2 *******************************************************************************
\r
3 * Copyright (C) 1996-2005, International Business Machines Corporation and *
\r
4 * others. All Rights Reserved. *
\r
5 *******************************************************************************
\r
7 package com.ibm.icu.text;
\r
8 import java.text.ParsePosition;
\r
11 * An interface that defines both lookup protocol and parsing of
\r
14 * <p>This interface is used by UnicodeSet to resolve $Variable style
\r
15 * references that appear in set patterns. RBBI and Transliteration
\r
16 * both independently implement this interface.
\r
18 * <p>A symbol table maintains two kinds of mappings. The first is
\r
19 * between symbolic names and their values. For example, if the
\r
20 * variable with the name "start" is set to the value "alpha"
\r
21 * (perhaps, though not necessarily, through an expression such as
\r
22 * "$start=alpha"), then the call lookup("start") will return the
\r
23 * char[] array ['a', 'l', 'p', 'h', 'a'].
\r
25 * <p>The second kind of mapping is between character values and
\r
26 * UnicodeMatcher objects. This is used by RuleBasedTransliterator,
\r
27 * which uses characters in the private use area to represent objects
\r
28 * such as UnicodeSets. If U+E015 is mapped to the UnicodeSet [a-z],
\r
29 * then lookupMatcher(0xE015) will return the UnicodeSet [a-z].
\r
31 * <p>Finally, a symbol table defines parsing behavior for symbolic
\r
32 * names. All symbolic names start with the SYMBOL_REF character.
\r
33 * When a parser encounters this character, it calls parseReference()
\r
34 * with the position immediately following the SYMBOL_REF. The symbol
\r
35 * table parses the name, if there is one, and returns it.
\r
39 public interface SymbolTable {
\r
42 * The character preceding a symbol reference name.
\r
45 static final char SYMBOL_REF = '$';
\r
48 * Lookup the characters associated with this string and return it.
\r
49 * Return <tt>null</tt> if no such name exists. The resultant
\r
50 * array may have length zero.
\r
51 * @param s the symbolic name to lookup
\r
52 * @return a char array containing the name's value, or null if
\r
53 * there is no mapping for s.
\r
56 char[] lookup(String s);
\r
59 * Lookup the UnicodeMatcher associated with the given character, and
\r
60 * return it. Return <tt>null</tt> if not found.
\r
61 * @param ch a 32-bit code point from 0 to 0x10FFFF inclusive.
\r
62 * @return the UnicodeMatcher object represented by the given
\r
63 * character, or null if there is no mapping for ch.
\r
66 UnicodeMatcher lookupMatcher(int ch);
\r
69 * Parse a symbol reference name from the given string, starting
\r
70 * at the given position. If no valid symbol reference name is
\r
71 * found, return null and leave pos unchanged. That is, if the
\r
72 * character at pos cannot start a name, or if pos is at or after
\r
73 * text.length(), then return null. This indicates an isolated
\r
74 * SYMBOL_REF character.
\r
75 * @param text the text to parse for the name
\r
76 * @param pos on entry, the index of the first character to parse.
\r
77 * This is the character following the SYMBOL_REF character. On
\r
78 * exit, the index after the last parsed character. If the parse
\r
79 * failed, pos is unchanged on exit.
\r
80 * @param limit the index after the last character to be parsed.
\r
81 * @return the parsed name, or null if there is no valid symbolic
\r
82 * name at the given position.
\r
85 String parseReference(String text, ParsePosition pos, int limit);
\r