/src/icu/source/i18n/number_affixutils.h

Source (jump to first uncovered line)
// © 2017 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html

#include "unicode/utypes.h"

#if !UCONFIG_NO_FORMATTING
#ifndef __NUMBER_AFFIXUTILS_H__
#define __NUMBER_AFFIXUTILS_H__

#include <cstdint>
#include "number_types.h"
#include "unicode/stringpiece.h"
#include "unicode/unistr.h"
#include "formatted_string_builder.h"
#include "unicode/uniset.h"

U_NAMESPACE_BEGIN namespace number {
namespace impl {

enum AffixPatternState {
    STATE_BASE = 0,
    STATE_FIRST_QUOTE = 1,
    STATE_INSIDE_QUOTE = 2,
    STATE_AFTER_QUOTE = 3,
    STATE_FIRST_CURR = 4,
    STATE_SECOND_CURR = 5,
    STATE_THIRD_CURR = 6,
    STATE_FOURTH_CURR = 7,
    STATE_FIFTH_CURR = 8,
    STATE_OVERFLOW_CURR = 9
};

// enum AffixPatternType defined in internals.h

struct AffixTag {
    int32_t offset;
    UChar32 codePoint;
    AffixPatternState state;
    AffixPatternType type;

    AffixTag()
            : offset(0), state(STATE_BASE) {}

    AffixTag(int32_t offset)
            : offset(offset) {}

    AffixTag(int32_t offset, UChar32 codePoint, AffixPatternState state, AffixPatternType type)
            : offset(offset), codePoint(codePoint), state(state), type(type) {}
};

class TokenConsumer {
  public:
    virtual ~TokenConsumer();

    virtual void consumeToken(AffixPatternType type, UChar32 cp, UErrorCode& status) = 0;
};

// Exported as U_I18N_API because it is a base class for other exported types
class U_I18N_API SymbolProvider {
  public:
    virtual ~SymbolProvider();

    // TODO: Could this be more efficient if it returned by reference?
    virtual UnicodeString getSymbol(AffixPatternType type) const = 0;
};

/**
 * Performs manipulations on affix patterns: the prefix and suffix strings associated with a decimal
 * format pattern. For example:
 *
 * <table>
 * <tr><th>Affix Pattern</th><th>Example Unescaped (Formatted) String</th></tr>
 * <tr><td>abc</td><td>abc</td></tr>
 * <tr><td>ab-</td><td>ab−</td></tr>
 * <tr><td>ab'-'</td><td>ab-</td></tr>
 * <tr><td>ab''</td><td>ab'</td></tr>
 * </table>
 *
 * To manually iterate over tokens in a literal string, use the following pattern, which is designed
 * to be efficient.
 *
 * <pre>
 * long tag = 0L;
 * while (AffixPatternUtils.hasNext(tag, patternString)) {
 *   tag = AffixPatternUtils.nextToken(tag, patternString);
 *   int typeOrCp = AffixPatternUtils.getTypeOrCp(tag);
 *   switch (typeOrCp) {
 *     case AffixPatternUtils.TYPE_MINUS_SIGN:
 *       // Current token is a minus sign.
 *       break;
 *     case AffixPatternUtils.TYPE_PLUS_SIGN:
 *       // Current token is a plus sign.
 *       break;
 *     case AffixPatternUtils.TYPE_PERCENT:
 *       // Current token is a percent sign.
 *       break;
 *     // ... other types ...
 *     default:
 *       // Current token is an arbitrary code point.
 *       // The variable typeOrCp is the code point.
 *       break;
 *   }
 * }
 * </pre>
 */
class U_I18N_API AffixUtils {

  public:

    /**
     * Estimates the number of code points present in an unescaped version of the affix pattern string
     * (one that would be returned by {@link #unescape}), assuming that all interpolated symbols
     * consume one code point and that currencies consume as many code points as their symbol width.
     * Used for computing padding width.
     *
     * @param patternString The original string whose width will be estimated.
     * @return The length of the unescaped string.
     */
    static int32_t estimateLength(const UnicodeString& patternString, UErrorCode& status);

    /**
     * Takes a string and escapes (quotes) characters that have special meaning in the affix pattern
     * syntax. This function does not reverse-lookup symbols.
     *
     * <p>Example input: "-$x"; example output: "'-'$x"
     *
     * @param input The string to be escaped.
     * @return The resulting UnicodeString.
     */
    static UnicodeString escape(const UnicodeString& input);

    static Field getFieldForType(AffixPatternType type);

    /**
     * Executes the unescape state machine. Replaces the unquoted characters "-", "+", "%", "‰", and
     * "¤" with the corresponding symbols provided by the {@link SymbolProvider}, and inserts the
     * result into the FormattedStringBuilder at the requested location.
     *
     * <p>Example input: "'-'¤x"; example output: "-$x"
     *
     * @param affixPattern The original string to be unescaped.
     * @param output The FormattedStringBuilder to mutate with the result.
     * @param position The index into the FormattedStringBuilder to insert the string.
     * @param provider An object to generate locale symbols.
     */
    static int32_t unescape(const UnicodeString& affixPattern, FormattedStringBuilder& output,
                            int32_t position, const SymbolProvider& provider, Field field,
                            UErrorCode& status);

    /**
   * Sames as {@link #unescape}, but only calculates the code point count.  More efficient than {@link #unescape}
   * if you only need the length but not the string itself.
     *
     * @param affixPattern The original string to be unescaped.
     * @param provider An object to generate locale symbols.
     * @return The same return value as if you called {@link #unescape}.
     */
    static int32_t unescapedCodePointCount(const UnicodeString& affixPattern,
                                           const SymbolProvider& provider, UErrorCode& status);

    /**
     * Checks whether the given affix pattern contains at least one token of the given type, which is
     * one of the constants "TYPE_" in {@link AffixPatternUtils}.
     *
     * @param affixPattern The affix pattern to check.
     * @param type The token type.
     * @return true if the affix pattern contains the given token type; false otherwise.
     */
    static bool containsType(const UnicodeString& affixPattern, AffixPatternType type, UErrorCode& status);

    /**
     * Checks whether the specified affix pattern has any unquoted currency symbols ("¤").
     *
     * @param affixPattern The string to check for currency symbols.
     * @return true if the literal has at least one unquoted currency symbol; false otherwise.
     */
    static bool hasCurrencySymbols(const UnicodeString& affixPattern, UErrorCode& status);

    /**
     * Replaces all occurrences of tokens with the given type with the given replacement char.
     *
     * @param affixPattern The source affix pattern (does not get modified).
     * @param type The token type.
     * @param replacementChar The char to substitute in place of chars of the given token type.
     * @return A string containing the new affix pattern.
     */
    static UnicodeString replaceType(const UnicodeString& affixPattern, AffixPatternType type,
                                     char16_t replacementChar, UErrorCode& status);

    /**
     * Returns whether the given affix pattern contains only symbols and ignorables as defined by the
     * given ignorables set.
     */
    static bool containsOnlySymbolsAndIgnorables(const UnicodeString& affixPattern,
                                                 const UnicodeSet& ignorables, UErrorCode& status);

    /**
     * Iterates over the affix pattern, calling the TokenConsumer for each token.
     */
    static void iterateWithConsumer(const UnicodeString& affixPattern, TokenConsumer& consumer,
                                    UErrorCode& status);

    /**
     * Returns the next token from the affix pattern.
     *
     * @param tag A bitmask used for keeping track of state from token to token. The initial value
     *     should be 0L.
     * @param patternString The affix pattern.
     * @return The bitmask tag to pass to the next call of this method to retrieve the following token
     *     (never negative), or -1 if there were no more tokens in the affix pattern.
     * @see #hasNext
     */
    static AffixTag nextToken(AffixTag tag, const UnicodeString& patternString, UErrorCode& status);

    /**
     * Returns whether the affix pattern string has any more tokens to be retrieved from a call to
     * {@link #nextToken}.
     *
     * @param tag The bitmask tag of the previous token, as returned by {@link #nextToken}.
     * @param string The affix pattern.
     * @return true if there are more tokens to consume; false otherwise.
     */
    static bool hasNext(const AffixTag& tag, const UnicodeString& string);

  private:
    /**
     * Encodes the given values into a tag struct.
     * The order of the arguments is consistent with Java, but the order of the stored
     * fields is not necessarily the same.
     */
    static inline AffixTag makeTag(int32_t offset, AffixPatternType type, AffixPatternState state,
                                   UChar32 cp) {
        return {offset, cp, state, type};
    }
};

} // namespace impl
} // namespace number
U_NAMESPACE_END


#endif //__NUMBER_AFFIXUTILS_H__

#endif /* #if !UCONFIG_NO_FORMATTING */

Coverage Report

Created: 2025-01-28 06:38

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_AFFIXUTILS_H__
8		#define __NUMBER_AFFIXUTILS_H__
9
10		#include <cstdint>
11		#include "number_types.h"
12		#include "unicode/stringpiece.h"
13		#include "unicode/unistr.h"
14		#include "formatted_string_builder.h"
15		#include "unicode/uniset.h"
16
17		U_NAMESPACE_BEGIN namespace number {
18		namespace impl {
19
20		enum AffixPatternState {
21		STATE_BASE = 0,
22		STATE_FIRST_QUOTE = 1,
23		STATE_INSIDE_QUOTE = 2,
24		STATE_AFTER_QUOTE = 3,
25		STATE_FIRST_CURR = 4,
26		STATE_SECOND_CURR = 5,
27		STATE_THIRD_CURR = 6,
28		STATE_FOURTH_CURR = 7,
29		STATE_FIFTH_CURR = 8,
30		STATE_OVERFLOW_CURR = 9
31		};
32
33		// enum AffixPatternType defined in internals.h
34
35		struct AffixTag {
36		int32_t offset;
37		UChar32 codePoint;
38		AffixPatternState state;
39		AffixPatternType type;
40
41		AffixTag()
42	0	: offset(0), state(STATE_BASE) {}
43
44		AffixTag(int32_t offset)
45	0	: offset(offset) {}
46
47		AffixTag(int32_t offset, UChar32 codePoint, AffixPatternState state, AffixPatternType type)
48	0	: offset(offset), codePoint(codePoint), state(state), type(type) {}
49		};
50
51		class TokenConsumer {
52		public:
53		virtual ~TokenConsumer();
54
55		virtual void consumeToken(AffixPatternType type, UChar32 cp, UErrorCode& status) = 0;
56		};
57
58		// Exported as U_I18N_API because it is a base class for other exported types
59		class U_I18N_API SymbolProvider {
60		public:
61		virtual ~SymbolProvider();
62
63		// TODO: Could this be more efficient if it returned by reference?
64		virtual UnicodeString getSymbol(AffixPatternType type) const = 0;
65		};
66
67		/**
68		* Performs manipulations on affix patterns: the prefix and suffix strings associated with a decimal
69		* format pattern. For example:
70		*
71		* <table>
72		* <tr><th>Affix Pattern</th><th>Example Unescaped (Formatted) String</th></tr>
73		* <tr><td>abc</td><td>abc</td></tr>
74		* <tr><td>ab-</td><td>ab−</td></tr>
75		* <tr><td>ab'-'</td><td>ab-</td></tr>
76		* <tr><td>ab''</td><td>ab'</td></tr>
77		* </table>
78		*
79		* To manually iterate over tokens in a literal string, use the following pattern, which is designed
80		* to be efficient.
81		*
82		* <pre>
83		* long tag = 0L;
84		* while (AffixPatternUtils.hasNext(tag, patternString)) {
85		* tag = AffixPatternUtils.nextToken(tag, patternString);
86		* int typeOrCp = AffixPatternUtils.getTypeOrCp(tag);
87		* switch (typeOrCp) {
88		* case AffixPatternUtils.TYPE_MINUS_SIGN:
89		* // Current token is a minus sign.
90		* break;
91		* case AffixPatternUtils.TYPE_PLUS_SIGN:
92		* // Current token is a plus sign.
93		* break;
94		* case AffixPatternUtils.TYPE_PERCENT:
95		* // Current token is a percent sign.
96		* break;
97		* // ... other types ...
98		* default:
99		* // Current token is an arbitrary code point.
100		* // The variable typeOrCp is the code point.
101		* break;
102		* }
103		* }
104		* </pre>
105		*/
106		class U_I18N_API AffixUtils {
107
108		public:
109
110		/**
111		* Estimates the number of code points present in an unescaped version of the affix pattern string
112		* (one that would be returned by {@link #unescape}), assuming that all interpolated symbols
113		* consume one code point and that currencies consume as many code points as their symbol width.
114		* Used for computing padding width.
115		*
116		* @param patternString The original string whose width will be estimated.
117		* @return The length of the unescaped string.
118		*/
119		static int32_t estimateLength(const UnicodeString& patternString, UErrorCode& status);
120
121		/**
122		* Takes a string and escapes (quotes) characters that have special meaning in the affix pattern
123		* syntax. This function does not reverse-lookup symbols.
124		*
125		* <p>Example input: "-$x"; example output: "'-'$x"
126		*
127		* @param input The string to be escaped.
128		* @return The resulting UnicodeString.
129		*/
130		static UnicodeString escape(const UnicodeString& input);
131
132		static Field getFieldForType(AffixPatternType type);
133
134		/**
135		* Executes the unescape state machine. Replaces the unquoted characters "-", "+", "%", "‰", and
136		* "¤" with the corresponding symbols provided by the {@link SymbolProvider}, and inserts the
137		* result into the FormattedStringBuilder at the requested location.
138		*
139		* <p>Example input: "'-'¤x"; example output: "-$x"
140		*
141		* @param affixPattern The original string to be unescaped.
142		* @param output The FormattedStringBuilder to mutate with the result.
143		* @param position The index into the FormattedStringBuilder to insert the string.
144		* @param provider An object to generate locale symbols.
145		*/
146		static int32_t unescape(const UnicodeString& affixPattern, FormattedStringBuilder& output,
147		int32_t position, const SymbolProvider& provider, Field field,
148		UErrorCode& status);
149
150		/**
151		* Sames as {@link #unescape}, but only calculates the code point count. More efficient than {@link #unescape}
152		* if you only need the length but not the string itself.
153		*
154		* @param affixPattern The original string to be unescaped.
155		* @param provider An object to generate locale symbols.
156		* @return The same return value as if you called {@link #unescape}.
157		*/
158		static int32_t unescapedCodePointCount(const UnicodeString& affixPattern,
159		const SymbolProvider& provider, UErrorCode& status);
160
161		/**
162		* Checks whether the given affix pattern contains at least one token of the given type, which is
163		* one of the constants "TYPE_" in {@link AffixPatternUtils}.
164		*
165		* @param affixPattern The affix pattern to check.
166		* @param type The token type.
167		* @return true if the affix pattern contains the given token type; false otherwise.
168		*/
169		static bool containsType(const UnicodeString& affixPattern, AffixPatternType type, UErrorCode& status);
170
171		/**
172		* Checks whether the specified affix pattern has any unquoted currency symbols ("¤").
173		*
174		* @param affixPattern The string to check for currency symbols.
175		* @return true if the literal has at least one unquoted currency symbol; false otherwise.
176		*/
177		static bool hasCurrencySymbols(const UnicodeString& affixPattern, UErrorCode& status);
178
179		/**
180		* Replaces all occurrences of tokens with the given type with the given replacement char.
181		*
182		* @param affixPattern The source affix pattern (does not get modified).
183		* @param type The token type.
184		* @param replacementChar The char to substitute in place of chars of the given token type.
185		* @return A string containing the new affix pattern.
186		*/
187		static UnicodeString replaceType(const UnicodeString& affixPattern, AffixPatternType type,
188		char16_t replacementChar, UErrorCode& status);
189
190		/**
191		* Returns whether the given affix pattern contains only symbols and ignorables as defined by the
192		* given ignorables set.
193		*/
194		static bool containsOnlySymbolsAndIgnorables(const UnicodeString& affixPattern,
195		const UnicodeSet& ignorables, UErrorCode& status);
196
197		/**
198		* Iterates over the affix pattern, calling the TokenConsumer for each token.
199		*/
200		static void iterateWithConsumer(const UnicodeString& affixPattern, TokenConsumer& consumer,
201		UErrorCode& status);
202
203		/**
204		* Returns the next token from the affix pattern.
205		*
206		* @param tag A bitmask used for keeping track of state from token to token. The initial value
207		* should be 0L.
208		* @param patternString The affix pattern.
209		* @return The bitmask tag to pass to the next call of this method to retrieve the following token
210		* (never negative), or -1 if there were no more tokens in the affix pattern.
211		* @see #hasNext
212		*/
213		static AffixTag nextToken(AffixTag tag, const UnicodeString& patternString, UErrorCode& status);
214
215		/**
216		* Returns whether the affix pattern string has any more tokens to be retrieved from a call to
217		* {@link #nextToken}.
218		*
219		* @param tag The bitmask tag of the previous token, as returned by {@link #nextToken}.
220		* @param string The affix pattern.
221		* @return true if there are more tokens to consume; false otherwise.
222		*/
223		static bool hasNext(const AffixTag& tag, const UnicodeString& string);
224
225		private:
226		/**
227		* Encodes the given values into a tag struct.
228		* The order of the arguments is consistent with Java, but the order of the stored
229		* fields is not necessarily the same.
230		*/
231		static inline AffixTag makeTag(int32_t offset, AffixPatternType type, AffixPatternState state,
232	0	UChar32 cp) {
233	0	return {offset, cp, state, type};
234	0	}
235		};
236
237		} // namespace impl
238		} // namespace number
239		U_NAMESPACE_END
240
241
242		#endif //__NUMBER_AFFIXUTILS_H__
243
244		#endif /* #if !UCONFIG_NO_FORMATTING */