git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Thomas Gummerer <t.gummerer@gmail.com>
To: git@vger.kernel.org
Cc: trast@inf.ethz.ch, mhagger@alum.mit.edu, gitster@pobox.com,
	pclouds@gmail.com, robin.rosenberg@dewire.com,
	sunshine@sunshineco.com, ramsay@ramsay1.demon.co.uk,
	t.gummerer@gmail.com
Subject: [PATCH v3 17/24] read-cache: read cache-tree in index-v5
Date: Sun, 18 Aug 2013 21:42:06 +0200	[thread overview]
Message-ID: <1376854933-31241-18-git-send-email-t.gummerer@gmail.com> (raw)
In-Reply-To: <1376854933-31241-1-git-send-email-t.gummerer@gmail.com>

Since the cache-tree data is saved as part of the directory data,
we already read it at the beginning of the index. The cache-tree
is only converted from this directory data.

The cache-tree data is arranged in a tree, with the children sorted by
pathlen at each node, while the ondisk format is sorted lexically.
So we have to rebuild this format from the on-disk directory list.

Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com>
---
 cache-tree.c    |  2 +-
 cache-tree.h    |  1 +
 read-cache-v5.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 80 insertions(+), 1 deletion(-)

diff --git a/cache-tree.c b/cache-tree.c
index 0bbec43..1209732 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -31,7 +31,7 @@ void cache_tree_free(struct cache_tree **it_p)
 	*it_p = NULL;
 }
 
-static int subtree_name_cmp(const char *one, int onelen,
+int subtree_name_cmp(const char *one, int onelen,
 			    const char *two, int twolen)
 {
 	if (onelen < twolen)
diff --git a/cache-tree.h b/cache-tree.h
index f1923ad..9818926 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -25,6 +25,7 @@ struct cache_tree *cache_tree(void);
 void cache_tree_free(struct cache_tree **);
 void cache_tree_invalidate_path(struct cache_tree *, const char *);
 struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
+int subtree_name_cmp(const char *, int, const char *, int);
 
 void cache_tree_write(struct strbuf *, struct cache_tree *root);
 struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
diff --git a/read-cache-v5.c b/read-cache-v5.c
index 85a2069..b14505a 100644
--- a/read-cache-v5.c
+++ b/read-cache-v5.c
@@ -471,6 +471,83 @@ static int convert_resolve_undo(struct index_state *istate,
 	return 0;
 }
 
+static struct cache_tree *convert_one(struct directory_entry *de)
+{
+	int i;
+	struct cache_tree *it;
+
+	it = cache_tree();
+	it->entry_count = de->de_nentries;
+	if (0 <= it->entry_count)
+		hashcpy(it->sha1, de->sha1);
+
+	/*
+	 * Just a heuristic -- we do not add directories that often but
+	 * we do not want to have to extend it immediately when we do,
+	 * hence +2.
+	 */
+	it->subtree_alloc = de->de_nsubtrees + 2;
+	it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *));
+	for (i = 0; i < de->de_nsubtrees; i++) {
+		struct cache_tree *sub;
+		struct cache_tree_sub *subtree;
+		char *buf, *name;
+
+		sub = convert_one(de->sub[i]);
+		if(!sub)
+			goto free_return;
+
+		name = "";
+		buf = strtok(de->sub[i]->pathname, "/");
+		while (buf) {
+			name = buf;
+			buf = strtok(NULL, "/");
+		}
+		subtree = cache_tree_sub(it, name);
+		subtree->cache_tree = sub;
+	}
+	if (de->de_nsubtrees != it->subtree_nr)
+		die("cache-tree: internal error");
+	return it;
+ free_return:
+	cache_tree_free(&it);
+	return NULL;
+}
+
+static int compare_cache_tree_elements(const void *a, const void *b)
+{
+	const struct directory_entry *de1, *de2;
+
+	de1 = (const struct directory_entry *) a;
+	de2 = (const struct directory_entry *) b;
+	return subtree_name_cmp(de1->pathname, de1->de_pathlen,
+				de2->pathname, de2->de_pathlen);
+}
+
+static void sort_directories(struct directory_entry *de)
+{
+	int i;
+
+	for (i = 0; i < de->de_nsubtrees; i++) {
+		if (de->sub[i]->de_nsubtrees)
+			sort_directories(de->sub[i]);
+	}
+	qsort(de->sub, de->de_nsubtrees, sizeof(struct directory_entry *),
+	      compare_cache_tree_elements);
+}
+
+/*
+ * This function modifies the directory argument that is given to it.
+ * Don't use it if the directory entries are still needed after.
+ */
+static struct cache_tree *cache_tree_convert_v5(struct directory_entry *de)
+{
+	if (!de->de_nentries)
+		return NULL;
+	sort_directories(de);
+	return convert_one(de);
+}
+
 static int read_entries(struct index_state *istate, struct directory_entry *de,
 			unsigned int first_entry_offset, void *mmap,
 			unsigned long mmap_size, unsigned int *nr,
@@ -591,6 +668,7 @@ static int read_index_v5(struct index_state *istate, void *mmap,
 		}
 		de = de->next;
 	}
+	istate->cache_tree = cache_tree_convert_v5(root_directory);
 	istate->cache_nr = nr;
 	return 0;
 }
-- 
1.8.3.4.1231.g9fbf354.dirty

  parent reply	other threads:[~2013-08-18 19:49 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-08-18 19:41 [PATCH v3 00/24] Index-v5 Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 01/24] t2104: Don't fail for index versions other than [23] Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 02/24] read-cache: use fixed width integer types Thomas Gummerer
2013-08-18 20:21   ` Eric Sunshine
2013-08-20 19:30   ` Junio C Hamano
2013-08-21  3:05     ` Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 03/24] read-cache: split index file version specific functionality Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 04/24] read-cache: clear version in discard_index() Thomas Gummerer
2013-08-20 19:34   ` Junio C Hamano
2013-08-21  3:06     ` Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 05/24] read-cache: move index v2 specific functions to their own file Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 06/24] read-cache: Don't compare uid, gid and ino on cygwin Thomas Gummerer
2013-08-18 22:34   ` Ramsay Jones
2013-08-20  8:36     ` Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 07/24] read-cache: Re-read index if index file changed Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 08/24] add documentation for the index api Thomas Gummerer
2013-08-18 20:50   ` Eric Sunshine
2013-08-18 19:41 ` [PATCH v3 09/24] read-cache: add index reading api Thomas Gummerer
2013-08-18 19:41 ` [PATCH v3 10/24] make sure partially read index is not changed Thomas Gummerer
2013-08-18 21:06   ` Eric Sunshine
2013-08-20  8:46     ` Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 11/24] grep.c: use index api Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 12/24] ls-files.c: " Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 13/24] documentation: add documentation of the index-v5 file format Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 14/24] read-cache: make in-memory format aware of stat_crc Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 15/24] read-cache: read index-v5 Thomas Gummerer
2013-08-19  1:57   ` Eric Sunshine
2013-08-20 14:01   ` Duy Nguyen
2013-08-20 20:59     ` Thomas Gummerer
2013-08-21  0:44       ` Duy Nguyen
2013-08-20 14:16   ` Duy Nguyen
2013-08-20 21:13     ` Thomas Gummerer
2013-08-23 23:52   ` Duy Nguyen
2013-08-18 19:42 ` [PATCH v3 16/24] read-cache: read resolve-undo data Thomas Gummerer
2013-08-19  1:59   ` Eric Sunshine
2013-08-18 19:42 ` Thomas Gummerer [this message]
2013-08-24  0:09   ` [PATCH v3 17/24] read-cache: read cache-tree in index-v5 Duy Nguyen
2013-11-25 15:41     ` Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 18/24] read-cache: write index-v5 Thomas Gummerer
2013-08-24  3:58   ` Duy Nguyen
2013-11-25 15:37     ` Thomas Gummerer
2013-08-24  4:07   ` Duy Nguyen
2013-08-24  9:56     ` Duy Nguyen
2013-08-18 19:42 ` [PATCH v3 19/24] read-cache: write index-v5 cache-tree data Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 20/24] read-cache: write resolve-undo data for index-v5 Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 21/24] update-index.c: rewrite index when index-version is given Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 22/24] p0003-index.sh: add perf test for the index formats Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 23/24] introduce GIT_INDEX_VERSION environment variable Thomas Gummerer
2013-08-21  0:57   ` Duy Nguyen
2013-08-21  4:01     ` Thomas Gummerer
2013-08-18 19:42 ` [PATCH v3 24/24] test-lib: allow setting the index format version Thomas Gummerer
2013-08-24  4:16 ` [PATCH v3 00/24] Index-v5 Duy Nguyen
2013-08-25  3:07   ` Junio C Hamano
2013-08-25  4:40     ` Duy Nguyen
2013-08-31  5:23     ` Thomas Gummerer

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

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

  git send-email \
    --in-reply-to=1376854933-31241-18-git-send-email-t.gummerer@gmail.com \
    --to=t.gummerer@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=mhagger@alum.mit.edu \
    --cc=pclouds@gmail.com \
    --cc=ramsay@ramsay1.demon.co.uk \
    --cc=robin.rosenberg@dewire.com \
    --cc=sunshine@sunshineco.com \
    --cc=trast@inf.ethz.ch \
    /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.
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 NNTP newsgroup(s).