xref: /aosp_15_r20/external/antlr/runtime/Cpp/include/antlr3parser.hpp (revision 16467b971bd3e2009fad32dd79016f2c7e421deb)
1*16467b97STreehugger Robot /** \file
2*16467b97STreehugger Robot  * Base implementation of an ANTLR3 parser.
3*16467b97STreehugger Robot  *
4*16467b97STreehugger Robot  *
5*16467b97STreehugger Robot  */
6*16467b97STreehugger Robot #ifndef	_ANTLR3_PARSER_HPP
7*16467b97STreehugger Robot #define	_ANTLR3_PARSER_HPP
8*16467b97STreehugger Robot 
9*16467b97STreehugger Robot // [The "BSD licence"]
10*16467b97STreehugger Robot // Copyright (c) 2005-2009 Gokulakannan Somasundaram, ElectronDB
11*16467b97STreehugger Robot 
12*16467b97STreehugger Robot //
13*16467b97STreehugger Robot // All rights reserved.
14*16467b97STreehugger Robot //
15*16467b97STreehugger Robot // Redistribution and use in source and binary forms, with or without
16*16467b97STreehugger Robot // modification, are permitted provided that the following conditions
17*16467b97STreehugger Robot // are met:
18*16467b97STreehugger Robot // 1. Redistributions of source code must retain the above copyright
19*16467b97STreehugger Robot //    notice, this list of conditions and the following disclaimer.
20*16467b97STreehugger Robot // 2. Redistributions in binary form must reproduce the above copyright
21*16467b97STreehugger Robot //    notice, this list of conditions and the following disclaimer in the
22*16467b97STreehugger Robot //    documentation and/or other materials provided with the distribution.
23*16467b97STreehugger Robot // 3. The name of the author may not be used to endorse or promote products
24*16467b97STreehugger Robot //    derived from this software without specific prior written permission.
25*16467b97STreehugger Robot //
26*16467b97STreehugger Robot // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
27*16467b97STreehugger Robot // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
28*16467b97STreehugger Robot // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
29*16467b97STreehugger Robot // IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
30*16467b97STreehugger Robot // INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
31*16467b97STreehugger Robot // NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
32*16467b97STreehugger Robot // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
33*16467b97STreehugger Robot // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
34*16467b97STreehugger Robot // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
35*16467b97STreehugger Robot // THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
36*16467b97STreehugger Robot 
37*16467b97STreehugger Robot #include    "antlr3defs.hpp"
38*16467b97STreehugger Robot 
39*16467b97STreehugger Robot ANTLR_BEGIN_NAMESPACE()
40*16467b97STreehugger Robot 
41*16467b97STreehugger Robot /** This is the main interface for an ANTLR3 parser.
42*16467b97STreehugger Robot  */
43*16467b97STreehugger Robot template< class ImplTraits >
44*16467b97STreehugger Robot class Parser  :  public ImplTraits::template RecognizerType< typename ImplTraits::TokenStreamType >
45*16467b97STreehugger Robot {
46*16467b97STreehugger Robot public:
47*16467b97STreehugger Robot 	typedef typename ImplTraits::StringType StringType;
48*16467b97STreehugger Robot 	typedef typename ImplTraits::TokenStreamType  TokenStreamType;
49*16467b97STreehugger Robot 	typedef typename TokenStreamType::IntStreamType  IntStreamType;
50*16467b97STreehugger Robot 	typedef TokenStreamType StreamType;
51*16467b97STreehugger Robot 
52*16467b97STreehugger Robot 	typedef typename ImplTraits::template RecognizerType< typename ImplTraits::TokenStreamType > RecognizerType;
53*16467b97STreehugger Robot 	typedef typename RecognizerType::RecognizerSharedStateType RecognizerSharedStateType;
54*16467b97STreehugger Robot 
55*16467b97STreehugger Robot 	typedef DebugEventListener<ImplTraits> DebugEventListenerType;
56*16467b97STreehugger Robot 	typedef typename ImplTraits::CommonTokenType CommonTokenType;
57*16467b97STreehugger Robot 	typedef CommonTokenType TokenType;
58*16467b97STreehugger Robot 	typedef typename ImplTraits::BitsetListType BitsetListType;
59*16467b97STreehugger Robot 	typedef ANTLR_ExceptionBase<ImplTraits, TokenStreamType> ExceptionBaseType;
60*16467b97STreehugger Robot 	typedef Empty TokenSourceType;
61*16467b97STreehugger Robot 
62*16467b97STreehugger Robot 	typedef typename RecognizerSharedStateType::FollowingType FollowingType;
63*16467b97STreehugger Robot 	typedef typename RecognizerSharedStateType::RuleMemoType RuleMemoType;
64*16467b97STreehugger Robot 	typedef typename ImplTraits::DebugEventListenerType DebuggerType;
65*16467b97STreehugger Robot 
66*16467b97STreehugger Robot private:
67*16467b97STreehugger Robot     /** A provider of a tokenstream interface, for the parser to consume
68*16467b97STreehugger Robot      *  tokens from.
69*16467b97STreehugger Robot      */
70*16467b97STreehugger Robot     TokenStreamType*			m_tstream;
71*16467b97STreehugger Robot 
72*16467b97STreehugger Robot public:
73*16467b97STreehugger Robot 	Parser( ANTLR_UINT32 sizeHint, RecognizerSharedStateType* state );
74*16467b97STreehugger Robot 	Parser( ANTLR_UINT32 sizeHint, TokenStreamType* tstream, RecognizerSharedStateType* state );
75*16467b97STreehugger Robot 	Parser( ANTLR_UINT32 sizeHint, TokenStreamType* tstream, DebugEventListenerType* dbg,
76*16467b97STreehugger Robot 											RecognizerSharedStateType* state );
77*16467b97STreehugger Robot 	TokenStreamType* get_tstream() const;
78*16467b97STreehugger Robot 	TokenStreamType* get_input() const;
79*16467b97STreehugger Robot 	IntStreamType* get_istream() const;
80*16467b97STreehugger Robot 	RecognizerType* get_rec();
81*16467b97STreehugger Robot 
82*16467b97STreehugger Robot 	//same as above. Just that get_istream exists for lexer, parser, treeparser
83*16467b97STreehugger Robot 	//get_parser_istream exists only for parser, treeparser. So use it accordingly
84*16467b97STreehugger Robot 	IntStreamType* get_parser_istream() const;
85*16467b97STreehugger Robot 
86*16467b97STreehugger Robot 	/** A pointer to a function that installs a debugger object (it also
87*16467b97STreehugger Robot 	 *  installs the debugging versions of the parser methods. This means that
88*16467b97STreehugger Robot 	 *  a non debug parser incurs no overhead because of the debugging stuff.
89*16467b97STreehugger Robot 	 */
90*16467b97STreehugger Robot 	void	setDebugListener(DebugEventListenerType* dbg);
91*16467b97STreehugger Robot 
92*16467b97STreehugger Robot     /** A pointer to a function that installs a token stream
93*16467b97STreehugger Robot      * for the parser.
94*16467b97STreehugger Robot      */
95*16467b97STreehugger Robot     void	setTokenStream(TokenStreamType*);
96*16467b97STreehugger Robot 
97*16467b97STreehugger Robot     /** A pointer to a function that returns the token stream for this
98*16467b97STreehugger Robot      *  parser.
99*16467b97STreehugger Robot      */
100*16467b97STreehugger Robot     TokenStreamType*	getTokenStream();
101*16467b97STreehugger Robot 
102*16467b97STreehugger Robot 	void exConstruct();
103*16467b97STreehugger Robot 	TokenType*	getMissingSymbol( IntStreamType* istream, ExceptionBaseType* e,
104*16467b97STreehugger Robot 								  ANTLR_UINT32	expectedTokenType, BitsetListType*	follow);
105*16467b97STreehugger Robot 
106*16467b97STreehugger Robot 	void mismatch(ANTLR_UINT32 ttype, BitsetListType* follow);
107*16467b97STreehugger Robot 
108*16467b97STreehugger Robot     /** Pointer to a function that knows how to free resources of an ANTLR3 parser.
109*16467b97STreehugger Robot      */
110*16467b97STreehugger Robot 	~Parser();
111*16467b97STreehugger Robot 
112*16467b97STreehugger Robot 	void fillExceptionData( ExceptionBaseType* ex );
113*16467b97STreehugger Robot 	void displayRecognitionError( ANTLR_UINT8** tokenNames, ExceptionBaseType* ex );
114*16467b97STreehugger Robot 
115*16467b97STreehugger Robot 	//convenience functions exposed in .stg
116*16467b97STreehugger Robot 	const RecognizerType* get_recognizer() const;
117*16467b97STreehugger Robot 	RecognizerSharedStateType* get_psrstate() const;
118*16467b97STreehugger Robot 	void set_psrstate(RecognizerSharedStateType* state);
119*16467b97STreehugger Robot 	bool haveParsedRule(ANTLR_MARKER	ruleIndex);
120*16467b97STreehugger Robot 	void memoize(ANTLR_MARKER	ruleIndex, ANTLR_MARKER	ruleParseStart);
121*16467b97STreehugger Robot 	ANTLR_MARKER  index() const;
122*16467b97STreehugger Robot 	bool hasException() const;
123*16467b97STreehugger Robot 	ExceptionBaseType* get_exception() const;
124*16467b97STreehugger Robot 	const CommonTokenType* matchToken( ANTLR_UINT32 ttype, BitsetListType* follow );
125*16467b97STreehugger Robot 	void matchAnyToken();
126*16467b97STreehugger Robot 	const FollowingType& get_follow_stack() const;
127*16467b97STreehugger Robot 	void followPush( const BitsetListType& follow );
128*16467b97STreehugger Robot 	void followPop();
129*16467b97STreehugger Robot 	void precover();
130*16467b97STreehugger Robot 	void preporterror();
131*16467b97STreehugger Robot 	ANTLR_UINT32 LA(ANTLR_INT32 i);
132*16467b97STreehugger Robot 	const CommonTokenType*  LT(ANTLR_INT32 k);
133*16467b97STreehugger Robot 	void constructEx();
134*16467b97STreehugger Robot 	void consume();
135*16467b97STreehugger Robot 	ANTLR_MARKER mark();
136*16467b97STreehugger Robot 	void rewind(ANTLR_MARKER marker);
137*16467b97STreehugger Robot 	void rewindLast();
138*16467b97STreehugger Robot 	void seek(ANTLR_MARKER index);
139*16467b97STreehugger Robot 	bool get_perror_recovery() const;
140*16467b97STreehugger Robot 	void set_perror_recovery( bool val );
141*16467b97STreehugger Robot 	bool hasFailed() const;
142*16467b97STreehugger Robot 	bool get_failedflag() const;
143*16467b97STreehugger Robot 	void set_failedflag( bool failed );
144*16467b97STreehugger Robot 	ANTLR_INT32 get_backtracking() const;
145*16467b97STreehugger Robot 	void inc_backtracking();
146*16467b97STreehugger Robot 	void dec_backtracking();
147*16467b97STreehugger Robot 	CommonTokenType* recoverFromMismatchedSet(BitsetListType*	follow);
148*16467b97STreehugger Robot 	bool	recoverFromMismatchedElement(BitsetListType*	follow);
149*16467b97STreehugger Robot 	RuleMemoType* getRuleMemo() const;
150*16467b97STreehugger Robot 	DebuggerType* get_debugger() const;
151*16467b97STreehugger Robot 	TokenStreamType* get_strstream() const;
152*16467b97STreehugger Robot 	void setRuleMemo(RuleMemoType* rulememo);
153*16467b97STreehugger Robot 
154*16467b97STreehugger Robot };
155*16467b97STreehugger Robot 
156*16467b97STreehugger Robot //Generic rule return value. Unlike the general ANTLR, this gets generated for
157*16467b97STreehugger Robot //every rule in the target. Handle rule exit here
158*16467b97STreehugger Robot template<class ImplTraits>
159*16467b97STreehugger Robot class RuleReturnValue
160*16467b97STreehugger Robot {
161*16467b97STreehugger Robot public:
162*16467b97STreehugger Robot 	typedef typename ImplTraits::BaseParserType BaseParserType;
163*16467b97STreehugger Robot 	typedef typename ImplTraits::CommonTokenType CommonTokenType;
164*16467b97STreehugger Robot 
165*16467b97STreehugger Robot public:
166*16467b97STreehugger Robot 	const CommonTokenType*		start;
167*16467b97STreehugger Robot 	const CommonTokenType*		stop;
168*16467b97STreehugger Robot 	BaseParserType*			parser;
169*16467b97STreehugger Robot 
170*16467b97STreehugger Robot 	RuleReturnValue(BaseParserType* psr = NULL );
171*16467b97STreehugger Robot 	RuleReturnValue( const RuleReturnValue& val );
172*16467b97STreehugger Robot 	RuleReturnValue& operator=( const RuleReturnValue& val );
173*16467b97STreehugger Robot 	void call_start_placeholder();
174*16467b97STreehugger Robot 	void call_stop_placeholder();
175*16467b97STreehugger Robot 	RuleReturnValue& get_struct();
176*16467b97STreehugger Robot 	~RuleReturnValue();
177*16467b97STreehugger Robot };
178*16467b97STreehugger Robot 
179*16467b97STreehugger Robot //This kind makes sure that whenever tokens are condensed into a rule,
180*16467b97STreehugger Robot //all the tokens except the start and stop tokens are deleted
181*16467b97STreehugger Robot template<class ImplTraits>
182*16467b97STreehugger Robot class RuleReturnValue_1 : public RuleReturnValue<ImplTraits>
183*16467b97STreehugger Robot {
184*16467b97STreehugger Robot public:
185*16467b97STreehugger Robot 	typedef RuleReturnValue<ImplTraits> BaseType;
186*16467b97STreehugger Robot 	typedef typename BaseType::BaseParserType BaseParserType;
187*16467b97STreehugger Robot 
188*16467b97STreehugger Robot public:
189*16467b97STreehugger Robot 	RuleReturnValue_1();
190*16467b97STreehugger Robot 	RuleReturnValue_1( BaseParserType* psr);
191*16467b97STreehugger Robot 	RuleReturnValue_1( const RuleReturnValue_1& val );
192*16467b97STreehugger Robot 	void call_start_placeholder();  //its dummy here
193*16467b97STreehugger Robot 	~RuleReturnValue_1();
194*16467b97STreehugger Robot };
195*16467b97STreehugger Robot 
196*16467b97STreehugger Robot ANTLR_END_NAMESPACE()
197*16467b97STreehugger Robot 
198*16467b97STreehugger Robot #include "antlr3parser.inl"
199*16467b97STreehugger Robot 
200*16467b97STreehugger Robot #endif
201