git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: Kevin Willford <kcwillford@gmail.com>
To: git@vger.kernel.org
Cc: Kevin Willford <kewillf@microsoft.com>,
	Kevin Willford <kcwillford@gmail.com>
Subject: [[PATCH v2] 1/4] patch-ids: stop using a hand-rolled hashmap implementation
Date: Fri, 29 Jul 2016 12:19:17 -0400	[thread overview]
Message-ID: <20160729161920.3792-2-kcwillford@gmail.com> (raw)
In-Reply-To: <20160729161920.3792-1-kcwillford@gmail.com>

From: Kevin Willford <kewillf@microsoft.com>

This change will use the hashmap from the hashmap.h to keep track of the
patch_ids that have been encountered instead of using an internal
implementation.  This simplifies the implementation of the patch ids.

Signed-off-by: Kevin Willford <kcwillford@gmail.com>
---
 patch-ids.c | 86 +++++++++++++++++++++----------------------------------------
 patch-ids.h |  7 +++--
 2 files changed, 32 insertions(+), 61 deletions(-)

diff --git a/patch-ids.c b/patch-ids.c
index a4d0016..db31fa6 100644
--- a/patch-ids.c
+++ b/patch-ids.c
@@ -16,90 +16,62 @@ int commit_patch_id(struct commit *commit, struct diff_options *options,
 	return diff_flush_patch_id(options, sha1);
 }
 
-static const unsigned char *patch_id_access(size_t index, void *table)
+static int patch_id_cmp(struct patch_id *a,
+			struct patch_id *b,
+			void *keydata)
 {
-	struct patch_id **id_table = table;
-	return id_table[index]->patch_id;
+	return hashcmp(a->patch_id, b->patch_id);
 }
 
-static int patch_pos(struct patch_id **table, int nr, const unsigned char *id)
-{
-	return sha1_pos(id, table, nr, patch_id_access);
-}
-
-#define BUCKET_SIZE 190 /* 190 * 21 = 3990, with slop close enough to 4K */
-struct patch_id_bucket {
-	struct patch_id_bucket *next;
-	int nr;
-	struct patch_id bucket[BUCKET_SIZE];
-};
-
 int init_patch_ids(struct patch_ids *ids)
 {
 	memset(ids, 0, sizeof(*ids));
 	diff_setup(&ids->diffopts);
 	DIFF_OPT_SET(&ids->diffopts, RECURSIVE);
 	diff_setup_done(&ids->diffopts);
+	hashmap_init(&ids->patches, (hashmap_cmp_fn)patch_id_cmp, 256);
 	return 0;
 }
 
 int free_patch_ids(struct patch_ids *ids)
 {
-	struct patch_id_bucket *next, *patches;
-
-	free(ids->table);
-	for (patches = ids->patches; patches; patches = next) {
-		next = patches->next;
-		free(patches);
-	}
+	hashmap_free(&ids->patches, 1);
 	return 0;
 }
 
-static struct patch_id *add_commit(struct commit *commit,
-				   struct patch_ids *ids,
-				   int no_add)
+static int init_patch_id_entry(struct patch_id *patch,
+			       struct commit *commit,
+			       struct patch_ids *ids)
 {
-	struct patch_id_bucket *bucket;
-	struct patch_id *ent;
-	unsigned char sha1[20];
-	int pos;
-
-	if (commit_patch_id(commit, &ids->diffopts, sha1))
-		return NULL;
-	pos = patch_pos(ids->table, ids->nr, sha1);
-	if (0 <= pos)
-		return ids->table[pos];
-	if (no_add)
-		return NULL;
-
-	pos = -1 - pos;
+	if (commit_patch_id(commit, &ids->diffopts, patch->patch_id))
+		return -1;
 
-	bucket = ids->patches;
-	if (!bucket || (BUCKET_SIZE <= bucket->nr)) {
-		bucket = xcalloc(1, sizeof(*bucket));
-		bucket->next = ids->patches;
-		ids->patches = bucket;
-	}
-	ent = &bucket->bucket[bucket->nr++];
-	hashcpy(ent->patch_id, sha1);
-
-	ALLOC_GROW(ids->table, ids->nr + 1, ids->alloc);
-	if (pos < ids->nr)
-		memmove(ids->table + pos + 1, ids->table + pos,
-			sizeof(ent) * (ids->nr - pos));
-	ids->nr++;
-	ids->table[pos] = ent;
-	return ids->table[pos];
+	hashmap_entry_init(patch, sha1hash(patch->patch_id));
+	return 0;
 }
 
 struct patch_id *has_commit_patch_id(struct commit *commit,
 				     struct patch_ids *ids)
 {
-	return add_commit(commit, ids, 1);
+	struct patch_id patch;
+
+	memset(&patch, 0, sizeof(patch));
+	if (init_patch_id_entry(&patch, commit, ids))
+		return NULL;
+
+	return hashmap_get(&ids->patches, &patch, NULL);
 }
 
 struct patch_id *add_commit_patch_id(struct commit *commit,
 				     struct patch_ids *ids)
 {
-	return add_commit(commit, ids, 0);
+	struct patch_id *key = xcalloc(1, sizeof(*key));
+
+	if (init_patch_id_entry(key, commit, ids)) {
+		free(key);
+		return NULL;
+	}
+
+	hashmap_add(&ids->patches, key);
+	return key;
 }
diff --git a/patch-ids.h b/patch-ids.h
index eeb56b3..9569ee0 100644
--- a/patch-ids.h
+++ b/patch-ids.h
@@ -2,15 +2,14 @@
 #define PATCH_IDS_H
 
 struct patch_id {
-	unsigned char patch_id[20];
+	struct hashmap_entry ent;
+	unsigned char patch_id[GIT_SHA1_RAWSZ];
 	char seen;
 };
 
 struct patch_ids {
+	struct hashmap patches;
 	struct diff_options diffopts;
-	int nr, alloc;
-	struct patch_id **table;
-	struct patch_id_bucket *patches;
 };
 
 int commit_patch_id(struct commit *commit, struct diff_options *options,
-- 
2.9.2.gvfs.2.42.gb7633a3


  reply	other threads:[~2016-07-29 16:20 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-29 16:19 [[PATCH v2] 0/4] Use header data patch ids for rebase to avoid loading file content Kevin Willford
2016-07-29 16:19 ` Kevin Willford [this message]
2016-07-29 20:47   ` [[PATCH v2] 1/4] patch-ids: stop using a hand-rolled hashmap implementation Junio C Hamano
2016-08-01  8:54     ` Johannes Schindelin
2016-08-01 20:04       ` Junio C Hamano
2016-08-01 22:34         ` Eric Wong
2016-08-02 10:30         ` Johannes Schindelin
2016-08-02 17:01           ` Junio C Hamano
2016-08-02 18:04             ` Junio C Hamano
2016-07-29 21:29   ` Junio C Hamano
2016-07-29 16:19 ` [[PATCH v2] 2/4] patch-ids: replace the seen indicator with a commit pointer Kevin Willford
2016-07-29 21:03   ` Junio C Hamano
2016-07-29 16:19 ` [[PATCH v2] 3/4] patch-ids: add flag to create the diff patch id using header only data Kevin Willford
2016-07-29 16:19 ` [[PATCH v2] 4/4] rebase: avoid computing unnecessary patch IDs Kevin Willford
2016-07-29 21:46   ` Junio C Hamano
2016-08-01  8:58     ` Johannes Schindelin
2016-08-01 20:11       ` Junio C Hamano
2016-08-02  9:50         ` Jakub Narębski
2016-08-02 17:06           ` Junio C Hamano
2016-08-02 10:45         ` Johannes Schindelin
2016-08-02 17:08           ` Junio C Hamano
2016-08-04  3:00             ` Junio C Hamano
2016-08-04 14:21               ` Johannes Schindelin
2016-07-29 20:22 ` [[PATCH v2] 0/4] Use header data patch ids for rebase to avoid loading file content Junio C Hamano
2016-08-01  9:01   ` Johannes Schindelin

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=20160729161920.3792-2-kcwillford@gmail.com \
    --to=kcwillford@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=kewillf@microsoft.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
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).