src/gram.h

   1 /* Data definitions for internal representation of bison's input,
   2    Copyright 1984, 1986, 1989, 1992, 2001  Free Software Foundation, Inc.
   3
   4    This file is part of Bison, the GNU Compiler Compiler.
   5
   6    Bison is free software; you can redistribute it and/or modify
   7    it under the terms of the GNU General Public License as published by
   8    the Free Software Foundation; either version 2, or (at your option)
   9    any later version.
  10
  11    Bison is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14    GNU General Public License for more details.
  15
  16    You should have received a copy of the GNU General Public License
  17    along with Bison; see the file COPYING.  If not, write to
  18    the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  19    Boston, MA 02111-1307, USA.  */
  20
  21 #ifndef GRAM_H_
  22 # define GRAM_H_
  23
  24 /* Representation of the grammar rules:
  25
  26    NTOKENS is the number of tokens, and NVARS is the number of
  27    variables (nonterminals).  NSYMS is the total number, ntokens +
  28    nvars.
  29
  30    Each symbol (either token or variable) receives a symbol number.
  31    Numbers 0 to NTOKENS - 1 are for tokens, and NTOKENS to NSYMS - 1
  32    are for variables.  Symbol number zero is the end-of-input token.
  33    This token is counted in ntokens.  The true number of token values
  34    assigned is NTOKENS reduced by one for each alias declaration.
  35
  36    The rules receive rule numbers 1 to NRULES in the order they are
  37    written.  More precisely Bison augments the grammar with the
  38    initial rule, `$axiom: START-SYMBOL EOF', which is numbered 1, all
  39    the user rules are 2, 3 etc.  Each time a rule number is presented
  40    to the user, we subtract 1, so *displayed* rule numbers are 0, 1,
  41    2...
  42
  43    Internally, we cannot use the number 0 for a rule because for
  44    instance RITEM stores both symbol (the RHS) and rule numbers: the
  45    symbols are shorts >= 0, and rule number are stored negative.
  46    Therefore 0 cannot be used, since it would be both the rule number
  47    0, and the token EOF).
  48
  49    Actions and guards are accessed via the rule number.
  50
  51    The rules themselves are described by several arrays: amongst which
  52    RITEM, and RULES.
  53
  54    RULES is an array of struct rule_s, which members are:
  55
  56    RULES[R].lhs -- the symbol number of the left hand side of rule R.
  57    If -1, the rule has been thrown out by reduce.c and should be
  58    ignored.
  59
  60    RULES[R].rhs -- the index in RITEM of the beginning of the portion
  61    for rule R.
  62
  63    RULES[R].prec -- the precedence level of R.
  64
  65    RULES[R].precsym -- the symbol-number of the symbol in %prec for R
  66    (if any).
  67
  68    RULES[R].assoc -- the associativity of R.
  69
  70    RULES[R].line -- the line where R was defined.
  71
  72    RULES[R].useful -- TRUE iff the rule is used.
  73
  74    The right hand side is stored as symbol numbers in a portion of
  75    RITEM.
  76
  77    The length of the portion is one greater than the number of symbols
  78    in the rule's right hand side.  The last element in the portion
  79    contains minus R, which identifies it as the end of a portion and
  80    says which rule it is for.
  81
  82    The portions of RITEM come in order of increasing rule number and
  83    are followed by an element which is zero to mark the end.  nitems
  84    is the total length of ritem, not counting the final zero.  Each
  85    element of RITEM is called an "item" and its index in RITEM is an
  86    item number.
  87
  88    Item numbers are used in the finite state machine to represent
  89    places that parsing can get to.
  90
  91    SYMBOLS[I]->prec records the precedence level of each symbol.
  92
  93    Precedence levels are assigned in increasing order starting with 1
  94    so that numerically higher precedence values mean tighter binding
  95    as they ought to.  Zero as a symbol or rule's precedence means none
  96    is assigned.
  97
  98    Associativities are recorded similarly in SYMBOLS[I]->assoc.  */
  99
 100
 101 #define ISTOKEN(s)      ((s) < ntokens)
 102 #define ISVAR(s)        ((s) >= ntokens)
 103
 104 extern int nitems;
 105 extern int nrules;
 106 extern int nsyms;
 107 extern int ntokens;
 108 extern int nvars;
 109
 110 extern short *ritem;
 111 extern int nritems;
 112
 113 extern int start_symbol;
 114
 115 /* Associativity values for tokens and rules.  */
 116 typedef enum
 117 {
 118   right_assoc,
 119   left_assoc,
 120   non_assoc
 121 } associativity;
 122
 123
 124 typedef struct rule_s
 125 {
 126   short lhs;
 127   short rhs;
 128   short prec;
 129   short precsym;
 130   associativity assoc;
 131   short line;
 132   bool useful;
 133
 134   const char *action;
 135   short action_line;
 136
 137   const char *guard;
 138   short guard_line;
 139 } rule_t;
 140
 141 extern struct rule_s *rules;
 142
 143 /* Table of the symbols, indexed by the symbol number. */
 144 extern struct bucket **symbols;
 145
 146 /* token translation table: indexed by a token number as returned by
 147    the user's yylex routine, it yields the internal token number used
 148    by the parser and throughout bison.  */
 149
 150 extern short *token_translations;
 151 extern int max_user_token_number;
 152
 153 /* SEMANTIC_PARSER is nonzero if the input file says to use the hairy
 154    parser that provides for semantic error recovery.  If it is zero,
 155    the yacc-compatible simplified parser is used.  */
 156
 157 extern int semantic_parser;
 158
 159 /* PURE_PARSER is nonzero if should generate a parser that is all pure
 160    and reentrant.  */
 161
 162 extern int pure_parser;
 163
 164 /* ERROR_TOKEN_NUMBER is the token number of the error token.  */
 165
 166 extern int error_token_number;
 167
 168
 169 /* Dump RITEM for traces. */
 170 void ritem_print PARAMS ((FILE *out));
 171
 172 /* Return the size of the longest rule RHS.  */
 173 size_t ritem_longest_rhs PARAMS ((void));
 174
 175 #endif /* !GRAM_H_ */