lib/libc/regex/regex2.h

   1 /*-
   2  * Copyright (c) 1992, 1993, 1994 Henry Spencer.
   3  * Copyright (c) 1992, 1993, 1994
   4  *      The Regents of the University of California.  All rights reserved.
   5  *
   6  * This code is derived from software contributed to Berkeley by
   7  * Henry Spencer.
   8  *
   9  * Redistribution and use in source and binary forms, with or without
  10  * modification, are permitted provided that the following conditions
  11  * are met:
  12  * 1. Redistributions of source code must retain the above copyright
  13  *    notice, this list of conditions and the following disclaimer.
  14  * 2. Redistributions in binary form must reproduce the above copyright
  15  *    notice, this list of conditions and the following disclaimer in the
  16  *    documentation and/or other materials provided with the distribution.
  17  * 3. All advertising materials mentioning features or use of this software
  18  *    must display the following acknowledgement:
  19  *      This product includes software developed by the University of
  20  *      California, Berkeley and its contributors.
  21  * 4. Neither the name of the University nor the names of its contributors
  22  *    may be used to endorse or promote products derived from this software
  23  *    without specific prior written permission.
  24  *
  25  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  26  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  27  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  28  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  29  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  30  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  31  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  32  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  33  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  34  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  35  * SUCH DAMAGE.
  36  *
  37  *      @(#)regex2.h    8.4 (Berkeley) 3/20/94
  38  *
  39  * $FreeBSD: src/lib/libc/regex/regex2.h,v 1.3.6.1 2000/07/31 06:30:37 dcs Exp $
  40  * $DragonFly: src/lib/libc/regex/regex2.h,v 1.2 2003/06/17 04:26:44 dillon Exp $
  41  */
  42
  43 /*
  44  * First, the stuff that ends up in the outside-world include file
  45  = typedef off_t regoff_t;
  46  = typedef struct {
  47  =      int re_magic;
  48  =      size_t re_nsub;         // number of parenthesized subexpressions
  49  =      const char *re_endp;    // end pointer for REG_PEND
  50  =      struct re_guts *re_g;   // none of your business :-)
  51  = } regex_t;
  52  = typedef struct {
  53  =      regoff_t rm_so;         // start of match
  54  =      regoff_t rm_eo;         // end of match
  55  = } regmatch_t;
  56  */
  57 /*
  58  * internals of regex_t
  59  */
  60 #define MAGIC1  ((('r'^0200)<<8) | 'e')
  61
  62 /*
  63  * The internal representation is a *strip*, a sequence of
  64  * operators ending with an endmarker.  (Some terminology etc. is a
  65  * historical relic of earlier versions which used multiple strips.)
  66  * Certain oddities in the representation are there to permit running
  67  * the machinery backwards; in particular, any deviation from sequential
  68  * flow must be marked at both its source and its destination.  Some
  69  * fine points:
  70  *
  71  * - OPLUS_ and O_PLUS are *inside* the loop they create.
  72  * - OQUEST_ and O_QUEST are *outside* the bypass they create.
  73  * - OCH_ and O_CH are *outside* the multi-way branch they create, while
  74  *   OOR1 and OOR2 are respectively the end and the beginning of one of
  75  *   the branches.  Note that there is an implicit OOR2 following OCH_
  76  *   and an implicit OOR1 preceding O_CH.
  77  *
  78  * In state representations, an operator's bit is on to signify a state
  79  * immediately *preceding* "execution" of that operator.
  80  */
  81 typedef unsigned long sop;      /* strip operator */
  82 typedef long sopno;
  83 #define OPRMASK 0xf8000000L
  84 #define OPDMASK 0x07ffffffL
  85 #define OPSHIFT ((unsigned)27)
  86 #define OP(n)   ((n)&OPRMASK)
  87 #define OPND(n) ((n)&OPDMASK)
  88 #define SOP(op, opnd)   ((op)|(opnd))
  89 /* operators                       meaning      operand                 */
  90 /*                                              (back, fwd are offsets) */
  91 #define OEND    (1L<<OPSHIFT)   /* endmarker    -                       */
  92 #define OCHAR   (2L<<OPSHIFT)   /* character    unsigned char           */
  93 #define OBOL    (3L<<OPSHIFT)   /* left anchor  -                       */
  94 #define OEOL    (4L<<OPSHIFT)   /* right anchor -                       */
  95 #define OANY    (5L<<OPSHIFT)   /* .            -                       */
  96 #define OANYOF  (6L<<OPSHIFT)   /* [...]        set number              */
  97 #define OBACK_  (7L<<OPSHIFT)   /* begin \d     paren number            */
  98 #define O_BACK  (8L<<OPSHIFT)   /* end \d       paren number            */
  99 #define OPLUS_  (9L<<OPSHIFT)   /* + prefix     fwd to suffix           */
 100 #define O_PLUS  (10L<<OPSHIFT)  /* + suffix     back to prefix          */
 101 #define OQUEST_ (11L<<OPSHIFT)  /* ? prefix     fwd to suffix           */
 102 #define O_QUEST (12L<<OPSHIFT)  /* ? suffix     back to prefix          */
 103 #define OLPAREN (13L<<OPSHIFT)  /* (            fwd to )                */
 104 #define ORPAREN (14L<<OPSHIFT)  /* )            back to (               */
 105 #define OCH_    (15L<<OPSHIFT)  /* begin choice fwd to OOR2             */
 106 #define OOR1    (16L<<OPSHIFT)  /* | pt. 1      back to OOR1 or OCH_    */
 107 #define OOR2    (17L<<OPSHIFT)  /* | pt. 2      fwd to OOR2 or O_CH     */
 108 #define O_CH    (18L<<OPSHIFT)  /* end choice   back to OOR1            */
 109 #define OBOW    (19L<<OPSHIFT)  /* begin word   -                       */
 110 #define OEOW    (20L<<OPSHIFT)  /* end word     -                       */
 111
 112 /*
 113  * Structure for [] character-set representation.  Character sets are
 114  * done as bit vectors, grouped 8 to a byte vector for compactness.
 115  * The individual set therefore has both a pointer to the byte vector
 116  * and a mask to pick out the relevant bit of each byte.  A hash code
 117  * simplifies testing whether two sets could be identical.
 118  *
 119  * This will get trickier for multicharacter collating elements.  As
 120  * preliminary hooks for dealing with such things, we also carry along
 121  * a string of multi-character elements, and decide the size of the
 122  * vectors at run time.
 123  */
 124 typedef struct {
 125         uch *ptr;               /* -> uch [csetsize] */
 126         uch mask;               /* bit within array */
 127         short hash;             /* hash code */
 128         size_t smultis;
 129         char *multis;           /* -> char[smulti]  ab\0cd\0ef\0\0 */
 130 } cset;
 131 /* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
 132 #define CHadd(cs, c)    ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (uch)(c))
 133 #define CHsub(cs, c)    ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (uch)(c))
 134 #define CHIN(cs, c)     ((cs)->ptr[(uch)(c)] & (cs)->mask)
 135 #define MCadd(p, cs, cp)        mcadd(p, cs, cp)        /* regcomp() internal fns */
 136 #define MCsub(p, cs, cp)        mcsub(p, cs, cp)
 137 #define MCin(p, cs, cp) mcin(p, cs, cp)
 138
 139 /* stuff for character categories */
 140 typedef unsigned char cat_t;
 141
 142 /*
 143  * main compiled-expression structure
 144  */
 145 struct re_guts {
 146         int magic;
 147 #               define  MAGIC2  ((('R'^0200)<<8)|'E')
 148         sop *strip;             /* malloced area for strip */
 149         int csetsize;           /* number of bits in a cset vector */
 150         int ncsets;             /* number of csets in use */
 151         cset *sets;             /* -> cset [ncsets] */
 152         uch *setbits;           /* -> uch[csetsize][ncsets/CHAR_BIT] */
 153         int cflags;             /* copy of regcomp() cflags argument */
 154         sopno nstates;          /* = number of sops */
 155         sopno firststate;       /* the initial OEND (normally 0) */
 156         sopno laststate;        /* the final OEND */
 157         int iflags;             /* internal flags */
 158 #               define  USEBOL  01      /* used ^ */
 159 #               define  USEEOL  02      /* used $ */
 160 #               define  BAD     04      /* something wrong */
 161         int nbol;               /* number of ^ used */
 162         int neol;               /* number of $ used */
 163         int ncategories;        /* how many character categories */
 164         cat_t *categories;      /* ->catspace[-CHAR_MIN] */
 165         char *must;             /* match must contain this string */
 166         int moffset;            /* latest point at which must may be located */
 167         int *charjump;          /* Boyer-Moore char jump table */
 168         int *matchjump;         /* Boyer-Moore match jump table */
 169         int mlen;               /* length of must */
 170         size_t nsub;            /* copy of re_nsub */
 171         int backrefs;           /* does it use back references? */
 172         sopno nplus;            /* how deep does it nest +s? */
 173         /* catspace must be last */
 174         cat_t catspace[1];      /* actually [NC] */
 175 };
 176
 177 /* misc utilities */
 178 #define OUT     (CHAR_MAX+1)    /* a non-character value */
 179 #define ISWORD(c)       (isalnum((uch)(c)) || (c) == '_')