From: Junio C Hamano <gitster@pobox.com>
Date: Wed, 16 Apr 2025 20:54:20 +0000 (-0700)
Subject: Merge branch 'ps/cat-file-filter-batch'
X-Git-Tag: v2.50.0-rc0~101
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=a271b05066a1fd2c3a62508d9908d6c5df14a1cb;p=thirdparty%2Fgit.git

Merge branch 'ps/cat-file-filter-batch'

"git cat-file --batch" and friends learned to allow "--filter=" to
omit certain objects, just like the transport layer does.

* ps/cat-file-filter-batch:
  builtin/cat-file: use bitmaps to efficiently filter by object type
  builtin/cat-file: deduplicate logic to iterate over all objects
  pack-bitmap: introduce function to check whether a pack is bitmapped
  pack-bitmap: add function to iterate over filtered bitmapped objects
  pack-bitmap: allow passing payloads to `show_reachable_fn()`
  builtin/cat-file: support "object:type=" objects filter
  builtin/cat-file: support "blob:limit=" objects filter
  builtin/cat-file: support "blob:none" objects filter
  builtin/cat-file: wire up an option to filter objects
  builtin/cat-file: introduce function to report object status
  builtin/cat-file: rename variable that tracks usage
---

a271b05066a1fd2c3a62508d9908d6c5df14a1cb
diff --cc t/t1006-cat-file.sh
index aa64678c64,98638fa2b9..ce8b27bf54
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@@ -1398,16 -1345,111 +1398,115 @@@ $? == 0 or die "\$?=$?"
  
  expect="$hello_oid blob $hello_size"
  
 -test_expect_success PERL '--batch-check is unbuffered by default' '
 -	perl -e "$script" -- --batch-check $hello_oid "$expect"
 +test_lazy_prereq PERL_IPC_OPEN2 '
 +	perl -MIPC::Open2 -e "exit 0"
 +'
 +
 +test_expect_success PERL_IPC_OPEN2 '--batch-check is unbuffered by default' '
 +	perl -e "$perl_script" -- --batch-check $hello_oid "$expect"
  '
  
 -test_expect_success PERL '--batch-command info is unbuffered by default' '
 -	perl -e "$script" -- --batch-command $hello_oid "$expect" "info "
 +test_expect_success PERL_IPC_OPEN2 '--batch-command info is unbuffered by default' '
 +	perl -e "$perl_script" -- --batch-command $hello_oid "$expect" "info "
  '
  
+ test_expect_success 'setup for objects filter' '
+ 	git init repo &&
+ 	(
+ 		# Seed the repository with four different sets of objects:
+ 		#
+ 		#   - The first set is fully packed and has a bitmap.
+ 		#   - The second set is packed, but has no bitmap.
+ 		#   - The third set is loose.
+ 		#   - The fourth set is loose and contains big objects.
+ 		#
+ 		# This ensures that we cover all these types as expected.
+ 		cd repo &&
+ 		test_commit first &&
+ 		git repack -Adb &&
+ 		test_commit second &&
+ 		git repack -d &&
+ 		test_commit third &&
+ 
+ 		for n in 1000 10000
+ 		do
+ 			printf "%"$n"s" X >large.$n || return 1
+ 		done &&
+ 		git add large.* &&
+ 		git commit -m fourth
+ 	)
+ '
+ 
+ test_expect_success 'objects filter with unknown option' '
+ 	cat >expect <<-EOF &&
+ 	fatal: invalid filter-spec ${SQ}unknown${SQ}
+ 	EOF
+ 	test_must_fail git -C repo cat-file --filter=unknown 2>err &&
+ 	test_cmp expect err
+ '
+ 
+ for option in sparse:oid=1234 tree:1 sparse:path=x
+ do
+ 	test_expect_success "objects filter with unsupported option $option" '
+ 		case "$option" in
+ 		tree:1)
+ 			echo "usage: objects filter not supported: ${SQ}tree${SQ}" >expect
+ 			;;
+ 		sparse:path=x)
+ 			echo "fatal: sparse:path filters support has been dropped" >expect
+ 			;;
+ 		*)
+ 			option_name=$(echo "$option" | cut -d= -f1) &&
+ 			printf "usage: objects filter not supported: ${SQ}%s${SQ}\n" "$option_name" >expect
+ 			;;
+ 		esac &&
+ 		test_must_fail git -C repo cat-file --filter=$option 2>err &&
+ 		test_cmp expect err
+ 	'
+ done
+ 
+ test_expect_success 'objects filter: disabled' '
+ 	git -C repo cat-file --batch-check="%(objectname)" --batch-all-objects --no-filter >actual &&
+ 	sort actual >actual.sorted &&
+ 	git -C repo rev-list --objects --no-object-names --all >expect &&
+ 	sort expect >expect.sorted &&
+ 	test_cmp expect.sorted actual.sorted
+ '
+ 
+ test_objects_filter () {
+ 	filter="$1"
+ 
+ 	test_expect_success "objects filter: $filter" '
+ 		git -C repo cat-file --batch-check="%(objectname)" --batch-all-objects --filter="$filter" >actual &&
+ 		sort actual >actual.sorted &&
+ 		git -C repo rev-list --objects --no-object-names --all --filter="$filter" --filter-provided-objects >expect &&
+ 		sort expect >expect.sorted &&
+ 		test_cmp expect.sorted actual.sorted
+ 	'
+ 
+ 	test_expect_success "objects filter prints excluded objects: $filter" '
+ 		# Find all objects that would be excluded by the current filter.
+ 		git -C repo rev-list --objects --no-object-names --all >all &&
+ 		git -C repo rev-list --objects --no-object-names --all --filter="$filter" --filter-provided-objects >filtered &&
+ 		sort all >all.sorted &&
+ 		sort filtered >filtered.sorted &&
+ 		comm -23 all.sorted filtered.sorted >expected.excluded &&
+ 		test_line_count -gt 0 expected.excluded &&
+ 
+ 		git -C repo cat-file --batch-check="%(objectname)" --filter="$filter" <expected.excluded >actual &&
+ 		awk "/excluded/{ print \$1 }" actual | sort >actual.excluded &&
+ 		test_cmp expected.excluded actual.excluded
+ 	'
+ }
+ 
+ test_objects_filter "blob:none"
+ test_objects_filter "blob:limit=1"
+ test_objects_filter "blob:limit=500"
+ test_objects_filter "blob:limit=1000"
+ test_objects_filter "blob:limit=1k"
+ test_objects_filter "object:type=blob"
+ test_objects_filter "object:type=commit"
+ test_objects_filter "object:type=tag"
+ test_objects_filter "object:type=tree"
+ 
  test_done