1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
|
/*
* Copyright 2001-2007 Adrian Thurston <thurston@complang.org>
*/
/* This file is part of Colm.
*
* Colm is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* Colm is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Colm; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#ifndef RLPARSE_H
#define RLPARSE_H
#include <iostream>
#include "avltree.h"
#include "parsedata.h"
#define PROPERTY_REDUCE_FIRST 0x1
struct ColmParser
{
ColmParser( Compiler *pd, const char *fileName, const char *sectionName, const InputLoc §ionLoc )
: pd(pd), sectionName(sectionName), enterRl(false)
{}
%%{
parser ColmParser;
# Use a class for tokens.
token uses class Token;
# Atoms.
token TK_Word, TK_Literal, TK_SingleLit, TK_DoubleLit, TK_Number, TK_UInt,
TK_Hex, KW_Nil, KW_True, KW_False;
# General tokens.
token TK_DotDot, TK_ColonGt, TK_ColonGtGt, TK_LtColon,
TK_DoubleArrow, TK_StarStar, TK_NameSep, TK_DashDash, TK_DoubleEql,
TK_NotEql, TK_DoubleColon, TK_LessEql, TK_GrtrEql, TK_RightArrow,
TK_LitPat, TK_AmpAmp, TK_BarBar, TK_SqOpen, TK_SqOpenNeg, TK_SqClose,
TK_Dash, TK_ReChar, TK_LtLt;
# Defining things.
token KW_Rl, KW_Def, KW_Lex, KW_Context, KW_Ignore, KW_Token, KW_Commit, KW_Namespace,
KW_Literal, KW_ReduceFirst, KW_Map, KW_List, KW_Vector, KW_Parser, KW_Global, KW_Export,
KW_Iter, KW_Reject, KW_Ptr, KW_Ref, KW_Deref;
# Language.
token KW_If, KW_While, KW_Else, KW_Elsif, KW_For, KW_Return, KW_Yield, KW_In,
KW_Break, KW_PrintXMLAC, KW_PrintXML, KW_Print, KW_PrintStream, KW_Require;
# Patterns.
token KW_Match, KW_Construct, KW_Parse, KW_ParseStop, KW_New, KW_MakeToken,
KW_MakeTree, KW_TypeId, KW_Alias, KW_Send, KW_Ni, KW_Ci;
token KW_Include, KW_Preeof;
token KW_Left, KW_Right, KW_Nonassoc, KW_Prec;
}%%
%% write instance_data;
void init();
int parseLangEl( int type, const Token *token );
int token( InputLoc &loc, int tokId, char *tokstart, int toklen );
void addRegularDef( const InputLoc &loc, Namespace *nspace,
const String &name, Join *join );
TokenRegion *createRegion( String &name );
void addRegionDef( const InputLoc &loc, Namespace *nspace,
const String &name, TokenRegion *join );
void addProduction( const InputLoc &loc, const String &name,
ProdElList *prodElList, bool commit, CodeBlock *redBlock, LangEl *predOf );
void addArgvList();
/* Report an error encountered by the parser. */
ostream &parse_error( int tokId, Token &token );
Compiler *pd;
/* The name of the root section, this does not change during an include. */
const char *sectionName;
NameRef nameRef;
NameRefList nameRefList;
LangElVect langElVect;
PatternItemList *patternItemList;
ReplItemList *replItemList;
RegionVect regionStack;
NamespaceVect namespaceStack;
ContextVect contextStack;
String curDefineId;
LelDefList *curDefList;
ProdElList *curProdElList;
PredType predType;
ReCaptureVect reCaptureVect;
bool enterRl;
};
%% write token_defs;
#endif
|
