/src/icu/source/i18n/number_patternstring.h
Line  | Count  | Source (jump to first uncovered line)  | 
1  |  | // © 2017 and later: Unicode, Inc. and others.  | 
2  |  | // License & terms of use: http://www.unicode.org/copyright.html  | 
3  |  |  | 
4  |  | #include "unicode/utypes.h"  | 
5  |  |  | 
6  |  | #if !UCONFIG_NO_FORMATTING  | 
7  |  | #ifndef __NUMBER_PATTERNSTRING_H__  | 
8  |  | #define __NUMBER_PATTERNSTRING_H__  | 
9  |  |  | 
10  |  |  | 
11  |  | #include <cstdint>  | 
12  |  | #include "unicode/unum.h"  | 
13  |  | #include "unicode/unistr.h"  | 
14  |  | #include "number_types.h"  | 
15  |  | #include "number_decimalquantity.h"  | 
16  |  | #include "number_decimfmtprops.h"  | 
17  |  | #include "number_affixutils.h"  | 
18  |  |  | 
19  |  | U_NAMESPACE_BEGIN namespace number { | 
20  |  | namespace impl { | 
21  |  |  | 
22  |  | // Forward declaration  | 
23  |  | class PatternParser;  | 
24  |  |  | 
25  |  | // Note: the order of fields in this enum matters for parsing.  | 
26  |  | enum PatternSignType { | 
27  |  |     /** Render using normal positive subpattern rules */  | 
28  |  |     PATTERN_SIGN_TYPE_POS,  | 
29  |  |     /** Render using rules to force the display of a plus sign */  | 
30  |  |     PATTERN_SIGN_TYPE_POS_SIGN,  | 
31  |  |     /** Render using negative subpattern rules */  | 
32  |  |     PATTERN_SIGN_TYPE_NEG,  | 
33  |  |     /** Count for looping over the possibilities */  | 
34  |  |     PATTERN_SIGN_TYPE_COUNT  | 
35  |  | };  | 
36  |  |  | 
37  |  | // Exported as U_I18N_API because it is a public member field of exported ParsedSubpatternInfo  | 
38  |  | struct U_I18N_API Endpoints { | 
39  |  |     int32_t start = 0;  | 
40  |  |     int32_t end = 0;  | 
41  |  | };  | 
42  |  |  | 
43  |  | // Exported as U_I18N_API because it is a public member field of exported ParsedPatternInfo  | 
44  |  | struct U_I18N_API ParsedSubpatternInfo { | 
45  |  |     uint64_t groupingSizes = 0x0000ffffffff0000L;  | 
46  |  |     int32_t integerLeadingHashSigns = 0;  | 
47  |  |     int32_t integerTrailingHashSigns = 0;  | 
48  |  |     int32_t integerNumerals = 0;  | 
49  |  |     int32_t integerAtSigns = 0;  | 
50  |  |     int32_t integerTotal = 0; // for convenience  | 
51  |  |     int32_t fractionNumerals = 0;  | 
52  |  |     int32_t fractionHashSigns = 0;  | 
53  |  |     int32_t fractionTotal = 0; // for convenience  | 
54  |  |     bool hasDecimal = false;  | 
55  |  |     int32_t widthExceptAffixes = 0;  | 
56  |  |     // Note: NullableValue causes issues here with std::move.  | 
57  |  |     bool hasPadding = false;  | 
58  |  |     UNumberFormatPadPosition paddingLocation = UNUM_PAD_BEFORE_PREFIX;  | 
59  |  |     DecimalQuantity rounding;  | 
60  |  |     bool exponentHasPlusSign = false;  | 
61  |  |     int32_t exponentZeros = 0;  | 
62  |  |     bool hasPercentSign = false;  | 
63  |  |     bool hasPerMilleSign = false;  | 
64  |  |     bool hasCurrencySign = false;  | 
65  |  |     bool hasMinusSign = false;  | 
66  |  |     bool hasPlusSign = false;  | 
67  |  |  | 
68  |  |     Endpoints prefixEndpoints;  | 
69  |  |     Endpoints suffixEndpoints;  | 
70  |  |     Endpoints paddingEndpoints;  | 
71  |  | };  | 
72  |  |  | 
73  |  | // Exported as U_I18N_API because it is needed for the unit test PatternStringTest  | 
74  |  | struct U_I18N_API ParsedPatternInfo : public AffixPatternProvider, public UMemory { | 
75  |  |     UnicodeString pattern;  | 
76  |  |     ParsedSubpatternInfo positive;  | 
77  |  |     ParsedSubpatternInfo negative;  | 
78  |  |  | 
79  |  |     ParsedPatternInfo()  | 
80  | 0  |             : state(this->pattern), currentSubpattern(nullptr) {} | 
81  |  |  | 
82  | 0  |     ~ParsedPatternInfo() U_OVERRIDE = default;  | 
83  |  |  | 
84  |  |     // Need to declare this explicitly because of the destructor  | 
85  |  |     ParsedPatternInfo& operator=(ParsedPatternInfo&& src) U_NOEXCEPT = default;  | 
86  |  |  | 
87  |  |     static int32_t getLengthFromEndpoints(const Endpoints& endpoints);  | 
88  |  |  | 
89  |  |     char16_t charAt(int32_t flags, int32_t index) const U_OVERRIDE;  | 
90  |  |  | 
91  |  |     int32_t length(int32_t flags) const U_OVERRIDE;  | 
92  |  |  | 
93  |  |     UnicodeString getString(int32_t flags) const U_OVERRIDE;  | 
94  |  |  | 
95  |  |     bool positiveHasPlusSign() const U_OVERRIDE;  | 
96  |  |  | 
97  |  |     bool hasNegativeSubpattern() const U_OVERRIDE;  | 
98  |  |  | 
99  |  |     bool negativeHasMinusSign() const U_OVERRIDE;  | 
100  |  |  | 
101  |  |     bool hasCurrencySign() const U_OVERRIDE;  | 
102  |  |  | 
103  |  |     bool containsSymbolType(AffixPatternType type, UErrorCode& status) const U_OVERRIDE;  | 
104  |  |  | 
105  |  |     bool hasBody() const U_OVERRIDE;  | 
106  |  |  | 
107  |  |   private:  | 
108  |  |     struct U_I18N_API ParserState { | 
109  |  |         const UnicodeString& pattern; // reference to the parent  | 
110  |  |         int32_t offset = 0;  | 
111  |  |  | 
112  |  |         explicit ParserState(const UnicodeString& _pattern)  | 
113  | 0  |                 : pattern(_pattern) {} | 
114  |  |  | 
115  | 0  |         ParserState& operator=(ParserState&& src) U_NOEXCEPT { | 
116  | 0  |             // Leave pattern reference alone; it will continue to point to the same place in memory,  | 
117  | 0  |             // which gets overwritten by ParsedPatternInfo's implicit move assignment.  | 
118  | 0  |             offset = src.offset;  | 
119  | 0  |             return *this;  | 
120  | 0  |         }  | 
121  |  |  | 
122  |  |         UChar32 peek();  | 
123  |  |  | 
124  |  |         UChar32 next();  | 
125  |  |  | 
126  |  |         // TODO: We don't currently do anything with the message string.  | 
127  |  |         // This method is here as a shell for Java compatibility.  | 
128  | 0  |         inline void toParseException(const char16_t* message) { (void) message; } | 
129  |  |     } state;  | 
130  |  |  | 
131  |  |     // NOTE: In Java, these are written as pure functions.  | 
132  |  |     // In C++, they're written as methods.  | 
133  |  |     // The behavior is the same.  | 
134  |  |  | 
135  |  |     // Mutable transient pointer:  | 
136  |  |     ParsedSubpatternInfo* currentSubpattern;  | 
137  |  |  | 
138  |  |     // In Java, "negative == null" tells us whether or not we had a negative subpattern.  | 
139  |  |     // In C++, we need to remember in another boolean.  | 
140  |  |     bool fHasNegativeSubpattern = false;  | 
141  |  |  | 
142  |  |     const Endpoints& getEndpoints(int32_t flags) const;  | 
143  |  |  | 
144  |  |     /** Run the recursive descent parser. */  | 
145  |  |     void consumePattern(const UnicodeString& patternString, UErrorCode& status);  | 
146  |  |  | 
147  |  |     void consumeSubpattern(UErrorCode& status);  | 
148  |  |  | 
149  |  |     void consumePadding(PadPosition paddingLocation, UErrorCode& status);  | 
150  |  |  | 
151  |  |     void consumeAffix(Endpoints& endpoints, UErrorCode& status);  | 
152  |  |  | 
153  |  |     void consumeLiteral(UErrorCode& status);  | 
154  |  |  | 
155  |  |     void consumeFormat(UErrorCode& status);  | 
156  |  |  | 
157  |  |     void consumeIntegerFormat(UErrorCode& status);  | 
158  |  |  | 
159  |  |     void consumeFractionFormat(UErrorCode& status);  | 
160  |  |  | 
161  |  |     void consumeExponent(UErrorCode& status);  | 
162  |  |  | 
163  |  |     friend class PatternParser;  | 
164  |  | };  | 
165  |  |  | 
166  |  | enum IgnoreRounding { | 
167  |  |     IGNORE_ROUNDING_NEVER = 0, IGNORE_ROUNDING_IF_CURRENCY = 1, IGNORE_ROUNDING_ALWAYS = 2  | 
168  |  | };  | 
169  |  |  | 
170  |  | class U_I18N_API PatternParser { | 
171  |  |   public:  | 
172  |  |     /**  | 
173  |  |      * Runs the recursive descent parser on the given pattern string, returning a data structure with raw information  | 
174  |  |      * about the pattern string.  | 
175  |  |      *  | 
176  |  |      * <p>  | 
177  |  |      * To obtain a more useful form of the data, consider using {@link #parseToProperties} instead. | 
178  |  |      *  | 
179  |  |      * TODO: Change argument type to const char16_t* instead of UnicodeString?  | 
180  |  |      *  | 
181  |  |      * @param patternString  | 
182  |  |      *            The LDML decimal format pattern (Excel-style pattern) to parse.  | 
183  |  |      * @return The results of the parse.  | 
184  |  |      */  | 
185  |  |     static void parseToPatternInfo(const UnicodeString& patternString, ParsedPatternInfo& patternInfo,  | 
186  |  |                                    UErrorCode& status);  | 
187  |  |  | 
188  |  |     /**  | 
189  |  |      * Parses a pattern string into a new property bag.  | 
190  |  |      *  | 
191  |  |      * @param pattern  | 
192  |  |      *            The pattern string, like "#,##0.00"  | 
193  |  |      * @param ignoreRounding  | 
194  |  |      *            Whether to leave out rounding information (minFrac, maxFrac, and rounding increment) when parsing the  | 
195  |  |      *            pattern. This may be desirable if a custom rounding mode, such as CurrencyUsage, is to be used  | 
196  |  |      *            instead.  | 
197  |  |      * @return A property bag object.  | 
198  |  |      * @throws IllegalArgumentException  | 
199  |  |      *             If there is a syntax error in the pattern string.  | 
200  |  |      */  | 
201  |  |     static DecimalFormatProperties parseToProperties(const UnicodeString& pattern,  | 
202  |  |                                                      IgnoreRounding ignoreRounding, UErrorCode& status);  | 
203  |  |  | 
204  |  |     static DecimalFormatProperties parseToProperties(const UnicodeString& pattern, UErrorCode& status);  | 
205  |  |  | 
206  |  |     /**  | 
207  |  |      * Parses a pattern string into an existing property bag. All properties that can be encoded into a pattern string  | 
208  |  |      * will be overwritten with either their default value or with the value coming from the pattern string. Properties  | 
209  |  |      * that cannot be encoded into a pattern string, such as rounding mode, are not modified.  | 
210  |  |      *  | 
211  |  |      * @param pattern  | 
212  |  |      *            The pattern string, like "#,##0.00"  | 
213  |  |      * @param properties  | 
214  |  |      *            The property bag object to overwrite.  | 
215  |  |      * @param ignoreRounding  | 
216  |  |      *            See {@link #parseToProperties(String pattern, int ignoreRounding)}. | 
217  |  |      * @throws IllegalArgumentException  | 
218  |  |      *             If there was a syntax error in the pattern string.  | 
219  |  |      */  | 
220  |  |     static void parseToExistingProperties(const UnicodeString& pattern,  | 
221  |  |                                           DecimalFormatProperties& properties,  | 
222  |  |                                           IgnoreRounding ignoreRounding, UErrorCode& status);  | 
223  |  |  | 
224  |  |   private:  | 
225  |  |     static void parseToExistingPropertiesImpl(const UnicodeString& pattern,  | 
226  |  |                                               DecimalFormatProperties& properties,  | 
227  |  |                                               IgnoreRounding ignoreRounding, UErrorCode& status);  | 
228  |  |  | 
229  |  |     /** Finalizes the temporary data stored in the ParsedPatternInfo to the Properties. */  | 
230  |  |     static void patternInfoToProperties(DecimalFormatProperties& properties,  | 
231  |  |                                         ParsedPatternInfo& patternInfo, IgnoreRounding _ignoreRounding,  | 
232  |  |                                         UErrorCode& status);  | 
233  |  | };  | 
234  |  |  | 
235  |  | class U_I18N_API PatternStringUtils { | 
236  |  |   public:  | 
237  |  |     /**  | 
238  |  |      * Determine whether a given roundingIncrement should be ignored for formatting  | 
239  |  |      * based on the current maxFrac value (maximum fraction digits). For example a  | 
240  |  |      * roundingIncrement of 0.01 should be ignored if maxFrac is 1, but not if maxFrac  | 
241  |  |      * is 2 or more. Note that roundingIncrements are rounded up in significance, so  | 
242  |  |      * a roundingIncrement of 0.006 is treated like 0.01 for this determination, i.e.  | 
243  |  |      * it should not be ignored if maxFrac is 2 or more (but a roundingIncrement of  | 
244  |  |      * 0.005 is treated like 0.001 for significance).  | 
245  |  |      *  | 
246  |  |      * This test is needed for both NumberPropertyMapper::oldToNew and   | 
247  |  |      * PatternStringUtils::propertiesToPatternString. In Java it cannot be  | 
248  |  |      * exported by NumberPropertyMapper (package private) so it is in  | 
249  |  |      * PatternStringUtils, do the same in C.  | 
250  |  |      *  | 
251  |  |      * @param roundIncr  | 
252  |  |      *            The roundingIncrement to be checked. Must be non-zero.  | 
253  |  |      * @param maxFrac  | 
254  |  |      *            The current maximum fraction digits value.  | 
255  |  |      * @return true if roundIncr should be ignored for formatting.  | 
256  |  |      */  | 
257  |  |      static bool ignoreRoundingIncrement(double roundIncr, int32_t maxFrac);  | 
258  |  |  | 
259  |  |     /**  | 
260  |  |      * Creates a pattern string from a property bag.  | 
261  |  |      *  | 
262  |  |      * <p>  | 
263  |  |      * Since pattern strings support only a subset of the functionality available in a property bag, a new property bag  | 
264  |  |      * created from the string returned by this function may not be the same as the original property bag.  | 
265  |  |      *  | 
266  |  |      * @param properties  | 
267  |  |      *            The property bag to serialize.  | 
268  |  |      * @return A pattern string approximately serializing the property bag.  | 
269  |  |      */  | 
270  |  |     static UnicodeString propertiesToPatternString(const DecimalFormatProperties& properties,  | 
271  |  |                                                    UErrorCode& status);  | 
272  |  |  | 
273  |  |  | 
274  |  |     /**  | 
275  |  |      * Converts a pattern between standard notation and localized notation. Localized notation means that instead of  | 
276  |  |      * using generic placeholders in the pattern, you use the corresponding locale-specific characters instead. For  | 
277  |  |      * example, in locale <em>fr-FR</em>, the period in the pattern "0.000" means "decimal" in standard notation (as it  | 
278  |  |      * does in every other locale), but it means "grouping" in localized notation.  | 
279  |  |      *  | 
280  |  |      * <p>  | 
281  |  |      * A greedy string-substitution strategy is used to substitute locale symbols. If two symbols are ambiguous or have  | 
282  |  |      * the same prefix, the result is not well-defined.  | 
283  |  |      *  | 
284  |  |      * <p>  | 
285  |  |      * Locale symbols are not allowed to contain the ASCII quote character.  | 
286  |  |      *  | 
287  |  |      * <p>  | 
288  |  |      * This method is provided for backwards compatibility and should not be used in any new code.  | 
289  |  |      *  | 
290  |  |      * TODO(C++): This method is not yet implemented.  | 
291  |  |      *  | 
292  |  |      * @param input  | 
293  |  |      *            The pattern to convert.  | 
294  |  |      * @param symbols  | 
295  |  |      *            The symbols corresponding to the localized pattern.  | 
296  |  |      * @param toLocalized  | 
297  |  |      *            true to convert from standard to localized notation; false to convert from localized to standard  | 
298  |  |      *            notation.  | 
299  |  |      * @return The pattern expressed in the other notation.  | 
300  |  |      */  | 
301  |  |     static UnicodeString convertLocalized(const UnicodeString& input, const DecimalFormatSymbols& symbols,  | 
302  |  |                                           bool toLocalized, UErrorCode& status);  | 
303  |  |  | 
304  |  |     /**  | 
305  |  |      * This method contains the heart of the logic for rendering LDML affix strings. It handles  | 
306  |  |      * sign-always-shown resolution, whether to use the positive or negative subpattern, permille  | 
307  |  |      * substitution, and plural forms for CurrencyPluralInfo.  | 
308  |  |      */  | 
309  |  |     static void patternInfoToStringBuilder(const AffixPatternProvider& patternInfo, bool isPrefix,  | 
310  |  |                                            PatternSignType patternSignType,  | 
311  |  |                                            bool approximately,  | 
312  |  |                                            StandardPlural::Form plural, bool perMilleReplacesPercent,  | 
313  |  |                                            UnicodeString& output);  | 
314  |  |  | 
315  |  |     static PatternSignType resolveSignDisplay(UNumberSignDisplay signDisplay, Signum signum);  | 
316  |  |  | 
317  |  |   private:  | 
318  |  |     /** @return The number of chars inserted. */  | 
319  |  |     static int escapePaddingString(UnicodeString input, UnicodeString& output, int startIndex,  | 
320  |  |                                    UErrorCode& status);  | 
321  |  | };  | 
322  |  |  | 
323  |  | } // namespace impl  | 
324  |  | } // namespace number  | 
325  |  | U_NAMESPACE_END  | 
326  |  |  | 
327  |  |  | 
328  |  | #endif //__NUMBER_PATTERNSTRING_H__  | 
329  |  |  | 
330  |  | #endif /* #if !UCONFIG_NO_FORMATTING */  |