On 29/12/10 21:12, Dmitry V. Levin wrote:
> Hi,
>
> I've got a bug report from Sergey Vlasov about split(1) regression
> in coreutils v8.8: https://bugzilla.altlinux.org/24841
>
> In short, the default suffix length is not 2 as it shall be according to
> POSIX.
> Looks like the regression is due to commit v8.7-25-gbe10739.
> For more details and the test case, please have a look at the bug report.
Cringe :(
The frustrating this is that I noticed this
but dropped the fixup code when I was moving
local git branches around.
The attached should fix it.
I'll log a fedora rawhide bug also.
cheers,
Pádraig.
>From ec19e2a647cb64d4a5620787d4ecf5964d85fcf6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A1draig=20Brady?= <p...@draigbrady.com>
Date: Thu, 30 Dec 2010 01:36:59 +0000
Subject: [PATCH] split: fix the suffix length calculation
* src/split.c (set_suffix_length): Only auto calculate
the suffix length when the number of files is specified.
* tests/misc/split-a: Add a case to trigger the bug.
* NEWS: Mention the fix.
---
NEWS | 6 ++++++
src/split.c | 32 ++++++++++++++++++++------------
tests/misc/split-a | 5 +++++
3 files changed, 31 insertions(+), 12 deletions(-)
diff --git a/NEWS b/NEWS
index 401b2f5..88596b5 100644
--- a/NEWS
+++ b/NEWS
@@ -2,6 +2,12 @@ GNU coreutils NEWS -*- outline -*-
* Noteworthy changes in release ?.? (????-??-??) [?]
+** Bug fixes
+
+ split no longer creates files with a suffix length that
+ is dependent on the number of bytes or lines per file.
+ [bug introduced in coreutils-8.8]
+
* Noteworthy changes in release 8.8 (2010-12-22) [stable]
diff --git a/src/split.c b/src/split.c
index ae98bc7..9e9efbf 100644
--- a/src/split.c
+++ b/src/split.c
@@ -78,6 +78,13 @@ static bool elide_empty_files;
input to output, which is much slower, so disabled by default. */
static bool unbuffered;
+/* The split mode to use. */
+enum Split_type
+{
+ type_undef, type_bytes, type_byteslines, type_lines, type_digits,
+ type_chunk_bytes, type_chunk_lines, type_rr
+};
+
/* For long options that have no equivalent short option, use a
non-character as a pseudo short option, starting with CHAR_MAX + 1. */
enum
@@ -105,16 +112,21 @@ static struct option const longopts[] =
};
static void
-set_suffix_length (uintmax_t n_units)
+set_suffix_length (uintmax_t n_units, enum Split_type split_type)
{
#define DEFAULT_SUFFIX_LENGTH 2
size_t suffix_needed = 0;
- size_t alphabet_len = strlen (suffix_alphabet);
- bool alphabet_slop = (n_units % alphabet_len) != 0;
- while (n_units /= alphabet_len)
- suffix_needed++;
- suffix_needed += alphabet_slop;
+
+ if (split_type == type_chunk_bytes || split_type == type_chunk_lines
+ || split_type == type_rr)
+ {
+ size_t alphabet_len = strlen (suffix_alphabet);
+ bool alphabet_slop = (n_units % alphabet_len) != 0;
+ while (n_units /= alphabet_len)
+ suffix_needed++;
+ suffix_needed += alphabet_slop;
+ }
if (suffix_length) /* set by user */
{
@@ -780,11 +792,7 @@ int
main (int argc, char **argv)
{
struct stat stat_buf;
- enum
- {
- type_undef, type_bytes, type_byteslines, type_lines, type_digits,
- type_chunk_bytes, type_chunk_lines, type_rr
- } split_type = type_undef;
+ enum Split_type split_type = type_undef;
size_t in_blk_size = 0; /* optimal block size of input file device */
char *buf; /* file i/o buffer */
size_t page_size = getpagesize ();
@@ -984,7 +992,7 @@ main (int argc, char **argv)
usage (EXIT_FAILURE);
}
- set_suffix_length (n_units);
+ set_suffix_length (n_units, split_type);
/* Get out the filename arguments. */
diff --git a/tests/misc/split-a b/tests/misc/split-a
index d861b92..b0526bc 100755
--- a/tests/misc/split-a
+++ b/tests/misc/split-a
@@ -63,4 +63,9 @@ for f in $files; do
n=$(expr $n + 1)
done
+# Ensure that -a is independent of -[bCl]
+split -a2 -b1000 < /dev/null || fail=1
+split -a2 -l1000 < /dev/null || fail=1
+split -a2 -C1000 < /dev/null || fail=1
+
Exit $fail
--
1.7.3.4
