git-commit-vandalism/t/t5500-fetch-pack.sh

1034 lines
26 KiB
Bash
Raw Normal View History

#!/bin/sh
#
# Copyright (c) 2005 Johannes Schindelin
#
test_description='Testing multi_ack pack fetching'
GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
tests: mark tests relying on the current default for `init.defaultBranch` In addition to the manual adjustment to let the `linux-gcc` CI job run the test suite with `master` and then with `main`, this patch makes sure that GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME is set in all test scripts that currently rely on the initial branch name being `master by default. To determine which test scripts to mark up, the first step was to force-set the default branch name to `master` in - all test scripts that contain the keyword `master`, - t4211, which expects `t/t4211/history.export` with a hard-coded ref to initialize the default branch, - t5560 because it sources `t/t556x_common` which uses `master`, - t8002 and t8012 because both source `t/annotate-tests.sh` which also uses `master`) This trick was performed by this command: $ sed -i '/^ *\. \.\/\(test-lib\|lib-\(bash\|cvs\|git-svn\)\|gitweb-lib\)\.sh$/i\ GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master\ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME\ ' $(git grep -l master t/t[0-9]*.sh) \ t/t4211*.sh t/t5560*.sh t/t8002*.sh t/t8012*.sh After that, careful, manual inspection revealed that some of the test scripts containing the needle `master` do not actually rely on a specific default branch name: either they mention `master` only in a comment, or they initialize that branch specificially, or they do not actually refer to the current default branch. Therefore, the aforementioned modification was undone in those test scripts thusly: $ git checkout HEAD -- \ t/t0027-auto-crlf.sh t/t0060-path-utils.sh \ t/t1011-read-tree-sparse-checkout.sh \ t/t1305-config-include.sh t/t1309-early-config.sh \ t/t1402-check-ref-format.sh t/t1450-fsck.sh \ t/t2024-checkout-dwim.sh \ t/t2106-update-index-assume-unchanged.sh \ t/t3040-subprojects-basic.sh t/t3301-notes.sh \ t/t3308-notes-merge.sh t/t3423-rebase-reword.sh \ t/t3436-rebase-more-options.sh \ t/t4015-diff-whitespace.sh t/t4257-am-interactive.sh \ t/t5323-pack-redundant.sh t/t5401-update-hooks.sh \ t/t5511-refspec.sh t/t5526-fetch-submodules.sh \ t/t5529-push-errors.sh t/t5530-upload-pack-error.sh \ t/t5548-push-porcelain.sh \ t/t5552-skipping-fetch-negotiator.sh \ t/t5572-pull-submodule.sh t/t5608-clone-2gb.sh \ t/t5614-clone-submodules-shallow.sh \ t/t7508-status.sh t/t7606-merge-custom.sh \ t/t9302-fast-import-unpack-limit.sh We excluded one set of test scripts in these commands, though: the range of `git p4` tests. The reason? `git p4` stores the (foreign) remote branch in the branch called `p4/master`, which is obviously not the default branch. Manual analysis revealed that only five of these tests actually require a specific default branch name to pass; They were modified thusly: $ sed -i '/^ *\. \.\/lib-git-p4\.sh$/i\ GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master\ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME\ ' t/t980[0167]*.sh t/t9811*.sh Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-11-19 00:44:19 +01:00
export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
. ./test-lib.sh
# Test fetch-pack/upload-pack pair.
# Some convenience functions
add () {
name=$1 &&
text="$@" &&
branch=$(echo $name | sed -e 's/^\(.\).*$/\1/') &&
parents="" &&
shift &&
while test $1; do
parents="$parents -p $1" &&
shift
done &&
echo "$text" > test.txt &&
git update-index --add test.txt &&
tree=$(git write-tree) &&
# make sure timestamps are in correct order
test_tick &&
commit=$(echo "$text" | git commit-tree $tree $parents) &&
eval "$name=$commit; export $name" &&
git update-ref "refs/heads/$branch" "$commit" &&
eval ${branch}TIP=$commit
}
pull_to_client () {
number=$1 &&
heads=$2 &&
count=$3 &&
test_expect_success "$number pull" '
(
cd client &&
git fetch-pack -k -v .. $heads &&
case "$heads" in
*A*)
git update-ref refs/heads/A "$ATIP";;
esac &&
case "$heads" in *B*)
git update-ref refs/heads/B "$BTIP";;
esac &&
git symbolic-ref HEAD refs/heads/$(
echo $heads |
sed -e "s/^\(.\).*$/\1/"
) &&
git fsck --full &&
mv .git/objects/pack/pack-* . &&
p=$(ls -1 pack-*.pack) &&
git unpack-objects <$p &&
git fsck --full &&
idx=$(echo pack-*.idx) &&
pack_count=$(git show-index <$idx | wc -l) &&
test $pack_count = $count &&
rm -f pack-*
)
'
}
# Here begins the actual testing
# A1 - ... - A20 - A21
# \
# B1 - B2 - .. - B70
# client pulls A20, B1. Then tracks only B. Then pulls A.
test_expect_success 'setup' '
mkdir client &&
(
cd client &&
git init &&
git config transfer.unpacklimit 0
) &&
add A1 &&
prev=1 &&
cur=2 &&
while [ $cur -le 10 ]; do
add A$cur $(eval echo \$A$prev) &&
prev=$cur &&
cur=$(($cur+1))
done &&
add B1 $A1 &&
git update-ref refs/heads/A "$ATIP" &&
git update-ref refs/heads/B "$BTIP" &&
git symbolic-ref HEAD refs/heads/B
'
pull_to_client 1st "refs/heads/B refs/heads/A" $((11*3))
test_expect_success 'post 1st pull setup' '
add A11 $A10 &&
prev=1 &&
cur=2 &&
while [ $cur -le 65 ]; do
add B$cur $(eval echo \$B$prev) &&
prev=$cur &&
cur=$(($cur+1))
done
'
pull_to_client 2nd "refs/heads/B" $((64*3))
pull_to_client 3rd "refs/heads/A" $((1*3))
test_expect_success 'single branch clone' '
git clone --single-branch "file://$(pwd)/." singlebranch
'
test_expect_success 'single branch object count' '
GIT_DIR=singlebranch/.git git count-objects -v |
grep "^in-pack:" > count.singlebranch &&
echo "in-pack: 198" >expected &&
test_cmp expected count.singlebranch
'
test_expect_success 'single given branch clone' '
git clone --single-branch --branch A "file://$(pwd)/." branch-a &&
test_must_fail git --git-dir=branch-a/.git rev-parse origin/B
'
test_expect_success 'clone shallow depth 1' '
git clone --no-single-branch --depth 1 "file://$(pwd)/." shallow0 &&
test "$(git --git-dir=shallow0/.git rev-list --count HEAD)" = 1
'
test_expect_success 'clone shallow depth 1 with fsck' '
git config --global fetch.fsckobjects true &&
git clone --no-single-branch --depth 1 "file://$(pwd)/." shallow0fsck &&
test "$(git --git-dir=shallow0fsck/.git rev-list --count HEAD)" = 1 &&
git config --global --unset fetch.fsckobjects
'
test_expect_success 'clone shallow' '
git clone --no-single-branch --depth 2 "file://$(pwd)/." shallow
'
test_expect_success 'clone shallow depth count' '
test "$(git --git-dir=shallow/.git rev-list --count HEAD)" = 2
'
test_expect_success 'clone shallow object count' '
(
cd shallow &&
git count-objects -v
) > count.shallow &&
grep "^in-pack: 12" count.shallow
'
test_expect_success 'clone shallow object count (part 2)' '
sed -e "/^in-pack:/d" -e "/^packs:/d" -e "/^size-pack:/d" \
-e "/: 0$/d" count.shallow > count_output &&
test_must_be_empty count_output
'
test_expect_success 'fsck in shallow repo' '
(
cd shallow &&
git fsck --full
)
'
test_expect_success 'simple fetch in shallow repo' '
(
cd shallow &&
git fetch
)
'
test_expect_success 'no changes expected' '
(
cd shallow &&
git count-objects -v
) > count.shallow.2 &&
cmp count.shallow count.shallow.2
'
test_expect_success 'fetch same depth in shallow repo' '
(
cd shallow &&
git fetch --depth=2
)
'
test_expect_success 'no changes expected' '
(
cd shallow &&
git count-objects -v
) > count.shallow.3 &&
cmp count.shallow count.shallow.3
'
test_expect_success 'add two more' '
add B66 $B65 &&
add B67 $B66
'
test_expect_success 'pull in shallow repo' '
(
cd shallow &&
git pull .. B
)
'
test_expect_success 'clone shallow object count' '
(
cd shallow &&
git count-objects -v
) > count.shallow &&
grep "^count: 6" count.shallow
'
test_expect_success 'add two more (part 2)' '
add B68 $B67 &&
add B69 $B68
'
test_expect_success 'deepening pull in shallow repo' '
(
cd shallow &&
git pull --depth 4 .. B
)
'
test_expect_success 'clone shallow object count' '
(
cd shallow &&
git count-objects -v
) > count.shallow &&
grep "^count: 12" count.shallow
'
test_expect_success 'deepening fetch in shallow repo' '
(
cd shallow &&
git fetch --depth 4 .. A:A
)
'
test_expect_success 'clone shallow object count' '
(
cd shallow &&
git count-objects -v
) > count.shallow &&
grep "^count: 18" count.shallow
'
test_expect_success 'pull in shallow repo with missing merge base' '
(
cd shallow &&
git fetch --depth 4 .. A &&
merge: refuse to create too cool a merge by default While it makes sense to allow merging unrelated histories of two projects that started independently into one, in the way "gitk" was merged to "git" itself aka "the coolest merge ever", such a merge is still an unusual event. Worse, if somebody creates an independent history by starting from a tarball of an established project and sends a pull request to the original project, "git merge" however happily creates such a merge without any sign of something unusual is happening. Teach "git merge" to refuse to create such a merge by default, unless the user passes a new "--allow-unrelated-histories" option to tell it that the user is aware that two unrelated projects are merged. Because such a "two project merge" is a rare event, a configuration option to always allow such a merge is not added. We could add the same option to "git pull" and have it passed through to underlying "git merge". I do not have a fundamental opposition against such a feature, but this commit does not do so and instead leaves it as low-hanging fruit for others, because such a "two project merge" would be done after fetching the other project into some location in the working tree of an existing project and making sure how well they fit together, it is sufficient to allow a local merge without such an option pass-through from "git pull" to "git merge". Many tests that are updated by this patch does the pass-through manually by turning: git pull something into its equivalent: git fetch something && git merge --allow-unrelated-histories FETCH_HEAD If somebody is inclined to add such an option, updated tests in this change need to be adjusted back to: git pull --allow-unrelated-histories something Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-03-18 21:21:09 +01:00
test_must_fail git merge --allow-unrelated-histories FETCH_HEAD
)
'
test_expect_success 'additional simple shallow deepenings' '
(
cd shallow &&
git fetch --depth=8 &&
git fetch --depth=10 &&
git fetch --depth=11
)
'
test_expect_success 'clone shallow depth count' '
test "$(git --git-dir=shallow/.git rev-list --count HEAD)" = 11
'
test_expect_success 'clone shallow object count' '
(
cd shallow &&
merge: refuse to create too cool a merge by default While it makes sense to allow merging unrelated histories of two projects that started independently into one, in the way "gitk" was merged to "git" itself aka "the coolest merge ever", such a merge is still an unusual event. Worse, if somebody creates an independent history by starting from a tarball of an established project and sends a pull request to the original project, "git merge" however happily creates such a merge without any sign of something unusual is happening. Teach "git merge" to refuse to create such a merge by default, unless the user passes a new "--allow-unrelated-histories" option to tell it that the user is aware that two unrelated projects are merged. Because such a "two project merge" is a rare event, a configuration option to always allow such a merge is not added. We could add the same option to "git pull" and have it passed through to underlying "git merge". I do not have a fundamental opposition against such a feature, but this commit does not do so and instead leaves it as low-hanging fruit for others, because such a "two project merge" would be done after fetching the other project into some location in the working tree of an existing project and making sure how well they fit together, it is sufficient to allow a local merge without such an option pass-through from "git pull" to "git merge". Many tests that are updated by this patch does the pass-through manually by turning: git pull something into its equivalent: git fetch something && git merge --allow-unrelated-histories FETCH_HEAD If somebody is inclined to add such an option, updated tests in this change need to be adjusted back to: git pull --allow-unrelated-histories something Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-03-18 21:21:09 +01:00
git prune &&
git count-objects -v
) > count.shallow &&
merge: refuse to create too cool a merge by default While it makes sense to allow merging unrelated histories of two projects that started independently into one, in the way "gitk" was merged to "git" itself aka "the coolest merge ever", such a merge is still an unusual event. Worse, if somebody creates an independent history by starting from a tarball of an established project and sends a pull request to the original project, "git merge" however happily creates such a merge without any sign of something unusual is happening. Teach "git merge" to refuse to create such a merge by default, unless the user passes a new "--allow-unrelated-histories" option to tell it that the user is aware that two unrelated projects are merged. Because such a "two project merge" is a rare event, a configuration option to always allow such a merge is not added. We could add the same option to "git pull" and have it passed through to underlying "git merge". I do not have a fundamental opposition against such a feature, but this commit does not do so and instead leaves it as low-hanging fruit for others, because such a "two project merge" would be done after fetching the other project into some location in the working tree of an existing project and making sure how well they fit together, it is sufficient to allow a local merge without such an option pass-through from "git pull" to "git merge". Many tests that are updated by this patch does the pass-through manually by turning: git pull something into its equivalent: git fetch something && git merge --allow-unrelated-histories FETCH_HEAD If somebody is inclined to add such an option, updated tests in this change need to be adjusted back to: git pull --allow-unrelated-histories something Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-03-18 21:21:09 +01:00
grep "^count: 54" count.shallow
'
test_expect_success 'fetch --no-shallow on full repo' '
test_must_fail git fetch --noshallow
'
test_expect_success 'fetch --depth --no-shallow' '
(
cd shallow &&
test_must_fail git fetch --depth=1 --noshallow
)
'
test_expect_success 'turn shallow to complete repository' '
(
cd shallow &&
git fetch --unshallow &&
! test -f .git/shallow &&
git fsck --full
)
'
test_expect_success 'clone shallow without --no-single-branch' '
git clone --depth 1 "file://$(pwd)/." shallow2
'
test_expect_success 'clone shallow object count' '
(
cd shallow2 &&
git count-objects -v
) > count.shallow2 &&
grep "^in-pack: 3" count.shallow2
'
test_expect_success 'clone shallow with --branch' '
git clone --depth 1 --branch A "file://$(pwd)/." shallow3
'
test_expect_success 'clone shallow object count' '
echo "in-pack: 3" > count3.expected &&
GIT_DIR=shallow3/.git git count-objects -v |
grep "^in-pack" > count3.actual &&
test_cmp count3.expected count3.actual
'
test_expect_success 'clone shallow with detached HEAD' '
git checkout HEAD^ &&
git clone --depth 1 "file://$(pwd)/." shallow5 &&
git checkout - &&
GIT_DIR=shallow5/.git git rev-parse HEAD >actual &&
git rev-parse HEAD^ >expected &&
test_cmp expected actual
'
test_expect_success 'shallow clone pulling tags' '
git tag -a -m A TAGA1 A &&
git tag -a -m B TAGB1 B &&
git tag TAGA2 A &&
git tag TAGB2 B &&
git clone --depth 1 "file://$(pwd)/." shallow6 &&
cat >taglist.expected <<\EOF &&
TAGB1
TAGB2
EOF
GIT_DIR=shallow6/.git git tag -l >taglist.actual &&
test_cmp taglist.expected taglist.actual &&
echo "in-pack: 4" > count6.expected &&
GIT_DIR=shallow6/.git git count-objects -v |
grep "^in-pack" > count6.actual &&
test_cmp count6.expected count6.actual
'
test_expect_success 'shallow cloning single tag' '
git clone --depth 1 --branch=TAGB1 "file://$(pwd)/." shallow7 &&
cat >taglist.expected <<\EOF &&
TAGB1
TAGB2
EOF
GIT_DIR=shallow7/.git git tag -l >taglist.actual &&
test_cmp taglist.expected taglist.actual &&
echo "in-pack: 4" > count7.expected &&
GIT_DIR=shallow7/.git git count-objects -v |
grep "^in-pack" > count7.actual &&
test_cmp count7.expected count7.actual
'
upload-pack: make sure "want" objects are parsed When upload-pack receives a "want" line from the client, it adds it to an object array. We call lookup_object to find the actual object, which will only check for objects already in memory. This works because we are expecting to find objects that we already loaded during the ref advertisement. We use the resulting object structs for a variety of purposes. Some of them care only about the object flags, but others care about the type of the object (e.g., ok_to_give_up), or even feed them to the revision parser (when --depth is used), which assumes that objects it receives are fully parsed. Once upon a time, this was OK; any object we loaded into memory would also have been parsed. But since 435c833 (upload-pack: use peel_ref for ref advertisements, 2012-10-04), we try to avoid parsing objects during the ref advertisement. This means that lookup_object may return an object with a type of OBJ_NONE. The resulting mess depends on the exact set of objects, but can include the revision parser barfing, or the shallow code sending the wrong set of objects. This patch teaches upload-pack to parse each "want" object as we receive it. We do not replace the lookup_object call with parse_object, as the current code is careful not to let just any object appear on a "want" line, but rather only one we have previously advertised (whereas parse_object would actually load any arbitrary object from disk). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-16 11:27:01 +01:00
test_expect_success 'clone shallow with packed refs' '
git pack-refs --all &&
git clone --depth 1 --branch A "file://$(pwd)/." shallow8 &&
echo "in-pack: 4" > count8.expected &&
GIT_DIR=shallow8/.git git count-objects -v |
grep "^in-pack" > count8.actual &&
test_cmp count8.expected count8.actual
'
test_expect_success 'in_vain not triggered before first ACK' '
rm -rf myserver myclient &&
git init myserver &&
test_commit -C myserver foo &&
git clone "file://$(pwd)/myserver" myclient &&
# MAX_IN_VAIN is 256. Because of batching, the client will send 496
# (16+32+64+128+256) commits, not 256, before giving up. So create 496
# irrelevant commits.
test_commit_bulk -C myclient 496 &&
# The new commit that the client wants to fetch.
test_commit -C myserver bar &&
git -C myclient fetch --progress origin 2>log &&
test_i18ngrep "remote: Total 3 " log
'
test_expect_success 'in_vain resetted upon ACK' '
rm -rf myserver myclient &&
git init myserver &&
# Linked list of commits on main. The first is common; the rest are
# not.
test_commit -C myserver first_main_commit &&
git clone "file://$(pwd)/myserver" myclient &&
test_commit_bulk -C myclient 255 &&
# Another linked list of commits on anotherbranch with no connection to
# main. The first is common; the rest are not.
git -C myserver checkout --orphan anotherbranch &&
test_commit -C myserver first_anotherbranch_commit &&
git -C myclient fetch origin anotherbranch:refs/heads/anotherbranch &&
git -C myclient checkout anotherbranch &&
test_commit_bulk -C myclient 255 &&
# The new commit that the client wants to fetch.
git -C myserver checkout main &&
test_commit -C myserver to_fetch &&
# The client will send (as "have"s) all 256 commits in anotherbranch
# first. The 256th commit is common between the client and the server,
# and should reset in_vain. This allows negotiation to continue until
# the client reports that first_anotherbranch_commit is common.
git -C myclient fetch --progress origin main 2>log &&
test_i18ngrep "Total 3 " log
'
test_expect_success 'fetch in shallow repo unreachable shallow objects' '
(
git clone --bare --branch B --single-branch "file://$(pwd)/." no-reflog &&
git clone --depth 1 "file://$(pwd)/no-reflog" shallow9 &&
cd no-reflog &&
git tag -d TAGB1 TAGB2 &&
git update-ref refs/heads/B B~~ &&
git gc --prune=now &&
cd ../shallow9 &&
git fetch origin &&
git fsck --no-dangling
)
'
test_expect_success 'fetch creating new shallow root' '
(
git clone "file://$(pwd)/." shallow10 &&
git commit --allow-empty -m empty &&
cd shallow10 &&
git fetch --depth=1 --progress 2>actual &&
# This should fetch only the empty commit, no tree or
# blob objects
test_i18ngrep "remote: Total 1" actual
)
'
test_expect_success 'setup tests for the --stdin parameter' '
for head in C D E F
do
add $head
done &&
for head in A B C D E F
do
git tag $head $head
done &&
cat >input <<-\EOF &&
refs/heads/C
refs/heads/A
refs/heads/D
refs/tags/C
refs/heads/B
refs/tags/A
refs/heads/E
refs/tags/B
refs/tags/E
refs/tags/D
EOF
sort <input >expect &&
(
echo refs/heads/E &&
echo refs/tags/E &&
cat input
) >input.dup
'
test_expect_success 'setup fetch refs from cmdline v[12]' '
cp -r client client0 &&
cp -r client client1 &&
cp -r client client2
'
for version in '' 0 1 2
do
test_expect_success "protocol.version=$version fetch refs from cmdline" "
(
cd client$version &&
GIT_TEST_PROTOCOL_VERSION=$version git fetch-pack --no-progress .. \$(cat ../input)
) >output &&
cut -d ' ' -f 2 <output | sort >actual &&
test_cmp expect actual
"
done
test_expect_success 'fetch refs from stdin' '
(
cd client &&
git fetch-pack --stdin --no-progress .. <../input
) >output &&
cut -d " " -f 2 <output | sort >actual &&
test_cmp expect actual
'
test_expect_success 'fetch mixed refs from cmdline and stdin' '
(
cd client &&
tail -n +5 ../input |
git fetch-pack --stdin --no-progress .. $(head -n 4 ../input)
) >output &&
cut -d " " -f 2 <output | sort >actual &&
test_cmp expect actual
'
test_expect_success 'test duplicate refs from stdin' '
(
cd client &&
git fetch-pack --stdin --no-progress .. <../input.dup
) >output &&
cut -d " " -f 2 <output | sort >actual &&
test_cmp expect actual
'
test_expect_success 'set up tests of missing reference' '
cat >expect-error <<-\EOF
error: no such remote ref refs/heads/xyzzy
EOF
'
test_expect_success 'test lonely missing ref' '
(
cd client &&
test_must_fail git fetch-pack --no-progress .. refs/heads/xyzzy 2>../error-m
) &&
test_cmp expect-error error-m
'
test_expect_success 'test missing ref after existing' '
(
cd client &&
test_must_fail git fetch-pack --no-progress .. refs/heads/A refs/heads/xyzzy 2>../error-em
) &&
test_cmp expect-error error-em
'
test_expect_success 'test missing ref before existing' '
(
cd client &&
test_must_fail git fetch-pack --no-progress .. refs/heads/xyzzy refs/heads/A 2>../error-me
) &&
test_cmp expect-error error-me
'
test_expect_success 'test --all, --depth, and explicit head' '
(
cd client &&
git fetch-pack --no-progress --all --depth=1 .. refs/heads/A
) >out-adh 2>error-adh
'
test_expect_success 'test --all, --depth, and explicit tag' '
git tag OLDTAG refs/heads/B~5 &&
(
cd client &&
git fetch-pack --no-progress --all --depth=1 .. refs/tags/OLDTAG
) >out-adt 2>error-adt
'
fetch-pack: don't try to fetch peel values with --all When "fetch-pack --all" sees a tag-to-blob on the remote, it tries to fetch both the tag itself ("refs/tags/foo") and the peeled value that the remote advertises ("refs/tags/foo^{}"). Asking for the object pointed to by the latter can cause upload-pack to complain with "not our ref", since it does not mark the peeled objects with the OUR_REF (unless they were at the tip of some other ref). Arguably upload-pack _should_ be marking those peeled objects. But it never has in the past, since clients would generally just ask for the tag and expect to get the peeled value along with it. And that's how "git fetch" works, as well as older versions of "fetch-pack --all". The problem was introduced by 5f0fc64513 (fetch-pack: eliminate spurious error messages, 2012-09-09). Before then, the matching logic was something like: if (refname is ill-formed) do nothing else if (doing --all) always consider it matched else look through list of sought refs for a match That commit wanted to flip the order of the second two arms of that conditional. But we ended up with: if (refname is ill-formed) do nothing else look through list of sought refs for a match if (--all and no match so far) always consider it matched That means tha an ill-formed ref will trigger the --all conditional block, even though we should just be ignoring it. We can fix that by having a single "else" with all of the well-formed logic, that checks the sought refs and "--all" in the correct order. Reported-by: Kirill Smelkov <kirr@nexedi.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-06-11 07:53:57 +02:00
test_expect_success 'test --all with tag to non-tip' '
git commit --allow-empty -m non-tip &&
git commit --allow-empty -m tip &&
git tag -m "annotated" non-tip HEAD^ &&
(
cd client &&
git fetch-pack --all ..
)
'
test_expect_success 'test --all wrt tag to non-commits' '
# create tag-to-{blob,tree,commit,tag}, making sure all tagged objects
# are reachable only via created tag references.
blob=$(echo "hello blob" | git hash-object -t blob -w --stdin) &&
git tag -a -m "tag -> blob" tag-to-blob $blob &&
tree=$(printf "100644 blob $blob\tfile" | git mktree) &&
git tag -a -m "tag -> tree" tag-to-tree $tree &&
tree2=$(printf "100644 blob $blob\tfile2" | git mktree) &&
commit=$(git commit-tree -m "hello commit" $tree) &&
git tag -a -m "tag -> commit" tag-to-commit $commit &&
blob2=$(echo "hello blob2" | git hash-object -t blob -w --stdin) &&
tag=$(git mktag <<-EOF
object $blob2
type blob
tag tag-to-blob2
tagger author A U Thor <author@example.com> 0 +0000
hello tag
EOF
) &&
git tag -a -m "tag -> tag" tag-to-tag $tag &&
# `fetch-pack --all` should succeed fetching all those objects.
mkdir fetchall &&
(
cd fetchall &&
git init &&
git fetch-pack --all .. &&
git cat-file blob $blob >/dev/null &&
git cat-file tree $tree >/dev/null &&
git cat-file commit $commit >/dev/null &&
git cat-file tag $tag >/dev/null
)
'
test_expect_success 'shallow fetch with tags does not break the repository' '
mkdir repo1 &&
(
cd repo1 &&
git init &&
test_commit 1 &&
test_commit 2 &&
test_commit 3 &&
mkdir repo2 &&
cd repo2 &&
git init &&
git fetch --depth=2 ../.git main:branch &&
git fsck
)
'
test_expect_success 'fetch-pack can fetch a raw sha1' '
git init hidden &&
(
cd hidden &&
test_commit 1 &&
test_commit 2 &&
git update-ref refs/hidden/one HEAD^ &&
git config transfer.hiderefs refs/hidden &&
git config uploadpack.allowtipsha1inwant true
) &&
git fetch-pack hidden $(git -C hidden rev-parse refs/hidden/one)
'
test_expect_success 'fetch-pack can fetch a raw sha1 that is advertised as a ref' '
rm -rf server client &&
git init server &&
test_commit -C server 1 &&
git init client &&
git -C client fetch-pack ../server \
$(git -C server rev-parse refs/heads/main)
'
test_expect_success 'fetch-pack can fetch a raw sha1 overlapping a named ref' '
rm -rf server client &&
git init server &&
test_commit -C server 1 &&
test_commit -C server 2 &&
git init client &&
git -C client fetch-pack ../server \
$(git -C server rev-parse refs/tags/1) refs/tags/1
'
test_expect_success 'fetch-pack cannot fetch a raw sha1 that is not advertised as a ref' '
rm -rf server &&
git init server &&
test_commit -C server 5 &&
git -C server tag -d 5 &&
test_commit -C server 6 &&
git init client &&
# Some protocol versions (e.g. 2) support fetching
# unadvertised objects, so restrict this test to v0.
test_must_fail env GIT_TEST_PROTOCOL_VERSION=0 git -C client fetch-pack ../server \
$(git -C server rev-parse refs/heads/main^) 2>err &&
test_i18ngrep "Server does not allow request for unadvertised object" err
'
check_prot_path () {
cat >expected <<-EOF &&
Diag: url=$1
Diag: protocol=$2
Diag: path=$3
EOF
git fetch-pack --diag-url "$1" | grep -v hostandport= >actual &&
test_cmp expected actual
}
check_prot_host_port_path () {
case "$2" in
*ssh*)
pp=ssh
uah=userandhost
ehost=$(echo $3 | tr -d "[]")
diagport="Diag: port=$4"
;;
*)
pp=$p
uah=hostandport
ehost=$(echo $3$4 | sed -e "s/22$/:22/" -e "s/NONE//")
diagport=""
;;
esac
cat >exp <<-EOF &&
Diag: url=$1
Diag: protocol=$pp
Diag: $uah=$ehost
$diagport
Diag: path=$5
EOF
grep -v "^$" exp >expected
git fetch-pack --diag-url "$1" >actual &&
test_cmp expected actual
}
for r in repo re:po re/po
do
# git or ssh with scheme
for p in "ssh+git" "git+ssh" git ssh
do
for h in host user@host user@[::1] user@::1
do
for c in "" :
do
test_expect_success "fetch-pack --diag-url $p://$h$c/$r" '
check_prot_host_port_path $p://$h/$r $p "$h" NONE "/$r"
'
# "/~" -> "~" conversion
test_expect_success "fetch-pack --diag-url $p://$h$c/~$r" '
check_prot_host_port_path $p://$h/~$r $p "$h" NONE "~$r"
'
done
done
for h in host User@host User@[::1]
do
test_expect_success "fetch-pack --diag-url $p://$h:22/$r" '
check_prot_host_port_path $p://$h:22/$r $p "$h" 22 "/$r"
'
done
done
# file with scheme
for p in file
do
test_expect_success !MINGW "fetch-pack --diag-url $p://$h/$r" '
check_prot_path $p://$h/$r $p "/$r"
'
test_expect_success MINGW "fetch-pack --diag-url $p://$h/$r" '
check_prot_path $p://$h/$r $p "//$h/$r"
'
test_expect_success MINGW "fetch-pack --diag-url $p:///$r" '
check_prot_path $p:///$r $p "/$r"
'
# No "/~" -> "~" conversion for file
test_expect_success !MINGW "fetch-pack --diag-url $p://$h/~$r" '
check_prot_path $p://$h/~$r $p "/~$r"
'
test_expect_success MINGW "fetch-pack --diag-url $p://$h/~$r" '
check_prot_path $p://$h/~$r $p "//$h/~$r"
'
done
# file without scheme
for h in nohost nohost:12 [::1] [::1]:23 [ [:aa
do
test_expect_success "fetch-pack --diag-url ./$h:$r" '
check_prot_path ./$h:$r $p "./$h:$r"
'
# No "/~" -> "~" conversion for file
test_expect_success "fetch-pack --diag-url ./$p:$h/~$r" '
check_prot_path ./$p:$h/~$r $p "./$p:$h/~$r"
'
done
#ssh without scheme
p=ssh
for h in host [::1]
do
test_expect_success "fetch-pack --diag-url $h:$r" '
check_prot_host_port_path $h:$r $p "$h" NONE "$r"
'
# Do "/~" -> "~" conversion
test_expect_success "fetch-pack --diag-url $h:/~$r" '
check_prot_host_port_path $h:/~$r $p "$h" NONE "~$r"
'
done
done
test_expect_success MINGW 'fetch-pack --diag-url file://c:/repo' '
check_prot_path file://c:/repo file c:/repo
'
test_expect_success MINGW 'fetch-pack --diag-url c:repo' '
check_prot_path c:repo file c:repo
'
test_expect_success 'clone shallow since ...' '
test_create_repo shallow-since &&
(
cd shallow-since &&
GIT_COMMITTER_DATE="100000000 +0700" git commit --allow-empty -m one &&
GIT_COMMITTER_DATE="200000000 +0700" git commit --allow-empty -m two &&
GIT_COMMITTER_DATE="300000000 +0700" git commit --allow-empty -m three &&
git clone --shallow-since "300000000 +0700" "file://$(pwd)/." ../shallow11 &&
git -C ../shallow11 log --pretty=tformat:%s HEAD >actual &&
echo three >expected &&
test_cmp expected actual
)
'
test_expect_success 'fetch shallow since ...' '
git -C shallow11 fetch --shallow-since "200000000 +0700" origin &&
git -C shallow11 log --pretty=tformat:%s origin/main >actual &&
cat >expected <<-\EOF &&
three
two
EOF
test_cmp expected actual
'
upload-pack: reject shallow requests that would return nothing Shallow clones with --shallow-since or --shalow-exclude work by running rev-list to get all reachable commits, then draw a boundary between reachable and unreachable and send "shallow" requests based on that. The code does miss one corner case: if rev-list returns nothing, we'll have no border and we'll send no shallow requests back to the client (i.e. no history cuts). This essentially means a full clone (or a full branch if the client requests just one branch). One example is the oldest commit is older than what is specified by --shallow-since. To avoid this, if rev-list returns nothing, we abort the clone/fetch. The user could adjust their request (e.g. --shallow-since further back in the past) and retry. Another possible option for this case is to fall back to a default depth (like depth 1). But I don't like too much magic that way because we may return something unexpected to the user. If they request "history since 2008" and we return a single depth at 2000, that might break stuff for them. It is better to tell them that something is wrong and let them take the best course of action. Note that we need to die() in get_shallow_commits_by_rev_list() instead of just checking for empty result from its caller deepen_by_rev_list() and handling the error there. The reason is, empty result could be a valid case: if you have commits in year 2013 and you request --shallow-since=year.2000 then you should get a full clone (i.e. empty result). Reported-by: Andreas Krey <a.krey@gmx.de> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-05-26 13:35:18 +02:00
test_expect_success 'clone shallow since selects no commits' '
test_create_repo shallow-since-the-future &&
(
cd shallow-since-the-future &&
GIT_COMMITTER_DATE="100000000 +0700" git commit --allow-empty -m one &&
GIT_COMMITTER_DATE="200000000 +0700" git commit --allow-empty -m two &&
GIT_COMMITTER_DATE="300000000 +0700" git commit --allow-empty -m three &&
test_must_fail git clone --shallow-since "900000000 +0700" "file://$(pwd)/." ../shallow111
)
'
upload-pack: disable commit graph more gently for shallow traversal When the client has asked for certain shallow options like "deepen-since", we do a custom rev-list walk that pretends to be shallow. Before doing so, we have to disable the commit-graph, since it is not compatible with the shallow view of the repository. That's handled by 829a321569 (commit-graph: close_commit_graph before shallow walk, 2018-08-20). That commit literally closes and frees our repo->objects->commit_graph struct. That creates an interesting problem for commits that have _already_ been parsed using the commit graph. Their commit->object.parsed flag is set, their commit->graph_pos is set, but their commit->maybe_tree may still be NULL. When somebody later calls repo_get_commit_tree(), we see that we haven't loaded the tree oid yet and try to get it from the commit graph. But since it has been freed, we segfault! So the root of the issue is a data dependency between the commit's lazy-load of the tree oid and the fact that the commit graph can go away mid-process. How can we resolve it? There are a couple of general approaches: 1. The obvious answer is to avoid loading the tree from the graph when we see that it's NULL. But then what do we return for the tree oid? If we return NULL, our caller in do_traverse() will rightly complain that we have no tree. We'd have to fallback to loading the actual commit object and re-parsing it. That requires teaching parse_commit_buffer() to understand re-parsing (i.e., not starting from a clean slate and not leaking any allocated bits like parent list pointers). 2. When we close the commit graph, walk through the set of in-memory objects and clear any graph_pos pointers. But this means we also have to "unparse" any such commits so that we know they still need to open the commit object to fill in their trees. So it's no less complicated than (1), and is more expensive (since we clear objects we might not later need). 3. Stop freeing the commit-graph struct. Continue to let it be used for lazy-loads of tree oids, but let upload-pack specify that it shouldn't be used for further commit parsing. 4. Push the whole shallow rev-list out to its own sub-process, with the commit-graph disabled from the start, giving it a clean memory space to work from. I've chosen (3) here. Options (1) and (2) would work, but are non-trivial to implement. Option (4) is more expensive, and I'm not sure how complicated it is (shelling out for the actual rev-list part is easy, but we do then parse the resulting commits internally, and I'm not clear which parts need to be handling shallow-ness). The new test in t5500 triggers this segfault, but see the comments there for how horribly intimate it has to be with how both upload-pack and commit graphs work. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-12 16:44:45 +02:00
# A few subtle things about the request in this test:
#
# - the server must have commit-graphs present and enabled
#
# - the history is such that our want/have share a common ancestor ("base"
# here)
#
# - we send only a single have, which is fewer than a normal client would
# send. This ensures that we don't parse "base" up front with
# parse_object(), but rather traverse to it as a parent while deciding if we
# can stop the "have" negotiation, and call parse_commit(). The former
# sees the actual object data and so always loads the three oid, whereas the
# latter will try to load it lazily.
#
# - we must use protocol v2, because it handles the "have" negotiation before
# processing the shallow directives
#
test_expect_success 'shallow since with commit graph and already-seen commit' '
test_create_repo shallow-since-graph &&
(
cd shallow-since-graph &&
test_commit base &&
test_commit main &&
upload-pack: disable commit graph more gently for shallow traversal When the client has asked for certain shallow options like "deepen-since", we do a custom rev-list walk that pretends to be shallow. Before doing so, we have to disable the commit-graph, since it is not compatible with the shallow view of the repository. That's handled by 829a321569 (commit-graph: close_commit_graph before shallow walk, 2018-08-20). That commit literally closes and frees our repo->objects->commit_graph struct. That creates an interesting problem for commits that have _already_ been parsed using the commit graph. Their commit->object.parsed flag is set, their commit->graph_pos is set, but their commit->maybe_tree may still be NULL. When somebody later calls repo_get_commit_tree(), we see that we haven't loaded the tree oid yet and try to get it from the commit graph. But since it has been freed, we segfault! So the root of the issue is a data dependency between the commit's lazy-load of the tree oid and the fact that the commit graph can go away mid-process. How can we resolve it? There are a couple of general approaches: 1. The obvious answer is to avoid loading the tree from the graph when we see that it's NULL. But then what do we return for the tree oid? If we return NULL, our caller in do_traverse() will rightly complain that we have no tree. We'd have to fallback to loading the actual commit object and re-parsing it. That requires teaching parse_commit_buffer() to understand re-parsing (i.e., not starting from a clean slate and not leaking any allocated bits like parent list pointers). 2. When we close the commit graph, walk through the set of in-memory objects and clear any graph_pos pointers. But this means we also have to "unparse" any such commits so that we know they still need to open the commit object to fill in their trees. So it's no less complicated than (1), and is more expensive (since we clear objects we might not later need). 3. Stop freeing the commit-graph struct. Continue to let it be used for lazy-loads of tree oids, but let upload-pack specify that it shouldn't be used for further commit parsing. 4. Push the whole shallow rev-list out to its own sub-process, with the commit-graph disabled from the start, giving it a clean memory space to work from. I've chosen (3) here. Options (1) and (2) would work, but are non-trivial to implement. Option (4) is more expensive, and I'm not sure how complicated it is (shelling out for the actual rev-list part is easy, but we do then parse the resulting commits internally, and I'm not clear which parts need to be handling shallow-ness). The new test in t5500 triggers this segfault, but see the comments there for how horribly intimate it has to be with how both upload-pack and commit graphs work. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-12 16:44:45 +02:00
git checkout -b other HEAD^ &&
test_commit other &&
git commit-graph write --reachable &&
git config core.commitGraph true &&
GIT_PROTOCOL=version=2 git upload-pack . <<-EOF >/dev/null
0012command=fetch
$(echo "object-format=$(test_oid algo)" | packetize)
upload-pack: disable commit graph more gently for shallow traversal When the client has asked for certain shallow options like "deepen-since", we do a custom rev-list walk that pretends to be shallow. Before doing so, we have to disable the commit-graph, since it is not compatible with the shallow view of the repository. That's handled by 829a321569 (commit-graph: close_commit_graph before shallow walk, 2018-08-20). That commit literally closes and frees our repo->objects->commit_graph struct. That creates an interesting problem for commits that have _already_ been parsed using the commit graph. Their commit->object.parsed flag is set, their commit->graph_pos is set, but their commit->maybe_tree may still be NULL. When somebody later calls repo_get_commit_tree(), we see that we haven't loaded the tree oid yet and try to get it from the commit graph. But since it has been freed, we segfault! So the root of the issue is a data dependency between the commit's lazy-load of the tree oid and the fact that the commit graph can go away mid-process. How can we resolve it? There are a couple of general approaches: 1. The obvious answer is to avoid loading the tree from the graph when we see that it's NULL. But then what do we return for the tree oid? If we return NULL, our caller in do_traverse() will rightly complain that we have no tree. We'd have to fallback to loading the actual commit object and re-parsing it. That requires teaching parse_commit_buffer() to understand re-parsing (i.e., not starting from a clean slate and not leaking any allocated bits like parent list pointers). 2. When we close the commit graph, walk through the set of in-memory objects and clear any graph_pos pointers. But this means we also have to "unparse" any such commits so that we know they still need to open the commit object to fill in their trees. So it's no less complicated than (1), and is more expensive (since we clear objects we might not later need). 3. Stop freeing the commit-graph struct. Continue to let it be used for lazy-loads of tree oids, but let upload-pack specify that it shouldn't be used for further commit parsing. 4. Push the whole shallow rev-list out to its own sub-process, with the commit-graph disabled from the start, giving it a clean memory space to work from. I've chosen (3) here. Options (1) and (2) would work, but are non-trivial to implement. Option (4) is more expensive, and I'm not sure how complicated it is (shelling out for the actual rev-list part is easy, but we do then parse the resulting commits internally, and I'm not clear which parts need to be handling shallow-ness). The new test in t5500 triggers this segfault, but see the comments there for how horribly intimate it has to be with how both upload-pack and commit graphs work. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-12 16:44:45 +02:00
00010013deepen-since 1
$(echo "want $(git rev-parse other)" | packetize)
$(echo "have $(git rev-parse main)" | packetize)
upload-pack: disable commit graph more gently for shallow traversal When the client has asked for certain shallow options like "deepen-since", we do a custom rev-list walk that pretends to be shallow. Before doing so, we have to disable the commit-graph, since it is not compatible with the shallow view of the repository. That's handled by 829a321569 (commit-graph: close_commit_graph before shallow walk, 2018-08-20). That commit literally closes and frees our repo->objects->commit_graph struct. That creates an interesting problem for commits that have _already_ been parsed using the commit graph. Their commit->object.parsed flag is set, their commit->graph_pos is set, but their commit->maybe_tree may still be NULL. When somebody later calls repo_get_commit_tree(), we see that we haven't loaded the tree oid yet and try to get it from the commit graph. But since it has been freed, we segfault! So the root of the issue is a data dependency between the commit's lazy-load of the tree oid and the fact that the commit graph can go away mid-process. How can we resolve it? There are a couple of general approaches: 1. The obvious answer is to avoid loading the tree from the graph when we see that it's NULL. But then what do we return for the tree oid? If we return NULL, our caller in do_traverse() will rightly complain that we have no tree. We'd have to fallback to loading the actual commit object and re-parsing it. That requires teaching parse_commit_buffer() to understand re-parsing (i.e., not starting from a clean slate and not leaking any allocated bits like parent list pointers). 2. When we close the commit graph, walk through the set of in-memory objects and clear any graph_pos pointers. But this means we also have to "unparse" any such commits so that we know they still need to open the commit object to fill in their trees. So it's no less complicated than (1), and is more expensive (since we clear objects we might not later need). 3. Stop freeing the commit-graph struct. Continue to let it be used for lazy-loads of tree oids, but let upload-pack specify that it shouldn't be used for further commit parsing. 4. Push the whole shallow rev-list out to its own sub-process, with the commit-graph disabled from the start, giving it a clean memory space to work from. I've chosen (3) here. Options (1) and (2) would work, but are non-trivial to implement. Option (4) is more expensive, and I'm not sure how complicated it is (shelling out for the actual rev-list part is easy, but we do then parse the resulting commits internally, and I'm not clear which parts need to be handling shallow-ness). The new test in t5500 triggers this segfault, but see the comments there for how horribly intimate it has to be with how both upload-pack and commit graphs work. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-12 16:44:45 +02:00
0000
EOF
)
'
test_expect_success 'shallow clone exclude tag two' '
test_create_repo shallow-exclude &&
(
cd shallow-exclude &&
test_commit one &&
test_commit two &&
test_commit three &&
git clone --shallow-exclude two "file://$(pwd)/." ../shallow12 &&
git -C ../shallow12 log --pretty=tformat:%s HEAD >actual &&
echo three >expected &&
test_cmp expected actual
)
'
test_expect_success 'fetch exclude tag one' '
git -C shallow12 fetch --shallow-exclude one origin &&
git -C shallow12 log --pretty=tformat:%s origin/main >actual &&
test_write_lines three two >expected &&
test_cmp expected actual
'
fetch, upload-pack: --deepen=N extends shallow boundary by N commits In git-fetch, --depth argument is always relative with the latest remote refs. This makes it a bit difficult to cover this use case, where the user wants to make the shallow history, say 3 levels deeper. It would work if remote refs have not moved yet, but nobody can guarantee that, especially when that use case is performed a couple months after the last clone or "git fetch --depth". Also, modifying shallow boundary using --depth does not work well with clones created by --since or --not. This patch fixes that. A new argument --deepen=<N> will add <N> more (*) parent commits to the current history regardless of where remote refs are. Have/Want negotiation is still respected. So if remote refs move, the server will send two chunks: one between "have" and "want" and another to extend shallow history. In theory, the client could send no "want"s in order to get the second chunk only. But the protocol does not allow that. Either you send no want lines, which means ls-remote; or you have to send at least one want line that carries deep-relative to the server.. The main work was done by Dongcan Jiang. I fixed it up here and there. And of course all the bugs belong to me. (*) We could even support --deepen=<N> where <N> is negative. In that case we can cut some history from the shallow clone. This operation (and --depth=<shorter depth>) does not require interaction with remote side (and more complicated to implement as a result). Helped-by: Duy Nguyen <pclouds@gmail.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Dongcan Jiang <dongcan.jiang@gmail.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-12 12:54:09 +02:00
test_expect_success 'fetching deepen' '
test_create_repo shallow-deepen &&
(
cd shallow-deepen &&
test_commit one &&
test_commit two &&
test_commit three &&
git clone --depth 1 "file://$(pwd)/." deepen &&
test_commit four &&
git -C deepen log --pretty=tformat:%s main >actual &&
fetch, upload-pack: --deepen=N extends shallow boundary by N commits In git-fetch, --depth argument is always relative with the latest remote refs. This makes it a bit difficult to cover this use case, where the user wants to make the shallow history, say 3 levels deeper. It would work if remote refs have not moved yet, but nobody can guarantee that, especially when that use case is performed a couple months after the last clone or "git fetch --depth". Also, modifying shallow boundary using --depth does not work well with clones created by --since or --not. This patch fixes that. A new argument --deepen=<N> will add <N> more (*) parent commits to the current history regardless of where remote refs are. Have/Want negotiation is still respected. So if remote refs move, the server will send two chunks: one between "have" and "want" and another to extend shallow history. In theory, the client could send no "want"s in order to get the second chunk only. But the protocol does not allow that. Either you send no want lines, which means ls-remote; or you have to send at least one want line that carries deep-relative to the server.. The main work was done by Dongcan Jiang. I fixed it up here and there. And of course all the bugs belong to me. (*) We could even support --deepen=<N> where <N> is negative. In that case we can cut some history from the shallow clone. This operation (and --depth=<shorter depth>) does not require interaction with remote side (and more complicated to implement as a result). Helped-by: Duy Nguyen <pclouds@gmail.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Dongcan Jiang <dongcan.jiang@gmail.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-12 12:54:09 +02:00
echo three >expected &&
test_cmp expected actual &&
git -C deepen fetch --deepen=1 &&
git -C deepen log --pretty=tformat:%s origin/main >actual &&
fetch, upload-pack: --deepen=N extends shallow boundary by N commits In git-fetch, --depth argument is always relative with the latest remote refs. This makes it a bit difficult to cover this use case, where the user wants to make the shallow history, say 3 levels deeper. It would work if remote refs have not moved yet, but nobody can guarantee that, especially when that use case is performed a couple months after the last clone or "git fetch --depth". Also, modifying shallow boundary using --depth does not work well with clones created by --since or --not. This patch fixes that. A new argument --deepen=<N> will add <N> more (*) parent commits to the current history regardless of where remote refs are. Have/Want negotiation is still respected. So if remote refs move, the server will send two chunks: one between "have" and "want" and another to extend shallow history. In theory, the client could send no "want"s in order to get the second chunk only. But the protocol does not allow that. Either you send no want lines, which means ls-remote; or you have to send at least one want line that carries deep-relative to the server.. The main work was done by Dongcan Jiang. I fixed it up here and there. And of course all the bugs belong to me. (*) We could even support --deepen=<N> where <N> is negative. In that case we can cut some history from the shallow clone. This operation (and --depth=<shorter depth>) does not require interaction with remote side (and more complicated to implement as a result). Helped-by: Duy Nguyen <pclouds@gmail.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Dongcan Jiang <dongcan.jiang@gmail.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-12 12:54:09 +02:00
cat >expected <<-\EOF &&
four
three
two
EOF
test_cmp expected actual
)
'
test_expect_success 'use ref advertisement to prune "have" lines sent' '
rm -rf server client &&
git init server &&
test_commit -C server both_have_1 &&
git -C server tag -d both_have_1 &&
test_commit -C server both_have_2 &&
git clone server client &&
test_commit -C server server_has &&
test_commit -C client client_has &&
# In both protocol v0 and v2, ensure that the parent of both_have_2 is
# not sent as a "have" line. The client should know that the server has
# both_have_2, so it only needs to inform the server that it has
# both_have_2, and the server can infer the rest.
rm -f trace &&
cp -r client clientv0 &&
GIT_TRACE_PACKET="$(pwd)/trace" git -C clientv0 \
fetch origin server_has both_have_2 &&
grep "have $(git -C client rev-parse client_has)" trace &&
grep "have $(git -C client rev-parse both_have_2)" trace &&
! grep "have $(git -C client rev-parse both_have_2^)" trace &&
rm -f trace &&
cp -r client clientv2 &&
GIT_TRACE_PACKET="$(pwd)/trace" git -C clientv2 -c protocol.version=2 \
fetch origin server_has both_have_2 &&
grep "have $(git -C client rev-parse client_has)" trace &&
grep "have $(git -C client rev-parse both_have_2)" trace &&
! grep "have $(git -C client rev-parse both_have_2^)" trace
'
test_expect_success 'filtering by size' '
rm -rf server client &&
test_create_repo server &&
test_commit -C server one &&
test_config -C server uploadpack.allowfilter 1 &&
test_create_repo client &&
git -C client fetch-pack --filter=blob:limit=0 ../server HEAD &&
# Ensure that object is not inadvertently fetched
commit=$(git -C server rev-parse HEAD) &&
blob=$(git hash-object server/one.t) &&
git -C client rev-list --objects --missing=allow-any "$commit" >oids &&
! grep "$blob" oids
'
test_expect_success 'filtering by size has no effect if support for it is not advertised' '
rm -rf server client &&
test_create_repo server &&
test_commit -C server one &&
test_create_repo client &&
git -C client fetch-pack --filter=blob:limit=0 ../server HEAD 2> err &&
# Ensure that object is fetched
commit=$(git -C server rev-parse HEAD) &&
blob=$(git hash-object server/one.t) &&
git -C client rev-list --objects --missing=allow-any "$commit" >oids &&
grep "$blob" oids &&
test_i18ngrep "filtering not recognized by server" err
'
fetch_filter_blob_limit_zero () {
SERVER="$1"
URL="$2"
rm -rf "$SERVER" client &&
test_create_repo "$SERVER" &&
test_commit -C "$SERVER" one &&
test_config -C "$SERVER" uploadpack.allowfilter 1 &&
git clone "$URL" client &&
test_commit -C "$SERVER" two &&
git -C client fetch --filter=blob:limit=0 origin HEAD:somewhere &&
# Ensure that commit is fetched, but blob is not
commit=$(git -C "$SERVER" rev-parse two) &&
blob=$(git hash-object server/two.t) &&
git -C client rev-list --objects --missing=allow-any "$commit" >oids &&
grep "$commit" oids &&
! grep "$blob" oids
}
test_expect_success 'fetch with --filter=blob:limit=0' '
fetch_filter_blob_limit_zero server server
'
. "$TEST_DIRECTORY"/lib-httpd.sh
start_httpd
test_expect_success 'fetch with --filter=blob:limit=0 and HTTP' '
fetch_filter_blob_limit_zero "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
'
# DO NOT add non-httpd-specific tests here, because the last part of this
# test script is only executed when httpd is available and enabled.
test_done