bug#11761: Slight bug in split :-)

[Pádraig Brady]

On 06/21/2012 11:12 PM, Jim Meyering wrote:
> François Pinard wrote:
>> Hi, Jim.
>>
>> I was looking for a problematic spot from a big file, and to isolate it,
>> used "split" repeatedly as a way to zoom into the proper place.  Just to
>> try, I used "split -C 100000 xad" at one place (after saving "xad"
>> first, of course).  "split" interrupted itself, producing less output
>> than input.
>>
>> My suggestion would be that split moans in some way before it destroys
>> its own input. :-)
>>
>> François
> 
> Hi François!
> Thank you for reporting that.
> That's definitely a bug.
> 
> For the record, here's a quick reproducer:
> 
>     $ seq 10 > xaa
>     $ split -C 6 xaa
>     $ wc -c x??
>     6 xaa
>     1 xab
>     7 total
>     $ head x??
>     ==> xaa <==
>     1
>     2
>     3
> 
>     ==> xab <==
>     3$
> 
> I've Cc'd the bug list, in case someone would like to write
> the patch (fix, NEWS and test) before I get to it.
> I may not have time tomorrow.

Nice catch :)
I'll fix it up with something like the following.

cheers,
Pádraig.

diff --git a/src/split.c b/src/split.c
index 53ee271..3e3313a 100644
--- a/src/split.c
+++ b/src/split.c
@@ -92,6 +92,9 @@ static char const *additional_suffix;
 /* Name of input file.  May be "-".  */
 static char *infile;

+/* stat buf for input file.  */
+static struct stat in_stat_buf;
+
 /* Descriptor on which output file is open.  */
 static int output_desc = -1;

@@ -362,6 +365,17 @@ create (const char *name)
     {
       if (verbose)
         fprintf (stdout, _("creating file %s\n"), quote (name));
+
+      struct stat out_stat_buf;
+      if (stat (name, &out_stat_buf) == 0)
+        {
+          if (SAME_INODE (in_stat_buf, out_stat_buf))
+            error (EXIT_FAILURE, 0, _("%s would overwrite input. Aborting."),
+                   quote (name));
+        }
+      else if (errno != ENOENT)
+        error (EXIT_FAILURE, errno, _("cannot stat %s"), quote (name));
+
       return open (name, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    (S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH))
     }
@@ -1058,7 +1072,6 @@ parse_chunk (uintmax_t *k_units, uintmax_t *n_units, char
 int
 main (int argc, char **argv)
 {
-  struct stat stat_buf;
   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 */
@@ -1335,16 +1348,16 @@ main (int argc, char **argv)

   /* Get the optimal block size of input device and make a buffer.  */

-  if (fstat (STDIN_FILENO, &stat_buf) != 0)
+  if (fstat (STDIN_FILENO, &in_stat_buf) != 0)
     error (EXIT_FAILURE, errno, "%s", infile);
   if (in_blk_size == 0)
-    in_blk_size = io_blksize (stat_buf);
+    in_blk_size = io_blksize (in_stat_buf);

   if (split_type == type_chunk_bytes || split_type == type_chunk_lines)
     {
       off_t input_offset = lseek (STDIN_FILENO, 0, SEEK_CUR);
-      if (usable_st_size (&stat_buf))
-        file_size = stat_buf.st_size;
+      if (usable_st_size (&in_stat_buf))
+        file_size = in_stat_buf.st_size;
       else if (0 <= input_offset)
         {
           file_size = lseek (STDIN_FILENO, 0, SEEK_END);