// © 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 … #else #define U_HAVE_RBNF … #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 { … }; /** * 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"). * * <p>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 <tt>RuleBasedNumberFormat</tt>s * by supplying programmer-defined rule sets.</p> * * <p>The behavior of a <tt>RuleBasedNumberFormat</tt> is specified by a textual description * that is either passed to the constructor as a <tt>String</tt> or loaded from a resource * bundle. In its simplest form, the description consists of a semicolon-delimited list of <em>rules.</em> * 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:</p> * * <pre>zero; one; two; three; four; five; six; seven; eight; nine; * ten; eleven; twelve; thirteen; fourteen; fifteen; sixteen; seventeen; eighteen; nineteen;</pre> * * <p>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:</p> * * <pre> 20: twenty[->>]; * 30: thirty[->>]; * 40: forty[->>]; * 50: fifty[->>]; * 60: sixty[->>]; * 70: seventy[->>]; * 80: eighty[->>]; * 90: ninety[->>];</pre> * * <p>In these rules, the <em>base value</em> 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 <em>substitution</em> 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").</p> * * <p>For even larger numbers, we can actually look up several parts of the number in the * list:</p> * * <pre>100: << hundred[ >>];</pre> * * <p>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 <em>divisor,</em> * 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.</p> * * <p>This rule covers values up to 999, at which point we add another rule:</p> * * <pre>1000: << thousand[ >>];</pre> * * <p>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:</p> * * <pre> 1,000,000: << million[ >>]; * 1,000,000,000: << billion[ >>]; * 1,000,000,000,000: << trillion[ >>]; * 1,000,000,000,000,000: OUT OF RANGE!;</pre> * * <p>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.</p> * * <p>To see how these rules actually work in practice, consider the following example: * Formatting 25,430 with this rule set would work like this:</p> * * <table border="0" width="100%"> * <tr> * <td><strong><< thousand >></strong></td> * <td>[the rule whose base value is 1,000 is applicable to 25,340]</td> * </tr> * <tr> * <td><strong>twenty->></strong> thousand >></td> * <td>[25,340 over 1,000 is 25. The rule for 20 applies.]</td> * </tr> * <tr> * <td>twenty-<strong>five</strong> thousand >></td> * <td>[25 mod 10 is 5. The rule for 5 is "five."</td> * </tr> * <tr> * <td>twenty-five thousand <strong><< hundred >></strong></td> * <td>[25,340 mod 1,000 is 340. The rule for 100 applies.]</td> * </tr> * <tr> * <td>twenty-five thousand <strong>three</strong> hundred >></td> * <td>[340 over 100 is 3. The rule for 3 is "three."]</td> * </tr> * <tr> * <td>twenty-five thousand three hundred <strong>forty</strong></td> * <td>[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.]</td> * </tr> * </table> * * <p>The above syntax suffices only to format positive integers. To format negative numbers, * we add a special rule:</p> * * <pre>-x: minus >>;</pre> * * <p>This is called a <em>negative-number rule,</em> 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."</p> * * <p>We also add a special rule called a <em>fraction rule </em>for numbers with fractional * parts:</p> * * <pre>x.x: << point >>;</pre> * * <p>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").</p> * * <p>To see how this rule syntax is applied to various languages, examine the resource data.</p> * * <p>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:</p> * * <hr> * * <p>The description of a <tt>RuleBasedNumberFormat</tt>'s behavior consists of one or more <em>rule * sets.</em> Each rule set consists of a name, a colon, and a list of <em>rules.</em> A rule * set name must begin with a % sign. Rule sets with names that begin with a single % sign * are <em>public:</em> the caller can specify that they be used to format and parse numbers. * Rule sets with names that begin with %% are <em>private:</em> they exist only for the use * of other rule sets. If a formatter only has one rule set, the name may be omitted.</p> * * <p>The user can also specify a special "rule set" named <tt>%%lenient-parse</tt>. * The body of <tt>%%lenient-parse</tt> isn't a set of number-formatting rules, but a <tt>RuleBasedCollator</tt> * description which is used to define equivalences for lenient parsing. For more information * on the syntax, see <tt>RuleBasedCollator</tt>. For more information on lenient parsing, * see <tt>setLenientParse()</tt>. <em>Note:</em> symbols that have syntactic meaning * in collation rules, such as '&', have no particular meaning when appearing outside * of the <tt>lenient-parse</tt> rule set.</p> * * <p>The body of a rule set consists of an ordered, semicolon-delimited list of <em>rules.</em> * Internally, every rule has a base value, a divisor, rule text, and zero, one, or two <em>substitutions.</em> * These parameters are controlled by the description syntax, which consists of a <em>rule * descriptor,</em> a colon, and a <em>rule body.</em></p> * * <p>A rule descriptor can take one of the following forms (text in <em>italics</em> is the * name of a token):</p> * * <table border="0" width="100%"> * <tr> * <td><em>bv</em>:</td> * <td><em>bv</em> specifies the rule's base value. <em>bv</em> is a decimal * number expressed using ASCII digits. <em>bv</em> 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.</td> * </tr> * <tr> * <td><em>bv</em>/<em>rad</em>:</td> * <td><em>bv</em> specifies the rule's base value. The rule's divisor is the * highest power of <em>rad</em> less than or equal to the base value.</td> * </tr> * <tr> * <td><em>bv</em>>:</td> * <td><em>bv</em> 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.</td> * </tr> * <tr> * <td><em>bv</em>/<em>rad</em>>:</td> * <td><em>bv</em> specifies the rule's base value. To calculate the divisor, * let the radix be <em>rad</em>, 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.</td> * </tr> * <tr> * <td>-x:</td> * <td>The rule is a negative-number rule.</td> * </tr> * <tr> * <td>x.x:</td> * <td>The rule is an <em>improper fraction rule</em>. 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.</td> * </tr> * <tr> * <td>0.x:</td> * <td>The rule is a <em>proper fraction rule</em>. 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.</td> * </tr> * <tr> * <td>x.0:</td> * <td>The rule is a <em>default rule</em>. 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.</td> * </tr> * <tr> * <td>Inf:</td> * <td>The rule for infinity.</td> * </tr> * <tr> * <td>NaN:</td> * <td>The rule for an IEEE 754 NaN (not a number).</td> * </tr> * <tr> * <td><em>nothing</em></td> * <td>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.</td> * </tr> * </table> * * <p>A rule set may be either a regular rule set or a <em>fraction rule set,</em> 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.</p> * * <p>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: * * <ul> * <li>If the rule set includes a default rule (and the number was passed in as a <tt>double</tt>), * use the default rule. (If the number being formatted was passed in as a <tt>long</tt>, * the default rule is ignored.)</li> * <li>If the number is negative, use the negative-number rule.</li> * <li>If the number has a fractional part and is greater than 1, use the improper fraction * rule.</li> * <li>If the number has a fractional part and is between 0 and 1, use the proper fraction * rule.</li> * <li>Binary-search the rule list for the rule with the highest base value less than or equal * to the number. If that rule has two substitutions, its base value is not an even multiple * of its divisor, and the number <em>is</em> an even multiple of the rule's divisor, use the * rule that precedes it in the rule list. Otherwise, use the rule itself.</li> * </ul> * * <p>If the rule set is a fraction rule set, do the following: * * <ul> * <li>Ignore negative-number and fraction rules.</li> * <li>For each rule in the list, multiply the number being formatted (which will always be * between 0 and 1) by the rule's base value. Keep track of the distance between the result * the nearest integer.</li> * <li>Use the rule that produced the result closest to zero in the above calculation. In the * event of a tie or a direct hit, use the first matching rule encountered. (The idea here is * to try each rule's base value as a possible denominator of a fraction. Whichever * denominator produces the fraction closest in value to the number being formatted wins.) If * the rule following the matching rule has the same base value, use it if the numerator of * the fraction is anything other than 1; if the numerator is 1, use the original matching * rule. (This is to allow singular and plural forms of the rule text without a lot of extra * hassle.)</li> * </ul> * * <p>A rule's body consists of a string of characters terminated by a semicolon. The rule * may include zero, one, or two <em>substitution tokens,</em> 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.</p> * * <p>A substitution token begins and ends with a <em>token character.</em> The token * character and the context together specify a mathematical operation to be performed on the * number being formatted. An optional <em>substitution descriptor </em>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.</p> * * <p>The meanings of the substitution token characters are as follows:</p> * * <table border="0" width="100%"> * <tr> * <td>>></td> * <td>in normal rule</td> * <td>Divide the number by the rule's divisor and format the remainder</td> * </tr> * <tr> * <td></td> * <td>in negative-number rule</td> * <td>Find the absolute value of the number and format the result</td> * </tr> * <tr> * <td></td> * <td>in fraction or default rule</td> * <td>Isolate the number's fractional part and format it.</td> * </tr> * <tr> * <td></td> * <td>in rule in fraction rule set</td> * <td>Not allowed.</td> * </tr> * <tr> * <td>>>></td> * <td>in normal rule</td> * <td>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.</td> * </tr> * <tr> * <td></td> * <td>in all other rules</td> * <td>Not allowed.</td> * </tr> * <tr> * <td><<</td> * <td>in normal rule</td> * <td>Divide the number by the rule's divisor and format the quotient</td> * </tr> * <tr> * <td></td> * <td>in negative-number rule</td> * <td>Not allowed.</td> * </tr> * <tr> * <td></td> * <td>in fraction or default rule</td> * <td>Isolate the number's integral part and format it.</td> * </tr> * <tr> * <td></td> * <td>in rule in fraction rule set</td> * <td>Multiply the number by the rule's base value and format the result.</td> * </tr> * <tr> * <td>==</td> * <td>in all rule sets</td> * <td>Format the number unchanged</td> * </tr> * <tr> * <td>[]</td> * <td>in normal rule</td> * <td>Omit the optional text if the number is an even multiple of the rule's divisor</td> * </tr> * <tr> * <td></td> * <td>in negative-number rule</td> * <td>Not allowed.</td> * </tr> * <tr> * <td></td> * <td>in improper-fraction rule</td> * <td>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)</td> * </tr> * <tr> * <td></td> * <td>in default rule</td> * <td>Omit the optional text if the number is an integer (same as specifying both an x.x * rule and an x.0 rule)</td> * </tr> * <tr> * <td></td> * <td>in proper-fraction rule</td> * <td>Not allowed.</td> * </tr> * <tr> * <td></td> * <td>in rule in fraction rule set</td> * <td>Omit the optional text if multiplying the number by the rule's base value yields 1.</td> * </tr> * <tr> * <td width="37">$(cardinal,<i>plural syntax</i>)$</td> * <td width="23"></td> * <td width="165" valign="top">in all rule sets</td> * <td>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.</td> * </tr> * <tr> * <td width="37">$(ordinal,<i>plural syntax</i>)$</td> * <td width="23"></td> * <td width="165" valign="top">in all rule sets</td> * <td>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.</td> * </tr> * </table> * * <p>The substitution descriptor (i.e., the text between the token characters) may take one * of three forms:</p> * * <table border="0" width="100%"> * <tr> * <td>a rule set name</td> * <td>Perform the mathematical operation on the number, and format the result using the * named rule set.</td> * </tr> * <tr> * <td>a DecimalFormat pattern</td> * <td>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 #.</td> * </tr> * <tr> * <td>nothing</td> * <td>Perform the mathematical operation on the number, and format the result using the rule * set containing the current rule, except: * <ul> * <li>You can't have an empty substitution descriptor with a == substitution.</li> * <li>If you omit the substitution descriptor in a >> substitution in a fraction rule, * format the result one digit at a time using the rule set containing the current rule.</li> * <li>If you omit the substitution descriptor in a << substitution in a rule in a * fraction rule set, format the result using the default rule set for this formatter.</li> * </ul> * </td> * </tr> * </table> * * <p>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.</p> * * <p>See the resource data and the demo program for annotated examples of real rule sets * using these features.</p> * * <p><em>User subclasses are not supported.</em> While clients may write * subclasses, such code will not necessarily work and will not be * guaranteed to work stably from release to release. * * <p><b>Localizations</b></p> * <p>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.</p> * <p>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.</p> * <p>For example:<pre> * < < %foo, %bar, %baz >, * < en, Foo, Bar, Baz >, * < fr, 'le Foo', 'le Bar', 'le Baz' > * < zh, \\u7532, \\u4e59, \\u4e19 > > * </pre></p> * @author Richard Gillam * @see NumberFormat * @see DecimalFormat * @see PluralFormat * @see PluralRules * @stable ICU 2.0 */ class U_I18N_API RuleBasedNumberFormat : public NumberFormat { … }; // --------------- #if !UCONFIG_NO_COLLATION inline UBool RuleBasedNumberFormat::isLenient(void) const { … } #endif inline NFRuleSet* RuleBasedNumberFormat::getDefaultRuleSet() const { … } U_NAMESPACE_END /* U_HAVE_RBNF */ #endif #endif /* U_SHOW_CPLUSPLUS_API */ /* RBNF_H */ #endif
Codebase Browser
chromium