// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * Copyright (C) 1997-2015, International Business Machines Corporation and others. * All Rights Reserved. ******************************************************************************* */ #ifndef RBNF_H #define RBNF_H #include "unicode/utypes.h" #if U_SHOW_CPLUSPLUS_API /** * \file * \brief C++ API: Rule Based Number Format */ /** * \def U_HAVE_RBNF * This will be 0 if RBNF support is not included in ICU * and 1 if it is. * * @stable ICU 2.4 */ #if UCONFIG_NO_FORMATTING #define U_HAVE_RBNF 0 #else #define U_HAVE_RBNF 1 #include "unicode/dcfmtsym.h" #include "unicode/fmtable.h" #include "unicode/locid.h" #include "unicode/numfmt.h" #include "unicode/unistr.h" #include "unicode/strenum.h" #include "unicode/brkiter.h" #include "unicode/upluralrules.h" U_NAMESPACE_BEGIN class NFRule; class NFRuleSet; class LocalizationInfo; class PluralFormat; class RuleBasedCollator; /** * Tags for the predefined rulesets. * * @stable ICU 2.2 */ enum URBNFRuleSetTag { URBNF_SPELLOUT, URBNF_ORDINAL, URBNF_DURATION, URBNF_NUMBERING_SYSTEM, #ifndef U_HIDE_DEPRECATED_API /** * One more than the highest normal URBNFRuleSetTag value. * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. */ URBNF_COUNT #endif // U_HIDE_DEPRECATED_API }; /** * The RuleBasedNumberFormat class formats numbers according to a set of rules. This number formatter is * typically used for spelling out numeric values in words (e.g., 25,3476 as * "twenty-five thousand three hundred seventy-six" or "vingt-cinq mille trois * cents soixante-seize" or * "fünfundzwanzigtausenddreihundertsechsundsiebzig"), but can also be used for * other complicated formatting tasks, such as formatting a number of seconds as hours, * minutes and seconds (e.g., 3,730 as "1:02:10"). * *
The resources contain three predefined formatters for each locale: spellout, which * spells out a value in words (123 is "one hundred twenty-three"); ordinal, which * appends an ordinal suffix to the end of a numeral (123 is "123rd"); and * duration, which shows a duration in seconds as hours, minutes, and seconds (123 is * "2:03"). The client can also define more specialized RuleBasedNumberFormats * by supplying programmer-defined rule sets.
* *The behavior of a RuleBasedNumberFormat is specified by a textual description * that is either passed to the constructor as a String or loaded from a resource * bundle. In its simplest form, the description consists of a semicolon-delimited list of rules. * Each rule has a string of output text and a value or range of values it is applicable to. * In a typical spellout rule set, the first twenty rules are the words for the numbers from * 0 to 19:
* *zero; one; two; three; four; five; six; seven; eight; nine; * ten; eleven; twelve; thirteen; fourteen; fifteen; sixteen; seventeen; eighteen; nineteen;* *
For larger numbers, we can use the preceding set of rules to format the ones place, and * we only have to supply the words for the multiples of 10:
* *20: twenty[->>]; * 30: thirty[->>]; * 40: forty[->>]; * 50: fifty[->>]; * 60: sixty[->>]; * 70: seventy[->>]; * 80: eighty[->>]; * 90: ninety[->>];* *
In these rules, the base value is spelled out explicitly and set off from the * rule's output text with a colon. The rules are in a sorted list, and a rule is applicable * to all numbers from its own base value to one less than the next rule's base value. The * ">>" token is called a substitution and tells the formatter to * isolate the number's ones digit, format it using this same set of rules, and place the * result at the position of the ">>" token. Text in brackets is omitted if * the number being formatted is an even multiple of 10 (the hyphen is a literal hyphen; 24 * is "twenty-four," not "twenty four").
* *For even larger numbers, we can actually look up several parts of the number in the * list:
* *100: << hundred[ >>];* *
The "<<" represents a new kind of substitution. The << isolates * the hundreds digit (and any digits to its left), formats it using this same rule set, and * places the result where the "<<" was. Notice also that the meaning of * >> has changed: it now refers to both the tens and the ones digits. The meaning of * both substitutions depends on the rule's base value. The base value determines the rule's divisor, * which is the highest power of 10 that is less than or equal to the base value (the user * can change this). To fill in the substitutions, the formatter divides the number being * formatted by the divisor. The integral quotient is used to fill in the << * substitution, and the remainder is used to fill in the >> substitution. The meaning * of the brackets changes similarly: text in brackets is omitted if the value being * formatted is an even multiple of the rule's divisor. The rules are applied recursively, so * if a substitution is filled in with text that includes another substitution, that * substitution is also filled in.
* *This rule covers values up to 999, at which point we add another rule:
* *1000: << thousand[ >>];* *
Again, the meanings of the brackets and substitution tokens shift because the rule's * base value is a higher power of 10, changing the rule's divisor. This rule can actually be * used all the way up to 999,999. This allows us to finish out the rules as follows:
* *1,000,000: << million[ >>]; * 1,000,000,000: << billion[ >>]; * 1,000,000,000,000: << trillion[ >>]; * 1,000,000,000,000,000: OUT OF RANGE!;* *
Commas, periods, and spaces can be used in the base values to improve legibility and * are ignored by the rule parser. The last rule in the list is customarily treated as an * "overflow rule," applying to everything from its base value on up, and often (as * in this example) being used to print out an error message or default representation. * Notice also that the size of the major groupings in large numbers is controlled by the * spacing of the rules: because in English we group numbers by thousand, the higher rules * are separated from each other by a factor of 1,000.
* *To see how these rules actually work in practice, consider the following example: * Formatting 25,430 with this rule set would work like this:
* *<< thousand >> | *[the rule whose base value is 1,000 is applicable to 25,340] | *
twenty->> thousand >> | *[25,340 over 1,000 is 25. The rule for 20 applies.] | *
twenty-five thousand >> | *[25 mod 10 is 5. The rule for 5 is "five." | *
twenty-five thousand << hundred >> | *[25,340 mod 1,000 is 340. The rule for 100 applies.] | *
twenty-five thousand three hundred >> | *[340 over 100 is 3. The rule for 3 is "three."] | *
twenty-five thousand three hundred forty | *[340 mod 100 is 40. The rule for 40 applies. Since 40 divides * evenly by 10, the hyphen and substitution in the brackets are omitted.] | *
The above syntax suffices only to format positive integers. To format negative numbers, * we add a special rule:
* *-x: minus >>;* *
This is called a negative-number rule, and is identified by "-x" * where the base value would be. This rule is used to format all negative numbers. the * >> token here means "find the number's absolute value, format it with these * rules, and put the result here."
* *We also add a special rule called a fraction rule for numbers with fractional * parts:
* *x.x: << point >>;* *
This rule is used for all positive non-integers (negative non-integers pass through the * negative-number rule first and then through this rule). Here, the << token refers to * the number's integral part, and the >> to the number's fractional part. The * fractional part is formatted as a series of single-digit numbers (e.g., 123.456 would be * formatted as "one hundred twenty-three point four five six").
* *To see how this rule syntax is applied to various languages, examine the resource data.
* *There is actually much more flexibility built into the rule language than the * description above shows. A formatter may own multiple rule sets, which can be selected by * the caller, and which can use each other to fill in their substitutions. Substitutions can * also be filled in with digits, using a DecimalFormat object. There is syntax that can be * used to alter a rule's divisor in various ways. And there is provision for much more * flexible fraction handling. A complete description of the rule syntax follows:
* *The description of a RuleBasedNumberFormat's behavior consists of one or more rule * sets. Each rule set consists of a name, a colon, and a list of rules. A rule * set name must begin with a % sign. Rule sets with names that begin with a single % sign * are public: the caller can specify that they be used to format and parse numbers. * Rule sets with names that begin with %% are private: they exist only for the use * of other rule sets. If a formatter only has one rule set, the name may be omitted.
* *The user can also specify a special "rule set" named %%lenient-parse. * The body of %%lenient-parse isn't a set of number-formatting rules, but a RuleBasedCollator * description which is used to define equivalences for lenient parsing. For more information * on the syntax, see RuleBasedCollator. For more information on lenient parsing, * see setLenientParse(). Note: symbols that have syntactic meaning * in collation rules, such as '&', have no particular meaning when appearing outside * of the lenient-parse rule set.
* *The body of a rule set consists of an ordered, semicolon-delimited list of rules. * Internally, every rule has a base value, a divisor, rule text, and zero, one, or two substitutions. * These parameters are controlled by the description syntax, which consists of a rule * descriptor, a colon, and a rule body.
* *A rule descriptor can take one of the following forms (text in italics is the * name of a token):
* *bv: | *bv specifies the rule's base value. bv is a decimal * number expressed using ASCII digits. bv may contain spaces, period, and commas, * which are ignored. The rule's divisor is the highest power of 10 less than or equal to * the base value. | *
bv/rad: | *bv specifies the rule's base value. The rule's divisor is the * highest power of rad less than or equal to the base value. | *
bv>: | *bv specifies the rule's base value. To calculate the divisor, * let the radix be 10, and the exponent be the highest exponent of the radix that yields a * result less than or equal to the base value. Every > character after the base value * decreases the exponent by 1. If the exponent is positive or 0, the divisor is the radix * raised to the power of the exponent; otherwise, the divisor is 1. | *
bv/rad>: | *bv specifies the rule's base value. To calculate the divisor, * let the radix be rad, and the exponent be the highest exponent of the radix that * yields a result less than or equal to the base value. Every > character after the radix * decreases the exponent by 1. If the exponent is positive or 0, the divisor is the radix * raised to the power of the exponent; otherwise, the divisor is 1. | *
-x: | *The rule is a negative-number rule. | *
x.x: | *The rule is an improper fraction rule. If the full stop in * the middle of the rule name is replaced with the decimal point * that is used in the language or DecimalFormatSymbols, then that rule will * have precedence when formatting and parsing this rule. For example, some * languages use the comma, and can thus be written as x,x instead. For example, * you can use "x.x: << point >>;x,x: << comma >>;" to * handle the decimal point that matches the language's natural spelling of * the punctuation of either the full stop or comma. | *
0.x: | *The rule is a proper fraction rule. If the full stop in * the middle of the rule name is replaced with the decimal point * that is used in the language or DecimalFormatSymbols, then that rule will * have precedence when formatting and parsing this rule. For example, some * languages use the comma, and can thus be written as 0,x instead. For example, * you can use "0.x: point >>;0,x: comma >>;" to * handle the decimal point that matches the language's natural spelling of * the punctuation of either the full stop or comma. | *
x.0: | *The rule is a default rule. If the full stop in * the middle of the rule name is replaced with the decimal point * that is used in the language or DecimalFormatSymbols, then that rule will * have precedence when formatting and parsing this rule. For example, some * languages use the comma, and can thus be written as x,0 instead. For example, * you can use "x.0: << point;x,0: << comma;" to * handle the decimal point that matches the language's natural spelling of * the punctuation of either the full stop or comma. | *
Inf: | *The rule for infinity. | *
NaN: | *The rule for an IEEE 754 NaN (not a number). | *
nothing | *If the rule's rule descriptor is left out, the base value is one plus the * preceding rule's base value (or zero if this is the first rule in the list) in a normal * rule set. In a fraction rule set, the base value is the same as the preceding rule's * base value. | *
A rule set may be either a regular rule set or a fraction rule set, depending * on whether it is used to format a number's integral part (or the whole number) or a * number's fractional part. Using a rule set to format a rule's fractional part makes it a * fraction rule set.
* *Which rule is used to format a number is defined according to one of the following * algorithms: If the rule set is a regular rule set, do the following: * *
If the rule set is a fraction rule set, do the following: * *
A rule's body consists of a string of characters terminated by a semicolon. The rule * may include zero, one, or two substitution tokens, and a range of text in * brackets. The brackets denote optional text (and may also include one or both * substitutions). The exact meanings of the substitution tokens, and under what conditions * optional text is omitted, depend on the syntax of the substitution token and the context. * The rest of the text in a rule body is literal text that is output when the rule matches * the number being formatted.
* *A substitution token begins and ends with a token character. The token * character and the context together specify a mathematical operation to be performed on the * number being formatted. An optional substitution descriptor specifies how the * value resulting from that operation is used to fill in the substitution. The position of * the substitution token in the rule body specifies the location of the resultant text in * the original rule text.
* *The meanings of the substitution token characters are as follows:
* *>> | *in normal rule | *Divide the number by the rule's divisor and format the remainder | *|
* | in negative-number rule | *Find the absolute value of the number and format the result | *|
* | in fraction or default rule | *Isolate the number's fractional part and format it. | *|
* | in rule in fraction rule set | *Not allowed. | *|
>>> | *in normal rule | *Divide the number by the rule's divisor and format the remainder, * but bypass the normal rule-selection process and just use the * rule that precedes this one in this rule list. | *|
* | in all other rules | *Not allowed. | *|
<< | *in normal rule | *Divide the number by the rule's divisor and format the quotient | *|
* | in negative-number rule | *Not allowed. | *|
* | in fraction or default rule | *Isolate the number's integral part and format it. | *|
* | in rule in fraction rule set | *Multiply the number by the rule's base value and format the result. | *|
== | *in all rule sets | *Format the number unchanged | *|
[] | *in normal rule | *Omit the optional text if the number is an even multiple of the rule's divisor | *|
* | in negative-number rule | *Not allowed. | *|
* | in improper-fraction rule | *Omit the optional text if the number is between 0 and 1 (same as specifying both an * x.x rule and a 0.x rule) | *|
* | in default rule | *Omit the optional text if the number is an integer (same as specifying both an x.x * rule and an x.0 rule) | *|
* | in proper-fraction rule | *Not allowed. | *|
* | in rule in fraction rule set | *Omit the optional text if multiplying the number by the rule's base value yields 1. | *|
$(cardinal,plural syntax)$ | ** | in all rule sets | *This provides the ability to choose a word based on the number divided by the radix to the power of the * exponent of the base value for the specified locale, which is normally equivalent to the << value. * This uses the cardinal plural rules from PluralFormat. All strings used in the plural format are treated * as the same base value for parsing. | *
$(ordinal,plural syntax)$ | ** | in all rule sets | *This provides the ability to choose a word based on the number divided by the radix to the power of the * exponent of the base value for the specified locale, which is normally equivalent to the << value. * This uses the ordinal plural rules from PluralFormat. All strings used in the plural format are treated * as the same base value for parsing. | *
The substitution descriptor (i.e., the text between the token characters) may take one * of three forms:
* *a rule set name | *Perform the mathematical operation on the number, and format the result using the * named rule set. | *
a DecimalFormat pattern | *Perform the mathematical operation on the number, and format the result using a * DecimalFormat with the specified pattern. The pattern must begin with 0 or #. | *
nothing | *Perform the mathematical operation on the number, and format the result using the rule
* set containing the current rule, except:
*
|
*
Whitespace is ignored between a rule set name and a rule set body, between a rule * descriptor and a rule body, or between rules. If a rule body begins with an apostrophe, * the apostrophe is ignored, but all text after it becomes significant (this is how you can * have a rule's rule text begin with whitespace). There is no escape function: the semicolon * is not allowed in rule set names or in rule text, and the colon is not allowed in rule set * names. The characters beginning a substitution token are always treated as the beginning * of a substitution token.
* *See the resource data and the demo program for annotated examples of real rule sets * using these features.
* *User subclasses are not supported. While clients may write * subclasses, such code will not necessarily work and will not be * guaranteed to work stably from release to release. * *
Localizations
*Constructors are available that allow the specification of localizations for the * public rule sets (and also allow more control over what public rule sets are available). * Localization data is represented as a textual description. The description represents * an array of arrays of string. The first element is an array of the public rule set names, * each of these must be one of the public rule set names that appear in the rules. Only * names in this array will be treated as public rule set names by the API. Each subsequent * element is an array of localizations of these names. The first element of one of these * subarrays is the locale name, and the remaining elements are localizations of the * public rule set names, in the same order as they were listed in the first array.
*In the syntax, angle brackets '<', '>' are used to delimit the arrays, and comma ',' is used * to separate elements of an array. Whitespace is ignored, unless quoted.
*For example:
* < < %foo, %bar, %baz >, * < en, Foo, Bar, Baz >, * < fr, 'le Foo', 'le Bar', 'le Baz' > * < zh, \\u7532, \\u4e59, \\u4e19 > > ** @author Richard Gillam * @see NumberFormat * @see DecimalFormat * @see PluralFormat * @see PluralRules * @stable ICU 2.0 */ class U_I18N_API RuleBasedNumberFormat : public NumberFormat { public: //----------------------------------------------------------------------- // constructors //----------------------------------------------------------------------- /** * Creates a RuleBasedNumberFormat that behaves according to the description * passed in. The formatter uses the default locale. * @param rules A description of the formatter's desired behavior. * See the class documentation for a complete explanation of the description * syntax. * @param perror The parse error if an error was encountered. * @param status The status indicating whether the constructor succeeded. * @stable ICU 3.2 */ RuleBasedNumberFormat(const UnicodeString& rules, UParseError& perror, UErrorCode& status); /** * Creates a RuleBasedNumberFormat that behaves according to the description * passed in. The formatter uses the default locale. *
* The localizations data provides information about the public * rule sets and their localized display names for different * locales. The first element in the list is an array of the names * of the public rule sets. The first element in this array is * the initial default ruleset. The remaining elements in the * list are arrays of localizations of the names of the public * rule sets. Each of these is one longer than the initial array, * with the first String being the ULocale ID, and the remaining * Strings being the localizations of the rule set names, in the * same order as the initial array. Arrays are NULL-terminated. * @param rules A description of the formatter's desired behavior. * See the class documentation for a complete explanation of the description * syntax. * @param localizations the localization information. * names in the description. These will be copied by the constructor. * @param perror The parse error if an error was encountered. * @param status The status indicating whether the constructor succeeded. * @stable ICU 3.2 */ RuleBasedNumberFormat(const UnicodeString& rules, const UnicodeString& localizations, UParseError& perror, UErrorCode& status); /** * Creates a RuleBasedNumberFormat that behaves according to the rules * passed in. The formatter uses the specified locale to determine the * characters to use when formatting numerals, and to define equivalences * for lenient parsing. * @param rules The formatter rules. * See the class documentation for a complete explanation of the rule * syntax. * @param locale A locale that governs which characters are used for * formatting values in numerals and which characters are equivalent in * lenient parsing. * @param perror The parse error if an error was encountered. * @param status The status indicating whether the constructor succeeded. * @stable ICU 2.0 */ RuleBasedNumberFormat(const UnicodeString& rules, const Locale& locale, UParseError& perror, UErrorCode& status); /** * Creates a RuleBasedNumberFormat that behaves according to the description * passed in. The formatter uses the default locale. *
* The localizations data provides information about the public
* rule sets and their localized display names for different
* locales. The first element in the list is an array of the names
* of the public rule sets. The first element in this array is
* the initial default ruleset. The remaining elements in the
* list are arrays of localizations of the names of the public
* rule sets. Each of these is one longer than the initial array,
* with the first String being the ULocale ID, and the remaining
* Strings being the localizations of the rule set names, in the
* same order as the initial array. Arrays are NULL-terminated.
* @param rules A description of the formatter's desired behavior.
* See the class documentation for a complete explanation of the description
* syntax.
* @param localizations a list of localizations for the rule set
* names in the description. These will be copied by the constructor.
* @param locale A locale that governs which characters are used for
* formatting values in numerals and which characters are equivalent in
* lenient parsing.
* @param perror The parse error if an error was encountered.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 3.2
*/
RuleBasedNumberFormat(const UnicodeString& rules, const UnicodeString& localizations,
const Locale& locale, UParseError& perror, UErrorCode& status);
/**
* Creates a RuleBasedNumberFormat from a predefined ruleset. The selector
* code chose among three possible predefined formats: spellout, ordinal,
* and duration.
* @param tag A selector code specifying which kind of formatter to create for that
* locale. There are four legal values: URBNF_SPELLOUT, which creates a formatter that
* spells out a value in words in the desired language, URBNF_ORDINAL, which attaches
* an ordinal suffix from the desired language to the end of a number (e.g. "123rd"),
* URBNF_DURATION, which formats a duration in seconds as hours, minutes, and seconds always rounding down,
* and URBNF_NUMBERING_SYSTEM, which is used to invoke rules for alternate numbering
* systems such as the Hebrew numbering system, or for Roman Numerals, etc.
* @param locale The locale for the formatter.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 2.0
*/
RuleBasedNumberFormat(URBNFRuleSetTag tag, const Locale& locale, UErrorCode& status);
//-----------------------------------------------------------------------
// boilerplate
//-----------------------------------------------------------------------
/**
* Copy constructor
* @param rhs the object to be copied from.
* @stable ICU 2.6
*/
RuleBasedNumberFormat(const RuleBasedNumberFormat& rhs);
/**
* Assignment operator
* @param rhs the object to be copied from.
* @stable ICU 2.6
*/
RuleBasedNumberFormat& operator=(const RuleBasedNumberFormat& rhs);
/**
* Release memory allocated for a RuleBasedNumberFormat when you are finished with it.
* @stable ICU 2.6
*/
virtual ~RuleBasedNumberFormat();
/**
* Clone this object polymorphically. The caller is responsible
* for deleting the result when done.
* @return A copy of the object.
* @stable ICU 2.6
*/
virtual RuleBasedNumberFormat* clone() const override;
/**
* Return true if the given Format objects are semantically equal.
* Objects of different subclasses are considered unequal.
* @param other the object to be compared with.
* @return true if the given Format objects are semantically equal.
* @stable ICU 2.6
*/
virtual bool operator==(const Format& other) const override;
//-----------------------------------------------------------------------
// public API functions
//-----------------------------------------------------------------------
/**
* return the rules that were provided to the RuleBasedNumberFormat.
* @return the result String that was passed in
* @stable ICU 2.0
*/
virtual UnicodeString getRules() const;
/**
* Return the number of public rule set names.
* @return the number of public rule set names.
* @stable ICU 2.0
*/
virtual int32_t getNumberOfRuleSetNames() const;
/**
* Return the name of the index'th public ruleSet. If index is not valid,
* the function returns null.
* @param index the index of the ruleset
* @return the name of the index'th public ruleSet.
* @stable ICU 2.0
*/
virtual UnicodeString getRuleSetName(int32_t index) const;
/**
* Return the number of locales for which we have localized rule set display names.
* @return the number of locales for which we have localized rule set display names.
* @stable ICU 3.2
*/
virtual int32_t getNumberOfRuleSetDisplayNameLocales(void) const;
/**
* Return the index'th display name locale.
* @param index the index of the locale
* @param status set to a failure code when this function fails
* @return the locale
* @see #getNumberOfRuleSetDisplayNameLocales
* @stable ICU 3.2
*/
virtual Locale getRuleSetDisplayNameLocale(int32_t index, UErrorCode& status) const;
/**
* Return the rule set display names for the provided locale. These are in the same order
* as those returned by getRuleSetName. The locale is matched against the locales for
* which there is display name data, using normal fallback rules. If no locale matches,
* the default display names are returned. (These are the internal rule set names minus
* the leading '%'.)
* @param index the index of the rule set
* @param locale the locale (returned by getRuleSetDisplayNameLocales) for which the localized
* display name is desired
* @return the display name for the given index, which might be bogus if there is an error
* @see #getRuleSetName
* @stable ICU 3.2
*/
virtual UnicodeString getRuleSetDisplayName(int32_t index,
const Locale& locale = Locale::getDefault());
/**
* Return the rule set display name for the provided rule set and locale.
* The locale is matched against the locales for which there is display name data, using
* normal fallback rules. If no locale matches, the default display name is returned.
* @return the display name for the rule set
* @stable ICU 3.2
* @see #getRuleSetDisplayName
*/
virtual UnicodeString getRuleSetDisplayName(const UnicodeString& ruleSetName,
const Locale& locale = Locale::getDefault());
using NumberFormat::format;
/**
* Formats the specified 32-bit number using the default ruleset.
* @param number The number to format.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(int32_t number,
UnicodeString& toAppendTo,
FieldPosition& pos) const override;
/**
* Formats the specified 64-bit number using the default ruleset.
* @param number The number to format.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @return A textual representation of the number.
* @stable ICU 2.1
*/
virtual UnicodeString& format(int64_t number,
UnicodeString& toAppendTo,
FieldPosition& pos) const override;
/**
* Formats the specified number using the default ruleset.
* @param number The number to format.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(double number,
UnicodeString& toAppendTo,
FieldPosition& pos) const override;
/**
* Formats the specified number using the named ruleset.
* @param number The number to format.
* @param ruleSetName The name of the rule set to format the number with.
* This must be the name of a valid public rule set for this formatter.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @param status the status
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(int32_t number,
const UnicodeString& ruleSetName,
UnicodeString& toAppendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Formats the specified 64-bit number using the named ruleset.
* @param number The number to format.
* @param ruleSetName The name of the rule set to format the number with.
* This must be the name of a valid public rule set for this formatter.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @param status the status
* @return A textual representation of the number.
* @stable ICU 2.1
*/
virtual UnicodeString& format(int64_t number,
const UnicodeString& ruleSetName,
UnicodeString& toAppendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Formats the specified number using the named ruleset.
* @param number The number to format.
* @param ruleSetName The name of the rule set to format the number with.
* This must be the name of a valid public rule set for this formatter.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @param status the status
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(double number,
const UnicodeString& ruleSetName,
UnicodeString& toAppendTo,
FieldPosition& pos,
UErrorCode& status) const;
protected:
/**
* Format a decimal number.
* The number is a DigitList wrapper onto a floating point decimal number.
* The default implementation in NumberFormat converts the decimal number
* to a double and formats that. Subclasses of NumberFormat that want
* to specifically handle big decimal numbers must override this method.
* class DecimalFormat does so.
*
* @param number The number, a DigitList format Decimal Floating Point.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @internal
*/
virtual UnicodeString& format(const number::impl::DecimalQuantity &number,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const override;
public:
using NumberFormat::parse;
/**
* Parses the specified string, beginning at the specified position, according
* to this formatter's rules. This will match the string against all of the
* formatter's public rule sets and return the value corresponding to the longest
* parseable substring. This function's behavior is affected by the lenient
* parse mode.
* @param text The string to parse
* @param result the result of the parse, either a double or a long.
* @param parsePosition On entry, contains the position of the first character
* in "text" to examine. On exit, has been updated to contain the position
* of the first character in "text" that wasn't consumed by the parse.
* @see #setLenient
* @stable ICU 2.0
*/
virtual void parse(const UnicodeString& text,
Formattable& result,
ParsePosition& parsePosition) const override;
#if !UCONFIG_NO_COLLATION
/**
* Turns lenient parse mode on and off.
*
* When in lenient parse mode, the formatter uses a Collator for parsing the text.
* Only primary differences are treated as significant. This means that case
* differences, accent differences, alternate spellings of the same letter
* (e.g., ae and a-umlaut in German), ignorable characters, etc. are ignored in
* matching the text. In many cases, numerals will be accepted in place of words
* or phrases as well.
*
* For example, all of the following will correctly parse as 255 in English in
* lenient-parse mode:
*
"two hundred fifty-five"
*
"two hundred fifty five"
*
"TWO HUNDRED FIFTY-FIVE"
*
"twohundredfiftyfive"
*
"2 hundred fifty-5"
*
* The Collator used is determined by the locale that was
* passed to this object on construction. The description passed to this object
* on construction may supply additional collation rules that are appended to the
* end of the default collator for the locale, enabling additional equivalences
* (such as adding more ignorable characters or permitting spelled-out version of
* symbols; see the demo program for examples).
*
* It's important to emphasize that even strict parsing is relatively lenient: it
* will accept some text that it won't produce as output. In English, for example,
* it will correctly parse "two hundred zero" and "fifteen hundred".
*
* @param enabled If true, turns lenient-parse mode on; if false, turns it off.
* @see RuleBasedCollator
* @stable ICU 2.0
*/
virtual void setLenient(UBool enabled) override;
/**
* Returns true if lenient-parse mode is turned on. Lenient parsing is off
* by default.
* @return true if lenient-parse mode is turned on.
* @see #setLenient
* @stable ICU 2.0
*/
virtual inline UBool isLenient(void) const override;
#endif
/**
* Override the default rule set to use. If ruleSetName is null, reset
* to the initial default rule set. If the rule set is not a public rule set name,
* U_ILLEGAL_ARGUMENT_ERROR is returned in status.
* @param ruleSetName the name of the rule set, or null to reset the initial default.
* @param status set to failure code when a problem occurs.
* @stable ICU 2.6
*/
virtual void setDefaultRuleSet(const UnicodeString& ruleSetName, UErrorCode& status);
/**
* Return the name of the current default rule set. If the current rule set is
* not public, returns a bogus (and empty) UnicodeString.
* @return the name of the current default rule set
* @stable ICU 3.0
*/
virtual UnicodeString getDefaultRuleSetName() const;
/**
* Set a particular UDisplayContext value in the formatter, such as
* UDISPCTX_CAPITALIZATION_FOR_STANDALONE. Note: For getContext, see
* NumberFormat.
* @param value The UDisplayContext value to set.
* @param status Input/output status. If at entry this indicates a failure
* status, the function will do nothing; otherwise this will be
* updated with any new status from the function.
* @stable ICU 53
*/
virtual void setContext(UDisplayContext value, UErrorCode& status) override;
/**
* Get the rounding mode.
* @return A rounding mode
* @stable ICU 60
*/
virtual ERoundingMode getRoundingMode(void) const override;
/**
* Set the rounding mode.
* @param roundingMode A rounding mode
* @stable ICU 60
*/
virtual void setRoundingMode(ERoundingMode roundingMode) override;
public:
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.8
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.8
*/
virtual UClassID getDynamicClassID(void) const override;
/**
* Sets the decimal format symbols, which is generally not changed
* by the programmer or user. The formatter takes ownership of
* symbolsToAdopt; the client must not delete it.
*
* @param symbolsToAdopt DecimalFormatSymbols to be adopted.
* @stable ICU 49
*/
virtual void adoptDecimalFormatSymbols(DecimalFormatSymbols* symbolsToAdopt);
/**
* Sets the decimal format symbols, which is generally not changed
* by the programmer or user. A clone of the symbols is created and
* the symbols is _not_ adopted; the client is still responsible for
* deleting it.
*
* @param symbols DecimalFormatSymbols.
* @stable ICU 49
*/
virtual void setDecimalFormatSymbols(const DecimalFormatSymbols& symbols);
private:
RuleBasedNumberFormat(); // default constructor not implemented
// this will ref the localizations if they are not NULL
// caller must deref to get adoption
RuleBasedNumberFormat(const UnicodeString& description, LocalizationInfo* localizations,
const Locale& locale, UParseError& perror, UErrorCode& status);
void init(const UnicodeString& rules, LocalizationInfo* localizations, UParseError& perror, UErrorCode& status);
void initCapitalizationContextInfo(const Locale& thelocale);
void dispose();
void stripWhitespace(UnicodeString& src);
void initDefaultRuleSet();
NFRuleSet* findRuleSet(const UnicodeString& name, UErrorCode& status) const;
/* friend access */
friend class NFSubstitution;
friend class NFRule;
friend class NFRuleSet;
friend class FractionalPartSubstitution;
inline NFRuleSet * getDefaultRuleSet() const;
const RuleBasedCollator * getCollator() const;
DecimalFormatSymbols * initializeDecimalFormatSymbols(UErrorCode &status);
const DecimalFormatSymbols * getDecimalFormatSymbols() const;
NFRule * initializeDefaultInfinityRule(UErrorCode &status);
const NFRule * getDefaultInfinityRule() const;
NFRule * initializeDefaultNaNRule(UErrorCode &status);
const NFRule * getDefaultNaNRule() const;
PluralFormat *createPluralFormat(UPluralType pluralType, const UnicodeString &pattern, UErrorCode& status) const;
UnicodeString& adjustForCapitalizationContext(int32_t startPos, UnicodeString& currentResult, UErrorCode& status) const;
UnicodeString& format(int64_t number, NFRuleSet *ruleSet, UnicodeString& toAppendTo, UErrorCode& status) const;
void format(double number, NFRuleSet& rs, UnicodeString& toAppendTo, UErrorCode& status) const;
private:
NFRuleSet **fRuleSets;
UnicodeString* ruleSetDescriptions;
int32_t numRuleSets;
NFRuleSet *defaultRuleSet;
Locale locale;
RuleBasedCollator* collator;
DecimalFormatSymbols* decimalFormatSymbols;
NFRule *defaultInfinityRule;
NFRule *defaultNaNRule;
ERoundingMode fRoundingMode;
UBool lenient;
UnicodeString* lenientParseRules;
LocalizationInfo* localizations;
UnicodeString originalDescription;
UBool capitalizationInfoSet;
UBool capitalizationForUIListMenu;
UBool capitalizationForStandAlone;
BreakIterator* capitalizationBrkIter;
};
// ---------------
#if !UCONFIG_NO_COLLATION
inline UBool
RuleBasedNumberFormat::isLenient(void) const {
return lenient;
}
#endif
inline NFRuleSet*
RuleBasedNumberFormat::getDefaultRuleSet() const {
return defaultRuleSet;
}
U_NAMESPACE_END
/* U_HAVE_RBNF */
#endif
#endif /* U_SHOW_CPLUSPLUS_API */
/* RBNF_H */
#endif