scuffed-code/icu4c/source/common/unicode/unifilt.h

138 lines
4.1 KiB
C
Raw Normal View History

/*
* Copyright (C) 1999, International Business Machines Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 11/17/99 aliu Creation.
**********************************************************************
*/
#ifndef UNIFILT_H
#define UNIFILT_H
#include "unicode/unifunct.h"
#include "unicode/unimatch.h"
U_NAMESPACE_BEGIN
/**
* U_ETHER is used to represent character values for positions outside
* a range. For example, transliterator uses this to represent
* characters outside the range contextStart..contextLimit-1. This
* allows explicit matching by rules and UnicodeSets of text outside a
* defined range.
*/
#define U_ETHER ((UChar)0xFFFF)
/**
* <code>UnicodeFilter</code> defines a protocol for selecting a
* subset of the full range (U+0000 to U+10FFFF) of Unicode characters.
* Currently, filters are used in conjunction with classes like {@link
* Transliterator} to only process selected characters through a
* transformation.
*
* <p>Note: UnicodeFilter currently stubs out two pure virtual methods
* of its base class, UnicodeMatcher. These methods are toPattern()
* and matchesIndexValue(). This is done so that filter classes that
* are not actually used as matchers -- specifically, those in the
* UnicodeFilterLogic component, and those in tests -- can continue to
* work without defining these methods. As long as a filter is not
* used in an RBT during real transliteration, these methods will not
* be called. However, this breaks the UnicodeMatcher base class
* protocol, and it is not a correct solution.
*
* <p>In the future we may revisit the UnicodeMatcher / UnicodeFilter
* hierarchy and either redesign it, or simply remove the stubs in
* UnicodeFilter and force subclasses to implement the full
* UnicodeMatcher protocol.
*
* @see UnicodeFilterLogic
* @stable
*/
class U_COMMON_API UnicodeFilter : public UnicodeFunctor, public UnicodeMatcher {
public:
/**
* Destructor
* @stable
*/
virtual ~UnicodeFilter();
/**
* Returns <tt>true</tt> for characters that are in the selected
* subset. In other words, if a character is <b>to be
* filtered</b>, then <tt>contains()</tt> returns
* <b><tt>false</tt></b>.
* @stable
*/
virtual UBool contains(UChar32 c) const = 0;
/**
* UnicodeFunctor API. Cast 'this' to a UnicodeMatcher* pointer
* and return the pointer.
*/
virtual UnicodeMatcher* toMatcher() const;
/**
* UnicodeMatcher API. This class stubs this out.
*/
UnicodeString& toPattern(UnicodeString& result,
UBool escapeUnprintable) const;
/**
* UnicodeMatcher API. This class stubs this out.
*/
UBool matchesIndexValue(uint8_t v) const;
/**
* Implement UnicodeMatcher API.
*/
virtual UMatchDegree matches(const Replaceable& text,
int32_t& offset,
int32_t limit,
UBool incremental);
/**
* UnicodeFunctor API. Nothing to do.
*/
virtual void setData(const TransliterationRuleData*) {}
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @draft ICU 2.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @draft ICU 2.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* Stubbed out implementation of UnicodeMatcher API.
* @param toUnionTo the set into which to union the source characters
* @return a reference to toUnionTo
*/
virtual void addMatchSetTo(UnicodeSet& toUnionTo) const;
protected:
UnicodeFilter();
private:
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
};
inline UnicodeFilter::UnicodeFilter() {}
inline UnicodeFilter::~UnicodeFilter() {}
U_NAMESPACE_END
#endif