external/bsd/flex/dist/ecs.c

   1 /* ecs - equivalence class routines */
   2
   3 /*  Copyright (c) 1990 The Regents of the University of California. */
   4 /*  All rights reserved. */
   5
   6 /*  This code is derived from software contributed to Berkeley by */
   7 /*  Vern Paxson. */
   8
   9 /*  The United States Government has rights in this work pursuant */
  10 /*  to contract no. DE-AC03-76SF00098 between the United States */
  11 /*  Department of Energy and the University of California. */
  12
  13 /* This file is part of flex */
  14
  15 /*  Redistribution and use in source and binary forms, with or without */
  16 /*  modification, are permitted provided that the following conditions */
  17 /*  are met: */
  18
  19 /*  1. Redistributions of source code must retain the above copyright */
  20 /*     notice, this list of conditions and the following disclaimer. */
  21 /*  2. Redistributions in binary form must reproduce the above copyright */
  22 /*     notice, this list of conditions and the following disclaimer in the */
  23 /*     documentation and/or other materials provided with the distribution. */
  24
  25 /*  Neither the name of the University nor the names of its contributors */
  26 /*  may be used to endorse or promote products derived from this software */
  27 /*  without specific prior written permission. */
  28
  29 /*  THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR */
  30 /*  IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED */
  31 /*  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR */
  32 /*  PURPOSE. */
  33 #include "flexdef.h"
  34 __RCSID("$NetBSD: ecs.c,v 1.3 2014/10/30 18:44:05 christos Exp $");
  35
  36 /* ccl2ecl - convert character classes to set of equivalence classes */
  37
  38 void    ccl2ecl ()
  39 {
  40         int     i, ich, newlen, cclp, ccls, cclmec;
  41
  42         for (i = 1; i <= lastccl; ++i) {
  43                 /* We loop through each character class, and for each character
  44                  * in the class, add the character's equivalence class to the
  45                  * new "character" class we are creating.  Thus when we are all
  46                  * done, character classes will really consist of collections
  47                  * of equivalence classes
  48                  */
  49
  50                 newlen = 0;
  51                 cclp = cclmap[i];
  52
  53                 for (ccls = 0; ccls < ccllen[i]; ++ccls) {
  54                         ich = ccltbl[cclp + ccls];
  55                         cclmec = ecgroup[ich];
  56
  57                         if (cclmec > 0) {
  58                                 ccltbl[cclp + newlen] = cclmec;
  59                                 ++newlen;
  60                         }
  61                 }
  62
  63                 ccllen[i] = newlen;
  64         }
  65 }
  66
  67
  68 /* cre8ecs - associate equivalence class numbers with class members
  69  *
  70  * fwd is the forward linked-list of equivalence class members.  bck
  71  * is the backward linked-list, and num is the number of class members.
  72  *
  73  * Returned is the number of classes.
  74  */
  75
  76 int     cre8ecs (fwd, bck, num)
  77      int     fwd[], bck[], num;
  78 {
  79         int     i, j, numcl;
  80
  81         numcl = 0;
  82
  83         /* Create equivalence class numbers.  From now on, ABS( bck(x) )
  84          * is the equivalence class number for object x.  If bck(x)
  85          * is positive, then x is the representative of its equivalence
  86          * class.
  87          */
  88         for (i = 1; i <= num; ++i)
  89                 if (bck[i] == NIL) {
  90                         bck[i] = ++numcl;
  91                         for (j = fwd[i]; j != NIL; j = fwd[j])
  92                                 bck[j] = -numcl;
  93                 }
  94
  95         return numcl;
  96 }
  97
  98
  99 /* mkeccl - update equivalence classes based on character class xtions
 100  *
 101  * synopsis
 102  *    Char ccls[];
 103  *    int lenccl, fwd[llsiz], bck[llsiz], llsiz, NUL_mapping;
 104  *    void mkeccl( Char ccls[], int lenccl, int fwd[llsiz], int bck[llsiz],
 105  *                      int llsiz, int NUL_mapping );
 106  *
 107  * ccls contains the elements of the character class, lenccl is the
 108  * number of elements in the ccl, fwd is the forward link-list of equivalent
 109  * characters, bck is the backward link-list, and llsiz size of the link-list.
 110  *
 111  * NUL_mapping is the value which NUL (0) should be mapped to.
 112  */
 113
 114 void    mkeccl (ccls, lenccl, fwd, bck, llsiz, NUL_mapping)
 115      Char    ccls[];
 116      int     lenccl, fwd[], bck[], llsiz, NUL_mapping;
 117 {
 118         int     cclp, oldec, newec;
 119         int     cclm, i, j;
 120         static unsigned char cclflags[CSIZE];   /* initialized to all '\0' */
 121
 122         /* Note that it doesn't matter whether or not the character class is
 123          * negated.  The same results will be obtained in either case.
 124          */
 125
 126         cclp = 0;
 127
 128         while (cclp < lenccl) {
 129                 cclm = ccls[cclp];
 130
 131                 if (NUL_mapping && cclm == 0)
 132                         cclm = NUL_mapping;
 133
 134                 oldec = bck[cclm];
 135                 newec = cclm;
 136
 137                 j = cclp + 1;
 138
 139                 for (i = fwd[cclm]; i != NIL && i <= llsiz; i = fwd[i]) {       /* look for the symbol in the character class */
 140                         for (; j < lenccl; ++j) {
 141                                 register int ccl_char;
 142
 143                                 if (NUL_mapping && ccls[j] == 0)
 144                                         ccl_char = NUL_mapping;
 145                                 else
 146                                         ccl_char = ccls[j];
 147
 148                                 if (ccl_char > i)
 149                                         break;
 150
 151                                 if (ccl_char == i && !cclflags[j]) {
 152                                         /* We found an old companion of cclm
 153                                          * in the ccl.  Link it into the new
 154                                          * equivalence class and flag it as
 155                                          * having been processed.
 156                                          */
 157
 158                                         bck[i] = newec;
 159                                         fwd[newec] = i;
 160                                         newec = i;
 161                                         /* Set flag so we don't reprocess. */
 162                                         cclflags[j] = 1;
 163
 164                                         /* Get next equivalence class member. */
 165                                         /* continue 2 */
 166                                         goto next_pt;
 167                                 }
 168                         }
 169
 170                         /* Symbol isn't in character class.  Put it in the old
 171                          * equivalence class.
 172                          */
 173
 174                         bck[i] = oldec;
 175
 176                         if (oldec != NIL)
 177                                 fwd[oldec] = i;
 178
 179                         oldec = i;
 180
 181                       next_pt:;
 182                 }
 183
 184                 if (bck[cclm] != NIL || oldec != bck[cclm]) {
 185                         bck[cclm] = NIL;
 186                         fwd[oldec] = NIL;
 187                 }
 188
 189                 fwd[newec] = NIL;
 190
 191                 /* Find next ccl member to process. */
 192
 193                 for (++cclp; cclflags[cclp] && cclp < lenccl; ++cclp) {
 194                         /* Reset "doesn't need processing" flag. */
 195                         cclflags[cclp] = 0;
 196                 }
 197         }
 198 }
 199
 200
 201 /* mkechar - create equivalence class for single character */
 202
 203 void    mkechar (tch, fwd, bck)
 204      int     tch, fwd[], bck[];
 205 {
 206         /* If until now the character has been a proper subset of
 207          * an equivalence class, break it away to create a new ec
 208          */
 209
 210         if (fwd[tch] != NIL)
 211                 bck[fwd[tch]] = bck[tch];
 212
 213         if (bck[tch] != NIL)
 214                 fwd[bck[tch]] = fwd[tch];
 215
 216         fwd[tch] = NIL;
 217         bck[tch] = NIL;
 218 }