git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 2/2] [GSOC] ref-filter: add %(header) atom

From
ZheNing Hu via GitGitGadget <gitgitgadget@gmail.com>
Date
May 27, 2021, 14:43 UTC
Message-ID
<aa6d73f3e526f416ee1e4e332e9ca3119efba0e8.1622126603.git.gitgitgadget@gmail.com>
In-Reply-To
<pull.963.git.1622126603.gitgitgadget@gmail.com>
From: ZheNing Hu <adlternative@gmail.com>

Add new formatting option `%(header)`, which will print the the structured header part of the raw object data.

In the storage layout of an object: blob and tree only contains raw data; commit and tag raw data contains two part: header and contents. The header of tag contains "object OOO", "type TTT", "tag AAA", "tagger GGG"; The header of commit contains "tree RRR", "parent PPP", "author UUU", "committer CCC".

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 Documentation/git-for-each-ref.txt |  7 +++++
 ref-filter.c                       | 26 +++++++++++++++++
 t/t6300-for-each-ref.sh            | 45 ++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+)
diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt
index f6ae751fd256..7827e48cde75 100644
--- a/Documentation/git-for-each-ref.txt
+++ b/Documentation/git-for-each-ref.txt
@@ -249,6 +249,13 @@ Note that `--format=%(raw)` should not combine with `--python`, `--shell`, `--tc
 `--perl` because if our binary raw data is passed to a variable in the host language,
 the host languages may cause escape errors.
 
+The structured header part of the raw data in a commit or a tag object is `header`,
+it composed of "tree XXX", "parent YYY", etc lines in commits, or composed of
+"object OOO", "type TTT", etc lines in tags.
+
+header:size::
+	The header size of the object.
+
 The message in a commit or a tag object is `contents`, from which
 `contents:<part>` can be used to extract various parts out of:
 
diff --git a/ref-filter.c b/ref-filter.c
index c2abf5da7006..2f426830f562 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -141,6 +141,9 @@ static struct used_atom {
 		struct {
 			enum { RAW_BARE, RAW_LENGTH } option;
 		} raw_data;
+		struct {
+			enum { H_BARE, H_LENGTH } option;
+		} header;
 		struct {
 			cmp_status cmp_status;
 			const char *str;
@@ -385,6 +388,18 @@ static int raw_atom_parser(const struct ref_format *format, struct used_atom *at
 	return 0;
 }
 
+static int header_atom_parser(const struct ref_format *format, struct used_atom *atom,
+			      const char *arg, struct strbuf *err)
+{
+	if (!arg)
+		atom->u.header.option = H_BARE;
+	else if (!strcmp(arg, "size"))
+		atom->u.header.option = H_LENGTH;
+	else
+		return strbuf_addf_ret(err, -1, _("unrecognized %%(header) argument: %s"), arg);
+	return 0;
+}
+
 static int oid_atom_parser(const struct ref_format *format, struct used_atom *atom,
 			   const char *arg, struct strbuf *err)
 {
@@ -546,6 +561,7 @@ static struct {
 	{ "trailers", SOURCE_OBJ, FIELD_STR, trailers_atom_parser },
 	{ "contents", SOURCE_OBJ, FIELD_STR, contents_atom_parser },
 	{ "raw", SOURCE_OBJ, FIELD_STR, raw_atom_parser },
+	{ "header", SOURCE_OBJ, FIELD_STR, header_atom_parser },
 	{ "upstream", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser },
 	{ "push", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser },
 	{ "symref", SOURCE_NONE, FIELD_STR, refname_atom_parser },
@@ -1362,6 +1378,7 @@ static void grab_raw_data(struct atom_value *val, int deref, void *buf, unsigned
 		if ((obj->type != OBJ_TAG &&
 		     obj->type != OBJ_COMMIT) ||
 		    (strcmp(name, "body") &&
+		     !starts_with(name, "header") &&
 		     !starts_with(name, "subject") &&
 		     !starts_with(name, "trailers") &&
 		     !starts_with(name, "contents")))
@@ -1372,6 +1389,15 @@ static void grab_raw_data(struct atom_value *val, int deref, void *buf, unsigned
 				    &bodypos, &bodylen, &nonsiglen,
 				    &sigpos, &siglen);
 
+		if (starts_with(name, "header")) {
+			size_t header_len = subpos - (const char *)buf - 1;
+			if (atom->u.header.option == H_BARE) {
+				v->s = xmemdupz(buf, header_len);
+			} else if (atom->u.header.option == H_LENGTH)
+				v->s = xstrfmt("%"PRIuMAX, (uintmax_t)header_len);
+			continue;
+		}
+
 		if (atom->u.contents.option == C_SUB)
 			v->s = copy_subject(subpos, sublen);
 		else if (atom->u.contents.option == C_SUB_SANITIZE) {
diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh
index 07de4a84d70b..11fc8fc53649 100755
--- a/t/t6300-for-each-ref.sh
+++ b/t/t6300-for-each-ref.sh
@@ -232,6 +232,35 @@ test_expect_success 'basic atom: refs/tags/testtag *raw' '
 	test_cmp expected.clean actual.clean
 '
 
+test_expect_success 'basic atom: refs/tags/testtag header' '
+	cat >expected <<-EOF &&
+	object ea122842f48be4afb2d1fc6a4b96c05885ab7463
+	type commit
+	tag testtag
+	tagger C O Mitter <committer@example.com> 1151968725 +0200
+
+	EOF
+	git for-each-ref --format="%(header)" refs/tags/testtag >actual &&
+	test_cmp expected actual &&
+	echo "131" >expected &&
+	git for-each-ref --format="%(header:size)" refs/tags/testtag >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'basic atom: refs/heads/main header' '
+	cat >expected <<-EOF &&
+	tree 8039ce043250c402d62ca312e9596e42ce1c7bb0
+	author A U Thor <author@example.com> 1151968724 +0200
+	committer C O Mitter <committer@example.com> 1151968723 +0200
+
+	EOF
+	git for-each-ref --format="%(header)" refs/heads/main >actual &&
+	test_cmp expected actual &&
+	echo "162" >expected &&
+	git for-each-ref --format="%(header:size)" refs/heads/main >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'Check invalid atoms names are errors' '
 	test_must_fail git for-each-ref --format="%(INVALID)" refs/heads
 '
@@ -768,6 +797,14 @@ test_expect_success 'basic atom: refs/mytrees/first raw' '
 	test_cmp expected actual
 '
 
+test_expect_success 'basic atom: refs/mytrees/first header' '
+	echo "" >expected &&
+	git for-each-ref --format="%(header)" refs/mytrees/first >actual &&
+	test_cmp expected actual &&
+	git for-each-ref --format="%(header: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 ""
@@ -785,6 +822,14 @@ test_expect_success 'basic atom: refs/myblobs/first raw' '
 	test_cmp expected actual
 '
 
+test_expect_success 'basic atom: refs/myblobs/first header' '
+	echo "" >expected &&
+	git for-each-ref --format="%(header)" refs/myblobs/first >actual &&
+	test_cmp expected actual &&
+	git for-each-ref --format="%(header:size)" refs/myblobs/first >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'set up refs pointing to binary blob' '
 	printf "%b" "a\0b\0c" >blob1 &&
 	printf "%b" "a\0c\0b" >blob2 &&

-- 
gitgitgadget
Previous: ZheNing HuNext: Felipe Contreras
Message 20 of 41 in “[GSOC] ref-filter: add %(raw) atom”
  1. 0/2 [GSOC] ref-filter: add %(raw) atomZheNing Hu via GitGitGadget, May 27, 2021
  2. 1/2 [GSOC] ref-filter: add %(raw) atomZheNing Hu via GitGitGadget, May 27, 2021
  3. Felipe ContrerasMay 27, 2021
  4. ZheNing HuMay 28, 2021
  5. Felipe ContrerasMay 28, 2021
  6. ZheNing HuMay 30, 2021
  7. Phillip WoodMay 29, 2021
  8. Felipe ContrerasMay 29, 2021
  9. Phillip WoodMay 29, 2021
  10. ZheNing HuMay 30, 2021
  11. Phillip WoodMay 30, 2021
  12. ZheNing HuMay 31, 2021
  13. Felipe ContrerasMay 31, 2021
  14. ZheNing HuMay 30, 2021
  15. Phillip WoodMay 30, 2021
  16. Junio C HamanoMay 28, 2021
  17. ZheNing HuMay 28, 2021
  18. Felipe ContrerasMay 28, 2021
  19. ZheNing HuMay 30, 2021
  20. 2/2 [GSOC] ref-filter: add %(header) atomZheNing Hu via GitGitGadget, May 27, 2021
  21. Felipe ContrerasMay 27, 2021
  22. Junio C HamanoMay 28, 2021
  23. Junio C HamanoMay 28, 2021
  24. ZheNing HuMay 28, 2021
  25. Felipe ContrerasMay 27, 2021
  26. 0/2 [GSOC] ref-filter: add %(raw) atomZheNing Hu via GitGitGadget, May 30, 2021
  27. 1/2 [GSOC] ref-filter: add obj-type check in grab contentsZheNing Hu via GitGitGadget, May 30, 2021
  28. Junio C HamanoMay 31, 2021
  29. 2/2 [GSOC] ref-filter: add %(raw) atomZheNing Hu via GitGitGadget, May 30, 2021
  30. Junio C HamanoMay 31, 2021
  31. ZheNing HuMay 31, 2021
  32. Junio C HamanoJun 1, 2021
  33. ZheNing HuJun 1, 2021
  34. Junio C HamanoMay 31, 2021
  35. ZheNing HuMay 31, 2021
  36. Junio C HamanoJun 1, 2021
  37. ZheNing HuJun 1, 2021
  38. Johannes SchindelinJun 1, 2021
  39. Junio C HamanoMay 31, 2021
  40. Felipe ContrerasMay 31, 2021
  41. ZheNing HuJun 1, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.