1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/common/unicode/caniter.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,208 @@
1.4 +/*
1.5 + *******************************************************************************
1.6 + * Copyright (C) 1996-2011, International Business Machines Corporation and
1.7 + * others. All Rights Reserved.
1.8 + *******************************************************************************
1.9 + */
1.10 +
1.11 +#ifndef CANITER_H
1.12 +#define CANITER_H
1.13 +
1.14 +#include "unicode/utypes.h"
1.15 +
1.16 +#if !UCONFIG_NO_NORMALIZATION
1.17 +
1.18 +#include "unicode/uobject.h"
1.19 +#include "unicode/unistr.h"
1.20 +
1.21 +/**
1.22 + * \file
1.23 + * \brief C++ API: Canonical Iterator
1.24 + */
1.25 +
1.26 +/** Should permutation skip characters with combining class zero
1.27 + * Should be either TRUE or FALSE. This is a compile time option
1.28 + * @stable ICU 2.4
1.29 + */
1.30 +#ifndef CANITER_SKIP_ZEROES
1.31 +#define CANITER_SKIP_ZEROES TRUE
1.32 +#endif
1.33 +
1.34 +U_NAMESPACE_BEGIN
1.35 +
1.36 +class Hashtable;
1.37 +class Normalizer2;
1.38 +class Normalizer2Impl;
1.39 +
1.40 +/**
1.41 + * This class allows one to iterate through all the strings that are canonically equivalent to a given
1.42 + * string. For example, here are some sample results:
1.43 +Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.44 +1: \\u0041\\u030A\\u0064\\u0307\\u0327
1.45 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.46 +2: \\u0041\\u030A\\u0064\\u0327\\u0307
1.47 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
1.48 +3: \\u0041\\u030A\\u1E0B\\u0327
1.49 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
1.50 +4: \\u0041\\u030A\\u1E11\\u0307
1.51 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
1.52 +5: \\u00C5\\u0064\\u0307\\u0327
1.53 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.54 +6: \\u00C5\\u0064\\u0327\\u0307
1.55 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
1.56 +7: \\u00C5\\u1E0B\\u0327
1.57 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
1.58 +8: \\u00C5\\u1E11\\u0307
1.59 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
1.60 +9: \\u212B\\u0064\\u0307\\u0327
1.61 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.62 +10: \\u212B\\u0064\\u0327\\u0307
1.63 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
1.64 +11: \\u212B\\u1E0B\\u0327
1.65 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
1.66 +12: \\u212B\\u1E11\\u0307
1.67 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
1.68 + *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones,
1.69 + * since it has not been optimized for that situation.
1.70 + * Note, CanonicalIterator is not intended to be subclassed.
1.71 + * @author M. Davis
1.72 + * @author C++ port by V. Weinstein
1.73 + * @stable ICU 2.4
1.74 + */
1.75 +class U_COMMON_API CanonicalIterator : public UObject {
1.76 +public:
1.77 + /**
1.78 + * Construct a CanonicalIterator object
1.79 + * @param source string to get results for
1.80 + * @param status Fill-in parameter which receives the status of this operation.
1.81 + * @stable ICU 2.4
1.82 + */
1.83 + CanonicalIterator(const UnicodeString &source, UErrorCode &status);
1.84 +
1.85 + /** Destructor
1.86 + * Cleans pieces
1.87 + * @stable ICU 2.4
1.88 + */
1.89 + virtual ~CanonicalIterator();
1.90 +
1.91 + /**
1.92 + * Gets the NFD form of the current source we are iterating over.
1.93 + * @return gets the source: NOTE: it is the NFD form of source
1.94 + * @stable ICU 2.4
1.95 + */
1.96 + UnicodeString getSource();
1.97 +
1.98 + /**
1.99 + * Resets the iterator so that one can start again from the beginning.
1.100 + * @stable ICU 2.4
1.101 + */
1.102 + void reset();
1.103 +
1.104 + /**
1.105 + * Get the next canonically equivalent string.
1.106 + * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b>
1.107 + * @return the next string that is canonically equivalent. A bogus string is returned when
1.108 + * the iteration is done.
1.109 + * @stable ICU 2.4
1.110 + */
1.111 + UnicodeString next();
1.112 +
1.113 + /**
1.114 + * Set a new source for this iterator. Allows object reuse.
1.115 + * @param newSource the source string to iterate against. This allows the same iterator to be used
1.116 + * while changing the source string, saving object creation.
1.117 + * @param status Fill-in parameter which receives the status of this operation.
1.118 + * @stable ICU 2.4
1.119 + */
1.120 + void setSource(const UnicodeString &newSource, UErrorCode &status);
1.121 +
1.122 +#ifndef U_HIDE_INTERNAL_API
1.123 + /**
1.124 + * Dumb recursive implementation of permutation.
1.125 + * TODO: optimize
1.126 + * @param source the string to find permutations for
1.127 + * @param skipZeros determine if skip zeros
1.128 + * @param result the results in a set.
1.129 + * @param status Fill-in parameter which receives the status of this operation.
1.130 + * @internal
1.131 + */
1.132 + static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status);
1.133 +#endif /* U_HIDE_INTERNAL_API */
1.134 +
1.135 + /**
1.136 + * ICU "poor man's RTTI", returns a UClassID for this class.
1.137 + *
1.138 + * @stable ICU 2.2
1.139 + */
1.140 + static UClassID U_EXPORT2 getStaticClassID();
1.141 +
1.142 + /**
1.143 + * ICU "poor man's RTTI", returns a UClassID for the actual class.
1.144 + *
1.145 + * @stable ICU 2.2
1.146 + */
1.147 + virtual UClassID getDynamicClassID() const;
1.148 +
1.149 +private:
1.150 + // ===================== PRIVATES ==============================
1.151 + // private default constructor
1.152 + CanonicalIterator();
1.153 +
1.154 +
1.155 + /**
1.156 + * Copy constructor. Private for now.
1.157 + * @internal
1.158 + */
1.159 + CanonicalIterator(const CanonicalIterator& other);
1.160 +
1.161 + /**
1.162 + * Assignment operator. Private for now.
1.163 + * @internal
1.164 + */
1.165 + CanonicalIterator& operator=(const CanonicalIterator& other);
1.166 +
1.167 + // fields
1.168 + UnicodeString source;
1.169 + UBool done;
1.170 +
1.171 + // 2 dimensional array holds the pieces of the string with
1.172 + // their different canonically equivalent representations
1.173 + UnicodeString **pieces;
1.174 + int32_t pieces_length;
1.175 + int32_t *pieces_lengths;
1.176 +
1.177 + // current is used in iterating to combine pieces
1.178 + int32_t *current;
1.179 + int32_t current_length;
1.180 +
1.181 + // transient fields
1.182 + UnicodeString buffer;
1.183 +
1.184 + const Normalizer2 &nfd;
1.185 + const Normalizer2Impl &nfcImpl;
1.186 +
1.187 + // we have a segment, in NFD. Find all the strings that are canonically equivalent to it.
1.188 + UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment)
1.189 +
1.190 + //Set getEquivalents2(String segment);
1.191 + Hashtable *getEquivalents2(Hashtable *fillinResult, const UChar *segment, int32_t segLen, UErrorCode &status);
1.192 + //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status);
1.193 +
1.194 + /**
1.195 + * See if the decomposition of cp2 is at segment starting at segmentPos
1.196 + * (with canonical rearrangment!)
1.197 + * If so, take the remainder, and return the equivalents
1.198 + */
1.199 + //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
1.200 + Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const UChar *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
1.201 + //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
1.202 +
1.203 + void cleanPieces();
1.204 +
1.205 +};
1.206 +
1.207 +U_NAMESPACE_END
1.208 +
1.209 +#endif /* #if !UCONFIG_NO_NORMALIZATION */
1.210 +
1.211 +#endif
