| 1 | /* dfa.h - declarations for GNU deterministic regexp compiler
|
|---|
| 2 | Copyright (C) 1988, 1998, 2002, 2004 Free Software Foundation, Inc.
|
|---|
| 3 |
|
|---|
| 4 | This program is free software; you can redistribute it and/or modify
|
|---|
| 5 | it under the terms of the GNU General Public License as published by
|
|---|
| 6 | the Free Software Foundation; either version 2, or (at your option)
|
|---|
| 7 | any later version.
|
|---|
| 8 |
|
|---|
| 9 | This program is distributed in the hope that it will be useful,
|
|---|
| 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 12 | GNU General Public License for more details.
|
|---|
| 13 |
|
|---|
| 14 | You should have received a copy of the GNU General Public License
|
|---|
| 15 | along with this program; if not, write to the Free Software
|
|---|
| 16 | Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA */
|
|---|
| 17 |
|
|---|
| 18 | /* Written June, 1988 by Mike Haertel */
|
|---|
| 19 |
|
|---|
| 20 | /* FIXME:
|
|---|
| 21 | 2. We should not export so much of the DFA internals.
|
|---|
| 22 | In addition to clobbering modularity, we eat up valuable
|
|---|
| 23 | name space. */
|
|---|
| 24 |
|
|---|
| 25 | #ifdef __STDC__
|
|---|
| 26 | # ifndef _PTR_T
|
|---|
| 27 | # define _PTR_T
|
|---|
| 28 | typedef void * ptr_t;
|
|---|
| 29 | # endif
|
|---|
| 30 | #else
|
|---|
| 31 | # ifndef _PTR_T
|
|---|
| 32 | # define _PTR_T
|
|---|
| 33 | typedef char * ptr_t;
|
|---|
| 34 | # endif
|
|---|
| 35 | #endif
|
|---|
| 36 |
|
|---|
| 37 | #ifdef PARAMS
|
|---|
| 38 | # undef PARAMS
|
|---|
| 39 | #endif
|
|---|
| 40 | #if PROTOTYPES
|
|---|
| 41 | # define PARAMS(x) x
|
|---|
| 42 | #else
|
|---|
| 43 | # define PARAMS(x) ()
|
|---|
| 44 | #endif
|
|---|
| 45 |
|
|---|
| 46 | /* Number of bits in an unsigned char. */
|
|---|
| 47 | #ifndef CHARBITS
|
|---|
| 48 | #define CHARBITS 8
|
|---|
| 49 | #endif
|
|---|
| 50 |
|
|---|
| 51 | /* First integer value that is greater than any character code. */
|
|---|
| 52 | #define NOTCHAR (1 << CHARBITS)
|
|---|
| 53 |
|
|---|
| 54 | /* INTBITS need not be exact, just a lower bound. */
|
|---|
| 55 | #ifndef INTBITS
|
|---|
| 56 | #define INTBITS (CHARBITS * sizeof (int))
|
|---|
| 57 | #endif
|
|---|
| 58 |
|
|---|
| 59 | /* Number of ints required to hold a bit for every character. */
|
|---|
| 60 | #define CHARCLASS_INTS ((NOTCHAR + INTBITS - 1) / INTBITS)
|
|---|
| 61 |
|
|---|
| 62 | /* Sets of unsigned characters are stored as bit vectors in arrays of ints. */
|
|---|
| 63 | typedef int charclass[CHARCLASS_INTS];
|
|---|
| 64 |
|
|---|
| 65 | /* The regexp is parsed into an array of tokens in postfix form. Some tokens
|
|---|
| 66 | are operators and others are terminal symbols. Most (but not all) of these
|
|---|
| 67 | codes are returned by the lexical analyzer. */
|
|---|
| 68 |
|
|---|
| 69 | typedef enum
|
|---|
| 70 | {
|
|---|
| 71 | END = -1, /* END is a terminal symbol that matches the
|
|---|
| 72 | end of input; any value of END or less in
|
|---|
| 73 | the parse tree is such a symbol. Accepting
|
|---|
| 74 | states of the DFA are those that would have
|
|---|
| 75 | a transition on END. */
|
|---|
| 76 |
|
|---|
| 77 | /* Ordinary character values are terminal symbols that match themselves. */
|
|---|
| 78 |
|
|---|
| 79 | EMPTY = NOTCHAR, /* EMPTY is a terminal symbol that matches
|
|---|
| 80 | the empty string. */
|
|---|
| 81 |
|
|---|
| 82 | BACKREF, /* BACKREF is generated by \<digit>; it
|
|---|
| 83 | it not completely handled. If the scanner
|
|---|
| 84 | detects a transition on backref, it returns
|
|---|
| 85 | a kind of "semi-success" indicating that
|
|---|
| 86 | the match will have to be verified with
|
|---|
| 87 | a backtracking matcher. */
|
|---|
| 88 |
|
|---|
| 89 | BEGLINE, /* BEGLINE is a terminal symbol that matches
|
|---|
| 90 | the empty string if it is at the beginning
|
|---|
| 91 | of a line. */
|
|---|
| 92 |
|
|---|
| 93 | ENDLINE, /* ENDLINE is a terminal symbol that matches
|
|---|
| 94 | the empty string if it is at the end of
|
|---|
|
|---|
