Date: Sat, 26 Jan 2002 17:04:22 +1100 From: "Tim J. Robbins" <tim@robbins.dropbear.id.au> To: Mike Barcroft <mike@FreeBSD.ORG> Cc: freebsd-standards@FreeBSD.ORG Subject: Re: split(1) -a option patch Message-ID: <20020126170422.A8594@descent.robbins.dropbear.id.au> In-Reply-To: <20020125132739.B92720@espresso.q9media.com>; from mike@FreeBSD.ORG on Fri, Jan 25, 2002 at 01:27:39PM -0500 References: <20020124210956.A13091@descent.robbins.dropbear.id.au> <20020125132739.B92720@espresso.q9media.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--gBBFr7Ir9EOA20Yy
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
On Fri, Jan 25, 2002 at 01:27:39PM -0500, Mike Barcroft wrote:
> Could you please update your patch to -CURRENT sources. There is
> atleast one change to split.c that hasn't been MFC'd.
Done. I've corrected the style problems (I hope) and the warnings, added
overflow checking when calculating `maxfiles' and fixed usage(). There
were also some things in the manual page that needed updating.
> > - fpnt[0] = fnum / 26 + 'a';
> > - fpnt[1] = fnum % 26 + 'a';
> > + for (tfnum = fnum, i = sufflen; i != 0; i--, tfnum /= 26)
> > + fpnt[i - 1] = tfnum % 26 + 'a';
> > + fpnt[sufflen] = '\0';
>
> Can you explain the purpose of this change? I don't think I
> completely understand it.
Instead of generating a two character suffix, I use a loop to do it more
generally. The idea is:
Save a copy of the file sequence number (tfnum = fnum) to mess around with.
Walk backwards through where the suffix should go, dividing tfnum by 26
and setting the character to the remainder +'a'.
Is this simpler?
tfnum = fnum;
i = sufflen - 1;
do {
fpnt[i] = tfnum % 26 + 'a';
tfnum /= 26;
} while (i >= 0);
Patch against -CURRENT is attached.
Tim
--gBBFr7Ir9EOA20Yy
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment; filename="split.diff"
Index: split/split.1
===================================================================
RCS file: /home/ncvs/src/usr.bin/split/split.1,v
retrieving revision 1.6
diff -u -r1.6 split.1
--- split/split.1 2001/07/15 08:01:34 1.6
+++ split/split.1 2002/01/26 05:55:45
@@ -40,6 +40,7 @@
.Nd split a file into pieces
.Sh SYNOPSIS
.Nm
+.Op Fl a Ar suffix_length
.Op Fl b Ar byte_count[k|m]
.Op Fl l Ar line_count
.Op Fl p Ar pattern
@@ -54,6 +55,12 @@
.Pp
The options are as follows:
.Bl -tag -width Ds
+.It Fl a
+Use
+.Ar suffix_length
+letters to form the suffix of the file name. If
+.Fl a
+is not specified, two letters are used as the suffix.
.It Fl b
Create smaller files
.Ar byte_count
@@ -89,22 +96,18 @@
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 .
+prefix followed by a lexically ordered suffix using
+.Ar suffix_length
+characters in the range
+.Dq Li a-z .
.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 .
+files named with prefixes in the range of
+.Dq Li x-z
+and with suffixes as above.
.Sh BUGS
-For historical reasons, if you specify
-.Ar name ,
-.Nm
-can only create 676 separate
-files.
-The default naming convention allows 2028 separate files.
-.Pp
The maximum line length for matching patterns is 65536.
.Sh SEE ALSO
.Xr re_format 7
Index: split/split.c
===================================================================
RCS file: /home/ncvs/src/usr.bin/split/split.c,v
retrieving revision 1.8
diff -u -r1.8 split.c
--- split/split.c 2001/12/12 23:09:07 1.8
+++ split/split.c 2002/01/26 05:55:46
@@ -67,6 +67,7 @@
char fname[MAXPATHLEN]; /* File name prefix. */
regex_t rgx;
int pflag;
+long sufflen = 2; /* File name suffix length. */
void newfile __P((void));
void split1 __P((void));
@@ -81,7 +82,7 @@
int ch;
char *ep, *p;
- while ((ch = getopt(argc, argv, "-0123456789b:l:p:")) != -1)
+ while ((ch = getopt(argc, argv, "-0123456789a:b:l:p:")) != -1)
switch (ch) {
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
@@ -106,6 +107,11 @@
usage();
ifd = 0;
break;
+ case 'a': /* Suffix length */
+ if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep)
+ err(EX_USAGE,
+ "%s: illegal suffix length", optarg);
+ break;
case 'b': /* Byte count. */
if ((bytecnt = strtoq(optarg, &ep, 10)) <= 0 ||
(*ep != '\0' && *ep != 'k' && *ep != 'm'))
@@ -145,6 +151,8 @@
if (*argv != NULL)
usage();
+ if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname))
+ err(EX_USAGE, "suffix is too long");
if (pflag && (numlines != 0 || bytecnt != 0))
usage();
@@ -273,6 +281,7 @@
void
newfile()
{
+ long i, maxfiles, tfnum;
static long fnum;
static int defname;
static char *fpnt;
@@ -288,19 +297,25 @@
}
ofd = fileno(stdout);
}
+
+ /* maxfiles = 26^sufflen, but don't use libm. */
+ for (maxfiles = 1, i = 0; i < sufflen; i++)
+ if ((maxfiles *= 26) <= 0)
+ errx(EX_USAGE, "suffix is too long (max %ld)", i);
+
/*
* Hack to increase max files; original code wandered through
- * magic characters. Maximum files is 3 * 26 * 26 == 2028
+ * magic characters.
*/
-#define MAXFILES 676
- if (fnum == MAXFILES) {
+ if (fnum == maxfiles) {
if (!defname || fname[0] == 'z')
errx(EX_DATAERR, "too many files");
++fname[0];
fnum = 0;
}
- fpnt[0] = fnum / 26 + 'a';
- fpnt[1] = fnum % 26 + 'a';
+ for (tfnum = fnum, i = sufflen; i != 0; i--, tfnum /= 26)
+ fpnt[i - 1] = tfnum % 26 + 'a';
+ fpnt[sufflen] = '\0';
++fnum;
if (!freopen(fname, "w", stdout))
err(EX_IOERR, "%s", fname);
@@ -311,6 +326,7 @@
usage()
{
(void)fprintf(stderr,
-"usage: split [-b byte_count] [-l line_count] [-p pattern] [file [prefix]]\n");
+"usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n");
+ (void)fprintf(stderr, "\t\t[file [prefix]]\n");
exit(EX_USAGE);
}
--gBBFr7Ir9EOA20Yy--
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-standards" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020126170422.A8594>