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
  40 /*
  41  * First, the stuff that ends up in the outside-world include file
  42  = typedef off_t regoff_t;
  43  = typedef struct {
  44  =      int re_magic;
  45  =      size_t re_nsub;         // number of parenthesized subexpressions
  46  =      const char *re_endp;    // end pointer for REG_PEND
  47  =      struct re_guts *re_g;   // none of your business :-)
  48  = } regex_t;
  49  = typedef struct {
  50  =      regoff_t rm_so;         // start of match
  51  =      regoff_t rm_eo;         // end of match
  52  = } regmatch_t;
  53  */
  54 /*
  55  * internals of regex_t
  56  */
  57 #define MAGIC1  ((('r'^0200)<<8) | 'e')
  58
  59 /*
  60  * The internal representation is a *strip*, a sequence of
  61  * operators ending with an endmarker.  (Some terminology etc. is a
  62  * historical relic of earlier versions which used multiple strips.)
  63  * Certain oddities in the representation are there to permit running
  64  * the machinery backwards; in particular, any deviation from sequential
  65  * flow must be marked at both its source and its destination.  Some
  66  * fine points:
  67  *
  68  * - OPLUS_ and O_PLUS are *inside* the loop they create.
  69  * - OQUEST_ and O_QUEST are *outside* the bypass they create.
  70  * - OCH_ and O_CH are *outside* the multi-way branch they create, while
  71  *   OOR1 and OOR2 are respectively the end and the beginning of one of
  72  *   the branches.  Note that there is an implicit OOR2 following OCH_
  73  *   and an implicit OOR1 preceding O_CH.
  74  *
  75  * In state representations, an operator's bit is on to signify a state
  76  * immediately *preceding* "execution" of that operator.
  77  */
  78 typedef unsigned long sop;      /* strip operator */
  79 typedef long sopno;
  80 #define OPRMASK 0xf8000000
  81 #define OPDMASK 0x07ffffff
  82 #define OPSHIFT ((unsigned)27)
  83 #define OP(n)   ((n)&OPRMASK)
  84 #define OPND(n) ((n)&OPDMASK)
  85 #define SOP(op, opnd)   ((op)|(opnd))
  86 /* operators                       meaning      operand                 */
  87 /*                                              (back, fwd are offsets) */
  88 #define OEND    (1<<OPSHIFT)    /* endmarker    -                       */
  89 #define OCHAR   (2<<OPSHIFT)    /* character    unsigned char           */
  90 #define OBOL    (3<<OPSHIFT)    /* left anchor  -                       */
  91 #define OEOL    (4<<OPSHIFT)    /* right anchor -                       */
  92 #define OANY    (5<<OPSHIFT)    /* .            -                       */
  93 #define OANYOF  (6<<OPSHIFT)    /* [...]        set number              */
  94 #define OBACK_  (7<<OPSHIFT)    /* begin \d     paren number            */
  95 #define O_BACK  (8<<OPSHIFT)    /* end \d       paren number            */
  96 #define OPLUS_  (9<<OPSHIFT)    /* + prefix     fwd to suffix           */
  97 #define O_PLUS  (10<<OPSHIFT)   /* + suffix     back to prefix          */
  98 #define OQUEST_ (11<<OPSHIFT)   /* ? prefix     fwd to suffix           */
  99 #define O_QUEST (12<<OPSHIFT)   /* ? suffix     back to prefix          */
 100 #define OLPAREN (13<<OPSHIFT)   /* (            fwd to )                */
 101 #define ORPAREN (14<<OPSHIFT)   /* )            back to (               */
 102 #define OCH_    (15<<OPSHIFT)   /* begin choice fwd to OOR2             */
 103 #define OOR1    (16<<OPSHIFT)   /* | pt. 1      back to OOR1 or OCH_    */
 104 #define OOR2    (17<<OPSHIFT)   /* | pt. 2      fwd to OOR2 or O_CH     */
 105 #define O_CH    (18<<OPSHIFT)   /* end choice   back to OOR1            */
 106 #define OBOW    (19<<OPSHIFT)   /* begin word   -                       */
 107 #define OEOW    (20<<OPSHIFT)   /* end word     -                       */
 108
 109 /*
 110  * Structure for [] character-set representation.  Character sets are
 111  * done as bit vectors, grouped 8 to a byte vector for compactness.
 112  * The individual set therefore has both a pointer to the byte vector
 113  * and a mask to pick out the relevant bit of each byte.  A hash code
 114  * simplifies testing whether two sets could be identical.
 115  *
 116  * This will get trickier for multicharacter collating elements.  As
 117  * preliminary hooks for dealing with such things, we also carry along
 118  * a string of multi-character elements, and decide the size of the
 119  * vectors at run time.
 120  */
 121 typedef struct {
 122         uch *ptr;               /* -> uch [csetsize] */
 123         uch mask;               /* bit within array */
 124         uch hash;               /* hash code */
 125         size_t smultis;
 126         char *multis;           /* -> char[smulti]  ab\0cd\0ef\0\0 */
 127 } cset;
 128 /* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
 129 #define CHadd(cs, c)    ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
 130 #define CHsub(cs, c)    ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
 131 #define CHIN(cs, c)     ((cs)->ptr[(uch)(c)] & (cs)->mask)
 132 #define MCadd(p, cs, cp)        mcadd(p, cs, cp)        /* regcomp() internal fns */
 133 #define MCsub(p, cs, cp)        mcsub(p, cs, cp)
 134 #define MCin(p, cs, cp) mcin(p, cs, cp)
 135
 136 /* stuff for character categories */
 137 typedef unsigned char cat_t;
 138
 139 /*
 140  * main compiled-expression structure
 141  */
 142 struct re_guts {
 143         int magic;
 144 #               define  MAGIC2  ((('R'^0200)<<8)|'E')
 145         sop *strip;             /* malloced area for strip */
 146         int csetsize;           /* number of bits in a cset vector */
 147         int ncsets;             /* number of csets in use */
 148         cset *sets;             /* -> cset [ncsets] */
 149         uch *setbits;           /* -> uch[csetsize][ncsets/CHAR_BIT] */
 150         int cflags;             /* copy of regcomp() cflags argument */
 151         sopno nstates;          /* = number of sops */
 152         sopno firststate;       /* the initial OEND (normally 0) */
 153         sopno laststate;        /* the final OEND */
 154         int iflags;             /* internal flags */
 155 #               define  USEBOL  01      /* used ^ */
 156 #               define  USEEOL  02      /* used $ */
 157 #               define  BAD     04      /* something wrong */
 158         int nbol;               /* number of ^ used */
 159         int neol;               /* number of $ used */
 160         int ncategories;        /* how many character categories */
 161         cat_t *categories;      /* ->catspace[-CHAR_MIN] */
 162         char *must;             /* match must contain this string */
 163         int mlen;               /* length of must */
 164         size_t nsub;            /* copy of re_nsub */
 165         int backrefs;           /* does it use back references? */
 166         sopno nplus;            /* how deep does it nest +s? */
 167         /* catspace must be last */
 168         cat_t catspace[1];      /* actually [NC] */
 169 };
 170
 171 /* misc utilities */
 172 #define OUT     (CHAR_MAX+1)    /* a non-character value */
 173 #define ISWORD(c)       (isalnum(c) || (c) == '_')