git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: Derrick Stolee <stolee@gmail.com>
To: git@vger.kernel.org
Cc: dstolee@microsoft.com, stolee@gmail.com, git@jeffhostetler.com,
	peff@peff.net, gitster@pobox.com, Johannes.Shindelin@gmx.de,
	jrnieder@gmail.com
Subject: [RFC PATCH 17/18] sha1_name: use midx for abbreviations
Date: Sun,  7 Jan 2018 13:14:58 -0500	[thread overview]
Message-ID: <20180107181459.222909-18-dstolee@microsoft.com> (raw)
In-Reply-To: <20180107181459.222909-1-dstolee@microsoft.com>

Create unique_in_midx() to mimic behavior of unique_in_pack().

Create find_abbrev_len_for_midx() to mimic behavior of
find_abbrev_len_for_pack().

Consume these methods when interacting with abbreviations.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 sha1_name.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 68 insertions(+), 2 deletions(-)

diff --git a/sha1_name.c b/sha1_name.c
index 611c7d24dd..2f426e136e 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -10,6 +10,7 @@
 #include "dir.h"
 #include "sha1-array.h"
 #include "packfile.h"
+#include "midx.h"
 
 static int get_oid_oneline(const char *, struct object_id *, struct commit_list *);
 
@@ -190,11 +191,40 @@ static void unique_in_pack(struct packed_git *p,
 	}
 }
 
+static void unique_in_midx(struct midxed_git *m,
+			   struct disambiguate_state *ds)
+{
+	uint32_t num, i, first = 0;
+	const struct object_id *current = NULL;
+
+	if (!m->num_objects)
+		return;
+
+	num = m->num_objects;
+	bsearch_midx(m, ds->bin_pfx.hash, &first);
+
+	/*
+	 * At this point, "first" is the location of the lowest object
+	 * with an object name that could match "bin_pfx".  See if we have
+	 * 0, 1 or more objects that actually match(es).
+	 */
+	for (i = first; i < num && !ds->ambiguous; i++) {
+		struct object_id oid;
+		current = nth_midxed_object_oid(&oid, m, i);
+		if (!match_sha(ds->len, ds->bin_pfx.hash, current->hash))
+			break;
+		update_candidates(ds, current);
+	}
+}
+
 static void find_short_packed_object(struct disambiguate_state *ds)
 {
 	struct packed_git *p;
+	struct midxed_git *m;
 
-	prepare_packed_git();
+	prepare_packed_git_internal(1);
+	for (m = midxed_git; m && !ds->ambiguous; m = m->next)
+		unique_in_midx(m, ds);
 	for (p = packed_git; p && !ds->ambiguous; p = p->next)
 		unique_in_pack(p, ds);
 }
@@ -508,6 +538,39 @@ static int extend_abbrev_len(const struct object_id *oid, void *cb_data)
 	return 0;
 }
 
+static void find_abbrev_len_for_midx(struct midxed_git *m,
+				     struct min_abbrev_data *mad)
+{
+	int match = 0;
+	uint32_t first = 0;
+	struct object_id oid;
+
+	if (!m->num_objects)
+		return;
+
+	match = bsearch_midx(m, mad->hash, &first);
+
+	/*
+	 * first is now the position in the packfile where we would insert
+	 * mad->hash if it does not exist (or the position of mad->hash if
+	 * it does exist). Hence, we consider a maximum of three objects
+	 * nearby for the abbreviation length.
+	 */
+	mad->init_len = 0;
+	if (!match) {
+		nth_midxed_object_oid(&oid, m, first);
+		extend_abbrev_len(&oid, mad);
+	} else if (first < m->num_objects - 1) {
+		nth_midxed_object_oid(&oid, m, first + 1);
+		extend_abbrev_len(&oid, mad);
+	}
+	if (first > 0) {
+		nth_midxed_object_oid(&oid, m, first - 1);
+		extend_abbrev_len(&oid, mad);
+	}
+	mad->init_len = mad->cur_len;
+}
+
 static void find_abbrev_len_for_pack(struct packed_git *p,
 				     struct min_abbrev_data *mad)
 {
@@ -563,8 +626,11 @@ static void find_abbrev_len_for_pack(struct packed_git *p,
 static void find_abbrev_len_packed(struct min_abbrev_data *mad)
 {
 	struct packed_git *p;
+	struct midxed_git *m;
 
-	prepare_packed_git();
+	prepare_packed_git_internal(1);
+	for (m = midxed_git; m; m = m->next)
+		find_abbrev_len_for_midx(m, mad);
 	for (p = packed_git; p; p = p->next)
 		find_abbrev_len_for_pack(p, mad);
 }
-- 
2.15.0


  parent reply	other threads:[~2018-01-07 18:15 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-07 18:14 [RFC PATCH 00/18] Multi-pack index (MIDX) Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 01/18] docs: Multi-Pack Index (MIDX) Design Notes Derrick Stolee
2018-01-08 19:32   ` Jonathan Tan
2018-01-08 20:35     ` Derrick Stolee
2018-01-08 22:06       ` Jonathan Tan
2018-01-07 18:14 ` [RFC PATCH 02/18] midx: specify midx file format Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 03/18] midx: create core.midx config setting Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 04/18] midx: write multi-pack indexes for an object list Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 05/18] midx: create midx builtin with --write mode Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 06/18] midx: add t5318-midx.sh test script Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 07/18] midx: teach midx --write to update midx-head Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 08/18] midx: teach git-midx to read midx file details Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 09/18] midx: find details of nth object in midx Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 10/18] midx: use existing midx when writing Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 11/18] midx: teach git-midx to clear midx files Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 12/18] midx: teach git-midx to delete expired files Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 13/18] t5318-midx.h: confirm git actions are stable Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 14/18] midx: load midx files when loading packs Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 15/18] midx: use midx for approximate object count Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 16/18] midx: nth_midxed_object_oid() and bsearch_midx() Derrick Stolee
2018-01-07 18:14 ` Derrick Stolee [this message]
2018-01-07 18:14 ` [RFC PATCH 18/18] packfile: use midx for object loads Derrick Stolee
2018-01-07 22:42 ` [RFC PATCH 00/18] Multi-pack index (MIDX) Ævar Arnfjörð Bjarmason
2018-01-08  0:08   ` Derrick Stolee
2018-01-08 10:20     ` Jeff King
2018-01-08 10:27       ` Jeff King
2018-01-08 12:28         ` Ævar Arnfjörð Bjarmason
2018-01-08 13:43       ` Johannes Schindelin
2018-01-09  6:50         ` Jeff King
2018-01-09 13:05           ` Johannes Schindelin
2018-01-09 19:51             ` Stefan Beller
2018-01-09 20:12               ` Junio C Hamano
2018-01-09 20:16                 ` Stefan Beller
2018-01-09 21:31                   ` Junio C Hamano
2018-01-10 17:05               ` Johannes Schindelin
2018-01-10 10:57             ` Jeff King
2018-01-08 13:43       ` Derrick Stolee
2018-01-09  7:12         ` Jeff King
2018-01-08 11:43     ` Ævar Arnfjörð Bjarmason
2018-06-06  8:13     ` Ævar Arnfjörð Bjarmason
2018-06-06 10:27       ` [RFC PATCH 0/2] unconditional O(1) SHA-1 abbreviation Ævar Arnfjörð Bjarmason
2018-06-06 10:27       ` [RFC PATCH 1/2] config.c: use braces on multiple conditional arms Ævar Arnfjörð Bjarmason
2018-06-06 10:27       ` [RFC PATCH 2/2] sha1-name: add core.validateAbbrev & relative core.abbrev Ævar Arnfjörð Bjarmason
2018-06-06 12:04         ` Christian Couder
2018-06-06 11:24       ` [RFC PATCH 00/18] Multi-pack index (MIDX) Derrick Stolee
2018-01-10 18:25 ` Martin Fick
2018-01-10 19:39   ` Derrick Stolee
2018-01-10 21:01     ` Martin Fick

Reply instructions:

You may reply publicly 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=20180107181459.222909-18-dstolee@microsoft.com \
    --to=stolee@gmail.com \
    --cc=Johannes.Shindelin@gmx.de \
    --cc=dstolee@microsoft.com \
    --cc=git@jeffhostetler.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jrnieder@gmail.com \
    --cc=peff@peff.net \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).