1999-12-28 23:57:50 +00:00
|
|
|
/*
|
|
|
|
**********************************************************************
|
2001-03-22 00:09:10 +00:00
|
|
|
* Copyright (C) 1999, International Business Machines Corporation and others. All Rights Reserved.
|
1999-12-28 23:57:50 +00:00
|
|
|
**********************************************************************
|
|
|
|
* Date Name Description
|
|
|
|
* 10/20/99 alan Creation.
|
|
|
|
**********************************************************************
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef UNICODESET_H
|
|
|
|
#define UNICODESET_H
|
|
|
|
|
2000-01-18 20:00:56 +00:00
|
|
|
#include "unicode/unifilt.h"
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/utypes.h"
|
|
|
|
#include "unicode/unistr.h"
|
|
|
|
|
2001-10-08 23:26:58 +00:00
|
|
|
U_NAMESPACE_BEGIN
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
class ParsePosition;
|
2000-02-08 02:49:15 +00:00
|
|
|
class SymbolTable;
|
2000-01-18 19:57:46 +00:00
|
|
|
class TransliterationRuleParser;
|
|
|
|
class TransliterationRule;
|
2001-10-08 23:26:58 +00:00
|
|
|
class Transliterator;
|
|
|
|
class TransliteratorParser;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* A mutable set of Unicode characters. Objects of this class
|
|
|
|
* represent <em>character classes</em> 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.
|
|
|
|
*
|
|
|
|
* <p>This class supports two APIs. The first is modeled after Java 2's
|
|
|
|
* <code>java.util.Set</code> interface, although this class does not
|
|
|
|
* implement that interface. All methods of <code>Set</code> are
|
|
|
|
* supported, with the modification that they take a character range
|
|
|
|
* or single character instead of an <code>Object</code>, and they
|
|
|
|
* take a <code>UnicodeSet</code> instead of a <code>Collection</code>.
|
|
|
|
*
|
|
|
|
* <p>The second API is the
|
|
|
|
* <code>applyPattern()</code>/<code>toPattern()</code> API from the
|
|
|
|
* <code>Format</code>-derived classes. Unlike the
|
|
|
|
* methods that add characters, add categories, and control the logic
|
|
|
|
* of the set, the method <code>applyPattern()</code> sets all
|
|
|
|
* attributes of a <code>UnicodeSet</code> at once, based on a
|
|
|
|
* string pattern.
|
|
|
|
*
|
|
|
|
* <p>In addition, the set complement operation is supported through
|
|
|
|
* the <code>complement()</code> method.
|
|
|
|
*
|
|
|
|
* <p><b>Pattern syntax</b></p>
|
|
|
|
*
|
|
|
|
* Patterns are accepted by the constructors and the
|
|
|
|
* <code>applyPattern()</code> methods and returned by the
|
|
|
|
* <code>toPattern()</code> method. These patterns follow a syntax
|
|
|
|
* similar to that employed by version 8 regular expression character
|
|
|
|
* classes:
|
|
|
|
*
|
2000-01-13 07:28:31 +00:00
|
|
|
* <blockquote>
|
|
|
|
* <table>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>pattern := </code></td>
|
|
|
|
* <td valign="top"><code>('[' '^'? item* ']') |
|
|
|
|
* ('[:' '^'? category ':]')</code></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>item := </code></td>
|
|
|
|
* <td valign="top"><code>char | (char '-' char) | pattern-expr<br>
|
|
|
|
* </code></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>pattern-expr := </code></td>
|
|
|
|
* <td valign="top"><code>pattern | pattern-expr pattern |
|
|
|
|
* pattern-expr op pattern<br>
|
|
|
|
* </code></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>op := </code></td>
|
|
|
|
* <td valign="top"><code>'&' | '-'<br>
|
|
|
|
* </code></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>special := </code></td>
|
|
|
|
* <td valign="top"><code>'[' | ']' | '-'<br>
|
|
|
|
* </code></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>char := </code></td>
|
|
|
|
* <td valign="top"><em>any character that is not</em><code> special<br>
|
|
|
|
* | ('\u005C' </code><em>any character</em><code>)<br>
|
|
|
|
* | ('\u005Cu' hex hex hex hex)<br>
|
|
|
|
* </code></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr align="top">
|
|
|
|
* <td nowrap valign="top" align="right"><code>hex := </code></td>
|
|
|
|
* <td valign="top"><em>any character for which
|
|
|
|
* </em><code>Character.digit(c, 16)</code><em>
|
|
|
|
* returns a non-negative result</em></td>
|
|
|
|
* </tr>
|
|
|
|
* <tr>
|
|
|
|
* <td nowrap valign="top" align="right"><code>category := </code></td>
|
|
|
|
* <td valign="top"><code>'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'</code></td>
|
|
|
|
* </tr>
|
|
|
|
* </table>
|
|
|
|
* <br>
|
|
|
|
* <table border="1">
|
|
|
|
* <tr>
|
|
|
|
* <td>Legend: <table>
|
|
|
|
* <tr>
|
|
|
|
* <td nowrap valign="top"><code>a := b</code></td>
|
|
|
|
* <td width="20" valign="top"> </td>
|
|
|
|
* <td valign="top"><code>a</code> may be replaced by <code>b</code> </td>
|
|
|
|
* </tr>
|
|
|
|
* <tr>
|
|
|
|
* <td nowrap valign="top"><code>a?</code></td>
|
|
|
|
* <td valign="top"></td>
|
|
|
|
* <td valign="top">zero or one instance of <code>a</code><br>
|
|
|
|
* </td>
|
|
|
|
* </tr>
|
|
|
|
* <tr>
|
|
|
|
* <td nowrap valign="top"><code>a*</code></td>
|
|
|
|
* <td valign="top"></td>
|
|
|
|
* <td valign="top">one or more instances of <code>a</code><br>
|
|
|
|
* </td>
|
|
|
|
* </tr>
|
|
|
|
* <tr>
|
|
|
|
* <td nowrap valign="top"><code>a | b</code></td>
|
|
|
|
* <td valign="top"></td>
|
|
|
|
* <td valign="top">either <code>a</code> or <code>b</code><br>
|
|
|
|
* </td>
|
|
|
|
* </tr>
|
|
|
|
* <tr>
|
|
|
|
* <td nowrap valign="top"><code>'a'</code></td>
|
|
|
|
* <td valign="top"></td>
|
|
|
|
* <td valign="top">the literal string between the quotes </td>
|
|
|
|
* </tr>
|
|
|
|
* </table>
|
|
|
|
* </td>
|
|
|
|
* </tr>
|
|
|
|
* </table>
|
1999-12-28 23:57:50 +00:00
|
|
|
* </blockquote>
|
|
|
|
*
|
2000-01-13 07:28:31 +00:00
|
|
|
* 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.
|
|
|
|
*
|
1999-12-28 23:57:50 +00:00
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
* <p>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 '-'.
|
|
|
|
*
|
|
|
|
* <p>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.
|
|
|
|
*
|
|
|
|
* <table>
|
|
|
|
* <tr valign=top><td nowrap><code>[a]</code><td>The set containing 'a'
|
|
|
|
* <tr valign=top><td nowrap><code>[a-z]</code><td>The set containing 'a'
|
|
|
|
* through 'z' and all letters in between, in Unicode order
|
|
|
|
* <tr valign=top><td nowrap><code>[^a-z]</code><td>The set containing
|
|
|
|
* all characters but 'a' through 'z',
|
|
|
|
* that is, U+0000 through 'a'-1 and 'z'+1 through U+FFFF
|
|
|
|
* <tr valign=top><td nowrap><code>[[<em>pat1</em>][<em>pat2</em>]]</code>
|
|
|
|
* <td>The union of sets specified by <em>pat1</em> and <em>pat2</em>
|
|
|
|
* <tr valign=top><td nowrap><code>[[<em>pat1</em>]&[<em>pat2</em>]]</code>
|
|
|
|
* <td>The intersection of sets specified by <em>pat1</em> and <em>pat2</em>
|
|
|
|
* <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:]</code>
|
|
|
|
* <td>The set of characters belonging to the given
|
|
|
|
* Unicode category, as defined by <code>Character.getType()</code>; in
|
|
|
|
* this case, Unicode uppercase letters
|
|
|
|
* <tr valign=top><td nowrap><code>[:L:]</code>
|
|
|
|
* <td>The set of characters belonging to all Unicode categories
|
|
|
|
* starting wih 'L', that is, <code>[[:Lu:][:Ll:][:Lt:][:Lm:][:Lo:]]</code>.
|
|
|
|
* </table>
|
|
|
|
*
|
|
|
|
* <p><b>Character categories.</b>
|
|
|
|
*
|
2001-10-18 04:06:14 +00:00
|
|
|
* <p>Character properties are specified using the POSIX-like syntax
|
|
|
|
* "[:Lu:]" or the Perl-like syntax "\p{Lu}". The complement of a
|
|
|
|
* category is specified as "[:^Lu:]" or "\P{Lu}". Actual
|
|
|
|
* determination of category data is accomplished by UCharacter using
|
|
|
|
* the underlying Unicode database.
|
1999-12-28 23:57:50 +00:00
|
|
|
*
|
2001-10-18 04:06:14 +00:00
|
|
|
* <p>For details of the property syntax please see this
|
|
|
|
* <a href="http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/unicodeset_properties.html">
|
|
|
|
* draft document</a>.
|
2001-03-22 00:09:10 +00:00
|
|
|
*
|
2001-10-18 04:06:14 +00:00
|
|
|
* <p><em>Note:</em> Not all properties are currently supported.
|
|
|
|
* Currently, only the general category, script, and numeric value
|
|
|
|
* properties are supported. Support for other properties will be
|
|
|
|
* added in the future.
|
1999-12-28 23:57:50 +00:00
|
|
|
*
|
|
|
|
* @author Alan Liu
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-01-18 20:00:56 +00:00
|
|
|
class U_I18N_API UnicodeSet : public UnicodeFilter {
|
1999-12-28 23:57:50 +00:00
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
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
|
|
|
|
|
2001-06-12 17:34:16 +00:00
|
|
|
/**
|
|
|
|
* 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;
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
public:
|
|
|
|
|
|
|
|
/**
|
2000-05-25 19:27:14 +00:00
|
|
|
* Minimum value that can be stored in a UnicodeSet.
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
static const UChar32 MIN_VALUE;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Maximum value that can be stored in a UnicodeSet.
|
|
|
|
*/
|
|
|
|
static const UChar32 MAX_VALUE;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
// Constructors &c
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
|
|
|
|
public:
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Constructs an empty set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
UnicodeSet();
|
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
/**
|
|
|
|
* Constructs a set containing the given range. If <code>end >
|
|
|
|
* start</code> 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);
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
/**
|
|
|
|
* 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 <code>IllegalArgumentException</code> if the pattern
|
|
|
|
* contains a syntax error.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
UnicodeSet(const UnicodeString& pattern,
|
|
|
|
UErrorCode& status);
|
|
|
|
|
|
|
|
/**
|
2001-10-18 04:06:14 +00:00
|
|
|
* DEPRECATED Constructs a set from the given Unicode character category.
|
1999-12-28 23:57:50 +00:00
|
|
|
* @param category an integer indicating the character category as
|
2001-10-18 04:06:14 +00:00
|
|
|
* defined in uchar.h.
|
|
|
|
* @deprecated To be removed after 2002-DEC-31
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
UnicodeSet(int8_t category, UErrorCode& status);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Constructs a set that is identical to the given UnicodeSet.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
UnicodeSet(const UnicodeSet& o);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Destructs the set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
virtual ~UnicodeSet();
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Assigns this object to be a copy of another.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
UnicodeSet& operator=(const UnicodeSet& o);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Compares the specified object with this set for equality. Returns
|
|
|
|
* <tt>true</tt> 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 <tt>true</tt> if the specified set is equal to this set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-18 22:08:39 +00:00
|
|
|
virtual UBool operator==(const UnicodeSet& o) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Compares the specified object with this set for equality. Returns
|
|
|
|
* <tt>true</tt> if the specified set is not equal to this set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-18 22:08:39 +00:00
|
|
|
UBool operator!=(const UnicodeSet& o) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
2000-01-18 20:00:56 +00:00
|
|
|
/**
|
2001-07-27 00:18:53 +00:00
|
|
|
* Returns a copy of this object. All UnicodeMatcher objects have
|
2000-01-18 20:00:56 +00:00
|
|
|
* to support cloning in order to allow classes using
|
2001-07-27 00:18:53 +00:00
|
|
|
* UnicodeMatchers, such as Transliterator, to implement cloning.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
2000-01-18 20:00:56 +00:00
|
|
|
*/
|
2001-07-27 00:18:53 +00:00
|
|
|
virtual UnicodeMatcher* clone() const;
|
2000-01-18 20:00:56 +00:00
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
/**
|
|
|
|
* Returns the hash code value for this set.
|
|
|
|
*
|
|
|
|
* @return the hash code value for this set.
|
|
|
|
* @see Object#hashCode()
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
virtual int32_t hashCode(void) const;
|
|
|
|
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
// Public API
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
/**
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
* @param start first character in the set, inclusive
|
|
|
|
* @rparam end last character in the set, inclusive
|
|
|
|
*/
|
|
|
|
void set(UChar32 start, UChar32 end);
|
|
|
|
|
2001-10-18 04:06:14 +00:00
|
|
|
/**
|
|
|
|
* Return true if the given position, in the given pattern, appears
|
|
|
|
* to be the start of a UnicodeSet pattern.
|
|
|
|
*/
|
|
|
|
static UBool resemblesPattern(const UnicodeString& pattern,
|
|
|
|
int32_t pos);
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
/**
|
|
|
|
* 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 <code>IllegalArgumentException</code> if the pattern
|
|
|
|
* contains a syntax error.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
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.
|
2001-06-12 17:34:16 +00:00
|
|
|
* @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.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2001-06-12 17:34:16 +00:00
|
|
|
virtual UnicodeString& toPattern(UnicodeString& result,
|
|
|
|
UBool escapeUnprintable = FALSE) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns the number of elements in this set (its cardinality),
|
|
|
|
* <em>n</em>, where <code>0 <= </code><em>n</em><code> <= 65536</code>.
|
|
|
|
*
|
|
|
|
* @return the number of elements in this set (its cardinality).
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
virtual int32_t size(void) const;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns <tt>true</tt> if this set contains no elements.
|
|
|
|
*
|
|
|
|
* @return <tt>true</tt> if this set contains no elements.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-18 22:08:39 +00:00
|
|
|
virtual UBool isEmpty(void) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns <tt>true</tt> if this set contains the specified range
|
|
|
|
* of chars.
|
|
|
|
*
|
|
|
|
* @return <tt>true</tt> if this set contains the specified range
|
|
|
|
* of chars.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
virtual UBool contains(UChar32 start, UChar32 end) const;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns <tt>true</tt> if this set contains the specified char.
|
|
|
|
*
|
|
|
|
* @return <tt>true</tt> if this set contains the specified char.
|
|
|
|
* @draft
|
|
|
|
*/
|
|
|
|
virtual UBool contains(UChar32 c) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
2001-07-25 18:50:09 +00:00
|
|
|
* Implement UnicodeMatcher::matches()
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2001-07-25 18:50:09 +00:00
|
|
|
UMatchDegree matches(const Replaceable& text,
|
|
|
|
int32_t& offset,
|
|
|
|
int32_t limit,
|
2001-10-30 23:55:09 +00:00
|
|
|
UBool incremental);
|
2001-07-25 18:50:09 +00:00
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
/**
|
|
|
|
* Adds the specified range to this set if it is not already
|
|
|
|
* present. If this set already contains the specified range,
|
2000-05-25 19:27:14 +00:00
|
|
|
* the call leaves this set unchanged. If <code>end > start</code>
|
1999-12-28 23:57:50 +00:00
|
|
|
* then an empty range is added, leaving the set unchanged.
|
2000-05-26 18:32:15 +00:00
|
|
|
* This is equivalent to a boolean logic OR, or a set UNION.
|
1999-12-28 23:57:50 +00:00
|
|
|
*
|
2000-05-25 19:27:14 +00:00
|
|
|
* @param start first character, inclusive, of range to be added
|
1999-12-28 23:57:50 +00:00
|
|
|
* to this set.
|
2000-05-25 19:27:14 +00:00
|
|
|
* @param end last character, inclusive, of range to be added
|
1999-12-28 23:57:50 +00:00
|
|
|
* to this set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
virtual void add(UChar32 start, UChar32 end);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* 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.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
void add(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Retain only the elements in this set that are contained in the
|
|
|
|
* specified range. If <code>end > start</code> then an empty range is
|
2000-05-26 18:32:15 +00:00
|
|
|
* retained, leaving the set empty. This is equivalent to
|
|
|
|
* a boolean logic AND, or a set INTERSECTION.
|
2000-05-25 19:27:14 +00:00
|
|
|
*
|
|
|
|
* @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);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Removes the specified range from this set if it is present.
|
|
|
|
* The set will not contain the specified range once the call
|
2000-05-25 19:27:14 +00:00
|
|
|
* returns. If <code>end > start</code> then an empty range is
|
1999-12-28 23:57:50 +00:00
|
|
|
* removed, leaving the set unchanged.
|
2001-03-22 00:09:10 +00:00
|
|
|
*
|
2000-05-25 19:27:14 +00:00
|
|
|
* @param start first character, inclusive, of range to be removed
|
1999-12-28 23:57:50 +00:00
|
|
|
* from this set.
|
2000-05-25 19:27:14 +00:00
|
|
|
* @param end last character, inclusive, of range to be removed
|
1999-12-28 23:57:50 +00:00
|
|
|
* from this set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
virtual void remove(UChar32 start, UChar32 end);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Removes the specified character from this set if it is present.
|
|
|
|
* The set will not contain the specified range once the call
|
|
|
|
* returns.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
void remove(UChar32 c);
|
|
|
|
|
2000-05-26 18:32:15 +00:00
|
|
|
/**
|
|
|
|
* 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>.
|
|
|
|
* @draft
|
|
|
|
*/
|
|
|
|
virtual void complement(void);
|
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
/**
|
|
|
|
* 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 <code>end > start</code>
|
2000-05-26 18:32:15 +00:00
|
|
|
* then an empty range is complemented, leaving the set unchanged.
|
|
|
|
* This is equivalent to a boolean logic XOR.
|
2000-05-25 19:27:14 +00:00
|
|
|
*
|
|
|
|
* @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.
|
|
|
|
*/
|
2000-05-26 18:32:15 +00:00
|
|
|
virtual void complement(UChar32 start, UChar32 end);
|
2000-05-25 19:27:14 +00:00
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
* 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.
|
|
|
|
*/
|
2000-05-26 18:32:15 +00:00
|
|
|
void complement(UChar32 c);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns <tt>true</tt> if the specified set is a <i>subset</i>
|
|
|
|
* of this set.
|
|
|
|
*
|
|
|
|
* @param c set to be checked for containment in this set.
|
|
|
|
* @return <tt>true</tt> if this set contains all of the elements of the
|
|
|
|
* specified set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
2000-05-18 22:08:39 +00:00
|
|
|
virtual UBool containsAll(const UnicodeSet& c) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* 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 <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.
|
|
|
|
*
|
|
|
|
* @param c set whose elements are to be added to this set.
|
|
|
|
* @see #add(char, char)
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
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 <i>intersection</i> of the two sets.
|
|
|
|
*
|
|
|
|
* @param c set that defines which elements this set will retain.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
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 <i>asymmetric set difference</i> of
|
|
|
|
* the two sets.
|
|
|
|
*
|
|
|
|
* @param c set that defines which elements will be removed from
|
|
|
|
* this set.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
virtual void removeAll(const UnicodeSet& c);
|
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
/**
|
|
|
|
* 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.
|
|
|
|
*/
|
2000-05-26 18:32:15 +00:00
|
|
|
virtual void complementAll(const UnicodeSet& c);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Removes all of the elements from this set. This set will be
|
|
|
|
* empty after this call returns.
|
2000-03-22 19:19:33 +00:00
|
|
|
* @draft
|
1999-12-28 23:57:50 +00:00
|
|
|
*/
|
|
|
|
virtual void clear(void);
|
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
/**
|
|
|
|
* 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();
|
|
|
|
|
2001-11-09 01:22:59 +00:00
|
|
|
/**
|
|
|
|
* Return the class ID for this class. This is useful only for
|
|
|
|
* comparing to a return value from getDynamicClassID(). For example:
|
|
|
|
* <pre>
|
|
|
|
* . Base* polymorphic_pointer = createPolymorphicObject();
|
|
|
|
* . if (polymorphic_pointer->getDynamicClassID() ==
|
|
|
|
* . Derived::getStaticClassID()) ...
|
|
|
|
* </pre>
|
|
|
|
* @return The class ID for all objects of this class.
|
|
|
|
* @stable
|
|
|
|
*/
|
|
|
|
static UClassID getStaticClassID(void) { return (UClassID)&fgClassID; }
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Implement UnicodeMatcher 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.
|
|
|
|
*/
|
|
|
|
virtual UClassID getDynamicClassID(void) const { return getStaticClassID(); };
|
|
|
|
|
|
|
|
private:
|
|
|
|
|
|
|
|
static const char fgClassID;
|
|
|
|
|
2000-01-13 07:28:31 +00:00
|
|
|
private:
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
//----------------------------------------------------------------
|
2000-01-13 07:28:31 +00:00
|
|
|
// RuleBasedTransliterator support
|
1999-12-28 23:57:50 +00:00
|
|
|
//----------------------------------------------------------------
|
|
|
|
|
2001-03-31 01:22:58 +00:00
|
|
|
friend class Transliterator;
|
2001-07-13 21:17:11 +00:00
|
|
|
friend class TransliteratorParser;
|
2000-01-13 07:28:31 +00:00
|
|
|
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 <code>IllegalArgumentException</code> if the pattern
|
|
|
|
* contains a syntax error.
|
|
|
|
*/
|
|
|
|
UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
|
2000-02-08 02:49:15 +00:00
|
|
|
const SymbolTable& symbols,
|
2000-01-13 07:28:31 +00:00
|
|
|
UErrorCode& status);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns <tt>true</tt> if this set contains any character whose low byte
|
|
|
|
* is the given value. This is used by <tt>RuleBasedTransliterator</tt> for
|
|
|
|
* indexing.
|
|
|
|
*/
|
2001-07-27 00:18:53 +00:00
|
|
|
virtual UBool matchesIndexValue(uint8_t v) const;
|
2000-01-13 07:28:31 +00:00
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
private:
|
|
|
|
|
2000-01-13 07:28:31 +00:00
|
|
|
//----------------------------------------------------------------
|
|
|
|
// Implementation: Pattern parsing
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
/**
|
|
|
|
* 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 IllegalArgumentException if the parse fails.
|
|
|
|
*/
|
2000-05-25 19:27:14 +00:00
|
|
|
void applyPattern(const UnicodeString& pattern,
|
|
|
|
ParsePosition& pos,
|
|
|
|
const SymbolTable* symbols,
|
|
|
|
UErrorCode& status);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
// Implementation: Utility methods
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
void ensureCapacity(int32_t newLen);
|
2001-03-22 00:09:10 +00:00
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
void ensureBufferCapacity(int32_t newLen);
|
2001-03-22 00:09:10 +00:00
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
void swapBuffers(void);
|
|
|
|
|
2001-06-12 17:34:16 +00:00
|
|
|
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);
|
2000-05-25 19:27:14 +00:00
|
|
|
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
// Implementation: Fundamental operators
|
|
|
|
//----------------------------------------------------------------
|
|
|
|
|
2000-05-26 01:18:36 +00:00
|
|
|
void exclusiveOr(const UChar32* other, int32_t otherLen, int8_t polarity);
|
2001-03-22 00:09:10 +00:00
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
void add(const UChar32* other, int32_t otherLen, int8_t polarity);
|
2001-03-22 00:09:10 +00:00
|
|
|
|
2000-05-25 19:27:14 +00:00
|
|
|
void retain(const UChar32* other, int32_t otherLen, int8_t polarity);
|
1999-12-28 23:57:50 +00:00
|
|
|
};
|
|
|
|
|
2000-05-18 22:08:39 +00:00
|
|
|
inline UBool UnicodeSet::operator!=(const UnicodeSet& o) const {
|
1999-12-28 23:57:50 +00:00
|
|
|
return !operator==(o);
|
|
|
|
}
|
|
|
|
|
2001-10-08 23:26:58 +00:00
|
|
|
U_NAMESPACE_END
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
#endif
|