DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (dcc6d7a0dc00)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#ifndef nsIUnicodeEncoder_h___
#define nsIUnicodeEncoder_h___

#include "nscore.h"
#include "nsError.h"
#include "nsISupports.h"

// Interface ID for our Unicode Encoder interface
// {2B2CA3D0-A4C9-11d2-8AA1-00600811A836}
#define NS_IUNICODEENCODER_IID \
	{ 0x2b2ca3d0, 0xa4c9, 0x11d2, \
		{ 0x8a, 0xa1, 0x0, 0x60, 0x8, 0x11, 0xa8, 0x36 }}  

// Interface ID for our Unicode Character Encoder interface
// {299BCCD0-C6DF-11d2-8AA8-00600811A836}
#define NS_IUNICHARENCODER_IID	\
	{ 0x299bccd0, 0xc6df, 0x11d2, \
		{0x8a, 0xa8, 0x0, 0x60, 0x8, 0x11, 0xa8, 0x36 }}


#define NS_UNICODEENCODER_CONTRACTID_BASE "@mozilla.org/intl/unicode/encoder;1?charset="

/**
 * Interface which converts a single character from Unicode into a given 
 * charset.
 *
 * @created         17/Feb/1999
 * @author  Catalin Rotaru [CATA]
 */
class nsIUnicharEncoder : public nsISupports
{
public:
  NS_DECLARE_STATIC_IID_ACCESSOR(NS_IUNICHARENCODER_IID)

  /**
   * Converts a character from Unicode to a Charset.
   */
  NS_IMETHOD Convert(char16_t aChar, char * aDest, int32_t * aDestLength) = 0;
};

NS_DEFINE_STATIC_IID_ACCESSOR(nsIUnicharEncoder, NS_IUNICHARENCODER_IID)

/**
 * Interface for a Converter from Unicode into a Charset.
 *
 * @created         23/Nov/1998
 * @author  Catalin Rotaru [CATA]
 */
class nsIUnicodeEncoder : public nsISupports
{
public:
  NS_DECLARE_STATIC_IID_ACCESSOR(NS_IUNICODEENCODER_IID)

  enum {
    kOnError_Signal,        // on an error, stop and signal
    kOnError_CallBack,      // on an error, call the error handler
    kOnError_Replace       // on an error, replace with a different character
  };

  /**
   * Converts the data from Unicode to a Charset.
   *
   * About the byte ordering:
   * - The input stream is Unicode, having the byte order which is internal
   * for the machine on which the converter is running on.
   * - For output, if the converter cares (that depends of the charset, for 
   * example a singlebyte will ignore the byte ordering) it should assume 
   * network order. If necessary and requested, we can add a method 
   * SetOutputByteOrder() so that the reverse order can be used, too. That 
   * method would have as default the assumed network order.
   *
   * For the last converted char, even if there is not enough output 
   * space, a partial output must be done until all available space will be 
   * used. The rest of the output should be buffered until more space becomes
   * available. But this is not also true about the error handling method!!!
   * So be very, very careful...
   *
   * @param aSrc        [IN] the source data buffer
   * @param aSrcLength  [IN/OUT] the length of source data buffer; after
   *                    conversion will contain the number of Unicode 
   *                    characters read
   * @param aDest       [OUT] the destination data buffer
   * @param aDestLength [IN/OUT] the length of the destination data buffer;
   *                    after conversion will contain the number of bytes
   *                    written
   * @return            NS_OK_UENC_MOREOUTPUT if only  a partial conversion
   *                    was done; more output space is needed to continue
   *                    NS_OK_UENC_MOREINPUT if only a partial conversion
   *                    was done; more input is needed to continue. This can
   *                    occur when the last UTF-16 code point in the input is
   *                    the first of a surrogate pair.
   *                    NS_ERROR_UENC_NOMAPPING if character without mapping
   *                    was encountered and the behavior was set to "signal".
   *                    In the case of an unmappable BMP character, aDestLength
   *                    must indicate that the unmappable character was
   *                    consumed by the encoder (unlike in the decode API!).
   *                    In the case of an unmappable astral character,
   *                    aDestLength must indicate that the high surrogate was
   *                    consumed by the encoder but the low surrogate was not.
   *                    NS_OK otherwise.
   */
  NS_IMETHOD Convert(const char16_t * aSrc, int32_t * aSrcLength, 
      char * aDest, int32_t * aDestLength) = 0;

  /**
   * Finishes the conversion. The converter has the possibility to write some 
   * extra data and flush its final state.
   *
   * @param aDest       [OUT] the destination data buffer
   * @param aDestLength [IN/OUT] the length of destination data buffer; after
   *                    conversion it will contain the number of bytes written
   * @return            NS_OK_UENC_MOREOUTPUT if only  a partial conversion
   *                    was done; more output space is needed to continue.
   *                    NS_ERROR_UENC_NOMAPPING if input ended with an unpaired
   *                    high surrogate, the behavior was "signal" and the
   *                    encoding can't represent U+FFFD.
   *                    NS_OK otherwise.
   */
  NS_IMETHOD Finish(char * aDest, int32_t * aDestLength) = 0;

  /**
   * Returns a quick estimation of the size of the buffer needed to hold the
   * converted data. Remember: this estimation is >= with the actual size of 
   * the buffer needed. It will be computed for the "worst case"
   *
   * @param aSrc        [IN] the source data buffer
   * @param aSrcLength  [IN] the length of source data buffer
   * @param aDestLength [OUT] the needed size of the destination buffer
   * @return            NS_OK_UENC_EXACTLENGTH if an exact length was computed
   *                    NS_ERROR_OUT_OF_MEMORY if OOM
   *                    NS_OK if all we have is an approximation
   */
  MOZ_WARN_UNUSED_RESULT NS_IMETHOD GetMaxLength(const char16_t* aSrc,
                                                 int32_t aSrcLength,
                                                 int32_t* aDestLength) = 0;

  /**
   * Resets the charset converter so it may be recycled for a completely 
   * different and urelated buffer of data.
   */
  NS_IMETHOD Reset() = 0;

  /**
   * Specify what to do when a character cannot be mapped into the dest charset
   *
   * @param aOrder      [IN] the behavior; taken from the enum
   */
  NS_IMETHOD SetOutputErrorBehavior(int32_t aBehavior, 
      nsIUnicharEncoder * aEncoder, char16_t aChar) = 0;
};

NS_DEFINE_STATIC_IID_ACCESSOR(nsIUnicodeEncoder, NS_IUNICODEENCODER_IID)

#endif /* nsIUnicodeEncoder_h___ */