1 /*- 2 * This code is derived from OpenBSD's libc/regex, original license follows: 3 * 4 * Copyright (c) 1992, 1993, 1994 Henry Spencer. 5 * Copyright (c) 1992, 1993, 1994 6 * The Regents of the University of California. All rights reserved. 7 * 8 * This code is derived from software contributed to Berkeley by 9 * Henry Spencer. 10 * 11 * Redistribution and use in source and binary forms, with or without 12 * modification, are permitted provided that the following conditions 13 * are met: 14 * 1. Redistributions of source code must retain the above copyright 15 * notice, this list of conditions and the following disclaimer. 16 * 2. Redistributions in binary form must reproduce the above copyright 17 * notice, this list of conditions and the following disclaimer in the 18 * documentation and/or other materials provided with the distribution. 19 * 3. Neither the name of the University nor the names of its contributors 20 * may be used to endorse or promote products derived from this software 21 * without specific prior written permission. 22 * 23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33 * SUCH DAMAGE. 34 * 35 * @(#)regex2.h 8.4 (Berkeley) 3/20/94 36 */ 37 38 #ifndef LLVM_SUPPORT_REGEX2_H 39 #define LLVM_SUPPORT_REGEX2_H 40 41 /* 42 * internals of regex_t 43 */ 44 #define MAGIC1 ((('r'^0200)<<8) | 'e') 45 46 /* 47 * The internal representation is a *strip*, a sequence of 48 * operators ending with an endmarker. (Some terminology etc. is a 49 * historical relic of earlier versions which used multiple strips.) 50 * Certain oddities in the representation are there to permit running 51 * the machinery backwards; in particular, any deviation from sequential 52 * flow must be marked at both its source and its destination. Some 53 * fine points: 54 * 55 * - OPLUS_ and O_PLUS are *inside* the loop they create. 56 * - OQUEST_ and O_QUEST are *outside* the bypass they create. 57 * - OCH_ and O_CH are *outside* the multi-way branch they create, while 58 * OOR1 and OOR2 are respectively the end and the beginning of one of 59 * the branches. Note that there is an implicit OOR2 following OCH_ 60 * and an implicit OOR1 preceding O_CH. 61 * 62 * In state representations, an operator's bit is on to signify a state 63 * immediately *preceding* "execution" of that operator. 64 */ 65 typedef unsigned long sop; /* strip operator */ 66 typedef long sopno; 67 #define OPRMASK 0xf8000000LU 68 #define OPDMASK 0x07ffffffLU 69 #define OPSHIFT ((unsigned)27) 70 #define OP(n) ((n)&OPRMASK) 71 #define OPND(n) ((n)&OPDMASK) 72 #define SOP(op, opnd) ((op)|(opnd)) 73 /* operators meaning operand */ 74 /* (back, fwd are offsets) */ 75 #define OEND (1LU<<OPSHIFT) /* endmarker - */ 76 #define OCHAR (2LU<<OPSHIFT) /* character unsigned char */ 77 #define OBOL (3LU<<OPSHIFT) /* left anchor - */ 78 #define OEOL (4LU<<OPSHIFT) /* right anchor - */ 79 #define OANY (5LU<<OPSHIFT) /* . - */ 80 #define OANYOF (6LU<<OPSHIFT) /* [...] set number */ 81 #define OBACK_ (7LU<<OPSHIFT) /* begin \d paren number */ 82 #define O_BACK (8LU<<OPSHIFT) /* end \d paren number */ 83 #define OPLUS_ (9LU<<OPSHIFT) /* + prefix fwd to suffix */ 84 #define O_PLUS (10LU<<OPSHIFT) /* + suffix back to prefix */ 85 #define OQUEST_ (11LU<<OPSHIFT) /* ? prefix fwd to suffix */ 86 #define O_QUEST (12LU<<OPSHIFT) /* ? suffix back to prefix */ 87 #define OLPAREN (13LU<<OPSHIFT) /* ( fwd to ) */ 88 #define ORPAREN (14LU<<OPSHIFT) /* ) back to ( */ 89 #define OCH_ (15LU<<OPSHIFT) /* begin choice fwd to OOR2 */ 90 #define OOR1 (16LU<<OPSHIFT) /* | pt. 1 back to OOR1 or OCH_ */ 91 #define OOR2 (17LU<<OPSHIFT) /* | pt. 2 fwd to OOR2 or O_CH */ 92 #define O_CH (18LU<<OPSHIFT) /* end choice back to OOR1 */ 93 #define OBOW (19LU<<OPSHIFT) /* begin word - */ 94 #define OEOW (20LU<<OPSHIFT) /* end word - */ 95 96 /* 97 * Structure for [] character-set representation. Character sets are 98 * done as bit vectors, grouped 8 to a byte vector for compactness. 99 * The individual set therefore has both a pointer to the byte vector 100 * and a mask to pick out the relevant bit of each byte. A hash code 101 * simplifies testing whether two sets could be identical. 102 * 103 * This will get trickier for multicharacter collating elements. As 104 * preliminary hooks for dealing with such things, we also carry along 105 * a string of multi-character elements, and decide the size of the 106 * vectors at run time. 107 */ 108 typedef struct { 109 uch *ptr; /* -> uch [csetsize] */ 110 uch mask; /* bit within array */ 111 uch hash; /* hash code */ 112 size_t smultis; 113 char *multis; /* -> char[smulti] ab\0cd\0ef\0\0 */ 114 } cset; 115 /* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */ 116 #define CHadd(cs, c) ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c)) 117 #define CHsub(cs, c) ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c)) 118 #define CHIN(cs, c) ((cs)->ptr[(uch)(c)] & (cs)->mask) 119 #define MCadd(p, cs, cp) mcadd(p, cs, cp) /* llvm_regcomp() internal fns */ 120 #define MCsub(p, cs, cp) mcsub(p, cs, cp) 121 #define MCin(p, cs, cp) mcin(p, cs, cp) 122 123 /* stuff for character categories */ 124 typedef unsigned char cat_t; 125 126 /* 127 * main compiled-expression structure 128 */ 129 struct re_guts { 130 int magic; 131 # define MAGIC2 ((('R'^0200)<<8)|'E') 132 sop *strip; /* malloced area for strip */ 133 int csetsize; /* number of bits in a cset vector */ 134 int ncsets; /* number of csets in use */ 135 cset *sets; /* -> cset [ncsets] */ 136 uch *setbits; /* -> uch[csetsize][ncsets/CHAR_BIT] */ 137 int cflags; /* copy of llvm_regcomp() cflags argument */ 138 sopno nstates; /* = number of sops */ 139 sopno firststate; /* the initial OEND (normally 0) */ 140 sopno laststate; /* the final OEND */ 141 int iflags; /* internal flags */ 142 # define USEBOL 01 /* used ^ */ 143 # define USEEOL 02 /* used $ */ 144 # define REGEX_BAD 04 /* something wrong */ 145 int nbol; /* number of ^ used */ 146 int neol; /* number of $ used */ 147 int ncategories; /* how many character categories */ 148 cat_t *categories; /* ->catspace[-CHAR_MIN] */ 149 char *must; /* match must contain this string */ 150 int mlen; /* length of must */ 151 size_t nsub; /* copy of re_nsub */ 152 int backrefs; /* does it use back references? */ 153 sopno nplus; /* how deep does it nest +s? */ 154 /* catspace must be last */ 155 cat_t catspace[1]; /* actually [NC] */ 156 }; 157 158 /* misc utilities */ 159 #define OUT (CHAR_MAX+1) /* a non-character value */ 160 #define ISWORD(c) (isalnum(c&0xff) || (c) == '_') 161 162 #endif 163