inStr = PromiseFlatCString(aString);
  72   rv = unicodeDecoder->GetMaxLength(inStr.get(), srcLen, &dstLen);
  73   NS_ENSURE_SUCCESS(rv, rv);
  74
  75   nsAutoArrayPtr<PRUnichar> ustr(new PRUnichar[dstLen]);
  76   NS_ENSURE_TRUE(ustr, NS_ERROR_OUT_OF_MEMORY);
  77
  78   rv = unicodeDecoder->Convert(inStr.get(), &srcLen, ustr, &dstLen);
  79   if (NS_SUCCEEDED(rv)){
  80     // Tru64 Cxx and IRIX MIPSpro 7.3  need an explicit get()
  81     CopyUTF16toUTF8(Substring(ustr.get(), ustr + dstLen), aResult);
  82   }
  83   return rv;
  84 }
  85
  86 NS_IMETHODIMP
  87 nsUTF8ConverterService::ConvertStringToUTF8(const nsACString &aString,
  88                                             const char *aCharset,
  89                                             PRBool aSkipCheck,
  90                                             nsACString &aUTF8String)
  91 {
  92   // return if ASCII only or valid UTF-8 providing that the ASCII/UTF-8
  93   // check is requested. It may not be asked for if a caller suspects
  94   // that the input is in non-ASCII 7bit charset (ISO-2022-xx, HZ) or
  95   // it's in a charset other than UTF-8 that can be mistaken for UTF-8.
  96   if (!aSkipCheck && (IsASCII(aString) || IsUTF8(aString))) {
  97     aUTF8String = aString;
  98     return NS_OK;
  99   }
 100
 101   aUTF8String.Truncate();
 102
 103   nsresult rv = ToUTF8(aString, aCharset, aUTF8String);
 104
 105   // additional protection for cases where check is skipped and  the input
 106   // is actually in UTF-8 as opposed to aCharset. (i.e. caller's hunch
 107   // was wrong.) We don't check ASCIIness assuming there's no charset
 108   // incompatible with ASCII (we don't support EBCDIC).
 109   if (aSkipCheck && NS_FAILED(rv) && IsUTF8(aString)) {
 110     aUTF8String = aString;
 111     return NS_OK;
 112   }
 113
 114   return rv;
 115 }
 116
 117 NS_IMETHODIMP
 118 nsUTF8ConverterService::ConvertURISpecToUTF8(const nsACString &aSpec,
 119                                              const char *aCharset,
 120                                              nsACString &aUTF8Spec)
 121 {
 122   // assume UTF-8 if the spec contains unescaped non-ASCII characters.
 123   // No valid spec in Mozilla would break this assumption.
 124   if (!IsASCII(aSpec)) {
 125     aUTF8Spec = aSpec;
 126     return NS_OK;
 127   }
 128
 129   aUTF8Spec.Truncate();
 130
 131   nsCAutoString unescapedSpec;
 132   // NS_UnescapeURL does not fill up unescapedSpec unless there's at least
 133   // one character to unescape.
 134   PRBool written = NS_UnescapeURL(PromiseFlatCString(aSpec).get(), aSpec.Length(),
 135                                   esc_OnlyNonASCII, unescapedSpec);
 136
 137   if (!written) {
 138     aUTF8Spec = aSpec;
 139     return NS_OK;
 140   }
 141   // return if ASCII only or escaped UTF-8
 142   if (IsASCII(unescapedSpec) || IsUTF8(unescapedSpec)) {
 143     aUTF8Spec = unescapedSpec;
 144     return NS_OK;
 145   }
 146
 147   return ToUTF8(unescapedSpec, aCharset, aUTF8Spec);
 148 }
 149