packfile: fix pack basename computation

When we have a multi-pack-index that covers many packfiles, we try to
avoid opening the .idx for those packfiles. To do that we feed the pack
name to midx_contains_pack(). But that function wants to see only the
basename, which we compute using strrchr() to find the final slash. But
that leaves an extra "/" at the start of our string.

We can fix this by incrementing the pointer. That also raises the
question of what to do when the name does not have a '/' at all. This
should generally not happen (we always find files in "pack/"), but it
doesn't hurt to be defensive here.

Let's wrap all of that up in a helper function and make it publicly
available, since a later patch will need to use it, too.

The tests don't notice because there's nothing about opening those .idx
files that would cause us to give incorrect output. It's just a little
slower. The new test checks this case by corrupting the covered .idx,
and then making sure we don't complain about it.

We also have to tweak t5570, which intentionally corrupts a .idx file
and expects us to notice it. When run with GIT_TEST_MULTI_PACK_INDEX,
this will fail since we now will (correctly) not bother opening the .idx
at all. We can fix that by unconditionally dropping any midx that's
there, which ensures we'll have to read the .idx.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/packfile.c b/packfile.c
index 6e40bd89c762caf71439ae597d3d9028c669afcb..7a2dd2fdbea4c750ad998fd6d6f9d95b3ddff060 100644 (file)
--- a/packfile.c
+++ b/packfile.c
@@ -466,6 +466,16 @@ static unsigned int get_max_fd_limit(void)
 #endif
 }
 
+const char *pack_basename(struct packed_git *p)
+{
+       const char *ret = strrchr(p->pack_name, '/');
+       if (ret)
+               ret = ret + 1; /* skip past slash */
+       else
+               ret = p->pack_name; /* we only have a base */
+       return ret;
+}
+
 /*
  * Do not call this directly as this leaks p->pack_fd on error return;
  * call open_packed_git() instead.
@@ -482,7 +492,7 @@ static int open_packed_git_1(struct packed_git *p)
 
        if (!p->index_data) {
                struct multi_pack_index *m;
-               const char *pack_name = strrchr(p->pack_name, '/');
+               const char *pack_name = pack_basename(p);
 
                for (m = the_repository->objects->multi_pack_index;
                     m; m = m->next) {

diff --git a/packfile.h b/packfile.h
index ea7a690fc6e3e4f6753032abfa3eb88e54023ac2..fe05fe0303f857374610d3b45c03494e46073d81 100644 (file)
--- a/packfile.h
+++ b/packfile.h
@@ -31,6 +31,12 @@ char *sha1_pack_name(const unsigned char *sha1);
  */
 char *sha1_pack_index_name(const unsigned char *sha1);
 
+/*
+ * Return the basename of the packfile, omitting any containing directory
+ * (e.g., "pack-1234abcd[...].pack").
+ */
+const char *pack_basename(struct packed_git *p);
+
 struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path);
 
 typedef void each_file_in_pack_dir_fn(const char *full_path, size_t full_path_len,

diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index 8c4d2bd849c94fd4bb57a19a3be2f2af63c9488f..1ebf19ec3cd559dbf9ae7205a225d6e49368a8d2 100755 (executable)
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -117,6 +117,20 @@ test_expect_success 'write midx with one v2 pack' '
 
 compare_results_with_midx "one v2 pack"
 
+test_expect_success 'corrupt idx not opened' '
+       idx=$(test-tool read-midx $objdir | grep "\.idx\$") &&
+       mv $objdir/pack/$idx backup-$idx &&
+       test_when_finished "mv backup-\$idx \$objdir/pack/\$idx" &&
+
+       # This is the minimum size for a sha-1 based .idx; this lets
+       # us pass perfunctory tests, but anything that actually opens and reads
+       # the idx file will complain.
+       test_copy_bytes 1064 <backup-$idx >$objdir/pack/$idx &&
+
+       git -c core.multiPackIndex=true rev-list --objects --all 2>err &&
+       test_must_be_empty err
+'
+
 test_expect_success 'add more objects' '
        for i in $(test_seq 6 10)
        do

diff --git a/t/t5570-git-daemon.sh b/t/t5570-git-daemon.sh
index 58ee7876853161087c256e56e687f0b341fde915..19e271bda6a479a95dafc5ea9cdca0b2d3e0cf25 100755 (executable)
--- a/t/t5570-git-daemon.sh
+++ b/t/t5570-git-daemon.sh
@@ -90,6 +90,7 @@ test_expect_success 'fetch notices corrupt pack' '
 test_expect_success 'fetch notices corrupt idx' '
        cp -R "$GIT_DAEMON_DOCUMENT_ROOT_PATH"/repo_pack.git "$GIT_DAEMON_DOCUMENT_ROOT_PATH"/repo_bad2.git &&
        (cd "$GIT_DAEMON_DOCUMENT_ROOT_PATH"/repo_bad2.git &&
+        rm -f objects/pack/multi-pack-index &&
         p=$(ls objects/pack/pack-*.idx) &&
         chmod u+w $p &&
         printf %0256d 0 | dd of=$p bs=256 count=1 seek=1 conv=notrunc