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
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/* vim:expandtab:shiftwidth=4:tabstop=4:
 */
/* 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/. */

#include "nsISupports.idl"

[scriptable, uuid(249f52a3-2599-4b00-ba40-0481364831a2)]
interface nsIUTF8ConverterService : nsISupports
{
  /**
   * Ensure that |aString| is encoded in UTF-8.  If not, 
   * convert to UTF-8 assuming it's encoded in |aCharset|
   * and return the converted string in UTF-8.
   *
   * @param aString a string to  ensure its UTF8ness
   * @param aCharset the charset to convert from if |aString| is not in UTF-8
   * @param aSkipCheck determines whether or not to skip 'ASCIIness' and 
   *        'UTF8ness' check. Set this to PR_TRUE only if you suspect that 
   *        aString can be mistaken for ASCII / UTF-8 but is actually NOT 
   *        in ASCII / UTF-8 so that aString has to go through the conversion.
   *        skipping ASCIIness/UTF8ness check.
   *        The most common case is the input is in 7bit non-ASCII charsets
   *        like ISO-2022-JP, HZ or UTF-7 (in its original form or
   *        a modified form used in IMAP folder names).
   * @param aAllowSubstitution when true, allow the decoder to substitute
   *        invalid input sequences by replacement characters (defaults to
   *        true)
   * @return the converted string in UTF-8.
   * @throws NS_ERROR_UCONV_NOCONV when there is no decoder for aCharset
   *         or error code of nsIUnicodeDecoder in case of conversion failure
   */

    [optional_argc]
    AUTF8String convertStringToUTF8(in ACString aString, 
                                    in string   aCharset,
                                    in boolean  aSkipCheck,
                                    [optional] in boolean aAllowSubstitution);

/* XXX : To-be-added. convertStringFromUTF8 */
   
  /**
   * Ensure that |aSpec| (after URL-unescaping it) is encoded in UTF-8.  
   * If not,  convert it to UTF-8, assuming it's encoded in |aCharset|,  
   * and return the result.
   *
   * <p>Make sure that all characters outside US-ASCII in your input spec 
   * are url-escaped if  your spec is not in UTF-8 (before url-escaping) 
   * because the presence of non-ASCII characters is <strong>blindly</strong>
   * regarded as an indication that your input spec is in unescaped UTF-8
   * and it will be returned without further processing. No valid spec
   * going around in Mozilla code would break this assumption. 
   *
   * <p>XXX The above may change in the future depending on the usage pattern.
   *
   * @param aSpec an url-escaped URI spec to  ensure its UTF8ness
   * @param aCharset the charset to convert from if |aSpec| is not in UTF-8
   * @return the converted spec in UTF-8.
   * @throws NS_ERROR_UCONV_NOCONV when there is no decoder for aCharset
   *         or error code of nsIUnicodeDecoder in case of conversion failure
   */

    AUTF8String convertURISpecToUTF8(in ACString aSpec, 
                                     in string   aCharset);
};