From: Junio C Hamano <gitster@pobox.com>
Date: Tue, 30 Oct 2018 06:43:39 +0000 (+0900)
Subject: Merge branch 'md/filter-trees'
X-Git-Tag: v2.20.0-rc0~129
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=77d503757d6328703f9571a4432dd83800bc26bb;p=thirdparty%2Fgit.git

Merge branch 'md/filter-trees'

The "rev-list --filter" feature learned to exclude all trees via
"tree:0" filter.

* md/filter-trees:
  list-objects: support for skipping tree traversal
  filter-trees: code clean-up of tests
  list-objects-filter: implement filter tree:0
  list-objects-filter-options: do not over-strbuf_init
  list-objects-filter: use BUG rather than die
  revision: mark non-user-given objects instead
  rev-list: handle missing tree objects properly
  list-objects: always parse trees gently
  list-objects: refactor to process_tree_contents
  list-objects: store common func args in struct
---

77d503757d6328703f9571a4432dd83800bc26bb
diff --cc builtin/rev-list.c
index cc1b70522f,49d6deed70..5064d08e1b
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@@ -370,9 -372,10 +372,10 @@@ int cmd_rev_list(int argc, const char *
  		usage(rev_list_usage);
  
  	git_config(git_default_config, NULL);
 -	init_revisions(&revs, prefix);
 +	repo_init_revisions(the_repository, &revs, prefix);
  	revs.abbrev = DEFAULT_ABBREV;
  	revs.commit_format = CMIT_FMT_UNSPECIFIED;
+ 	revs.do_not_die_on_missing_tree = 1;
  
  	/*
  	 * Scan the argument list before invoking setup_revisions(), so that we
diff --cc t/t5317-pack-objects-filter-objects.sh
index 2e718f0bde,d9dccf4d4d..24541ea137
--- a/t/t5317-pack-objects-filter-objects.sh
+++ b/t/t5317-pack-objects-filter-objects.sh
@@@ -54,19 -48,58 +54,60 @@@ test_expect_success 'verify blob:none p
  '
  
  test_expect_success 'verify normal and blob:none packfiles have same commits/trees' '
 -	git -C r1 verify-pack -v ../all.pack \
 -		| grep -E "commit|tree" \
 -		| awk -f print_1.awk \
 -		| sort >expected &&
 -	git -C r1 verify-pack -v ../filter.pack \
 -		| grep -E "commit|tree" \
 -		| awk -f print_1.awk \
 -		| sort >observed &&
 -	test_cmp observed expected
 +	git -C r1 verify-pack -v ../all.pack >verify_result &&
 +	grep -E "commit|tree" verify_result |
 +	awk -f print_1.awk |
 +	sort >expected &&
 +
 +	git -C r1 verify-pack -v ../filter.pack >verify_result &&
 +	grep -E "commit|tree" verify_result |
 +	awk -f print_1.awk |
 +	sort >observed &&
 +
 +	test_cmp expected observed
  '
  
+ test_expect_success 'get an error for missing tree object' '
+ 	git init r5 &&
+ 	echo foo >r5/foo &&
+ 	git -C r5 add foo &&
+ 	git -C r5 commit -m "foo" &&
+ 	del=$(git -C r5 rev-parse HEAD^{tree} | sed "s|..|&/|") &&
+ 	rm r5/.git/objects/$del &&
+ 	test_must_fail git -C r5 pack-objects --rev --stdout 2>bad_tree <<-EOF &&
+ 	HEAD
+ 	EOF
+ 	grep "bad tree object" bad_tree
+ '
+ 
+ test_expect_success 'setup for tests of tree:0' '
+ 	mkdir r1/subtree &&
+ 	echo "This is a file in a subtree" >r1/subtree/file &&
+ 	git -C r1 add subtree/file &&
+ 	git -C r1 commit -m subtree
+ '
+ 
+ test_expect_success 'verify tree:0 packfile has no blobs or trees' '
+ 	git -C r1 pack-objects --rev --stdout --filter=tree:0 >commitsonly.pack <<-EOF &&
+ 	HEAD
+ 	EOF
+ 	git -C r1 index-pack ../commitsonly.pack &&
+ 	git -C r1 verify-pack -v ../commitsonly.pack >objs &&
+ 	! grep -E "tree|blob" objs
+ '
+ 
+ test_expect_success 'grab tree directly when using tree:0' '
+ 	# We should get the tree specified directly but not its blobs or subtrees.
+ 	git -C r1 pack-objects --rev --stdout --filter=tree:0 >commitsonly.pack <<-EOF &&
+ 	HEAD:
+ 	EOF
+ 	git -C r1 index-pack ../commitsonly.pack &&
+ 	git -C r1 verify-pack -v ../commitsonly.pack >objs &&
+ 	awk "/tree|blob/{print \$1}" objs >trees_and_blobs &&
+ 	git -C r1 rev-parse HEAD: >expected &&
+ 	test_cmp expected trees_and_blobs
+ '
+ 
  # Test blob:limit=<n>[kmg] filter.
  # We boundary test around the size parameter.  The filter is strictly less than
  # the value, so size 500 and 1000 should have the same results, but 1001 should
diff --cc t/t6112-rev-list-filters-objects.sh
index 53975c5724,c6aae93b57..eb32505a6e
--- a/t/t6112-rev-list-filters-objects.sh
+++ b/t/t6112-rev-list-filters-objects.sh
@@@ -21,31 -21,36 +21,43 @@@ test_expect_success 'setup r1' 
  
  test_expect_success 'verify blob:none omits all 5 blobs' '
  	git -C r1 ls-files -s file.1 file.2 file.3 file.4 file.5 \
 -		| awk -f print_2.awk \
 -		| sort >expected &&
 -	git -C r1 rev-list HEAD --quiet --objects --filter-print-omitted --filter=blob:none \
 -		| awk -f print_1.awk \
 -		| sed "s/~//" \
 -		| sort >observed &&
 -	test_cmp observed expected
 +		>ls_files_result &&
 +	awk -f print_2.awk ls_files_result |
 +	sort >expected &&
 +
 +	git -C r1 rev-list --quiet --objects --filter-print-omitted \
 +		--filter=blob:none HEAD >revs &&
 +	awk -f print_1.awk revs |
 +	sed "s/~//" |
 +	sort >observed &&
 +
 +	test_cmp expected observed
  '
  
+ test_expect_success 'specify blob explicitly prevents filtering' '
+ 	file_3=$(git -C r1 ls-files -s file.3 |
+ 		 awk -f print_2.awk) &&
+ 
+ 	file_4=$(git -C r1 ls-files -s file.4 |
+ 		 awk -f print_2.awk) &&
+ 
+ 	git -C r1 rev-list --objects --filter=blob:none HEAD $file_3 >observed &&
+ 	grep "$file_3" observed &&
+ 	! grep "$file_4" observed
+ '
+ 
  test_expect_success 'verify emitted+omitted == all' '
 -	git -C r1 rev-list HEAD --objects \
 -		| awk -f print_1.awk \
 -		| sort >expected &&
 -	git -C r1 rev-list HEAD --objects --filter-print-omitted --filter=blob:none \
 -		| awk -f print_1.awk \
 -		| sed "s/~//" \
 -		| sort >observed &&
 -	test_cmp observed expected
 +	git -C r1 rev-list --objects HEAD >revs &&
 +	awk -f print_1.awk revs |
 +	sort >expected &&
 +
 +	git -C r1 rev-list --objects --filter-print-omitted --filter=blob:none \
 +		HEAD >revs &&
 +	awk -f print_1.awk revs |
 +	sed "s/~//" |
 +	sort >observed &&
 +
 +	test_cmp expected observed
  '
  
  
@@@ -219,19 -198,66 +231,69 @@@ test_expect_success 'verify sparse:oid=
  '
  
  test_expect_success 'verify sparse:oid=oid-ish omits top-level files' '
 -	git -C r3 ls-files -s pattern sparse1 sparse2 \
 -		| awk -f print_2.awk \
 -		| sort >expected &&
 -	git -C r3 rev-list HEAD --quiet --objects --filter-print-omitted --filter=sparse:oid=master:pattern \
 -		| awk -f print_1.awk \
 -		| sed "s/~//" \
 -		| sort >observed &&
 -	test_cmp observed expected
 +	git -C r3 ls-files -s pattern sparse1 sparse2 >ls_files_result &&
 +	awk -f print_2.awk ls_files_result |
 +	sort >expected &&
 +
 +	git -C r3 rev-list --quiet --objects --filter-print-omitted \
 +		--filter=sparse:oid=master:pattern HEAD >revs &&
 +	awk -f print_1.awk revs |
 +	sed "s/~//" |
 +	sort >observed &&
 +
 +	test_cmp expected observed
  '
  
+ test_expect_success 'rev-list W/ --missing=print and --missing=allow-any for trees' '
+ 	TREE=$(git -C r3 rev-parse HEAD:dir1) &&
+ 
+ 	# Create a spare repo because we will be deleting objects from this one.
+ 	git clone r3 r3.b &&
+ 
+ 	rm r3.b/.git/objects/$(echo $TREE | sed "s|^..|&/|") &&
+ 
+ 	git -C r3.b rev-list --quiet --missing=print --objects HEAD \
+ 		>missing_objs 2>rev_list_err &&
+ 	echo "?$TREE" >expected &&
+ 	test_cmp expected missing_objs &&
+ 
+ 	# do not complain when a missing tree cannot be parsed
+ 	test_must_be_empty rev_list_err &&
+ 
+ 	git -C r3.b rev-list --missing=allow-any --objects HEAD \
+ 		>objs 2>rev_list_err &&
+ 	! grep $TREE objs &&
+ 	test_must_be_empty rev_list_err
+ '
+ 
+ # Test tree:0 filter.
+ 
+ test_expect_success 'verify tree:0 includes trees in "filtered" output' '
+ 	git -C r3 rev-list --quiet --objects --filter-print-omitted \
+ 		--filter=tree:0 HEAD >revs &&
+ 
+ 	awk -f print_1.awk revs |
+ 	sed s/~// |
+ 	xargs -n1 git -C r3 cat-file -t >unsorted_filtered_types &&
+ 
+ 	sort -u unsorted_filtered_types >filtered_types &&
+ 	test_write_lines blob tree >expected &&
+ 	test_cmp expected filtered_types
+ '
+ 
+ # Make sure tree:0 does not iterate through any trees.
+ 
+ test_expect_success 'filter a GIANT tree through tree:0' '
+ 	GIT_TRACE=1 git -C r3 rev-list \
+ 		--objects --filter=tree:0 HEAD 2>filter_trace &&
+ 	grep "Skipping contents of tree [.][.][.]" filter_trace >actual &&
+ 	# One line for each commit traversed.
+ 	test_line_count = 2 actual &&
+ 
+ 	# Make sure no other trees were considered besides the root.
+ 	! grep "Skipping contents of tree [^.]" filter_trace
+ '
+ 
  # Delete some loose objects and use rev-list, but WITHOUT any filtering.
  # This models previously omitted objects that we did not receive.