1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/common/unicode/symtable.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,112 @@
1.4 +/*
1.5 +**********************************************************************
1.6 +* Copyright (c) 2000-2005, International Business Machines
1.7 +* Corporation and others. All Rights Reserved.
1.8 +**********************************************************************
1.9 +* Date Name Description
1.10 +* 02/04/00 aliu Creation.
1.11 +**********************************************************************
1.12 +*/
1.13 +#ifndef SYMTABLE_H
1.14 +#define SYMTABLE_H
1.15 +
1.16 +#include "unicode/utypes.h"
1.17 +#include "unicode/uobject.h"
1.18 +
1.19 +/**
1.20 + * \file
1.21 + * \brief C++ API: An interface that defines both lookup protocol and parsing of
1.22 + * symbolic names.
1.23 + */
1.24 +
1.25 +U_NAMESPACE_BEGIN
1.26 +
1.27 +class ParsePosition;
1.28 +class UnicodeFunctor;
1.29 +class UnicodeSet;
1.30 +class UnicodeString;
1.31 +
1.32 +/**
1.33 + * An interface that defines both lookup protocol and parsing of
1.34 + * symbolic names.
1.35 + *
1.36 + * <p>A symbol table maintains two kinds of mappings. The first is
1.37 + * between symbolic names and their values. For example, if the
1.38 + * variable with the name "start" is set to the value "alpha"
1.39 + * (perhaps, though not necessarily, through an expression such as
1.40 + * "$start=alpha"), then the call lookup("start") will return the
1.41 + * char[] array ['a', 'l', 'p', 'h', 'a'].
1.42 + *
1.43 + * <p>The second kind of mapping is between character values and
1.44 + * UnicodeMatcher objects. This is used by RuleBasedTransliterator,
1.45 + * which uses characters in the private use area to represent objects
1.46 + * such as UnicodeSets. If U+E015 is mapped to the UnicodeSet [a-z],
1.47 + * then lookupMatcher(0xE015) will return the UnicodeSet [a-z].
1.48 + *
1.49 + * <p>Finally, a symbol table defines parsing behavior for symbolic
1.50 + * names. All symbolic names start with the SYMBOL_REF character.
1.51 + * When a parser encounters this character, it calls parseReference()
1.52 + * with the position immediately following the SYMBOL_REF. The symbol
1.53 + * table parses the name, if there is one, and returns it.
1.54 + *
1.55 + * @stable ICU 2.8
1.56 + */
1.57 +class U_COMMON_API SymbolTable /* not : public UObject because this is an interface/mixin class */ {
1.58 +public:
1.59 +
1.60 + /**
1.61 + * The character preceding a symbol reference name.
1.62 + * @stable ICU 2.8
1.63 + */
1.64 + enum { SYMBOL_REF = 0x0024 /*$*/ };
1.65 +
1.66 + /**
1.67 + * Destructor.
1.68 + * @stable ICU 2.8
1.69 + */
1.70 + virtual ~SymbolTable();
1.71 +
1.72 + /**
1.73 + * Lookup the characters associated with this string and return it.
1.74 + * Return <tt>NULL</tt> if no such name exists. The resultant
1.75 + * string may have length zero.
1.76 + * @param s the symbolic name to lookup
1.77 + * @return a string containing the name's value, or <tt>NULL</tt> if
1.78 + * there is no mapping for s.
1.79 + * @stable ICU 2.8
1.80 + */
1.81 + virtual const UnicodeString* lookup(const UnicodeString& s) const = 0;
1.82 +
1.83 + /**
1.84 + * Lookup the UnicodeMatcher associated with the given character, and
1.85 + * return it. Return <tt>NULL</tt> if not found.
1.86 + * @param ch a 32-bit code point from 0 to 0x10FFFF inclusive.
1.87 + * @return the UnicodeMatcher object represented by the given
1.88 + * character, or NULL if there is no mapping for ch.
1.89 + * @stable ICU 2.8
1.90 + */
1.91 + virtual const UnicodeFunctor* lookupMatcher(UChar32 ch) const = 0;
1.92 +
1.93 + /**
1.94 + * Parse a symbol reference name from the given string, starting
1.95 + * at the given position. If no valid symbol reference name is
1.96 + * found, return the empty string and leave pos unchanged. That is, if the
1.97 + * character at pos cannot start a name, or if pos is at or after
1.98 + * text.length(), then return an empty string. This indicates an
1.99 + * isolated SYMBOL_REF character.
1.100 + * @param text the text to parse for the name
1.101 + * @param pos on entry, the index of the first character to parse.
1.102 + * This is the character following the SYMBOL_REF character. On
1.103 + * exit, the index after the last parsed character. If the parse
1.104 + * failed, pos is unchanged on exit.
1.105 + * @param limit the index after the last character to be parsed.
1.106 + * @return the parsed name, or an empty string if there is no
1.107 + * valid symbolic name at the given position.
1.108 + * @stable ICU 2.8
1.109 + */
1.110 + virtual UnicodeString parseReference(const UnicodeString& text,
1.111 + ParsePosition& pos, int32_t limit) const = 0;
1.112 +};
1.113 +U_NAMESPACE_END
1.114 +
1.115 +#endif
