+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
-* Copyright (C) 2007-2010, International Business Machines Corporation and
+* Copyright (C) 2007-2014, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
* File PLURFMT.H
-*
-* Modification History:*
-* Date Name Description
-*
********************************************************************************
*/
#if !UCONFIG_NO_FORMATTING
+#include "unicode/messagepattern.h"
#include "unicode/numfmt.h"
#include "unicode/plurrule.h"
+#if U_SHOW_CPLUSPLUS_API
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 users language and the
+ * plural case that can appear in the user's language and the
* <code>PluralFormat</code> selects the appropriate message based on
* the number.
* </p>
* 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., paucal applies to
+ * 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>
* 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 locales. Thus, the programmer
- * need not worry about the plural cases of a language. On the flip side,
- * the localizer does not have to specify the plural cases; he can simply
+ * <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 CLDR <i>Language Plural Rules</i> page at
+ * rules, see the CLDR <i>Language Plural Rules</i> page at
* http://unicode.org/repos/cldr-tmp/trunk/diff/supplemental/language_plural_rules.html
* </ul>
* </p>
* <h4>Usage of <code>PluralFormat</code></h4>
- * <p>
+ * <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
* <h5>Patterns and Their Interpretation</h5>
* <p>
* The pattern text defines the message output for each plural case of the
- * used locale. The pattern is a sequence of
- * <code><i>caseKeyword</i>{<i>message</i>}</code> clauses, separated by white
- * space characters. Each clause assigns the message <code><i>message</i></code>
- * to the plural case identified by <code><i>caseKeyword</i></code>.
+ * 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 ICU - 'zero', 'one', 'two', 'few', 'many' and
+ * 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 the plural
- * rules of the <code>PluralFormat</code> object do not contain a plural case
- * identified by <code><i>caseKeyword</i></code>, U_DEFAULT_KEYWORD_MISSING
- * will be set to status.
+ * <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. If you specify more than one message for the same plural case,
- * U_DUPLICATE_KEYWORD will be set to status.
- * <br>
- * Spaces between <code><i>caseKeyword</i></code> and
- * <code><i>message</i></code> will be ignored; spaces within
- * <code><i>message</i></code> will be preserved.
+ * 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>
- * The message text for a particular plural case may contain other message
- * format patterns. <code>PluralFormat</code> preserves these so that you
- * can use the strings produced by <code>PluralFormat</code> with other
- * formatters. If you are using <code>PluralFormat</code> inside a
- * <code>MessageFormat</code> pattern, <code>MessageFormat</code> will
- * automatically evaluate the resulting format pattern.<br>
- * Thus, curly braces (<code>{</code>, <code>}</code>) are <i>only</i> allowed
- * in message texts to define a nested format pattern.<br>
- * The pound sign (<code>#</code>) will be interpreted as the number placeholder
- * in the message text, if it is not contained in curly braces (to preserve
- * <code>NumberFormat</code> patterns). <code>PluralFormat</code> will
- * replace each of those pound signs by the number passed to the
- * <code>format()</code> method. It will be formatted using a
+ * 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 explicitly specify a
- * <code>NumberFormat</code> for the <code>PluralFormat</code> to use.
- * </p>
- * Example
- * <pre>
- * \code
- * UErrorCode status = U_ZERO_ERROR;
- * MessageFormat* msgFmt = new MessageFormat(UnicodeString("{0, plural,
- * one{{0, number, C''est #,##0.0# fichier}} other {Ce sont # fichiers}} dans la liste."),
- * Locale("fr"), status);
- * if (U_FAILURE(status)) {
- * return;
- * }
- * Formattable args1[] = {(int32_t)0};
- * Formattable args2[] = {(int32_t)3};
- * FieldPosition ignore(FieldPosition::DONT_CARE);
- * UnicodeString result;
- * msgFmt->format(args1, 1, result, ignore, status);
- * cout << result << endl;
- * result.remove();
- * msgFmt->format(args2, 1, result, ignore, status);
- * cout << result << endl;
- * \endcode
- * </pre>
- * Produces the output:<br>
- * <code>C'est 0,0 fichier dans la liste.</code><br>
- * <code>Ce sont 3 fichiers dans la liste.</code>
- * <p>
- * <strong>Note:</strong><br>
- * Currently <code>PluralFormat</code>
- * does not make use of quotes like <code>MessageFormat</code>.
- * If you use plural format strings with <code>MessageFormat</code> and want
- * to use a quote sign <code>'</code>, you have to write <code>''</code>.
- * <code>MessageFormat</code> unquotes this pattern and passes the unquoted
- * pattern to <code>PluralFormat</code>. It's a bit trickier if you use
- * nested formats that do quoting. In the example above, we wanted to insert
- * <code>'</code> in the number format pattern. Since
- * <code>NumberFormat</code> supports quotes, we had to insert
- * <code>''</code>. But since <code>MessageFormat</code> unquotes the
- * pattern before it gets passed to <code>PluralFormat</code>, we have to
- * double these quotes, i.e. write <code>''''</code>.
+ * 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
public:
/**
- * Creates a new <code>PluralFormat</code> for the default locale.
+ * Creates a new cardinal-number <code>PluralFormat</code> for the default locale.
* This locale will be used to get the set of plural rules and for standard
* number formatting.
* @param status output param set to success/failure code on exit, which
PluralFormat(UErrorCode& status);
/**
- * Creates a new <code>PluralFormat</code> for a given locale.
+ * Creates a new cardinal-number <code>PluralFormat</code> for a given locale.
* @param locale the <code>PluralFormat</code> will be configured with
* rules for this locale. This locale will also be used for
* standard number formatting.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
+ * <p>
+ * <h4>Sample code</h4>
+ * \snippet samples/plurfmtsample/plurfmtsample.cpp PluralFormatExample1
+ * \snippet samples/plurfmtsample/plurfmtsample.cpp PluralFormatExample
+ * <p>
*/
PluralFormat(const Locale& locale, const PluralRules& rules, UErrorCode& status);
/**
- * Creates a new <code>PluralFormat</code> for a given pattern string.
+ * Creates a new <code>PluralFormat</code> for the plural type.
+ * The standard number formatting will be done using the given locale.
+ * @param locale the default number formatting will be done using this
+ * locale.
+ * @param type The plural type (e.g., cardinal or ordinal).
+ * @param status output param set to success/failure code on exit, which
+ * must not indicate a failure before the function call.
+ * @stable ICU 50
+ */
+ PluralFormat(const Locale& locale, UPluralType type, UErrorCode& status);
+
+ /**
+ * Creates a new cardinal-number <code>PluralFormat</code> for a given pattern string.
* The default locale will be used to get the set of plural rules and for
* standard number formatting.
* @param pattern the pattern for this <code>PluralFormat</code>.
PluralFormat(const UnicodeString& pattern, UErrorCode& status);
/**
- * Creates a new <code>PluralFormat</code> for a given pattern string and
+ * Creates a new cardinal-number <code>PluralFormat</code> for a given pattern string and
* locale.
* The locale will be used to get the set of plural rules and for
* standard number formatting.
const UnicodeString& pattern,
UErrorCode& status);
+ /**
+ * Creates a new <code>PluralFormat</code> for a plural type, a
+ * pattern and a locale.
+ * @param locale the <code>PluralFormat</code> will be configured with
+ * rules for this locale. This locale will also be used for
+ * standard number formatting.
+ * @param type The plural type (e.g., cardinal or ordinal).
+ * @param pattern the pattern for this <code>PluralFormat</code>.
+ * errors are returned to status if the pattern is invalid.
+ * @param status output param set to success/failure code on exit, which
+ * must not indicate a failure before the function call.
+ * @stable ICU 50
+ */
+ PluralFormat(const Locale& locale,
+ UPluralType type,
+ const UnicodeString& pattern,
+ UErrorCode& status);
+
/**
* copy constructor.
* @stable ICU 4.0
FieldPosition& pos,
UErrorCode& status) const;
+#ifndef U_HIDE_DEPRECATED_API
/**
* Sets the locale used by this <code>PluraFormat</code> object.
* Note: Calling this method resets this <code>PluraFormat</code> object,
* i.e., a pattern that was applied previously will be removed,
* and the NumberFormat is set to the default number format for
* the locale. The resulting format behaves the same as one
- * constructed from {@link #PluralFormat(const Locale& locale, UErrorCode& status)}.
+ * constructed from {@link #PluralFormat(const Locale& locale, UPluralType type, UErrorCode& status)}
+ * with UPLURAL_TYPE_CARDINAL.
* @param locale the <code>locale</code> to use to configure the formatter.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
- * @stable ICU 4.0
+ * @deprecated ICU 50 This method clears the pattern and might create
+ * a different kind of PluralRules instance;
+ * use one of the constructors to create a new instance instead.
*/
void setLocale(const Locale& locale, UErrorCode& status);
+#endif /* U_HIDE_DEPRECATED_API */
/**
* Sets the number format used by this formatter. You only need to
*/
virtual Format* clone(void) const;
- /**
- * Redeclared Format method.
+ /**
+ * Formats a plural message for a number taken from a Formattable object.
*
- * @param obj The object to be formatted into a string.
+ * @param obj The object containing a number for which the
+ * plural message should be formatted.
+ * The object must be of a numeric type.
* @param appendTo output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
*/
virtual UClassID getDynamicClassID() const;
+#if (defined(__xlC__) && (__xlC__ < 0x0C00)) || (U_PLATFORM == U_PF_OS390) || (U_PLATFORM ==U_PF_OS400)
+// Work around a compiler bug on xlC 11.1 on AIX 7.1 that would
+// prevent PluralSelectorAdapter from implementing private PluralSelector.
+// xlC error message:
+// 1540-0300 (S) The "private" member "class icu_49::PluralFormat::PluralSelector" cannot be accessed.
+public:
+#else
private:
- typedef enum fmtToken {
- none,
- tLetter,
- tNumber,
- tSpace,
- tNumberSign,
- tLeftBrace,
- tRightBrace
- }fmtToken;
+#endif
+ /**
+ * @internal
+ */
+ class U_I18N_API PluralSelector : public UMemory {
+ public:
+ virtual ~PluralSelector();
+ /**
+ * Given a number, returns the appropriate PluralFormat keyword.
+ *
+ * @param context worker object for the selector.
+ * @param number The number to be plural-formatted.
+ * @param ec Error code.
+ * @return The selected PluralFormat keyword.
+ * @internal
+ */
+ virtual UnicodeString select(void *context, double number, UErrorCode& ec) const = 0;
+ };
+
+ /**
+ * @internal
+ */
+ class U_I18N_API PluralSelectorAdapter : public PluralSelector {
+ public:
+ PluralSelectorAdapter() : pluralRules(NULL) {
+ }
+
+ virtual ~PluralSelectorAdapter();
+ virtual UnicodeString select(void *context, double number, UErrorCode& /*ec*/) const; /**< @internal */
+
+ void reset();
+
+ PluralRules* pluralRules;
+ };
+
+#if defined(__xlC__)
+// End of xlC bug workaround, keep remaining definitions private.
+private:
+#endif
Locale locale;
- PluralRules* pluralRules;
- UnicodeString pattern;
- Hashtable *fParsedValuesHash;
+ MessagePattern msgPattern;
NumberFormat* numberFormat;
- NumberFormat* replacedNumberFormat;
+ double offset;
+ PluralSelectorAdapter pluralRulesWrapper;
PluralFormat(); // default constructor not implemented
- void init(const PluralRules* rules, const Locale& curlocale, UErrorCode& status);
- UBool inRange(UChar ch, fmtToken& type);
- UBool checkSufficientDefinition();
- void parsingFailure();
- UnicodeString insertFormattedNumber(double number,
- UnicodeString& message,
- UnicodeString& appendTo,
- FieldPosition& pos) const;
- void copyHashtable(Hashtable *other, UErrorCode& status);
+ void init(const PluralRules* rules, UPluralType type, UErrorCode& status);
+ /**
+ * Copies dynamically allocated values (pointer fields).
+ * Others are copied using their copy constructors and assignment operators.
+ */
+ void copyObjects(const PluralFormat& other);
+
+ UnicodeString& format(const Formattable& numberObject, double number,
+ UnicodeString& appendTo,
+ FieldPosition& pos,
+ UErrorCode& status) const; /**< @internal */
+
+ /**
+ * Finds the PluralFormat sub-message for the given number, or the "other" sub-message.
+ * @param pattern A MessagePattern.
+ * @param partIndex the index of the first PluralFormat argument style part.
+ * @param selector the PluralSelector for mapping the number (minus offset) to a keyword.
+ * @param context worker object for the selector.
+ * @param number a number to be matched to one of the PluralFormat argument's explicit values,
+ * or mapped via the PluralSelector.
+ * @param ec ICU error code.
+ * @return the sub-message start part index.
+ */
+ static int32_t findSubMessage(
+ const MessagePattern& pattern, int32_t partIndex,
+ const PluralSelector& selector, void *context, double number, UErrorCode& ec); /**< @internal */
+
+ void parseType(const UnicodeString& source, const NFRule *rbnfLenientScanner,
+ Formattable& result, FieldPosition& pos) const;
+
+ friend class MessageFormat;
+ friend class NFRule;
};
U_NAMESPACE_END
+#endif // U_SHOW_CPLUSPLUS_API
#endif /* #if !UCONFIG_NO_FORMATTING */
projects / apple / icu.git / blobdiff