dd/conv.c

   1 /*-
   2  * Copyright (c) 1991, 1993, 1994
   3  *      The Regents of the University of California.  All rights reserved.
   4  *
   5  * This code is derived from software contributed to Berkeley by
   6  * Keith Muller of the University of California, San Diego and Lance
   7  * Visser of Convex Computer Corporation.
   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
  38 #ifndef lint
  39 #if 0
  40 static char sccsid[] = "@(#)conv.c      8.3 (Berkeley) 4/2/94";
  41 #endif
  42 static const char rcsid[] =
  43   "$FreeBSD: src/bin/dd/conv.c,v 1.16 2002/02/02 06:24:12 imp Exp $";
  44 #endif /* not lint */
  45
  46 #include <sys/param.h>
  47
  48 #include <err.h>
  49 #include <string.h>
  50
  51 #include "dd.h"
  52 #include "extern.h"
  53
  54 /*
  55  * def --
  56  * Copy input to output.  Input is buffered until reaches obs, and then
  57  * output until less than obs remains.  Only a single buffer is used.
  58  * Worst case buffer calculation is (ibs + obs - 1).
  59  */
  60 void
  61 def(void)
  62 {
  63         u_char *inp;
  64         const u_char *t;
  65         size_t cnt;
  66
  67         if ((t = ctab) != NULL)
  68                 for (inp = in.dbp - (cnt = in.dbrcnt); cnt--; ++inp)
  69                         *inp = t[*inp];
  70
  71         /* Make the output buffer look right. */
  72         out.dbp = in.dbp;
  73         out.dbcnt = in.dbcnt;
  74
  75         if (in.dbcnt >= out.dbsz) {
  76                 /* If the output buffer is full, write it. */
  77                 dd_out(0);
  78
  79                 /*
  80                  * Ddout copies the leftover output to the beginning of
  81                  * the buffer and resets the output buffer.  Reset the
  82                  * input buffer to match it.
  83                  */
  84                 in.dbp = out.dbp;
  85                 in.dbcnt = out.dbcnt;
  86         }
  87 }
  88
  89 void
  90 def_close(void)
  91 {
  92         /* Just update the count, everything is already in the buffer. */
  93         if (in.dbcnt)
  94                 out.dbcnt = in.dbcnt;
  95 }
  96
  97 /*
  98  * Copy variable length newline terminated records with a max size cbsz
  99  * bytes to output.  Records less than cbs are padded with spaces.
 100  *
 101  * max in buffer:  MAX(ibs, cbsz)
 102  * max out buffer: obs + cbsz
 103  */
 104 void
 105 block(void)
 106 {
 107         u_char *inp, *outp;
 108         const u_char *t;
 109         size_t cnt, maxlen;
 110         static int intrunc;
 111         int ch;
 112
 113         /*
 114          * Record truncation can cross block boundaries.  If currently in a
 115          * truncation state, keep tossing characters until reach a newline.
 116          * Start at the beginning of the buffer, as the input buffer is always
 117          * left empty.
 118          */
 119         if (intrunc) {
 120                 for (inp = in.db, cnt = in.dbrcnt; cnt && *inp++ != '\n'; --cnt)
 121                         ;
 122                 if (!cnt) {
 123                         in.dbcnt = 0;
 124                         in.dbp = in.db;
 125                         return;
 126                 }
 127                 intrunc = 0;
 128                 /* Adjust the input buffer numbers. */
 129                 in.dbcnt = cnt - 1;
 130                 in.dbp = inp + cnt - 1;
 131         }
 132
 133         /*
 134          * Copy records (max cbsz size chunks) into the output buffer.  The
 135          * translation is done as we copy into the output buffer.
 136          */
 137         ch = 0;
 138         for (inp = in.dbp - in.dbcnt, outp = out.dbp; in.dbcnt;) {
 139                 maxlen = MIN(cbsz, in.dbcnt);
 140                 if ((t = ctab) != NULL)
 141                         for (cnt = 0; cnt < maxlen && (ch = *inp++) != '\n';
 142                             ++cnt)
 143                                 *outp++ = t[ch];
 144                 else
 145                         for (cnt = 0; cnt < maxlen && (ch = *inp++) != '\n';
 146                             ++cnt)
 147                                 *outp++ = ch;
 148                 /*
 149                  * Check for short record without a newline.  Reassemble the
 150                  * input block.
 151                  */
 152                 if (ch != '\n' && in.dbcnt < cbsz) {
 153                         (void)memmove(in.db, in.dbp - in.dbcnt, in.dbcnt);
 154                         break;
 155                 }
 156
 157                 /* Adjust the input buffer numbers. */
 158                 in.dbcnt -= cnt;
 159                 if (ch == '\n')
 160                         --in.dbcnt;
 161
 162                 /* Pad short records with spaces. */
 163                 if (cnt < cbsz)
 164                         (void)memset(outp, ctab ? ctab[' '] : ' ', cbsz - cnt);
 165                 else {
 166                         /*
 167                          * If the next character wouldn't have ended the
 168                          * block, it's a truncation.
 169                          */
 170                         if (!in.dbcnt || *inp != '\n')
 171                                 ++st.trunc;
 172
 173                         /* Toss characters to a newline. */
 174                         for (; in.dbcnt && *inp++ != '\n'; --in.dbcnt);
 175                         if (!in.dbcnt)
 176                                 intrunc = 1;
 177                         else
 178                                 --in.dbcnt;
 179                 }
 180
 181                 /* Adjust output buffer numbers. */
 182                 out.dbp += cbsz;
 183                 if ((out.dbcnt += cbsz) >= out.dbsz)
 184                         dd_out(0);
 185                 outp = out.dbp;
 186         }
 187         in.dbp = in.db + in.dbcnt;
 188 }
 189
 190 void
 191 block_close(void)
 192 {
 193         /*
 194          * Copy any remaining data into the output buffer and pad to a record.
 195          * Don't worry about truncation or translation, the input buffer is
 196          * always empty when truncating, and no characters have been added for
 197          * translation.  The bottom line is that anything left in the input
 198          * buffer is a truncated record.  Anything left in the output buffer
 199          * just wasn't big enough.
 200          */
 201         if (in.dbcnt) {
 202                 ++st.trunc;
 203                 (void)memmove(out.dbp, in.dbp - in.dbcnt, in.dbcnt);
 204                 (void)memset(out.dbp + in.dbcnt, ctab ? ctab[' '] : ' ',
 205                     cbsz - in.dbcnt);
 206                 out.dbcnt += cbsz;
 207         }
 208 }
 209
 210 /*
 211  * Convert fixed length (cbsz) records to variable length.  Deletes any
 212  * trailing blanks and appends a newline.
 213  *
 214  * max in buffer:  MAX(ibs, cbsz) + cbsz
 215  * max out buffer: obs + cbsz
 216  */
 217 void
 218 unblock(void)
 219 {
 220         u_char *inp;
 221         const u_char *t;
 222         size_t cnt;
 223
 224         /* Translation and case conversion. */
 225         if ((t = ctab) != NULL)
 226                 for (cnt = in.dbrcnt, inp = in.dbp; cnt--;)
 227                         *--inp = t[*inp];
 228         /*
 229          * Copy records (max cbsz size chunks) into the output buffer.  The
 230          * translation has to already be done or we might not recognize the
 231          * spaces.
 232          */
 233         for (inp = in.db; in.dbcnt >= cbsz; inp += cbsz, in.dbcnt -= cbsz) {
 234                 for (t = inp + cbsz - 1; t >= inp && *t == ' '; --t)
 235                         ;
 236                 if (t >= inp) {
 237                         cnt = t - inp + 1;
 238                         (void)memmove(out.dbp, inp, cnt);
 239                         out.dbp += cnt;
 240                         out.dbcnt += cnt;
 241                 }
 242                 *out.dbp++ = '\n';
 243                 if (++out.dbcnt >= out.dbsz)
 244                         dd_out(0);
 245         }
 246         if (in.dbcnt)
 247                 (void)memmove(in.db, in.dbp - in.dbcnt, in.dbcnt);
 248         in.dbp = in.db + in.dbcnt;
 249 }
 250
 251 void
 252 unblock_close(void)
 253 {
 254         u_char *t;
 255         size_t cnt;
 256
 257         if (in.dbcnt) {
 258                 warnx("%s: short input record", in.name);
 259                 for (t = in.db + in.dbcnt - 1; t >= in.db && *t == ' '; --t)
 260                         ;
 261                 if (t >= in.db) {
 262                         cnt = t - in.db + 1;
 263                         (void)memmove(out.dbp, in.db, cnt);
 264                         out.dbp += cnt;
 265                         out.dbcnt += cnt;
 266                 }
 267                 ++out.dbcnt;
 268                 *out.dbp++ = '\n';
 269         }
 270 }