du: don't miscount duplicate directories or link-count-1 files

* NEWS: Mention this.
* src/du.c (hash_all): New static var.
(process_file): Use it.
(main): Set it.
* tests/du/hard-link: Add a couple of test cases to help make
sure this bug stays squashed.
* tests/du/files0-from: Adjust existing tests to reflect
change in semantics with duplicate arguments.

2 files changed, 34 insertions, 18 deletions

diff --git a/tests/du/files0-from b/tests/du/files0-from
index 620246d56..860fc6aad 100755
--- a/tests/du/files0-from
+++ b/tests/du/files0-from
@@ -70,15 +70,15 @@ my @Tests =
     {IN=>{f=>"g\0"}}, {AUX=>{g=>''}},
     {OUT=>"0\tg\n"}, {OUT_SUBST=>'s/^\d+/0/'} ],
 
-   # two file names, no final NUL
+   # two identical file names, no final NUL
    ['2', '--files0-from=-', '<',
     {IN=>{f=>"g\0g"}}, {AUX=>{g=>''}},
-    {OUT=>"0\tg\n0\tg\n"}, {OUT_SUBST=>'s/^\d+/0/'} ],
+    {OUT=>"0\tg\n"}, {OUT_SUBST=>'s/^\d+/0/'} ],
 
-   # two file names, with final NUL
+   # two identical file names, with final NUL
    ['2a', '--files0-from=-', '<',
     {IN=>{f=>"g\0g\0"}}, {AUX=>{g=>''}},
-    {OUT=>"0\tg\n0\tg\n"}, {OUT_SUBST=>'s/^\d+/0/'} ],
+    {OUT=>"0\tg\n"}, {OUT_SUBST=>'s/^\d+/0/'} ],
 
    # Ensure that $prog processes FILEs following a zero-length name.
    ['zero-len', '--files0-from=-', '<',
diff --git a/tests/du/hard-link b/tests/du/hard-link
index 7e4f51aee..e22320b56 100755
--- a/tests/du/hard-link
+++ b/tests/du/hard-link
@@ -26,24 +26,40 @@ fi
 . $srcdir/test-lib.sh
 
 mkdir -p dir/sub
-( cd dir && { echo non-empty > f1; ln f1 f2; echo non-empty > sub/F; } )
-
-
-# Note that for this first test, we transform f1 or f2
-# (whichever name we find first) to f_.  That is necessary because,
-# depending on the type of file system, du could encounter either of those
-# two hard-linked files first, thus listing that one and not the other.
-du -a --exclude=sub dir \
-  | sed 's/^[0-9][0-9]*	//' | sed 's/f[12]/f_/' > out || fail=1
-echo === >> out
-du -a --exclude=sub --count-links dir \
-  | sed 's/^[0-9][0-9]*	//' | sort -r >> out || fail=1
+( cd dir &&
+  { echo non-empty > f1
+    ln f1 f2
+    ln -s f1 f3
+    echo non-empty > sub/F; } )
+
+du -a -L --exclude=sub --count-links dir \
+  | sed 's/^[0-9][0-9]*	//' | sort -r > out || fail=1
+
+# For these tests, transform f1 or f2 or f3 (whichever name is find
+# first) to f_.  That is necessary because, depending on the type of
+# file system, du could encounter any of those linked files first,
+# thus listing that one and not the others.
+for args in '-L' 'dir' '-L dir'
+do
+  echo === >> out
+  du -a --exclude=sub $args dir \
+    | sed 's/^[0-9][0-9]*	//' | sed 's/f[123]/f_/' >> out || fail=1
+done
+
 cat <<\EOF > exp
+dir/f3
+dir/f2
+dir/f1
+dir
+===
 dir/f_
 dir
 ===
-dir/f2
-dir/f1
+dir/f_
+dir/f_
+dir
+===
+dir/f_
 dir
 EOF