sl@0
|
1 |
/*
|
sl@0
|
2 |
**********************************************************************
|
sl@0
|
3 |
* Copyright (c) 2000-2005, International Business Machines
|
sl@0
|
4 |
* Corporation and others. All Rights Reserved.
|
sl@0
|
5 |
**********************************************************************
|
sl@0
|
6 |
* Date Name Description
|
sl@0
|
7 |
* 02/04/00 aliu Creation.
|
sl@0
|
8 |
**********************************************************************
|
sl@0
|
9 |
*/
|
sl@0
|
10 |
#ifndef SYMTABLE_H
|
sl@0
|
11 |
#define SYMTABLE_H
|
sl@0
|
12 |
|
sl@0
|
13 |
#include "unicode/utypes.h"
|
sl@0
|
14 |
#include "unicode/uobject.h"
|
sl@0
|
15 |
|
sl@0
|
16 |
/**
|
sl@0
|
17 |
* \file
|
sl@0
|
18 |
* \brief C++ API: An interface that defines both lookup protocol and parsing of
|
sl@0
|
19 |
* symbolic names.
|
sl@0
|
20 |
*/
|
sl@0
|
21 |
|
sl@0
|
22 |
U_NAMESPACE_BEGIN
|
sl@0
|
23 |
|
sl@0
|
24 |
class ParsePosition;
|
sl@0
|
25 |
class UnicodeFunctor;
|
sl@0
|
26 |
class UnicodeSet;
|
sl@0
|
27 |
class UnicodeString;
|
sl@0
|
28 |
|
sl@0
|
29 |
/**
|
sl@0
|
30 |
* An interface that defines both lookup protocol and parsing of
|
sl@0
|
31 |
* symbolic names.
|
sl@0
|
32 |
*
|
sl@0
|
33 |
* <p>A symbol table maintains two kinds of mappings. The first is
|
sl@0
|
34 |
* between symbolic names and their values. For example, if the
|
sl@0
|
35 |
* variable with the name "start" is set to the value "alpha"
|
sl@0
|
36 |
* (perhaps, though not necessarily, through an expression such as
|
sl@0
|
37 |
* "$start=alpha"), then the call lookup("start") will return the
|
sl@0
|
38 |
* char[] array ['a', 'l', 'p', 'h', 'a'].
|
sl@0
|
39 |
*
|
sl@0
|
40 |
* <p>The second kind of mapping is between character values and
|
sl@0
|
41 |
* UnicodeMatcher objects. This is used by RuleBasedTransliterator,
|
sl@0
|
42 |
* which uses characters in the private use area to represent objects
|
sl@0
|
43 |
* such as UnicodeSets. If U+E015 is mapped to the UnicodeSet [a-z],
|
sl@0
|
44 |
* then lookupMatcher(0xE015) will return the UnicodeSet [a-z].
|
sl@0
|
45 |
*
|
sl@0
|
46 |
* <p>Finally, a symbol table defines parsing behavior for symbolic
|
sl@0
|
47 |
* names. All symbolic names start with the SYMBOL_REF character.
|
sl@0
|
48 |
* When a parser encounters this character, it calls parseReference()
|
sl@0
|
49 |
* with the position immediately following the SYMBOL_REF. The symbol
|
sl@0
|
50 |
* table parses the name, if there is one, and returns it.
|
sl@0
|
51 |
*
|
sl@0
|
52 |
* @stable ICU 2.8
|
sl@0
|
53 |
*/
|
sl@0
|
54 |
class U_COMMON_API SymbolTable /* not : public UObject because this is an interface/mixin class */ {
|
sl@0
|
55 |
public:
|
sl@0
|
56 |
|
sl@0
|
57 |
/**
|
sl@0
|
58 |
* The character preceding a symbol reference name.
|
sl@0
|
59 |
* @stable ICU 2.8
|
sl@0
|
60 |
*/
|
sl@0
|
61 |
enum { SYMBOL_REF = 0x0024 /*$*/ };
|
sl@0
|
62 |
|
sl@0
|
63 |
/**
|
sl@0
|
64 |
* Destructor.
|
sl@0
|
65 |
* @stable ICU 2.8
|
sl@0
|
66 |
*/
|
sl@0
|
67 |
virtual ~SymbolTable();
|
sl@0
|
68 |
|
sl@0
|
69 |
/**
|
sl@0
|
70 |
* Lookup the characters associated with this string and return it.
|
sl@0
|
71 |
* Return <tt>NULL</tt> if no such name exists. The resultant
|
sl@0
|
72 |
* string may have length zero.
|
sl@0
|
73 |
* @param s the symbolic name to lookup
|
sl@0
|
74 |
* @return a string containing the name's value, or <tt>NULL</tt> if
|
sl@0
|
75 |
* there is no mapping for s.
|
sl@0
|
76 |
* @stable ICU 2.8
|
sl@0
|
77 |
*/
|
sl@0
|
78 |
virtual const UnicodeString* lookup(const UnicodeString& s) const = 0;
|
sl@0
|
79 |
|
sl@0
|
80 |
/**
|
sl@0
|
81 |
* Lookup the UnicodeMatcher associated with the given character, and
|
sl@0
|
82 |
* return it. Return <tt>NULL</tt> if not found.
|
sl@0
|
83 |
* @param ch a 32-bit code point from 0 to 0x10FFFF inclusive.
|
sl@0
|
84 |
* @return the UnicodeMatcher object represented by the given
|
sl@0
|
85 |
* character, or NULL if there is no mapping for ch.
|
sl@0
|
86 |
* @stable ICU 2.8
|
sl@0
|
87 |
*/
|
sl@0
|
88 |
virtual const UnicodeFunctor* lookupMatcher(UChar32 ch) const = 0;
|
sl@0
|
89 |
|
sl@0
|
90 |
/**
|
sl@0
|
91 |
* Parse a symbol reference name from the given string, starting
|
sl@0
|
92 |
* at the given position. If no valid symbol reference name is
|
sl@0
|
93 |
* found, return the empty string and leave pos unchanged. That is, if the
|
sl@0
|
94 |
* character at pos cannot start a name, or if pos is at or after
|
sl@0
|
95 |
* text.length(), then return an empty string. This indicates an
|
sl@0
|
96 |
* isolated SYMBOL_REF character.
|
sl@0
|
97 |
* @param text the text to parse for the name
|
sl@0
|
98 |
* @param pos on entry, the index of the first character to parse.
|
sl@0
|
99 |
* This is the character following the SYMBOL_REF character. On
|
sl@0
|
100 |
* exit, the index after the last parsed character. If the parse
|
sl@0
|
101 |
* failed, pos is unchanged on exit.
|
sl@0
|
102 |
* @param limit the index after the last character to be parsed.
|
sl@0
|
103 |
* @return the parsed name, or an empty string if there is no
|
sl@0
|
104 |
* valid symbolic name at the given position.
|
sl@0
|
105 |
* @stable ICU 2.8
|
sl@0
|
106 |
*/
|
sl@0
|
107 |
virtual UnicodeString parseReference(const UnicodeString& text,
|
sl@0
|
108 |
ParsePosition& pos, int32_t limit) const = 0;
|
sl@0
|
109 |
};
|
sl@0
|
110 |
U_NAMESPACE_END
|
sl@0
|
111 |
|
sl@0
|
112 |
#endif
|