/*
**************************************************************************
* Copyright (C) 1999-2001, International Business Machines Corporation and
* others. All Rights Reserved.
**************************************************************************
* Date Name Description
* 11/17/99 aliu Creation. Ported from java. Modified to
* match current UnicodeString API. Forced
* to use name "handleReplaceBetween" because
* of existing methods in UnicodeString.
**************************************************************************
*/
#ifndef REP_H
#define REP_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
class UnicodeString;
/**
* Replaceable
is an abstract base class representing a
* string of characters that supports the replacement of a range of
* itself with a new string of characters. It is used by APIs that
* change a piece of text while retaining metadata. Metadata is data
* other than the Unicode characters returned by char32At(). One
* example of metadata is style attributes; another is an edit
* history, marking each character with an author and revision number.
*
*
An implicit aspect of the Replaceable
API is that
* during a replace operation, new characters take on the metadata of
* the old characters. For example, if the string "the bold
* font" has range (4, 8) replaced with "strong", then it becomes "the
* strong font".
*
*
Replaceable
specifies ranges using a start
* offset and a limit offset. The range of characters thus specified
* includes the characters at offset start..limit-1. That is, the
* start offset is inclusive, and the limit offset is exclusive.
*
*
Replaceable
also includes API to access characters
* in the string: length()
, charAt()
,
* char32At()
, and extractBetween()
.
*
*
For a subclass to support metadata, typical behavior of
* replace()
is the following:
*
length()
-1
* inclusive
* @return 16-bit code unit of text at given offset
* @since ICU 1.8
*/
inline UChar charAt(int32_t offset) const;
/**
* Returns the 32-bit code point at the given 16-bit offset into
* the text. This assumes the text is stored as 16-bit code units
* with surrogate pairs intermixed. If the offset of a leading or
* trailing code unit of a surrogate pair is given, return the
* code point of the surrogate pair.
*
* @param offset an integer between 0 and length()
-1
* inclusive
* @return 32-bit code point of text at given offset
* @since ICU 1.8
*/
inline UChar32 char32At(int32_t offset) const;
/**
* Copies characters in the range [start, limit)
* into the UnicodeString target.
* @param start offset of first character which will be copied
* @param limit offset immediately following the last character to
* be copied
* @param target UnicodeString into which to copy characters.
* @return A reference to target
* @since ICU 2.1
*/
virtual void extractBetween(int32_t start,
int32_t limit,
UnicodeString& target) const = 0;
/**
* Replaces a substring of this object with the given text. If the
* characters being replaced have metadata, the new characters
* that replace them should be given the same metadata.
*
* Subclasses must ensure that if the text between start and
* limit is equal to the replacement text, that replace has no
* effect. That is, any metadata
* should be unaffected. In addition, subclasses are encouraged to
* check for initial and trailing identical characters, and make a
* smaller replacement if possible. This will preserve as much
* metadata as possible.
* @param start the beginning index, inclusive; 0 <= start
* <= limit
.
* @param limit the ending index, exclusive; start <= limit
* <= length()
.
* @param text the text to replace characters start
* to limit - 1
* @stable
*/
virtual void handleReplaceBetween(int32_t start,
int32_t limit,
const UnicodeString& text) = 0;
// Note: All other methods in this class take the names of
// existing UnicodeString methods. This method is the exception.
// It is named differently because all replace methods of
// UnicodeString return a UnicodeString&. The 'between' is
// required in order to conform to the UnicodeString naming
// convention; API taking start/length are named 0 <= start <=
* limit
.
* @param limit the ending index, exclusive; start <= limit <=
* length()
.
* @param dest the destination index. The characters from
* start..limit-1
will be copied to dest
.
* Implementations of this method may assume that dest <= start ||
* dest >= limit
.
* @stable
*/
virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0;
/**
* Returns true if this object contains metadata. If a
* Replaceable object has metadata, calls to the Replaceable API
* must be made so as to preserve metadata. If it does not, calls
* to the Replaceable API may be optimized to improve performance.
* The default implementation returns true.
* @return true if this object contains metadata
* @since ICU 2.2
*/
virtual UBool hasMetaData() const;
protected:
/**
* Default constructor.
*/
Replaceable();
/**
* Virtual version of length().
*/
virtual int32_t getLength() const = 0;
/**
* Virtual version of charAt().
*/
virtual UChar getCharAt(int32_t offset) const = 0;
/**
* Virtual version of char32At().
*/
virtual UChar32 getChar32At(int32_t offset) const = 0;
};
inline Replaceable::Replaceable() {}
inline Replaceable::~Replaceable() {}
inline int32_t
Replaceable::length() const {
return getLength();
}
inline UChar
Replaceable::charAt(int32_t offset) const {
return getCharAt(offset);
}
inline UChar32
Replaceable::char32At(int32_t offset) const {
return getChar32At(offset);
}
// See unistr.cpp for Replaceable::hasMetaData()
U_NAMESPACE_END
#endif