git-commit-vandalism/t/t0003-attributes.sh

373 lines
9.9 KiB
Bash
Raw Normal View History

#!/bin/sh
test_description=gitattributes
. ./test-lib.sh
attr: do not respect symlinks for in-tree .gitattributes The attributes system may sometimes read in-tree files from the filesystem, and sometimes from the index. In the latter case, we do not resolve symbolic links (and are not likely to ever start doing so). Let's open filesystem links with O_NOFOLLOW so that the two cases behave consistently. As a bonus, this means that git will not follow such symlinks to read and parse out-of-tree paths. In some cases this could have security implications, as a malicious repository can cause Git to open and read arbitrary files. It could already feed arbitrary content to the parser, but in certain setups it might be able to exfiltrate data from those paths (e.g., if an automated service operating on the malicious repo reveals its stderr to an attacker). Note that O_NOFOLLOW only prevents following links for the path itself, not intermediate directories in the path. At first glance, it seems like ln -s /some/path in-repo might still look at "in-repo/.gitattributes", following the symlink to "/some/path/.gitattributes". However, if "in-repo" is a symbolic link, then we know that it has no git paths below it, and will never look at its .gitattributes file. We will continue to support out-of-tree symbolic links (e.g., in $GIT_DIR/info/attributes); this just affects in-tree links. When a symbolic link is encountered, the contents are ignored and a warning is printed. POSIX specifies ELOOP in this case, so the user would generally see something like: warning: unable to access '.gitattributes': Too many levels of symbolic links Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-16 15:44:32 +01:00
attr_check_basic () {
path="$1" expect="$2" git_opts="$3" &&
git $git_opts check-attr test -- "$path" >actual 2>err &&
echo "$path: test: $expect" >expect &&
attr: do not respect symlinks for in-tree .gitattributes The attributes system may sometimes read in-tree files from the filesystem, and sometimes from the index. In the latter case, we do not resolve symbolic links (and are not likely to ever start doing so). Let's open filesystem links with O_NOFOLLOW so that the two cases behave consistently. As a bonus, this means that git will not follow such symlinks to read and parse out-of-tree paths. In some cases this could have security implications, as a malicious repository can cause Git to open and read arbitrary files. It could already feed arbitrary content to the parser, but in certain setups it might be able to exfiltrate data from those paths (e.g., if an automated service operating on the malicious repo reveals its stderr to an attacker). Note that O_NOFOLLOW only prevents following links for the path itself, not intermediate directories in the path. At first glance, it seems like ln -s /some/path in-repo might still look at "in-repo/.gitattributes", following the symlink to "/some/path/.gitattributes". However, if "in-repo" is a symbolic link, then we know that it has no git paths below it, and will never look at its .gitattributes file. We will continue to support out-of-tree symbolic links (e.g., in $GIT_DIR/info/attributes); this just affects in-tree links. When a symbolic link is encountered, the contents are ignored and a warning is printed. POSIX specifies ELOOP in this case, so the user would generally see something like: warning: unable to access '.gitattributes': Too many levels of symbolic links Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-16 15:44:32 +01:00
test_cmp expect actual
}
attr_check () {
attr_check_basic "$@" &&
test_must_be_empty err
}
attr_check_quote () {
path="$1" quoted_path="$2" expect="$3" &&
git check-attr test -- "$path" >actual &&
echo "\"$quoted_path\": test: $expect" >expect &&
test_cmp expect actual
}
test_expect_success 'open-quoted pathname' '
echo "\"a test=a" >.gitattributes &&
attr_check a unspecified
'
test_expect_success 'setup' '
mkdir -p a/b/d a/c b &&
(
echo "[attr]notest !test" &&
echo "\" d \" test=d" &&
echo " e test=e" &&
echo " e\" test=e" &&
echo "f test=f" &&
echo "a/i test=a/i" &&
echo "onoff test -test" &&
echo "offon -test test" &&
echo "no notest" &&
echo "A/e/F test=A/e/F"
) >.gitattributes &&
(
echo "g test=a/g" &&
echo "b/g test=a/b/g"
) >a/.gitattributes &&
(
echo "h test=a/b/h" &&
echo "d/* test=a/b/d/*" &&
echo "d/yes notest"
) >a/b/.gitattributes &&
(
echo "global test=global"
) >"$HOME"/global-gitattributes &&
cat <<-EOF >expect-all
f: test: f
a/f: test: f
a/c/f: test: f
a/g: test: a/g
a/b/g: test: a/b/g
b/g: test: unspecified
a/b/h: test: a/b/h
a/b/d/g: test: a/b/d/*
onoff: test: unset
offon: test: set
no: notest: set
no: test: unspecified
a/b/d/no: notest: set
a/b/d/no: test: a/b/d/*
a/b/d/yes: notest: set
a/b/d/yes: test: unspecified
EOF
'
test_expect_success 'command line checks' '
test_must_fail git check-attr &&
test_must_fail git check-attr -- &&
test_must_fail git check-attr test &&
test_must_fail git check-attr test -- &&
test_must_fail git check-attr -- f &&
echo "f" | test_must_fail git check-attr --stdin &&
echo "f" | test_must_fail git check-attr --stdin -- f &&
echo "f" | test_must_fail git check-attr --stdin test -- f &&
test_must_fail git check-attr "" -- f
'
test_expect_success 'attribute test' '
attr_check " d " d &&
attr_check e e &&
attr_check_quote e\" e\\\" e &&
attr_check f f &&
attr_check a/f f &&
attr_check a/c/f f &&
attr_check a/g a/g &&
attr_check a/b/g a/b/g &&
attr_check b/g unspecified &&
attr_check a/b/h a/b/h &&
attr_check a/b/d/g "a/b/d/*" &&
attr_check onoff unset &&
attr_check offon set &&
attr_check no unspecified &&
attr_check a/b/d/no "a/b/d/*" &&
attr_check a/b/d/yes unspecified
'
test_expect_success 'attribute matching is case sensitive when core.ignorecase=0' '
attr_check F unspecified "-c core.ignorecase=0" &&
attr_check a/F unspecified "-c core.ignorecase=0" &&
attr_check a/c/F unspecified "-c core.ignorecase=0" &&
attr_check a/G unspecified "-c core.ignorecase=0" &&
attr_check a/B/g a/g "-c core.ignorecase=0" &&
attr_check a/b/G unspecified "-c core.ignorecase=0" &&
attr_check a/b/H unspecified "-c core.ignorecase=0" &&
attr_check a/b/D/g a/g "-c core.ignorecase=0" &&
attr_check oNoFf unspecified "-c core.ignorecase=0" &&
attr_check oFfOn unspecified "-c core.ignorecase=0" &&
attr_check NO unspecified "-c core.ignorecase=0" &&
attr_check a/b/D/NO unspecified "-c core.ignorecase=0" &&
attr_check a/b/d/YES a/b/d/* "-c core.ignorecase=0" &&
attr_check a/E/f f "-c core.ignorecase=0"
'
test_expect_success 'attribute matching is case insensitive when core.ignorecase=1' '
attr_check F f "-c core.ignorecase=1" &&
attr_check a/F f "-c core.ignorecase=1" &&
attr_check a/c/F f "-c core.ignorecase=1" &&
attr_check a/G a/g "-c core.ignorecase=1" &&
attr_check a/B/g a/b/g "-c core.ignorecase=1" &&
attr_check a/b/G a/b/g "-c core.ignorecase=1" &&
attr_check a/b/H a/b/h "-c core.ignorecase=1" &&
attr_check a/b/D/g "a/b/d/*" "-c core.ignorecase=1" &&
attr_check oNoFf unset "-c core.ignorecase=1" &&
attr_check oFfOn set "-c core.ignorecase=1" &&
attr_check NO unspecified "-c core.ignorecase=1" &&
attr_check a/b/D/NO "a/b/d/*" "-c core.ignorecase=1" &&
attr_check a/b/d/YES unspecified "-c core.ignorecase=1" &&
attr_check a/E/f "A/e/F" "-c core.ignorecase=1"
'
test_expect_success CASE_INSENSITIVE_FS 'additional case insensitivity tests' '
attr_check a/B/D/g a/g "-c core.ignorecase=0" &&
attr_check A/B/D/NO unspecified "-c core.ignorecase=0" &&
attr_check A/b/h a/b/h "-c core.ignorecase=1" &&
attr_check a/B/D/g "a/b/d/*" "-c core.ignorecase=1" &&
attr_check A/B/D/NO "a/b/d/*" "-c core.ignorecase=1"
'
test_expect_success 'unnormalized paths' '
attr_check ./f f &&
attr_check ./a/g a/g &&
attr_check a/./g a/g &&
attr_check a/c/../b/g a/b/g
'
test_expect_success 'relative paths' '
(cd a && attr_check ../f f) &&
(cd a && attr_check f f) &&
(cd a && attr_check i a/i) &&
(cd a && attr_check g a/g) &&
(cd a && attr_check b/g a/b/g) &&
(cd b && attr_check ../a/f f) &&
(cd b && attr_check ../a/g a/g) &&
(cd b && attr_check ../a/b/g a/b/g)
'
attr: don't confuse prefixes with leading directories When we prepare the attribute stack for a lookup on a path, we start with the cached stack from the previous lookup (because it is common to do several lookups in the same directory hierarchy). So the first thing we must do in preparing the stack is to pop any entries that point to directories we are no longer interested in. For example, if our stack contains gitattributes for: foo/bar/baz foo/bar foo but we want to do a lookup in "foo/bar/bleep", then we want to pop the top element, but retain the others. To do this we walk down the stack from the top, popping elements that do not match our lookup directory. However, the test do this simply checked strncmp, meaning we would mistake "foo/bar/baz" as a leading directory of "foo/bar/baz_plus". We must also check that the character after our match is '/', meaning we matched the whole path component. There are two special cases to consider: 1. The top of our attr stack has the empty path. So we must not check for '/', but rather special-case the empty path, which always matches. 2. Typically when matching paths in this way, you would also need to check for a full string match (i.e., the character after is '\0'). We don't need to do so in this case, though, because our path string is actually just the directory component of the path to a file (i.e., we know that it terminates with "/", because the filename comes after that). Helped-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-10 19:08:21 +01:00
test_expect_success 'prefixes are not confused with leading directories' '
attr_check a_plus/g unspecified &&
cat >expect <<-\EOF &&
a/g: test: a/g
a_plus/g: test: unspecified
EOF
git check-attr test a/g a_plus/g >actual &&
test_cmp expect actual
'
test_expect_success 'core.attributesfile' '
attr_check global unspecified &&
git config core.attributesfile "$HOME/global-gitattributes" &&
attr_check global global &&
git config core.attributesfile "~/global-gitattributes" &&
attr_check global global &&
echo "global test=precedence" >>.gitattributes &&
attr_check global precedence
'
test_expect_success 'attribute test: read paths from stdin' '
grep -v notest <expect-all >expect &&
sed -e "s/:.*//" <expect | git check-attr --stdin test >actual &&
test_cmp expect actual
'
test_expect_success 'attribute test: --all option' '
grep -v unspecified <expect-all | sort >specified-all &&
sed -e "s/:.*//" <expect-all | uniq >stdin-all &&
git check-attr --stdin --all <stdin-all | sort >actual &&
test_cmp specified-all actual
'
test_expect_success 'attribute test: --cached option' '
git check-attr --cached --stdin --all <stdin-all | sort >actual &&
tests: use 'test_must_be_empty' instead of 'test_cmp <empty> <out>' Using 'test_must_be_empty' is shorter and more idiomatic than >empty && test_cmp empty out as it saves the creation of an empty file. Furthermore, sometimes the expected empty file doesn't have such a descriptive name like 'empty', and its creation is far away from the place where it's finally used for comparison (e.g. in 't7600-merge.sh', where two expected empty files are created in the 'setup' test, but are used only about 500 lines later). These cases were found by instrumenting 'test_cmp' to error out the test script when it's used to compare empty files, and then converted manually. Note that even after this patch there still remain a lot of cases where we use 'test_cmp' to check empty files: - Sometimes the expected output is not hard-coded in the test, but 'test_cmp' is used to ensure that two similar git commands produce the same output, and that output happens to be empty, e.g. the test 'submodule update --merge - ignores --merge for new submodules' in 't7406-submodule-update.sh'. - Repetitive common tasks, including preparing the expected results and running 'test_cmp', are often extracted into a helper function, and some of this helper's callsites expect no output. - For the same reason as above, the whole 'test_expect_success' block is within a helper function, e.g. in 't3070-wildmatch.sh'. - Or 'test_cmp' is invoked in a loop, e.g. the test 'cvs update (-p)' in 't9400-git-cvsserver-server.sh'. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-08-19 23:57:25 +02:00
test_must_be_empty actual &&
git add .gitattributes a/.gitattributes a/b/.gitattributes &&
git check-attr --cached --stdin --all <stdin-all | sort >actual &&
test_cmp specified-all actual
'
test_expect_success 'root subdir attribute test' '
attr_check a/i a/i &&
attr_check subdir/a/i unspecified
'
test_expect_success 'negative patterns' '
echo "!f test=bar" >.gitattributes &&
git check-attr test -- '"'"'!f'"'"' 2>errors &&
test_i18ngrep "Negative patterns are ignored" errors
'
test_expect_success 'patterns starting with exclamation' '
echo "\!f test=foo" >.gitattributes &&
attr_check "!f" foo
'
test_expect_success '"**" test' '
echo "**/f foo=bar" >.gitattributes &&
cat <<\EOF >expect &&
f: foo: bar
a/f: foo: bar
a/b/f: foo: bar
a/b/c/f: foo: bar
EOF
git check-attr foo -- "f" >actual 2>err &&
git check-attr foo -- "a/f" >>actual 2>>err &&
git check-attr foo -- "a/b/f" >>actual 2>>err &&
git check-attr foo -- "a/b/c/f" >>actual 2>>err &&
test_cmp expect actual &&
test_must_be_empty err
'
test_expect_success '"**" with no slashes test' '
echo "a**f foo=bar" >.gitattributes &&
git check-attr foo -- "f" >actual &&
cat <<\EOF >expect &&
f: foo: unspecified
af: foo: bar
axf: foo: bar
a/f: foo: unspecified
a/b/f: foo: unspecified
a/b/c/f: foo: unspecified
EOF
git check-attr foo -- "f" >actual 2>err &&
git check-attr foo -- "af" >>actual 2>err &&
git check-attr foo -- "axf" >>actual 2>err &&
git check-attr foo -- "a/f" >>actual 2>>err &&
git check-attr foo -- "a/b/f" >>actual 2>>err &&
git check-attr foo -- "a/b/c/f" >>actual 2>>err &&
test_cmp expect actual &&
test_must_be_empty err
'
test_expect_success 'using --git-dir and --work-tree' '
mkdir unreal real &&
git init real &&
echo "file test=in-real" >real/.gitattributes &&
(
cd unreal &&
attr_check file in-real "--git-dir ../real/.git --work-tree ../real"
)
'
test_expect_success 'setup bare' '
git clone --bare . bare.git
'
test_expect_success 'bare repository: check that .gitattribute is ignored' '
(
cd bare.git &&
(
echo "f test=f" &&
echo "a/i test=a/i"
) >.gitattributes &&
attr_check f unspecified &&
attr_check a/f unspecified &&
attr_check a/c/f unspecified &&
attr_check a/i unspecified &&
attr_check subdir/a/i unspecified
)
'
test_expect_success 'bare repository: check that --cached honors index' '
(
cd bare.git &&
GIT_INDEX_FILE=../.git/index \
git check-attr --cached --stdin --all <../stdin-all |
sort >actual &&
test_cmp ../specified-all actual
)
'
test_expect_success 'bare repository: test info/attributes' '
(
cd bare.git &&
(
echo "f test=f" &&
echo "a/i test=a/i"
) >info/attributes &&
attr_check f f &&
attr_check a/f f &&
attr_check a/c/f f &&
attr_check a/i a/i &&
attr_check subdir/a/i unspecified
)
'
attr: do not mark queried macros as unset Since 60a12722ac (attr: remove maybe-real, maybe-macro from git_attr, 2017-01-27), we will always mark an attribute macro (e.g., "binary") that is specifically queried for as "unspecified", even though listing _all_ attributes would display it at set. E.g.: $ echo "* binary" >.gitattributes $ git check-attr -a file file: binary: set file: diff: unset file: merge: unset file: text: unset $ git check-attr binary file file: binary: unspecified The problem stems from an incorrect conversion of the optimization from 06a604e670 (attr: avoid heavy work when we know the specified attr is not defined, 2014-12-28). There we tried in collect_some_attrs() to avoid even looking at the attr_stack when the user has asked for "foo" and we know that "foo" did not ever appear in any .gitattributes file. It used a flag "maybe_real" in each attribute struct, where "real" meant that the attribute appeared in an actual file (we have to make this distinction because we also create an attribute struct for any names that are being queried). But as explained in that commit message, the meaning of "real" was tangled with some special cases around macros. When 60a12722ac later refactored the macro code, it dropped maybe_real entirely. This missed the fact that "maybe_real" could be unset for two reasons: because of a macro, or because it was never found during parsing. This had two results: - the optimization in collect_some_attrs() ceased doing anything meaningful, since it no longer kept track of "was it found during parsing" - worse, it actually kicked in when the caller _did_ ask about a macro by name, causing us to mark it as unspecified It should be possible to salvage this optimization, but let's start with just removing the remnants. It hasn't been doing anything (except creating bugs) since 60a12722ac, and nobody seems to have noticed the performance regression. It's more important to fix the correctness problem clearly first. I've added two tests here. The second one actually shows off the bug. The test of "check-attr -a" is not strictly necessary, but we currently do not test attribute macros much, and the builtin "binary" not at all. So this increases our general test coverage, as well as making sure we didn't mess up this related case. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-18 22:34:58 +01:00
test_expect_success 'binary macro expanded by -a' '
echo "file binary" >.gitattributes &&
cat >expect <<-\EOF &&
file: binary: set
file: diff: unset
file: merge: unset
file: text: unset
EOF
git check-attr -a file >actual &&
test_cmp expect actual
'
test_expect_success 'query binary macro directly' '
echo "file binary" >.gitattributes &&
echo file: binary: set >expect &&
git check-attr binary file >actual &&
test_cmp expect actual
'
attr: do not respect symlinks for in-tree .gitattributes The attributes system may sometimes read in-tree files from the filesystem, and sometimes from the index. In the latter case, we do not resolve symbolic links (and are not likely to ever start doing so). Let's open filesystem links with O_NOFOLLOW so that the two cases behave consistently. As a bonus, this means that git will not follow such symlinks to read and parse out-of-tree paths. In some cases this could have security implications, as a malicious repository can cause Git to open and read arbitrary files. It could already feed arbitrary content to the parser, but in certain setups it might be able to exfiltrate data from those paths (e.g., if an automated service operating on the malicious repo reveals its stderr to an attacker). Note that O_NOFOLLOW only prevents following links for the path itself, not intermediate directories in the path. At first glance, it seems like ln -s /some/path in-repo might still look at "in-repo/.gitattributes", following the symlink to "/some/path/.gitattributes". However, if "in-repo" is a symbolic link, then we know that it has no git paths below it, and will never look at its .gitattributes file. We will continue to support out-of-tree symbolic links (e.g., in $GIT_DIR/info/attributes); this just affects in-tree links. When a symbolic link is encountered, the contents are ignored and a warning is printed. POSIX specifies ELOOP in this case, so the user would generally see something like: warning: unable to access '.gitattributes': Too many levels of symbolic links Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-16 15:44:32 +01:00
test_expect_success SYMLINKS 'set up symlink tests' '
echo "* test" >attr &&
rm -f .gitattributes
'
test_expect_success SYMLINKS 'symlinks respected in core.attributesFile' '
test_when_finished "rm symlink" &&
ln -s attr symlink &&
test_config core.attributesFile "$(pwd)/symlink" &&
attr_check file set
'
test_expect_success SYMLINKS 'symlinks respected in info/attributes' '
test_when_finished "rm .git/info/attributes" &&
ln -s ../../attr .git/info/attributes &&
attr_check file set
'
test_expect_success SYMLINKS 'symlinks not respected in-tree' '
test_when_finished "rm -rf .gitattributes subdir" &&
ln -s attr .gitattributes &&
mkdir subdir &&
ln -s ../attr subdir/.gitattributes &&
attr_check_basic subdir/file unspecified &&
test_i18ngrep "unable to access.*gitattributes" err
'
test_done