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

[PATCHv2 11/36] attr: (re)introduce git_check_attr() and struct git_attr_check

From
Stefan Beller <sbeller@google.com>
Date
Oct 28, 2016, 18:54 UTC
Message-ID
<20161028185502.8789-12-sbeller@google.com>
In-Reply-To
<20161028185502.8789-1-sbeller@google.com>
From: Junio C Hamano <gitster@pobox.com>
A common pattern to check N attributes for many paths is to
 (1) prepare an array A of N git_attr_check_elem items;
 (2) call git_attr() to intern the N attribute names and fill A;
 (3) repeatedly call git_check_attrs() for path with N and A;

A look-up for these N attributes for a single path P scans the entire attr_stack, starting from the .git/info/attributes file and then .gitattributes file in the directory the path P is in, going upwards to find .gitattributes file found in parent directories.

An earlier commit 06a604e6 (attr: avoid heavy work when we know the specified attr is not defined, 2014-12-28) tried to optimize out this scanning for one trivial special case: when the attribute being sought is known not to exist, we do not have to scan for it. While this may be a cheap and effective heuristic, it would not work well when N is (much) more than 1.

What we would want is a more customized way to skip irrelevant entries in the attribute stack, and the definition of irrelevance is tied to the set of attributes passed to git_check_attrs() call, i.e. the set of attributes being sought. The data necessary for this optimization needs to live alongside the set of attributes, but a simple array of git_attr_check_elem simply does not have any place for that.

Introduce "struct git_attr_check" that contains N, the number of attributes being sought, and A, the array that holds N git_attr_check_elem items, and a function git_check_attr() that takes a path P and this structure as its parameters. This structure can later be extended to hold extra data necessary for optimization.

Also, to make it easier to write the first two steps in common cases, introduce git_attr_check_initl() helper function, which takes a NULL-terminated list of attribute names and initialize this structure.

As an illustration of this new API, convert archive.c that asks for export-subst and export-ignore attributes for each paths.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
---
 archive.c | 24 ++++++------------------
 attr.c    | 34 ++++++++++++++++++++++++++++++++++
 attr.h    |  9 +++++++++
 3 files changed, 49 insertions(+), 18 deletions(-)
diff --git a/archive.c b/archive.c
index 2dc8d6ca57..11e3951371 100644
--- a/archive.c
+++ b/archive.c
@@ -87,19 +87,6 @@ void *sha1_file_to_archive(const struct archiver_args *args,
 	return buffer;
 }
 
-static void setup_archive_check(struct git_attr_check_elem *check)
-{
-	static struct git_attr *attr_export_ignore;
-	static struct git_attr *attr_export_subst;
-
-	if (!attr_export_ignore) {
-		attr_export_ignore = git_attr("export-ignore");
-		attr_export_subst = git_attr("export-subst");
-	}
-	check[0].attr = attr_export_ignore;
-	check[1].attr = attr_export_subst;
-}
-
 struct directory {
 	struct directory *up;
 	struct object_id oid;
@@ -123,7 +110,7 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 	struct archiver_context *c = context;
 	struct archiver_args *args = c->args;
 	write_archive_entry_fn_t write_entry = c->write_entry;
-	struct git_attr_check_elem check[2];
+	static struct git_attr_check *check;
 	const char *path_without_prefix;
 	int err;
 
@@ -137,11 +124,12 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 		strbuf_addch(&path, '/');
 	path_without_prefix = path.buf + args->baselen;
 
-	setup_archive_check(check);
-	if (!git_check_attrs(path_without_prefix, ARRAY_SIZE(check), check)) {
-		if (ATTR_TRUE(check[0].value))
+	if (!check)
+		check = git_attr_check_initl("export-ignore", "export-subst", NULL);
+	if (!git_check_attr(path_without_prefix, check)) {
+		if (ATTR_TRUE(check->check[0].value))
 			return 0;
-		args->convert = ATTR_TRUE(check[1].value);
+		args->convert = ATTR_TRUE(check->check[1].value);
 	}
 
 	if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
diff --git a/attr.c b/attr.c
index ff7f0a59eb..20d64b34f4 100644
--- a/attr.c
+++ b/attr.c
@@ -833,3 +833,37 @@ void git_attr_set_direction(enum git_attr_direction new, struct index_state *ist
 		drop_attr_stack();
 	use_index = istate;
 }
+
+int git_check_attr(const char *path, struct git_attr_check *check)
+{
+	return git_check_attrs(path, check->check_nr, check->check);
+}
+
+struct git_attr_check *git_attr_check_initl(const char *one, ...)
+{
+	struct git_attr_check *check;
+	int cnt;
+	va_list params;
+	const char *param;
+
+	va_start(params, one);
+	for (cnt = 1; (param = va_arg(params, const char *)) != NULL; cnt++)
+		;
+	va_end(params);
+	check = xcalloc(1,
+			sizeof(*check) + cnt * sizeof(*(check->check)));
+	check->check_nr = cnt;
+	check->check = (struct git_attr_check_elem *)(check + 1);
+
+	check->check[0].attr = git_attr(one);
+	va_start(params, one);
+	for (cnt = 1; cnt < check->check_nr; cnt++) {
+		param = va_arg(params, const char *);
+		if (!param)
+			die("BUG: counted %d != ended at %d",
+			    check->check_nr, cnt);
+		check->check[cnt].attr = git_attr(param);
+	}
+	va_end(params);
+	return check;
+}
diff --git a/attr.h b/attr.h
index dd3c4a3aef..3fd8690749 100644
--- a/attr.h
+++ b/attr.h
@@ -29,6 +29,15 @@ struct git_attr_check_elem {
 	const char *value;
 };
 
+struct git_attr_check {
+	int check_nr;
+	int check_alloc;
+	struct git_attr_check_elem *check;
+};
+
+extern struct git_attr_check *git_attr_check_initl(const char *, ...);
+extern int git_check_attr(const char *path, struct git_attr_check *);
+
 /*
  * Return the name of the attribute represented by the argument.  The
  * return value is a pointer to a null-delimited string that is part
-- 
2.10.1.714.ge3da0db
Previous: Stefan BellerNext: Junio C Hamano
Message 45 of 50 in “[PATCHv2 00/36] Revamp the attr subsystem!”
  1. Stefan BellerOct 28, 2016
  2. 01/36 commit.c: use strchrnul() to scan for one lineStefan Beller, Oct 28, 2016
  3. 02/36 attr.c: use strchrnul() to scan for one lineStefan Beller, Oct 28, 2016
  4. 03/36 attr.c: update a stale comment on "struct match_attr"Stefan Beller, Oct 28, 2016
  5. 04/36 attr.c: explain the lack of attr-name syntax check in parse_attr()Stefan Beller, Oct 28, 2016
  6. 06/36 attr.c: mark where #if DEBUG ends more clearlyStefan Beller, Oct 28, 2016
  7. 07/36 attr.c: simplify macroexpand_one()Stefan Beller, Oct 28, 2016
  8. 05/36 attr.c: complete a sentence in a commentStefan Beller, Oct 28, 2016
  9. 09/36 attr.c: plug small leak in parse_attr_line()Stefan Beller, Oct 28, 2016
  10. 08/36 attr.c: tighten constness around "git_attr" structureStefan Beller, Oct 28, 2016
  11. 10/36 attr: rename function and struct related to checking attributesStefan Beller, Oct 28, 2016
  12. 14/36 attr: retire git_check_attrs() APIStefan Beller, Oct 28, 2016
  13. 19/36 attr.c: add push_stack() helperStefan Beller, Oct 28, 2016
  14. 25/36 attr.c: outline the future plans by heavily commentingStefan Beller, Oct 28, 2016
  15. 18/36 attr: support quoting pathname patterns in C styleStefan Beller, Oct 28, 2016
  16. 20/36 attr.c: pass struct git_attr_check down the callchainStefan Beller, Oct 28, 2016
  17. 21/36 attr.c: rename a local variable checkStefan Beller, Oct 28, 2016
  18. 22/36 attr.c: correct ugly hack for git_all_attrs()Stefan Beller, Oct 28, 2016
  19. 28/36 attr: keep attr stack for each checkStefan Beller, Oct 28, 2016
  20. Junio C HamanoOct 28, 2016
  21. 23/36 attr.c: introduce empty_attr_check_elems()Stefan Beller, Oct 28, 2016
  22. 26/36 attr: make git_check_attr_counted staticStefan Beller, Oct 28, 2016
  23. 27/36 attr: convert to new threadsafe APIStefan Beller, Oct 28, 2016
  24. Junio C HamanoOct 28, 2016
  25. Stefan BellerOct 28, 2016
  26. Junio C HamanoOct 28, 2016
  27. Johannes SixtOct 29, 2016
  28. 29/36 Documentation: fix a typoStefan Beller, Oct 28, 2016
  29. 34/36 submodule update: add `--init-default-path` switchStefan Beller, Oct 28, 2016
  30. SQUASH to: submodule update: add `--init-default-path` switchStefan Beller, Nov 3, 2016
  31. 32/36 pathspec: allow querying for attributesStefan Beller, Oct 28, 2016
  32. Duy NguyenNov 9, 2016
  33. Stefan BellerNov 9, 2016
  34. 36/36 completion: clone can initialize specific submodulesStefan Beller, Oct 28, 2016
  35. 31/36 pathspec: move prefix check out of the inner loopStefan Beller, Oct 28, 2016
  36. 35/36 clone: add --init-submodule=<pathspec> switchStefan Beller, Oct 28, 2016
  37. 33/36 pathspec: allow escaped query valuesStefan Beller, Oct 28, 2016
  38. 30/36 pathspec: move long magic parsing out of prefix_pathspecStefan Beller, Oct 28, 2016
  39. 24/36 attr.c: always pass check[] to collect_some_attrs()Stefan Beller, Oct 28, 2016
  40. 13/36 attr: convert git_check_attrs() callers to use the new APIStefan Beller, Oct 28, 2016
  41. 17/36 attr: expose validity check for attribute namesStefan Beller, Oct 28, 2016
  42. 16/36 attr: add counted string version of git_attr()Stefan Beller, Oct 28, 2016
  43. 15/36 attr: add counted string version of git_check_attr()Stefan Beller, Oct 28, 2016
  44. 12/36 attr: convert git_all_attrs() to use "struct git_attr_check"Stefan Beller, Oct 28, 2016
  45. 11/36 attr: (re)introduce git_check_attr() and struct git_attr_checkStefan Beller, Oct 28, 2016
  46. Junio C HamanoOct 28, 2016
  47. Stefan BellerOct 28, 2016
  48. Ramsay JonesOct 28, 2016
  49. Johannes SixtNov 3, 2016
  50. Stefan BellerNov 3, 2016

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.