/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 */ |