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  * $FreeBSD: src/lib/libc/regex/regex2.h,v 1.8 2004/07/12 07:35:59 tjr Exp $
  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 unsigned long sop;      /* strip operator */
  80 typedef long sopno;
  81 #define OPRMASK 0xf8000000L
  82 #define OPDMASK 0x07ffffffL
  83 #define OPSHIFT ((unsigned)27)
  84 #define OP(n)   ((n)&OPRMASK)
  85 #define OPND(n) ((n)&OPDMASK)
  86 #define SOP(op, opnd)   ((op)|(opnd))
  87 /* operators                       meaning      operand                 */
  88 /*                                              (back, fwd are offsets) */
  89 #define OEND    (1L<<OPSHIFT)   /* endmarker    -                       */
  90 #define OCHAR   (2L<<OPSHIFT)   /* character    wide character          */
  91 #define OBOL    (3L<<OPSHIFT)   /* left anchor  -                       */
  92 #define OEOL    (4L<<OPSHIFT)   /* right anchor -                       */
  93 #define OANY    (5L<<OPSHIFT)   /* .            -                       */
  94 #define OANYOF  (6L<<OPSHIFT)   /* [...]        set number              */
  95 #define OBACK_  (7L<<OPSHIFT)   /* begin \d     paren number            */
  96 #define O_BACK  (8L<<OPSHIFT)   /* end \d       paren number            */
  97 #define OPLUS_  (9L<<OPSHIFT)   /* + prefix     fwd to suffix           */
  98 #define O_PLUS  (10L<<OPSHIFT)  /* + suffix     back to prefix          */
  99 #define OQUEST_ (11L<<OPSHIFT)  /* ? prefix     fwd to suffix           */
 100 #define O_QUEST (12L<<OPSHIFT)  /* ? suffix     back to prefix          */
 101 #define OLPAREN (13L<<OPSHIFT)  /* (            fwd to )                */
 102 #define ORPAREN (14L<<OPSHIFT)  /* )            back to (               */
 103 #define OCH_    (15L<<OPSHIFT)  /* begin choice fwd to OOR2             */
 104 #define OOR1    (16L<<OPSHIFT)  /* | pt. 1      back to OOR1 or OCH_    */
 105 #define OOR2    (17L<<OPSHIFT)  /* | pt. 2      fwd to OOR2 or O_CH     */
 106 #define O_CH    (18L<<OPSHIFT)  /* end choice   back to OOR1            */
 107 #define OBOW    (19L<<OPSHIFT)  /* begin word   -                       */
 108 #define OEOW    (20L<<OPSHIFT)  /* end word     -                       */
 109
 110 /*
 111  * Structures for [] character-set representation.
 112  */
 113 typedef struct {
 114         wint_t          min;
 115         wint_t          max;
 116 } crange;
 117 typedef struct {
 118         unsigned char   bmp[NC / 8];
 119         wctype_t        *types;
 120         int             ntypes;
 121         wint_t          *wides;
 122         int             nwides;
 123         crange          *ranges;
 124         int             nranges;
 125         int             invert;
 126         int             icase;
 127         int             *equiv_classes;
 128         int             nequiv_classes;
 129 } cset;
 130
 131 #include "collate.h"
 132
 133 static int
 134 CHIN1(cs, ch, loc)
 135 cset *cs;
 136 wint_t ch;
 137 locale_t loc;
 138 {
 139         int i;
 140
 141         assert(ch >= 0);
 142         for (i = 0; i < cs->nequiv_classes; i++)
 143                 /* sadly, we can only deal with single characters from an
 144                  * equivalence class */
 145                 if (__collate_equiv_match(cs->equiv_classes[i], NULL, 0, ch, NULL, 0, NULL, NULL, loc) > 0)
 146                         return (!cs->invert);
 147         if (ch < NC)
 148                 return (((cs->bmp[ch >> 3] & (1 << (ch & 7))) != 0) ^
 149                     cs->invert);
 150         for (i = 0; i < cs->nwides; i++)
 151                 if (ch == cs->wides[i])
 152                         return (!cs->invert);
 153         for (i = 0; i < cs->nranges; i++)
 154                 if (cs->ranges[i].min <= ch && ch <= cs->ranges[i].max)
 155                         return (!cs->invert);
 156         for (i = 0; i < cs->ntypes; i++)
 157                 if (iswctype_l(ch, cs->types[i], loc))
 158                         return (!cs->invert);
 159         return (cs->invert);
 160 }
 161
 162 static __inline int
 163 CHIN(cs, ch, loc)
 164 cset *cs;
 165 wint_t ch;
 166 locale_t loc;
 167 {
 168
 169         assert(ch >= 0);
 170         if (ch < NC && cs->nequiv_classes == 0)
 171                 return (((cs->bmp[ch >> 3] & (1 << (ch & 7))) != 0) ^
 172                     cs->invert);
 173         else if (cs->icase)
 174                 return (CHIN1(cs, ch, loc) || CHIN1(cs, towlower_l(ch, loc), loc) ||
 175                     CHIN1(cs, towupper_l(ch, loc), loc));
 176         else
 177                 return (CHIN1(cs, ch, loc));
 178 }
 179
 180 /*
 181  * main compiled-expression structure
 182  */
 183 struct re_guts {
 184         int magic;
 185 #               define  MAGIC2  ((('R'^0200)<<8)|'E')
 186         sop *strip;             /* malloced area for strip */
 187         int ncsets;             /* number of csets in use */
 188         cset *sets;             /* -> cset [ncsets] */
 189         int cflags;             /* copy of regcomp() cflags argument */
 190         sopno nstates;          /* = number of sops */
 191         sopno firststate;       /* the initial OEND (normally 0) */
 192         sopno laststate;        /* the final OEND */
 193         int iflags;             /* internal flags */
 194 #               define  USEBOL  01      /* used ^ */
 195 #               define  USEEOL  02      /* used $ */
 196 #               define  BAD     04      /* something wrong */
 197         int nbol;               /* number of ^ used */
 198         int neol;               /* number of $ used */
 199         char *must;             /* match must contain this string */
 200         int moffset;            /* latest point at which must may be located */
 201         int *charjump;          /* Boyer-Moore char jump table */
 202         int *matchjump;         /* Boyer-Moore match jump table */
 203         int mlen;               /* length of must */
 204         size_t nsub;            /* copy of re_nsub */
 205         int backrefs;           /* does it use back references? */
 206         sopno nplus;            /* how deep does it nest +s? */
 207         locale_t loc;           /* current locale */
 208 };
 209
 210 /* misc utilities */
 211 #define OUT     (-130)  /* a non-character value */
 212 #define ISWORD(c,l)     (iswalnum_l((uch)(c), l) || (c) == '_')