Coverage Report

Created: 2023-03-04 07:00

/src/icu/icu4c/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 hasCurrencyDecimal = false;
66
    bool hasMinusSign = false;
67
    bool hasPlusSign = false;
68
69
    Endpoints prefixEndpoints;
70
    Endpoints suffixEndpoints;
71
    Endpoints paddingEndpoints;
72
};
73
74
// Exported as U_I18N_API because it is needed for the unit test PatternStringTest
75
struct U_I18N_API ParsedPatternInfo : public AffixPatternProvider, public UMemory {
76
    UnicodeString pattern;
77
    ParsedSubpatternInfo positive;
78
    ParsedSubpatternInfo negative;
79
80
    ParsedPatternInfo()
81
623
            : state(this->pattern), currentSubpattern(nullptr) {}
82
83
623
    ~ParsedPatternInfo() override = default;
84
85
    // Need to declare this explicitly because of the destructor
86
    ParsedPatternInfo& operator=(ParsedPatternInfo&& src) noexcept = default;
87
88
    static int32_t getLengthFromEndpoints(const Endpoints& endpoints);
89
90
    char16_t charAt(int32_t flags, int32_t index) const override;
91
92
    int32_t length(int32_t flags) const override;
93
94
    UnicodeString getString(int32_t flags) const override;
95
96
    bool positiveHasPlusSign() const override;
97
98
    bool hasNegativeSubpattern() const override;
99
100
    bool negativeHasMinusSign() const override;
101
102
    bool hasCurrencySign() const override;
103
104
    bool containsSymbolType(AffixPatternType type, UErrorCode& status) const override;
105
106
    bool hasBody() const override;
107
108
    bool currencyAsDecimal() const override;
109
110
  private:
111
    struct U_I18N_API ParserState {
112
        const UnicodeString& pattern; // reference to the parent
113
        int32_t offset = 0;
114
115
        explicit ParserState(const UnicodeString& _pattern)
116
623
                : pattern(_pattern) {}
117
118
0
        ParserState& operator=(ParserState&& src) noexcept {
119
0
            // Leave pattern reference alone; it will continue to point to the same place in memory,
120
0
            // which gets overwritten by ParsedPatternInfo's implicit move assignment.
121
0
            offset = src.offset;
122
0
            return *this;
123
0
        }
124
125
        /** Returns the next code point, or -1 if string is too short. */
126
        UChar32 peek();
127
128
        /** Returns the code point after the next code point, or -1 if string is too short. */
129
        UChar32 peek2();
130
131
        /** Returns the next code point and then steps forward. */
132
        UChar32 next();
133
134
        // TODO: We don't currently do anything with the message string.
135
        // This method is here as a shell for Java compatibility.
136
0
        inline void toParseException(const char16_t* message) { (void) message; }
137
    } state;
138
139
    // NOTE: In Java, these are written as pure functions.
140
    // In C++, they're written as methods.
141
    // The behavior is the same.
142
143
    // Mutable transient pointer:
144
    ParsedSubpatternInfo* currentSubpattern;
145
146
    // In Java, "negative == null" tells us whether or not we had a negative subpattern.
147
    // In C++, we need to remember in another boolean.
148
    bool fHasNegativeSubpattern = false;
149
150
    const Endpoints& getEndpoints(int32_t flags) const;
151
152
    /** Run the recursive descent parser. */
153
    void consumePattern(const UnicodeString& patternString, UErrorCode& status);
154
155
    void consumeSubpattern(UErrorCode& status);
156
157
    void consumePadding(PadPosition paddingLocation, UErrorCode& status);
158
159
    void consumeAffix(Endpoints& endpoints, UErrorCode& status);
160
161
    void consumeLiteral(UErrorCode& status);
162
163
    void consumeFormat(UErrorCode& status);
164
165
    void consumeIntegerFormat(UErrorCode& status);
166
167
    void consumeFractionFormat(UErrorCode& status);
168
169
    void consumeExponent(UErrorCode& status);
170
171
    friend class PatternParser;
172
};
173
174
enum IgnoreRounding {
175
    IGNORE_ROUNDING_NEVER = 0, IGNORE_ROUNDING_IF_CURRENCY = 1, IGNORE_ROUNDING_ALWAYS = 2
176
};
177
178
class U_I18N_API PatternParser {
179
  public:
180
    /**
181
     * Runs the recursive descent parser on the given pattern string, returning a data structure with raw information
182
     * about the pattern string.
183
     *
184
     * <p>
185
     * To obtain a more useful form of the data, consider using {@link #parseToProperties} instead.
186
     *
187
     * TODO: Change argument type to const char16_t* instead of UnicodeString?
188
     *
189
     * @param patternString
190
     *            The LDML decimal format pattern (Excel-style pattern) to parse.
191
     * @return The results of the parse.
192
     */
193
    static void parseToPatternInfo(const UnicodeString& patternString, ParsedPatternInfo& patternInfo,
194
                                   UErrorCode& status);
195
196
    /**
197
     * Parses a pattern string into a new property bag.
198
     *
199
     * @param pattern
200
     *            The pattern string, like "#,##0.00"
201
     * @param ignoreRounding
202
     *            Whether to leave out rounding information (minFrac, maxFrac, and rounding increment) when parsing the
203
     *            pattern. This may be desirable if a custom rounding mode, such as CurrencyUsage, is to be used
204
     *            instead.
205
     * @return A property bag object.
206
     * @throws IllegalArgumentException
207
     *             If there is a syntax error in the pattern string.
208
     */
209
    static DecimalFormatProperties parseToProperties(const UnicodeString& pattern,
210
                                                     IgnoreRounding ignoreRounding, UErrorCode& status);
211
212
    static DecimalFormatProperties parseToProperties(const UnicodeString& pattern, UErrorCode& status);
213
214
    /**
215
     * Parses a pattern string into an existing property bag. All properties that can be encoded into a pattern string
216
     * will be overwritten with either their default value or with the value coming from the pattern string. Properties
217
     * that cannot be encoded into a pattern string, such as rounding mode, are not modified.
218
     *
219
     * @param pattern
220
     *            The pattern string, like "#,##0.00"
221
     * @param properties
222
     *            The property bag object to overwrite.
223
     * @param ignoreRounding
224
     *            See {@link #parseToProperties(String pattern, int ignoreRounding)}.
225
     * @throws IllegalArgumentException
226
     *             If there was a syntax error in the pattern string.
227
     */
228
    static void parseToExistingProperties(const UnicodeString& pattern,
229
                                          DecimalFormatProperties& properties,
230
                                          IgnoreRounding ignoreRounding, UErrorCode& status);
231
232
  private:
233
    static void parseToExistingPropertiesImpl(const UnicodeString& pattern,
234
                                              DecimalFormatProperties& properties,
235
                                              IgnoreRounding ignoreRounding, UErrorCode& status);
236
237
    /** Finalizes the temporary data stored in the ParsedPatternInfo to the Properties. */
238
    static void patternInfoToProperties(DecimalFormatProperties& properties,
239
                                        ParsedPatternInfo& patternInfo, IgnoreRounding _ignoreRounding,
240
                                        UErrorCode& status);
241
};
242
243
class U_I18N_API PatternStringUtils {
244
  public:
245
    /**
246
     * Determine whether a given roundingIncrement should be ignored for formatting
247
     * based on the current maxFrac value (maximum fraction digits). For example a
248
     * roundingIncrement of 0.01 should be ignored if maxFrac is 1, but not if maxFrac
249
     * is 2 or more. Note that roundingIncrements are rounded up in significance, so
250
     * a roundingIncrement of 0.006 is treated like 0.01 for this determination, i.e.
251
     * it should not be ignored if maxFrac is 2 or more (but a roundingIncrement of
252
     * 0.005 is treated like 0.001 for significance).
253
     *
254
     * This test is needed for both NumberPropertyMapper::oldToNew and 
255
     * PatternStringUtils::propertiesToPatternString. In Java it cannot be
256
     * exported by NumberPropertyMapper (package private) so it is in
257
     * PatternStringUtils, do the same in C.
258
     *
259
     * @param roundIncr
260
     *            The roundingIncrement to be checked. Must be non-zero.
261
     * @param maxFrac
262
     *            The current maximum fraction digits value.
263
     * @return true if roundIncr should be ignored for formatting.
264
     */
265
     static bool ignoreRoundingIncrement(double roundIncr, int32_t maxFrac);
266
267
    /**
268
     * Creates a pattern string from a property bag.
269
     *
270
     * <p>
271
     * Since pattern strings support only a subset of the functionality available in a property bag, a new property bag
272
     * created from the string returned by this function may not be the same as the original property bag.
273
     *
274
     * @param properties
275
     *            The property bag to serialize.
276
     * @return A pattern string approximately serializing the property bag.
277
     */
278
    static UnicodeString propertiesToPatternString(const DecimalFormatProperties& properties,
279
                                                   UErrorCode& status);
280
281
282
    /**
283
     * Converts a pattern between standard notation and localized notation. Localized notation means that instead of
284
     * using generic placeholders in the pattern, you use the corresponding locale-specific characters instead. For
285
     * example, in locale <em>fr-FR</em>, the period in the pattern "0.000" means "decimal" in standard notation (as it
286
     * does in every other locale), but it means "grouping" in localized notation.
287
     *
288
     * <p>
289
     * A greedy string-substitution strategy is used to substitute locale symbols. If two symbols are ambiguous or have
290
     * the same prefix, the result is not well-defined.
291
     *
292
     * <p>
293
     * Locale symbols are not allowed to contain the ASCII quote character.
294
     *
295
     * <p>
296
     * This method is provided for backwards compatibility and should not be used in any new code.
297
     *
298
     * TODO(C++): This method is not yet implemented.
299
     *
300
     * @param input
301
     *            The pattern to convert.
302
     * @param symbols
303
     *            The symbols corresponding to the localized pattern.
304
     * @param toLocalized
305
     *            true to convert from standard to localized notation; false to convert from localized to standard
306
     *            notation.
307
     * @return The pattern expressed in the other notation.
308
     */
309
    static UnicodeString convertLocalized(const UnicodeString& input, const DecimalFormatSymbols& symbols,
310
                                          bool toLocalized, UErrorCode& status);
311
312
    /**
313
     * This method contains the heart of the logic for rendering LDML affix strings. It handles
314
     * sign-always-shown resolution, whether to use the positive or negative subpattern, permille
315
     * substitution, and plural forms for CurrencyPluralInfo.
316
     */
317
    static void patternInfoToStringBuilder(const AffixPatternProvider& patternInfo, bool isPrefix,
318
                                           PatternSignType patternSignType,
319
                                           bool approximately,
320
                                           StandardPlural::Form plural,
321
                                           bool perMilleReplacesPercent,
322
                                           bool dropCurrencySymbols,
323
                                           UnicodeString& output);
324
325
    static PatternSignType resolveSignDisplay(UNumberSignDisplay signDisplay, Signum signum);
326
327
  private:
328
    /** @return The number of chars inserted. */
329
    static int escapePaddingString(UnicodeString input, UnicodeString& output, int startIndex,
330
                                   UErrorCode& status);
331
};
332
333
} // namespace impl
334
} // namespace number
335
U_NAMESPACE_END
336
337
338
#endif //__NUMBER_PATTERNSTRING_H__
339
340
#endif /* #if !UCONFIG_NO_FORMATTING */