summaryrefslogtreecommitdiffstats
path: root/usr.bin/split
diff options
context:
space:
mode:
authorrgrimes <rgrimes@FreeBSD.org>1994-05-27 12:33:43 +0000
committerrgrimes <rgrimes@FreeBSD.org>1994-05-27 12:33:43 +0000
commitf9ab90d9d6d02989a075d0f0074496d5b1045e4b (patch)
treeadd7e996bac5289cdc55e6935750c352505560a9 /usr.bin/split
parentbe22b15ae2ff8d7fe06b6e14fddf0c5b444a95da (diff)
downloadFreeBSD-src-f9ab90d9d6d02989a075d0f0074496d5b1045e4b.zip
FreeBSD-src-f9ab90d9d6d02989a075d0f0074496d5b1045e4b.tar.gz
BSD 4.4 Lite Usr.bin Sources
Diffstat (limited to 'usr.bin/split')
-rw-r--r--usr.bin/split/Makefile5
-rw-r--r--usr.bin/split/split.199
-rw-r--r--usr.bin/split/split.c288
3 files changed, 392 insertions, 0 deletions
diff --git a/usr.bin/split/Makefile b/usr.bin/split/Makefile
new file mode 100644
index 0000000..93048f7
--- /dev/null
+++ b/usr.bin/split/Makefile
@@ -0,0 +1,5 @@
+# @(#)Makefile 8.1 (Berkeley) 6/6/93
+
+PROG= split
+
+.include <bsd.prog.mk>
diff --git a/usr.bin/split/split.1 b/usr.bin/split/split.1
new file mode 100644
index 0000000..34f3c07
--- /dev/null
+++ b/usr.bin/split/split.1
@@ -0,0 +1,99 @@
+.\" Copyright (c) 1990, 1991, 1993, 1994
+.\" The Regents of the University of California. All rights reserved.
+.\"
+.\" Redistribution and use in source and binary forms, with or without
+.\" modification, are permitted provided that the following conditions
+.\" are met:
+.\" 1. Redistributions of source code must retain the above copyright
+.\" notice, this list of conditions and the following disclaimer.
+.\" 2. Redistributions in binary form must reproduce the above copyright
+.\" notice, this list of conditions and the following disclaimer in the
+.\" documentation and/or other materials provided with the distribution.
+.\" 3. All advertising materials mentioning features or use of this software
+.\" must display the following acknowledgement:
+.\" This product includes software developed by the University of
+.\" California, Berkeley and its contributors.
+.\" 4. Neither the name of the University nor the names of its contributors
+.\" may be used to endorse or promote products derived from this software
+.\" without specific prior written permission.
+.\"
+.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+.\" SUCH DAMAGE.
+.\"
+.\" @(#)split.1 8.3 (Berkeley) 4/16/94
+.\"
+.Dd April 16, 1994
+.Dt SPLIT 1
+.Os
+.Sh NAME
+.Nm split
+.Nd split a file into pieces
+.Sh SYNOPSIS
+.Nm split
+.Op Fl b Ar byte_count[k|m]
+.Op Fl l Ar line_count
+.Op Ar file Op Ar name
+.Sh DESCRIPTION
+The
+.Nm split
+utility reads the given
+.Ar file
+(or standard input if no file is specified)
+and breaks it up into files of 1000 lines each.
+.Pp
+The options are as follows:
+.Bl -tag -width Ds
+.It Fl b
+Create smaller files
+.Ar byte_count
+bytes in length.
+If
+.Dq Li k
+is appended to the number, the file is split into
+.Ar byte_count
+kilobyte pieces.
+If
+.Dq Li m
+is appended to the number, the file is split into
+.Ar byte_count
+megabyte pieces.
+.It Fl l
+Create smaller files
+.Ar n
+lines in length.
+.El
+.Pp
+If additional arguments are specified, the first is used as the name
+of the input file which is to be split.
+If a second additional argument is specified, it is used as a prefix
+for the names of the files into which the file is split.
+In this case, each file into which the file is split is named by the
+prefix followed by a lexically ordered suffix in the range of
+.Dq Li aa-zz .
+.Pp
+If the
+.Ar name
+argument is not specified, the file is split into lexically ordered
+files named in the range of
+.Dq Li xaa-zzz .
+.Sh BUGS
+For historical reasons, if you specify
+.Ar name ,
+.Nm split
+can only create 676 separate
+files.
+The default naming convention allows 2028 separate files.
+.Sh HISTORY
+A
+.Nm split
+command appeared in
+.At v6 .
diff --git a/usr.bin/split/split.c b/usr.bin/split/split.c
new file mode 100644
index 0000000..198532b
--- /dev/null
+++ b/usr.bin/split/split.c
@@ -0,0 +1,288 @@
+/*
+ * Copyright (c) 1987, 1993, 1994
+ * The Regents of the University of California. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ * must display the following acknowledgement:
+ * This product includes software developed by the University of
+ * California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef lint
+static char copyright[] =
+"@(#) Copyright (c) 1987, 1993, 1994\n\
+ The Regents of the University of California. All rights reserved.\n";
+#endif /* not lint */
+
+#ifndef lint
+static char sccsid[] = "@(#)split.c 8.2 (Berkeley) 4/16/94";
+#endif /* not lint */
+
+#include <sys/param.h>
+
+#include <ctype.h>
+#include <err.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#define DEFLINE 1000 /* Default num lines per file. */
+
+long bytecnt; /* Byte count to split on. */
+long numlines; /* Line count to split on. */
+int file_open; /* If a file open. */
+int ifd = -1, ofd = -1; /* Input/output file descriptors. */
+char bfr[MAXBSIZE]; /* I/O buffer. */
+char fname[MAXPATHLEN]; /* File name prefix. */
+
+void newfile __P((void));
+void split1 __P((void));
+void split2 __P((void));
+void usage __P((void));
+
+int
+main(argc, argv)
+ int argc;
+ char *argv[];
+{
+ int ch;
+ char *ep, *p;
+
+ while ((ch = getopt(argc, argv, "-0123456789b:l:")) != EOF)
+ switch (ch) {
+ case '0': case '1': case '2': case '3': case '4':
+ case '5': case '6': case '7': case '8': case '9':
+ /*
+ * Undocumented kludge: split was originally designed
+ * to take a number after a dash.
+ */
+ if (numlines == 0) {
+ p = argv[optind - 1];
+ if (p[0] == '-' && p[1] == ch && !p[2])
+ numlines = strtol(++p, &ep, 10);
+ else
+ numlines =
+ strtol(argv[optind] + 1, &ep, 10);
+ if (numlines <= 0 || *ep)
+ errx(1,
+ "%s: illegal line count.", optarg);
+ }
+ break;
+ case '-': /* Undocumented: historic stdin flag. */
+ if (ifd != -1)
+ usage();
+ ifd = 0;
+ break;
+ case 'b': /* Byte count. */
+ if ((bytecnt = strtol(optarg, &ep, 10)) <= 0 ||
+ *ep != '\0' && *ep != 'k' && *ep != 'm')
+ errx(1, "%s: illegal byte count.", optarg);
+ if (*ep == 'k')
+ bytecnt *= 1024;
+ else if (*ep == 'm')
+ bytecnt *= 1048576;
+ break;
+ case 'l': /* Line count. */
+ if (numlines != 0)
+ usage();
+ if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *p)
+ errx(1, "%s: illegal line count.", optarg);
+ break;
+ default:
+ usage();
+ }
+ argv += optind;
+ argc -= optind;
+
+ if (*argv != NULL)
+ if (ifd == -1) { /* Input file. */
+ if ((ifd = open(*argv, O_RDONLY, 0)) < 0)
+ err(1, "%s", *argv);
+ ++argv;
+ }
+ if (*argv != NULL) /* File name prefix. */
+ (void)strcpy(fname, *argv++);
+ if (*argv != NULL)
+ usage();
+
+ if (numlines == 0)
+ numlines = DEFLINE;
+ else if (bytecnt)
+ usage();
+
+ if (ifd == -1) /* Stdin by default. */
+ ifd = 0;
+
+ if (bytecnt) {
+ split1();
+ exit (0);
+ }
+ split2();
+ exit(0);
+}
+
+/*
+ * split1 --
+ * Split the input by bytes.
+ */
+void
+split1()
+{
+ long bcnt;
+ int dist, len;
+ char *C;
+
+ for (bcnt = 0;;)
+ switch (len = read(ifd, bfr, MAXBSIZE)) {
+ case 0:
+ exit(0);
+ case -1:
+ err(1, "read");
+ /* NOTREACHED */
+ default:
+ if (!file_open) {
+ newfile();
+ file_open = 1;
+ }
+ if (bcnt + len >= bytecnt) {
+ dist = bytecnt - bcnt;
+ if (write(ofd, bfr, dist) != dist)
+ err(1, "write");
+ len -= dist;
+ for (C = bfr + dist; len >= bytecnt;
+ len -= bytecnt, C += bytecnt) {
+ newfile();
+ if (write(ofd,
+ C, (int)bytecnt) != bytecnt)
+ err(1, "write");
+ }
+ if (len) {
+ newfile();
+ if (write(ofd, C, len) != len)
+ err(1, "write");
+ } else
+ file_open = 0;
+ bcnt = len;
+ } else {
+ bcnt += len;
+ if (write(ofd, bfr, len) != len)
+ err(1, "write");
+ }
+ }
+}
+
+/*
+ * split2 --
+ * Split the input by lines.
+ */
+void
+split2()
+{
+ long lcnt;
+ int len, bcnt;
+ char *Ce, *Cs;
+
+ for (lcnt = 0;;)
+ switch (len = read(ifd, bfr, MAXBSIZE)) {
+ case 0:
+ exit(0);
+ case -1:
+ err(1, "read");
+ /* NOTREACHED */
+ default:
+ if (!file_open) {
+ newfile();
+ file_open = 1;
+ }
+ for (Cs = Ce = bfr; len--; Ce++)
+ if (*Ce == '\n' && ++lcnt == numlines) {
+ bcnt = Ce - Cs + 1;
+ if (write(ofd, Cs, bcnt) != bcnt)
+ err(1, "write");
+ lcnt = 0;
+ Cs = Ce + 1;
+ if (len)
+ newfile();
+ else
+ file_open = 0;
+ }
+ if (Cs < Ce) {
+ bcnt = Ce - Cs;
+ if (write(ofd, Cs, bcnt) != bcnt)
+ err(1, "write");
+ }
+ }
+}
+
+/*
+ * newfile --
+ * Open a new output file.
+ */
+void
+newfile()
+{
+ static long fnum;
+ static int defname;
+ static char *fpnt;
+
+ if (ofd == -1) {
+ if (fname[0] == '\0') {
+ fname[0] = 'x';
+ fpnt = fname + 1;
+ defname = 1;
+ } else {
+ fpnt = fname + strlen(fname);
+ defname = 0;
+ }
+ ofd = fileno(stdout);
+ }
+ /*
+ * Hack to increase max files; original code wandered through
+ * magic characters. Maximum files is 3 * 26 * 26 == 2028
+ */
+#define MAXFILES 676
+ if (fnum == MAXFILES) {
+ if (!defname || fname[0] == 'z')
+ errx(1, "too many files.");
+ ++fname[0];
+ fnum = 0;
+ }
+ fpnt[0] = fnum / 26 + 'a';
+ fpnt[1] = fnum % 26 + 'a';
+ ++fnum;
+ if (!freopen(fname, "w", stdout))
+ err(1, "%s", fname);
+}
+
+void
+usage()
+{
+ (void)fprintf(stderr,
+"usage: split [-b byte_count] [-l line_count] [file [prefix]]\n");
+ exit(1);
+}
OpenPOWER on IntegriCloud