regex.subproj/regex2.h

   1 /*
   2  * Copyright (c) 1999 Apple Computer, Inc. All rights reserved.
   3  *
   4  * @APPLE_LICENSE_HEADER_START@
   5  *
   6  * The contents of this file constitute Original Code as defined in and
   7  * are subject to the Apple Public Source License Version 1.1 (the
   8  * "License").  You may not use this file except in compliance with the
   9  * License.  Please obtain a copy of the License at
  10  * http://www.apple.com/publicsource and read it before using this file.
  11  *
  12  * This Original Code and all software distributed under the License are
  13  * distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, EITHER
  14  * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
  15  * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
  16  * FITNESS FOR A PARTICULAR PURPOSE OR NON-INFRINGEMENT.  Please see the
  17  * License for the specific language governing rights and limitations
  18  * under the License.
  19  *
  20  * @APPLE_LICENSE_HEADER_END@
  21  */
  22 /*
  23  * Copyright (c) 1992, 1993, 1994
  24  *      The Regents of the University of California.  All rights reserved.
  25  *
  26  * This code is derived from software contributed to Berkeley by
  27  * Henry Spencer.
  28  *
  29  * Redistribution and use in source and binary forms, with or without
  30  * modification, are permitted provided that the following conditions
  31  * are met:
  32  * 1. Redistributions of source code must retain the above copyright
  33  *    notice, this list of conditions and the following disclaimer.
  34  * 2. Redistributions in binary form must reproduce the above copyright
  35  *    notice, this list of conditions and the following disclaimer in the
  36  *    documentation and/or other materials provided with the distribution.
  37  * 3. All advertising materials mentioning features or use of this software
  38  *    must display the following acknowledgement:
  39  *      This product includes software developed by the University of
  40  *      California, Berkeley and its contributors.
  41  * 4. Neither the name of the University nor the names of its contributors
  42  *    may be used to endorse or promote products derived from this software
  43  *    without specific prior written permission.
  44  *
  45  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  46  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  47  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  48  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  49  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  50  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  51  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  52  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  53  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  54  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  55  * SUCH DAMAGE.
  56  */
  57
  58 /*
  59  * First, the stuff that ends up in the outside-world include file
  60  = typedef off_t regoff_t;
  61  = typedef struct {
  62  =      int re_magic;
  63  =      size_t re_nsub;         // number of parenthesized subexpressions
  64  =      const char *re_endp;    // end pointer for REG_PEND
  65  =      struct re_guts *re_g;   // none of your business :-)
  66  = } regex_t;
  67  = typedef struct {
  68  =      regoff_t rm_so;         // start of match
  69  =      regoff_t rm_eo;         // end of match
  70  = } regmatch_t;
  71  */
  72 /*
  73  * internals of regex_t
  74  */
  75 #define MAGIC1  ((('r'^0200)<<8) | 'e')
  76
  77 /*
  78  * The internal representation is a *strip*, a sequence of
  79  * operators ending with an endmarker.  (Some terminology etc. is a
  80  * historical relic of earlier versions which used multiple strips.)
  81  * Certain oddities in the representation are there to permit running
  82  * the machinery backwards; in particular, any deviation from sequential
  83  * flow must be marked at both its source and its destination.  Some
  84  * fine points:
  85  *
  86  * - OPLUS_ and O_PLUS are *inside* the loop they create.
  87  * - OQUEST_ and O_QUEST are *outside* the bypass they create.
  88  * - OCH_ and O_CH are *outside* the multi-way branch they create, while
  89  *   OOR1 and OOR2 are respectively the end and the beginning of one of
  90  *   the branches.  Note that there is an implicit OOR2 following OCH_
  91  *   and an implicit OOR1 preceding O_CH.
  92  *
  93  * In state representations, an operator's bit is on to signify a state
  94  * immediately *preceding* "execution" of that operator.
  95  */
  96 typedef unsigned long sop;      /* strip operator */
  97 typedef long sopno;
  98 #define OPRMASK 0xf8000000
  99 #define OPDMASK 0x07ffffff
 100 #define OPSHIFT ((unsigned)27)
 101 #define OP(n)   ((n)&OPRMASK)
 102 #define OPND(n) ((n)&OPDMASK)
 103 #define SOP(op, opnd)   ((op)|(opnd))
 104 /* operators                       meaning      operand                 */
 105 /*                                              (back, fwd are offsets) */
 106 #define OEND    (1<<OPSHIFT)    /* endmarker    -                       */
 107 #define OCHAR   (2<<OPSHIFT)    /* character    unsigned char           */
 108 #define OBOL    (3<<OPSHIFT)    /* left anchor  -                       */
 109 #define OEOL    (4<<OPSHIFT)    /* right anchor -                       */
 110 #define OANY    (5<<OPSHIFT)    /* .            -                       */
 111 #define OANYOF  (6<<OPSHIFT)    /* [...]        set number              */
 112 #define OBACK_  (7<<OPSHIFT)    /* begin \d     paren number            */
 113 #define O_BACK  (8<<OPSHIFT)    /* end \d       paren number            */
 114 #define OPLUS_  (9<<OPSHIFT)    /* + prefix     fwd to suffix           */
 115 #define O_PLUS  (10<<OPSHIFT)   /* + suffix     back to prefix          */
 116 #define OQUEST_ (11<<OPSHIFT)   /* ? prefix     fwd to suffix           */
 117 #define O_QUEST (12<<OPSHIFT)   /* ? suffix     back to prefix          */
 118 #define OLPAREN (13<<OPSHIFT)   /* (            fwd to )                */
 119 #define ORPAREN (14<<OPSHIFT)   /* )            back to (               */
 120 #define OCH_    (15<<OPSHIFT)   /* begin choice fwd to OOR2             */
 121 #define OOR1    (16<<OPSHIFT)   /* | pt. 1      back to OOR1 or OCH_    */
 122 #define OOR2    (17<<OPSHIFT)   /* | pt. 2      fwd to OOR2 or O_CH     */
 123 #define O_CH    (18<<OPSHIFT)   /* end choice   back to OOR1            */
 124 #define OBOW    (19<<OPSHIFT)   /* begin word   -                       */
 125 #define OEOW    (20<<OPSHIFT)   /* end word     -                       */
 126
 127 /*
 128  * Structure for [] character-set representation.  Character sets are
 129  * done as bit vectors, grouped 8 to a byte vector for compactness.
 130  * The individual set therefore has both a pointer to the byte vector
 131  * and a mask to pick out the relevant bit of each byte.  A hash code
 132  * simplifies testing whether two sets could be identical.
 133  *
 134  * This will get trickier for multicharacter collating elements.  As
 135  * preliminary hooks for dealing with such things, we also carry along
 136  * a string of multi-character elements, and decide the size of the
 137  * vectors at run time.
 138  */
 139 typedef struct {
 140         uch *ptr;               /* -> uch [csetsize] */
 141         uch mask;               /* bit within array */
 142         uch hash;               /* hash code */
 143         size_t smultis;
 144         char *multis;           /* -> char[smulti]  ab\0cd\0ef\0\0 */
 145 } cset;
 146 /* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
 147 #define CHadd(cs, c)    ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
 148 #define CHsub(cs, c)    ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
 149 #define CHIN(cs, c)     ((cs)->ptr[(uch)(c)] & (cs)->mask)
 150 #define MCadd(p, cs, cp)        mcadd(p, cs, cp)        /* regcomp() internal fns */
 151 #define MCsub(p, cs, cp)        mcsub(p, cs, cp)
 152 #define MCin(p, cs, cp) mcin(p, cs, cp)
 153
 154 /* stuff for character categories */
 155 typedef unsigned char cat_t;
 156
 157 /*
 158  * main compiled-expression structure
 159  */
 160 struct re_guts {
 161         int magic;
 162 #               define  MAGIC2  ((('R'^0200)<<8)|'E')
 163         sop *strip;             /* malloced area for strip */
 164         int csetsize;           /* number of bits in a cset vector */
 165         int ncsets;             /* number of csets in use */
 166         cset *sets;             /* -> cset [ncsets] */
 167         uch *setbits;           /* -> uch[csetsize][ncsets/CHAR_BIT] */
 168         int cflags;             /* copy of regcomp() cflags argument */
 169         sopno nstates;          /* = number of sops */
 170         sopno firststate;       /* the initial OEND (normally 0) */
 171         sopno laststate;        /* the final OEND */
 172         int iflags;             /* internal flags */
 173 #               define  USEBOL  01      /* used ^ */
 174 #               define  USEEOL  02      /* used $ */
 175 #               define  BAD     04      /* something wrong */
 176         int nbol;               /* number of ^ used */
 177         int neol;               /* number of $ used */
 178         int ncategories;        /* how many character categories */
 179         cat_t *categories;      /* ->catspace[-CHAR_MIN] */
 180         char *must;             /* match must contain this string */
 181         int mlen;               /* length of must */
 182         size_t nsub;            /* copy of re_nsub */
 183         int backrefs;           /* does it use back references? */
 184         sopno nplus;            /* how deep does it nest +s? */
 185         /* catspace must be last */
 186         cat_t catspace[1];      /* actually [NC] */
 187 };
 188
 189 /* misc utilities */
 190 #define OUT     (CHAR_MAX+1)    /* a non-character value */
 191 #define ISWORD(c)       (isalnum(c) || (c) == '_')