Line data Source code
1 : // © 2016 and later: Unicode, Inc. and others.
2 : // License & terms of use: http://www.unicode.org/copyright.html
3 : /*
4 : **************************************************************************
5 : * Copyright (C) 1999-2012, International Business Machines Corporation and
6 : * others. All Rights Reserved.
7 : **************************************************************************
8 : * Date Name Description
9 : * 11/17/99 aliu Creation. Ported from java. Modified to
10 : * match current UnicodeString API. Forced
11 : * to use name "handleReplaceBetween" because
12 : * of existing methods in UnicodeString.
13 : **************************************************************************
14 : */
15 :
16 : #ifndef REP_H
17 : #define REP_H
18 :
19 : #include "unicode/uobject.h"
20 :
21 : /**
22 : * \file
23 : * \brief C++ API: Replaceable String
24 : */
25 :
26 : U_NAMESPACE_BEGIN
27 :
28 : class UnicodeString;
29 :
30 : /**
31 : * <code>Replaceable</code> is an abstract base class representing a
32 : * string of characters that supports the replacement of a range of
33 : * itself with a new string of characters. It is used by APIs that
34 : * change a piece of text while retaining metadata. Metadata is data
35 : * other than the Unicode characters returned by char32At(). One
36 : * example of metadata is style attributes; another is an edit
37 : * history, marking each character with an author and revision number.
38 : *
39 : * <p>An implicit aspect of the <code>Replaceable</code> API is that
40 : * during a replace operation, new characters take on the metadata of
41 : * the old characters. For example, if the string "the <b>bold</b>
42 : * font" has range (4, 8) replaced with "strong", then it becomes "the
43 : * <b>strong</b> font".
44 : *
45 : * <p><code>Replaceable</code> specifies ranges using a start
46 : * offset and a limit offset. The range of characters thus specified
47 : * includes the characters at offset start..limit-1. That is, the
48 : * start offset is inclusive, and the limit offset is exclusive.
49 : *
50 : * <p><code>Replaceable</code> also includes API to access characters
51 : * in the string: <code>length()</code>, <code>charAt()</code>,
52 : * <code>char32At()</code>, and <code>extractBetween()</code>.
53 : *
54 : * <p>For a subclass to support metadata, typical behavior of
55 : * <code>replace()</code> is the following:
56 : * <ul>
57 : * <li>Set the metadata of the new text to the metadata of the first
58 : * character replaced</li>
59 : * <li>If no characters are replaced, use the metadata of the
60 : * previous character</li>
61 : * <li>If there is no previous character (i.e. start == 0), use the
62 : * following character</li>
63 : * <li>If there is no following character (i.e. the replaceable was
64 : * empty), use default metadata.<br>
65 : * <li>If the code point U+FFFF is seen, it should be interpreted as
66 : * a special marker having no metadata<li>
67 : * </li>
68 : * </ul>
69 : * If this is not the behavior, the subclass should document any differences.
70 : * @author Alan Liu
71 : * @stable ICU 2.0
72 : */
73 : class U_COMMON_API Replaceable : public UObject {
74 :
75 : public:
76 : /**
77 : * Destructor.
78 : * @stable ICU 2.0
79 : */
80 : virtual ~Replaceable();
81 :
82 : /**
83 : * Returns the number of 16-bit code units in the text.
84 : * @return number of 16-bit code units in text
85 : * @stable ICU 1.8
86 : */
87 : inline int32_t length() const;
88 :
89 : /**
90 : * Returns the 16-bit code unit at the given offset into the text.
91 : * @param offset an integer between 0 and <code>length()</code>-1
92 : * inclusive
93 : * @return 16-bit code unit of text at given offset
94 : * @stable ICU 1.8
95 : */
96 : inline char16_t charAt(int32_t offset) const;
97 :
98 : /**
99 : * Returns the 32-bit code point at the given 16-bit offset into
100 : * the text. This assumes the text is stored as 16-bit code units
101 : * with surrogate pairs intermixed. If the offset of a leading or
102 : * trailing code unit of a surrogate pair is given, return the
103 : * code point of the surrogate pair.
104 : *
105 : * @param offset an integer between 0 and <code>length()</code>-1
106 : * inclusive
107 : * @return 32-bit code point of text at given offset
108 : * @stable ICU 1.8
109 : */
110 : inline UChar32 char32At(int32_t offset) const;
111 :
112 : /**
113 : * Copies characters in the range [<tt>start</tt>, <tt>limit</tt>)
114 : * into the UnicodeString <tt>target</tt>.
115 : * @param start offset of first character which will be copied
116 : * @param limit offset immediately following the last character to
117 : * be copied
118 : * @param target UnicodeString into which to copy characters.
119 : * @return A reference to <TT>target</TT>
120 : * @stable ICU 2.1
121 : */
122 : virtual void extractBetween(int32_t start,
123 : int32_t limit,
124 : UnicodeString& target) const = 0;
125 :
126 : /**
127 : * Replaces a substring of this object with the given text. If the
128 : * characters being replaced have metadata, the new characters
129 : * that replace them should be given the same metadata.
130 : *
131 : * <p>Subclasses must ensure that if the text between start and
132 : * limit is equal to the replacement text, that replace has no
133 : * effect. That is, any metadata
134 : * should be unaffected. In addition, subclasses are encouraged to
135 : * check for initial and trailing identical characters, and make a
136 : * smaller replacement if possible. This will preserve as much
137 : * metadata as possible.
138 : * @param start the beginning index, inclusive; <code>0 <= start
139 : * <= limit</code>.
140 : * @param limit the ending index, exclusive; <code>start <= limit
141 : * <= length()</code>.
142 : * @param text the text to replace characters <code>start</code>
143 : * to <code>limit - 1</code>
144 : * @stable ICU 2.0
145 : */
146 : virtual void handleReplaceBetween(int32_t start,
147 : int32_t limit,
148 : const UnicodeString& text) = 0;
149 : // Note: All other methods in this class take the names of
150 : // existing UnicodeString methods. This method is the exception.
151 : // It is named differently because all replace methods of
152 : // UnicodeString return a UnicodeString&. The 'between' is
153 : // required in order to conform to the UnicodeString naming
154 : // convention; API taking start/length are named <operation>, and
155 : // those taking start/limit are named <operationBetween>. The
156 : // 'handle' is added because 'replaceBetween' and
157 : // 'doReplaceBetween' are already taken.
158 :
159 : /**
160 : * Copies a substring of this object, retaining metadata.
161 : * This method is used to duplicate or reorder substrings.
162 : * The destination index must not overlap the source range.
163 : *
164 : * @param start the beginning index, inclusive; <code>0 <= start <=
165 : * limit</code>.
166 : * @param limit the ending index, exclusive; <code>start <= limit <=
167 : * length()</code>.
168 : * @param dest the destination index. The characters from
169 : * <code>start..limit-1</code> will be copied to <code>dest</code>.
170 : * Implementations of this method may assume that <code>dest <= start ||
171 : * dest >= limit</code>.
172 : * @stable ICU 2.0
173 : */
174 : virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0;
175 :
176 : /**
177 : * Returns true if this object contains metadata. If a
178 : * Replaceable object has metadata, calls to the Replaceable API
179 : * must be made so as to preserve metadata. If it does not, calls
180 : * to the Replaceable API may be optimized to improve performance.
181 : * The default implementation returns true.
182 : * @return true if this object contains metadata
183 : * @stable ICU 2.2
184 : */
185 : virtual UBool hasMetaData() const;
186 :
187 : /**
188 : * Clone this object, an instance of a subclass of Replaceable.
189 : * Clones can be used concurrently in multiple threads.
190 : * If a subclass does not implement clone(), or if an error occurs,
191 : * then NULL is returned.
192 : * The clone functions in all subclasses return a pointer to a Replaceable
193 : * because some compilers do not support covariant (same-as-this)
194 : * return types; cast to the appropriate subclass if necessary.
195 : * The caller must delete the clone.
196 : *
197 : * @return a clone of this object
198 : *
199 : * @see getDynamicClassID
200 : * @stable ICU 2.6
201 : */
202 : virtual Replaceable *clone() const;
203 :
204 : protected:
205 :
206 : /**
207 : * Default constructor.
208 : * @stable ICU 2.4
209 : */
210 : inline Replaceable();
211 :
212 : /*
213 : * Assignment operator not declared. The compiler will provide one
214 : * which does nothing since this class does not contain any data members.
215 : * API/code coverage may show the assignment operator as present and
216 : * untested - ignore.
217 : * Subclasses need this assignment operator if they use compiler-provided
218 : * assignment operators of their own. An alternative to not declaring one
219 : * here would be to declare and empty-implement a protected or public one.
220 : Replaceable &Replaceable::operator=(const Replaceable &);
221 : */
222 :
223 : /**
224 : * Virtual version of length().
225 : * @stable ICU 2.4
226 : */
227 : virtual int32_t getLength() const = 0;
228 :
229 : /**
230 : * Virtual version of charAt().
231 : * @stable ICU 2.4
232 : */
233 : virtual char16_t getCharAt(int32_t offset) const = 0;
234 :
235 : /**
236 : * Virtual version of char32At().
237 : * @stable ICU 2.4
238 : */
239 : virtual UChar32 getChar32At(int32_t offset) const = 0;
240 : };
241 :
242 0 : inline Replaceable::Replaceable() {}
243 :
244 : inline int32_t
245 0 : Replaceable::length() const {
246 0 : return getLength();
247 : }
248 :
249 : inline char16_t
250 0 : Replaceable::charAt(int32_t offset) const {
251 0 : return getCharAt(offset);
252 : }
253 :
254 : inline UChar32
255 0 : Replaceable::char32At(int32_t offset) const {
256 0 : return getChar32At(offset);
257 : }
258 :
259 : // There is no rep.cpp, see unistr.cpp for Replaceable function implementations.
260 :
261 : U_NAMESPACE_END
262 :
263 : #endif
|
