ref-filter: add %(raw) atom

Add new formatting option `%(raw)`, which will print the raw
object data without any changes. It will help further to migrate
all cat-file formatting logic from cat-file to ref-filter.

The raw data of blob, tree objects may contain '\0', but most of
the logic in `ref-filter` depends on the output of the atom being
text (specifically, no embedded NULs in it).

E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()`
add the data to the buffer. The raw data of a tree object is
`100644 one\0...`, only the `100644 one` will be added to the buffer,
which is incorrect.

Therefore, we need to find a way to record the length of the
atom_value's member `s`. Although strbuf can already record the
string and its length, if we want to replace the type of atom_value's
member `s` with strbuf, many places in ref-filter that are filled
with dynamically allocated mermory in `v->s` are not easy to replace.
At the same time, we need to check if `v->s == NULL` in
populate_value(), and strbuf cannot easily distinguish NULL and empty
strings, but c-style "const char *" can do it. So add a new member in
`struct atom_value`: `s_size`, which can record raw object size, it
can help us add raw object data to the buffer or compare two buffers
which contain raw object data.

Note that `--format=%(raw)` cannot be used with `--python`, `--shell`,
`--tcl`, and `--perl` because if the binary raw data is passed to a
variable in such languages, these may not support arbitrary binary data
in their string variable type.

Reviewed-by: Jacob Keller <jacob.keller@gmail.com>
Mentored-by: Christian Couder <christian.couder@gmail.com>
Mentored-by: Hariom Verma <hariom18599@gmail.com>
Helped-by: Bagas Sanjaya <bagasdotme@gmail.com>
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Felipe Contreras <felipe.contreras@gmail.com>
Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Helped-by: Junio C Hamano <gitster@pobox.com>
Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com>
Signed-off-by: ZheNing Hu <adlternative@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 216 insertions, 0 deletions

diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh
index 9e0214076b..18554f62d9 100755
--- a/t/t6300-for-each-ref.sh
+++ b/t/t6300-for-each-ref.sh
@@ -130,6 +130,8 @@ test_atom head parent:short=10 ''
 test_atom head numparent 0
 test_atom head object ''
 test_atom head type ''
+test_atom head raw "$(git cat-file commit refs/heads/main)
+"
 test_atom head '*objectname' ''
 test_atom head '*objecttype' ''
 test_atom head author 'A U Thor <author@example.com> 1151968724 +0200'
@@ -221,6 +223,15 @@ test_atom tag contents 'Tagging at 1151968727
 '
 test_atom tag HEAD ' '
 
+test_expect_success 'basic atom: refs/tags/testtag *raw' '
+	git cat-file commit refs/tags/testtag^{} >expected &&
+	git for-each-ref --format="%(*raw)" refs/tags/testtag >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_expect_success 'Check invalid atoms names are errors' '
 	test_must_fail git for-each-ref --format="%(INVALID)" refs/heads
 '
@@ -686,6 +697,15 @@ test_atom refs/tags/signed-empty contents:body ''
 test_atom refs/tags/signed-empty contents:signature "$sig"
 test_atom refs/tags/signed-empty contents "$sig"
 
+test_expect_success GPG 'basic atom: refs/tags/signed-empty raw' '
+	git cat-file tag refs/tags/signed-empty >expected &&
+	git for-each-ref --format="%(raw)" refs/tags/signed-empty >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_atom refs/tags/signed-short subject 'subject line'
 test_atom refs/tags/signed-short subject:sanitize 'subject-line'
 test_atom refs/tags/signed-short contents:subject 'subject line'
@@ -695,6 +715,15 @@ test_atom refs/tags/signed-short contents:signature "$sig"
 test_atom refs/tags/signed-short contents "subject line
 $sig"
 
+test_expect_success GPG 'basic atom: refs/tags/signed-short raw' '
+	git cat-file tag refs/tags/signed-short >expected &&
+	git for-each-ref --format="%(raw)" refs/tags/signed-short >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_atom refs/tags/signed-long subject 'subject line'
 test_atom refs/tags/signed-long subject:sanitize 'subject-line'
 test_atom refs/tags/signed-long contents:subject 'subject line'
@@ -708,6 +737,15 @@ test_atom refs/tags/signed-long contents "subject line
 body contents
 $sig"
 
+test_expect_success GPG 'basic atom: refs/tags/signed-long raw' '
+	git cat-file tag refs/tags/signed-long >expected &&
+	git for-each-ref --format="%(raw)" refs/tags/signed-long >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_expect_success 'set up refs pointing to tree and blob' '
 	git update-ref refs/mytrees/first refs/heads/main^{tree} &&
 	git update-ref refs/myblobs/first refs/heads/main:one
@@ -720,6 +758,16 @@ test_atom refs/mytrees/first contents:body ""
 test_atom refs/mytrees/first contents:signature ""
 test_atom refs/mytrees/first contents ""
 
+test_expect_success 'basic atom: refs/mytrees/first raw' '
+	git cat-file tree refs/mytrees/first >expected &&
+	echo >>expected &&
+	git for-each-ref --format="%(raw)" refs/mytrees/first >actual &&
+	test_cmp expected actual &&
+	git cat-file -s refs/mytrees/first >expected &&
+	git for-each-ref --format="%(raw:size)" refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
 test_atom refs/myblobs/first subject ""
 test_atom refs/myblobs/first contents:subject ""
 test_atom refs/myblobs/first body ""
@@ -727,6 +775,174 @@ test_atom refs/myblobs/first contents:body ""
 test_atom refs/myblobs/first contents:signature ""
 test_atom refs/myblobs/first contents ""
 
+test_expect_success 'basic atom: refs/myblobs/first raw' '
+	git cat-file blob refs/myblobs/first >expected &&
+	echo >>expected &&
+	git for-each-ref --format="%(raw)" refs/myblobs/first >actual &&
+	test_cmp expected actual &&
+	git cat-file -s refs/myblobs/first >expected &&
+	git for-each-ref --format="%(raw:size)" refs/myblobs/first >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'set up refs pointing to binary blob' '
+	printf "a\0b\0c" >blob1 &&
+	printf "a\0c\0b" >blob2 &&
+	printf "\0a\0b\0c" >blob3 &&
+	printf "abc" >blob4 &&
+	printf "\0 \0 \0 " >blob5 &&
+	printf "\0 \0a\0 " >blob6 &&
+	printf "  " >blob7 &&
+	>blob8 &&
+	obj=$(git hash-object -w blob1) &&
+	git update-ref refs/myblobs/blob1 "$obj" &&
+	obj=$(git hash-object -w blob2) &&
+	git update-ref refs/myblobs/blob2 "$obj" &&
+	obj=$(git hash-object -w blob3) &&
+	git update-ref refs/myblobs/blob3 "$obj" &&
+	obj=$(git hash-object -w blob4) &&
+	git update-ref refs/myblobs/blob4 "$obj" &&
+	obj=$(git hash-object -w blob5) &&
+	git update-ref refs/myblobs/blob5 "$obj" &&
+	obj=$(git hash-object -w blob6) &&
+	git update-ref refs/myblobs/blob6 "$obj" &&
+	obj=$(git hash-object -w blob7) &&
+	git update-ref refs/myblobs/blob7 "$obj" &&
+	obj=$(git hash-object -w blob8) &&
+	git update-ref refs/myblobs/blob8 "$obj"
+'
+
+test_expect_success 'Verify sorts with raw' '
+	cat >expected <<-EOF &&
+	refs/myblobs/blob8
+	refs/myblobs/blob5
+	refs/myblobs/blob6
+	refs/myblobs/blob3
+	refs/myblobs/blob7
+	refs/mytrees/first
+	refs/myblobs/first
+	refs/myblobs/blob1
+	refs/myblobs/blob2
+	refs/myblobs/blob4
+	refs/heads/main
+	EOF
+	git for-each-ref --format="%(refname)" --sort=raw \
+		refs/heads/main refs/myblobs/ refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'Verify sorts with raw:size' '
+	cat >expected <<-EOF &&
+	refs/myblobs/blob8
+	refs/myblobs/first
+	refs/myblobs/blob7
+	refs/heads/main
+	refs/myblobs/blob4
+	refs/myblobs/blob1
+	refs/myblobs/blob2
+	refs/myblobs/blob3
+	refs/myblobs/blob5
+	refs/myblobs/blob6
+	refs/mytrees/first
+	EOF
+	git for-each-ref --format="%(refname)" --sort=raw:size \
+		refs/heads/main refs/myblobs/ refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'validate raw atom with %(if:equals)' '
+	cat >expected <<-EOF &&
+	not equals
+	not equals
+	not equals
+	not equals
+	not equals
+	not equals
+	refs/myblobs/blob4
+	not equals
+	not equals
+	not equals
+	not equals
+	not equals
+	EOF
+	git for-each-ref --format="%(if:equals=abc)%(raw)%(then)%(refname)%(else)not equals%(end)" \
+		refs/myblobs/ refs/heads/ >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'validate raw atom with %(if:notequals)' '
+	cat >expected <<-EOF &&
+	refs/heads/ambiguous
+	refs/heads/main
+	refs/heads/newtag
+	refs/myblobs/blob1
+	refs/myblobs/blob2
+	refs/myblobs/blob3
+	equals
+	refs/myblobs/blob5
+	refs/myblobs/blob6
+	refs/myblobs/blob7
+	refs/myblobs/blob8
+	refs/myblobs/first
+	EOF
+	git for-each-ref --format="%(if:notequals=abc)%(raw)%(then)%(refname)%(else)equals%(end)" \
+		refs/myblobs/ refs/heads/ >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'empty raw refs with %(if)' '
+	cat >expected <<-EOF &&
+	refs/myblobs/blob1 not empty
+	refs/myblobs/blob2 not empty
+	refs/myblobs/blob3 not empty
+	refs/myblobs/blob4 not empty
+	refs/myblobs/blob5 not empty
+	refs/myblobs/blob6 not empty
+	refs/myblobs/blob7 empty
+	refs/myblobs/blob8 empty
+	refs/myblobs/first not empty
+	EOF
+	git for-each-ref --format="%(refname) %(if)%(raw)%(then)not empty%(else)empty%(end)" \
+		refs/myblobs/ >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success '%(raw) with --python must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --python
+'
+
+test_expect_success '%(raw) with --tcl must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --tcl
+'
+
+test_expect_success '%(raw) with --perl must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --perl
+'
+
+test_expect_success '%(raw) with --shell must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --shell
+'
+
+test_expect_success '%(raw) with --shell and --sort=raw must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --sort=raw --shell
+'
+
+test_expect_success '%(raw:size) with --shell' '
+	git for-each-ref --format="%(raw:size)" | while read line
+	do
+		echo "'\''$line'\''" >>expect
+	done &&
+	git for-each-ref --format="%(raw:size)" --shell >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'for-each-ref --format compare with cat-file --batch' '
+	git rev-parse refs/mytrees/first | git cat-file --batch >expected &&
+	git for-each-ref --format="%(objectname) %(objecttype) %(objectsize)
+%(raw)" refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'set up multiple-sort tags' '
 	for when in 100000 200000
 	do