summaryrefslogtreecommitdiff
path: root/usr.bin
diff options
context:
space:
mode:
authorjschauma <jschauma@NetBSD.org>2023-01-30 15:22:02 +0000
committerjschauma <jschauma@NetBSD.org>2023-01-30 15:22:02 +0000
commit199875ea3580b7fef75ccd4a30a30813bca9926f (patch)
tree5cf1ce75cb8cce9cb5402fc751e62cbf6ef302b7 /usr.bin
parent69cadf71ed6fd9c1a413f8cc1059aeb9bd64a8e9 (diff)
auto-extend suffix length if required
If the input cannot be split into the number of files resulting from the default suffix length, automatically extend the suffix length rather than bailing out with 'too many files'. Suffixes are extended such that the resulting files continue to sort lexically and "cat *" would reproduce the input. For example, splitting a 1M lines file into (default) 1000 lines per file would yield files named 'xaa', 'xab', ..., 'xyy', 'xyz', 'xzaaa', 'xzaab', ..., 'xzanl'. If '-a' is specified, the suffix length is not auto-extended. This behavior matches GNU sort(1) since around version 8.16.
Diffstat (limited to 'usr.bin')
-rw-r--r--usr.bin/split/split.111
-rw-r--r--usr.bin/split/split.c38
2 files changed, 44 insertions, 5 deletions
diff --git a/usr.bin/split/split.1 b/usr.bin/split/split.1
index a25e3c6ea25..29b2a8d4471 100644
--- a/usr.bin/split/split.1
+++ b/usr.bin/split/split.1
@@ -1,4 +1,4 @@
-.\" $NetBSD: split.1,v 1.15 2007/05/31 01:35:35 jschauma Exp $
+.\" $NetBSD: split.1,v 1.16 2023/01/30 15:22:02 jschauma Exp $
.\"
.\" Copyright (c) 1990, 1991, 1993, 1994
.\" The Regents of the University of California. All rights reserved.
@@ -29,7 +29,7 @@
.\"
.\" @(#)split.1 8.3 (Berkeley) 4/16/94
.\"
-.Dd May 28, 2007
+.Dd January 28, 2023
.Dt SPLIT 1
.Os
.Sh NAME
@@ -99,7 +99,12 @@ characters in the range
.Dq Li a-z .
If
.Fl a
-is not specified, two letters are used as the suffix.
+is not specified, two letters are used as the initial
+suffix.
+If the output does not fit into the resulting number
+of files, then the suffix length is automatically
+extended as needed such that all output files continue
+to sort in lexical order.
.Pp
If the
.Ar name
diff --git a/usr.bin/split/split.c b/usr.bin/split/split.c
index ad4d6e3b209..ce717b30f58 100644
--- a/usr.bin/split/split.c
+++ b/usr.bin/split/split.c
@@ -1,4 +1,4 @@
-/* $NetBSD: split.c,v 1.28 2023/01/27 19:39:04 jschauma Exp $ */
+/* $NetBSD: split.c,v 1.29 2023/01/30 15:22:02 jschauma Exp $ */
/*
* Copyright (c) 1987, 1993, 1994
@@ -39,7 +39,7 @@ __COPYRIGHT("@(#) Copyright (c) 1987, 1993, 1994\
#if 0
static char sccsid[] = "@(#)split.c 8.3 (Berkeley) 4/25/94";
#endif
-__RCSID("$NetBSD: split.c,v 1.28 2023/01/27 19:39:04 jschauma Exp $");
+__RCSID("$NetBSD: split.c,v 1.29 2023/01/30 15:22:02 jschauma Exp $");
#endif /* not lint */
#include <sys/param.h>
@@ -60,6 +60,7 @@ static int file_open; /* If a file is open. */
static int ifd = STDIN_FILENO, ofd = -1; /* Input/output file descriptors. */
static char *fname; /* File name prefix. */
static size_t sfxlen = 2; /* Suffix length. */
+static int autosfx = 1; /* Whether to auto-extend the suffix length. */
static void newfile(void);
static void split1(off_t, int) __dead;
@@ -120,6 +121,7 @@ main(int argc, char *argv[])
(sfxlen = (size_t)strtoul(optarg, &ep, 10)) == 0 ||
*ep != '\0')
errx(1, "%s: illegal suffix length.", optarg);
+ autosfx = 0;
break;
case 'n': /* Chunks. */
if (!isdigit((unsigned char)optarg[0]) ||
@@ -323,6 +325,38 @@ newfile(void)
err(1, "%s", fname);
quot = fnum;
+
+ /* If '-a' is not specified, then we automatically expand the
+ * suffix length to accomodate splitting all input. We do this
+ * by moving the suffix pointer (fpnt) forward and incrementing
+ * sfxlen by one, thereby yielding an additional two characters
+ * and allowing all output files to sort such that 'cat *' yields
+ * the input in order. I.e., the order is '... xyy xyz xzaaa
+ * xzaab ... xzyzy, xzyzz, xzzaaaa, xzzaaab' and so on. */
+ if (autosfx && (fpnt[0] == 'y') && (strspn(fpnt+1, "z") == strlen(fpnt+1))) {
+ if ((fname = realloc(fname, strlen(fname) + sfxlen + 2 + 1)) == NULL)
+ err(EXIT_FAILURE, NULL);
+ /* NOTREACHED */
+
+ fpnt = fname + strlen(fname) - sfxlen;
+ fpnt[sfxlen + 2] = '\0';
+
+ fpnt[0] = 'z';
+ fpnt[1] = 'a';
+
+ /* Basename | Suffix
+ * before:
+ * x | yz
+ * after:
+ * xz | a.. */
+ fpnt++;
+ sfxlen++;
+
+ /* Reset so we start back at all 'a's in our extended suffix. */
+ quot = 0;
+ fnum = 0;
+ }
+
for (i = sfxlen - 1; i >= 0; i--) {
fpnt[i] = quot % 26 + 'a';
quot = quot / 26;