2008-02-21 11:06:47 +01:00
|
|
|
#!/bin/sh
|
|
|
|
|
2008-09-03 10:59:27 +02:00
|
|
|
test_description="git hash-object"
|
2008-02-21 11:06:47 +01:00
|
|
|
|
2022-02-05 01:04:29 +01:00
|
|
|
TEST_PASSES_SANITIZE_LEAK=true
|
2008-02-21 11:06:47 +01:00
|
|
|
. ./test-lib.sh
|
|
|
|
|
2008-05-23 16:19:37 +02:00
|
|
|
echo_without_newline() {
|
|
|
|
printf '%s' "$*"
|
|
|
|
}
|
|
|
|
|
|
|
|
test_blob_does_not_exist() {
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success 'blob does not exist in database' "
|
2008-05-23 16:19:37 +02:00
|
|
|
test_must_fail git cat-file blob $1
|
|
|
|
"
|
|
|
|
}
|
|
|
|
|
|
|
|
test_blob_exists() {
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success 'blob exists in database' "
|
2008-05-23 16:19:37 +02:00
|
|
|
git cat-file blob $1
|
|
|
|
"
|
|
|
|
}
|
|
|
|
|
|
|
|
hello_content="Hello World"
|
|
|
|
example_content="This is an example"
|
|
|
|
|
|
|
|
setup_repo() {
|
|
|
|
echo_without_newline "$hello_content" > hello
|
|
|
|
echo_without_newline "$example_content" > example
|
|
|
|
}
|
|
|
|
|
|
|
|
test_repo=test
|
|
|
|
push_repo() {
|
|
|
|
test_create_repo $test_repo
|
|
|
|
cd $test_repo
|
|
|
|
|
|
|
|
setup_repo
|
|
|
|
}
|
|
|
|
|
|
|
|
pop_repo() {
|
|
|
|
cd ..
|
|
|
|
rm -rf $test_repo
|
|
|
|
}
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success 'setup' '
|
|
|
|
setup_repo &&
|
|
|
|
test_oid_cache <<-EOF
|
|
|
|
hello sha1:5e1c309dae7f45e0f39b1bf3ac3cd9db12e7d689
|
|
|
|
hello sha256:1e3b6c04d2eeb2b3e45c8a330445404c0b7cc7b257e2b097167d26f5230090c4
|
|
|
|
|
|
|
|
example sha1:ddd3f836d3e3fbb7ae289aa9ae83536f76956399
|
|
|
|
example sha256:b44fe1fe65589848253737db859bd490453510719d7424daab03daf0767b85ae
|
|
|
|
EOF
|
|
|
|
'
|
2008-05-23 16:19:37 +02:00
|
|
|
|
|
|
|
# Argument checking
|
|
|
|
|
|
|
|
test_expect_success "multiple '--stdin's are rejected" '
|
2008-08-03 16:36:18 +02:00
|
|
|
echo example | test_must_fail git hash-object --stdin --stdin
|
2008-05-23 16:19:37 +02:00
|
|
|
'
|
|
|
|
|
2008-05-23 16:19:38 +02:00
|
|
|
test_expect_success "Can't use --stdin and --stdin-paths together" '
|
2008-08-03 16:36:18 +02:00
|
|
|
echo example | test_must_fail git hash-object --stdin --stdin-paths &&
|
|
|
|
echo example | test_must_fail git hash-object --stdin-paths --stdin
|
2008-05-23 16:19:38 +02:00
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success "Can't pass filenames as arguments with --stdin-paths" '
|
2008-08-03 16:36:18 +02:00
|
|
|
echo example | test_must_fail git hash-object --stdin-paths hello
|
2008-05-23 16:19:38 +02:00
|
|
|
'
|
|
|
|
|
2008-08-03 16:36:21 +02:00
|
|
|
test_expect_success "Can't use --path with --stdin-paths" '
|
|
|
|
echo example | test_must_fail git hash-object --stdin-paths --path=foo
|
|
|
|
'
|
|
|
|
|
2008-08-03 16:36:22 +02:00
|
|
|
test_expect_success "Can't use --path with --no-filters" '
|
|
|
|
test_must_fail git hash-object --no-filters --path=foo
|
|
|
|
'
|
|
|
|
|
2008-05-23 16:19:37 +02:00
|
|
|
# Behavior
|
|
|
|
|
|
|
|
push_repo
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success 'hash a file' '
|
|
|
|
test "$(test_oid hello)" = $(git hash-object hello)
|
2008-05-23 16:19:37 +02:00
|
|
|
'
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_blob_does_not_exist "$(test_oid hello)"
|
2008-05-23 16:19:37 +02:00
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success 'hash from stdin' '
|
|
|
|
test "$(test_oid example)" = $(git hash-object --stdin < example)
|
2008-05-23 16:19:37 +02:00
|
|
|
'
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_blob_does_not_exist "$(test_oid example)"
|
2008-05-23 16:19:37 +02:00
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success 'hash a file and write to database' '
|
|
|
|
test "$(test_oid hello)" = $(git hash-object -w hello)
|
2008-05-23 16:19:37 +02:00
|
|
|
'
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_blob_exists "$(test_oid hello)"
|
2008-05-23 16:19:37 +02:00
|
|
|
|
|
|
|
test_expect_success 'git hash-object --stdin file1 <file0 first operates on file0, then file1' '
|
|
|
|
echo foo > file1 &&
|
|
|
|
obname0=$(echo bar | git hash-object --stdin) &&
|
|
|
|
obname1=$(git hash-object file1) &&
|
|
|
|
obname0new=$(echo bar | git hash-object --stdin file1 | sed -n -e 1p) &&
|
|
|
|
obname1new=$(echo bar | git hash-object --stdin file1 | sed -n -e 2p) &&
|
|
|
|
test "$obname0" = "$obname0new" &&
|
|
|
|
test "$obname1" = "$obname1new"
|
|
|
|
'
|
|
|
|
|
2016-09-13 05:23:12 +02:00
|
|
|
test_expect_success 'set up crlf tests' '
|
2008-08-03 16:36:21 +02:00
|
|
|
echo fooQ | tr Q "\\015" >file0 &&
|
|
|
|
cp file0 file1 &&
|
|
|
|
echo "file0 -crlf" >.gitattributes &&
|
|
|
|
echo "file1 crlf" >>.gitattributes &&
|
|
|
|
git config core.autocrlf true &&
|
|
|
|
file0_sha=$(git hash-object file0) &&
|
|
|
|
file1_sha=$(git hash-object file1) &&
|
2016-09-13 05:23:12 +02:00
|
|
|
test "$file0_sha" != "$file1_sha"
|
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success 'check that appropriate filter is invoke when --path is used' '
|
2008-08-03 16:36:21 +02:00
|
|
|
path1_sha=$(git hash-object --path=file1 file0) &&
|
|
|
|
path0_sha=$(git hash-object --path=file0 file1) &&
|
|
|
|
test "$file0_sha" = "$path0_sha" &&
|
|
|
|
test "$file1_sha" = "$path1_sha" &&
|
|
|
|
path1_sha=$(cat file0 | git hash-object --path=file1 --stdin) &&
|
|
|
|
path0_sha=$(cat file1 | git hash-object --path=file0 --stdin) &&
|
|
|
|
test "$file0_sha" = "$path0_sha" &&
|
2016-09-13 05:23:12 +02:00
|
|
|
test "$file1_sha" = "$path1_sha"
|
2008-08-03 16:36:21 +02:00
|
|
|
'
|
|
|
|
|
hash-object: always try to set up the git repository
When "hash-object" is run without "-w", we don't need to be
in a git repository at all; we can just hash the object and
write its sha1 to stdout. However, if we _are_ in a git
repository, we would want to know that so we can follow the
normal rules for respecting config, .gitattributes, etc.
This happens to work at the top-level of a git repository
because we blindly read ".git/config", but as the included
test shows, it does not work when you are in a subdirectory.
The solution is to just do a "gentle" setup in this case. We
already take care to use prefix_filename() on any filename
arguments we get (to handle the "-w" case), so we don't need
to do anything extra to handle the side effects of repo
setup.
An alternative would be to specify RUN_SETUP_GENTLY for this
command in git.c, and then die if "-w" is set but we are not
in a repository. However, the error messages generated at
the time of setup_git_directory() are more detailed, so it's
better to find out which mode we are in, and then call the
appropriate function.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-13 05:23:17 +02:00
|
|
|
test_expect_success 'gitattributes also work in a subdirectory' '
|
|
|
|
mkdir subdir &&
|
|
|
|
(
|
|
|
|
cd subdir &&
|
|
|
|
subdir_sha0=$(git hash-object ../file0) &&
|
|
|
|
subdir_sha1=$(git hash-object ../file1) &&
|
|
|
|
test "$file0_sha" = "$subdir_sha0" &&
|
|
|
|
test "$file1_sha" = "$subdir_sha1"
|
|
|
|
)
|
|
|
|
'
|
|
|
|
|
2017-03-21 02:20:42 +01:00
|
|
|
test_expect_success '--path works in a subdirectory' '
|
|
|
|
(
|
|
|
|
cd subdir &&
|
|
|
|
path1_sha=$(git hash-object --path=../file1 ../file0) &&
|
|
|
|
path0_sha=$(git hash-object --path=../file0 ../file1) &&
|
|
|
|
test "$file0_sha" = "$path0_sha" &&
|
|
|
|
test "$file1_sha" = "$path1_sha"
|
|
|
|
)
|
|
|
|
'
|
|
|
|
|
2008-08-03 16:36:22 +02:00
|
|
|
test_expect_success 'check that --no-filters option works' '
|
|
|
|
nofilters_file1=$(git hash-object --no-filters file1) &&
|
|
|
|
test "$file0_sha" = "$nofilters_file1" &&
|
|
|
|
nofilters_file1=$(cat file1 | git hash-object --stdin) &&
|
2016-09-13 05:23:12 +02:00
|
|
|
test "$file0_sha" = "$nofilters_file1"
|
2008-08-03 16:36:22 +02:00
|
|
|
'
|
|
|
|
|
2010-03-03 21:10:21 +01:00
|
|
|
test_expect_success 'check that --no-filters option works with --stdin-paths' '
|
|
|
|
nofilters_file1=$(echo "file1" | git hash-object --stdin-paths --no-filters) &&
|
2016-09-13 05:23:12 +02:00
|
|
|
test "$file0_sha" = "$nofilters_file1"
|
2010-03-03 21:10:21 +01:00
|
|
|
'
|
|
|
|
|
2008-05-23 16:19:37 +02:00
|
|
|
pop_repo
|
|
|
|
|
|
|
|
for args in "-w --stdin" "--stdin -w"; do
|
|
|
|
push_repo
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success "hash from stdin and write to database ($args)" '
|
|
|
|
test "$(test_oid example)" = $(git hash-object $args < example)
|
2008-05-23 16:19:37 +02:00
|
|
|
'
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_blob_exists "$(test_oid example)"
|
2008-05-23 16:19:37 +02:00
|
|
|
|
|
|
|
pop_repo
|
|
|
|
done
|
2008-02-21 11:06:47 +01:00
|
|
|
|
2008-05-23 16:19:38 +02:00
|
|
|
filenames="hello
|
|
|
|
example"
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
oids="$(test_oid hello)
|
|
|
|
$(test_oid example)"
|
2008-05-23 16:19:38 +02:00
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success "hash two files with names on stdin" '
|
|
|
|
test "$oids" = "$(echo_without_newline "$filenames" | git hash-object --stdin-paths)"
|
2008-05-23 16:19:38 +02:00
|
|
|
'
|
|
|
|
|
|
|
|
for args in "-w --stdin-paths" "--stdin-paths -w"; do
|
|
|
|
push_repo
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_expect_success "hash two files with names on stdin and write to database ($args)" '
|
|
|
|
test "$oids" = "$(echo_without_newline "$filenames" | git hash-object $args)"
|
2008-05-23 16:19:38 +02:00
|
|
|
'
|
|
|
|
|
2019-06-29 00:59:26 +02:00
|
|
|
test_blob_exists "$(test_oid hello)"
|
|
|
|
test_blob_exists "$(test_oid example)"
|
2008-05-23 16:19:38 +02:00
|
|
|
|
|
|
|
pop_repo
|
|
|
|
done
|
|
|
|
|
2016-09-27 22:59:50 +02:00
|
|
|
test_expect_success 'too-short tree' '
|
2011-12-08 14:10:17 +01:00
|
|
|
echo abc >malformed-tree &&
|
2016-09-27 22:59:50 +02:00
|
|
|
test_must_fail git hash-object -t tree malformed-tree 2>err &&
|
2023-01-18 21:35:30 +01:00
|
|
|
grep "too-short tree object" err
|
2016-09-27 22:59:50 +02:00
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success 'malformed mode in tree' '
|
2023-01-18 21:35:30 +01:00
|
|
|
hex_oid=$(echo foo | git hash-object --stdin -w) &&
|
|
|
|
bin_oid=$(echo $hex_oid | hex2oct) &&
|
|
|
|
printf "9100644 \0$bin_oid" >tree-with-malformed-mode &&
|
2016-09-27 22:59:50 +02:00
|
|
|
test_must_fail git hash-object -t tree tree-with-malformed-mode 2>err &&
|
2023-01-18 21:35:30 +01:00
|
|
|
grep "malformed mode in tree entry" err
|
2016-09-27 22:59:50 +02:00
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success 'empty filename in tree' '
|
2023-01-18 21:35:30 +01:00
|
|
|
hex_oid=$(echo foo | git hash-object --stdin -w) &&
|
|
|
|
bin_oid=$(echo $hex_oid | hex2oct) &&
|
|
|
|
printf "100644 \0$bin_oid" >tree-with-empty-filename &&
|
2016-09-27 22:59:50 +02:00
|
|
|
test_must_fail git hash-object -t tree tree-with-empty-filename 2>err &&
|
2023-01-18 21:35:30 +01:00
|
|
|
grep "empty filename in tree entry" err
|
2011-02-05 11:52:21 +01:00
|
|
|
'
|
|
|
|
|
hash-object: use fsck for object checks
Since c879daa237 (Make hash-object more robust against malformed
objects, 2011-02-05), we've done some rudimentary checks against objects
we're about to write by running them through our usual parsers for
trees, commits, and tags.
These parsers catch some problems, but they are not nearly as careful as
the fsck functions (which make sense; the parsers are designed to be
fast and forgiving, bailing only when the input is unintelligible). We
are better off doing the more thorough fsck checks when writing objects.
Doing so at write time is much better than writing garbage only to find
out later (after building more history atop it!) that fsck complains
about it, or hosts with transfer.fsckObjects reject it.
This is obviously going to be a user-visible behavior change, and the
test changes earlier in this series show the scope of the impact. But
I'd argue that this is OK:
- the documentation for hash-object is already vague about which
checks we might do, saying that --literally will allow "any
garbage[...] which might not otherwise pass standard object parsing
or git-fsck checks". So we are already covered under the documented
behavior.
- users don't generally run hash-object anyway. There are a lot of
spots in the tests that needed to be updated because creating
garbage objects is something that Git's tests disproportionately do.
- it's hard to imagine anyone thinking the new behavior is worse. Any
object we reject would be a potential problem down the road for the
user. And if they really want to create garbage, --literally is
already the escape hatch they need.
Note that the change here is actually in index_mem(), which handles the
HASH_FORMAT_CHECK flag passed by hash-object. That flag is also used by
"git-replace --edit" to sanity-check the result. Covering that with more
thorough checks likewise seems like a good thing.
Besides being more thorough, there are a few other bonuses:
- we get rid of some questionable stack allocations of object structs.
These don't seem to currently cause any problems in practice, but
they subtly violate some of the assumptions made by the rest of the
code (e.g., the "struct commit" we put on the stack and
zero-initialize will not have a proper index from
alloc_comit_index().
- likewise, those parsed object structs are the source of some small
memory leaks
- the resulting messages are much better. For example:
[before]
$ echo 'tree 123' | git hash-object -t commit --stdin
error: bogus commit object 0000000000000000000000000000000000000000
fatal: corrupt commit
[after]
$ echo 'tree 123' | git.compile hash-object -t commit --stdin
error: object fails fsck: badTreeSha1: invalid 'tree' line format - bad sha1
fatal: refusing to create malformed object
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-01-18 21:44:12 +01:00
|
|
|
test_expect_success 'duplicate filename in tree' '
|
|
|
|
hex_oid=$(echo foo | git hash-object --stdin -w) &&
|
|
|
|
bin_oid=$(echo $hex_oid | hex2oct) &&
|
|
|
|
{
|
|
|
|
printf "100644 file\0$bin_oid" &&
|
|
|
|
printf "100644 file\0$bin_oid"
|
|
|
|
} >tree-with-duplicate-filename &&
|
|
|
|
test_must_fail git hash-object -t tree tree-with-duplicate-filename 2>err &&
|
|
|
|
grep "duplicateEntries" err
|
|
|
|
'
|
|
|
|
|
2011-02-05 11:52:21 +01:00
|
|
|
test_expect_success 'corrupt commit' '
|
|
|
|
test_must_fail git hash-object -t commit --stdin </dev/null
|
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success 'corrupt tag' '
|
|
|
|
test_must_fail git hash-object -t tag --stdin </dev/null
|
|
|
|
'
|
|
|
|
|
2015-04-17 16:52:48 +02:00
|
|
|
test_expect_success 'hash-object complains about bogus type name' '
|
|
|
|
test_must_fail git hash-object -t bogus --stdin </dev/null
|
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success 'hash-object complains about truncated type name' '
|
|
|
|
test_must_fail git hash-object -t bl --stdin </dev/null
|
|
|
|
'
|
|
|
|
|
2015-05-04 09:25:14 +02:00
|
|
|
test_expect_success '--literally' '
|
|
|
|
t=1234567890 &&
|
|
|
|
echo example | git hash-object -t $t --literally --stdin
|
|
|
|
'
|
|
|
|
|
|
|
|
test_expect_success '--literally with extra-long type' '
|
|
|
|
t=12345678901234567890123456789012345678901234567890 &&
|
|
|
|
t="$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t" &&
|
|
|
|
echo example | git hash-object -t $t --literally --stdin
|
|
|
|
'
|
|
|
|
|
2008-02-21 11:06:47 +01:00
|
|
|
test_done
|