1 // © 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
3 /*
4 **********************************************************************
5 *   Copyright (c) 2000-2005, International Business Machines
6 *   Corporation and others.  All Rights Reserved.
7 **********************************************************************
8 *   Date        Name        Description
9 *   02/04/00    aliu        Creation.
10 **********************************************************************
11 */
12 #ifndef SYMTABLE_H
13 #define SYMTABLE_H
14 
15 #include "unicode/utypes.h"
16 
17 #if U_SHOW_CPLUSPLUS_API
18 
19 #include "unicode/uobject.h"
20 
21 /**
22  * \file
23  * \brief C++ API: An interface that defines both lookup protocol and parsing of
24  * symbolic names.
25  */
26 
27 U_NAMESPACE_BEGIN
28 
29 class ParsePosition;
30 class UnicodeFunctor;
31 class UnicodeSet;
32 class UnicodeString;
33 
34 /**
35  * An interface that defines both lookup protocol and parsing of
36  * symbolic names.
37  *
38  * <p>A symbol table maintains two kinds of mappings.  The first is
39  * between symbolic names and their values.  For example, if the
40  * variable with the name "start" is set to the value "alpha"
41  * (perhaps, though not necessarily, through an expression such as
42  * "$start=alpha"), then the call lookup("start") will return the
43  * char[] array ['a', 'l', 'p', 'h', 'a'].
44  *
45  * <p>The second kind of mapping is between character values and
46  * UnicodeMatcher objects.  This is used by RuleBasedTransliterator,
47  * which uses characters in the private use area to represent objects
48  * such as UnicodeSets.  If U+E015 is mapped to the UnicodeSet [a-z],
49  * then lookupMatcher(0xE015) will return the UnicodeSet [a-z].
50  *
51  * <p>Finally, a symbol table defines parsing behavior for symbolic
52  * names.  All symbolic names start with the SYMBOL_REF character.
53  * When a parser encounters this character, it calls parseReference()
54  * with the position immediately following the SYMBOL_REF.  The symbol
55  * table parses the name, if there is one, and returns it.
56  *
57  * @stable ICU 2.8
58  */
59 class U_COMMON_API SymbolTable /* not : public UObject because this is an interface/mixin class */ {
60 public:
61 
62     /**
63      * The character preceding a symbol reference name.
64      * @stable ICU 2.8
65      */
66     enum { SYMBOL_REF = 0x0024 /*$*/ };
67 
68     /**
69      * Destructor.
70      * @stable ICU 2.8
71      */
72     virtual ~SymbolTable();
73 
74     /**
75      * Lookup the characters associated with this string and return it.
76      * Return <tt>NULL</tt> if no such name exists.  The resultant
77      * string may have length zero.
78      * @param s the symbolic name to lookup
79      * @return a string containing the name's value, or <tt>NULL</tt> if
80      * there is no mapping for s.
81      * @stable ICU 2.8
82      */
83     virtual const UnicodeString* lookup(const UnicodeString& s) const = 0;
84 
85     /**
86      * Lookup the UnicodeMatcher associated with the given character, and
87      * return it.  Return <tt>NULL</tt> if not found.
88      * @param ch a 32-bit code point from 0 to 0x10FFFF inclusive.
89      * @return the UnicodeMatcher object represented by the given
90      * character, or NULL if there is no mapping for ch.
91      * @stable ICU 2.8
92      */
93     virtual const UnicodeFunctor* lookupMatcher(UChar32 ch) const = 0;
94 
95     /**
96      * Parse a symbol reference name from the given string, starting
97      * at the given position.  If no valid symbol reference name is
98      * found, return the empty string and leave pos unchanged.  That is, if the
99      * character at pos cannot start a name, or if pos is at or after
100      * text.length(), then return an empty string.  This indicates an
101      * isolated SYMBOL_REF character.
102      * @param text the text to parse for the name
103      * @param pos on entry, the index of the first character to parse.
104      * This is the character following the SYMBOL_REF character.  On
105      * exit, the index after the last parsed character.  If the parse
106      * failed, pos is unchanged on exit.
107      * @param limit the index after the last character to be parsed.
108      * @return the parsed name, or an empty string if there is no
109      * valid symbolic name at the given position.
110      * @stable ICU 2.8
111      */
112     virtual UnicodeString parseReference(const UnicodeString& text,
113                                          ParsePosition& pos, int32_t limit) const = 0;
114 };
115 U_NAMESPACE_END
116 
117 #endif /* U_SHOW_CPLUSPLUS_API */
118 
119 #endif
120