diff options
Diffstat (limited to 'colm/lmparse.kh')
-rw-r--r-- | colm/lmparse.kh | 111 |
1 files changed, 111 insertions, 0 deletions
diff --git a/colm/lmparse.kh b/colm/lmparse.kh new file mode 100644 index 00000000..2cc3e99a --- /dev/null +++ b/colm/lmparse.kh @@ -0,0 +1,111 @@ +/* + * 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" + +struct Parser +{ + %%{ + parser Parser; + + # 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; + + # Defining things. + token KW_Rl, KW_Def, KW_Lex, KW_Ignore, KW_Token, KW_Commit, KW_Namespace, + KW_Literal, KW_ReduceFirst, KW_Map, KW_List, KW_Vector, KW_Global, + 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_Require; + + # Patterns. + token KW_Match, KW_Construct, KW_Parse, KW_ParseStop, KW_New, KW_MakeToken, + KW_MakeTree, KW_TypeId; + + 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 ); + + Parser( const char *fileName, const char *sectionName, const InputLoc §ionLoc ) + : sectionName(sectionName) + { + pd = new ParseData( fileName, sectionName, sectionLoc, std::cout ); + } + + int token( InputLoc &loc, int tokId, char *tokstart, int toklen ); + void addRegularDef( const InputLoc &loc, Namespace *nspace, + const String &name, JoinOrLm *joinOrLm, bool isInstance ); + void addProduction( InputLoc &loc, const String &name, + ProdElList *prodElList, bool commit, CodeBlock *redBlock, KlangEl *predOf ); + + /* Report an error encountered by the parser. */ + ostream &parse_error( int tokId, Token &token ); + + ParseData *pd; + + /* The name of the root section, this does not change during an include. */ + const char *sectionName; + + NameRef nameRef; + NameRefList nameRefList; + + KlangElVect langElVect; + + PatternItemList *patternItemList; + ReplItemList *replItemList; + RegionVect regionStack; + NamespaceVect namespaceStack; + + String curDefineId; + ProdElList *curProdElList; + + PredType predType; + ReCaptureVect reCaptureVect; +}; + +%% write token_defs; + +#endif |