michael@0: /********************************************************************
michael@0:  * COPYRIGHT:
michael@0:  * Copyright (c) 1997-2011, International Business Machines Corporation and
michael@0:  * others. All Rights Reserved.
michael@0:  * Copyright (C) 2010 , Yahoo! Inc.
michael@0:  ********************************************************************
michael@0:  *
michael@0:  * File SELFMT.H
michael@0:  *
michael@0:  * Modification History:
michael@0:  *
michael@0:  *   Date        Name        Description
michael@0:  *   11/11/09    kirtig      Finished first cut of implementation.
michael@0:  ********************************************************************/
michael@0: 
michael@0: #ifndef SELFMT
michael@0: #define SELFMT
michael@0: 
michael@0: #include "unicode/messagepattern.h"
michael@0: #include "unicode/numfmt.h"
michael@0: #include "unicode/utypes.h"
michael@0: 
michael@0: /**
michael@0:  * \file
michael@0:  * \brief C++ API: SelectFormat object
michael@0:  */
michael@0: 
michael@0: #if !UCONFIG_NO_FORMATTING
michael@0: 
michael@0: U_NAMESPACE_BEGIN
michael@0: 
michael@0: class MessageFormat;
michael@0: 
michael@0: /**
michael@0:   * <p><code>SelectFormat</code> supports the creation of  internationalized
michael@0:   * messages by selecting phrases based on keywords. The pattern  specifies
michael@0:   * how to map keywords to phrases and provides a default phrase. The
michael@0:   * object provided to the format method is a string that's matched
michael@0:   * against the keywords. If there is a match, the corresponding phrase
michael@0:   * is selected; otherwise, the default phrase is used.</p>
michael@0:   *
michael@0:   * <h4>Using <code>SelectFormat</code> for Gender Agreement</h4>
michael@0:   *
michael@0:   * <p>Note: Typically, select formatting is done via <code>MessageFormat</code>
michael@0:   * with a <code>select</code> argument type,
michael@0:   * rather than using a stand-alone <code>SelectFormat</code>.</p>
michael@0:   *
michael@0:   * <p>The main use case for the select format is gender based  inflection.
michael@0:   * When names or nouns are inserted into sentences, their gender can  affect pronouns,
michael@0:   * verb forms, articles, and adjectives. Special care needs to be
michael@0:   * taken for the case where the gender cannot be determined.
michael@0:   * The impact varies between languages:</p>
michael@0:   * \htmlonly
michael@0:   * <ul>
michael@0:   * <li>English has three genders, and unknown gender is handled as a  special
michael@0:   * case. Names use the gender of the named person (if known), nouns  referring
michael@0:   * to people use natural gender, and inanimate objects are usually  neutral.
michael@0:   * The gender only affects pronouns: "he", "she", "it", "they".
michael@0:   *
michael@0:   * <li>German differs from English in that the gender of nouns is  rather
michael@0:   * arbitrary, even for nouns referring to people ("M&#x00E4;dchen", girl, is  neutral).
michael@0:   * The gender affects pronouns ("er", "sie", "es"), articles ("der",  "die",
michael@0:   * "das"), and adjective forms ("guter Mann", "gute Frau", "gutes  M&#x00E4;dchen").
michael@0:   *
michael@0:   * <li>French has only two genders; as in German the gender of nouns
michael@0:   * is rather arbitrary - for sun and moon, the genders
michael@0:   * are the opposite of those in German. The gender affects
michael@0:   * pronouns ("il", "elle"), articles ("le", "la"),
michael@0:   * adjective forms ("bon", "bonne"), and sometimes
michael@0:   * verb forms ("all&#x00E9;", "all&#x00E9;e").
michael@0:   *
michael@0:   * <li>Polish distinguishes five genders (or noun classes),
michael@0:   * human masculine, animate non-human masculine, inanimate masculine,
michael@0:   * feminine, and neuter.
michael@0:   * </ul>
michael@0:   * \endhtmlonly
michael@0:   * <p>Some other languages have noun classes that are not related to  gender,
michael@0:   * but similar in grammatical use.
michael@0:   * Some African languages have around 20 noun classes.</p>
michael@0:   *
michael@0:   * <p><b>Note:</b>For the gender of a <i>person</i> in a given sentence,
michael@0:   * we usually need to distinguish only between female, male and other/unknown.</p>
michael@0:   *
michael@0:   * <p>To enable localizers to create sentence patterns that take their
michael@0:   * language's gender dependencies into consideration, software has to  provide
michael@0:   * information about the gender associated with a noun or name to
michael@0:   * <code>MessageFormat</code>.
michael@0:   * Two main cases can be distinguished:</p>
michael@0:   *
michael@0:   * <ul>
michael@0:   * <li>For people, natural gender information should be maintained  for each person.
michael@0:   * Keywords like "male", "female", "mixed" (for groups of people)
michael@0:   * and "unknown" could be used.
michael@0:   *
michael@0:   * <li>For nouns, grammatical gender information should be maintained  for
michael@0:   * each noun and per language, e.g., in resource bundles.
michael@0:   * The keywords "masculine", "feminine", and "neuter" are commonly  used,
michael@0:   * but some languages may require other keywords.
michael@0:   * </ul>
michael@0:   *
michael@0:   * <p>The resulting keyword is provided to <code>MessageFormat</code>  as a
michael@0:   * parameter separate from the name or noun it's associated with. For  example,
michael@0:   * to generate a message such as "Jean went to Paris", three separate  arguments
michael@0:   * would be provided: The name of the person as argument 0, the  gender of
michael@0:   * the person as argument 1, and the name of the city as argument 2.
michael@0:   * The sentence pattern for English, where the gender of the person has
michael@0:   * no impact on this simple sentence, would not refer to argument 1  at all:</p>
michael@0:   *
michael@0:   * <pre>{0} went to {2}.</pre>
michael@0:   *
michael@0:   * <p><b>Note:</b> The entire sentence should be included (and partially repeated)
michael@0:   * inside each phrase. Otherwise translators would have to be trained on how to
michael@0:   * move bits of the sentence in and out of the select argument of a message.
michael@0:   * (The examples below do not follow this recommendation!)</p>
michael@0:   *
michael@0:   * <p>The sentence pattern for French, where the gender of the person affects
michael@0:   * the form of the participle, uses a select format based on argument 1:</p>
michael@0:   *
michael@0:   * \htmlonly<pre>{0} est {1, select, female {all&#x00E9;e} other {all&#x00E9;}} &#x00E0; {2}.</pre>\endhtmlonly
michael@0:   *
michael@0:   * <p>Patterns can be nested, so that it's possible to handle  interactions of
michael@0:   * number and gender where necessary. For example, if the above  sentence should
michael@0:   * allow for the names of several people to be inserted, the  following sentence
michael@0:   * pattern can be used (with argument 0 the list of people's names,
michael@0:   * argument 1 the number of people, argument 2 their combined gender, and
michael@0:   * argument 3 the city name):</p>
michael@0:   *
michael@0:   * \htmlonly
michael@0:   * <pre>{0} {1, plural,
michael@0:   *                 one {est {2, select, female {all&#x00E9;e} other  {all&#x00E9;}}}
michael@0:   *                 other {sont {2, select, female {all&#x00E9;es} other {all&#x00E9;s}}}
michael@0:   *          }&#x00E0; {3}.</pre>
michael@0:   * \endhtmlonly
michael@0:   *
michael@0:   * <h4>Patterns and Their Interpretation</h4>
michael@0:   *
michael@0:   * <p>The <code>SelectFormat</code> pattern string defines the phrase output
michael@0:   * for each user-defined keyword.
michael@0:   * The pattern is a sequence of (keyword, message) pairs.
michael@0:   * A keyword is a "pattern identifier": [^[[:Pattern_Syntax:][:Pattern_White_Space:]]]+</p>
michael@0:   *
michael@0:   * <p>Each message is a MessageFormat pattern string enclosed in {curly braces}.</p>
michael@0:   *
michael@0:   * <p>You always have to define a phrase for the default keyword
michael@0:   * <code>other</code>; this phrase is returned when the keyword
michael@0:   * provided to
michael@0:   * the <code>format</code> method matches no other keyword.
michael@0:   * If a pattern does not provide a phrase for <code>other</code>, the  method
michael@0:   * it's provided to returns the error  <code>U_DEFAULT_KEYWORD_MISSING</code>.
michael@0:   * <br>
michael@0:   * Pattern_White_Space between keywords and messages is ignored.
michael@0:   * Pattern_White_Space within a message is preserved and output.</p>
michael@0:   *
michael@0:   * <p><pre>Example:
michael@0:   * \htmlonly
michael@0:   *
michael@0:   * UErrorCode status = U_ZERO_ERROR;
michael@0:   * MessageFormat *msgFmt = new MessageFormat(UnicodeString("{0} est  {1, select, female {all&#x00E9;e} other {all&#x00E9;}} &#x00E0; Paris."), Locale("fr"),  status);
michael@0:   * if (U_FAILURE(status)) {
michael@0:   *       return;
michael@0:   * }
michael@0:   * FieldPosition ignore(FieldPosition::DONT_CARE);
michael@0:   * UnicodeString result;
michael@0:   *
michael@0:   * char* str1= "Kirti,female";
michael@0:   * Formattable args1[] = {"Kirti","female"};
michael@0:   * msgFmt->format(args1, 2, result, ignore, status);
michael@0:   * cout << "Input is " << str1 << " and result is: " << result << endl;
michael@0:   * delete msgFmt;
michael@0:   *
michael@0:   * \endhtmlonly
michael@0:   * </pre>
michael@0:   * </p>
michael@0:   *
michael@0:   * Produces the output:<br>
michael@0:   * \htmlonly
michael@0:   * <code>Kirti est all&#x00E9;e &#x00E0; Paris.</code>
michael@0:   * \endhtmlonly
michael@0:   *
michael@0:   * @stable ICU 4.4
michael@0:   */
michael@0: 
michael@0: class U_I18N_API SelectFormat : public Format {
michael@0: public:
michael@0: 
michael@0:     /**
michael@0:      * Creates a new <code>SelectFormat</code> for a given pattern string.
michael@0:      * @param  pattern the pattern for this <code>SelectFormat</code>.
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 4.4
michael@0:      */
michael@0:     SelectFormat(const UnicodeString& pattern, UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:      * copy constructor.
michael@0:      * @stable ICU 4.4
michael@0:      */
michael@0:     SelectFormat(const SelectFormat& other);
michael@0: 
michael@0:     /**
michael@0:      * Destructor.
michael@0:      * @stable ICU 4.4
michael@0:      */
michael@0:     virtual ~SelectFormat();
michael@0: 
michael@0:     /**
michael@0:      * Sets the pattern used by this select format.
michael@0:      * for the keyword rules.
michael@0:      * Patterns and their interpretation are specified in the class description.
michael@0:      *
michael@0:      * @param pattern the pattern for this select 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 4.4
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:      * Selects the phrase for  the given keyword
michael@0:      *
michael@0:      * @param keyword  The keyword that is used to select an alternative.
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         Reference to 'appendTo' parameter.
michael@0:      * @stable ICU 4.4
michael@0:      */
michael@0:     UnicodeString& format(const UnicodeString& keyword,
michael@0:                             UnicodeString& appendTo,
michael@0:                             FieldPosition& pos,
michael@0:                             UErrorCode& status) const;
michael@0: 
michael@0:     /**
michael@0:      * Assignment operator
michael@0:      *
michael@0:      * @param other    the SelectFormat object to copy from.
michael@0:      * @stable ICU 4.4
michael@0:      */
michael@0:     SelectFormat& operator=(const SelectFormat& 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 SelectFormat object to be compared with.
michael@0:      * @return         true if other is semantically equal to this.
michael@0:      * @stable ICU 4.4
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 SelectFormat object to be compared with.
michael@0:      * @return         true if other is semantically unequal to this.
michael@0:      * @stable ICU 4.4
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 4.4
michael@0:      */
michael@0:     virtual Format* clone(void) const;
michael@0: 
michael@0:     /**
michael@0:      * Format an object to produce a string.
michael@0:      * This method handles keyword strings.
michael@0:      * If the Formattable object is not a <code>UnicodeString</code>,
michael@0:      * then it returns a failing UErrorCode.
michael@0:      *
michael@0:      * @param obj       A keyword string that is used to select an alternative.
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 4.4
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 4.4
michael@0:      */
michael@0:     UnicodeString& toPattern(UnicodeString& appendTo);
michael@0: 
michael@0:     /**
michael@0:      * This method is not yet supported by <code>SelectFormat</code>.
michael@0:      * <P>
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:      * <P>
michael@0:      * When parsing, leading whitespace is discarded (with a successful parse),
michael@0:      * while trailing whitespace is left as is.
michael@0:      * <P>
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 4.4
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:      * @stable ICU 4.4
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:      * @stable ICU 4.4
michael@0:      */
michael@0:     virtual UClassID getDynamicClassID() const;
michael@0: 
michael@0: private:
michael@0:     friend class MessageFormat;
michael@0: 
michael@0:     SelectFormat();   // default constructor not implemented.
michael@0: 
michael@0:     /**
michael@0:      * Finds the SelectFormat sub-message for the given keyword, or the "other" sub-message.
michael@0:      * @param pattern A MessagePattern.
michael@0:      * @param partIndex the index of the first SelectFormat argument style part.
michael@0:      * @param keyword a keyword to be matched to one of the SelectFormat argument's keywords.
michael@0:      * @param ec Error code.
michael@0:      * @return the sub-message start part index.
michael@0:      */
michael@0:     static int32_t findSubMessage(const MessagePattern& pattern, int32_t partIndex,
michael@0:                                   const UnicodeString& keyword, UErrorCode& ec);
michael@0: 
michael@0:     MessagePattern msgPattern;
michael@0: };
michael@0: 
michael@0: U_NAMESPACE_END
michael@0: 
michael@0: #endif /* #if !UCONFIG_NO_FORMATTING */
michael@0: 
michael@0: #endif // _SELFMT
michael@0: //eof