split: fix --number=K/N to output correct part of file

This functionality regressed with the adjustments
in commit v8.25-4-g62e7af032

* src/split.c (bytes_chunk_extract): Account for already read data
when seeking into the file.
* tests/split/b-chunk.sh: Use the hidden ---io-blksize option,
to test this functionality.
* NEWS: Mention the bug fix.
Fixes https://bugs.gnu.org/46048

diff --git a/NEWS b/NEWS
index a6ba96450d778b8b68b9969df8e499cc64b434a4..0929f0ae2fd2e9383fc6856c860081206fbc9718 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -30,6 +30,10 @@ GNU coreutils NEWS                                    -*- outline -*-
   rm no longer skips an extra file when the removal of an empty directory fails.
   [bug introduced by the rewrite to use fts in coreutils-8.0]
 
+  split --number=K/N will again correctly split chunk K of N to stdout.
+  Previously a chunk starting after 128KiB, output the wrong part of the file.
+  [bug introduced in coreutils-8.26]
+
   tr no longer crashes when using --complement with certain
   invalid combinations of case character classes.
   [bug introduced in coreutils-8.6]

diff --git a/src/split.c b/src/split.c
index 0660da13fd00a68c4a7f4dea0827cdf194d2acfd..59c234c12cffd80d2df03a0dec82c12f89ee4707 100644 (file)
--- a/src/split.c
+++ b/src/split.c
@@ -1001,7 +1001,7 @@ bytes_chunk_extract (uintmax_t k, uintmax_t n, char *buf, size_t bufsize,
     }
   else
     {
-      if (lseek (STDIN_FILENO, start, SEEK_CUR) < 0)
+      if (lseek (STDIN_FILENO, start - initial_read, SEEK_CUR) < 0)
         die (EXIT_FAILURE, errno, "%s", quotef (infile));
       initial_read = SIZE_MAX;
     }

diff --git a/tests/split/b-chunk.sh b/tests/split/b-chunk.sh
index 8238dcb6d45e64cce833bc81172ce0938d8a17cc..dbed681f7dd646421ae37084f90c1ba7bd7d2ef6 100755 (executable)
--- a/tests/split/b-chunk.sh
+++ b/tests/split/b-chunk.sh
@@ -35,32 +35,39 @@ split -e -n 10 /dev/null || fail=1
 returns_ 1 stat x?? 2>/dev/null || fail=1
 
 printf '1\n2\n3\n4\n5\n' > input || framework_failure_
+printf '1\n2' > exp-1 || framework_failure_
+printf '\n3\n' > exp-2 || framework_failure_
+printf '4\n5\n' > exp-3 || framework_failure_
 
 for file in input /proc/version /sys/kernel/profiling; do
   test -f $file || continue
 
-  split -n 3 $file > out || fail=1
-  split -n 1/3 $file > b1 || fail=1
-  split -n 2/3 $file > b2 || fail=1
-  split -n 3/3 $file > b3 || fail=1
+  for blksize in 1 2 4096; do
+    if ! test "$file" = 'input'; then
+      # For /proc like files we must be able to read all
+      # into the internal buffer to be able to determine size.
+      test "$blksize" = 4096 || continue
+    fi
 
-  case $file in
-    input)
-      printf '1\n2' > exp-1
-      printf '\n3\n' > exp-2
-      printf '4\n5\n' > exp-3
+    split -n 3 ---io-blksize=$blksize $file > out || fail=1
+    split -n 1/3 ---io-blksize=$blksize $file > b1 || fail=1
+    split -n 2/3 ---io-blksize=$blksize $file > b2 || fail=1
+    split -n 3/3 ---io-blksize=$blksize $file > b3 || fail=1
 
-      compare exp-1 xaa || fail=1
-      compare exp-2 xab || fail=1
-      compare exp-3 xac || fail=1
-      ;;
-  esac
+    case $file in
+      input)
+        compare exp-1 xaa || fail=1
+        compare exp-2 xab || fail=1
+        compare exp-3 xac || fail=1
+        ;;
+    esac
 
-  compare xaa b1 || fail=1
-  compare xab b2 || fail=1
-  compare xac b3 || fail=1
-  cat xaa xab xac | compare - $file || fail=1
-  test -f xad && fail=1
+    compare xaa b1 || fail=1
+    compare xab b2 || fail=1
+    compare xac b3 || fail=1
+    cat xaa xab xac | compare - $file || fail=1
+    test -f xad && fail=1
+  done
 done
 
 Exit $fail