/* ********************************************************************** * Copyright (C) 1999, 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" U_NAMESPACE_BEGIN class ParsePosition; class SymbolTable; class TransliterationRuleParser; class TransliterationRule; class Transliterator; class TransliteratorParser; /** * A mutable set of Unicode characters. Objects of this class * represent character classes used in regular expressions. * Such classes specify a subset of the set of all Unicode characters, * which in this implementation is the characters from U+0000 to * U+FFFF, ignoring surrogates. * *
This class supports two APIs. The first is modeled after Java 2's
* java.util.Set
interface, although this class does not
* 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 second API is the
* applyPattern()
/toPattern()
API from the
* 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.
*
*
In addition, the set complement operation is supported through
* the complement()
method.
*
*
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:
*
* ** * Any character may be preceded by a backslash in order to remove any special * meaning. White space characters, as defined by Character.isWhitespace(), are * ignored, unless they are escaped. * * Patterns specify individual characters, ranges of characters, and * Unicode character categories. When elements are concatenated, they * specify their union. To complement a set, place a '^' immediately * after the opening '[' or '[:'. In any other location, '^' has no * special meaning. * **
** ** pattern :=
* ('[' '^'? item* ']') | * ('[:' '^'? category ':]')
* ** item :=
* char | (char '-' char) | pattern-expr
** ** pattern-expr :=
* pattern | pattern-expr pattern | * pattern-expr op pattern
** ** op :=
* '&' | '-'
** ** special :=
* '[' | ']' | '-'
** ** char :=
any character that is not *special
any character
* | ('\u005C')
* | ('\u005Cu' hex hex hex hex)
** ** hex :=
any character for which * *Character.digit(c, 16)
* returns a non-negative result* ** category :=
* 'M' | 'N' | 'Z' | 'C' | 'L' | 'P' | * 'S' | 'Mn' | 'Mc' | 'Me' | 'Nd' | 'Nl' | 'No' | 'Zs' | 'Zl' | * 'Zp' | 'Cc' | 'Cf' | 'Cs' | 'Co' | 'Cn' | 'Lu' | 'Ll' | 'Lt' * | 'Lm' | 'Lo' | 'Pc' | 'Pd' | 'Ps' | 'Pe' | 'Po' | 'Sm' | * 'Sc' | 'Sk' | 'So'
**
** *Legend: **
** ** a := b
* * a
may be replaced byb
* ** a?
* zero or one instance of *a
** ** a*
* one or more instances of *a
** ** a | b
* either *a
orb
** ** 'a'
* the literal string between the quotes *
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 and right characters are the same, then the range consists of * just that character. If the left character is greater than 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+FFFF * |
[[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:]
* | The set of characters belonging to the given
* Unicode category, as defined by Character.getType() ; in
* this case, Unicode uppercase letters
* |
[:L:]
* | The set of characters belonging to all Unicode categories
* starting wih 'L', that is, [[:Lu:][:Ll:][:Lt:][:Lm:][:Lo:]] .
* |
Character categories.
*
* Character categories are specified using the POSIX-like syntax
* '[:Lu:]'. The complement of a category is specified by inserting
* '^' after the opening '[:'. The following category names are
* recognized. Actual determination of category data uses
* Unicode::getType()
, so it reflects the underlying
* data used by Unicode
.
*
*
* Normative * Mn = Mark, Non-Spacing * Mc = Mark, Spacing Combining * Me = Mark, Enclosing * * Nd = Number, Decimal Digit * Nl = Number, Letter * No = Number, Other * * Zs = Separator, Space * Zl = Separator, Line * Zp = Separator, Paragraph * * Cc = Other, Control * Cf = Other, Format * Cs = Other, Surrogate * Co = Other, Private Use * Cn = Other, Not Assigned * * Informative * Lu = Letter, Uppercase * Ll = Letter, Lowercase * Lt = Letter, Titlecase * Lm = Letter, Modifier * Lo = Letter, Other * * Pc = Punctuation, Connector * Pd = Punctuation, Dash * Ps = Punctuation, Open * Pe = Punctuation, Close * Pi = Punctuation, Initial quote * Pf = Punctuation, Final quote * Po = Punctuation, Other * * Sm = Symbol, Math * Sc = Symbol, Currency * Sk = Symbol, Modifier * So = Symbol, Other ** * @author Alan Liu * @draft */ class U_I18N_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 /** * 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: /** * Minimum value that can be stored in a UnicodeSet. */ static const UChar32 MIN_VALUE; /** * Maximum value that can be stored in a UnicodeSet. */ static const UChar32 MAX_VALUE; //---------------------------------------------------------------- // Constructors &c //---------------------------------------------------------------- public: /** * Constructs an empty set. * @draft */ UnicodeSet(); /** * Constructs a set containing the given range. If
end >
* start
then an empty set is created.
*
* @param start first character, inclusive, of range
* @param end last character, inclusive, of range
*/
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
* @exception IllegalArgumentException
if the pattern
* contains a syntax error.
* @draft
*/
UnicodeSet(const UnicodeString& pattern,
UErrorCode& status);
/**
* Constructs a set from the given Unicode character category.
* @param category an integer indicating the character category as
* returned by Character.getType()
.
* @exception IllegalArgumentException
if the given
* category is invalid.
* @draft
*/
UnicodeSet(int8_t category, UErrorCode& status);
/**
* Constructs a set that is identical to the given UnicodeSet.
* @draft
*/
UnicodeSet(const UnicodeSet& o);
/**
* Destructs the set.
* @draft
*/
virtual ~UnicodeSet();
/**
* Assigns this object to be a copy of another.
* @draft
*/
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.
* @draft
*/
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.
* @draft
*/
UBool operator!=(const UnicodeSet& o) const;
/**
* Returns a copy of this object. All UnicodeMatcher objects have
* to support cloning in order to allow classes using
* UnicodeMatchers, such as Transliterator, to implement cloning.
* @draft
*/
virtual UnicodeMatcher* clone() const;
/**
* Returns the hash code value for this set.
*
* @return the hash code value for this set.
* @see Object#hashCode()
* @draft
*/
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
* @rparam end last character in the set, inclusive
*/
void set(UChar32 start, UChar32 end);
/**
* 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
* @exception IllegalArgumentException
if the pattern
* contains a syntax error.
* @draft
*/
virtual void applyPattern(const UnicodeString& pattern,
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.
* @draft
*/
virtual UnicodeString& toPattern(UnicodeString& result,
UBool escapeUnprintable = FALSE) const;
/**
* Returns the number of elements in this set (its cardinality),
* n, where 0 <=
n <= 65536
.
*
* @return the number of elements in this set (its cardinality).
* @draft
*/
virtual int32_t size(void) const;
/**
* Returns true if this set contains no elements.
*
* @return true if this set contains no elements.
* @draft
*/
virtual UBool isEmpty(void) const;
/**
* Returns true if this set contains the specified range
* of chars.
*
* @return true if this set contains the specified range
* of chars.
* @draft
*/
virtual UBool contains(UChar32 start, UChar32 end) const;
/**
* Returns true if this set contains the specified char.
*
* @return true if this set contains the specified char.
* @draft
*/
virtual UBool contains(UChar32 c) const;
/**
* Implement UnicodeMatcher::matches()
*/
UMatchDegree matches(const Replaceable& text,
int32_t& offset,
int32_t limit,
UBool incremental) 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.
* @draft
*/
virtual void 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.
* @draft
*/
void add(UChar32 c);
/**
* Retain only the elements in this set that are contained in the
* specified range. If 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.
*/
virtual void retain(UChar32 start, UChar32 end);
/**
* Retain the specified character from this set if it is present.
*/
void 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.
* @draft
*/
virtual void 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.
* @draft
*/
void remove(UChar32 c);
/**
* Inverts this set. This operation modifies this set so that
* its value is its complement. This is equivalent to
* complement(MIN_VALUE, MAX_VALUE)
.
* @draft
*/
virtual void 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.
*/
virtual void 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.
*/
void complement(UChar32 c);
/**
* Returns true if the specified set is a subset
* of this set.
*
* @param c set to be checked for containment in this set.
* @return true if this set contains all of the elements of the
* specified set.
* @draft
*/
virtual UBool containsAll(const UnicodeSet& c) const;
/**
* Adds all of the elements in the specified set to this set if
* they're not already present. This operation effectively
* modifies this set so that its value is the union of the two
* sets. The behavior of this operation is unspecified if the specified
* collection is modified while the operation is in progress.
*
* @param c set whose elements are to be added to this set.
* @see #add(char, char)
* @draft
*/
virtual void addAll(const UnicodeSet& c);
/**
* Retains only the elements in this set that are contained in the
* specified set. In other words, removes from this set all of
* its elements that are not contained in the specified set. This
* operation effectively modifies this set so that its value is
* the intersection of the two sets.
*
* @param c set that defines which elements this set will retain.
* @draft
*/
virtual void retainAll(const UnicodeSet& c);
/**
* Removes from this set all of its elements that are contained in the
* specified set. This operation effectively modifies this
* set so that its value is the asymmetric set difference of
* the two sets.
*
* @param c set that defines which elements will be removed from
* this set.
* @draft
*/
virtual void removeAll(const UnicodeSet& c);
/**
* 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.
*
* @param c set that defines which elements will be xor'ed from
* this set.
*/
virtual void complementAll(const UnicodeSet& c);
/**
* Removes all of the elements from this set. This set will be
* empty after this call returns.
* @draft
*/
virtual void clear(void);
/**
* Iteration method that returns the number of ranges contained in
* this set.
* @see #getRangeStart
* @see #getRangeEnd
*/
virtual int32_t getRangeCount(void) const;
/**
* Iteration method that returns the first character in the
* specified range of this set.
* @see #getRangeCount
* @see #getRangeEnd
*/
virtual UChar32 getRangeStart(int32_t index) const;
/**
* Iteration method that returns the last character in the
* specified range of this set.
* @see #getRangeStart
* @see #getRangeEnd
*/
virtual UChar32 getRangeEnd(int32_t index) const;
/**
* Reallocate this objects internal structures to take up the least
* possible space, without changing this object's value.
*/
virtual void compact();
private:
//----------------------------------------------------------------
// RuleBasedTransliterator support
//----------------------------------------------------------------
friend class Transliterator;
friend class TransliteratorParser;
friend class TransliterationRule;
/**
* 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 IllegalArgumentException
if the pattern
* contains a syntax error.
*/
UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
const SymbolTable& symbols,
UErrorCode& status);
/**
* 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
//----------------------------------------------------------------
/**
* 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 pattern
* @exception IllegalArgumentException if the parse fails.
*/
void applyPattern(const UnicodeString& pattern,
ParsePosition& pos,
const SymbolTable* symbols,
UErrorCode& status);
//----------------------------------------------------------------
// Implementation: Generation of pairs for Unicode categories
//----------------------------------------------------------------
/**
* Sets this object to the given category, given its name.
* The category name must be either a two-letter name, such as
* "Lu", or a one letter name, such as "L". One-letter names
* indicate the logical union of all two-letter names that start
* with that letter. Case is significant. If the name starts
* with the character '^' then the complement of the given
* character set is returned.
*
* Although individual categories such as "Lu" are cached, we do
* not currently cache single-letter categories such as "L" or
* complements such as "^Lu" or "^L". It would be easy to cache
* these as well in a hashtable should the need arise.
*/
void applyCategory(const UnicodeString& catName,
UErrorCode& status);
/**
* Returns a pairs string for the given category. This string is
* cached and returned again if this method is called again with
* the same parameter.
*/
static const UnicodeSet& getCategorySet(int8_t cat);
//----------------------------------------------------------------
// Implementation: Utility methods
//----------------------------------------------------------------
void ensureCapacity(int32_t newLen);
void ensureBufferCapacity(int32_t newLen);
void swapBuffers(void);
void _applyPattern(const UnicodeString& pattern,
ParsePosition& pos,
const SymbolTable* symbols,
UnicodeString& rebuiltPat,
UErrorCode& status);
UnicodeString& _toPattern(UnicodeString& result,
UBool escapeUnprintable) const;
UnicodeString& _generatePattern(UnicodeString& result,
UBool escapeUnprintable) const;
static void _appendToPat(UnicodeString& buf, UChar32 c, UBool escapeUnprintable);
static UBool _isUnprintable(UChar32 c);
static UBool _escapeUnprintable(UnicodeString& result, UChar32 c);
//----------------------------------------------------------------
// 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);
};
inline UBool UnicodeSet::operator!=(const UnicodeSet& o) const {
return !operator==(o);
}
U_NAMESPACE_END
#endif