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