/src/icu/source/i18n/plurrule_impl.h
Line  | Count  | Source (jump to first uncovered line)  | 
1  |  | // © 2016 and later: Unicode, Inc. and others.  | 
2  |  | // License & terms of use: http://www.unicode.org/copyright.html  | 
3  |  | /*  | 
4  |  | *******************************************************************************  | 
5  |  | * Copyright (C) 2007-2016, International Business Machines Corporation and  | 
6  |  | * others. All Rights Reserved.  | 
7  |  | *******************************************************************************  | 
8  |  | *  | 
9  |  | * File PLURRULE_IMPL.H  | 
10  |  | *  | 
11  |  | *******************************************************************************  | 
12  |  | */  | 
13  |  |  | 
14  |  |  | 
15  |  | #ifndef PLURRULE_IMPL  | 
16  |  | #define PLURRULE_IMPL  | 
17  |  |  | 
18  |  | // Internal definitions for the PluralRules implementation.  | 
19  |  |  | 
20  |  | #include "unicode/utypes.h"  | 
21  |  |  | 
22  |  | #if !UCONFIG_NO_FORMATTING  | 
23  |  |  | 
24  |  | #include "unicode/format.h"  | 
25  |  | #include "unicode/locid.h"  | 
26  |  | #include "unicode/parseerr.h"  | 
27  |  | #include "unicode/strenum.h"  | 
28  |  | #include "unicode/ures.h"  | 
29  |  | #include "uvector.h"  | 
30  |  | #include "hash.h"  | 
31  |  | #include "uassert.h"  | 
32  |  |  | 
33  |  | /**  | 
34  |  |  * A FixedDecimal version of UPLRULES_NO_UNIQUE_VALUE used in PluralRulesTest  | 
35  |  |  * for parsing of samples.  | 
36  |  |  */  | 
37  |  | #define UPLRULES_NO_UNIQUE_VALUE_DECIMAL (FixedDecimal((double)-0.00123456777))  | 
38  |  |  | 
39  |  | class PluralRulesTest;  | 
40  |  |  | 
41  |  | U_NAMESPACE_BEGIN  | 
42  |  |  | 
43  |  | class AndConstraint;  | 
44  |  | class RuleChain;  | 
45  |  | class DigitInterval;  | 
46  |  | class PluralRules;  | 
47  |  | class VisibleDigits;  | 
48  |  |  | 
49  |  | namespace pluralimpl { | 
50  |  |  | 
51  |  | // TODO: Remove this and replace with u"" literals. Was for EBCDIC compatibility.  | 
52  |  |  | 
53  |  | static const UChar DOT = ((UChar) 0x002E);  | 
54  |  | static const UChar SINGLE_QUOTE = ((UChar) 0x0027);  | 
55  |  | static const UChar SLASH = ((UChar) 0x002F);  | 
56  |  | static const UChar BACKSLASH = ((UChar) 0x005C);  | 
57  |  | static const UChar SPACE = ((UChar) 0x0020);  | 
58  |  | static const UChar EXCLAMATION = ((UChar) 0x0021);  | 
59  |  | static const UChar QUOTATION_MARK = ((UChar) 0x0022);  | 
60  |  | static const UChar NUMBER_SIGN = ((UChar) 0x0023);  | 
61  |  | static const UChar PERCENT_SIGN = ((UChar) 0x0025);  | 
62  |  | static const UChar ASTERISK = ((UChar) 0x002A);  | 
63  |  | static const UChar COMMA = ((UChar) 0x002C);  | 
64  |  | static const UChar HYPHEN = ((UChar) 0x002D);  | 
65  |  | static const UChar U_ZERO = ((UChar) 0x0030);  | 
66  |  | static const UChar U_ONE = ((UChar) 0x0031);  | 
67  |  | static const UChar U_TWO = ((UChar) 0x0032);  | 
68  |  | static const UChar U_THREE = ((UChar) 0x0033);  | 
69  |  | static const UChar U_FOUR = ((UChar) 0x0034);  | 
70  |  | static const UChar U_FIVE = ((UChar) 0x0035);  | 
71  |  | static const UChar U_SIX = ((UChar) 0x0036);  | 
72  |  | static const UChar U_SEVEN = ((UChar) 0x0037);  | 
73  |  | static const UChar U_EIGHT = ((UChar) 0x0038);  | 
74  |  | static const UChar U_NINE = ((UChar) 0x0039);  | 
75  |  | static const UChar COLON = ((UChar) 0x003A);  | 
76  |  | static const UChar SEMI_COLON = ((UChar) 0x003B);  | 
77  |  | static const UChar EQUALS = ((UChar) 0x003D);  | 
78  |  | static const UChar AT = ((UChar) 0x0040);  | 
79  |  | static const UChar CAP_A = ((UChar) 0x0041);  | 
80  |  | static const UChar CAP_B = ((UChar) 0x0042);  | 
81  |  | static const UChar CAP_R = ((UChar) 0x0052);  | 
82  |  | static const UChar CAP_Z = ((UChar) 0x005A);  | 
83  |  | static const UChar LOWLINE = ((UChar) 0x005F);  | 
84  |  | static const UChar LEFTBRACE = ((UChar) 0x007B);  | 
85  |  | static const UChar RIGHTBRACE = ((UChar) 0x007D);  | 
86  |  | static const UChar TILDE = ((UChar) 0x007E);  | 
87  |  | static const UChar ELLIPSIS = ((UChar) 0x2026);  | 
88  |  |  | 
89  |  | static const UChar LOW_A = ((UChar) 0x0061);  | 
90  |  | static const UChar LOW_B = ((UChar) 0x0062);  | 
91  |  | static const UChar LOW_C = ((UChar) 0x0063);  | 
92  |  | static const UChar LOW_D = ((UChar) 0x0064);  | 
93  |  | static const UChar LOW_E = ((UChar) 0x0065);  | 
94  |  | static const UChar LOW_F = ((UChar) 0x0066);  | 
95  |  | static const UChar LOW_G = ((UChar) 0x0067);  | 
96  |  | static const UChar LOW_H = ((UChar) 0x0068);  | 
97  |  | static const UChar LOW_I = ((UChar) 0x0069);  | 
98  |  | static const UChar LOW_J = ((UChar) 0x006a);  | 
99  |  | static const UChar LOW_K = ((UChar) 0x006B);  | 
100  |  | static const UChar LOW_L = ((UChar) 0x006C);  | 
101  |  | static const UChar LOW_M = ((UChar) 0x006D);  | 
102  |  | static const UChar LOW_N = ((UChar) 0x006E);  | 
103  |  | static const UChar LOW_O = ((UChar) 0x006F);  | 
104  |  | static const UChar LOW_P = ((UChar) 0x0070);  | 
105  |  | static const UChar LOW_Q = ((UChar) 0x0071);  | 
106  |  | static const UChar LOW_R = ((UChar) 0x0072);  | 
107  |  | static const UChar LOW_S = ((UChar) 0x0073);  | 
108  |  | static const UChar LOW_T = ((UChar) 0x0074);  | 
109  |  | static const UChar LOW_U = ((UChar) 0x0075);  | 
110  |  | static const UChar LOW_V = ((UChar) 0x0076);  | 
111  |  | static const UChar LOW_W = ((UChar) 0x0077);  | 
112  |  | static const UChar LOW_Y = ((UChar) 0x0079);  | 
113  |  | static const UChar LOW_Z = ((UChar) 0x007A);  | 
114  |  |  | 
115  |  | }  | 
116  |  |  | 
117  |  |  | 
118  |  | static const int32_t PLURAL_RANGE_HIGH = 0x7fffffff;  | 
119  |  |  | 
120  |  | enum tokenType { | 
121  |  |   none,  | 
122  |  |   tNumber,  | 
123  |  |   tComma,  | 
124  |  |   tSemiColon,  | 
125  |  |   tSpace,  | 
126  |  |   tColon,  | 
127  |  |   tAt,           // '@'  | 
128  |  |   tDot,  | 
129  |  |   tDot2,  | 
130  |  |   tEllipsis,  | 
131  |  |   tKeyword,  | 
132  |  |   tAnd,  | 
133  |  |   tOr,  | 
134  |  |   tMod,          // 'mod' or '%'  | 
135  |  |   tNot,          //  'not' only.  | 
136  |  |   tIn,           //  'in'  only.  | 
137  |  |   tEqual,        //  '='   only.  | 
138  |  |   tNotEqual,     //  '!='  | 
139  |  |   tTilde,  | 
140  |  |   tWithin,  | 
141  |  |   tIs,  | 
142  |  |   tVariableN,  | 
143  |  |   tVariableI,  | 
144  |  |   tVariableF,  | 
145  |  |   tVariableV,  | 
146  |  |   tVariableT,  | 
147  |  |   tVariableE,  | 
148  |  |   tVariableC,  | 
149  |  |   tDecimal,  | 
150  |  |   tInteger,  | 
151  |  |   tEOF  | 
152  |  | };  | 
153  |  |  | 
154  |  |  | 
155  |  | class PluralRuleParser: public UMemory { | 
156  |  | public:  | 
157  |  |     PluralRuleParser();  | 
158  |  |     virtual ~PluralRuleParser();  | 
159  |  |  | 
160  |  |     void parse(const UnicodeString &rules, PluralRules *dest, UErrorCode &status);  | 
161  |  |     void getNextToken(UErrorCode &status);  | 
162  |  |     void checkSyntax(UErrorCode &status);  | 
163  |  |     static int32_t getNumberValue(const UnicodeString &token);  | 
164  |  |  | 
165  |  | private:  | 
166  |  |     static tokenType getKeyType(const UnicodeString& token, tokenType type);  | 
167  |  |     static tokenType charType(UChar ch);  | 
168  |  |     static UBool isValidKeyword(const UnicodeString& token);  | 
169  |  |  | 
170  |  |     const UnicodeString  *ruleSrc;  // The rules string.  | 
171  |  |     int32_t        ruleIndex;       // String index in the input rules, the current parse position.  | 
172  |  |     UnicodeString  token;           // Token most recently scanned.  | 
173  |  |     tokenType      type;  | 
174  |  |     tokenType      prevType;  | 
175  |  |  | 
176  |  |                                     // The items currently being parsed & built.  | 
177  |  |                                     // Note: currentChain may not be the last RuleChain in the  | 
178  |  |                                     //       list because the "other" chain is forced to the end.  | 
179  |  |     AndConstraint *curAndConstraint;  | 
180  |  |     RuleChain     *currentChain;  | 
181  |  |  | 
182  |  |     int32_t        rangeLowIdx;     // Indices in the UVector of ranges of the  | 
183  |  |     int32_t        rangeHiIdx;      //    low and hi values currently being parsed.  | 
184  |  |  | 
185  |  |     enum EParseState { | 
186  |  |        kKeyword,  | 
187  |  |        kExpr,  | 
188  |  |        kValue,  | 
189  |  |        kRangeList,  | 
190  |  |        kSamples  | 
191  |  |     };  | 
192  |  | };  | 
193  |  |  | 
194  |  | enum PluralOperand { | 
195  |  |     /**  | 
196  |  |     * The double value of the entire number.  | 
197  |  |     */  | 
198  |  |     PLURAL_OPERAND_N,  | 
199  |  |  | 
200  |  |     /**  | 
201  |  |      * The integer value, with the fraction digits truncated off.  | 
202  |  |      */  | 
203  |  |     PLURAL_OPERAND_I,  | 
204  |  |  | 
205  |  |     /**  | 
206  |  |      * All visible fraction digits as an integer, including trailing zeros.  | 
207  |  |      */  | 
208  |  |     PLURAL_OPERAND_F,  | 
209  |  |  | 
210  |  |     /**  | 
211  |  |      * Visible fraction digits as an integer, not including trailing zeros.  | 
212  |  |      */  | 
213  |  |     PLURAL_OPERAND_T,  | 
214  |  |  | 
215  |  |     /**  | 
216  |  |      * Number of visible fraction digits.  | 
217  |  |      */  | 
218  |  |     PLURAL_OPERAND_V,  | 
219  |  |  | 
220  |  |     /**  | 
221  |  |      * Number of visible fraction digits, not including trailing zeros.  | 
222  |  |      */  | 
223  |  |     PLURAL_OPERAND_W,  | 
224  |  |  | 
225  |  |     /**  | 
226  |  |      * Suppressed exponent for scientific notation (exponent needed in  | 
227  |  |      * scientific notation to approximate i).  | 
228  |  |      */  | 
229  |  |     PLURAL_OPERAND_E,  | 
230  |  |  | 
231  |  |     /**  | 
232  |  |      * This operand is currently treated as an alias for `PLURAL_OPERAND_E`.  | 
233  |  |      * In the future, it will represent:  | 
234  |  |      *  | 
235  |  |      * Suppressed exponent for compact notation (exponent needed in  | 
236  |  |      * compact notation to approximate i).  | 
237  |  |      */  | 
238  |  |     PLURAL_OPERAND_C,  | 
239  |  |  | 
240  |  |     /**  | 
241  |  |      * THIS OPERAND IS DEPRECATED AND HAS BEEN REMOVED FROM THE SPEC.  | 
242  |  |      *  | 
243  |  |      * <p>Returns the integer value, but will fail if the number has fraction digits.  | 
244  |  |      * That is, using "j" instead of "i" is like implicitly adding "v is 0".  | 
245  |  |      *  | 
246  |  |      * <p>For example, "j is 3" is equivalent to "i is 3 and v is 0": it matches  | 
247  |  |      * "3" but not "3.1" or "3.0".  | 
248  |  |      */  | 
249  |  |     PLURAL_OPERAND_J  | 
250  |  | };  | 
251  |  |  | 
252  |  | /**  | 
253  |  |  * Converts from the tokenType enum to PluralOperand. Asserts that the given  | 
254  |  |  * tokenType can be mapped to a PluralOperand.  | 
255  |  |  */  | 
256  |  | PluralOperand tokenTypeToPluralOperand(tokenType tt);  | 
257  |  |  | 
258  |  | /**  | 
259  |  |  * An interface to FixedDecimal, allowing for other implementations.  | 
260  |  |  * @internal  | 
261  |  |  */  | 
262  |  | class U_I18N_API IFixedDecimal { | 
263  |  |   public:  | 
264  |  |     virtual ~IFixedDecimal();  | 
265  |  |  | 
266  |  |     /**  | 
267  |  |      * Returns the value corresponding to the specified operand (n, i, f, t, v, or w).  | 
268  |  |      * If the operand is 'n', returns a double; otherwise, returns an integer.  | 
269  |  |      */  | 
270  |  |     virtual double getPluralOperand(PluralOperand operand) const = 0;  | 
271  |  |  | 
272  |  |     virtual bool isNaN() const = 0;  | 
273  |  |  | 
274  |  |     virtual bool isInfinite() const = 0;  | 
275  |  |  | 
276  |  |     /** Whether the number has no nonzero fraction digits. */  | 
277  |  |     virtual bool hasIntegerValue() const = 0;  | 
278  |  | };  | 
279  |  |  | 
280  |  | /**  | 
281  |  |  * class FixedDecimal serves to communicate the properties  | 
282  |  |  * of a formatted number from a decimal formatter to PluralRules::select()  | 
283  |  |  *  | 
284  |  |  * see DecimalFormat::getFixedDecimal()  | 
285  |  |  * @internal  | 
286  |  |  */  | 
287  |  | class U_I18N_API FixedDecimal: public IFixedDecimal, public UObject { | 
288  |  |   public:  | 
289  |  |     /**  | 
290  |  |       * @param n   the number, e.g. 12.345  | 
291  |  |       * @param v   The number of visible fraction digits, e.g. 3  | 
292  |  |       * @param f   The fraction digits, e.g. 345  | 
293  |  |       * @param e   The exponent, e.g. 7 in 1.2e7, for scientific notation  | 
294  |  |       * @param c   Currently: an alias for param `e`.  | 
295  |  |       */  | 
296  |  |     FixedDecimal(double  n, int32_t v, int64_t f, int32_t e, int32_t c);  | 
297  |  |     FixedDecimal(double  n, int32_t v, int64_t f, int32_t e);  | 
298  |  |     FixedDecimal(double  n, int32_t v, int64_t f);  | 
299  |  |     FixedDecimal(double n, int32_t);  | 
300  |  |     explicit FixedDecimal(double n);  | 
301  |  |     FixedDecimal();  | 
302  |  |     ~FixedDecimal() U_OVERRIDE;  | 
303  |  |     FixedDecimal(const UnicodeString &s, UErrorCode &ec);  | 
304  |  |     FixedDecimal(const FixedDecimal &other);  | 
305  |  |  | 
306  |  |     static FixedDecimal createWithExponent(double n, int32_t v, int32_t e);  | 
307  |  |  | 
308  |  |     double getPluralOperand(PluralOperand operand) const U_OVERRIDE;  | 
309  |  |     bool isNaN() const U_OVERRIDE;  | 
310  |  |     bool isInfinite() const U_OVERRIDE;  | 
311  |  |     bool hasIntegerValue() const U_OVERRIDE;  | 
312  |  |  | 
313  |  |     bool isNanOrInfinity() const;  // used in decimfmtimpl.cpp  | 
314  |  |  | 
315  |  |     int32_t getVisibleFractionDigitCount() const;  | 
316  |  |  | 
317  |  |     void init(double n, int32_t v, int64_t f, int32_t e, int32_t c);  | 
318  |  |     void init(double n, int32_t v, int64_t f, int32_t e);  | 
319  |  |     void init(double n, int32_t v, int64_t f);  | 
320  |  |     void init(double n);  | 
321  |  |     UBool quickInit(double n);  // Try a fast-path only initialization,  | 
322  |  |                                 //    return true if successful.  | 
323  |  |     void adjustForMinFractionDigits(int32_t min);  | 
324  |  |     static int64_t getFractionalDigits(double n, int32_t v);  | 
325  |  |     static int32_t decimals(double n);  | 
326  |  |  | 
327  | 0  |     FixedDecimal& operator=(const FixedDecimal& other) = default;  | 
328  |  |     bool operator==(const FixedDecimal &other) const;  | 
329  |  |  | 
330  |  |     UnicodeString toString() const;  | 
331  |  |  | 
332  |  |     double      source;  | 
333  |  |     int32_t     visibleDecimalDigitCount;  | 
334  |  |     int64_t     decimalDigits;  | 
335  |  |     int64_t     decimalDigitsWithoutTrailingZeros;  | 
336  |  |     int64_t     intValue;  | 
337  |  |     int32_t     exponent;  | 
338  |  |     UBool       _hasIntegerValue;  | 
339  |  |     UBool       isNegative;  | 
340  |  |     UBool       _isNaN;  | 
341  |  |     UBool       _isInfinite;  | 
342  |  | };  | 
343  |  |  | 
344  |  | class AndConstraint : public UMemory  { | 
345  |  | public:  | 
346  |  |     typedef enum RuleOp { | 
347  |  |         NONE,  | 
348  |  |         MOD  | 
349  |  |     } RuleOp;  | 
350  |  |     RuleOp op = AndConstraint::NONE;  | 
351  |  |     int32_t opNum = -1;             // for mod expressions, the right operand of the mod.  | 
352  |  |     int32_t value = -1;             // valid for 'is' rules only.  | 
353  |  |     UVector32 *rangeList = nullptr; // for 'in', 'within' rules. Null otherwise.  | 
354  |  |     UBool negated = false;          // true for negated rules.  | 
355  |  |     UBool integerOnly = false;      // true for 'within' rules.  | 
356  |  |     tokenType digitsType = none;    // n | i | v | f constraint.  | 
357  |  |     AndConstraint *next = nullptr;  | 
358  |  |     // Internal error status, used for errors that occur during the copy constructor.  | 
359  |  |     UErrorCode fInternalStatus = U_ZERO_ERROR;      | 
360  |  |  | 
361  | 0  |     AndConstraint() = default;  | 
362  |  |     AndConstraint(const AndConstraint& other);  | 
363  |  |     virtual ~AndConstraint();  | 
364  |  |     AndConstraint* add(UErrorCode& status);  | 
365  |  |     // UBool isFulfilled(double number);  | 
366  |  |     UBool isFulfilled(const IFixedDecimal &number);  | 
367  |  | };  | 
368  |  |  | 
369  |  | class OrConstraint : public UMemory  { | 
370  |  | public:  | 
371  |  |     AndConstraint *childNode = nullptr;  | 
372  |  |     OrConstraint *next = nullptr;  | 
373  |  |     // Internal error status, used for errors that occur during the copy constructor.  | 
374  |  |     UErrorCode fInternalStatus = U_ZERO_ERROR;  | 
375  |  |  | 
376  | 0  |     OrConstraint() = default;  | 
377  |  |     OrConstraint(const OrConstraint& other);  | 
378  |  |     virtual ~OrConstraint();  | 
379  |  |     AndConstraint* add(UErrorCode& status);  | 
380  |  |     // UBool isFulfilled(double number);  | 
381  |  |     UBool isFulfilled(const IFixedDecimal &number);  | 
382  |  | };  | 
383  |  |  | 
384  |  | class RuleChain : public UMemory  { | 
385  |  | public:  | 
386  |  |     UnicodeString   fKeyword;  | 
387  |  |     RuleChain      *fNext = nullptr;  | 
388  |  |     OrConstraint   *ruleHeader = nullptr;  | 
389  |  |     UnicodeString   fDecimalSamples;  // Samples strings from rule source  | 
390  |  |     UnicodeString   fIntegerSamples;  //   without @decimal or @integer, otherwise unprocessed.  | 
391  |  |     UBool           fDecimalSamplesUnbounded = false;  | 
392  |  |     UBool           fIntegerSamplesUnbounded = false;  | 
393  |  |     // Internal error status, used for errors that occur during the copy constructor.  | 
394  |  |     UErrorCode      fInternalStatus = U_ZERO_ERROR;  | 
395  |  |  | 
396  | 0  |     RuleChain() = default;  | 
397  |  |     RuleChain(const RuleChain& other);  | 
398  |  |     virtual ~RuleChain();  | 
399  |  |  | 
400  |  |     UnicodeString select(const IFixedDecimal &number) const;  | 
401  |  |     void          dumpRules(UnicodeString& result);  | 
402  |  |     UErrorCode    getKeywords(int32_t maxArraySize, UnicodeString *keywords, int32_t& arraySize) const;  | 
403  |  |     UBool         isKeyword(const UnicodeString& keyword) const;  | 
404  |  | };  | 
405  |  |  | 
406  |  | class PluralKeywordEnumeration : public StringEnumeration { | 
407  |  | public:  | 
408  |  |     PluralKeywordEnumeration(RuleChain *header, UErrorCode& status);  | 
409  |  |     virtual ~PluralKeywordEnumeration();  | 
410  |  |     static UClassID U_EXPORT2 getStaticClassID(void);  | 
411  |  |     virtual UClassID getDynamicClassID(void) const;  | 
412  |  |     virtual const UnicodeString* snext(UErrorCode& status);  | 
413  |  |     virtual void reset(UErrorCode& status);  | 
414  |  |     virtual int32_t count(UErrorCode& status) const;  | 
415  |  | private:  | 
416  |  |     int32_t         pos;  | 
417  |  |     UVector         fKeywordNames;  | 
418  |  | };  | 
419  |  |  | 
420  |  |  | 
421  |  | class U_I18N_API PluralAvailableLocalesEnumeration: public StringEnumeration { | 
422  |  |   public:  | 
423  |  |     PluralAvailableLocalesEnumeration(UErrorCode &status);  | 
424  |  |     virtual ~PluralAvailableLocalesEnumeration();  | 
425  |  |     virtual const char* next(int32_t *resultLength, UErrorCode& status);  | 
426  |  |     virtual void reset(UErrorCode& status);  | 
427  |  |     virtual int32_t count(UErrorCode& status) const;  | 
428  |  |   private:  | 
429  |  |     UErrorCode      fOpenStatus;  | 
430  |  |     UResourceBundle *fLocales = nullptr;  | 
431  |  |     UResourceBundle *fRes = nullptr;  | 
432  |  | };  | 
433  |  |  | 
434  |  | U_NAMESPACE_END  | 
435  |  |  | 
436  |  | #endif /* #if !UCONFIG_NO_FORMATTING */  | 
437  |  |  | 
438  |  | #endif // _PLURRULE_IMPL  | 
439  |  | //eof  |