2 * Defines the the class interface for an antlr3 INTSTREAM.
4 * Certain functionality (such as DFAs for instance) abstract the stream of tokens
5 * or characters in to a steam of integers. Hence this structure should be included
6 * in any stream that is able to provide the output as a stream of integers (which is anything
9 * There are no specific implementations of the methods in this interface in general. Though
10 * for purposes of casting and so on, it may be necesssary to implement a function with
11 * the signature in this interface which abstracts the base immplementation. In essence though
12 * the base stream provides a pointer to this interface, within which it installs its
13 * normal match() functions and so on. Interaces such as DFA are then passed the pANTLR3_INT_STREAM
14 * and can treat any input as an int stream.
16 * For instance, a lexer implements a pANTLR3_BASE_RECOGNIZER, within which there is a pANTLR3_INT_STREAM.
17 * However, a pANTLR3_INPUT_STREAM also provides a pANTLR3_INT_STREAM, which it has constructed from
18 * it's normal interface when it was created. This is then pointed at by the pANTLR_BASE_RECOGNIZER
19 * when it is intialized with a pANTLR3_INPUT_STREAM.
21 * Similarly if a pANTLR3_BASE_RECOGNIZER is initialized with a pANTLR3_TOKEN_STREAM, then the
22 * pANTLR3_INT_STREAM is taken from the pANTLR3_TOKEN_STREAM.
24 * If a pANTLR3_BASE_RECOGNIZER is initialized with a pANTLR3_TREENODE_STREAM, then guess where
25 * the pANTLR3_INT_STREAM comes from?
27 * Note that because the context pointer points to the actual interface structure that is providing
28 * the ANTLR3_INT_STREAM it is defined as a (void *) in this interface. There is no direct implementation
29 * of an ANTLR3_INT_STREAM (unless someone did not understand what I was doing here =;?P
31 #ifndef _ANTLR3_INTSTREAM_H
32 #define _ANTLR3_INTSTREAM_H
34 // [The "BSD licence"]
35 // Copyright (c) 2005-2009 Jim Idle, Temporal Wave LLC
36 // http://www.temporal-wave.com
37 // http://www.linkedin.com/in/jimidle
39 // All rights reserved.
41 // Redistribution and use in source and binary forms, with or without
42 // modification, are permitted provided that the following conditions
44 // 1. Redistributions of source code must retain the above copyright
45 // notice, this list of conditions and the following disclaimer.
46 // 2. Redistributions in binary form must reproduce the above copyright
47 // notice, this list of conditions and the following disclaimer in the
48 // documentation and/or other materials provided with the distribution.
49 // 3. The name of the author may not be used to endorse or promote products
50 // derived from this software without specific prior written permission.
52 // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
53 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
54 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
55 // IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
56 // INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
57 // NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
58 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
59 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
60 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
61 // THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
63 #include <antlr3defs.h>
64 #include <antlr3commontoken.h>
66 /** Type indicator for a character stream
67 * \remark if a custom stream is created but it can be treated as
68 * a char stream, then you may OR in this value to your type indicator
70 #define ANTLR3_CHARSTREAM 0x0001
72 /** Type indicator for a Token stream
73 * \remark if a custom stream is created but it can be treated as
74 * a token stream, then you may OR in this value to your type indicator
76 #define ANTLR3_TOKENSTREAM 0x0002
78 /** Type indicator for a common tree node stream
79 * \remark if a custom stream is created but it can be treated as
80 * a common tree node stream, then you may OR in this value to your type indicator
82 #define ANTLR3_COMMONTREENODE 0x0004
84 /** Type mask for input stream so we can switch in the above types
85 * \remark DO NOT USE 0x0000 as a stream type!
87 #define ANTLR3_INPUT_MASK 0x0007
93 typedef struct ANTLR3_INT_STREAM_struct
95 /** Input stream type indicator. Sometimes useful for error reporting etc.
99 /** Potentially useful in error reporting and so on, this string is
100 * an identification of the input source. It may be NULL, so anything
101 * attempting to access it needs to check this and substitute a sensible
104 pANTLR3_STRING streamName
;
106 /** Pointer to the super structure that contains this interface. This
107 * will usually be a token stream or a tree stream.
111 /** Last marker position allocated
113 ANTLR3_MARKER lastMarker
;
115 // Return a string that identifies the input source
117 pANTLR3_STRING (*getSourceName
) (struct ANTLR3_INT_STREAM_struct
* intStream
);
119 /** Consume the next 'ANTR3_UINT32' in the stream
121 void (*consume
) (struct ANTLR3_INT_STREAM_struct
* intStream
);
123 /** Get ANTLR3_UINT32 at current input pointer + i ahead where i=1 is next ANTLR3_UINT32
125 ANTLR3_UINT32 (*_LA
) (struct ANTLR3_INT_STREAM_struct
* intStream
, ANTLR3_INT32 i
);
127 /** Tell the stream to start buffering if it hasn't already. Return
128 * current input position, index(), or some other marker so that
129 * when passed to rewind() you get back to the same spot.
130 * rewind(mark()) should not affect the input cursor.
132 ANTLR3_MARKER (*mark
) (struct ANTLR3_INT_STREAM_struct
* intStream
);
134 /** Return the current input symbol index 0..n where n indicates the
135 * last symbol has been read.
137 ANTLR3_MARKER (*index
) (struct ANTLR3_INT_STREAM_struct
* intStream
);
139 /** Reset the stream so that next call to index would return marker.
140 * The marker will usually be index() but it doesn't have to be. It's
141 * just a marker to indicate what state the stream was in. This is
142 * essentially calling release() and seek(). If there are markers
143 * created after this marker argument, this routine must unroll them
144 * like a stack. Assume the state the stream was in when this marker
147 void (*rewind
) (struct ANTLR3_INT_STREAM_struct
* intStream
, ANTLR3_MARKER marker
);
149 /** Reset the stream to the last marker position, witouh destryoing the
150 * last marker position.
152 void (*rewindLast
) (struct ANTLR3_INT_STREAM_struct
* intStream
);
154 /** You may want to commit to a backtrack but don't want to force the
155 * stream to keep bookkeeping objects around for a marker that is
156 * no longer necessary. This will have the same behavior as
157 * rewind() except it releases resources without the backward seek.
159 void (*release
) (struct ANTLR3_INT_STREAM_struct
* intStream
, ANTLR3_MARKER mark
);
161 /** Set the input cursor to the position indicated by index. This is
162 * normally used to seek ahead in the input stream. No buffering is
163 * required to do this unless you know your stream will use seek to
164 * move backwards such as when backtracking.
166 * This is different from rewind in its multi-directional
167 * requirement and in that its argument is strictly an input cursor (index).
169 * For char streams, seeking forward must update the stream state such
170 * as line number. For seeking backwards, you will be presumably
171 * backtracking using the mark/rewind mechanism that restores state and
172 * so this method does not need to update state when seeking backwards.
174 * Currently, this method is only used for efficient backtracking, but
175 * in the future it may be used for incremental parsing.
177 void (*seek
) (struct ANTLR3_INT_STREAM_struct
* intStream
, ANTLR3_MARKER index
);
179 /** Only makes sense for streams that buffer everything up probably, but
180 * might be useful to display the entire stream or for testing.
182 ANTLR3_UINT32 (*size
) (struct ANTLR3_INT_STREAM_struct
* intStream
);
184 /** Because the indirect call, though small in individual cases can
185 * mount up if there are thousands of tokens (very large input streams), callers
186 * of size can optionally use this cached size field.
188 ANTLR3_UINT32 cachedSize
;
190 /** Frees any resources that were allocated for the implementation of this
191 * interface. Usually this is just releasing the memory allocated
192 * for the structure itself, but it may of course do anything it need to
193 * so long as it does not stamp on anything else.
195 void (*free
) (struct ANTLR3_INT_STREAM_struct
* stream
);