usr.bin/sed/main.c

   1 /*      $NetBSD: main.c,v 1.21 2010/02/19 16:35:27 tnn Exp $    */
   2
   3 /*-
   4  * Copyright (c) 1992, 1993
   5  *      The Regents of the University of California.  All rights reserved.
   6  *
   7  * This code is derived from software contributed to Berkeley by
   8  * Diomidis Spinellis of Imperial College, University of London.
   9  *
  10  * Redistribution and use in source and binary forms, with or without
  11  * modification, are permitted provided that the following conditions
  12  * are met:
  13  * 1. Redistributions of source code must retain the above copyright
  14  *    notice, this list of conditions and the following disclaimer.
  15  * 2. Redistributions in binary form must reproduce the above copyright
  16  *    notice, this list of conditions and the following disclaimer in the
  17  *    documentation and/or other materials provided with the distribution.
  18  * 3. Neither the name of the University nor the names of its contributors
  19  *    may be used to endorse or promote products derived from this software
  20  *    without specific prior written permission.
  21  *
  22  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  23  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  24  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  25  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  26  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  27  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  28  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  29  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  30  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  31  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  32  * SUCH DAMAGE.
  33  */
  34
  35 /*-
  36  * Copyright (c) 1992 Diomidis Spinellis.
  37  *
  38  * This code is derived from software contributed to Berkeley by
  39  * Diomidis Spinellis of Imperial College, University of London.
  40  *
  41  * Redistribution and use in source and binary forms, with or without
  42  * modification, are permitted provided that the following conditions
  43  * are met:
  44  * 1. Redistributions of source code must retain the above copyright
  45  *    notice, this list of conditions and the following disclaimer.
  46  * 2. Redistributions in binary form must reproduce the above copyright
  47  *    notice, this list of conditions and the following disclaimer in the
  48  *    documentation and/or other materials provided with the distribution.
  49  * 3. All advertising materials mentioning features or use of this software
  50  *    must display the following acknowledgement:
  51  *      This product includes software developed by the University of
  52  *      California, Berkeley and its contributors.
  53  * 4. Neither the name of the University nor the names of its contributors
  54  *    may be used to endorse or promote products derived from this software
  55  *    without specific prior written permission.
  56  *
  57  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  58  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  59  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  60  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  61  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  62  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  63  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  64  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  65  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  66  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  67  * SUCH DAMAGE.
  68  */
  69
  70 #if HAVE_NBTOOL_CONFIG_H
  71 #include "nbtool_config.h"
  72 #endif
  73
  74 #include <sys/cdefs.h>
  75 #ifndef lint
  76 __COPYRIGHT("@(#) Copyright (c) 1992, 1993\
  77  The Regents of the University of California.  All rights reserved.");
  78 #endif /* not lint */
  79
  80 #ifndef lint
  81 #if 0
  82 static char sccsid[] = "@(#)main.c      8.2 (Berkeley) 1/3/94";
  83 #else
  84 __RCSID("$NetBSD: main.c,v 1.21 2010/02/19 16:35:27 tnn Exp $");
  85 #endif
  86 #endif /* not lint */
  87
  88 #include <sys/types.h>
  89
  90 #include <ctype.h>
  91 #include <errno.h>
  92 #include <fcntl.h>
  93 #include <limits.h>
  94 #include <regex.h>
  95 #include <stddef.h>
  96 #include <stdio.h>
  97 #include <stdlib.h>
  98 #include <string.h>
  99 #include <unistd.h>
 100
 101 #include "defs.h"
 102 #include "extern.h"
 103
 104 /*
 105  * Linked list of units (strings and files) to be compiled
 106  */
 107 struct s_compunit {
 108         struct s_compunit *next;
 109         enum e_cut {CU_FILE, CU_STRING} type;
 110         char *s;                        /* Pointer to string or fname */
 111 };
 112
 113 /*
 114  * Linked list pointer to compilation units and pointer to current
 115  * next pointer.
 116  */
 117 static struct s_compunit *script, **cu_nextp = &script;
 118
 119 /*
 120  * Linked list of files to be processed
 121  */
 122 struct s_flist {
 123         char *fname;
 124         struct s_flist *next;
 125 };
 126
 127 /*
 128  * Linked list pointer to files and pointer to current
 129  * next pointer.
 130  */
 131 static struct s_flist *files, **fl_nextp = &files;
 132
 133 int aflag, eflag, nflag, ere;
 134
 135 /*
 136  * Current file and line number; line numbers restart across compilation
 137  * units, but span across input files.
 138  */
 139 const char *fname;                      /* File name. */
 140 u_long linenum;
 141 int lastline;                   /* TRUE on the last line of the last file */
 142
 143 static void add_compunit(enum e_cut, char *);
 144 static void add_file(char *);
 145 int     main(int, char **);
 146
 147 int
 148 main(int argc, char *argv[])
 149 {
 150         int c, fflag;
 151
 152         setprogname(*argv);
 153         fflag = 0;
 154         while ((c = getopt(argc, argv, "ae:f:nrE")) != -1)
 155                 switch (c) {
 156                 case 'a':
 157                         aflag = 1;
 158                         break;
 159                 case 'e':
 160                         eflag = 1;
 161                         add_compunit(CU_STRING, optarg);
 162                         break;
 163                 case 'f':
 164                         fflag = 1;
 165                         add_compunit(CU_FILE, optarg);
 166                         break;
 167                 case 'n':
 168                         nflag = 1;
 169                         break;
 170                 case 'r':
 171                 case 'E':
 172                         ere = REG_EXTENDED;
 173                         break;
 174                 default:
 175                 case '?':
 176                         (void)fprintf(stderr,
 177 "usage:\t%s [-aEnr] script [file ...]\n\t%s [-aEnr] [-e script] ... [-f script_file] ... [file ...]\n",
 178                             getprogname(), getprogname());
 179                         exit(1);
 180                 }
 181         argc -= optind;
 182         argv += optind;
 183
 184         /* First usage case; script is the first arg */
 185         if (!eflag && !fflag && *argv) {
 186                 add_compunit(CU_STRING, *argv);
 187                 argv++;
 188         }
 189
 190         compile();
 191
 192         /* Continue with first and start second usage */
 193         if (*argv)
 194                 for (; *argv; argv++)
 195                         add_file(*argv);
 196         else
 197                 add_file(NULL);
 198         process();
 199         cfclose(prog, NULL);
 200         if (fclose(stdout))
 201                 err(FATAL, "stdout: %s", strerror(errno));
 202         exit (0);
 203 }
 204
 205 /*
 206  * Like fgets, but go through the chain of compilation units chaining them
 207  * together.  Empty strings and files are ignored.
 208  */
 209 char *
 210 cu_fgets(char **outbuf, size_t *outsize)
 211 {
 212         static enum {ST_EOF, ST_FILE, ST_STRING} state = ST_EOF;
 213         static FILE *f;         /* Current open file */
 214         static char *s;         /* Current pointer inside string */
 215         static char string_ident[30];
 216         size_t len;
 217         char *p;
 218
 219         if (*outbuf == NULL)
 220                 *outsize = 0;
 221
 222 again:
 223         switch (state) {
 224         case ST_EOF:
 225                 if (script == NULL)
 226                         return (NULL);
 227                 linenum = 0;
 228                 switch (script->type) {
 229                 case CU_FILE:
 230                         if ((f = fopen(script->s, "r")) == NULL)
 231                                 err(FATAL,
 232                                     "%s: %s", script->s, strerror(errno));
 233                         fname = script->s;
 234                         state = ST_FILE;
 235                         goto again;
 236                 case CU_STRING:
 237                         if ((snprintf(string_ident,
 238                             sizeof(string_ident), "\"%s\"", script->s)) >=
 239                             (int)(sizeof(string_ident) - 1))
 240                                 (void)strcpy(string_ident +
 241                                     sizeof(string_ident) - 6, " ...\"");
 242                         fname = string_ident;
 243                         s = script->s;
 244                         state = ST_STRING;
 245                         goto again;
 246                 }
 247         case ST_FILE:
 248                 if ((p = fgetln(f, &len)) != NULL) {
 249                         linenum++;
 250                         if (len >= *outsize) {
 251                                 free(*outbuf);
 252                                 *outsize = ROUNDLEN(len + 1);
 253                                 *outbuf = xmalloc(*outsize);
 254                         }
 255                         memcpy(*outbuf, p, len);
 256                         (*outbuf)[len] = '\0';
 257                         if (linenum == 1 && p[0] == '#' && p[1] == 'n')
 258                                 nflag = 1;
 259                         return (*outbuf);
 260                 }
 261                 script = script->next;
 262                 (void)fclose(f);
 263                 state = ST_EOF;
 264                 goto again;
 265         case ST_STRING:
 266                 if (linenum == 0 && s[0] == '#' && s[1] == 'n')
 267                         nflag = 1;
 268                 p = *outbuf;
 269                 len = *outsize;
 270                 for (;;) {
 271                         if (len <= 1) {
 272                                 *outbuf = xrealloc(*outbuf,
 273                                     *outsize + _POSIX2_LINE_MAX);
 274                                 p = *outbuf + *outsize - len;
 275                                 len += _POSIX2_LINE_MAX;
 276                                 *outsize += _POSIX2_LINE_MAX;
 277                         }
 278                         switch (*s) {
 279                         case '\0':
 280                                 state = ST_EOF;
 281                                 if (s == script->s) {
 282                                         script = script->next;
 283                                         goto again;
 284                                 } else {
 285                                         script = script->next;
 286                                         *p = '\0';
 287                                         linenum++;
 288                                         return (*outbuf);
 289                                 }
 290                         case '\n':
 291                                 *p++ = '\n';
 292                                 *p = '\0';
 293                                 s++;
 294                                 linenum++;
 295                                 return (*outbuf);
 296                         default:
 297                                 *p++ = *s++;
 298                                 len--;
 299                         }
 300                 }
 301         }
 302         /* NOTREACHED */
 303         return (NULL);
 304 }
 305
 306 /*
 307  * Like fgets, but go through the list of files chaining them together.
 308  * Set len to the length of the line.
 309  */
 310 int
 311 mf_fgets(SPACE *sp, enum e_spflag spflag)
 312 {
 313         static FILE *f;         /* Current open file */
 314         size_t len;
 315         char *p;
 316         int c;
 317
 318         if (f == NULL)
 319                 /* Advance to first non-empty file */
 320                 for (;;) {
 321                         if (files == NULL) {
 322                                 lastline = 1;
 323                                 return (0);
 324                         }
 325                         if (files->fname == NULL) {
 326                                 f = stdin;
 327                                 fname = "stdin";
 328                         } else {
 329                                 fname = files->fname;
 330                                 if ((f = fopen(fname, "r")) == NULL)
 331                                         err(FATAL, "%s: %s",
 332                                             fname, strerror(errno));
 333                         }
 334                         if ((c = getc(f)) != EOF) {
 335                                 (void)ungetc(c, f);
 336                                 break;
 337                         }
 338                         (void)fclose(f);
 339                         files = files->next;
 340                 }
 341
 342         if (lastline) {
 343                 sp->len = 0;
 344                 return (0);
 345         }
 346
 347         /*
 348          * Use fgetln so that we can handle essentially infinite input data.
 349          * Can't use the pointer into the stdio buffer as the process space
 350          * because the ungetc() can cause it to move.
 351          */
 352         p = fgetln(f, &len);
 353         if (ferror(f))
 354                 err(FATAL, "%s: %s", fname, strerror(errno ? errno : EIO));
 355         cspace(sp, p, len, spflag);
 356
 357         linenum++;
 358         /* Advance to next non-empty file */
 359         while ((c = getc(f)) == EOF) {
 360                 (void)fclose(f);
 361                 files = files->next;
 362                 if (files == NULL) {
 363                         lastline = 1;
 364                         return (1);
 365                 }
 366                 if (files->fname == NULL) {
 367                         f = stdin;
 368                         fname = "stdin";
 369                 } else {
 370                         fname = files->fname;
 371                         if ((f = fopen(fname, "r")) == NULL)
 372                                 err(FATAL, "%s: %s", fname, strerror(errno));
 373                 }
 374         }
 375         (void)ungetc(c, f);
 376         return (1);
 377 }
 378
 379 /*
 380  * Add a compilation unit to the linked list
 381  */
 382 static void
 383 add_compunit(enum e_cut type, char *s)
 384 {
 385         struct s_compunit *cu;
 386
 387         cu = xmalloc(sizeof(struct s_compunit));
 388         cu->type = type;
 389         cu->s = s;
 390         cu->next = NULL;
 391         *cu_nextp = cu;
 392         cu_nextp = &cu->next;
 393 }
 394
 395 /*
 396  * Add a file to the linked list
 397  */
 398 static void
 399 add_file(char *s)
 400 {
 401         struct s_flist *fp;
 402
 403         fp = xmalloc(sizeof(struct s_flist));
 404         fp->next = NULL;
 405         *fl_nextp = fp;
 406         fp->fname = s;
 407         fl_nextp = &fp->next;
 408 }