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