1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/os/textandloc/fontservices/textshaperplugin/IcuSource/common/unicode/caniter.h Fri Jun 15 03:10:57 2012 +0200
1.3 @@ -0,0 +1,201 @@
1.4 +/*
1.5 + *******************************************************************************
1.6 + * Copyright (C) 1996-2005, 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 +
1.38 +/**
1.39 + * This class allows one to iterate through all the strings that are canonically equivalent to a given
1.40 + * string. For example, here are some sample results:
1.41 +Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.42 +1: \\u0041\\u030A\\u0064\\u0307\\u0327
1.43 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.44 +2: \\u0041\\u030A\\u0064\\u0327\\u0307
1.45 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
1.46 +3: \\u0041\\u030A\\u1E0B\\u0327
1.47 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
1.48 +4: \\u0041\\u030A\\u1E11\\u0307
1.49 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
1.50 +5: \\u00C5\\u0064\\u0307\\u0327
1.51 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.52 +6: \\u00C5\\u0064\\u0327\\u0307
1.53 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
1.54 +7: \\u00C5\\u1E0B\\u0327
1.55 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
1.56 +8: \\u00C5\\u1E11\\u0307
1.57 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
1.58 +9: \\u212B\\u0064\\u0307\\u0327
1.59 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1.60 +10: \\u212B\\u0064\\u0327\\u0307
1.61 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
1.62 +11: \\u212B\\u1E0B\\u0327
1.63 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
1.64 +12: \\u212B\\u1E11\\u0307
1.65 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
1.66 + *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones,
1.67 + * since it has not been optimized for that situation.
1.68 + * Note, CanonicalIterator is not intended to be subclassed.
1.69 + * @author M. Davis
1.70 + * @author C++ port by V. Weinstein
1.71 + * @stable ICU 2.4
1.72 + */
1.73 +class U_COMMON_API CanonicalIterator : public UObject {
1.74 +public:
1.75 + /**
1.76 + * Construct a CanonicalIterator object
1.77 + * @param source string to get results for
1.78 + * @param status Fill-in parameter which receives the status of this operation.
1.79 + * @stable ICU 2.4
1.80 + */
1.81 + CanonicalIterator(const UnicodeString &source, UErrorCode &status);
1.82 +
1.83 + /** Destructor
1.84 + * Cleans pieces
1.85 + * @stable ICU 2.4
1.86 + */
1.87 + virtual ~CanonicalIterator();
1.88 +
1.89 + /**
1.90 + * Gets the NFD form of the current source we are iterating over.
1.91 + * @return gets the source: NOTE: it is the NFD form of source
1.92 + * @stable ICU 2.4
1.93 + */
1.94 + UnicodeString getSource();
1.95 +
1.96 + /**
1.97 + * Resets the iterator so that one can start again from the beginning.
1.98 + * @stable ICU 2.4
1.99 + */
1.100 + void reset();
1.101 +
1.102 + /**
1.103 + * Get the next canonically equivalent string.
1.104 + * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b>
1.105 + * @return the next string that is canonically equivalent. A bogus string is returned when
1.106 + * the iteration is done.
1.107 + * @stable ICU 2.4
1.108 + */
1.109 + UnicodeString next();
1.110 +
1.111 + /**
1.112 + * Set a new source for this iterator. Allows object reuse.
1.113 + * @param newSource the source string to iterate against. This allows the same iterator to be used
1.114 + * while changing the source string, saving object creation.
1.115 + * @param status Fill-in parameter which receives the status of this operation.
1.116 + * @stable ICU 2.4
1.117 + */
1.118 + void setSource(const UnicodeString &newSource, UErrorCode &status);
1.119 +
1.120 + /**
1.121 + * Dumb recursive implementation of permutation.
1.122 + * TODO: optimize
1.123 + * @param source the string to find permutations for
1.124 + * @param skipZeros determine if skip zeros
1.125 + * @param result the results in a set.
1.126 + * @param status Fill-in parameter which receives the status of this operation.
1.127 + * @internal
1.128 + */
1.129 + static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status);
1.130 +
1.131 + /**
1.132 + * ICU "poor man's RTTI", returns a UClassID for this class.
1.133 + *
1.134 + * @stable ICU 2.2
1.135 + */
1.136 + static UClassID U_EXPORT2 getStaticClassID();
1.137 +
1.138 + /**
1.139 + * ICU "poor man's RTTI", returns a UClassID for the actual class.
1.140 + *
1.141 + * @stable ICU 2.2
1.142 + */
1.143 + virtual UClassID getDynamicClassID() const;
1.144 +
1.145 +private:
1.146 + // ===================== PRIVATES ==============================
1.147 + // private default constructor
1.148 + CanonicalIterator();
1.149 +
1.150 +
1.151 + /**
1.152 + * Copy constructor. Private for now.
1.153 + * @internal
1.154 + */
1.155 + CanonicalIterator(const CanonicalIterator& other);
1.156 +
1.157 + /**
1.158 + * Assignment operator. Private for now.
1.159 + * @internal
1.160 + */
1.161 + CanonicalIterator& operator=(const CanonicalIterator& other);
1.162 +
1.163 + // fields
1.164 + UnicodeString source;
1.165 + UBool done;
1.166 +
1.167 + // 2 dimensional array holds the pieces of the string with
1.168 + // their different canonically equivalent representations
1.169 + UnicodeString **pieces;
1.170 + int32_t pieces_length;
1.171 + int32_t *pieces_lengths;
1.172 +
1.173 + // current is used in iterating to combine pieces
1.174 + int32_t *current;
1.175 + int32_t current_length;
1.176 +
1.177 + // transient fields
1.178 + UnicodeString buffer;
1.179 +
1.180 + // we have a segment, in NFD. Find all the strings that are canonically equivalent to it.
1.181 + UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment)
1.182 +
1.183 + //Set getEquivalents2(String segment);
1.184 + Hashtable *getEquivalents2(const UChar *segment, int32_t segLen, UErrorCode &status);
1.185 + //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status);
1.186 +
1.187 + /**
1.188 + * See if the decomposition of cp2 is at segment starting at segmentPos
1.189 + * (with canonical rearrangment!)
1.190 + * If so, take the remainder, and return the equivalents
1.191 + */
1.192 + //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
1.193 + Hashtable *extract(UChar32 comp, const UChar *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
1.194 + //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
1.195 +
1.196 + void cleanPieces();
1.197 +
1.198 +};
1.199 +
1.200 +U_NAMESPACE_END
1.201 +
1.202 +#endif /* #if !UCONFIG_NO_NORMALIZATION */
1.203 +
1.204 +#endif