michael@0: /* michael@0: ******************************************************************************* michael@0: * Copyright (C) 2007-2013, International Business Machines Corporation and michael@0: * others. All Rights Reserved. michael@0: ******************************************************************************* michael@0: * michael@0: michael@0: * File PLURFMT.H michael@0: ******************************************************************************** michael@0: */ michael@0: michael@0: #ifndef PLURFMT michael@0: #define PLURFMT michael@0: michael@0: #include "unicode/utypes.h" michael@0: michael@0: /** michael@0: * \file michael@0: * \brief C++ API: PluralFormat object michael@0: */ michael@0: michael@0: #if !UCONFIG_NO_FORMATTING michael@0: michael@0: #include "unicode/messagepattern.h" michael@0: #include "unicode/numfmt.h" michael@0: #include "unicode/plurrule.h" michael@0: michael@0: U_NAMESPACE_BEGIN michael@0: michael@0: class Hashtable; michael@0: michael@0: /** michael@0: *

michael@0: * PluralFormat supports the creation of internationalized michael@0: * messages with plural inflection. It is based on plural michael@0: * selection, i.e. the caller specifies messages for each michael@0: * plural case that can appear in the user's language and the michael@0: * PluralFormat selects the appropriate message based on michael@0: * the number. michael@0: *

michael@0: *

The Problem of Plural Forms in Internationalized Messages

michael@0: *

michael@0: * Different languages have different ways to inflect michael@0: * plurals. Creating internationalized messages that include plural michael@0: * forms is only feasible when the framework is able to handle plural michael@0: * forms of all languages correctly. ChoiceFormat michael@0: * doesn't handle this well, because it attaches a number interval to michael@0: * each message and selects the message whose interval contains a michael@0: * given number. This can only handle a finite number of michael@0: * intervals. But in some languages, like Polish, one plural case michael@0: * applies to infinitely many intervals (e.g., the plural case applies to michael@0: * numbers ending with 2, 3, or 4 except those ending with 12, 13, or michael@0: * 14). Thus ChoiceFormat is not adequate. michael@0: *

michael@0: * PluralFormat deals with this by breaking the problem michael@0: * into two parts: michael@0: *

michael@0: *

michael@0: *

Usage of PluralFormat

michael@0: *

Note: Typically, plural formatting is done via MessageFormat michael@0: * with a plural argument type, michael@0: * rather than using a stand-alone PluralFormat. michael@0: *

michael@0: * This discussion assumes that you use PluralFormat with michael@0: * a predefined set of plural rules. You can create one using one of michael@0: * the constructors that takes a locale object. To michael@0: * specify the message pattern, you can either pass it to the michael@0: * constructor or set it explicitly using the michael@0: * applyPattern() method. The format() michael@0: * method takes a number object and selects the message of the michael@0: * matching plural case. This message will be returned. michael@0: *

michael@0: *
Patterns and Their Interpretation
michael@0: *

michael@0: * The pattern text defines the message output for each plural case of the michael@0: * specified locale. Syntax: michael@0: *

michael@0:  * pluralStyle = [offsetValue] (selector '{' message '}')+
michael@0:  * offsetValue = "offset:" number
michael@0:  * selector = explicitValue | keyword
michael@0:  * explicitValue = '=' number  // adjacent, no white space in between
michael@0:  * keyword = [^[[:Pattern_Syntax:][:Pattern_White_Space:]]]+
michael@0:  * message: see {@link MessageFormat}
michael@0:  * 
michael@0: * Pattern_White_Space between syntax elements is ignored, except michael@0: * between the {curly braces} and their sub-message, michael@0: * and between the '=' and the number of an explicitValue. michael@0: * michael@0: *

michael@0: * There are 6 predefined casekeyword in CLDR/ICU - 'zero', 'one', 'two', 'few', 'many' and michael@0: * 'other'. You always have to define a message text for the default plural case michael@0: * other which is contained in every rule set. michael@0: * If you do not specify a message text for a particular plural case, the michael@0: * message text of the plural case other gets assigned to this michael@0: * plural case. michael@0: *

michael@0: * When formatting, the input number is first matched against the explicitValue clauses. michael@0: * If there is no exact-number match, then a keyword is selected by calling michael@0: * the PluralRules with the input number minus the offset. michael@0: * (The offset defaults to 0 if it is omitted from the pattern string.) michael@0: * If there is no clause with that keyword, then the "other" clauses is returned. michael@0: *

michael@0: * An unquoted pound sign (#) in the selected sub-message michael@0: * itself (i.e., outside of arguments nested in the sub-message) michael@0: * is replaced by the input number minus the offset. michael@0: * The number-minus-offset value is formatted using a michael@0: * NumberFormat for the PluralFormat's locale. If you michael@0: * need special number formatting, you have to use a MessageFormat michael@0: * and explicitly specify a NumberFormat argument. michael@0: * Note: That argument is formatting without subtracting the offset! michael@0: * If you need a custom format and have a non-zero offset, then you need to pass the michael@0: * number-minus-offset value as a separate parameter. michael@0: *

michael@0: * For a usage example, see the {@link MessageFormat} class documentation. michael@0: * michael@0: *

Defining Custom Plural Rules

michael@0: *

If you need to use PluralFormat with custom rules, you can michael@0: * create a PluralRules object and pass it to michael@0: * PluralFormat's constructor. If you also specify a locale in this michael@0: * constructor, this locale will be used to format the number in the message michael@0: * texts. michael@0: *

michael@0: * For more information about PluralRules, see michael@0: * {@link PluralRules}. michael@0: *

michael@0: * michael@0: * ported from Java michael@0: * @stable ICU 4.0 michael@0: */ michael@0: michael@0: class U_I18N_API PluralFormat : public Format { michael@0: public: michael@0: michael@0: /** michael@0: * Creates a new cardinal-number PluralFormat for the default locale. michael@0: * This locale will be used to get the set of plural rules and for standard michael@0: * number formatting. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new cardinal-number PluralFormat for a given locale. michael@0: * @param locale the PluralFormat will be configured with michael@0: * rules for this locale. This locale will also be used for michael@0: * standard number formatting. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const Locale& locale, UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new PluralFormat for a given set of rules. michael@0: * The standard number formatting will be done using the default locale. michael@0: * @param rules defines the behavior of the PluralFormat michael@0: * object. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const PluralRules& rules, UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new PluralFormat for a given set of rules. michael@0: * The standard number formatting will be done using the given locale. michael@0: * @param locale the default number formatting will be done using this michael@0: * locale. michael@0: * @param rules defines the behavior of the PluralFormat michael@0: * object. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: *

michael@0: *

Sample code

michael@0: * \snippet samples/plurfmtsample/plurfmtsample.cpp PluralFormatExample1 michael@0: * \snippet samples/plurfmtsample/plurfmtsample.cpp PluralFormatExample michael@0: *

michael@0: */ michael@0: PluralFormat(const Locale& locale, const PluralRules& rules, UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new PluralFormat for the plural type. michael@0: * The standard number formatting will be done using the given locale. michael@0: * @param locale the default number formatting will be done using this michael@0: * locale. michael@0: * @param type The plural type (e.g., cardinal or ordinal). michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 50 michael@0: */ michael@0: PluralFormat(const Locale& locale, UPluralType type, UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new cardinal-number PluralFormat for a given pattern string. michael@0: * The default locale will be used to get the set of plural rules and for michael@0: * standard number formatting. michael@0: * @param pattern the pattern for this PluralFormat. michael@0: * errors are returned to status if the pattern is invalid. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const UnicodeString& pattern, UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new cardinal-number PluralFormat for a given pattern string and michael@0: * locale. michael@0: * The locale will be used to get the set of plural rules and for michael@0: * standard number formatting. michael@0: * @param locale the PluralFormat will be configured with michael@0: * rules for this locale. This locale will also be used for michael@0: * standard number formatting. michael@0: * @param pattern the pattern for this PluralFormat. michael@0: * errors are returned to status if the pattern is invalid. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const Locale& locale, const UnicodeString& pattern, UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new PluralFormat for a given set of rules, a michael@0: * pattern and a locale. michael@0: * @param rules defines the behavior of the PluralFormat michael@0: * object. michael@0: * @param pattern the pattern for this PluralFormat. michael@0: * errors are returned to status if the pattern is invalid. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const PluralRules& rules, michael@0: const UnicodeString& pattern, michael@0: UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new PluralFormat for a given set of rules, a michael@0: * pattern and a locale. michael@0: * @param locale the PluralFormat will be configured with michael@0: * rules for this locale. This locale will also be used for michael@0: * standard number formatting. michael@0: * @param rules defines the behavior of the PluralFormat michael@0: * object. michael@0: * @param pattern the pattern for this PluralFormat. michael@0: * errors are returned to status if the pattern is invalid. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const Locale& locale, michael@0: const PluralRules& rules, michael@0: const UnicodeString& pattern, michael@0: UErrorCode& status); michael@0: michael@0: /** michael@0: * Creates a new PluralFormat for a plural type, a michael@0: * pattern and a locale. michael@0: * @param locale the PluralFormat will be configured with michael@0: * rules for this locale. This locale will also be used for michael@0: * standard number formatting. michael@0: * @param type The plural type (e.g., cardinal or ordinal). michael@0: * @param pattern the pattern for this PluralFormat. michael@0: * errors are returned to status if the pattern is invalid. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 50 michael@0: */ michael@0: PluralFormat(const Locale& locale, michael@0: UPluralType type, michael@0: const UnicodeString& pattern, michael@0: UErrorCode& status); michael@0: michael@0: /** michael@0: * copy constructor. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat(const PluralFormat& other); michael@0: michael@0: /** michael@0: * Destructor. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: virtual ~PluralFormat(); michael@0: michael@0: /** michael@0: * Sets the pattern used by this plural format. michael@0: * The method parses the pattern and creates a map of format strings michael@0: * for the plural rules. michael@0: * Patterns and their interpretation are specified in the class description. michael@0: * michael@0: * @param pattern the pattern for this plural format michael@0: * errors are returned to status if the pattern is invalid. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: void applyPattern(const UnicodeString& pattern, UErrorCode& status); michael@0: michael@0: michael@0: using Format::format; michael@0: michael@0: /** michael@0: * Formats a plural message for a given number. michael@0: * michael@0: * @param number a number for which the plural message should be formatted michael@0: * for. If no pattern has been applied to this michael@0: * PluralFormat object yet, the formatted number michael@0: * will be returned. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @return the string containing the formatted plural message. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: UnicodeString format(int32_t number, UErrorCode& status) const; michael@0: michael@0: /** michael@0: * Formats a plural message for a given number. michael@0: * michael@0: * @param number a number for which the plural message should be formatted michael@0: * for. If no pattern has been applied to this michael@0: * PluralFormat object yet, the formatted number michael@0: * will be returned. michael@0: * @param status output param set to success or failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @return the string containing the formatted plural message. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: UnicodeString format(double number, UErrorCode& status) const; michael@0: michael@0: /** michael@0: * Formats a plural message for a given number. michael@0: * michael@0: * @param number a number for which the plural message should be formatted michael@0: * for. If no pattern has been applied to this michael@0: * PluralFormat object yet, the formatted number michael@0: * will be returned. michael@0: * @param appendTo output parameter to receive result. michael@0: * result is appended to existing contents. michael@0: * @param pos On input: an alignment field, if desired. michael@0: * On output: the offsets of the alignment field. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @return the string containing the formatted plural message. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: UnicodeString& format(int32_t number, michael@0: UnicodeString& appendTo, michael@0: FieldPosition& pos, michael@0: UErrorCode& status) const; michael@0: michael@0: /** michael@0: * Formats a plural message for a given number. michael@0: * michael@0: * @param number a number for which the plural message should be formatted michael@0: * for. If no pattern has been applied to this michael@0: * PluralFormat object yet, the formatted number michael@0: * will be returned. michael@0: * @param appendTo output parameter to receive result. michael@0: * result is appended to existing contents. michael@0: * @param pos On input: an alignment field, if desired. michael@0: * On output: the offsets of the alignment field. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @return the string containing the formatted plural message. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: UnicodeString& format(double number, michael@0: UnicodeString& appendTo, michael@0: FieldPosition& pos, michael@0: UErrorCode& status) const; michael@0: michael@0: #ifndef U_HIDE_DEPRECATED_API michael@0: /** michael@0: * Sets the locale used by this PluraFormat object. michael@0: * Note: Calling this method resets this PluraFormat object, michael@0: * i.e., a pattern that was applied previously will be removed, michael@0: * and the NumberFormat is set to the default number format for michael@0: * the locale. The resulting format behaves the same as one michael@0: * constructed from {@link #PluralFormat(const Locale& locale, UPluralType type, UErrorCode& status)} michael@0: * with UPLURAL_TYPE_CARDINAL. michael@0: * @param locale the locale to use to configure the formatter. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @deprecated ICU 50 This method clears the pattern and might create michael@0: * a different kind of PluralRules instance; michael@0: * use one of the constructors to create a new instance instead. michael@0: */ michael@0: void setLocale(const Locale& locale, UErrorCode& status); michael@0: #endif /* U_HIDE_DEPRECATED_API */ michael@0: michael@0: /** michael@0: * Sets the number format used by this formatter. You only need to michael@0: * call this if you want a different number format than the default michael@0: * formatter for the locale. michael@0: * @param format the number format to use. michael@0: * @param status output param set to success/failure code on exit, which michael@0: * must not indicate a failure before the function call. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: void setNumberFormat(const NumberFormat* format, UErrorCode& status); michael@0: michael@0: /** michael@0: * Assignment operator michael@0: * michael@0: * @param other the PluralFormat object to copy from. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: PluralFormat& operator=(const PluralFormat& other); michael@0: michael@0: /** michael@0: * Return true if another object is semantically equal to this one. michael@0: * michael@0: * @param other the PluralFormat object to be compared with. michael@0: * @return true if other is semantically equal to this. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: virtual UBool operator==(const Format& other) const; michael@0: michael@0: /** michael@0: * Return true if another object is semantically unequal to this one. michael@0: * michael@0: * @param other the PluralFormat object to be compared with. michael@0: * @return true if other is semantically unequal to this. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: virtual UBool operator!=(const Format& other) const; michael@0: michael@0: /** michael@0: * Clones this Format object polymorphically. The caller owns the michael@0: * result and should delete it when done. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: virtual Format* clone(void) const; michael@0: michael@0: /** michael@0: * Formats a plural message for a number taken from a Formattable object. michael@0: * michael@0: * @param obj The object containing a number for which the michael@0: * plural message should be formatted. michael@0: * The object must be of a numeric type. michael@0: * @param appendTo output parameter to receive result. michael@0: * Result is appended to existing contents. michael@0: * @param pos On input: an alignment field, if desired. michael@0: * On output: the offsets of the alignment field. michael@0: * @param status output param filled with success/failure status. michael@0: * @return Reference to 'appendTo' parameter. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: UnicodeString& format(const Formattable& obj, michael@0: UnicodeString& appendTo, michael@0: FieldPosition& pos, michael@0: UErrorCode& status) const; michael@0: michael@0: /** michael@0: * Returns the pattern from applyPattern() or constructor(). michael@0: * michael@0: * @param appendTo output parameter to receive result. michael@0: * Result is appended to existing contents. michael@0: * @return the UnicodeString with inserted pattern. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: UnicodeString& toPattern(UnicodeString& appendTo); michael@0: michael@0: /** michael@0: * This method is not yet supported by PluralFormat. michael@0: *

michael@0: * Before calling, set parse_pos.index to the offset you want to start michael@0: * parsing at in the source. After calling, parse_pos.index is the end of michael@0: * the text you parsed. If error occurs, index is unchanged. michael@0: *

michael@0: * When parsing, leading whitespace is discarded (with a successful parse), michael@0: * while trailing whitespace is left as is. michael@0: *

michael@0: * See Format::parseObject() for more. michael@0: * michael@0: * @param source The string to be parsed into an object. michael@0: * @param result Formattable to be set to the parse result. michael@0: * If parse fails, return contents are undefined. michael@0: * @param parse_pos The position to start parsing at. Upon return michael@0: * this param is set to the position after the michael@0: * last character successfully parsed. If the michael@0: * source is not parsed successfully, this param michael@0: * will remain unchanged. michael@0: * @stable ICU 4.0 michael@0: */ michael@0: virtual void parseObject(const UnicodeString& source, michael@0: Formattable& result, michael@0: ParsePosition& parse_pos) const; michael@0: michael@0: /** michael@0: * ICU "poor man's RTTI", returns a UClassID for this class. michael@0: * michael@0: * @stable ICU 4.0 michael@0: * michael@0: */ michael@0: static UClassID U_EXPORT2 getStaticClassID(void); michael@0: michael@0: /** michael@0: * ICU "poor man's RTTI", returns a UClassID for the actual class. michael@0: * michael@0: * @stable ICU 4.0 michael@0: */ michael@0: virtual UClassID getDynamicClassID() const; michael@0: michael@0: #if (defined(__xlC__) && (__xlC__ < 0x0C00)) || (U_PLATFORM == U_PF_OS390) || (U_PLATFORM ==U_PF_OS400) michael@0: // Work around a compiler bug on xlC 11.1 on AIX 7.1 that would michael@0: // prevent PluralSelectorAdapter from implementing private PluralSelector. michael@0: // xlC error message: michael@0: // 1540-0300 (S) The "private" member "class icu_49::PluralFormat::PluralSelector" cannot be accessed. michael@0: public: michael@0: #else michael@0: private: michael@0: #endif michael@0: /** michael@0: * @internal michael@0: */ michael@0: class U_I18N_API PluralSelector : public UMemory { michael@0: public: michael@0: virtual ~PluralSelector(); michael@0: /** michael@0: * Given a number, returns the appropriate PluralFormat keyword. michael@0: * michael@0: * @param context worker object for the selector. michael@0: * @param number The number to be plural-formatted. michael@0: * @param ec Error code. michael@0: * @return The selected PluralFormat keyword. michael@0: * @internal michael@0: */ michael@0: virtual UnicodeString select(void *context, double number, UErrorCode& ec) const = 0; michael@0: }; michael@0: michael@0: /** michael@0: * @internal michael@0: */ michael@0: class U_I18N_API PluralSelectorAdapter : public PluralSelector { michael@0: public: michael@0: PluralSelectorAdapter() : pluralRules(NULL) { michael@0: } michael@0: michael@0: virtual ~PluralSelectorAdapter(); michael@0: michael@0: virtual UnicodeString select(void *context, double number, UErrorCode& /*ec*/) const; /**< @internal */ michael@0: michael@0: void reset(); michael@0: michael@0: PluralRules* pluralRules; michael@0: }; michael@0: michael@0: #if defined(__xlC__) michael@0: // End of xlC bug workaround, keep remaining definitions private. michael@0: private: michael@0: #endif michael@0: Locale locale; michael@0: MessagePattern msgPattern; michael@0: NumberFormat* numberFormat; michael@0: double offset; michael@0: PluralSelectorAdapter pluralRulesWrapper; michael@0: michael@0: PluralFormat(); // default constructor not implemented michael@0: void init(const PluralRules* rules, UPluralType type, UErrorCode& status); michael@0: /** michael@0: * Copies dynamically allocated values (pointer fields). michael@0: * Others are copied using their copy constructors and assignment operators. michael@0: */ michael@0: void copyObjects(const PluralFormat& other); michael@0: michael@0: UnicodeString& format(const Formattable& numberObject, double number, michael@0: UnicodeString& appendTo, michael@0: FieldPosition& pos, michael@0: UErrorCode& status) const; /**< @internal */ michael@0: michael@0: /** michael@0: * Finds the PluralFormat sub-message for the given number, or the "other" sub-message. michael@0: * @param pattern A MessagePattern. michael@0: * @param partIndex the index of the first PluralFormat argument style part. michael@0: * @param selector the PluralSelector for mapping the number (minus offset) to a keyword. michael@0: * @param context worker object for the selector. michael@0: * @param number a number to be matched to one of the PluralFormat argument's explicit values, michael@0: * or mapped via the PluralSelector. michael@0: * @param ec ICU error code. michael@0: * @return the sub-message start part index. michael@0: */ michael@0: static int32_t findSubMessage( michael@0: const MessagePattern& pattern, int32_t partIndex, michael@0: const PluralSelector& selector, void *context, double number, UErrorCode& ec); /**< @internal */ michael@0: michael@0: friend class MessageFormat; michael@0: }; michael@0: michael@0: U_NAMESPACE_END michael@0: michael@0: #endif /* #if !UCONFIG_NO_FORMATTING */ michael@0: michael@0: #endif // _PLURFMT michael@0: //eof