DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (d38398e5144e)

VCS Links

CanonicalIterator

Macros

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 *******************************************************************************
 * Copyright (C) 1996-2014, International Business Machines Corporation and
 * others. All Rights Reserved.
 *******************************************************************************
 */

#ifndef CANITER_H
#define CANITER_H

#include "unicode/utypes.h"

#if !UCONFIG_NO_NORMALIZATION

#include "unicode/uobject.h"
#include "unicode/unistr.h"

/**
 * \file
 * \brief C++ API: Canonical Iterator
 */
 
/** Should permutation skip characters with combining class zero
 *  Should be either TRUE or FALSE. This is a compile time option
 *  @stable ICU 2.4
 */
#ifndef CANITER_SKIP_ZEROES
#define CANITER_SKIP_ZEROES TRUE
#endif

U_NAMESPACE_BEGIN

class Hashtable;
class Normalizer2;
class Normalizer2Impl;

/**
 * This class allows one to iterate through all the strings that are canonically equivalent to a given
 * string. For example, here are some sample results:
Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1: \\u0041\\u030A\\u0064\\u0307\\u0327
 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
2: \\u0041\\u030A\\u0064\\u0327\\u0307
 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
3: \\u0041\\u030A\\u1E0B\\u0327
 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
4: \\u0041\\u030A\\u1E11\\u0307
 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
5: \\u00C5\\u0064\\u0307\\u0327
 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
6: \\u00C5\\u0064\\u0327\\u0307
 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
7: \\u00C5\\u1E0B\\u0327
 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
8: \\u00C5\\u1E11\\u0307
 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
9: \\u212B\\u0064\\u0307\\u0327
 = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
10: \\u212B\\u0064\\u0327\\u0307
 = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
11: \\u212B\\u1E0B\\u0327
 = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
12: \\u212B\\u1E11\\u0307
 = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
 *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones,
 * since it has not been optimized for that situation.
 * Note, CanonicalIterator is not intended to be subclassed.
 * @author M. Davis
 * @author C++ port by V. Weinstein
 * @stable ICU 2.4
 */
class U_COMMON_API CanonicalIterator U_FINAL : public UObject {
public:
    /**
     * Construct a CanonicalIterator object
     * @param source    string to get results for
     * @param status    Fill-in parameter which receives the status of this operation.
     * @stable ICU 2.4
     */
    CanonicalIterator(const UnicodeString &source, UErrorCode &status);

    /** Destructor
     *  Cleans pieces
     * @stable ICU 2.4
     */
    virtual ~CanonicalIterator();

    /**
     * Gets the NFD form of the current source we are iterating over.
     * @return gets the source: NOTE: it is the NFD form of source
     * @stable ICU 2.4
     */
    UnicodeString getSource();

    /**
     * Resets the iterator so that one can start again from the beginning.
     * @stable ICU 2.4
     */
    void reset();

    /**
     * Get the next canonically equivalent string.
     * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b>
     * @return the next string that is canonically equivalent. A bogus string is returned when
     * the iteration is done.
     * @stable ICU 2.4
     */
    UnicodeString next();

    /**
     * Set a new source for this iterator. Allows object reuse.
     * @param newSource     the source string to iterate against. This allows the same iterator to be used
     *                     while changing the source string, saving object creation.
     * @param status        Fill-in parameter which receives the status of this operation.
     * @stable ICU 2.4
     */
    void setSource(const UnicodeString &newSource, UErrorCode &status);

#ifndef U_HIDE_INTERNAL_API
    /**
     * Dumb recursive implementation of permutation.
     * TODO: optimize
     * @param source     the string to find permutations for
     * @param skipZeros  determine if skip zeros
     * @param result     the results in a set.
     * @param status       Fill-in parameter which receives the status of this operation.
     * @internal
     */
    static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status);
#endif  /* U_HIDE_INTERNAL_API */

    /**
     * ICU "poor man's RTTI", returns a UClassID for this class.
     *
     * @stable ICU 2.2
     */
    static UClassID U_EXPORT2 getStaticClassID();

    /**
     * ICU "poor man's RTTI", returns a UClassID for the actual class.
     *
     * @stable ICU 2.2
     */
    virtual UClassID getDynamicClassID() const;

private:
    // ===================== PRIVATES ==============================
    // private default constructor
    CanonicalIterator();


    /**
     * Copy constructor. Private for now.
     * @internal
     */
    CanonicalIterator(const CanonicalIterator& other);

    /**
     * Assignment operator. Private for now.
     * @internal
     */
    CanonicalIterator& operator=(const CanonicalIterator& other);

    // fields
    UnicodeString source;
    UBool done;

    // 2 dimensional array holds the pieces of the string with
    // their different canonically equivalent representations
    UnicodeString **pieces;
    int32_t pieces_length;
    int32_t *pieces_lengths;

    // current is used in iterating to combine pieces
    int32_t *current;
    int32_t current_length;

    // transient fields
    UnicodeString buffer;

    const Normalizer2 &nfd;
    const Normalizer2Impl &nfcImpl;

    // we have a segment, in NFD. Find all the strings that are canonically equivalent to it.
    UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment)

    //Set getEquivalents2(String segment);
    Hashtable *getEquivalents2(Hashtable *fillinResult, const UChar *segment, int32_t segLen, UErrorCode &status);
    //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status);

    /**
     * See if the decomposition of cp2 is at segment starting at segmentPos
     * (with canonical rearrangment!)
     * If so, take the remainder, and return the equivalents
     */
    //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
    Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const UChar *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
    //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);

    void cleanPieces();

};

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_NORMALIZATION */

#endif