godot/thirdparty/icu4c/common/unicode/normalizer2.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2009-2013, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  normalizer2.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2009nov22
*   created by: Markus W. Scherer
*/

#ifndef __NORMALIZER2_H__
#define __NORMALIZER2_H__

/**
 * \file
 * \brief C++ API: New API for Unicode Normalization.
 */

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

#if !UCONFIG_NO_NORMALIZATION

#include "unicode/stringpiece.h"
#include "unicode/uniset.h"
#include "unicode/unistr.h"
#include "unicode/unorm2.h"

U_NAMESPACE_BEGIN

class ByteSink;

/**
 * Unicode normalization functionality for standard Unicode normalization or
 * for using custom mapping tables.
 * All instances of this class are unmodifiable/immutable.
 * Instances returned by getInstance() are singletons that must not be deleted by the caller.
 * The Normalizer2 class is not intended for public subclassing.
 *
 * The primary functions are to produce a normalized string and to detect whether
 * a string is already normalized.
 * The most commonly used normalization forms are those defined in
 * http://www.unicode.org/unicode/reports/tr15/
 * However, this API supports additional normalization forms for specialized purposes.
 * For example, NFKC_Casefold is provided via getInstance("nfkc_cf", COMPOSE)
 * and can be used in implementations of UTS #46.
 *
 * Not only are the standard compose and decompose modes supplied,
 * but additional modes are provided as documented in the Mode enum.
 *
 * Some of the functions in this class identify normalization boundaries.
 * At a normalization boundary, the portions of the string
 * before it and starting from it do not interact and can be handled independently.
 *
 * The spanQuickCheckYes() stops at a normalization boundary.
 * When the goal is a normalized string, then the text before the boundary
 * can be copied, and the remainder can be processed with normalizeSecondAndAppend().
 *
 * The hasBoundaryBefore(), hasBoundaryAfter() and isInert() functions test whether
 * a character is guaranteed to be at a normalization boundary,
 * regardless of context.
 * This is used for moving from one normalization boundary to the next
 * or preceding boundary, and for performing iterative normalization.
 *
 * Iterative normalization is useful when only a small portion of a
 * longer string needs to be processed.
 * For example, in ICU, iterative normalization is used by the NormalizationTransliterator
 * (to avoid replacing already-normalized text) and ucol_nextSortKeyPart()
 * (to process only the substring for which sort key bytes are computed).
 *
 * The set of normalization boundaries returned by these functions may not be
 * complete: There may be more boundaries that could be returned.
 * Different functions may return different boundaries.
 * @stable ICU 4.4
 */
class U_COMMON_API Normalizer2 : public UObject { … };

/**
 * Normalization filtered by a UnicodeSet.
 * Normalizes portions of the text contained in the filter set and leaves
 * portions not contained in the filter set unchanged.
 * Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE).
 * Not-in-the-filter text is treated as "is normalized" and "quick check yes".
 * This class implements all of (and only) the Normalizer2 API.
 * An instance of this class is unmodifiable/immutable but is constructed and
 * must be destructed by the owner.
 * @stable ICU 4.4
 */
class U_COMMON_API FilteredNormalizer2 : public Normalizer2 { … };

U_NAMESPACE_END

#endif  // !UCONFIG_NO_NORMALIZATION

#endif /* U_SHOW_CPLUSPLUS_API */

#endif  // __NORMALIZER2_H__