1 | // © 2016 and later: Unicode, Inc. and others. |
2 | // License & terms of use: http://www.unicode.org/copyright.html |
3 | /* |
4 | ******************************************************************************* |
5 | * Copyright (C) 1996-2014, International Business Machines Corporation and |
6 | * others. All Rights Reserved. |
7 | ******************************************************************************* |
8 | */ |
9 | |
10 | #ifndef CANITER_H |
11 | #define CANITER_H |
12 | |
13 | #include "unicode/utypes.h" |
14 | |
15 | #if U_SHOW_CPLUSPLUS_API |
16 | |
17 | #if !UCONFIG_NO_NORMALIZATION |
18 | |
19 | #include "unicode/uobject.h" |
20 | #include "unicode/unistr.h" |
21 | |
22 | /** |
23 | * \file |
24 | * \brief C++ API: Canonical Iterator |
25 | */ |
26 | |
27 | /** Should permutation skip characters with combining class zero |
28 | * Should be either TRUE or FALSE. This is a compile time option |
29 | * @stable ICU 2.4 |
30 | */ |
31 | #ifndef CANITER_SKIP_ZEROES |
32 | #define CANITER_SKIP_ZEROES TRUE |
33 | #endif |
34 | |
35 | U_NAMESPACE_BEGIN |
36 | |
37 | class Hashtable; |
38 | class Normalizer2; |
39 | class Normalizer2Impl; |
40 | |
41 | /** |
42 | * This class allows one to iterate through all the strings that are canonically equivalent to a given |
43 | * string. For example, here are some sample results: |
44 | Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} |
45 | 1: \\u0041\\u030A\\u0064\\u0307\\u0327 |
46 | = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} |
47 | 2: \\u0041\\u030A\\u0064\\u0327\\u0307 |
48 | = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} |
49 | 3: \\u0041\\u030A\\u1E0B\\u0327 |
50 | = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} |
51 | 4: \\u0041\\u030A\\u1E11\\u0307 |
52 | = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} |
53 | 5: \\u00C5\\u0064\\u0307\\u0327 |
54 | = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} |
55 | 6: \\u00C5\\u0064\\u0327\\u0307 |
56 | = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} |
57 | 7: \\u00C5\\u1E0B\\u0327 |
58 | = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} |
59 | 8: \\u00C5\\u1E11\\u0307 |
60 | = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} |
61 | 9: \\u212B\\u0064\\u0307\\u0327 |
62 | = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} |
63 | 10: \\u212B\\u0064\\u0327\\u0307 |
64 | = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} |
65 | 11: \\u212B\\u1E0B\\u0327 |
66 | = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} |
67 | 12: \\u212B\\u1E11\\u0307 |
68 | = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} |
69 | *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones, |
70 | * since it has not been optimized for that situation. |
71 | * Note, CanonicalIterator is not intended to be subclassed. |
72 | * @author M. Davis |
73 | * @author C++ port by V. Weinstein |
74 | * @stable ICU 2.4 |
75 | */ |
76 | class U_COMMON_API CanonicalIterator U_FINAL : public UObject { |
77 | public: |
78 | /** |
79 | * Construct a CanonicalIterator object |
80 | * @param source string to get results for |
81 | * @param status Fill-in parameter which receives the status of this operation. |
82 | * @stable ICU 2.4 |
83 | */ |
84 | CanonicalIterator(const UnicodeString &source, UErrorCode &status); |
85 | |
86 | /** Destructor |
87 | * Cleans pieces |
88 | * @stable ICU 2.4 |
89 | */ |
90 | virtual ~CanonicalIterator(); |
91 | |
92 | /** |
93 | * Gets the NFD form of the current source we are iterating over. |
94 | * @return gets the source: NOTE: it is the NFD form of source |
95 | * @stable ICU 2.4 |
96 | */ |
97 | UnicodeString getSource(); |
98 | |
99 | /** |
100 | * Resets the iterator so that one can start again from the beginning. |
101 | * @stable ICU 2.4 |
102 | */ |
103 | void reset(); |
104 | |
105 | /** |
106 | * Get the next canonically equivalent string. |
107 | * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b> |
108 | * @return the next string that is canonically equivalent. A bogus string is returned when |
109 | * the iteration is done. |
110 | * @stable ICU 2.4 |
111 | */ |
112 | UnicodeString next(); |
113 | |
114 | /** |
115 | * Set a new source for this iterator. Allows object reuse. |
116 | * @param newSource the source string to iterate against. This allows the same iterator to be used |
117 | * while changing the source string, saving object creation. |
118 | * @param status Fill-in parameter which receives the status of this operation. |
119 | * @stable ICU 2.4 |
120 | */ |
121 | void setSource(const UnicodeString &newSource, UErrorCode &status); |
122 | |
123 | #ifndef U_HIDE_INTERNAL_API |
124 | /** |
125 | * Dumb recursive implementation of permutation. |
126 | * TODO: optimize |
127 | * @param source the string to find permutations for |
128 | * @param skipZeros determine if skip zeros |
129 | * @param result the results in a set. |
130 | * @param status Fill-in parameter which receives the status of this operation. |
131 | * @internal |
132 | */ |
133 | static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status); |
134 | #endif /* U_HIDE_INTERNAL_API */ |
135 | |
136 | /** |
137 | * ICU "poor man's RTTI", returns a UClassID for this class. |
138 | * |
139 | * @stable ICU 2.2 |
140 | */ |
141 | static UClassID U_EXPORT2 getStaticClassID(); |
142 | |
143 | /** |
144 | * ICU "poor man's RTTI", returns a UClassID for the actual class. |
145 | * |
146 | * @stable ICU 2.2 |
147 | */ |
148 | virtual UClassID getDynamicClassID() const; |
149 | |
150 | private: |
151 | // ===================== PRIVATES ============================== |
152 | // private default constructor |
153 | CanonicalIterator(); |
154 | |
155 | |
156 | /** |
157 | * Copy constructor. Private for now. |
158 | * @internal (private) |
159 | */ |
160 | CanonicalIterator(const CanonicalIterator& other); |
161 | |
162 | /** |
163 | * Assignment operator. Private for now. |
164 | * @internal (private) |
165 | */ |
166 | CanonicalIterator& operator=(const CanonicalIterator& other); |
167 | |
168 | // fields |
169 | UnicodeString source; |
170 | UBool done; |
171 | |
172 | // 2 dimensional array holds the pieces of the string with |
173 | // their different canonically equivalent representations |
174 | UnicodeString **pieces; |
175 | int32_t pieces_length; |
176 | int32_t *pieces_lengths; |
177 | |
178 | // current is used in iterating to combine pieces |
179 | int32_t *current; |
180 | int32_t current_length; |
181 | |
182 | // transient fields |
183 | UnicodeString buffer; |
184 | |
185 | const Normalizer2 &nfd; |
186 | const Normalizer2Impl &nfcImpl; |
187 | |
188 | // we have a segment, in NFD. Find all the strings that are canonically equivalent to it. |
189 | UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment) |
190 | |
191 | //Set getEquivalents2(String segment); |
192 | Hashtable *getEquivalents2(Hashtable *fillinResult, const char16_t *segment, int32_t segLen, UErrorCode &status); |
193 | //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status); |
194 | |
195 | /** |
196 | * See if the decomposition of cp2 is at segment starting at segmentPos |
197 | * (with canonical rearrangment!) |
198 | * If so, take the remainder, and return the equivalents |
199 | */ |
200 | //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer); |
201 | Hashtable *(Hashtable *fillinResult, UChar32 comp, const char16_t *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status); |
202 | //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status); |
203 | |
204 | void cleanPieces(); |
205 | |
206 | }; |
207 | |
208 | U_NAMESPACE_END |
209 | |
210 | #endif /* #if !UCONFIG_NO_NORMALIZATION */ |
211 | |
212 | #endif /* U_SHOW_CPLUSPLUS_API */ |
213 | |
214 | #endif |
215 | |