UnicodeMatcher


1   /*
2    *******************************************************************************
3    * Copyright (C) 2001-2004, International Business Machines Corporation and    *
4    * others. All Rights Reserved.                                                *
5    *******************************************************************************
6    */
7   package com.ibm.icu.text;
8   
9   /**
10   * <code>UnicodeMatcher</code> defines a protocol for objects that can
11   * match a range of characters in a Replaceable string.
12   * @stable ICU 2.0
13   */
14  public interface UnicodeMatcher {
15  
16      /**
17       * Constant returned by <code>matches()</code> indicating a
18       * mismatch between the text and this matcher.  The text contains
19       * a character which does not match, or the text does not contain
20       * all desired characters for a non-incremental match.
21       * @stable ICU 2.0
22       */
23      public static final int U_MISMATCH = 0;
24  
25      /**
26       * Constant returned by <code>matches()</code> indicating a
27       * partial match between the text and this matcher.  This value is
28       * only returned for incremental match operations.  All characters
29       * of the text match, but more characters are required for a
30       * complete match.  Alternatively, for variable-length matchers,
31       * all characters of the text match, and if more characters were
32       * supplied at limit, they might also match.
33       * @stable ICU 2.0
34       */
35      public static final int U_PARTIAL_MATCH = 1;
36  
37      /**
38       * Constant returned by <code>matches()</code> indicating a
39       * complete match between the text and this matcher.  For an
40       * incremental variable-length match, this value is returned if
41       * the given text matches, and it is known that additional
42       * characters would not alter the extent of the match.
43       * @stable ICU 2.0
44       */
45      public static final int U_MATCH = 2;
46  
47      /**
48       * The character at index i, where i < contextStart || i >= contextLimit,
49       * is ETHER.  This allows explicit matching by rules and UnicodeSets
50       * of text outside the context.  In traditional terms, this allows anchoring
51       * at the start and/or end.
52       * @stable ICU 2.0
53       */
54      static final char ETHER = '\uFFFF';
55  
56      /**
57       * Return a UMatchDegree value indicating the degree of match for
58       * the given text at the given offset.  Zero, one, or more
59       * characters may be matched.
60       *
61       * Matching in the forward direction is indicated by limit >
62       * offset.  Characters from offset forwards to limit-1 will be
63       * considered for matching.
64       *
65       * Matching in the reverse direction is indicated by limit <
66       * offset.  Characters from offset backwards to limit+1 will be
67       * considered for matching.
68       *
69       * If limit == offset then the only match possible is a zero
70       * character match (which subclasses may implement if desired).
71       *
72       * If U_MATCH is returned, then as a side effect, advance the
73       * offset parameter to the limit of the matched substring.  In the
74       * forward direction, this will be the index of the last matched
75       * character plus one.  In the reverse direction, this will be the
76       * index of the last matched character minus one.
77       *
78       * @param text the text to be matched
79       * @param offset on input, the index into text at which to begin
80       * matching.  On output, the limit of the matched text.  The
81       * number of matched characters is the output value of offset
82       * minus the input value.  Offset should always point to the
83       * HIGH SURROGATE (leading code unit) of a pair of surrogates,
84       * both on entry and upon return.
85       * @param limit the limit index of text to be matched.  Greater
86       * than offset for a forward direction match, less than offset for
87       * a backward direction match.  The last character to be
88       * considered for matching will be text.charAt(limit-1) in the
89       * forward direction or text.charAt(limit+1) in the backward
90       * direction.
91       * @param incremental if TRUE, then assume further characters may
92       * be inserted at limit and check for partial matching.  Otherwise
93       * assume the text as given is complete.
94       * @return a match degree value indicating a full match, a partial
95       * match, or a mismatch.  If incremental is FALSE then
96       * U_PARTIAL_MATCH should never be returned.
97       * @stable ICU 2.0
98       */
99      public abstract int matches(Replaceable text,
100                                 int[] offset,
101                                 int limit,
102                                 boolean incremental);
103 
104     /**
105      * Returns a string representation of this matcher.  If the result of
106      * calling this function is passed to the appropriate parser, it
107      * will produce another matcher that is equal to this one.
108      * @param escapeUnprintable if TRUE then convert unprintable
109      * character to their hex escape representations, \\uxxxx or
110      * \\Uxxxxxxxx.  Unprintable characters are those other than
111      * U+000A, U+0020..U+007E.
112      * @stable ICU 2.0
113      */
114     public abstract String   toPattern(boolean escapeUnprintable);
115 
116     /**
117      * Returns TRUE if this matcher will match a character c, where c
118      * & 0xFF == v, at offset, in the forward direction (with limit >
119      * offset).  This is used by <tt>RuleBasedTransliterator</tt> for
120      * indexing.
121      *
122      * <p>Note:  This API uses an int even though the value will be
123      * restricted to 8 bits in order to avoid complications with
124      * signedness (bytes convert to ints in the range -128..127).
125      * @stable ICU 2.0
126      */
127     public abstract boolean matchesIndexValue(int v);
128 
129     /**
130      * Union the set of all characters that may be matched by this object
131      * into the given set.
132      * @param toUnionTo the set into which to union the source characters
133      * @stable ICU 2.2
134      */
135     public abstract void addMatchSetTo(UnicodeSet toUnionTo);
136 }
137 
138 //eof
139
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags