13:34
ľ File not found.
+ lY> j-
@_I|+ ? // © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (c) 1996-2016, International Business Machines Corporation
* and others. All Rights Reserved.
*******************************************************************************
* File unorm.h
*
* Created by: Vladimir Weinstein 12052000
*
* Modification history :
*
* Date Name Description
* 02/01/01 synwee Added normalization quickcheck enum and method.
*/
#ifndef UNORM_H
#define UNORM_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/uiter.h"
#include "unicode/unorm2.h"
/**
* \file
* \brief C API: Unicode Normalization
*
* Old Unicode normalization API.
*
* This API has been replaced by the unorm2.h API and is only available
* for backward compatibility. The functions here simply delegate to the
* unorm2.h functions, for example unorm2_getInstance() and unorm2_normalize().
* There is one exception: The new API does not provide a replacement for unorm_compare().
* Its declaration has been moved to unorm2.h.
*
* unorm_normalize transforms Unicode text into an equivalent composed or
* decomposed form, allowing for easier sorting and searching of text.
* unorm_normalize supports the standard normalization forms described in
*
* Unicode Standard Annex #15: Unicode Normalization Forms.
*
* Characters with accents or other adornments can be encoded in
* several different ways in Unicode. For example, take the character A-acute.
* In Unicode, this can be encoded as a single character (the
* "composed" form):
*
* \code
* 00C1 LATIN CAPITAL LETTER A WITH ACUTE
* \endcode
*
* or as two separate characters (the "decomposed" form):
*
* \code
* 0041 LATIN CAPITAL LETTER A
* 0301 COMBINING ACUTE ACCENT
* \endcode
*
* To a user of your program, however, both of these sequences should be
* treated as the same "user-level" character "A with acute accent". When you are searching or
* comparing text, you must ensure that these two sequences are treated
* equivalently. In addition, you must handle characters with more than one
* accent. Sometimes the order of a character's combining accents is
* significant, while in other cases accent sequences in different orders are
* really equivalent.
*
* Similarly, the string "ffi" can be encoded as three separate letters:
*
* \code
* 0066 LATIN SMALL LETTER F
* 0066 LATIN SMALL LETTER F
* 0069 LATIN SMALL LETTER I
* \endcode
*
* or as the single character
*
* \code
* FB03 LATIN SMALL LIGATURE FFI
* \endcode
*
* The ffi ligature is not a distinct semantic character, and strictly speaking
* it shouldn't be in Unicode at all, but it was included for compatibility
* with existing character sets that already provided it. The Unicode standard
* identifies such characters by giving them "compatibility" decompositions
* into the corresponding semantic characters. When sorting and searching, you
* will often want to use these mappings.
*
* unorm_normalize helps solve these problems by transforming text into the
* canonical composed and decomposed forms as shown in the first example above.
* In addition, you can have it perform compatibility decompositions so that
* you can treat compatibility characters the same as their equivalents.
* Finally, unorm_normalize rearranges accents into the proper canonical
* order, so that you do not have to worry about accent rearrangement on your
* own.
*
* Form FCD, "Fast C or D", is also designed for collation.
* It allows to work on strings that are not necessarily normalized
* with an algorithm (like in collation) that works under "canonical c