external/bsd/nvi/dist/regex/regex2.h

   1 /*      $NetBSD: regex2.h,v 1.2 2013/11/22 15:52:06 christos Exp $ */
   2 /*-
   3  * Copyright (c) 1992, 1993, 1994 Henry Spencer.
   4  * Copyright (c) 1992, 1993, 1994
   5  *      The Regents of the University of California.  All rights reserved.
   6  *
   7  * This code is derived from software contributed to Berkeley by
   8  * Henry Spencer of the University of Toronto.
   9  *
  10  * Redistribution and use in source and binary forms, with or without
  11  * modification, are permitted provided that the following conditions
  12  * are met:
  13  * 1. Redistributions of source code must retain the above copyright
  14  *    notice, this list of conditions and the following disclaimer.
  15  * 2. Redistributions in binary form must reproduce the above copyright
  16  *    notice, this list of conditions and the following disclaimer in the
  17  *    documentation and/or other materials provided with the distribution.
  18  * 3. All advertising materials mentioning features or use of this software
  19  *    must display the following acknowledgement:
  20  *      This product includes software developed by the University of
  21  *      California, Berkeley and its contributors.
  22  * 4. Neither the name of the University nor the names of its contributors
  23  *    may be used to endorse or promote products derived from this software
  24  *    without specific prior written permission.
  25  *
  26  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  27  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  28  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  29  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  30  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  31  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  32  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  33  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  34  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  35  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  36  * SUCH DAMAGE.
  37  *
  38  *      @(#)regex2.h    8.3 (Berkeley) 3/16/94
  39  */
  40
  41 /*
  42  * First, the stuff that ends up in the outside-world include file
  43  = typedef off_t regoff_t;
  44  = typedef struct {
  45  =      int re_magic;
  46  =      size_t re_nsub;         // number of parenthesized subexpressions
  47  =      const char *re_endp;    // end pointer for REG_PEND
  48  =      struct re_guts *re_g;   // none of your business :-)
  49  = } regex_t;
  50  = typedef struct {
  51  =      regoff_t rm_so;         // start of match
  52  =      regoff_t rm_eo;         // end of match
  53  = } regmatch_t;
  54  */
  55 /*
  56  * internals of regex_t
  57  */
  58 #define MAGIC1  ((('r'^0200)<<8) | 'e')
  59
  60 /*
  61  * The internal representation is a *strip*, a sequence of
  62  * operators ending with an endmarker.  (Some terminology etc. is a
  63  * historical relic of earlier versions which used multiple strips.)
  64  * Certain oddities in the representation are there to permit running
  65  * the machinery backwards; in particular, any deviation from sequential
  66  * flow must be marked at both its source and its destination.  Some
  67  * fine points:
  68  *
  69  * - OPLUS_ and O_PLUS are *inside* the loop they create.
  70  * - OQUEST_ and O_QUEST are *outside* the bypass they create.
  71  * - OCH_ and O_CH are *outside* the multi-way branch they create, while
  72  *   OOR1 and OOR2 are respectively the end and the beginning of one of
  73  *   the branches.  Note that there is an implicit OOR2 following OCH_
  74  *   and an implicit OOR1 preceding O_CH.
  75  *
  76  * In state representations, an operator's bit is on to signify a state
  77  * immediately *preceding* "execution" of that operator.
  78  */
  79 typedef char sop;       /* strip operator */
  80 typedef size_t sopno;
  81 /* operators                       meaning      operand                 */
  82 /*                                              (back, fwd are offsets) */
  83 #define OEND    (1)             /* endmarker    -                       */
  84 #define OCHAR   (2)             /* character    unsigned char           */
  85 #define OBOL    (3)             /* left anchor  -                       */
  86 #define OEOL    (4)             /* right anchor -                       */
  87 #define OANY    (5)             /* .            -                       */
  88 #define OANYOF  (6)             /* [...]        set number              */
  89 #define OBACK_  (7)             /* begin \d     paren number            */
  90 #define O_BACK  (8)             /* end \d       paren number            */
  91 #define OPLUS_  (9)             /* + prefix     fwd to suffix           */
  92 #define O_PLUS  (10)            /* + suffix     back to prefix          */
  93 #define OQUEST_ (11)            /* ? prefix     fwd to suffix           */
  94 #define O_QUEST (12)            /* ? suffix     back to prefix          */
  95 #define OLPAREN (13)            /* (            fwd to )                */
  96 #define ORPAREN (14)            /* )            back to (               */
  97 #define OCH_    (15)            /* begin choice fwd to OOR2             */
  98 #define OOR1    (16)            /* | pt. 1      back to OOR1 or OCH_    */
  99 #define OOR2    (17)            /* | pt. 2      fwd to OOR2 or O_CH     */
 100 #define O_CH    (18)            /* end choice   back to OOR1            */
 101 #define OBOW    (19)            /* begin word   -                       */
 102 #define OEOW    (20)            /* end word     -                       */
 103
 104 /*
 105  * Structure for [] character-set representation.  Character sets are
 106  * done as bit vectors, grouped 8 to a byte vector for compactness.
 107  * The individual set therefore has both a pointer to the byte vector
 108  * and a mask to pick out the relevant bit of each byte.  A hash code
 109  * simplifies testing whether two sets could be identical.
 110  *
 111  * This will get trickier for multicharacter collating elements.  As
 112  * preliminary hooks for dealing with such things, we also carry along
 113  * a string of multi-character elements, and decide the size of the
 114  * vectors at run time.
 115  */
 116 typedef struct {
 117         uch *ptr;               /* -> uch [csetsize] */
 118         uch mask;               /* bit within array */
 119         uch hash;               /* hash code */
 120         size_t smultis;
 121         char *multis;           /* -> char[smulti]  ab\0cd\0ef\0\0 */
 122 } cset;
 123 /* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
 124 #define CHadd(cs, c)    ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
 125 #define CHsub(cs, c)    ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
 126 #define CHIN(cs, c)     ((cs)->ptr[(uch)(c)] & (cs)->mask)
 127 #define MCadd(p, cs, cp)        mcadd(p, cs, cp)        /* regcomp() internal fns */
 128 #define MCsub(p, cs, cp)        mcsub(p, cs, cp)
 129 #define MCin(p, cs, cp) mcin(p, cs, cp)
 130
 131 /* stuff for character categories */
 132 typedef RCHAR_T cat_t;
 133
 134 /*
 135  * main compiled-expression structure
 136  */
 137 struct re_guts {
 138         int magic;
 139 #               define  MAGIC2  ((('R'^0200)<<8)|'E')
 140         sop *strip;             /* malloced area for strip */
 141         RCHAR_T *stripdata;     /* malloced area for stripdata */
 142         size_t csetsize;        /* number of bits in a cset vector */
 143         size_t ncsets;          /* number of csets in use */
 144         cset *sets;             /* -> cset [ncsets] */
 145         uch *setbits;           /* -> uch[csetsize][ncsets/CHAR_BIT] */
 146         int cflags;             /* copy of regcomp() cflags argument */
 147         sopno nstates;          /* = number of sops */
 148         sopno firststate;       /* the initial OEND (normally 0) */
 149         sopno laststate;        /* the final OEND */
 150         int iflags;             /* internal flags */
 151 #               define  USEBOL  01      /* used ^ */
 152 #               define  USEEOL  02      /* used $ */
 153 #               define  BAD     04      /* something wrong */
 154         size_t nbol;            /* number of ^ used */
 155         size_t neol;            /* number of $ used */
 156 #if 0
 157         size_t ncategories;     /* how many character categories */
 158         cat_t *categories;      /* ->catspace[-CHAR_MIN] */
 159 #endif
 160         RCHAR_T *must;          /* match must contain this string */
 161         size_t mlen;            /* length of must */
 162         size_t nsub;            /* copy of re_nsub */
 163         int backrefs;           /* does it use back references? */
 164         sopno nplus;            /* how deep does it nest +s? */
 165         /* catspace must be last */
 166 #if 0
 167         cat_t catspace[1];      /* actually [NC] */
 168 #endif
 169 };
 170
 171 /* misc utilities */
 172 #define OUT     REOF    /* a non-character value */
 173 #define ISWORD(c) ((c) == '_' || (ISGRAPH((UCHAR_T)c) && !ISPUNCT((UCHAR_T)c)))