lib/libc/regex/regex2.h

   1 /*      $NetBSD: regex2.h,v 1.11 2004/03/26 22:42:17 enami Exp $        */
   2
   3 /*-
   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.
   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. Neither the name of the University nor the names of its contributors
  19  *    may be used to endorse or promote products derived from this software
  20  *    without specific prior written permission.
  21  *
  22  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  23  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  24  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  25  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  26  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  27  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  28  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  29  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  30  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  31  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  32  * SUCH DAMAGE.
  33  *
  34  *      @(#)regex2.h    8.4 (Berkeley) 3/20/94
  35  */
  36
  37 /*-
  38  * Copyright (c) 1992, 1993, 1994 Henry Spencer.
  39  *
  40  * This code is derived from software contributed to Berkeley by
  41  * Henry Spencer.
  42  *
  43  * Redistribution and use in source and binary forms, with or without
  44  * modification, are permitted provided that the following conditions
  45  * are met:
  46  * 1. Redistributions of source code must retain the above copyright
  47  *    notice, this list of conditions and the following disclaimer.
  48  * 2. Redistributions in binary form must reproduce the above copyright
  49  *    notice, this list of conditions and the following disclaimer in the
  50  *    documentation and/or other materials provided with the distribution.
  51  * 3. All advertising materials mentioning features or use of this software
  52  *    must display the following acknowledgement:
  53  *      This product includes software developed by the University of
  54  *      California, Berkeley and its contributors.
  55  * 4. Neither the name of the University nor the names of its contributors
  56  *    may be used to endorse or promote products derived from this software
  57  *    without specific prior written permission.
  58  *
  59  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  60  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  61  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  62  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  63  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  64  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  65  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  66  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  67  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  68  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  69  * SUCH DAMAGE.
  70  *
  71  *      @(#)regex2.h    8.4 (Berkeley) 3/20/94
  72  */
  73
  74 /*
  75  * First, the stuff that ends up in the outside-world include file
  76  = typedef off_t regoff_t;
  77  = typedef struct {
  78  =      int re_magic;
  79  =      size_t re_nsub;         // number of parenthesized subexpressions
  80  =      const char *re_endp;    // end pointer for REG_PEND
  81  =      struct re_guts *re_g;   // none of your business :-)
  82  = } regex_t;
  83  = typedef struct {
  84  =      regoff_t rm_so;         // start of match
  85  =      regoff_t rm_eo;         // end of match
  86  = } regmatch_t;
  87  */
  88 /*
  89  * internals of regex_t
  90  */
  91 #define MAGIC1  ((('r'^0200)<<8) | 'e')
  92
  93 /*
  94  * The internal representation is a *strip*, a sequence of
  95  * operators ending with an endmarker.  (Some terminology etc. is a
  96  * historical relic of earlier versions which used multiple strips.)
  97  * Certain oddities in the representation are there to permit running
  98  * the machinery backwards; in particular, any deviation from sequential
  99  * flow must be marked at both its source and its destination.  Some
 100  * fine points:
 101  *
 102  * - OPLUS_ and O_PLUS are *inside* the loop they create.
 103  * - OQUEST_ and O_QUEST are *outside* the bypass they create.
 104  * - OCH_ and O_CH are *outside* the multi-way branch they create, while
 105  *   OOR1 and OOR2 are respectively the end and the beginning of one of
 106  *   the branches.  Note that there is an implicit OOR2 following OCH_
 107  *   and an implicit OOR1 preceding O_CH.
 108  *
 109  * In state representations, an operator's bit is on to signify a state
 110  * immediately *preceding* "execution" of that operator.
 111  */
 112 typedef u_int32_t sop;  /* strip operator */
 113 typedef int sopno;
 114 #define OPRMASK ((u_int32_t)0xf8000000UL)
 115 #define OPDMASK ((u_int32_t)0x07ffffffUL)
 116 #define OPSHIFT ((unsigned)27)
 117 #define OP(n)   ((n)&OPRMASK)
 118 #define OPND(n) ((int)((n)&OPDMASK))
 119 #define SOP(op, opnd)   ((op)|(opnd))
 120
 121 #define OPC(n)  (((u_int32_t)(n))<<OPSHIFT)
 122 /* operators               meaning      operand                 */
 123 /*                                      (back, fwd are offsets) */
 124 #define OEND    OPC(1)  /* endmarker    -                       */
 125 #define OCHAR   OPC(2)  /* character    unsigned char           */
 126 #define OBOL    OPC(3)  /* left anchor  -                       */
 127 #define OEOL    OPC(4)  /* right anchor -                       */
 128 #define OANY    OPC(5)  /* .            -                       */
 129 #define OANYOF  OPC(6)  /* [...]        set number              */
 130 #define OBACK_  OPC(7)  /* begin \d     paren number            */
 131 #define O_BACK  OPC(8)  /* end \d       paren number            */
 132 #define OPLUS_  OPC(9)  /* + prefix     fwd to suffix           */
 133 #define O_PLUS  OPC(10) /* + suffix     back to prefix          */
 134 #define OQUEST_ OPC(11) /* ? prefix     fwd to suffix           */
 135 #define O_QUEST OPC(12) /* ? suffix     back to prefix          */
 136 #define OLPAREN OPC(13) /* (            fwd to )                */
 137 #define ORPAREN OPC(14) /* )            back to (               */
 138 #define OCH_    OPC(15) /* begin choice fwd to OOR2             */
 139 #define OOR1    OPC(16) /* | pt. 1      back to OOR1 or OCH_    */
 140 #define OOR2    OPC(17) /* | pt. 2      fwd to OOR2 or O_CH     */
 141 #define O_CH    OPC(18) /* end choice   back to OOR1            */
 142 #define OBOW    OPC(19) /* begin word   -                       */
 143 #define OEOW    OPC(20) /* end word     -                       */
 144
 145 /*
 146  * Structure for [] character-set representation.  Character sets are
 147  * done as bit vectors, grouped 8 to a byte vector for compactness.
 148  * The individual set therefore has both a pointer to the byte vector
 149  * and a mask to pick out the relevant bit of each byte.  A hash code
 150  * simplifies testing whether two sets could be identical.
 151  *
 152  * This will get trickier for multicharacter collating elements.  As
 153  * preliminary hooks for dealing with such things, we also carry along
 154  * a string of multi-character elements, and decide the size of the
 155  * vectors at run time.
 156  */
 157 typedef struct {
 158         uch *ptr;               /* -> uch [csetsize] */
 159         uch mask;               /* bit within array */
 160         uch hash;               /* hash code */
 161         size_t smultis;
 162         char *multis;           /* -> char[smulti]  ab\0cd\0ef\0\0 */
 163 } cset;
 164 /* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
 165 #define CHadd(cs, c)    ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
 166 #define CHsub(cs, c)    ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
 167 #define CHIN(cs, c)     ((cs)->ptr[(uch)(c)] & (cs)->mask)
 168 #define MCadd(p, cs, cp)        mcadd(p, cs, cp)        /* regcomp() internal fns */
 169 #define MCsub(p, cs, cp)        mcsub(p, cs, cp)
 170 #define MCin(p, cs, cp) mcin(p, cs, cp)
 171
 172 /* stuff for character categories */
 173 typedef unsigned char cat_t;
 174
 175 /*
 176  * main compiled-expression structure
 177  */
 178 struct re_guts {
 179         int magic;
 180 #               define  MAGIC2  ((('R'^0200)<<8)|'E')
 181         sop *strip;             /* malloced area for strip */
 182         int csetsize;           /* number of bits in a cset vector */
 183         int ncsets;             /* number of csets in use */
 184         cset *sets;             /* -> cset [ncsets] */
 185         uch *setbits;           /* -> uch[csetsize][ncsets/CHAR_BIT] */
 186         int cflags;             /* copy of regcomp() cflags argument */
 187         sopno nstates;          /* = number of sops */
 188         sopno firststate;       /* the initial OEND (normally 0) */
 189         sopno laststate;        /* the final OEND */
 190         int iflags;             /* internal flags */
 191 #               define  USEBOL  01      /* used ^ */
 192 #               define  USEEOL  02      /* used $ */
 193 #               define  BAD     04      /* something wrong */
 194         int nbol;               /* number of ^ used */
 195         int neol;               /* number of $ used */
 196         int ncategories;        /* how many character categories */
 197         cat_t *categories;      /* ->catspace[-CHAR_MIN] */
 198         char *must;             /* match must contain this string */
 199         int mlen;               /* length of must */
 200         size_t nsub;            /* copy of re_nsub */
 201         int backrefs;           /* does it use back references? */
 202         sopno nplus;            /* how deep does it nest +s? */
 203         /* catspace must be last */
 204         cat_t catspace[1];      /* actually [NC] */
 205 };
 206
 207 /* misc utilities */
 208 #define OUT     (CHAR_MAX+1)    /* a non-character value */
 209 #define ISWORD(c)       (isalnum((unsigned char)c) || (c) == '_')