icuSources/common/unicode/rep.h

   1 /*
   2 **************************************************************************
   3 * Copyright (C) 1999-2004, International Business Machines Corporation and
   4 * others. All Rights Reserved.
   5 **************************************************************************
   6 *   Date        Name        Description
   7 *   11/17/99    aliu        Creation.  Ported from java.  Modified to
   8 *                           match current UnicodeString API.  Forced
   9 *                           to use name "handleReplaceBetween" because
  10 *                           of existing methods in UnicodeString.
  11 **************************************************************************
  12 */
  13
  14 #ifndef REP_H
  15 #define REP_H
  16
  17 #include "unicode/uobject.h"
  18
  19 U_NAMESPACE_BEGIN
  20
  21 class UnicodeString;
  22
  23 /**
  24  * <code>Replaceable</code> is an abstract base class representing a
  25  * string of characters that supports the replacement of a range of
  26  * itself with a new string of characters.  It is used by APIs that
  27  * change a piece of text while retaining metadata.  Metadata is data
  28  * other than the Unicode characters returned by char32At().  One
  29  * example of metadata is style attributes; another is an edit
  30  * history, marking each character with an author and revision number.
  31  *
  32  * <p>An implicit aspect of the <code>Replaceable</code> API is that
  33  * during a replace operation, new characters take on the metadata of
  34  * the old characters.  For example, if the string "the <b>bold</b>
  35  * font" has range (4, 8) replaced with "strong", then it becomes "the
  36  * <b>strong</b> font".
  37  *
  38  * <p><code>Replaceable</code> specifies ranges using a start
  39  * offset and a limit offset.  The range of characters thus specified
  40  * includes the characters at offset start..limit-1.  That is, the
  41  * start offset is inclusive, and the limit offset is exclusive.
  42  *
  43  * <p><code>Replaceable</code> also includes API to access characters
  44  * in the string: <code>length()</code>, <code>charAt()</code>,
  45  * <code>char32At()</code>, and <code>extractBetween()</code>.
  46  *
  47  * <p>For a subclass to support metadata, typical behavior of
  48  * <code>replace()</code> is the following:
  49  * <ul>
  50  *   <li>Set the metadata of the new text to the metadata of the first
  51  *   character replaced</li>
  52  *   <li>If no characters are replaced, use the metadata of the
  53  *   previous character</li>
  54  *   <li>If there is no previous character (i.e. start == 0), use the
  55  *   following character</li>
  56  *   <li>If there is no following character (i.e. the replaceable was
  57  *   empty), use default metadata.<br>
  58  *   <li>If the code point U+FFFF is seen, it should be interpreted as
  59  *   a special marker having no metadata<li>
  60  *   </li>
  61  * </ul>
  62  * If this is not the behavior, the subclass should document any differences.
  63  * @author Alan Liu
  64  * @stable ICU 2.0
  65  */
  66 class U_COMMON_API Replaceable : public UObject {
  67
  68 public:
  69     /**
  70      * Destructor.
  71      * @stable ICU 2.0
  72      */
  73     virtual ~Replaceable();
  74
  75     /**
  76      * Returns the number of 16-bit code units in the text.
  77      * @return number of 16-bit code units in text
  78      * @stable ICU 1.8
  79      */
  80     inline int32_t length() const;
  81
  82     /**
  83      * Returns the 16-bit code unit at the given offset into the text.
  84      * @param offset an integer between 0 and <code>length()</code>-1
  85      * inclusive
  86      * @return 16-bit code unit of text at given offset
  87      * @stable ICU 1.8
  88      */
  89     inline UChar charAt(int32_t offset) const;
  90
  91     /**
  92      * Returns the 32-bit code point at the given 16-bit offset into
  93      * the text.  This assumes the text is stored as 16-bit code units
  94      * with surrogate pairs intermixed.  If the offset of a leading or
  95      * trailing code unit of a surrogate pair is given, return the
  96      * code point of the surrogate pair.
  97      *
  98      * @param offset an integer between 0 and <code>length()</code>-1
  99      * inclusive
 100      * @return 32-bit code point of text at given offset
 101      * @stable ICU 1.8
 102      */
 103     inline UChar32 char32At(int32_t offset) const;
 104
 105     /**
 106      * Copies characters in the range [<tt>start</tt>, <tt>limit</tt>)
 107      * into the UnicodeString <tt>target</tt>.
 108      * @param start offset of first character which will be copied
 109      * @param limit offset immediately following the last character to
 110      * be copied
 111      * @param target UnicodeString into which to copy characters.
 112      * @return A reference to <TT>target</TT>
 113      * @stable ICU 2.1
 114      */
 115     virtual void extractBetween(int32_t start,
 116                                 int32_t limit,
 117                                 UnicodeString& target) const = 0;
 118
 119     /**
 120      * Replaces a substring of this object with the given text.  If the
 121      * characters being replaced have metadata, the new characters
 122      * that replace them should be given the same metadata.
 123      *
 124      * <p>Subclasses must ensure that if the text between start and
 125      * limit is equal to the replacement text, that replace has no
 126      * effect. That is, any metadata
 127      * should be unaffected. In addition, subclasses are encouraged to
 128      * check for initial and trailing identical characters, and make a
 129      * smaller replacement if possible. This will preserve as much
 130      * metadata as possible.
 131      * @param start the beginning index, inclusive; <code>0 <= start
 132      * <= limit</code>.
 133      * @param limit the ending index, exclusive; <code>start <= limit
 134      * <= length()</code>.
 135      * @param text the text to replace characters <code>start</code>
 136      * to <code>limit - 1</code>
 137      * @stable ICU 2.0
 138      */
 139     virtual void handleReplaceBetween(int32_t start,
 140                                       int32_t limit,
 141                                       const UnicodeString& text) = 0;
 142     // Note: All other methods in this class take the names of
 143     // existing UnicodeString methods.  This method is the exception.
 144     // It is named differently because all replace methods of
 145     // UnicodeString return a UnicodeString&.  The 'between' is
 146     // required in order to conform to the UnicodeString naming
 147     // convention; API taking start/length are named <operation>, and
 148     // those taking start/limit are named <operationBetween>.  The
 149     // 'handle' is added because 'replaceBetween' and
 150     // 'doReplaceBetween' are already taken.
 151
 152     /**
 153      * Copies a substring of this object, retaining metadata.
 154      * This method is used to duplicate or reorder substrings.
 155      * The destination index must not overlap the source range.
 156      *
 157      * @param start the beginning index, inclusive; <code>0 <= start <=
 158      * limit</code>.
 159      * @param limit the ending index, exclusive; <code>start <= limit <=
 160      * length()</code>.
 161      * @param dest the destination index.  The characters from
 162      * <code>start..limit-1</code> will be copied to <code>dest</code>.
 163      * Implementations of this method may assume that <code>dest <= start ||
 164      * dest >= limit</code>.
 165      * @stable ICU 2.0
 166      */
 167     virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0;
 168
 169     /**
 170      * Returns true if this object contains metadata.  If a
 171      * Replaceable object has metadata, calls to the Replaceable API
 172      * must be made so as to preserve metadata.  If it does not, calls
 173      * to the Replaceable API may be optimized to improve performance.
 174      * The default implementation returns true.
 175      * @return true if this object contains metadata
 176      * @stable ICU 2.2
 177      */
 178     virtual UBool hasMetaData() const;
 179
 180     /**
 181      * Clone this object, an instance of a subclass of Replaceable.
 182      * Clones can be used concurrently in multiple threads.
 183      * If a subclass does not implement clone(), or if an error occurs,
 184      * then NULL is returned.
 185      * The clone functions in all subclasses return a pointer to a Replaceable
 186      * because some compilers do not support covariant (same-as-this)
 187      * return types; cast to the appropriate subclass if necessary.
 188      * The caller must delete the clone.
 189      *
 190      * @return a clone of this object
 191      *
 192      * @see getDynamicClassID
 193      * @stable ICU 2.6
 194      */
 195     virtual Replaceable *clone() const;
 196
 197 protected:
 198
 199     /**
 200      * Default constructor.
 201      * @stable ICU 2.4
 202      */
 203     Replaceable();
 204
 205     /*
 206      * Assignment operator not declared. The compiler will provide one
 207      * which does nothing since this class does not contain any data members.
 208      * API/code coverage may show the assignment operator as present and
 209      * untested - ignore.
 210      * Subclasses need this assignment operator if they use compiler-provided
 211      * assignment operators of their own. An alternative to not declaring one
 212      * here would be to declare and empty-implement a protected or public one.
 213     Replaceable &Replaceable::operator=(const Replaceable &);
 214      */
 215
 216     /**
 217      * Virtual version of length().
 218      * @stable ICU 2.4
 219      */
 220     virtual int32_t getLength() const = 0;
 221
 222     /**
 223      * Virtual version of charAt().
 224      * @stable ICU 2.4
 225      */
 226     virtual UChar getCharAt(int32_t offset) const = 0;
 227
 228     /**
 229      * Virtual version of char32At().
 230      * @stable ICU 2.4
 231      */
 232     virtual UChar32 getChar32At(int32_t offset) const = 0;
 233 };
 234
 235 inline int32_t
 236 Replaceable::length() const {
 237     return getLength();
 238 }
 239
 240 inline UChar
 241 Replaceable::charAt(int32_t offset) const {
 242     return getCharAt(offset);
 243 }
 244
 245 inline UChar32
 246 Replaceable::char32At(int32_t offset) const {
 247     return getChar32At(offset);
 248 }
 249
 250 // There is no rep.cpp, see unistr.cpp for Replaceable function implementations.
 251
 252 U_NAMESPACE_END
 253
 254 #endif