01: /*
02: *******************************************************************************
03: * Copyright (C) 1996-2005, International Business Machines Corporation and *
04: * others. All Rights Reserved. *
05: *******************************************************************************
06: */
07: package com.ibm.icu.text;
08:
09: import java.text.ParsePosition;
10:
11: /**
12: * An interface that defines both lookup protocol and parsing of
13: * symbolic names.
14: *
15: * <p>This interface is used by UnicodeSet to resolve $Variable style
16: * references that appear in set patterns. RBBI and Transliteration
17: * both independently implement this interface.
18: *
19: * <p>A symbol table maintains two kinds of mappings. The first is
20: * between symbolic names and their values. For example, if the
21: * variable with the name "start" is set to the value "alpha"
22: * (perhaps, though not necessarily, through an expression such as
23: * "$start=alpha"), then the call lookup("start") will return the
24: * char[] array ['a', 'l', 'p', 'h', 'a'].
25: *
26: * <p>The second kind of mapping is between character values and
27: * UnicodeMatcher objects. This is used by RuleBasedTransliterator,
28: * which uses characters in the private use area to represent objects
29: * such as UnicodeSets. If U+E015 is mapped to the UnicodeSet [a-z],
30: * then lookupMatcher(0xE015) will return the UnicodeSet [a-z].
31: *
32: * <p>Finally, a symbol table defines parsing behavior for symbolic
33: * names. All symbolic names start with the SYMBOL_REF character.
34: * When a parser encounters this character, it calls parseReference()
35: * with the position immediately following the SYMBOL_REF. The symbol
36: * table parses the name, if there is one, and returns it.
37: *
38: * @stable ICU 2.8
39: */
40: public interface SymbolTable {
41:
42: /**
43: * The character preceding a symbol reference name.
44: * @stable ICU 2.8
45: */
46: static final char SYMBOL_REF = '$';
47:
48: /**
49: * Lookup the characters associated with this string and return it.
50: * Return <tt>null</tt> if no such name exists. The resultant
51: * array may have length zero.
52: * @param s the symbolic name to lookup
53: * @return a char array containing the name's value, or null if
54: * there is no mapping for s.
55: * @stable ICU 2.8
56: */
57: char[] lookup(String s);
58:
59: /**
60: * Lookup the UnicodeMatcher associated with the given character, and
61: * return it. Return <tt>null</tt> if not found.
62: * @param ch a 32-bit code point from 0 to 0x10FFFF inclusive.
63: * @return the UnicodeMatcher object represented by the given
64: * character, or null if there is no mapping for ch.
65: * @stable ICU 2.8
66: */
67: UnicodeMatcher lookupMatcher(int ch);
68:
69: /**
70: * Parse a symbol reference name from the given string, starting
71: * at the given position. If no valid symbol reference name is
72: * found, return null and leave pos unchanged. That is, if the
73: * character at pos cannot start a name, or if pos is at or after
74: * text.length(), then return null. This indicates an isolated
75: * SYMBOL_REF character.
76: * @param text the text to parse for the name
77: * @param pos on entry, the index of the first character to parse.
78: * This is the character following the SYMBOL_REF character. On
79: * exit, the index after the last parsed character. If the parse
80: * failed, pos is unchanged on exit.
81: * @param limit the index after the last character to be parsed.
82: * @return the parsed name, or null if there is no valid symbolic
83: * name at the given position.
84: * @stable ICU 2.8
85: */
86: String parseReference(String text, ParsePosition pos, int limit);
87: }
|