/*
-**********************************************************************
-* Copyright (C) 1999-2003, International Business Machines Corporation and others. All Rights Reserved.
-**********************************************************************
+***************************************************************************
+* Copyright (C) 1999-2013, International Business Machines Corporation
+* and others. All Rights Reserved.
+***************************************************************************
* Date Name Description
* 10/20/99 alan Creation.
-**********************************************************************
+***************************************************************************
*/
#ifndef UNICODESET_H
#define UNICODESET_H
#include "unicode/unifilt.h"
-#include "unicode/utypes.h"
#include "unicode/unistr.h"
-#include "unicode/uchar.h"
#include "unicode/uset.h"
+/**
+ * \file
+ * \brief C++ API: Unicode Set
+ */
+
U_NAMESPACE_BEGIN
+// Forward Declarations.
+void U_CALLCONV UnicodeSet_initInclusion(int32_t src, UErrorCode &status); /**< @internal */
+
+class BMPSet;
class ParsePosition;
+class RBBIRuleScanner;
class SymbolTable;
+class UnicodeSetStringSpan;
class UVector;
-class CaseEquivClass;
+class RuleCharacterIterator;
-
/**
* A mutable set of Unicode characters and multicharacter strings. Objects of this class
* represent <em>character classes</em> used in regular expressions.
* similar to that employed by version 8 regular expression character
* classes. Here are some simple examples:
*
- * <blockquote>
+ * \htmlonly<blockquote>\endhtmlonly
* <table>
* <tr align="top">
* <td nowrap valign="top" align="left"><code>[]</code></td>
* </tr>
* <tr>
* <td nowrap valign="top" align="left"><code>[a-e]</code></td>
- * <td valign="top">The characters 'a' through 'e' inclusive, in Unicode code
+ * <td valign="top">The characters 'a' through 'e' inclusive, in Unicode code
* point order</td>
* </tr>
* <tr>
- * <td nowrap valign="top" align="left"><code>[\u4E01]</code></td>
+ * <td nowrap valign="top" align="left"><code>[\\u4E01]</code></td>
* <td valign="top">The character U+4E01</td>
* </tr>
* <tr>
* <td nowrap valign="top" align="left"><code>[a{ab}{ac}]</code></td>
- * <td valign="top">The character 'a' and the multicharacter strings "ab" and
+ * <td valign="top">The character 'a' and the multicharacter strings "ab" and
* "ac"</td>
* </tr>
* <tr>
- * <td nowrap valign="top" align="left"><code>[\p{Lu}]</code></td>
+ * <td nowrap valign="top" align="left"><code>[\\p{Lu}]</code></td>
* <td valign="top">All characters in the general category Uppercase Letter</td>
* </tr>
* </table>
- * </blockquote>
- *
+ * \htmlonly</blockquote>\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.
*
* <p>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
+ * "[: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
- * <a href="http://oss.software.ibm.com/icu/userguide/unicodeSet.html">
- * http://oss.software.ibm.com/icu/userguide/unicodeSet.html</a>.
+ * <a href="http://icu-project.org/userguide/unicodeSet.html">
+ * http://icu-project.org/userguide/unicodeSet.html</a>.
* Actual determination of property data is defined by the underlying
* Unicode database as implemented by UCharacter.
*
* 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,
+ * their delimiters; "[:^foo]" and "\\P{foo}". In any other location,
* '^' has no special meaning.
*
* <p>Ranges are indicated by placing two a '-' between two
* 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\u005C-b]", "[-ab]", and "[ab-]" all indicate the same
+ * literal. Thus "[a\-b]", "[-ab]", and "[ab-]" all indicate the same
* set of three characters, 'a', 'b', and '-'.
*
* <p>Sets may be intersected using the '&' operator or the asymmetric
* set difference may be taken using the '-' operator, for example,
- * "[[:L:]&[\u005Cu0000-\u005Cu0FFF]]" indicates the set of all Unicode letters
+ * "[[: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]-[\u005Cu0100-\u005Cu01FF]]" is equivalent to
- * "[[[:L:]-[a-z]]-[\u005Cu0100-\u005Cu01FF]]". This only really matters for
+ * "[[:L:]-[a-z]-[\\u0100-\\u01FF]]" is equivalent to
+ * "[[[:L:]-[a-z]]-[\\u0100-\\u01FF]]". This only really matters for
* difference; intersection is commutative.
*
* <table>
* <tr valign=top><td nowrap><code>[[<em>pat1</em>]-[<em>pat2</em>]]</code>
* <td>The asymmetric difference of sets specified by <em>pat1</em> and
* <em>pat2</em>
- * <tr valign=top><td nowrap><code>[:Lu:] or \p{Lu}</code>
+ * <tr valign=top><td nowrap><code>[:Lu:] or \\p{Lu}</code>
* <td>The set of characters having the specified
* Unicode property; in
* this case, Unicode uppercase letters
- * <tr valign=top><td nowrap><code>[:^Lu:] or \P{Lu}</code>
+ * <tr valign=top><td nowrap><code>[:^Lu:] or \\P{Lu}</code>
* <td>The set of characters <em>not</em> having the given
* Unicode property
* </table>
*
* <p><b>Formal syntax</b></p>
*
- * <blockquote>
+ * \htmlonly<blockquote>\endhtmlonly
* <table>
* <tr align="top">
* <td nowrap valign="top" align="right"><code>pattern := </code></td>
* <td nowrap valign="top" align="right"><code>char := </code></td>
* <td valign="top"><em>any character that is not</em><code> special<br>
* | ('\' </code><em>any character</em><code>)<br>
- * | ('\u' hex hex hex hex)<br>
+ * | ('\\u' hex hex hex hex)<br>
* </code></td>
* </tr>
* <tr align="top">
* </td>
* </tr>
* </table>
- * </blockquote>
+ * \htmlonly</blockquote>\endhtmlonly
+ *
+ * <p>Note:
+ * - Most UnicodeSet methods do not take a UErrorCode parameter because
+ * there are usually very few opportunities for failure other than a shortage
+ * of memory, error codes in low-level C++ string methods would be inconvenient,
+ * and the error code as the last parameter (ICU convention) would prevent
+ * the use of default parameter values.
+ * Instead, such methods set the UnicodeSet into a "bogus" state
+ * (see isBogus()) if an error occurs.
*
* @author Alan Liu
* @stable ICU 2.0
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
+ BMPSet *bmpSet; // The set is frozen iff either bmpSet or stringSpan is not NULL.
UChar32* buffer; // internal buffer, may be NULL
-
- UVector* strings; // maintained in sorted order
+ int32_t bufferCapacity; // capacity of buffer
+ int32_t patLen;
/**
* The pattern representation of this set. This may not be the
* indicating that toPattern() must generate a pattern
* representation from the inversion list.
*/
- UnicodeString pat;
+ UChar *pat;
+ UVector* strings; // maintained in sorted order
+ UnicodeSetStringSpan *stringSpan;
+private:
+ enum { // constants
+ kIsBogus = 1 // This set is bogus (i.e. not valid)
+ };
+ uint8_t fFlags; // Bit flag (see constants above)
public:
-
/**
- * Minimum value that can be stored in a UnicodeSet.
- * @draft ICU 2.4
+ * Determine if this object contains a valid set.
+ * A bogus set has no value. It is different from an empty set.
+ * It can be used to indicate that no set value is available.
+ *
+ * @return TRUE if the set is valid, FALSE otherwise
+ * @see setToBogus()
+ * @stable ICU 4.0
*/
- static const UChar32 MIN_VALUE;
-
+ inline UBool isBogus(void) const;
+
/**
- * Maximum value that can be stored in a UnicodeSet.
- * @draft ICU 2.4
+ * Make this UnicodeSet object invalid.
+ * The string will test TRUE with isBogus().
+ *
+ * A bogus set has no value. It is different from an empty set.
+ * It can be used to indicate that no set value is available.
+ *
+ * This utility function is used throughout the UnicodeSet
+ * implementation to indicate that a UnicodeSet operation failed,
+ * and may be used in other functions,
+ * especially but not exclusively when such functions do not
+ * take a UErrorCode for simplicity.
+ *
+ * @see isBogus()
+ * @stable ICU 4.0
*/
- static const UChar32 MAX_VALUE;
+ void setToBogus();
+
+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
*
* @param start first character, inclusive, of range
* @param end last character, inclusive, of range
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet(UChar32 start, UChar32 end);
UnicodeSet(const UnicodeString& pattern,
UErrorCode& status);
+#ifndef U_HIDE_INTERNAL_API
/**
* 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 <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern
* contains a syntax error.
* @internal
*/
UnicodeSet(const UnicodeString& pattern,
uint32_t options,
+ const SymbolTable* symbols,
UErrorCode& status);
+#endif /* U_HIDE_INTERNAL_API */
-#ifdef U_USE_UNICODESET_DEPRECATES
/**
- * Obsolete: Constructs a set from the given Unicode character category.
- * @param category an integer indicating the character category as
- * defined in uchar.h.
- * @obsolete ICU 2.6. Use a pattern with the category instead since this API will be removed in that release.
+ * 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(int8_t category, UErrorCode& status);
-#endif
+ UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
+ uint32_t options,
+ const SymbolTable* symbols,
+ UErrorCode& status);
/**
* Constructs a set that is identical to the given UnicodeSet.
/**
* Assigns this object to be a copy of another.
+ * A frozen set will not be modified.
* @stable ICU 2.0
*/
UnicodeSet& operator=(const UnicodeSet& o);
* 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.
+ * If this set is frozen, then the clone will be frozen as well.
+ * Use cloneAsThawed() for a mutable clone of a frozen set.
+ * @see cloneAsThawed
* @stable ICU 2.0
*/
virtual UnicodeFunctor* clone() const;
*/
virtual int32_t hashCode(void) const;
+ /**
+ * Get a UnicodeSet pointer from a USet
+ *
+ * @param uset a USet (the ICU plain C type for UnicodeSet)
+ * @return the corresponding UnicodeSet pointer.
+ *
+ * @stable ICU 4.2
+ */
+ inline static UnicodeSet *fromUSet(USet *uset);
+
+ /**
+ * Get a UnicodeSet pointer from a const USet
+ *
+ * @param uset a const USet (the ICU plain C type for UnicodeSet)
+ * @return the corresponding UnicodeSet pointer.
+ *
+ * @stable ICU 4.2
+ */
+ inline static const UnicodeSet *fromUSet(const USet *uset);
+
+ /**
+ * Produce a USet * pointer for this UnicodeSet.
+ * USet is the plain C type for UnicodeSet
+ *
+ * @return a USet pointer for this UnicodeSet
+ * @stable ICU 4.2
+ */
+ inline USet *toUSet();
+
+
+ /**
+ * Produce a const USet * pointer for this UnicodeSet.
+ * USet is the plain C type for UnicodeSet
+ *
+ * @return a const USet pointer for this UnicodeSet
+ * @stable ICU 4.2
+ */
+ inline const USet * toUSet() const;
+
+
+ //----------------------------------------------------------------
+ // Freezable API
+ //----------------------------------------------------------------
+
+ /**
+ * Determines whether the set has been frozen (made immutable) or not.
+ * See the ICU4J Freezable interface for details.
+ * @return TRUE/FALSE for whether the set has been frozen
+ * @see freeze
+ * @see cloneAsThawed
+ * @stable ICU 3.8
+ */
+ inline UBool isFrozen() const;
+
+ /**
+ * Freeze the set (make it immutable).
+ * Once frozen, it cannot be unfrozen and is therefore thread-safe
+ * until it is deleted.
+ * See the ICU4J Freezable interface for details.
+ * Freezing the set may also make some operations faster, for example
+ * contains() and span().
+ * A frozen set will not be modified. (It remains frozen.)
+ * @return this set.
+ * @see isFrozen
+ * @see cloneAsThawed
+ * @stable ICU 3.8
+ */
+ UnicodeFunctor *freeze();
+
+ /**
+ * Clone the set and make the clone mutable.
+ * See the ICU4J Freezable interface for details.
+ * @return the mutable clone
+ * @see freeze
+ * @see isFrozen
+ * @stable ICU 3.8
+ */
+ UnicodeFunctor *cloneAsThawed() const;
+
//----------------------------------------------------------------
// Public API
//----------------------------------------------------------------
* Make this object represent the range <code>start - end</code>.
* If <code>end > start</code> then this object is set to an
* an empty range.
+ * A frozen set will not be modified.
*
* @param start first character in the set, inclusive
* @param end last character in the set, inclusive
- * @draft ICU 2.4
+ * @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.
- * @draft ICU 2.4
+ * @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.
+ * pattern, ignoring Unicode Pattern_White_Space characters.
+ * See the class description for the syntax of the pattern language.
+ * A frozen set will not be modified.
* @param pattern a string specifying what characters are in the set
* @param status returns <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern
* contains a syntax error.
+ * <em> Empties the set passed before applying the pattern.</em>
+ * @return a reference to this
* @stable ICU 2.0
*/
- virtual UnicodeSet& applyPattern(const UnicodeString& pattern,
- UErrorCode& status);
+ UnicodeSet& applyPattern(const UnicodeString& pattern,
+ UErrorCode& status);
+#ifndef U_HIDE_INTERNAL_API
/**
* 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.
+ * pattern, optionally ignoring Unicode Pattern_White_Space characters.
+ * See the class description for the syntax of the pattern language.
+ * A frozen set will not be modified.
* @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 <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern
* contains a syntax error.
+ *<em> Empties the set passed before applying the pattern.</em>
+ * @return a reference to this
* @internal
*/
UnicodeSet& applyPattern(const UnicodeString& pattern,
uint32_t options,
+ const SymbolTable* symbols,
+ UErrorCode& status);
+#endif /* U_HIDE_INTERNAL_API */
+
+ /**
+ * 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.
+ *<em> Empties the set passed before applying the pattern.</em>
+ * A frozen set will not be modified.
+ *
+ * @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 <code>U_ILLEGAL_ARGUMENT_ERROR</code> 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.
+ * A frozen set will not be modified.
* @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
+ * 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;
+ 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.
+ * A frozen set will not be modified.
*
* @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1
* or UCHAR_INT_START..UCHAR_INT_LIMIT-1
*
* @return a reference to this set
*
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& applyIntPropertyValue(UProperty prop,
int32_t value,
* Modifies this set to contain those code points which have the
* given value for the given property. Prior contents of this
* set are lost.
+ * A frozen set will not be modified.
*
* @param prop a property alias, either short or long. The name is matched
* loosely. See PropertyAliases.txt for names and a description of loose
* property alias, or a special ID. Special IDs are matched loosely and
* correspond to the following sets:
*
- * "ANY" = [\u0000-\U0010FFFF],
- * "ASCII" = [\u0000-\u007F].
+ * "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
*
* @return a reference to this set
*
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& applyPropertyAlias(const UnicodeString& prop,
const UnicodeString& value,
UErrorCode& ec);
/**
- * Returns the number of elements in this set (its cardinality),
- * <em>n</em>, where <code>0 <= </code><em>n</em><code> <= 65536</code>.
+ * 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
/**
* Returns true if this set contains the given character.
+ * This function works faster with a frozen set.
* @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.
* multicharacter string.
* @param s string to be checked for containment
* @return <tt>true</tt> if this set contains the specified string
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UBool containsNone(UChar32 start, UChar32 end) const;
* of the given set.
* @param c set to be checked for containment
* @return true if the test condition is met
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @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
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
inline UBool containsSome(const UnicodeString& s) const;
-
+
+ /**
+ * Returns the length of the initial substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Similar to the strspn() C library function.
+ * Unpaired surrogates are treated according to contains() of their surrogate code points.
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param s start of the string
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the length of the initial substring according to the spanCondition;
+ * 0 if the start of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+ int32_t span(const UChar *s, int32_t length, USetSpanCondition spanCondition) const;
+
+ /**
+ * Returns the end of the substring of the input string according to the USetSpanCondition.
+ * Same as <code>start+span(s.getBuffer()+start, s.length()-start, spanCondition)</code>
+ * after pinning start to 0<=start<=s.length().
+ * @param s the string
+ * @param start the start index in the string for the span operation
+ * @param spanCondition specifies the containment condition
+ * @return the exclusive end of the substring according to the spanCondition;
+ * the substring s.tempSubStringBetween(start, end) fulfills the spanCondition
+ * @stable ICU 4.4
+ * @see USetSpanCondition
+ */
+ inline int32_t span(const UnicodeString &s, int32_t start, USetSpanCondition spanCondition) const;
+
+ /**
+ * Returns the start of the trailing substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Unpaired surrogates are treated according to contains() of their surrogate code points.
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param s start of the string
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the start of the trailing substring according to the spanCondition;
+ * the string length if the end of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+ int32_t spanBack(const UChar *s, int32_t length, USetSpanCondition spanCondition) const;
+
+ /**
+ * Returns the start of the substring of the input string according to the USetSpanCondition.
+ * Same as <code>spanBack(s.getBuffer(), limit, spanCondition)</code>
+ * after pinning limit to 0<=end<=s.length().
+ * @param s the string
+ * @param limit the exclusive-end index in the string for the span operation
+ * (use s.length() or INT32_MAX for spanning back from the end of the string)
+ * @param spanCondition specifies the containment condition
+ * @return the start of the substring according to the spanCondition;
+ * the substring s.tempSubStringBetween(start, limit) fulfills the spanCondition
+ * @stable ICU 4.4
+ * @see USetSpanCondition
+ */
+ inline int32_t spanBack(const UnicodeString &s, int32_t limit, USetSpanCondition spanCondition) const;
+
+ /**
+ * Returns the length of the initial substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Similar to the strspn() C library function.
+ * Malformed byte sequences are treated according to contains(0xfffd).
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param s start of the string (UTF-8)
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the length of the initial substring according to the spanCondition;
+ * 0 if the start of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+ int32_t spanUTF8(const char *s, int32_t length, USetSpanCondition spanCondition) const;
+
+ /**
+ * Returns the start of the trailing substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Malformed byte sequences are treated according to contains(0xfffd).
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param s start of the string (UTF-8)
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the start of the trailing substring according to the spanCondition;
+ * the string length if the end of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+ int32_t spanBackUTF8(const char *s, int32_t length, USetSpanCondition spanCondition) const;
+
/**
* Implement UnicodeMatcher::matches()
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
- UMatchDegree matches(const Replaceable& text,
+ virtual UMatchDegree matches(const Replaceable& text,
int32_t& offset,
int32_t limit,
UBool incremental);
- private:
+private:
/**
* Returns the longest match for s in text at the given position.
* If limit > start then match forward from start+1 to limit
* @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.
+ * @param s
* @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
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
*/
int32_t findCodePoint(UChar32 c) const;
- public:
+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
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
- void addMatchSetTo(UnicodeSet& toUnionTo) const;
+ virtual void addMatchSetTo(UnicodeSet& toUnionTo) const;
/**
* Returns the index of the given character within this set, where
* is not in this set, return -1. The inverse of this method is
* <code>charAt()</code>.
* @return an index from 0..size()-1, or -1
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
int32_t indexOf(UChar32 c) const;
* <code>indexOf()</code>.
* @param index an index from 0..size()-1
* @return the character at the given index, or (UChar32)-1.
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UChar32 charAt(int32_t index) const;
* the call leaves this set unchanged. If <code>end > start</code>
* then an empty range is added, leaving the set unchanged.
* This is equivalent to a boolean logic OR, or a set UNION.
+ * A frozen set will not be modified.
*
* @param start first character, inclusive, of range to be added
* to this set.
* 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.
+ * A frozen set will not be modified.
* @stable ICU 2.0
*/
UnicodeSet& add(UChar32 c);
* the call leaves this set unchanged.
* Thus "ch" => {"ch"}
* <br><b>Warning: you cannot add an empty string ("") to a UnicodeSet.</b>
+ * A frozen set will not be modified.
* @param s the source string
* @return this object, for chaining
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& add(const UnicodeString& s);
- private:
+ private:
/**
* @return a code point IF the string consists of a single one.
* otherwise returns -1.
- * @param string to test
+ * @param s string to test
*/
static int32_t getSingleCP(const UnicodeString& s);
void _add(const UnicodeString& s);
-
+
public:
/**
* Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"}
* If this set already any particular character, it has no effect on that character.
+ * A frozen set will not be modified.
* @param s the source string
* @return this object, for chaining
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& addAll(const UnicodeString& s);
/**
* Retains EACH of the characters in this string. Note: "ch" == {"c", "h"}
* If this set already any particular character, it has no effect on that character.
+ * A frozen set will not be modified.
* @param s the source string
* @return this object, for chaining
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& retainAll(const UnicodeString& s);
/**
* Complement EACH of the characters in this string. Note: "ch" == {"c", "h"}
* If this set already any particular character, it has no effect on that character.
+ * A frozen set will not be modified.
* @param s the source string
* @return this object, for chaining
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& complementAll(const UnicodeString& s);
/**
* Remove EACH of the characters in this string. Note: "ch" == {"c", "h"}
* If this set already any particular character, it has no effect on that character.
+ * A frozen set will not be modified.
* @param s the source string
* @return this object, for chaining
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& removeAll(const UnicodeString& s);
* @param s the source string
* @return a newly created set containing the given string.
* The caller owns the return object and is responsible for deleting it.
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
- static UnicodeSet* createFrom(const UnicodeString& s);
+ static UnicodeSet* U_EXPORT2 createFrom(const UnicodeString& s);
+
-
/**
* Makes a set from each of the characters in the string. Thus "ch" => {"c", "h"}
* @param s the source string
* @return a newly created set containing the given characters
* The caller owns the return object and is responsible for deleting it.
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
- static UnicodeSet* createFromAll(const UnicodeString& s);
+ static UnicodeSet* U_EXPORT2 createFromAll(const UnicodeString& s);
/**
* Retain only the elements in this set that are contained in the
* specified range. If <code>end > start</code> then an empty range is
* retained, leaving the set empty. This is equivalent to
* a boolean logic AND, or a set INTERSECTION.
+ * A frozen set will not be modified.
*
* @param start first character, inclusive, of range to be retained
* to this set.
/**
* Retain the specified character from this set if it is present.
+ * A frozen set will not be modified.
* @stable ICU 2.0
*/
UnicodeSet& retain(UChar32 c);
* The set will not contain the specified range once the call
* returns. If <code>end > start</code> then an empty range is
* removed, leaving the set unchanged.
+ * A frozen set will not be modified.
*
* @param start first character, inclusive, of range to be removed
* from this set.
* Removes the specified character from this set if it is present.
* The set will not contain the specified range once the call
* returns.
+ * A frozen set will not be modified.
* @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.
+ * A frozen set will not be modified.
* @param s the source string
* @return this object, for chaining
- * @draft ICU 2.4
+ * @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
* <code>complement(MIN_VALUE, MAX_VALUE)</code>.
+ * A frozen set will not be modified.
* @stable ICU 2.0
*/
virtual UnicodeSet& complement(void);
* added if it is not in this set. If <code>end > start</code>
* then an empty range is complemented, leaving the set unchanged.
* This is equivalent to a boolean logic XOR.
+ * A frozen set will not be modified.
*
* @param start first character, inclusive, of range to be removed
* from this set.
* 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.
+ * A frozen set will not be modified.
* @stable ICU 2.0
*/
UnicodeSet& complement(UChar32 c);
* The set will not contain the specified string once the call
* returns.
* <br><b>Warning: you cannot add an empty string ("") to a UnicodeSet.</b>
+ * A frozen set will not be modified.
* @param s the string to complement
* @return this object, for chaining
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
UnicodeSet& complement(const UnicodeString& s);
* modifies this set so that its value is the <i>union</i> of the two
* sets. The behavior of this operation is unspecified if the specified
* collection is modified while the operation is in progress.
+ * A frozen set will not be modified.
*
* @param c set whose elements are to be added to this set.
- * @see #add(char, char)
+ * @see #add(UChar32, UChar32)
* @stable ICU 2.0
*/
virtual UnicodeSet& addAll(const UnicodeSet& c);
* its elements that are not contained in the specified set. This
* operation effectively modifies this set so that its value is
* the <i>intersection</i> of the two sets.
+ * A frozen set will not be modified.
*
* @param c set that defines which elements this set will retain.
* @stable ICU 2.0
* specified set. This operation effectively modifies this
* set so that its value is the <i>asymmetric set difference</i> of
* the two sets.
+ * A frozen set will not be modified.
*
* @param c set that defines which elements will be removed from
* this set.
* Complements in this set all elements contained in the specified
* set. Any character in the other set will be removed if it is
* in this set, or will be added if it is not in this set.
+ * A frozen set will not be modified.
*
* @param c set that defines which elements will be xor'ed from
* this set.
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
virtual UnicodeSet& complementAll(const UnicodeSet& c);
/**
* Removes all of the elements from this set. This set will be
* empty after this call returns.
+ * A frozen set will not be modified.
* @stable ICU 2.0
*/
virtual UnicodeSet& clear(void);
* 2. For each string 'e' in the resulting set, if e !=
* foldCase(e), 'e' will be removed.
*
- * Example: [aq\u00DF{Bc}{bC}{Fi}] => [aAqQ\u00DF\uFB01{ss}{bc}{fi}]
+ * Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}]
*
* (Here foldCase(x) refers to the operation u_strFoldCase, and a
* == b denotes that the contents are the same, not pointer
* comparison.)
*
+ * A frozen set will not be modified.
+ *
* @param attribute bitmask for attributes to close over.
* Currently only the USET_CASE bit is supported. Any undefined bits
* are ignored.
* @return a reference to this set.
- * @internal
+ * @stable ICU 4.2
*/
UnicodeSet& closeOver(int32_t attribute);
+ /**
+ * Remove all strings from this set.
+ *
+ * @return a reference to this set.
+ * @stable ICU 4.2
+ */
+ virtual UnicodeSet &removeAllStrings();
+
/**
* Iteration method that returns the number of ranges contained in
* this set.
* @see #getRangeStart
* @see #getRangeEnd
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
virtual int32_t getRangeCount(void) const;
* specified range of this set.
* @see #getRangeCount
* @see #getRangeEnd
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
virtual UChar32 getRangeStart(int32_t index) const;
* specified range of this set.
* @see #getRangeStart
* @see #getRangeEnd
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
virtual UChar32 getRangeEnd(int32_t index) const;
* @return the total length of the serialized format, including
* the header, that is, n+2*m+(m!=0?2:1), or 0 on error other
* than U_BUFFER_OVERFLOW_ERROR.
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
int32_t serialize(uint16_t *dest, int32_t destCapacity, UErrorCode& ec) const;
/**
* Reallocate this objects internal structures to take up the least
* possible space, without changing this object's value.
- * @draft ICU 2.4
+ * A frozen set will not be modified.
+ * @stable ICU 2.4
*/
virtual UnicodeSet& compact();
* @return The class ID for all objects of this class.
* @stable ICU 2.0
*/
- static UClassID getStaticClassID(void);
+ 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.
- * @draft ICU 2.4
+ * @stable ICU 2.4
*/
virtual UClassID getDynamicClassID(void) const;
const UnicodeString* getString(int32_t index) const;
-private:
-
- static const char fgClassID;
-
//----------------------------------------------------------------
// RuleBasedTransliterator support
//----------------------------------------------------------------
- friend class TransliteratorParser;
- friend class TransliteratorIDParser;
-
- friend class RBBIRuleScanner;
- friend class RegexCompile;
-
- /**
- * 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 varNameToChar a mapping from variable names (String) to characters
- * (Character). May be null. If varCharToSet is non-null, then names may
- * map to either single characters or sets, depending on whether a mapping
- * exists in varCharToSet. If varCharToSet is null then all names map to
- * single characters.
- * @param varCharToSet a mapping from characters (Character objects from
- * varNameToChar) to UnicodeSet objects. May be null. Is only used if
- * varNameToChar is also non-null.
- * @exception <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern
- * contains a syntax error.
- */
- UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
- const SymbolTable& symbols,
- UErrorCode& status);
-
- /**
- * Constructs a set from the given pattern. Identical to the
- * 4-parameter ParsePosition contstructor, but does not take a
- * SymbolTable, and does not recognize embedded variables.
- */
- UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
- uint32_t options, UErrorCode& status);
+private:
/**
* Returns <tt>true</tt> if this set contains any character whose low byte
virtual UBool matchesIndexValue(uint8_t v) const;
private:
+ friend class RBBIRuleScanner;
+
+ //----------------------------------------------------------------
+ // Implementation: Clone as thawed (see ICU4J Freezable)
+ //----------------------------------------------------------------
+
+ UnicodeSet(const UnicodeSet& o, UBool /* asThawed */);
//----------------------------------------------------------------
// Implementation: Pattern parsing
//----------------------------------------------------------------
- /**
- * 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.
- *
- * @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.
- * @return a StringBuffer containing a pairs list for the parsed
- * substring of <code>pattern</code>
- * @exception U_ILLEGAL_ARGUMENT_ERROR if the parse fails.
- */
- void applyPattern(const UnicodeString& pattern,
- ParsePosition& pos,
- uint32_t options,
+ void applyPatternIgnoreSpace(const UnicodeString& pattern,
+ ParsePosition& pos,
+ const SymbolTable* symbols,
+ UErrorCode& status);
+
+ void applyPattern(RuleCharacterIterator& chars,
const SymbolTable* symbols,
- UErrorCode& status);
+ UnicodeString& rebuiltPat,
+ uint32_t options,
+ UnicodeSet& (UnicodeSet::*caseClosure)(int32_t attribute),
+ UErrorCode& ec);
//----------------------------------------------------------------
// Implementation: Utility methods
//----------------------------------------------------------------
- void ensureCapacity(int32_t newLen);
+ void ensureCapacity(int32_t newLen, UErrorCode& ec);
- void ensureBufferCapacity(int32_t newLen);
+ void ensureBufferCapacity(int32_t newLen, UErrorCode& ec);
void swapBuffers(void);
- UBool allocateStrings();
-
- void _applyPattern(const UnicodeString& pattern,
- ParsePosition& pos,
- uint32_t options,
- const SymbolTable* symbols,
- UnicodeString& rebuiltPat,
- UErrorCode& status);
+ UBool allocateStrings(UErrorCode &status);
UnicodeString& _toPattern(UnicodeString& result,
UBool escapeUnprintable) const;
/**
* 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}.
+ * 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://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/unicodeset_properties.html
+ * http://source.icu-project.org/repos/icu/icuhtml/trunk/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"
+ * \\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
+ * Other than the above restrictions, Unicode Pattern_White_Space characters are 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.
*
* @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}
+ * [: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.
+ * @param ec status
* @return a reference to this.
*/
UnicodeSet& applyPropertyPattern(const UnicodeString& pattern,
ParsePosition& ppos,
UErrorCode &ec);
+ void applyPropertyPattern(RuleCharacterIterator& chars,
+ UnicodeString& rebuiltPat,
+ UErrorCode& ec);
+
+ friend void U_CALLCONV UnicodeSet_initInclusion(int32_t src, UErrorCode &status);
+ static const UnicodeSet* getInclusions(int32_t src, UErrorCode &status);
+
/**
* A filter that returns TRUE if the given code point should be
* included in the UnicodeSet being constructed.
* 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
- * uprv_getInclusions().
+ * 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 that
- * uprv_getInclusions() produces.
+ * Set the new pattern to cache.
*/
- static const UnicodeSet* getInclusions(UErrorCode &errorCode);
+ void setPattern(const UnicodeString& newPat);
+ /**
+ * Release existing cached pattern.
+ */
+ void releasePattern();
friend class UnicodeSetIterator;
-
- //----------------------------------------------------------------
- // Implementation: closeOver
- //----------------------------------------------------------------
-
- void caseCloseOne(const UnicodeString& folded);
-
- void caseCloseOne(const CaseEquivClass& c);
-
- void caseCloseOne(UChar folded);
-
- static const CaseEquivClass* getCaseMapOf(const UnicodeString& folded);
-
- static const CaseEquivClass* getCaseMapOf(UChar folded);
};
-inline UClassID
-UnicodeSet::getStaticClassID(void)
-{ return (UClassID)&fgClassID; }
-inline UClassID
-UnicodeSet::getDynamicClassID(void) const
-{ return UnicodeSet::getStaticClassID(); }
inline UBool UnicodeSet::operator!=(const UnicodeSet& o) const {
return !operator==(o);
}
+inline UBool UnicodeSet::isFrozen() const {
+ return (UBool)(bmpSet!=NULL || stringSpan!=NULL);
+}
+
inline UBool UnicodeSet::containsSome(UChar32 start, UChar32 end) const {
return !containsNone(start, end);
}
return !containsNone(s);
}
+inline UBool UnicodeSet::isBogus() const {
+ return (UBool)(fFlags & kIsBogus);
+}
+
+inline UnicodeSet *UnicodeSet::fromUSet(USet *uset) {
+ return reinterpret_cast<UnicodeSet *>(uset);
+}
+
+inline const UnicodeSet *UnicodeSet::fromUSet(const USet *uset) {
+ return reinterpret_cast<const UnicodeSet *>(uset);
+}
+
+inline USet *UnicodeSet::toUSet() {
+ return reinterpret_cast<USet *>(this);
+}
+
+inline const USet *UnicodeSet::toUSet() const {
+ return reinterpret_cast<const USet *>(this);
+}
+
+inline int32_t UnicodeSet::span(const UnicodeString &s, int32_t start, USetSpanCondition spanCondition) const {
+ int32_t sLength=s.length();
+ if(start<0) {
+ start=0;
+ } else if(start>sLength) {
+ start=sLength;
+ }
+ return start+span(s.getBuffer()+start, sLength-start, spanCondition);
+}
+
+inline int32_t UnicodeSet::spanBack(const UnicodeString &s, int32_t limit, USetSpanCondition spanCondition) const {
+ int32_t sLength=s.length();
+ if(limit<0) {
+ limit=0;
+ } else if(limit>sLength) {
+ limit=sLength;
+ }
+ return spanBack(s.getBuffer(), limit, spanCondition);
+}
+
U_NAMESPACE_END
#endif
projects / apple / icu.git / blobdiff