include/unicode/caniter.h

0001 // © 2016 and later: Unicode, Inc. and others.
0002 // License & terms of use: http://www.unicode.org/copyright.html
0003 /*
0004  *******************************************************************************
0005  * Copyright (C) 1996-2014, International Business Machines Corporation and
0006  * others. All Rights Reserved.
0007  *******************************************************************************
0008  */
0009
0010 #ifndef CANITER_H
0011 #define CANITER_H
0012
0013 #include "unicode/utypes.h"
0014
0015 #if U_SHOW_CPLUSPLUS_API
0016
0017 #if !UCONFIG_NO_NORMALIZATION
0018
0019 #include "unicode/uobject.h"
0020 #include "unicode/unistr.h"
0021
0022 /**
0023  * \file
0024  * \brief C++ API: Canonical Iterator
0025  */
0026
0027 /** Should permutation skip characters with combining class zero
0028  *  Should be either true or false. This is a compile time option
0029  *  @stable ICU 2.4
0030  */
0031 #ifndef CANITER_SKIP_ZEROES
0032 #define CANITER_SKIP_ZEROES true
0033 #endif
0034
0035 U_NAMESPACE_BEGIN
0036
0037 class Hashtable;
0038 class Normalizer2;
0039 class Normalizer2Impl;
0040
0041 /**
0042  * This class allows one to iterate through all the strings that are canonically equivalent to a given
0043  * string. For example, here are some sample results:
0044 Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
0045 1: \\u0041\\u030A\\u0064\\u0307\\u0327
0046  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
0047 2: \\u0041\\u030A\\u0064\\u0327\\u0307
0048  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
0049 3: \\u0041\\u030A\\u1E0B\\u0327
0050  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
0051 4: \\u0041\\u030A\\u1E11\\u0307
0052  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
0053 5: \\u00C5\\u0064\\u0307\\u0327
0054  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
0055 6: \\u00C5\\u0064\\u0327\\u0307
0056  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
0057 7: \\u00C5\\u1E0B\\u0327
0058  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
0059 8: \\u00C5\\u1E11\\u0307
0060  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
0061 9: \\u212B\\u0064\\u0307\\u0327
0062  = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
0063 10: \\u212B\\u0064\\u0327\\u0307
0064  = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
0065 11: \\u212B\\u1E0B\\u0327
0066  = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
0067 12: \\u212B\\u1E11\\u0307
0068  = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
0069  *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones,
0070  * since it has not been optimized for that situation.
0071  * Note, CanonicalIterator is not intended to be subclassed.
0072  * @author M. Davis
0073  * @author C++ port by V. Weinstein
0074  * @stable ICU 2.4
0075  */
0076 class U_COMMON_API CanonicalIterator final : public UObject {
0077 public:
0078     /**
0079      * Construct a CanonicalIterator object
0080      * @param source    string to get results for
0081      * @param status    Fill-in parameter which receives the status of this operation.
0082      * @stable ICU 2.4
0083      */
0084     CanonicalIterator(const UnicodeString &source, UErrorCode &status);
0085
0086     /** Destructor
0087      *  Cleans pieces
0088      * @stable ICU 2.4
0089      */
0090     virtual ~CanonicalIterator();
0091
0092     /**
0093      * Gets the NFD form of the current source we are iterating over.
0094      * @return gets the source: NOTE: it is the NFD form of source
0095      * @stable ICU 2.4
0096      */
0097     UnicodeString getSource();
0098
0099     /**
0100      * Resets the iterator so that one can start again from the beginning.
0101      * @stable ICU 2.4
0102      */
0103     void reset();
0104
0105     /**
0106      * Get the next canonically equivalent string.
0107      * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b>
0108      * @return the next string that is canonically equivalent. A bogus string is returned when
0109      * the iteration is done.
0110      * @stable ICU 2.4
0111      */
0112     UnicodeString next();
0113
0114     /**
0115      * Set a new source for this iterator. Allows object reuse.
0116      * @param newSource     the source string to iterate against. This allows the same iterator to be used
0117      *                     while changing the source string, saving object creation.
0118      * @param status        Fill-in parameter which receives the status of this operation.
0119      * @stable ICU 2.4
0120      */
0121     void setSource(const UnicodeString &newSource, UErrorCode &status);
0122
0123 #ifndef U_HIDE_INTERNAL_API
0124     /**
0125      * Dumb recursive implementation of permutation.
0126      * TODO: optimize
0127      * @param source     the string to find permutations for
0128      * @param skipZeros  determine if skip zeros
0129      * @param result     the results in a set.
0130      * @param status       Fill-in parameter which receives the status of this operation.
0131      * @param depth     depth of the call.
0132      * @internal
0133      */
0134     static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status, int32_t depth=0);
0135 #endif  /* U_HIDE_INTERNAL_API */
0136
0137     /**
0138      * ICU "poor man's RTTI", returns a UClassID for this class.
0139      *
0140      * @stable ICU 2.2
0141      */
0142     static UClassID U_EXPORT2 getStaticClassID();
0143
0144     /**
0145      * ICU "poor man's RTTI", returns a UClassID for the actual class.
0146      *
0147      * @stable ICU 2.2
0148      */
0149     virtual UClassID getDynamicClassID() const override;
0150
0151 private:
0152     // ===================== PRIVATES ==============================
0153     // private default constructor
0154     CanonicalIterator() = delete;
0155
0156
0157     /**
0158      * Copy constructor. Private for now.
0159      * @internal (private)
0160      */
0161     CanonicalIterator(const CanonicalIterator& other) = delete;
0162
0163     /**
0164      * Assignment operator. Private for now.
0165      * @internal (private)
0166      */
0167     CanonicalIterator& operator=(const CanonicalIterator& other) = delete;
0168
0169     // fields
0170     UnicodeString source;
0171     UBool done;
0172
0173     // 2 dimensional array holds the pieces of the string with
0174     // their different canonically equivalent representations
0175     UnicodeString **pieces;
0176     int32_t pieces_length;
0177     int32_t *pieces_lengths;
0178
0179     // current is used in iterating to combine pieces
0180     int32_t *current;
0181     int32_t current_length;
0182
0183     // transient fields
0184     UnicodeString buffer;
0185
0186     const Normalizer2 *nfd;
0187     const Normalizer2Impl *nfcImpl;
0188
0189     // we have a segment, in NFD. Find all the strings that are canonically equivalent to it.
0190     UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment)
0191
0192     //Set getEquivalents2(String segment);
0193     Hashtable *getEquivalents2(Hashtable *fillinResult, const char16_t *segment, int32_t segLen, UErrorCode &status);
0194     //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status);
0195
0196     /**
0197      * See if the decomposition of cp2 is at segment starting at segmentPos
0198      * (with canonical rearrangement!)
0199      * If so, take the remainder, and return the equivalents
0200      */
0201     //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
0202     Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const char16_t *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
0203     //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
0204
0205     void cleanPieces();
0206
0207 };
0208
0209 U_NAMESPACE_END
0210
0211 #endif /* #if !UCONFIG_NO_NORMALIZATION */
0212
0213 #endif /* U_SHOW_CPLUSPLUS_API */
0214
0215 #endif