The UnicodeSet class is not designed to be subclassed. * *
UnicodeSet supports two APIs. The first is the
* operand API that allows the caller to modify the value of
* a UnicodeSet object. It conforms to Java 2's
* java.util.Set interface, although
* UnicodeSet does not actually implement that
* interface. All methods of Set are supported, with the
* modification that they take a character range or single character
* instead of an Object, and they take a
* UnicodeSet instead of a Collection. The
* operand API may be thought of in terms of boolean logic: a boolean
* OR is implemented by add, a boolean AND is implemented
* by retain, a boolean XOR is implemented by
* complement taking an argument, and a boolean NOT is
* implemented by complement with no argument. In terms
* of traditional set theory function names, add is a
* union, retain is an intersection, remove
* is an asymmetric difference, and complement with no
* argument is a set complement with respect to the superset range
* MIN_VALUE-MAX_VALUE
*
*
The second API is the
* applyPattern()/toPattern() API from the
* java.text.Format-derived classes. Unlike the
* methods that add characters, add categories, and control the logic
* of the set, the method applyPattern() sets all
* attributes of a UnicodeSet at once, based on a
* string pattern.
*
*
Pattern syntax
* * Patterns are accepted by the constructors and the *applyPattern() methods and returned by the
* toPattern() method. These patterns follow a syntax
* similar to that employed by version 8 regular expression character
* classes. Here are some simple examples:
*
* \htmlonly\endhtmlonly *\endhtmlonly * * Any character may be preceded by a backslash in order to remove any special * meaning. White space characters, as defined by UCharacter.isWhitespace(), are * ignored, unless they are escaped. * **
* \htmlonly* * []No characters ** * [a]The character 'a' ** ** [ae]The characters 'a' and 'e' ** ** [a-e]The characters 'a' through 'e' inclusive, in Unicode code * point order ** ** [\\u4E01]The character U+4E01 ** ** [a{ab}{ac}]The character 'a' and the multicharacter strings "ab" and * "ac" ** ** [\\p{Lu}]All characters in the general category Uppercase Letter *
Property patterns specify a set of characters having a certain * property as defined by the Unicode standard. Both the POSIX-like * "[:Lu:]" and the Perl-like syntax "\\p{Lu}" are recognized. For a * complete list of supported property patterns, see the User's Guide * for UnicodeSet at * * http://icu.sourceforge.net/userguide/unicodeSet.html. * Actual determination of property data is defined by the underlying * Unicode database as implemented by UCharacter. * *
Patterns specify individual characters, ranges of characters, and * Unicode property sets. When elements are concatenated, they * specify their union. To complement a set, place a '^' immediately * after the opening '['. Property patterns are inverted by modifying * their delimiters; "[:^foo]" and "\\P{foo}". In any other location, * '^' has no special meaning. * *
Ranges are indicated by placing two a '-' between two * characters, as in "a-z". This specifies the range of all * characters from the left to the right, in Unicode order. If the * left character is greater than or equal to the * right character it is a syntax error. If a '-' occurs as the first * character after the opening '[' or '[^', or if it occurs as the * last character before the closing ']', then it is taken as a * literal. Thus "[a\-b]", "[-ab]", and "[ab-]" all indicate the same * set of three characters, 'a', 'b', and '-'. * *
Sets may be intersected using the '&' operator or the asymmetric * set difference may be taken using the '-' operator, for example, * "[[:L:]&[\\u0000-\\u0FFF]]" indicates the set of all Unicode letters * with values less than 4096. Operators ('&' and '|') have equal * precedence and bind left-to-right. Thus * "[[:L:]-[a-z]-[\\u0100-\\u01FF]]" is equivalent to * "[[[:L:]-[a-z]]-[\\u0100-\\u01FF]]". This only really matters for * difference; intersection is commutative. * *
[a] | The set containing 'a' * |
[a-z] | The set containing 'a' * through 'z' and all letters in between, in Unicode order * |
[^a-z] | The set containing * all characters but 'a' through 'z', * that is, U+0000 through 'a'-1 and 'z'+1 through U+10FFFF * |
[[pat1][pat2]]
* | The union of sets specified by pat1 and pat2 * |
[[pat1]&[pat2]]
* | The intersection of sets specified by pat1 and pat2 * |
[[pat1]-[pat2]]
* | The asymmetric difference of sets specified by pat1 and * pat2 * |
[:Lu:] or \\p{Lu}
* | The set of characters having the specified * Unicode property; in * this case, Unicode uppercase letters * |
[:^Lu:] or \\P{Lu}
* | The set of characters not having the given * Unicode property * |
Warning: you cannot add an empty string ("") to a UnicodeSet.
* *Formal syntax
* * \htmlonly\endhtmlonly *\endhtmlonly * * @author Alan Liu * @stable ICU 2.0 */ class U_COMMON_API UnicodeSet : public UnicodeFilter { int32_t len; // length of list used; 0 <= len <= capacity int32_t capacity; // capacity of list int32_t bufferCapacity; // capacity of buffer UChar32* list; // MUST be terminated with HIGH UChar32* buffer; // internal buffer, may be NULL UVector* strings; // maintained in sorted order /** * The pattern representation of this set. This may not be the * most economical pattern. It is the pattern supplied to * applyPattern(), with variables substituted and whitespace * removed. For sets constructed without applyPattern(), or * modified using the non-pattern API, this string will be empty, * indicating that toPattern() must generate a pattern * representation from the inversion list. */ UnicodeString pat; public: enum { /** * Minimum value that can be stored in a UnicodeSet. * @stable ICU 2.4 */ MIN_VALUE = 0, /** * Maximum value that can be stored in a UnicodeSet. * @stable ICU 2.4 */ MAX_VALUE = 0x10ffff }; //---------------------------------------------------------------- // Constructors &c //---------------------------------------------------------------- public: /** * Constructs an empty set. * @stable ICU 2.0 */ UnicodeSet(); /** * Constructs a set containing the given range. If*
** ** pattern :=* ('[' '^'? item* ']') | * property* ** item :=* char | (char '-' char) | pattern-expr
** ** pattern-expr :=* pattern | pattern-expr pattern | * pattern-expr op pattern
** ** op :=* '&' | '-'
** ** special :=* '[' | ']' | '-'
** ** char :=any character that is not *specialany character
* | ('\')
* | ('\\u' hex hex hex hex)
** ** hex :=any character for which * *Character.digit(c, 16)* returns a non-negative result* ** property :=a Unicode property set pattern *
**
* \htmlonly* *Legend: **
** ** a := b* * amay be replaced byb* ** a?* zero or one instance of *a
** ** a** one or more instances of *a
** ** a | b* either *aorb
** ** 'a'* the literal string between the quotes *
end >
* start then an empty set is created.
*
* @param start first character, inclusive, of range
* @param end last character, inclusive, of range
* @stable ICU 2.4
*/
UnicodeSet(UChar32 start, UChar32 end);
/**
* Constructs a set from the given pattern. See the class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param status returns U_ILLEGAL_ARGUMENT_ERROR if the pattern
* contains a syntax error.
* @stable ICU 2.0
*/
UnicodeSet(const UnicodeString& pattern,
UErrorCode& status);
/**
* Constructs a set from the given pattern. See the class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param options bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param symbols a symbol table mapping variable names to values
* and stand-in characters to UnicodeSets; may be NULL
* @param status returns U_ILLEGAL_ARGUMENT_ERROR if the pattern
* contains a syntax error.
* @internal
*/
UnicodeSet(const UnicodeString& pattern,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status);
/**
* Constructs a set from the given pattern. See the class description
* for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param pos on input, the position in pattern at which to start parsing.
* On output, the position after the last character parsed.
* @param options bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param symbols a symbol table mapping variable names to values
* and stand-in characters to UnicodeSets; may be NULL
* @param status input-output error code
* @stable ICU 2.8
*/
UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status);
/**
* Constructs a set that is identical to the given UnicodeSet.
* @stable ICU 2.0
*/
UnicodeSet(const UnicodeSet& o);
/**
* Destructs the set.
* @stable ICU 2.0
*/
virtual ~UnicodeSet();
/**
* Assigns this object to be a copy of another.
* @stable ICU 2.0
*/
UnicodeSet& operator=(const UnicodeSet& o);
/**
* Compares the specified object with this set for equality. Returns
* true if the two sets
* have the same size, and every member of the specified set is
* contained in this set (or equivalently, every member of this set is
* contained in the specified set).
*
* @param o set to be compared for equality with this set.
* @return true if the specified set is equal to this set.
* @stable ICU 2.0
*/
virtual UBool operator==(const UnicodeSet& o) const;
/**
* Compares the specified object with this set for equality. Returns
* true if the specified set is not equal to this set.
* @stable ICU 2.0
*/
UBool operator!=(const UnicodeSet& o) const;
/**
* Returns a copy of this object. All UnicodeFunctor objects have
* to support cloning in order to allow classes using
* UnicodeFunctors, such as Transliterator, to implement cloning.
* @stable ICU 2.0
*/
virtual UnicodeFunctor* clone() const;
/**
* Returns the hash code value for this set.
*
* @return the hash code value for this set.
* @see Object#hashCode()
* @stable ICU 2.0
*/
virtual int32_t hashCode(void) const;
//----------------------------------------------------------------
// Public API
//----------------------------------------------------------------
/**
* Make this object represent the range start - end.
* If end > start then this object is set to an
* an empty range.
*
* @param start first character in the set, inclusive
* @param end last character in the set, inclusive
* @stable ICU 2.4
*/
UnicodeSet& set(UChar32 start, UChar32 end);
/**
* Return true if the given position, in the given pattern, appears
* to be the start of a UnicodeSet pattern.
* @stable ICU 2.4
*/
static UBool resemblesPattern(const UnicodeString& pattern,
int32_t pos);
/**
* Modifies this set to represent the set specified by the given
* pattern, optionally ignoring white space. See the class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param status returns U_ILLEGAL_ARGUMENT_ERROR if the pattern
* contains a syntax error.
* Empties the set passed before applying the pattern.
* @return a reference to this
* @stable ICU 2.0
*/
UnicodeSet& applyPattern(const UnicodeString& pattern,
UErrorCode& status);
/**
* Modifies this set to represent the set specified by the given
* pattern, optionally ignoring white space. See the class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param options bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param symbols a symbol table mapping variable names to
* values and stand-ins to UnicodeSets; may be NULL
* @param status returns U_ILLEGAL_ARGUMENT_ERROR if the pattern
* contains a syntax error.
* Empties the set passed before applying the pattern.
* @return a reference to this
* @internal
*/
UnicodeSet& applyPattern(const UnicodeString& pattern,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status);
/**
* Parses the given pattern, starting at the given position. The
* character at pattern.charAt(pos.getIndex()) must be '[', or the
* parse fails. Parsing continues until the corresponding closing
* ']'. If a syntax error is encountered between the opening and
* closing brace, the parse fails. Upon return from a successful
* parse, the ParsePosition is updated to point to the character
* following the closing ']', and a StringBuffer containing a
* pairs list for the parsed pattern is returned. This method calls
* itself recursively to parse embedded subpatterns.
* Empties the set passed before applying the pattern.
*
* @param pattern the string containing the pattern to be parsed.
* The portion of the string from pos.getIndex(), which must be a
* '[', to the corresponding closing ']', is parsed.
* @param pos upon entry, the position at which to being parsing.
* The character at pattern.charAt(pos.getIndex()) must be a '['.
* Upon return from a successful parse, pos.getIndex() is either
* the character after the closing ']' of the parsed pattern, or
* pattern.length() if the closing ']' is the last character of
* the pattern string.
* @param options bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param symbols a symbol table mapping variable names to
* values and stand-ins to UnicodeSets; may be NULL
* @param status returns U_ILLEGAL_ARGUMENT_ERROR if the pattern
* contains a syntax error.
* @return a reference to this
* @stable ICU 2.8
*/
UnicodeSet& applyPattern(const UnicodeString& pattern,
ParsePosition& pos,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status);
/**
* Returns a string representation of this set. If the result of
* calling this function is passed to a UnicodeSet constructor, it
* will produce another set that is equal to this one.
* @param result the string to receive the rules. 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.
* @stable ICU 2.0
*/
virtual UnicodeString& toPattern(UnicodeString& result,
UBool escapeUnprintable = FALSE) const;
/**
* Modifies this set to contain those code points which have the given value
* for the given binary or enumerated property, as returned by
* u_getIntPropertyValue. Prior contents of this set are lost.
*
* @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1
* or UCHAR_INT_START..UCHAR_INT_LIMIT-1
* or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1.
*
* @param value a value in the range u_getIntPropertyMinValue(prop)..
* u_getIntPropertyMaxValue(prop), with one exception. If prop is
* UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but
* rather a mask value produced by U_GET_GC_MASK(). This allows grouped
* categories such as [:L:] to be represented.
*
* @param ec error code input/output parameter
*
* @return a reference to this set
*
* @stable ICU 2.4
*/
UnicodeSet& applyIntPropertyValue(UProperty prop,
int32_t value,
UErrorCode& ec);
/**
* Modifies this set to contain those code points which have the
* given value for the given property. Prior contents of this
* set are lost.
*
* @param prop a property alias, either short or long. The name is matched
* loosely. See PropertyAliases.txt for names and a description of loose
* matching. If the value string is empty, then this string is interpreted
* as either a General_Category value alias, a Script value alias, a binary
* property alias, or a special ID. Special IDs are matched loosely and
* correspond to the following sets:
*
* "ANY" = [\\u0000-\\U0010FFFF],
* "ASCII" = [\\u0000-\\u007F],
* "Assigned" = [:^Cn:].
*
* @param value a value alias, either short or long. The name is matched
* loosely. See PropertyValueAliases.txt for names and a description of
* loose matching. In addition to aliases listed, numeric values and
* canonical combining classes may be expressed numerically, e.g., ("nv",
* "0.5") or ("ccc", "220"). The value string may also be empty.
*
* @param ec error code input/output parameter
*
* @return a reference to this set
*
* @stable ICU 2.4
*/
UnicodeSet& applyPropertyAlias(const UnicodeString& prop,
const UnicodeString& value,
UErrorCode& ec);
/**
* Returns the number of elements in this set (its cardinality).
* Note than the elements of a set may include both individual
* codepoints and strings.
*
* @return the number of elements in this set (its cardinality).
* @stable ICU 2.0
*/
virtual int32_t size(void) const;
/**
* Returns true if this set contains no elements.
*
* @return true if this set contains no elements.
* @stable ICU 2.0
*/
virtual UBool isEmpty(void) const;
/**
* Returns true if this set contains the given character.
* @param c character to be checked for containment
* @return true if the test condition is met
* @stable ICU 2.0
*/
virtual UBool contains(UChar32 c) const;
/**
* Returns true if this set contains every character
* of the given range.
* @param start first character, inclusive, of the range
* @param end last character, inclusive, of the range
* @return true if the test condition is met
* @stable ICU 2.0
*/
virtual UBool contains(UChar32 start, UChar32 end) const;
/**
* Returns true if this set contains the given
* multicharacter string.
* @param s string to be checked for containment
* @return true if this set contains the specified string
* @stable ICU 2.4
*/
UBool contains(const UnicodeString& s) const;
/**
* Returns true if this set contains all the characters and strings
* of the given set.
* @param c set to be checked for containment
* @return true if the test condition is met
* @stable ICU 2.4
*/
virtual UBool containsAll(const UnicodeSet& c) const;
/**
* Returns true if this set contains all the characters
* of the given string.
* @param s string containing characters to be checked for containment
* @return true if the test condition is met
* @stable ICU 2.4
*/
UBool containsAll(const UnicodeString& s) const;
/**
* Returns true if this set contains none of the characters
* of the given range.
* @param start first character, inclusive, of the range
* @param end last character, inclusive, of the range
* @return true if the test condition is met
* @stable ICU 2.4
*/
UBool containsNone(UChar32 start, UChar32 end) const;
/**
* Returns true if this set contains none of the characters and strings
* of the given set.
* @param c set to be checked for containment
* @return true if the test condition is met
* @stable ICU 2.4
*/
UBool containsNone(const UnicodeSet& c) const;
/**
* Returns true if this set contains none of the characters
* of the given string.
* @param s string containing characters to be checked for containment
* @return true if the test condition is met
* @stable ICU 2.4
*/
UBool containsNone(const UnicodeString& s) const;
/**
* Returns true if this set contains one or more of the characters
* in the given range.
* @param start first character, inclusive, of the range
* @param end last character, inclusive, of the range
* @return true if the condition is met
* @stable ICU 2.4
*/
inline UBool containsSome(UChar32 start, UChar32 end) const;
/**
* Returns true if this set contains one or more of the characters
* and strings of the given set.
* @param s The set to be checked for containment
* @return true if the condition is met
* @stable ICU 2.4
*/
inline UBool containsSome(const UnicodeSet& s) const;
/**
* Returns true if this set contains one or more of the characters
* of the given string.
* @param s string containing characters to be checked for containment
* @return true if the condition is met
* @stable ICU 2.4
*/
inline UBool containsSome(const UnicodeString& s) const;
/**
* Implement UnicodeMatcher::matches()
* @stable ICU 2.4
*/
virtual UMatchDegree matches(const Replaceable& text,
int32_t& offset,
int32_t limit,
UBool incremental);
private:
/**
* Returns the longest match for s in text at the given position.
* If limit > start then match forward from start+1 to limit
* matching all characters except s.charAt(0). If limit < start,
* go backward starting from start-1 matching all characters
* except s.charAt(s.length()-1). This method assumes that the
* first character, text.charAt(start), matches s, so it does not
* check it.
* @param text the text to match
* @param start the first character to match. In the forward
* direction, text.charAt(start) is matched against s.charAt(0).
* In the reverse direction, it is matched against
* s.charAt(s.length()-1).
* @param limit the limit offset for matching, either last+1 in
* the forward direction, or last-1 in the reverse direction,
* where last is the index of the last character to match.
* @return If part of s matches up to the limit, return |limit -
* start|. If all of s matches before reaching the limit, return
* s.length(). If there is a mismatch between s and text, return
* 0
*/
static int32_t matchRest(const Replaceable& text,
int32_t start, int32_t limit,
const UnicodeString& s);
/**
* Returns the smallest value i such that c < list[i]. Caller
* must ensure that c is a legal value or this method will enter
* an infinite loop. This method performs a binary search.
* @param c a character in the range MIN_VALUE..MAX_VALUE
* inclusive
* @return the smallest integer i in the range 0..len-1,
* inclusive, such that c < list[i]
*/
int32_t findCodePoint(UChar32 c) const;
public:
/**
* Implementation of UnicodeMatcher API. Union the set of all
* characters that may be matched by this object into the given
* set.
* @param toUnionTo the set into which to union the source characters
* @stable ICU 2.4
*/
virtual void addMatchSetTo(UnicodeSet& toUnionTo) const;
/**
* Returns the index of the given character within this set, where
* the set is ordered by ascending code point. If the character
* is not in this set, return -1. The inverse of this method is
* charAt().
* @return an index from 0..size()-1, or -1
* @stable ICU 2.4
*/
int32_t indexOf(UChar32 c) const;
/**
* Returns the character at the given index within this set, where
* the set is ordered by ascending code point. If the index is
* out of range, return (UChar32)-1. The inverse of this method is
* indexOf().
* @param index an index from 0..size()-1
* @return the character at the given index, or (UChar32)-1.
* @stable ICU 2.4
*/
UChar32 charAt(int32_t index) const;
/**
* Adds the specified range to this set if it is not already
* present. If this set already contains the specified range,
* the call leaves this set unchanged. If end > start
* then an empty range is added, leaving the set unchanged.
* This is equivalent to a boolean logic OR, or a set UNION.
*
* @param start first character, inclusive, of range to be added
* to this set.
* @param end last character, inclusive, of range to be added
* to this set.
* @stable ICU 2.0
*/
virtual UnicodeSet& add(UChar32 start, UChar32 end);
/**
* Adds the specified character to this set if it is not already
* present. If this set already contains the specified character,
* the call leaves this set unchanged.
* @stable ICU 2.0
*/
UnicodeSet& add(UChar32 c);
/**
* Adds the specified multicharacter to this set if it is not already
* present. If this set already contains the multicharacter,
* the call leaves this set unchanged.
* Thus "ch" => {"ch"}
* end > start then an empty range is
* retained, leaving the set empty. This is equivalent to
* a boolean logic AND, or a set INTERSECTION.
*
* @param start first character, inclusive, of range to be retained
* to this set.
* @param end last character, inclusive, of range to be retained
* to this set.
* @stable ICU 2.0
*/
virtual UnicodeSet& retain(UChar32 start, UChar32 end);
/**
* Retain the specified character from this set if it is present.
* @stable ICU 2.0
*/
UnicodeSet& retain(UChar32 c);
/**
* Removes the specified range from this set if it is present.
* The set will not contain the specified range once the call
* returns. If end > start then an empty range is
* removed, leaving the set unchanged.
*
* @param start first character, inclusive, of range to be removed
* from this set.
* @param end last character, inclusive, of range to be removed
* from this set.
* @stable ICU 2.0
*/
virtual UnicodeSet& remove(UChar32 start, UChar32 end);
/**
* Removes the specified character from this set if it is present.
* The set will not contain the specified range once the call
* returns.
* @stable ICU 2.0
*/
UnicodeSet& remove(UChar32 c);
/**
* Removes the specified string from this set if it is present.
* The set will not contain the specified character once the call
* returns.
* @param s the source string
* @return this object, for chaining
* @stable ICU 2.4
*/
UnicodeSet& remove(const UnicodeString& s);
/**
* Inverts this set. This operation modifies this set so that
* its value is its complement. This is equivalent to
* complement(MIN_VALUE, MAX_VALUE).
* @stable ICU 2.0
*/
virtual UnicodeSet& complement(void);
/**
* Complements the specified range in this set. Any character in
* the range will be removed if it is in this set, or will be
* added if it is not in this set. If end > start
* then an empty range is complemented, leaving the set unchanged.
* This is equivalent to a boolean logic XOR.
*
* @param start first character, inclusive, of range to be removed
* from this set.
* @param end last character, inclusive, of range to be removed
* from this set.
* @stable ICU 2.0
*/
virtual UnicodeSet& complement(UChar32 start, UChar32 end);
/**
* Complements the specified character in this set. The character
* will be removed if it is in this set, or will be added if it is
* not in this set.
* @stable ICU 2.0
*/
UnicodeSet& complement(UChar32 c);
/**
* Complement the specified string in this set.
* The set will not contain the specified string once the call
* returns.
*
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . Derived::getStaticClassID()) ...
*
* @return The class ID for all objects of this class.
* @stable ICU 2.0
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Implement UnicodeFunctor API.
*
* @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.
* @stable ICU 2.4
*/
virtual UClassID getDynamicClassID(void) const;
private:
// Private API for the USet API
friend class USetAccess;
int32_t getStringCount() const;
const UnicodeString* getString(int32_t index) const;
//----------------------------------------------------------------
// RuleBasedTransliterator support
//----------------------------------------------------------------
private:
/**
* Returns true if this set contains any character whose low byte
* is the given value. This is used by RuleBasedTransliterator for
* indexing.
*/
virtual UBool matchesIndexValue(uint8_t v) const;
private:
//----------------------------------------------------------------
// Implementation: Pattern parsing
//----------------------------------------------------------------
void applyPattern(RuleCharacterIterator& chars,
const SymbolTable* symbols,
UnicodeString& rebuiltPat,
uint32_t options,
UErrorCode& ec);
//----------------------------------------------------------------
// Implementation: Utility methods
//----------------------------------------------------------------
void ensureCapacity(int32_t newLen);
void ensureBufferCapacity(int32_t newLen);
void swapBuffers(void);
UBool allocateStrings();
UnicodeString& _toPattern(UnicodeString& result,
UBool escapeUnprintable) const;
UnicodeString& _generatePattern(UnicodeString& result,
UBool escapeUnprintable) const;
static void _appendToPat(UnicodeString& buf, const UnicodeString& s, UBool escapeUnprintable);
static void _appendToPat(UnicodeString& buf, UChar32 c, UBool escapeUnprintable);
//----------------------------------------------------------------
// Implementation: Fundamental operators
//----------------------------------------------------------------
void exclusiveOr(const UChar32* other, int32_t otherLen, int8_t polarity);
void add(const UChar32* other, int32_t otherLen, int8_t polarity);
void retain(const UChar32* other, int32_t otherLen, int8_t polarity);
/**
* Return true if the given position, in the given pattern, appears
* to be the start of a property set pattern [:foo:], \\p{foo}, or
* \\P{foo}, or \\N{name}.
*/
static UBool resemblesPropertyPattern(const UnicodeString& pattern,
int32_t pos);
static UBool resemblesPropertyPattern(RuleCharacterIterator& chars,
int32_t iterOpts);
/**
* Parse the given property pattern at the given parse position
* and set this UnicodeSet to the result.
*
* The original design document is out of date, but still useful.
* Ignore the property and value names:
* http://dev.icu-project.org/cgi-bin/viewcvs.cgi/~checkout~/icuhtml/design/unicodeset_properties.html
*
* Recognized syntax:
*
* [:foo:] [:^foo:] - white space not allowed within "[:" or ":]"
* \\p{foo} \\P{foo} - white space not allowed within "\\p" or "\\P"
* \\N{name} - white space not allowed within "\\N"
*
* Other than the above restrictions, white space is ignored. Case
* is ignored except in "\\p" and "\\P" and "\\N". In 'name' leading
* and trailing space is deleted, and internal runs of whitespace
* are collapsed to a single space.
*
* We support binary properties, enumerated properties, and the
* following non-enumerated properties:
*
* Numeric_Value
* Name
* Unicode_1_Name
*
* @param pattern the pattern string
* @param ppos on entry, the position at which to begin parsing.
* This should be one of the locations marked '^':
*
* [:blah:] \\p{blah} \\P{blah} \\N{name}
* ^ % ^ % ^ % ^ %
*
* On return, the position after the last character parsed, that is,
* the locations marked '%'. If the parse fails, ppos is returned
* unchanged.
* @return a reference to this.
*/
UnicodeSet& applyPropertyPattern(const UnicodeString& pattern,
ParsePosition& ppos,
UErrorCode &ec);
void applyPropertyPattern(RuleCharacterIterator& chars,
UnicodeString& rebuiltPat,
UErrorCode& ec);
/**
* A filter that returns TRUE if the given code point should be
* included in the UnicodeSet being constructed.
*/
typedef UBool (*Filter)(UChar32 codePoint, void* context);
/**
* Given a filter, set this UnicodeSet to the code points
* contained by that filter. The filter MUST be
* property-conformant. That is, if it returns value v for one
* code point, then it must return v for all affiliated code
* points, as defined by the inclusions list. See
* getInclusions().
* src is a UPropertySource value.
*/
void applyFilter(Filter filter,
void* context,
int32_t src,
UErrorCode &status);
/**
* Return a cached copy of the inclusions list for the property source.
*/
static const UnicodeSet* getInclusions(int32_t src, UErrorCode &errorCode);
friend class UnicodeSetIterator;
};
inline UBool UnicodeSet::operator!=(const UnicodeSet& o) const {
return !operator==(o);
}
inline UBool UnicodeSet::containsSome(UChar32 start, UChar32 end) const {
return !containsNone(start, end);
}
inline UBool UnicodeSet::containsSome(const UnicodeSet& s) const {
return !containsNone(s);
}
inline UBool UnicodeSet::containsSome(const UnicodeString& s) const {
return !containsNone(s);
}
U_NAMESPACE_END
#endif