end=spanQuickCheckYes(s, ec);
* the substring UnicodeString(s, 0, end)
* will pass the quick check with a "yes" result.
*
* The returned end index is usually one or more characters before the
* "no" or "maybe" character: The end index is at a normalization boundary.
* (See the class documentation for more about normalization boundaries.)
*
* When the goal is a normalized string and most input strings are expected
* to be normalized already, then call this method,
* and if it returns a prefix shorter than the input string,
* copy that prefix and use normalizeSecondAndAppend() for the remainder.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return "yes" span end index
* @stable ICU 4.4
*/
virtual int32_t
spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const = 0;
/**
* Tests if the character always has a normalization boundary before it,
* regardless of context.
* If true, then the character does not normalization-interact with
* preceding characters.
* In other words, a string containing this character can be normalized
* by processing portions before this character and starting from this
* character independently.
* This is used for iterative normalization. See the class documentation for details.
* @param c character to test
* @return TRUE if c has a normalization boundary before it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryBefore(UChar32 c) const = 0;
/**
* Tests if the character always has a normalization boundary after it,
* regardless of context.
* If true, then the character does not normalization-interact with
* following characters.
* In other words, a string containing this character can be normalized
* by processing portions up to this character and after this
* character independently.
* This is used for iterative normalization. See the class documentation for details.
* Note that this operation may be significantly slower than hasBoundaryBefore().
* @param c character to test
* @return TRUE if c has a normalization boundary after it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryAfter(UChar32 c) const = 0;
/**
* Tests if the character is normalization-inert.
* If true, then the character does not change, nor normalization-interact with
* preceding or following characters.
* In other words, a string containing this character can be normalized
* by processing portions before this character and after this
* character independently.
* This is used for iterative normalization. See the class documentation for details.
* Note that this operation may be significantly slower than hasBoundaryBefore().
* @param c character to test
* @return TRUE if c is normalization-inert
* @stable ICU 4.4
*/
virtual UBool isInert(UChar32 c) const = 0;
private:
// No ICU "poor man's RTTI" for this class nor its subclasses.
virtual UClassID getDynamicClassID() const;
};
/**
* Normalization filtered by a UnicodeSet.
* Normalizes portions of the text contained in the filter set and leaves
* portions not contained in the filter set unchanged.
* Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE).
* Not-in-the-filter text is treated as "is normalized" and "quick check yes".
* This class implements all of (and only) the Normalizer2 API.
* An instance of this class is unmodifiable/immutable but is constructed and
* must be destructed by the owner.
* @stable ICU 4.4
*/
class U_COMMON_API FilteredNormalizer2 : public Normalizer2 {
public:
/**
* Constructs a filtered normalizer wrapping any Normalizer2 instance
* and a filter set.
* Both are aliased and must not be modified or deleted while this object
* is used.
* The filter set should be frozen; otherwise the performance will suffer greatly.
* @param n2 wrapped Normalizer2 instance
* @param filterSet UnicodeSet which determines the characters to be normalized
* @stable ICU 4.4
*/
FilteredNormalizer2(const Normalizer2 &n2, const UnicodeSet &filterSet) :
norm2(n2), set(filterSet) {}
/**
* Destructor.
* @stable ICU 4.4
*/
~FilteredNormalizer2();
/**
* Writes the normalized form of the source string to the destination string
* (replacing its contents) and returns the destination string.
* The source and destination strings must be different objects.
* @param src source string
* @param dest destination string; its contents is replaced with normalized src
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.4
*/
virtual UnicodeString &
normalize(const UnicodeString &src,
UnicodeString &dest,
UErrorCode &errorCode) const;
/**
* Appends the normalized form of the second string to the first string
* (merging them at the boundary) and returns the first string.
* The result is normalized if the first string was normalized.
* The first and second strings must be different objects.
* @param first string, should be normalized
* @param second string, will be normalized
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
virtual UnicodeString &
normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const;
/**
* Appends the second string to the first string
* (merging them at the boundary) and returns the first string.
* The result is normalized if both the strings were normalized.
* The first and second strings must be different objects.
* @param first string, should be normalized
* @param second string, should be normalized
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
virtual UnicodeString &
append(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const;
/**
* Gets the decomposition mapping of c.
* For details see the base class documentation.
*
* This function is independent of the mode of the Normalizer2.
* @param c code point
* @param decomposition String object which will be set to c's
* decomposition mapping, if there is one.
* @return TRUE if c has a decomposition, otherwise FALSE
* @stable ICU 4.6
*/
virtual UBool
getDecomposition(UChar32 c, UnicodeString &decomposition) const;
/**
* Gets the raw decomposition mapping of c.
* For details see the base class documentation.
*
* This function is independent of the mode of the Normalizer2.
* @param c code point
* @param decomposition String object which will be set to c's
* raw decomposition mapping, if there is one.
* @return TRUE if c has a decomposition, otherwise FALSE
* @draft ICU 49
*/
virtual UBool
getRawDecomposition(UChar32 c, UnicodeString &decomposition) const;
/**
* Performs pairwise composition of a & b and returns the composite if there is one.
* For details see the base class documentation.
*
* This function is independent of the mode of the Normalizer2.
* @param a A (normalization starter) code point.
* @param b Another code point.
* @return The non-negative composite code point if there is one; otherwise a negative value.
* @draft ICU 49
*/
virtual UChar32
composePair(UChar32 a, UChar32 b) const;
/**
* Gets the combining class of c.
* The default implementation returns 0
* but all standard implementations return the Unicode Canonical_Combining_Class value.
* @param c code point
* @return c's combining class
* @draft ICU 49
*/
virtual uint8_t
getCombiningClass(UChar32 c) const;
/**
* Tests if the string is normalized.
* For details see the Normalizer2 base class documentation.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return TRUE if s is normalized
* @stable ICU 4.4
*/
virtual UBool
isNormalized(const UnicodeString &s, UErrorCode &errorCode) const;
/**
* Tests if the string is normalized.
* For details see the Normalizer2 base class documentation.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return UNormalizationCheckResult
* @stable ICU 4.4
*/
virtual UNormalizationCheckResult
quickCheck(const UnicodeString &s, UErrorCode &errorCode) const;
/**
* Returns the end of the normalized substring of the input string.
* For details see the Normalizer2 base class documentation.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return "yes" span end index
* @stable ICU 4.4
*/
virtual int32_t
spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const;
/**
* Tests if the character always has a normalization boundary before it,
* regardless of context.
* For details see the Normalizer2 base class documentation.
* @param c character to test
* @return TRUE if c has a normalization boundary before it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryBefore(UChar32 c) const;
/**
* Tests if the character always has a normalization boundary after it,
* regardless of context.
* For details see the Normalizer2 base class documentation.
* @param c character to test
* @return TRUE if c has a normalization boundary after it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryAfter(UChar32 c) const;
/**
* Tests if the character is normalization-inert.
* For details see the Normalizer2 base class documentation.
* @param c character to test
* @return TRUE if c is normalization-inert
* @stable ICU 4.4
*/
virtual UBool isInert(UChar32 c) const;
private:
UnicodeString &
normalize(const UnicodeString &src,
UnicodeString &dest,
USetSpanCondition spanCondition,
UErrorCode &errorCode) const;
UnicodeString &
normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
UBool doNormalize,
UErrorCode &errorCode) const;
const Normalizer2 &norm2;
const UnicodeSet &set;
};
U_NAMESPACE_END
#endif // !UCONFIG_NO_NORMALIZATION
#endif // __NORMALIZER2_H__