diff options
| -rw-r--r-- | Documentation/git-cat-file.txt | 12 | ||||
| -rw-r--r-- | builtin/cat-file.c | 6 | ||||
| -rwxr-xr-x | t/t1006-cat-file.sh | 34 |
3 files changed, 49 insertions, 3 deletions
diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt index 322f5ed31..f6a16f430 100644 --- a/Documentation/git-cat-file.txt +++ b/Documentation/git-cat-file.txt @@ -109,6 +109,11 @@ newline. The available atoms are: The size, in bytes, that the object takes up on disk. See the note about on-disk sizes in the `CAVEATS` section below. +`deltabase`:: + If the object is stored as a delta on-disk, this expands to the + 40-hex sha1 of the delta base object. Otherwise, expands to the + null sha1 (40 zeroes). See `CAVEATS` below. + `rest`:: If this atom is used in the output string, input lines are split at the first whitespace boundary. All characters before that @@ -152,10 +157,11 @@ should be taken in drawing conclusions about which refs or objects are responsible for disk usage. The size of a packed non-delta object may be much larger than the size of objects which delta against it, but the choice of which object is the base and which is the delta is arbitrary -and is subject to change during a repack. Note also that multiple copies -of an object may be present in the object database; in this case, it is -undefined which copy's size will be reported. +and is subject to change during a repack. +Note also that multiple copies of an object may be present in the object +database; in this case, it is undefined which copy's size or delta base +will be reported. GIT --- diff --git a/builtin/cat-file.c b/builtin/cat-file.c index b2ca775a8..2e0af2e61 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -118,6 +118,7 @@ struct expand_data { unsigned long size; unsigned long disk_size; const char *rest; + unsigned char delta_base_sha1[20]; /* * If mark_query is true, we do not expand anything, but rather @@ -174,6 +175,11 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len, data->split_on_whitespace = 1; else if (data->rest) strbuf_addstr(sb, data->rest); + } else if (is_atom("deltabase", atom, len)) { + if (data->mark_query) + data->info.delta_base_sha1 = data->delta_base_sha1; + else + strbuf_addstr(sb, sha1_to_hex(data->delta_base_sha1)); } else die("unknown format element: %.*s", len, atom); } diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index 8a1bc5c53..633dc825e 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -240,4 +240,38 @@ test_expect_success "--batch-check with multiple sha1s gives correct format" ' "$(echo_without_newline "$batch_check_input" | git cat-file --batch-check)" ' +test_expect_success 'setup blobs which are likely to delta' ' + test-genrandom foo 10240 >foo && + { cat foo; echo plus; } >foo-plus && + git add foo foo-plus && + git commit -m foo && + cat >blobs <<-\EOF + HEAD:foo + HEAD:foo-plus + EOF +' + +test_expect_success 'confirm that neither loose blob is a delta' ' + cat >expect <<-EOF + $_z40 + $_z40 + EOF + git cat-file --batch-check="%(deltabase)" <blobs >actual && + test_cmp expect actual +' + +# To avoid relying too much on the current delta heuristics, +# we will check only that one of the two objects is a delta +# against the other, but not the order. We can do so by just +# asking for the base of both, and checking whether either +# sha1 appears in the output. +test_expect_success '%(deltabase) reports packed delta bases' ' + git repack -ad && + git cat-file --batch-check="%(deltabase)" <blobs >actual && + { + grep "$(git rev-parse HEAD:foo)" actual || + grep "$(git rev-parse HEAD:foo-plus)" actual + } +' + test_done |