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/utypes.h"
20
21 #if U_SHOW_CPLUSPLUS_API
22
23 #include "unicode/uobject.h"
24
25 /**
26 * \file
27 * \brief C++ API: Replaceable String
28 */
29
30 U_NAMESPACE_BEGIN
31
32 class UnicodeString;
33
34 /**
35 * <code>Replaceable</code> is an abstract base class representing a
36 * string of characters that supports the replacement of a range of
37 * itself with a new string of characters. It is used by APIs that
38 * change a piece of text while retaining metadata. Metadata is data
39 * other than the Unicode characters returned by char32At(). One
40 * example of metadata is style attributes; another is an edit
41 * history, marking each character with an author and revision number.
42 *
43 * <p>An implicit aspect of the <code>Replaceable</code> API is that
44 * during a replace operation, new characters take on the metadata of
45 * the old characters. For example, if the string "the <b>bold</b>
46 * font" has range (4, 8) replaced with "strong", then it becomes "the
47 * <b>strong</b> font".
48 *
49 * <p><code>Replaceable</code> specifies ranges using a start
50 * offset and a limit offset. The range of characters thus specified
51 * includes the characters at offset start..limit-1. That is, the
52 * start offset is inclusive, and the limit offset is exclusive.
53 *
54 * <p><code>Replaceable</code> also includes API to access characters
55 * in the string: <code>length()</code>, <code>charAt()</code>,
56 * <code>char32At()</code>, and <code>extractBetween()</code>.
57 *
58 * <p>For a subclass to support metadata, typical behavior of
59 * <code>replace()</code> is the following:
60 * <ul>
61 * <li>Set the metadata of the new text to the metadata of the first
62 * character replaced</li>
63 * <li>If no characters are replaced, use the metadata of the
64 * previous character</li>
65 * <li>If there is no previous character (i.e. start == 0), use the
66 * following character</li>
67 * <li>If there is no following character (i.e. the replaceable was
68 * empty), use default metadata.<br>
69 * <li>If the code point U+FFFF is seen, it should be interpreted as
70 * a special marker having no metadata<li>
71 * </li>
72 * </ul>
73 * If this is not the behavior, the subclass should document any differences.
74 * @author Alan Liu
75 * @stable ICU 2.0
76 */
77 class U_COMMON_API Replaceable : public UObject {
78
79 public:
80 /**
81 * Destructor.
82 * @stable ICU 2.0
83 */
84 virtual ~Replaceable();
85
86 /**
87 * Returns the number of 16-bit code units in the text.
88 * @return number of 16-bit code units in text
89 * @stable ICU 1.8
90 */
91 inline int32_t length() const;
92
93 /**
94 * Returns the 16-bit code unit at the given offset into the text.
95 * @param offset an integer between 0 and <code>length()</code>-1
96 * inclusive
97 * @return 16-bit code unit of text at given offset
98 * @stable ICU 1.8
99 */
100 inline char16_t charAt(int32_t offset) const;
101
102 /**
103 * Returns the 32-bit code point at the given 16-bit offset into
104 * the text. This assumes the text is stored as 16-bit code units
105 * with surrogate pairs intermixed. If the offset of a leading or
106 * trailing code unit of a surrogate pair is given, return the
107 * code point of the surrogate pair.
108 *
109 * @param offset an integer between 0 and <code>length()</code>-1
110 * inclusive
111 * @return 32-bit code point of text at given offset
112 * @stable ICU 1.8
113 */
114 inline UChar32 char32At(int32_t offset) const;
115
116 /**
117 * Copies characters in the range [<tt>start</tt>, <tt>limit</tt>)
118 * into the UnicodeString <tt>target</tt>.
119 * @param start offset of first character which will be copied
120 * @param limit offset immediately following the last character to
121 * be copied
122 * @param target UnicodeString into which to copy characters.
123 * @return A reference to <TT>target</TT>
124 * @stable ICU 2.1
125 */
126 virtual void extractBetween(int32_t start,
127 int32_t limit,
128 UnicodeString& target) const = 0;
129
130 /**
131 * Replaces a substring of this object with the given text. If the
132 * characters being replaced have metadata, the new characters
133 * that replace them should be given the same metadata.
134 *
135 * <p>Subclasses must ensure that if the text between start and
136 * limit is equal to the replacement text, that replace has no
137 * effect. That is, any metadata
138 * should be unaffected. In addition, subclasses are encouraged to
139 * check for initial and trailing identical characters, and make a
140 * smaller replacement if possible. This will preserve as much
141 * metadata as possible.
142 * @param start the beginning index, inclusive; <code>0 <= start
143 * <= limit</code>.
144 * @param limit the ending index, exclusive; <code>start <= limit
145 * <= length()</code>.
146 * @param text the text to replace characters <code>start</code>
147 * to <code>limit - 1</code>
148 * @stable ICU 2.0
149 */
150 virtual void handleReplaceBetween(int32_t start,
151 int32_t limit,
152 const UnicodeString& text) = 0;
153 // Note: All other methods in this class take the names of
154 // existing UnicodeString methods. This method is the exception.
155 // It is named differently because all replace methods of
156 // UnicodeString return a UnicodeString&. The 'between' is
157 // required in order to conform to the UnicodeString naming
158 // convention; API taking start/length are named <operation>, and
159 // those taking start/limit are named <operationBetween>. The
160 // 'handle' is added because 'replaceBetween' and
161 // 'doReplaceBetween' are already taken.
162
163 /**
164 * Copies a substring of this object, retaining metadata.
165 * This method is used to duplicate or reorder substrings.
166 * The destination index must not overlap the source range.
167 *
168 * @param start the beginning index, inclusive; <code>0 <= start <=
169 * limit</code>.
170 * @param limit the ending index, exclusive; <code>start <= limit <=
171 * length()</code>.
172 * @param dest the destination index. The characters from
173 * <code>start..limit-1</code> will be copied to <code>dest</code>.
174 * Implementations of this method may assume that <code>dest <= start ||
175 * dest >= limit</code>.
176 * @stable ICU 2.0
177 */
178 virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0;
179
180 /**
181 * Returns true if this object contains metadata. If a
182 * Replaceable object has metadata, calls to the Replaceable API
183 * must be made so as to preserve metadata. If it does not, calls
184 * to the Replaceable API may be optimized to improve performance.
185 * The default implementation returns true.
186 * @return true if this object contains metadata
187 * @stable ICU 2.2
188 */
189 virtual UBool hasMetaData() const;
190
191 /**
192 * Clone this object, an instance of a subclass of Replaceable.
193 * Clones can be used concurrently in multiple threads.
194 * If a subclass does not implement clone(), or if an error occurs,
195 * then nullptr is returned.
196 * The caller must delete the clone.
197 *
198 * @return a clone of this object
199 *
200 * @see getDynamicClassID
201 * @stable ICU 2.6
202 */
203 virtual Replaceable *clone() const;
204
205 protected:
206
207 /**
208 * Default constructor.
209 * @stable ICU 2.4
210 */
211 inline Replaceable();
212
213 /*
214 * Assignment operator not declared. The compiler will provide one
215 * which does nothing since this class does not contain any data members.
216 * API/code coverage may show the assignment operator as present and
217 * untested - ignore.
218 * Subclasses need this assignment operator if they use compiler-provided
219 * assignment operators of their own. An alternative to not declaring one
220 * here would be to declare and empty-implement a protected or public one.
221 Replaceable &Replaceable::operator=(const Replaceable &);
222 */
223
224 /**
225 * Virtual version of length().
226 * @stable ICU 2.4
227 */
228 virtual int32_t getLength() const = 0;
229
230 /**
231 * Virtual version of charAt().
232 * @stable ICU 2.4
233 */
234 virtual char16_t getCharAt(int32_t offset) const = 0;
235
236 /**
237 * Virtual version of char32At().
238 * @stable ICU 2.4
239 */
240 virtual UChar32 getChar32At(int32_t offset) const = 0;
241 };
242
Replaceable()243 inline Replaceable::Replaceable() {}
244
245 inline int32_t
length()246 Replaceable::length() const {
247 return getLength();
248 }
249
250 inline char16_t
charAt(int32_t offset)251 Replaceable::charAt(int32_t offset) const {
252 return getCharAt(offset);
253 }
254
255 inline UChar32
char32At(int32_t offset)256 Replaceable::char32At(int32_t offset) const {
257 return getChar32At(offset);
258 }
259
260 // There is no rep.cpp, see unistr.cpp for Replaceable function implementations.
261
262 U_NAMESPACE_END
263
264 #endif /* U_SHOW_CPLUSPLUS_API */
265
266 #endif
267