plurfmt.h | Explore in Territory

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2007-2014, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*

* File PLURFMT.H
********************************************************************************
*/

#ifndef PLURFMT
#define PLURFMT

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

/**
 * \file
 * \brief C++ API: PluralFormat object
 */

#if !UCONFIG_NO_FORMATTING

#include "unicode/messagepattern.h"
#include "unicode/numfmt.h"
#include "unicode/plurrule.h"

U_NAMESPACE_BEGIN

class Hashtable;
class NFRule;

/**
 * <p>
 * <code>PluralFormat</code> supports the creation of internationalized
 * messages with plural inflection. It is based on <i>plural
 * selection</i>, i.e. the caller specifies messages for each
 * plural case that can appear in the user's language and the
 * <code>PluralFormat</code> selects the appropriate message based on
 * the number.
 * </p>
 * <h4>The Problem of Plural Forms in Internationalized Messages</h4>
 * <p>
 * Different languages have different ways to inflect
 * plurals. Creating internationalized messages that include plural
 * forms is only feasible when the framework is able to handle plural
 * forms of <i>all</i> languages correctly. <code>ChoiceFormat</code>
 * doesn't handle this well, because it attaches a number interval to
 * each message and selects the message whose interval contains a
 * given number. This can only handle a finite number of
 * intervals. But in some languages, like Polish, one plural case
 * applies to infinitely many intervals (e.g., the plural case applies to
 * numbers ending with 2, 3, or 4 except those ending with 12, 13, or
 * 14). Thus <code>ChoiceFormat</code> is not adequate.
 * </p><p>
 * <code>PluralFormat</code> deals with this by breaking the problem
 * into two parts:
 * <ul>
 * <li>It uses <code>PluralRules</code> that can define more complex
 *     conditions for a plural case than just a single interval. These plural
 *     rules define both what plural cases exist in a language, and to
 *     which numbers these cases apply.
 * <li>It provides predefined plural rules for many languages. Thus, the programmer
 *     need not worry about the plural cases of a language and
 *     does not have to define the plural cases; they can simply
 *     use the predefined keywords. The whole plural formatting of messages can
 *     be done using localized patterns from resource bundles. For predefined plural
 *     rules, see the CLDR <i>Language Plural Rules</i> page at
 *     https://unicode-org.github.io/cldr-staging/charts/latest/supplemental/language_plural_rules.html
 * </ul>
 * </p>
 * <h4>Usage of <code>PluralFormat</code></h4>
 * <p>Note: Typically, plural formatting is done via <code>MessageFormat</code>
 * with a <code>plural</code> argument type,
 * rather than using a stand-alone <code>PluralFormat</code>.
 * </p><p>
 * This discussion assumes that you use <code>PluralFormat</code> with
 * a predefined set of plural rules. You can create one using one of
 * the constructors that takes a <code>locale</code> object. To
 * specify the message pattern, you can either pass it to the
 * constructor or set it explicitly using the
 * <code>applyPattern()</code> method. The <code>format()</code>
 * method takes a number object and selects the message of the
 * matching plural case. This message will be returned.
 * </p>
 * <h5>Patterns and Their Interpretation</h5>
 * <p>
 * The pattern text defines the message output for each plural case of the
 * specified locale. Syntax:
 * <pre>
 * pluralStyle = [offsetValue] (selector '{' message '}')+
 * offsetValue = "offset:" number
 * selector = explicitValue | keyword
 * explicitValue = '=' number  // adjacent, no white space in between
 * keyword = [^[[:Pattern_Syntax:][:Pattern_White_Space:]]]+
 * message: see {@link MessageFormat}
 * </pre>
 * Pattern_White_Space between syntax elements is ignored, except
 * between the {curly braces} and their sub-message,
 * and between the '=' and the number of an explicitValue.
 *
 * </p><p>
 * There are 6 predefined casekeyword in CLDR/ICU - 'zero', 'one', 'two', 'few', 'many' and
 * 'other'. You always have to define a message text for the default plural case
 * <code>other</code> which is contained in every rule set.
 * If you do not specify a message text for a particular plural case, the
 * message text of the plural case <code>other</code> gets assigned to this
 * plural case.
 * </p><p>
 * When formatting, the input number is first matched against the explicitValue clauses.
 * If there is no exact-number match, then a keyword is selected by calling
 * the <code>PluralRules</code> with the input number <em>minus the offset</em>.
 * (The offset defaults to 0 if it is omitted from the pattern string.)
 * If there is no clause with that keyword, then the "other" clauses is returned.
 * </p><p>
 * An unquoted pound sign (<code>#</code>) in the selected sub-message
 * itself (i.e., outside of arguments nested in the sub-message)
 * is replaced by the input number minus the offset.
 * The number-minus-offset value is formatted using a
 * <code>NumberFormat</code> for the <code>PluralFormat</code>'s locale. If you
 * need special number formatting, you have to use a <code>MessageFormat</code>
 * and explicitly specify a <code>NumberFormat</code> argument.
 * <strong>Note:</strong> That argument is formatting without subtracting the offset!
 * If you need a custom format and have a non-zero offset, then you need to pass the
 * number-minus-offset value as a separate parameter.
 * </p>
 * For a usage example, see the {@link MessageFormat} class documentation.
 *
 * <h4>Defining Custom Plural Rules</h4>
 * <p>If you need to use <code>PluralFormat</code> with custom rules, you can
 * create a <code>PluralRules</code> object and pass it to
 * <code>PluralFormat</code>'s constructor. If you also specify a locale in this
 * constructor, this locale will be used to format the number in the message
 * texts.
 * </p><p>
 * For more information about <code>PluralRules</code>, see
 * {@link PluralRules}.
 * </p>
 *
 * ported from Java
 * @stable ICU 4.0
 */

class U_I18N_API PluralFormat : public Format { … };

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_FORMATTING */

#endif /* U_SHOW_CPLUSPLUS_API */

#endif // _PLURFMT
//eof
chromium/third_party/icu/source/i18n/unicode/plurfmt.h
