200 lines
7.3 KiB
C++
200 lines
7.3 KiB
C++
/*
|
|
* Copyright (C) 2001, International Business Machines Corporation and others. All Rights Reserved.
|
|
**********************************************************************
|
|
* Date Name Description
|
|
* 07/18/01 aliu Creation.
|
|
**********************************************************************
|
|
*/
|
|
#ifndef UNIMATCH_H
|
|
#define UNIMATCH_H
|
|
|
|
#include "unicode/utypes.h"
|
|
|
|
U_NAMESPACE_BEGIN
|
|
|
|
class Replaceable;
|
|
class UnicodeString;
|
|
|
|
/**
|
|
* Constants returned by <code>UnicodeMatcher::matches()</code>
|
|
* indicating the degree of match.
|
|
*/
|
|
enum UMatchDegree {
|
|
/**
|
|
* Constant returned by <code>matches()</code> indicating a
|
|
* mismatch between the text and this matcher. The text contains
|
|
* a character which does not match, or the text does not contain
|
|
* all desired characters for a non-incremental match.
|
|
*/
|
|
U_MISMATCH,
|
|
|
|
/**
|
|
* Constant returned by <code>matches()</code> indicating a
|
|
* partial match between the text and this matcher. This value is
|
|
* only returned for incremental match operations. All characters
|
|
* of the text match, but more characters are required for a
|
|
* complete match. Alternatively, for variable-length matchers,
|
|
* all characters of the text match, and if more characters were
|
|
* supplied at limit, they might also match.
|
|
*/
|
|
U_PARTIAL_MATCH,
|
|
|
|
/**
|
|
* Constant returned by <code>matches()</code> indicating a
|
|
* complete match between the text and this matcher. For an
|
|
* incremental variable-length match, this value is returned if
|
|
* the given text matches, and it is known that additional
|
|
* characters would not alter the extent of the match.
|
|
*/
|
|
U_MATCH
|
|
};
|
|
|
|
/**
|
|
* <code>UnicodeMatcher</code> defines a protocol for objects that can
|
|
* match a range of characters in a Replaceable string.
|
|
*/
|
|
class U_I18N_API UnicodeMatcher {
|
|
|
|
public:
|
|
|
|
/**
|
|
* Destructor
|
|
*/
|
|
virtual ~UnicodeMatcher();
|
|
|
|
/**
|
|
* Returns a copy of this object. All UnicodeMatcher objects have
|
|
* to support cloning in order to allow classes using
|
|
* UnicodeMatchers to implement cloning.
|
|
*/
|
|
virtual UnicodeMatcher* clone() const = 0;
|
|
|
|
/**
|
|
* Return a UMatchDegree value indicating the degree of match for
|
|
* the given text at the given offset. Zero, one, or more
|
|
* characters may be matched.
|
|
*
|
|
* Matching in the forward direction is indicated by limit >
|
|
* offset. Characters from offset forwards to limit-1 will be
|
|
* considered for matching.
|
|
*
|
|
* Matching in the reverse direction is indicated by limit <
|
|
* offset. Characters from offset backwards to limit+1 will be
|
|
* considered for matching.
|
|
*
|
|
* If limit == offset then the only match possible is a zero
|
|
* character match (which subclasses may implement if desired).
|
|
*
|
|
* As a side effect, advance the offset parameter to the limit of
|
|
* the matched substring. In the forward direction, this will be
|
|
* the index of the last matched character plus one. In the
|
|
* reverse direction, this will be the index of the last matched
|
|
* character minus one.
|
|
*
|
|
* <p>Note: This method is not const because some classes may
|
|
* modify their state as the result of a match.
|
|
*
|
|
* @param text the text to be matched
|
|
* @param offset on input, the index into text at which to begin
|
|
* matching. On output, the limit of the matched text. The
|
|
* number of matched characters is the output value of offset
|
|
* minus the input value. Offset should always point to the
|
|
* HIGH SURROGATE (leading code unit) of a pair of surrogates,
|
|
* both on entry and upon return.
|
|
* @param limit the limit index of text to be matched. Greater
|
|
* than offset for a forward direction match, less than offset for
|
|
* a backward direction match. The last character to be
|
|
* considered for matching will be text.charAt(limit-1) in the
|
|
* forward direction or text.charAt(limit+1) in the backward
|
|
* direction.
|
|
* @param incremental if TRUE, then assume further characters may
|
|
* be inserted at limit and check for partial matching. Otherwise
|
|
* assume the text as given is complete.
|
|
* @return a match degree value indicating a full match, a partial
|
|
* match, or a mismatch. If incremental is FALSE then
|
|
* U_PARTIAL_MATCH should never be returned.
|
|
*/
|
|
virtual UMatchDegree matches(const Replaceable& text,
|
|
int32_t& offset,
|
|
int32_t limit,
|
|
UBool incremental) = 0;
|
|
|
|
/**
|
|
* Returns a string representation of this matcher. If the result of
|
|
* calling this function is passed to the appropriate parser, it
|
|
* will produce another matcher that is equal to this one.
|
|
* @param result the string to receive the pattern. Previous
|
|
* contents will be deleted.
|
|
* @param escapeUnprintable if TRUE then convert unprintable
|
|
* character to their hex escape representations, \uxxxx or
|
|
* \Uxxxxxxxx. Unprintable characters are those other than
|
|
* U+000A, U+0020..U+007E.
|
|
*/
|
|
virtual UnicodeString& toPattern(UnicodeString& result,
|
|
UBool escapeUnprintable = FALSE) const = 0;
|
|
|
|
/**
|
|
* Returns TRUE if this matcher will match a character c, where c
|
|
* & 0xFF == v, at offset, in the forward direction (with limit >
|
|
* offset). This is used by <tt>RuleBasedTransliterator</tt> for
|
|
* indexing.
|
|
*/
|
|
virtual UBool matchesIndexValue(uint8_t v) const = 0;
|
|
|
|
/**
|
|
* Return the class ID for this class. This is useful only for
|
|
* comparing to a return value from getDynamicClassID(). For example:
|
|
* <pre>
|
|
* . Base* polymorphic_pointer = createPolymorphicObject();
|
|
* . if (polymorphic_pointer->getDynamicClassID() ==
|
|
* . Derived::getStaticClassID()) ...
|
|
* </pre>
|
|
* @return The class ID for all objects of this class.
|
|
* @stable
|
|
*/
|
|
static UClassID getStaticClassID(void) { return (UClassID)&fgClassID; }
|
|
|
|
/**
|
|
* Returns a unique class ID <b>polymorphically</b>. This method
|
|
* is to implement a simple version of RTTI, since not all C++
|
|
* compilers support genuine RTTI. Polymorphic operator==() and
|
|
* clone() methods call this method.
|
|
*
|
|
* <p>Concrete subclasses of UnicodeMatcher that wish clients to
|
|
* be able to identify them should implement getDynamicClassID()
|
|
* and also a static method and data member:
|
|
*
|
|
* <pre>
|
|
* static UClassID getStaticClassID() { return (UClassID)&fgClassID; }
|
|
* static char fgClassID;
|
|
* </pre>
|
|
*
|
|
* Subclasses that do not implement this method will have a
|
|
* dynamic class ID of UnicodeMatcher::getStatisClassID().
|
|
*
|
|
* @return The class ID for this object. All objects of a given
|
|
* class have the same class ID. Objects of other classes have
|
|
* different class IDs.
|
|
*/
|
|
virtual UClassID getDynamicClassID(void) const { return getStaticClassID(); };
|
|
|
|
private:
|
|
|
|
/**
|
|
* Class identifier for subclasses of UnicodeMatcher that do not
|
|
* define their class (anonymous subclasses).
|
|
*/
|
|
static const char fgClassID;
|
|
|
|
protected:
|
|
|
|
UnicodeMatcher();
|
|
};
|
|
|
|
inline UnicodeMatcher::UnicodeMatcher() {}
|
|
inline UnicodeMatcher::~UnicodeMatcher() {}
|
|
|
|
U_NAMESPACE_END
|
|
|
|
#endif
|