git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / Atom feed
From: Derrick Stolee <stolee@gmail.com>
To: git@vger.kernel.org, dstolee@microsoft.com
Cc: gitster@pobox.com, sbeller@google.com, pclouds@gmail.com,
	avarab@gmail.com, sunshine@sunshineco.com, szeder.dev@gmail.com
Subject: [PATCH v4 08/23] packfile: generalize pack directory list
Date: Thu, 12 Jul 2018 15:39:25 -0400
Message-ID: <20180712193940.21065-9-dstolee@microsoft.com> (raw)
In-Reply-To: <20180712193940.21065-1-dstolee@microsoft.com>

In anticipation of sharing the pack directory listing with the
multi-pack-index, generalize prepare_packed_git_one() into
for_each_file_in_pack_dir().

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 packfile.c | 101 +++++++++++++++++++++++++++++++++--------------------
 packfile.h |   6 ++++
 2 files changed, 69 insertions(+), 38 deletions(-)

diff --git a/packfile.c b/packfile.c
index 7cd45aa4b2..ee1ab9b804 100644
--- a/packfile.c
+++ b/packfile.c
@@ -738,13 +738,14 @@ static void report_pack_garbage(struct string_list *list)
 	report_helper(list, seen_bits, first, list->nr);
 }
 
-static void prepare_packed_git_one(struct repository *r, char *objdir, int local)
+void for_each_file_in_pack_dir(const char *objdir,
+			       each_file_in_pack_dir_fn fn,
+			       void *data)
 {
 	struct strbuf path = STRBUF_INIT;
 	size_t dirnamelen;
 	DIR *dir;
 	struct dirent *de;
-	struct string_list garbage = STRING_LIST_INIT_DUP;
 
 	strbuf_addstr(&path, objdir);
 	strbuf_addstr(&path, "/pack");
@@ -759,53 +760,77 @@ static void prepare_packed_git_one(struct repository *r, char *objdir, int local
 	strbuf_addch(&path, '/');
 	dirnamelen = path.len;
 	while ((de = readdir(dir)) != NULL) {
-		struct packed_git *p;
-		size_t base_len;
-
 		if (is_dot_or_dotdot(de->d_name))
 			continue;
 
 		strbuf_setlen(&path, dirnamelen);
 		strbuf_addstr(&path, de->d_name);
 
-		base_len = path.len;
-		if (strip_suffix_mem(path.buf, &base_len, ".idx")) {
-			/* Don't reopen a pack we already have. */
-			for (p = r->objects->packed_git; p;
-			     p = p->next) {
-				size_t len;
-				if (strip_suffix(p->pack_name, ".pack", &len) &&
-				    len == base_len &&
-				    !memcmp(p->pack_name, path.buf, len))
-					break;
-			}
-			if (p == NULL &&
-			    /*
-			     * See if it really is a valid .idx file with
-			     * corresponding .pack file that we can map.
-			     */
-			    (p = add_packed_git(path.buf, path.len, local)) != NULL)
-				install_packed_git(r, p);
-		}
-
-		if (!report_garbage)
-			continue;
-
-		if (ends_with(de->d_name, ".idx") ||
-		    ends_with(de->d_name, ".pack") ||
-		    ends_with(de->d_name, ".bitmap") ||
-		    ends_with(de->d_name, ".keep") ||
-		    ends_with(de->d_name, ".promisor"))
-			string_list_append(&garbage, path.buf);
-		else
-			report_garbage(PACKDIR_FILE_GARBAGE, path.buf);
+		fn(path.buf, path.len, de->d_name, data);
 	}
+
 	closedir(dir);
-	report_pack_garbage(&garbage);
-	string_list_clear(&garbage, 0);
 	strbuf_release(&path);
 }
 
+struct prepare_pack_data {
+	struct repository *r;
+	struct string_list *garbage;
+	int local;
+};
+
+static void prepare_pack(const char *full_name, size_t full_name_len,
+			 const char *file_name, void *_data)
+{
+	struct prepare_pack_data *data = (struct prepare_pack_data *)_data;
+	struct packed_git *p;
+	size_t base_len = full_name_len;
+
+	if (strip_suffix_mem(full_name, &base_len, ".idx")) {
+		/* Don't reopen a pack we already have. */
+		for (p = data->r->objects->packed_git; p; p = p->next) {
+			size_t len;
+			if (strip_suffix(p->pack_name, ".pack", &len) &&
+			    len == base_len &&
+			    !memcmp(p->pack_name, full_name, len))
+				break;
+		}
+
+		if (!p) {
+			p = add_packed_git(full_name, full_name_len, data->local);
+			if (p)
+				install_packed_git(data->r, p);
+		}
+	}
+
+	if (!report_garbage)
+		return;
+
+	if (ends_with(file_name, ".idx") ||
+	    ends_with(file_name, ".pack") ||
+	    ends_with(file_name, ".bitmap") ||
+	    ends_with(file_name, ".keep") ||
+	    ends_with(file_name, ".promisor"))
+		string_list_append(data->garbage, full_name);
+	else
+		report_garbage(PACKDIR_FILE_GARBAGE, full_name);
+}
+
+static void prepare_packed_git_one(struct repository *r, char *objdir, int local)
+{
+	struct prepare_pack_data data;
+	struct string_list garbage = STRING_LIST_INIT_DUP;
+
+	data.r = r;
+	data.garbage = &garbage;
+	data.local = local;
+
+	for_each_file_in_pack_dir(objdir, prepare_pack, &data);
+
+	report_pack_garbage(data.garbage);
+	string_list_clear(data.garbage, 0);
+}
+
 static void prepare_packed_git(struct repository *r);
 /*
  * Give a fast, rough count of the number of objects in the repository. This
diff --git a/packfile.h b/packfile.h
index e0a38aba93..d2ad30300a 100644
--- a/packfile.h
+++ b/packfile.h
@@ -28,6 +28,12 @@ extern char *sha1_pack_index_name(const unsigned char *sha1);
 
 extern struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path);
 
+typedef void each_file_in_pack_dir_fn(const char *full_path, size_t full_path_len,
+				      const char *file_pach, void *data);
+void for_each_file_in_pack_dir(const char *objdir,
+			       each_file_in_pack_dir_fn fn,
+			       void *data);
+
 /* A hook to report invalid files in pack directory */
 #define PACKDIR_FILE_PACK 1
 #define PACKDIR_FILE_IDX 2
-- 
2.18.0.118.gd4f65b8d14


  parent reply index

Thread overview: 192+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-07 14:03 [PATCH 00/23] Multi-pack-index (MIDX) Derrick Stolee
2018-06-07 14:03 ` [PATCH 01/23] midx: add design document Derrick Stolee
2018-06-11 19:04   ` Stefan Beller
2018-06-18 18:48     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 02/23] midx: add midx format details to pack-format.txt Derrick Stolee
2018-06-11 19:19   ` Stefan Beller
2018-06-18 19:01     ` Derrick Stolee
2018-06-18 19:41       ` Stefan Beller
2018-06-07 14:03 ` [PATCH 03/23] midx: add midx builtin Derrick Stolee
2018-06-07 17:20   ` Duy Nguyen
2018-06-18 19:23     ` Derrick Stolee
2018-06-11 21:02   ` Stefan Beller
2018-06-18 19:40     ` Derrick Stolee
2018-06-18 19:55       ` Stefan Beller
2018-06-18 19:58         ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 04/23] midx: add 'write' subcommand and basic wiring Derrick Stolee
2018-06-07 17:27   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 05/23] midx: write header information to lockfile Derrick Stolee
2018-06-07 17:35   ` Duy Nguyen
2018-06-12 15:00   ` Duy Nguyen
2018-06-19 12:54     ` Derrick Stolee
2018-06-19 14:59       ` Duy Nguyen
2018-06-19 15:24         ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 06/23] midx: struct midxed_git and 'read' subcommand Derrick Stolee
2018-06-07 17:54   ` Duy Nguyen
2018-06-20 13:13     ` Derrick Stolee
2018-06-07 18:31   ` Duy Nguyen
2018-06-20 13:33     ` Derrick Stolee
2018-06-20 15:07       ` Duy Nguyen
2018-06-20 16:39         ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 07/23] midx: expand test data Derrick Stolee
2018-06-07 14:03 ` [PATCH 08/23] midx: read packfiles from pack directory Derrick Stolee
2018-06-07 18:03   ` Duy Nguyen
2018-06-20 16:33     ` [PATCH] packfile: generalize pack directory list Derrick Stolee
2018-06-07 14:03 ` [PATCH 09/23] midx: write pack names in chunk Derrick Stolee
2018-06-07 18:26   ` Duy Nguyen
2018-06-21 15:25     ` Derrick Stolee
2018-06-21 17:38       ` Junio C Hamano
2018-06-22 18:25         ` Derrick Stolee
2018-06-22 18:31           ` Junio C Hamano
2018-06-22 18:32             ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 10/23] midx: write a lookup into the pack names chunk Derrick Stolee
2018-06-09 16:43   ` Duy Nguyen
2018-06-21 17:23     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 11/23] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-06-09 17:07   ` Duy Nguyen
2018-06-21 17:54     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 12/23] midx: write object ids in a chunk Derrick Stolee
2018-06-09 17:25   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 13/23] midx: write object id fanout chunk Derrick Stolee
2018-06-09 17:28   ` Duy Nguyen
2018-06-21 19:49     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 14/23] midx: write object offsets Derrick Stolee
2018-06-09 17:41   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 15/23] midx: create core.midx config setting Derrick Stolee
2018-06-07 14:03 ` [PATCH 16/23] midx: prepare midxed_git struct Derrick Stolee
2018-06-09 17:47   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 17/23] midx: read objects from multi-pack-index Derrick Stolee
2018-06-09 17:56   ` Duy Nguyen
2018-06-21 20:03     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 18/23] midx: use midx in abbreviation calculations Derrick Stolee
2018-06-09 18:01   ` Duy Nguyen
2018-06-22 18:38     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 19/23] midx: use existing midx when writing new one Derrick Stolee
2018-06-07 14:03 ` [PATCH 20/23] midx: use midx in approximate_object_count Derrick Stolee
2018-06-09 18:03   ` Duy Nguyen
2018-06-22 18:39     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 21/23] midx: prevent duplicate packfile loads Derrick Stolee
2018-06-09 18:05   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 22/23] midx: use midx to find ref-deltas Derrick Stolee
2018-06-07 14:03 ` [PATCH 23/23] midx: clear midx on repack Derrick Stolee
2018-06-09 18:13   ` Duy Nguyen
2018-06-22 18:44     ` Derrick Stolee
2018-06-07 14:06 ` [PATCH 00/23] Multi-pack-index (MIDX) Derrick Stolee
2018-06-07 14:45 ` Ævar Arnfjörð Bjarmason
2018-06-07 14:54   ` Derrick Stolee
2018-06-25 14:34 ` [PATCH v2 00/24] " Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 01/24] multi-pack-index: add design document Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 02/24] multi-pack-index: add format details Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 03/24] multi-pack-index: add builtin Derrick Stolee
2018-06-25 19:15     ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 04/24] multi-pack-index: add 'write' verb Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 05/24] midx: write header information to lockfile Derrick Stolee
2018-06-25 19:19     ` Junio C Hamano
2018-07-05 19:13       ` Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 06/24] multi-pack-index: load into memory Derrick Stolee
2018-06-25 19:38     ` Junio C Hamano
2018-07-05 14:19       ` Derrick Stolee
2018-07-05 18:58         ` Eric Sunshine
2018-07-06 19:20           ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 07/24] multi-pack-index: expand test data Derrick Stolee
2018-06-25 19:45     ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 08/24] packfile: generalize pack directory list Derrick Stolee
2018-06-25 19:57     ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 09/24] multi-pack-index: read packfile list Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 10/24] multi-pack-index: write pack names in chunk Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 11/24] midx: read pack names into array Derrick Stolee
2018-06-25 23:52     ` Eric Sunshine
2018-06-25 14:34   ` [PATCH v2 12/24] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 13/24] midx: write object ids in a chunk Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 14/24] midx: write object id fanout chunk Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 15/24] midx: write object offsets Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 16/24] config: create core.multiPackIndex setting Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 17/24] midx: prepare midxed_git struct Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 18/24] midx: read objects from multi-pack-index Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 19/24] midx: use midx in abbreviation calculations Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 20/24] midx: use existing midx when writing new one Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 21/24] midx: use midx in approximate_object_count Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 22/24] midx: prevent duplicate packfile loads Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 23/24] packfile: skip loading index if in multi-pack-index Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 24/24] midx: clear midx on repack Derrick Stolee
2018-07-06  0:52   ` [PATCH v3 00/24] Multi-pack-index (MIDX) Derrick Stolee
2018-07-06  0:52     ` [PATCH v3 01/24] multi-pack-index: add design document Derrick Stolee
2018-07-06  0:52     ` [PATCH v3 02/24] multi-pack-index: add format details Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 03/24] multi-pack-index: add builtin Derrick Stolee
2018-07-06  3:54       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 04/24] multi-pack-index: add 'write' verb Derrick Stolee
2018-07-06  4:07       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 05/24] midx: write header information to lockfile Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 06/24] multi-pack-index: load into memory Derrick Stolee
2018-07-06  4:19       ` Eric Sunshine
2018-07-06  5:18         ` Eric Sunshine
2018-07-09 19:08       ` Junio C Hamano
2018-07-12 16:06         ` Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 07/24] multi-pack-index: expand test data Derrick Stolee
2018-07-06  4:36       ` Eric Sunshine
2018-07-06  5:20         ` Eric Sunshine
2018-07-12 14:10         ` Derrick Stolee
2018-07-12 18:02           ` Eric Sunshine
2018-07-12 18:06             ` Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 08/24] packfile: generalize pack directory list Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 09/24] multi-pack-index: read packfile list Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 10/24] multi-pack-index: write pack names in chunk Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 11/24] midx: read pack names into array Derrick Stolee
2018-07-06  4:58       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 12/24] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 13/24] midx: write object ids in a chunk Derrick Stolee
2018-07-06  5:04       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 14/24] midx: write object id fanout chunk Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 15/24] midx: write object offsets Derrick Stolee
2018-07-06  5:27       ` Eric Sunshine
2018-07-12 16:33         ` Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 16/24] config: create core.multiPackIndex setting Derrick Stolee
2018-07-06  5:39       ` Eric Sunshine
2018-07-12 13:19         ` Derrick Stolee
2018-07-12 16:30           ` Derrick Stolee
2018-07-11  9:48       ` SZEDER Gábor
2018-07-12 13:01         ` Derrick Stolee
2018-07-12 13:31           ` SZEDER Gábor
2018-07-12 15:40             ` Derrick Stolee
2018-07-12 17:29             ` Junio C Hamano
2018-07-06  0:53     ` [PATCH v3 17/24] midx: prepare midxed_git struct Derrick Stolee
2018-07-06  5:41       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 18/24] midx: read objects from multi-pack-index Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 19/24] midx: use midx in abbreviation calculations Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 20/24] midx: use existing midx when writing new one Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 21/24] midx: use midx in approximate_object_count Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 22/24] midx: prevent duplicate packfile loads Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 23/24] packfile: skip loading index if in multi-pack-index Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 24/24] midx: clear midx on repack Derrick Stolee
2018-07-06  5:52       ` Eric Sunshine
2018-07-12 19:39     ` [PATCH v4 00/23] Multi-pack-index (MIDX) Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 01/23] multi-pack-index: add design document Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 02/23] multi-pack-index: add format details Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 03/23] multi-pack-index: add builtin Derrick Stolee
2018-07-20 18:22         ` Junio C Hamano
2018-07-20 22:15           ` brian m. carlson
2018-07-20 22:28             ` Junio C Hamano
2018-07-12 19:39       ` [PATCH v4 04/23] multi-pack-index: add 'write' verb Derrick Stolee
2018-07-12 22:56         ` Eric Sunshine
2018-07-12 19:39       ` [PATCH v4 05/23] midx: write header information to lockfile Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 06/23] multi-pack-index: load into memory Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 07/23] t5319: expand test data Derrick Stolee
2018-07-12 19:39       ` Derrick Stolee [this message]
2018-07-12 19:39       ` [PATCH v4 09/23] multi-pack-index: read packfile list Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 10/23] multi-pack-index: write pack names in chunk Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 11/23] midx: read pack names into array Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 12/23] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 13/23] midx: write object ids in a chunk Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 14/23] midx: write object id fanout chunk Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 15/23] midx: write object offsets Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 16/23] config: create core.multiPackIndex setting Derrick Stolee
2018-07-12 21:05         ` Junio C Hamano
2018-07-13  0:50           ` Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 17/23] midx: read objects from multi-pack-index Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 18/23] midx: use midx in abbreviation calculations Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 19/23] midx: use existing midx when writing new one Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 20/23] midx: use midx in approximate_object_count Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 21/23] midx: prevent duplicate packfile loads Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 22/23] packfile: skip loading index if in multi-pack-index Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 23/23] midx: clear midx on repack Derrick Stolee
2018-07-12 21:11       ` [PATCH v4 00/23] Multi-pack-index (MIDX) Junio C Hamano

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180712193940.21065-9-dstolee@microsoft.com \
    --to=stolee@gmail.com \
    --cc=avarab@gmail.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=pclouds@gmail.com \
    --cc=sbeller@google.com \
    --cc=sunshine@sunshineco.com \
    --cc=szeder.dev@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org list mirror (unofficial, one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox