[RFC/PATCHv10 00/11] git notes

@@ -245,6 +245,7 @@ struct branch
 	const char *name;
 	struct tree_entry branch_tree;
 	uintmax_t last_commit;
+	uintmax_t num_notes;
 	unsigned active : 1;
 	unsigned pack_id : PACK_ID_BITS;
 	unsigned char sha1[20];

@@ -693,6 +694,7 @@ static struct branch *new_branch(const char *name)
 	b->table_next_branch = branch_table[hc];
 	b->branch_tree.versions[0].mode = S_IFDIR;
 	b->branch_tree.versions[1].mode = S_IFDIR;
+	b->num_notes = 0;
 	b->active = 0;
 	b->pack_id = MAX_PACK_ID;
 	branch_table[hc] = b;

@@ -1860,6 +1862,109 @@ static void load_branch(struct branch *b)
 	}
 }

+static unsigned char convert_num_notes_to_fanout(uintmax_t num_notes)
+{
+	unsigned char fanout = 0;
+	while ((num_notes >>= 8))
+		fanout++;
+	return fanout;
+}
+
+static void construct_path_with_fanout(const char *hex_sha1,
+		unsigned char fanout, char *path)
+{
+	unsigned int i = 0, j = 0;
+	if (fanout >= 20)
+		die("Too large fanout (%u)", fanout);
+	while (fanout) {
+		path[i++] = hex_sha1[j++];
+		path[i++] = hex_sha1[j++];
+		path[i++] = '/';
+		fanout--;
+	}
+	memcpy(path + i, hex_sha1 + j, 40 - j);
+	path[i + 40 - j] = '\0';
+}
+
+static uintmax_t do_change_note_fanout(
+		struct tree_entry *orig_root, struct tree_entry *root,
+		char *hex_sha1, unsigned int hex_sha1_len,
+		char *fullpath, unsigned int fullpath_len,
+		unsigned char fanout)
+{
+	struct tree_content *t = root->tree;
+	struct tree_entry *e, leaf;
+	unsigned int i, tmp_hex_sha1_len, tmp_fullpath_len;
+	uintmax_t num_notes = 0;
+	unsigned char sha1[20];
+	char realpath[60];
+
+	for (i = 0; t && i < t->entry_count; i++) {
+		e = t->entries[i];
+		tmp_hex_sha1_len = hex_sha1_len + e->name->str_len;
+		tmp_fullpath_len = fullpath_len;
+
+		/*
+		 * We're interested in EITHER existing note entries (entries
+		 * with exactly 40 hex chars in path, not including directory
+		 * separators), OR directory entries that may contain note
+		 * entries (with < 40 hex chars in path).
+		 * Also, each path component in a note entry must be a multiple
+		 * of 2 chars.
+		 */
+		if (!e->versions[1].mode ||
+		    tmp_hex_sha1_len > 40 ||
+		    e->name->str_len % 2)
+			continue;
+
+		/* This _may_ be a note entry, or a subdir containing notes */
+		memcpy(hex_sha1 + hex_sha1_len, e->name->str_dat,
+		       e->name->str_len);
+		if (tmp_fullpath_len)
+			fullpath[tmp_fullpath_len++] = '/';
+		memcpy(fullpath + tmp_fullpath_len, e->name->str_dat,
+		       e->name->str_len);
+		tmp_fullpath_len += e->name->str_len;
+		fullpath[tmp_fullpath_len] = '\0';
+
+		if (tmp_hex_sha1_len == 40 && !get_sha1_hex(hex_sha1, sha1)) {
+			/* This is a note entry */
+			construct_path_with_fanout(hex_sha1, fanout, realpath);
+			if (!strcmp(fullpath, realpath)) {
+				/* Note entry is in correct location */
+				num_notes++;
+				continue;
+			}
+
+			/* Rename fullpath to realpath */
+			if (!tree_content_remove(orig_root, fullpath, &leaf))
+				die("Failed to remove path %s", fullpath);
+			tree_content_set(orig_root, realpath,
+				leaf.versions[1].sha1,
+				leaf.versions[1].mode,
+				leaf.tree);
+		} else if (S_ISDIR(e->versions[1].mode)) {
+			/* This is a subdir that may contain note entries */
+			if (!e->tree)
+				load_tree(e);
+			num_notes += do_change_note_fanout(orig_root, e,
+				hex_sha1, tmp_hex_sha1_len,
+				fullpath, tmp_fullpath_len, fanout);
+		}
+
+		/* The above may have reallocated the current tree_content */
+		t = root->tree;
+	}
+	return num_notes;
+}
+
+static uintmax_t change_note_fanout(struct tree_entry *root,
+		unsigned char fanout)
+{
+	char hex_sha1[40], path[60];
+	return do_change_note_fanout(root, root, hex_sha1, 0, path, 0, fanout);
+}
+
 static void file_change_m(struct branch *b)
 {
 	const char *p = command_buf.buf + 2;

@@ -2010,14 +2115,16 @@ static void file_change_cr(struct branch *b, int rename)
 		leaf.tree);
 }

-static void note_change_n(struct branch *b)
+static void note_change_n(struct branch *b, unsigned char old_fanout)
 {
 	const char *p = command_buf.buf + 2;
 	static struct strbuf uq = STRBUF_INIT;
 	struct object_entry *oe = oe;
 	struct branch *s;
 	unsigned char sha1[20], commit_sha1[20];
+	char path[60];
 	uint16_t inline_data = 0;
+	unsigned char new_fanout;

 	/* <dataref> or 'inline' */
 	if (*p == ':') {

@@ -2071,7 +2178,7 @@ static void note_change_n(struct branch *b)
 		if (oe->type != OBJ_BLOB)
 			die("Not a blob (actually a %s): %s",
 				typename(oe->type), command_buf.buf);
-	} else {
+	} else if (!is_null_sha1(sha1)) {
 		enum object_type type = sha1_object_info(sha1, NULL);
 		if (type < 0)
 			die("Blob not found: %s", command_buf.buf);

@@ -2080,8 +2187,17 @@ static void note_change_n(struct branch *b)
 			    typename(type), command_buf.buf);
 	}

-	tree_content_set(&b->branch_tree, sha1_to_hex(commit_sha1), sha1,
-		S_IFREG | 0644, NULL);
+	construct_path_with_fanout(sha1_to_hex(commit_sha1), old_fanout, path);
+	if (tree_content_remove(&b->branch_tree, path, NULL))
+		b->num_notes--;
+
+	if (is_null_sha1(sha1))
+		return; /* nothing to insert */
+
+	b->num_notes++;
+	new_fanout = convert_num_notes_to_fanout(b->num_notes);
+	construct_path_with_fanout(sha1_to_hex(commit_sha1), new_fanout, path);
+	tree_content_set(&b->branch_tree, path, sha1, S_IFREG | 0644, NULL);
 }

 static void file_change_deleteall(struct branch *b)

@@ -2090,6 +2206,7 @@ static void file_change_deleteall(struct branch *b)
 	hashclr(b->branch_tree.versions[0].sha1);
 	hashclr(b->branch_tree.versions[1].sha1);
 	load_tree(&b->branch_tree);
+	b->num_notes = 0;
 }

 static void parse_from_commit(struct branch *b, char *buf, unsigned long size)

@@ -2213,6 +2330,7 @@ static void parse_new_commit(void)
 	char *committer = NULL;
 	struct hash_list *merge_list = NULL;
 	unsigned int merge_count;
+	unsigned char prev_fanout, new_fanout;

 	/* Obtain the branch name from the rest of our command */
 	sp = strchr(command_buf.buf, ' ') + 1;

@@ -2243,6 +2361,8 @@ static void parse_new_commit(void)
 		load_branch(b);
 	}

+	prev_fanout = convert_num_notes_to_fanout(b->num_notes);
+
 	/* file_change* */
 	while (command_buf.len > 0) {
 		if (!prefixcmp(command_buf.buf, "M "))

@@ -2254,7 +2374,7 @@ static void parse_new_commit(void)
 		else if (!prefixcmp(command_buf.buf, "C "))
 			file_change_cr(b, 0);
 		else if (!prefixcmp(command_buf.buf, "N "))
-			note_change_n(b);
+			note_change_n(b, prev_fanout);
 		else if (!strcmp("deleteall", command_buf.buf))
 			file_change_deleteall(b);
 		else {

@@ -2265,6 +2385,10 @@ static void parse_new_commit(void)
 			break;
 	}

+	new_fanout = convert_num_notes_to_fanout(b->num_notes);
+	if (new_fanout != prev_fanout)
+		b->num_notes = change_note_fanout(&b->branch_tree, new_fanout);
+
 	/* build the tree and the commit */
 	store_tree(&b->branch_tree);
 	hashcpy(b->branch_tree.versions[0].sha1,

@@ -1092,9 +1092,12 @@ test_expect_success 'P: fail on blob mark in gitlink' '
 ### series Q (notes)
 ###

-note1_data="Note for the first commit"
-note2_data="Note for the second commit"
-note3_data="Note for the third commit"
+note1_data="The first note for the first commit"
+note2_data="The first note for the second commit"
+note3_data="The first note for the third commit"
+note1b_data="The second note for the first commit"
+note1c_data="The third note for the first commit"
+note2b_data="The second note for the second commit"

 test_tick
 cat >input <<INPUT_END

@@ -1169,7 +1172,45 @@ data <<EOF
 $note3_data
 EOF

+commit refs/notes/foobar
+mark :10
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+notes (:10)
+COMMIT
+
+N inline :3
+data <<EOF
+$note1b_data
+EOF
+
+commit refs/notes/foobar2
+mark :11
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+notes (:11)
+COMMIT
+
+N inline :3
+data <<EOF
+$note1c_data
+EOF
+
+commit refs/notes/foobar
+mark :12
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+notes (:12)
+COMMIT
+
+deleteall
+N inline :5
+data <<EOF
+$note2b_data
+EOF
+
 INPUT_END
+
 test_expect_success \
 	'Q: commit notes' \
 	'git fast-import <input &&

@@ -1224,8 +1265,8 @@ committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
 notes (:9)
 EOF
 test_expect_success \
-	'Q: verify notes commit' \
-	'git cat-file commit refs/notes/foobar | sed 1d >actual &&
+	'Q: verify first notes commit' \
+	'git cat-file commit refs/notes/foobar~2 | sed 1d >actual &&
 	test_cmp expect actual'

 cat >expect.unsorted <<EOF

@@ -1235,23 +1276,112 @@ cat >expect.unsorted <<EOF
 EOF
 cat expect.unsorted | sort >expect
 test_expect_success \
-	'Q: verify notes tree' \
-	'git cat-file -p refs/notes/foobar^{tree} | sed "s/ [0-9a-f]*	/ /" >actual &&
+	'Q: verify first notes tree' \
+	'git cat-file -p refs/notes/foobar~2^{tree} | sed "s/ [0-9a-f]*	/ /" >actual &&
 	 test_cmp expect actual'

 echo "$note1_data" >expect
 test_expect_success \
-	'Q: verify note for first commit' \
-	'git cat-file blob refs/notes/foobar:$commit1 >actual && test_cmp expect actual'
+	'Q: verify first note for first commit' \
+	'git cat-file blob refs/notes/foobar~2:$commit1 >actual && test_cmp expect actual'

 echo "$note2_data" >expect
 test_expect_success \
-	'Q: verify note for second commit' \
-	'git cat-file blob refs/notes/foobar:$commit2 >actual && test_cmp expect actual'
+	'Q: verify first note for second commit' \
+	'git cat-file blob refs/notes/foobar~2:$commit2 >actual && test_cmp expect actual'
+
+echo "$note3_data" >expect
+test_expect_success \
+	'Q: verify first note for third commit' \
+	'git cat-file blob refs/notes/foobar~2:$commit3 >actual && test_cmp expect actual'
+
+cat >expect <<EOF
+parent `git rev-parse --verify refs/notes/foobar~2`
+author $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+
+notes (:10)
+EOF
+test_expect_success \
+	'Q: verify second notes commit' \
+	'git cat-file commit refs/notes/foobar^ | sed 1d >actual &&
+	test_cmp expect actual'
+
+cat >expect.unsorted <<EOF
+100644 blob $commit1
+100644 blob $commit2
+100644 blob $commit3
+EOF
+cat expect.unsorted | sort >expect
+test_expect_success \
+	'Q: verify second notes tree' \
+	'git cat-file -p refs/notes/foobar^^{tree} | sed "s/ [0-9a-f]*	/ /" >actual &&
+	 test_cmp expect actual'
+
+echo "$note1b_data" >expect
+test_expect_success \
+	'Q: verify second note for first commit' \
+	'git cat-file blob refs/notes/foobar^:$commit1 >actual && test_cmp expect actual'
+
+echo "$note2_data" >expect
+test_expect_success \
+	'Q: verify first note for second commit' \
+	'git cat-file blob refs/notes/foobar^:$commit2 >actual && test_cmp expect actual'

 echo "$note3_data" >expect
 test_expect_success \
-	'Q: verify note for third commit' \
-	'git cat-file blob refs/notes/foobar:$commit3 >actual && test_cmp expect actual'
+	'Q: verify first note for third commit' \
+	'git cat-file blob refs/notes/foobar^:$commit3 >actual && test_cmp expect actual'
+
+cat >expect <<EOF
+author $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+
+notes (:11)
+EOF
+test_expect_success \
+	'Q: verify third notes commit' \
+	'git cat-file commit refs/notes/foobar2 | sed 1d >actual &&
+	test_cmp expect actual'
+
+cat >expect.unsorted <<EOF
+100644 blob $commit1
+EOF
+cat expect.unsorted | sort >expect
+test_expect_success \
+	'Q: verify third notes tree' \
+	'git cat-file -p refs/notes/foobar2^{tree} | sed "s/ [0-9a-f]*	/ /" >actual &&
+	 test_cmp expect actual'
+
+echo "$note1c_data" >expect
+test_expect_success \
+	'Q: verify third note for first commit' \
+	'git cat-file blob refs/notes/foobar2:$commit1 >actual && test_cmp expect actual'
+
+cat >expect <<EOF
+parent `git rev-parse --verify refs/notes/foobar^`
+author $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+
+notes (:12)
+EOF
+test_expect_success \
+	'Q: verify fourth notes commit' \
+	'git cat-file commit refs/notes/foobar | sed 1d >actual &&
+	test_cmp expect actual'
+
+cat >expect.unsorted <<EOF
+100644 blob $commit2
+EOF
+cat expect.unsorted | sort >expect
+test_expect_success \
+	'Q: verify fourth notes tree' \
+	'git cat-file -p refs/notes/foobar^{tree} | sed "s/ [0-9a-f]*	/ /" >actual &&
+	 test_cmp expect actual'
+
+echo "$note2b_data" >expect
+test_expect_success \
+	'Q: verify second note for second commit' \
+	'git cat-file blob refs/notes/foobar:$commit2 >actual && test_cmp expect actual'

 test_done
--

@@ -0,0 +1,623 @@
+#!/bin/sh
+#
+# Copyright (c) 2009 Johan Herland
+#
+
+test_description='test git fast-import of notes objects'
+. ./test-lib.sh
+
+
+test_tick
+cat >input <<INPUT_END
+commit refs/heads/master
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+first commit
+COMMIT
+
+M 644 inline foo
+data <<EOF
+file foo in first commit
+EOF
+
+M 755 inline bar
+data <<EOF
+file bar in first commit
+EOF
+
+M 644 inline baz/xyzzy
+data <<EOF
+file baz/xyzzy in first commit
+EOF
+
+commit refs/heads/master
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+second commit
+COMMIT
+
+M 644 inline foo
+data <<EOF
+file foo in second commit
+EOF
+
+M 755 inline baz/xyzzy
+data <<EOF
+file baz/xyzzy in second commit
+EOF
+
+commit refs/heads/master
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+third commit
+COMMIT
+
+M 644 inline foo
+data <<EOF
+file foo in third commit
+EOF
+
+commit refs/heads/master
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+fourth commit
+COMMIT
+
+M 755 inline bar
+data <<EOF
+file bar in fourth commit
+EOF
+
+INPUT_END
+
+test_expect_success 'set up master branch' '
+
+	git fast-import <input &&
+	git whatchanged master
+'
+
+commit4=$(git rev-parse refs/heads/master)
+commit3=$(git rev-parse "$commit4^")
+commit2=$(git rev-parse "$commit4~2")
+commit1=$(git rev-parse "$commit4~3")
+
+test_tick
+cat >input <<INPUT_END
+commit refs/notes/test
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+first notes commit
+COMMIT
+
+M 644 inline $commit1
+data <<EOF
+first note for first commit
+EOF
+
+M 755 inline $commit2
+data <<EOF
+first note for second commit
+EOF
+
+INPUT_END
+
+cat >expect <<EXPECT_END
+    fourth commit
+    third commit
+    second commit
+    first note for second commit
+    first commit
+    first note for first commit
+EXPECT_END
+
+test_expect_success 'add notes with simple M command' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/test git log | grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_tick
+cat >input <<INPUT_END
+commit refs/notes/test
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+second notes commit
+COMMIT
+
+from refs/notes/test^0
+N inline $commit3
+data <<EOF
+first note for third commit
+EOF
+
+N inline $commit4
+data <<EOF
+first note for fourth commit
+EOF
+
+INPUT_END
+
+cat >expect <<EXPECT_END
+    fourth commit
+    first note for fourth commit
+    third commit
+    first note for third commit
+    second commit
+    first note for second commit
+    first commit
+    first note for first commit
+EXPECT_END
+
+test_expect_success 'add notes with simple N command' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/test git log | grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_tick
+cat >input <<INPUT_END
+commit refs/notes/test
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+third notes commit
+COMMIT
+
+from refs/notes/test^0
+N inline $commit1
+data <<EOF
+second note for first commit
+EOF
+
+N inline $commit2
+data <<EOF
+second note for second commit
+EOF
+
+N inline $commit3
+data <<EOF
+second note for third commit
+EOF
+
+N inline $commit4
+data <<EOF
+second note for fourth commit
+EOF
+
+INPUT_END
+
+cat >expect <<EXPECT_END
+    fourth commit
+    second note for fourth commit
+    third commit
+    second note for third commit
+    second commit
+    second note for second commit
+    first commit
+    second note for first commit
+EXPECT_END
+
+test_expect_success 'update existing notes with N command' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/test git log | grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_tick
+cat >input <<INPUT_END
+commit refs/notes/test
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+fourth notes commit
+COMMIT
+
+from refs/notes/test^0
+M 644 inline $(echo "$commit3" | sed "s|^..|&/|")
+data <<EOF
+prefix of note for third commit
+EOF
+
+M 644 inline $(echo "$commit4" | sed "s|^..|&/|")
+data <<EOF
+prefix of note for fourth commit
+EOF
+
+M 644 inline $(echo "$commit4" | sed "s|^\(..\)\(..\)|\1/\2/|")
+data <<EOF
+pre-prefix of note for fourth commit
+EOF
+
+N inline $commit1
+data <<EOF
+third note for first commit
+EOF
+
+N inline $commit2
+data <<EOF
+third note for second commit
+EOF
+
+N inline $commit3
+data <<EOF
+third note for third commit
+EOF
+
+N inline $commit4
+data <<EOF
+third note for fourth commit
+EOF
+
+
+INPUT_END
+
+cat >expect <<EXPECT_END
+    fourth commit
+    pre-prefix of note for fourth commit
+    prefix of note for fourth commit
+    third note for fourth commit
+    third commit
+    prefix of note for third commit
+    third note for third commit
+    second commit
+    third note for second commit
+    first commit
+    third note for first commit
+EXPECT_END
+
+test_expect_success 'add concatentation notes with M command' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/test git log | grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_tick
+cat >input <<INPUT_END
+commit refs/notes/test
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+fifth notes commit
+COMMIT
+
+from refs/notes/test^0
+deleteall
+
+INPUT_END
+
+cat >expect <<EXPECT_END
+    fourth commit
+    third commit
+    second commit
+    first commit
+EXPECT_END
+
+test_expect_success 'verify that deleteall also removes notes' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/test git log | grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_tick
+cat >input <<INPUT_END
+commit refs/notes/test
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+sixth notes commit
+COMMIT
+
+from refs/notes/test^0
+M 644 inline $commit1
+data <<EOF
+third note for first commit
+EOF
+
+M 644 inline $commit3
+data <<EOF
+third note for third commit
+EOF
+
+N inline $commit1
+data <<EOF
+fourth note for first commit
+EOF
+
+N inline $commit3
+data <<EOF
+fourth note for third commit
+EOF
+
+INPUT_END
+
+cat >expect <<EXPECT_END
+    fourth commit
+    third commit
+    fourth note for third commit
+    second commit
+    first commit
+    fourth note for first commit
+EXPECT_END
+
+test_expect_success 'verify that later N commands override earlier M commands' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/test git log | grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+# Write fast-import commands to create the given number of commits
+fast_import_commits () {
+	my_ref=$1
+	my_num_commits=$2
+	my_append_to_file=$3
+	my_i=0
+	while test $my_i -lt $my_num_commits
+	do
+		my_i=$(($my_i + 1))
+		test_tick
+		cat >>"$my_append_to_file" <<INPUT_END
+commit $my_ref
+mark :$my_i
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+commit #$my_i
+COMMIT
+
+M 644 inline file
+data <<EOF
+file contents in commit #$my_i
+EOF
+
+INPUT_END
+	done
+}
+
+# Write fast-import commands to create the given number of notes annotating
+# the commits created by fast_import_commits()
+fast_import_notes () {
+	my_notes_ref=$1
+	my_num_commits=$2
+	my_append_to_file=$3
+	my_note_append=$4
+	test_tick
+	cat >>"$my_append_to_file" <<INPUT_END
+commit $my_notes_ref
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+committing $my_num_commits notes
+COMMIT
+
+INPUT_END
+
+	my_i=0
+	while test $my_i -lt $my_num_commits
+	do
+		my_i=$(($my_i + 1))
+		cat >>"$my_append_to_file" <<INPUT_END
+N inline :$my_i
+data <<EOF
+note for commit #$my_i$my_note_append
+EOF
+
+INPUT_END
+	done
+}
+
+
+rm input expect
+num_commits=400
+# Create lots of commits
+fast_import_commits "refs/heads/many_commits" $num_commits input
+# Create one note per above commit
+fast_import_notes "refs/notes/many_notes" $num_commits input
+# Add a couple of non-notes as well
+test_tick
+cat >>input <<INPUT_END
+commit refs/notes/many_notes
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+committing some non-notes to the notes tree
+COMMIT
+
+M 755 inline foobar/non-note.txt
+data <<EOF
+This is not a note, but rather a regular file residing in a notes tree
+EOF
+
+M 644 inline deadbeef
+data <<EOF
+Non-note file
+EOF
+
+M 644 inline de/adbeef
+data <<EOF
+Another non-note file
+EOF
+
+INPUT_END
+# Finally create the expected output from all these notes and commits
+i=$num_commits
+while test $i -gt 0
+do
+	cat >>expect <<EXPECT_END
+    commit #$i
+    note for commit #$i
+EXPECT_END
+	i=$(($i - 1))
+done
+
+test_expect_success 'add lots of commits and notes' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/many_notes git log refs/heads/many_commits |
+	    grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_expect_success 'verify that lots of notes trigger a fanout scheme' '
+
+	# None of the entries in the top-level notes tree should be a full SHA1
+	git ls-tree --name-only refs/notes/many_notes |
+	while read path
+	do
+		if test $(expr length "$path") -ge 40
+		then
+			return 1
+		fi
+	done
+
+'
+
+cat >>expect_non-note1 << EOF
+This is not a note, but rather a regular file residing in a notes tree
+EOF
+
+cat >>expect_non-note2 << EOF
+Non-note file
+EOF
+
+cat >>expect_non-note3 << EOF
+Another non-note file
+EOF
+
+test_expect_success 'verify that non-notes are untouched by a fanout change' '
+
+	git cat-file -p refs/notes/many_notes:foobar/non-note.txt > actual &&
+	test_cmp expect_non-note1 actual &&
+	git cat-file -p refs/notes/many_notes:deadbeef > actual &&
+	test_cmp expect_non-note2 actual &&
+	git cat-file -p refs/notes/many_notes:de/adbeef > actual &&
+	test_cmp expect_non-note3 actual
+
+'
+remaining_notes=10
+test_tick
+cat >>input <<INPUT_END
+commit refs/notes/many_notes
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+removing all notes but $remaining_notes
+COMMIT
+from refs/notes/many_notes^0
+INPUT_END
+
+i=$remaining_notes
+while test $i -lt $num_commits
+do
+	i=$(($i + 1))
+	cat >>input <<INPUT_END
+N 0000000000000000000000000000000000000000 :$i
+INPUT_END
+done
+
+i=$num_commits
+rm expect
+while test $i -gt 0
+do
+	cat >>expect <<EXPECT_END
+    commit #$i
+EXPECT_END
+	if test $i -le $remaining_notes
+	then
+		cat >>expect <<EXPECT_END
+    note for commit #$i
+EXPECT_END
+	fi
+	i=$(($i - 1))
+done
+
+test_expect_success 'remove lots of notes' '
+
+	git fast-import <input &&
+	GIT_NOTES_REF=refs/notes/many_notes git log refs/heads/many_commits |
+	    grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_expect_success 'verify that removing notes trigger fanout consolidation' '
+
+	# All entries in the top-level notes tree should be a full SHA1
+	git ls-tree --name-only -r refs/notes/many_notes |
+	while read path
+	do
+		# Explicitly ignore the non-note paths
+		test "$path" = "foobar/non-note.txt" && continue
+		test "$path" = "deadbeef" && continue
+		test "$path" = "de/adbeef" && continue
+
+		if test $(expr length "$path") -ne 40
+		then
+			return 1
+		fi
+	done
+
+'
+
+test_expect_success 'verify that non-notes are untouched by a fanout change' '
+
+	git cat-file -p refs/notes/many_notes:foobar/non-note.txt > actual &&
+	test_cmp expect_non-note1 actual &&
+	git cat-file -p refs/notes/many_notes:deadbeef > actual &&
+	test_cmp expect_non-note2 actual &&
+	git cat-file -p refs/notes/many_notes:de/adbeef > actual &&
+	test_cmp expect_non-note3 actual
+
+'
+
+
+rm input expect
+num_notes_refs=10
+num_commits=16
+some_commits=8
+# Create commits
+fast_import_commits "refs/heads/more_commits" $num_commits input
+# Create one note per above commit per notes ref
+i=0
+while test $i -lt $num_notes_refs
+do
+	i=$(($i + 1))
+	fast_import_notes "refs/notes/more_notes_$i" $num_commits input
+done
+# Trigger branch reloading in git-fast-import by repeating the note creation
+i=0
+while test $i -lt $num_notes_refs
+do
+	i=$(($i + 1))
+	fast_import_notes "refs/notes/more_notes_$i" $some_commits input " (2)"
+done
+# Finally create the expected output from the notes in refs/notes/more_notes_1
+i=$num_commits
+while test $i -gt 0
+do
+	note_data="note for commit #$i"
+	if test $i -le $some_commits
+	then
+		note_data="$note_data (2)"
+	fi
+	cat >>expect <<EXPECT_END
+    commit #$i
+    $note_data
+EXPECT_END
+	i=$(($i - 1))
+done
+
+test_expect_success "add notes to $num_commits commits in each of $num_notes_refs refs" '
+
+	git fast-import --active-branches=5 <input &&
+	GIT_NOTES_REF=refs/notes/more_notes_1 git log refs/heads/more_commits |
+	    grep "^    " > actual &&
+	test_cmp expect actual
+
+'
+
+test_done

@@ -93,7 +93,7 @@ static void **note_tree_search(struct int_node **tree,
 
 	i = GET_NIBBLE(*n, key_sha1);
 	p = (*tree)->a[i];
-	switch(GET_PTR_TYPE(p)) {
+	switch (GET_PTR_TYPE(p)) {
 	case PTR_TYPE_INTERNAL:
 		*tree = CLR_PTR_TYPE(p);
 		(*n)++;

@@ -195,7 +195,7 @@ static void note_tree_insert(struct int_node *tree, unsigned char n,
 
 	assert(GET_PTR_TYPE(entry) == 0); /* no type bits set */
 	l = (struct leaf_node *) CLR_PTR_TYPE(*p);
-	switch(GET_PTR_TYPE(*p)) {
+	switch (GET_PTR_TYPE(*p)) {
 	case PTR_TYPE_NULL:
 		assert(!*p);
 		*p = SET_PTR_TYPE(entry, type);

@@ -257,7 +257,7 @@ static void note_tree_free(struct int_node *tree)
 	unsigned int i;
 	for (i = 0; i < 16; i++) {
 		void *p = tree->a[i];
-		switch(GET_PTR_TYPE(p)) {
+		switch (GET_PTR_TYPE(p)) {
 		case PTR_TYPE_INTERNAL:
 			note_tree_free(CLR_PTR_TYPE(p));
 			/* fall through */

@@ -341,6 +341,101 @@ static void load_subtree(struct leaf_node *subtree, struct int_node *node,
 	free(buf);
 }
 
+/*
+ * Determine optimal on-disk fanout for this part of the notes tree
+ *
+ * Given a (sub)tree and the level in the internal tree structure, determine
+ * whether or not the given existing fanout should be expanded for this
+ * (sub)tree.
+ *
+ * Values of the 'fanout' variable:
+ * - 0: No fanout (all notes are stored directly in the root notes tree)
+ * - 1: 2/38 fanout
+ * - 2: 2/2/36 fanout
+ * - 3: 2/2/2/34 fanout
+ * etc.
+ */
+static unsigned char determine_fanout(struct int_node *tree, unsigned char n,
+		unsigned char fanout)
+{
+	/*
+	 * The following is a simple heuristic that works well in practice:
+	 * For each even-numbered 16-tree level (remember that each on-disk
+	 * fanout level corresponds to two 16-tree levels), peek at all 16
+	 * entries at that tree level. If any of them are subtree entries, then
+	 * there are likely plenty of notes below this level, so we return an
+	 * incremented fanout immediately. Otherwise, we return an incremented
+	 * fanout only if all of the entries at this level are int_nodes.
+	 */
+	unsigned int i;
+	if ((n % 2) || (n > 2 * fanout))
+		return fanout;
+	for (i = 0; i < 16; i++) {
+		switch (GET_PTR_TYPE(tree->a[i])) {
+		case PTR_TYPE_SUBTREE:
+			return fanout + 1;
+		case PTR_TYPE_INTERNAL:
+			continue;
+		default:
+			return fanout;
+		}
+	}
+	return fanout + 1;
+}
+
+static void construct_path_with_fanout(const unsigned char *sha1,
+		unsigned char fanout, char *path)
+{
+	unsigned int i = 0, j = 0;
+	const char *hex_sha1 = sha1_to_hex(sha1);
+	assert(fanout < 20);
+	while (fanout) {
+		path[i++] = hex_sha1[j++];
+		path[i++] = hex_sha1[j++];
+		path[i++] = '/';
+		fanout--;
+	}
+	strcpy(path + i, hex_sha1 + j);
+}
+
+static int for_each_note_helper(struct int_node *tree, unsigned char n,
+		unsigned char fanout, each_note_fn fn, void *cb_data)
+{
+	unsigned int i;
+	void *p;
+	int ret = 0;
+	struct leaf_node *l;
+	static char path[40 + 19 + 1];  /* hex SHA1 + 19 * '/' + NUL */
+
+	fanout = determine_fanout(tree, n, fanout);
+	for (i = 0; i < 16; i++) {
+redo:
+		p = tree->a[i];
+		switch (GET_PTR_TYPE(p)) {
+		case PTR_TYPE_INTERNAL:
+			/* recurse into int_node */
+			ret = for_each_note_helper(
+				CLR_PTR_TYPE(p), n + 1, fanout, fn, cb_data);
+			break;
+		case PTR_TYPE_SUBTREE:
+			/* unpack subtree and resume traversal */
+			l = (struct leaf_node *) CLR_PTR_TYPE(p);
+			tree->a[i] = NULL;
+			load_subtree(l, tree, n);
+			free(l);
+			goto redo;
+		case PTR_TYPE_NOTE:
+			l = (struct leaf_node *) CLR_PTR_TYPE(p);
+			construct_path_with_fanout(l->key_sha1, fanout, path);
+			ret = fn(l->key_sha1, l->val_sha1, path, cb_data);
+			break;
+		}
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 void init_notes(const char *notes_ref, int flags)
 {
 	unsigned char sha1[20], object_sha1[20];

@@ -388,6 +483,12 @@ const unsigned char *get_note(const unsigned char *object_sha1)
 	return found ? found->val_sha1 : NULL;
 }
 
+int for_each_note(each_note_fn fn, void *cb_data)
+{
+	assert(initialized);
+	return for_each_note_helper(&root_node, 0, 0, fn, cb_data);
+}
+
 void free_notes(void)
 {
 	note_tree_free(&root_node);

@@ -28,6 +28,23 @@ void add_note(const unsigned char *object_sha1,
 /* Get the note object SHA1 containing the note data for the given object */
 const unsigned char *get_note(const unsigned char *object_sha1);
 
+/*
+ * Invoke the specified callback function for each note
+ *
+ * If the callback returns nonzero, the note walk is aborted, and the return
+ * value from the callback is returned from for_each_note().
+ *
+ * IMPORTANT: The callback function is NOT allowed to change the notes tree.
+ * In other words, the following functions can NOT be invoked (on the current
+ * notes tree) from within the callback:
+ * - add_note()
+ * - free_notes()
+ */
+typedef int each_note_fn(const unsigned char *object_sha1,
+		const unsigned char *note_sha1, const char *note_tree_path,
+		void *cb_data);
+int for_each_note(each_note_fn fn, void *cb_data);
+
 /* Free (and de-initialize) the internal notes tree structure */
 void free_notes(void);
 

@@ -1,5 +1,4 @@
 #include "cache.h"
-#include "commit.h"
 #include "notes.h"
 #include "refs.h"
 #include "utf8.h"

@@ -25,10 +24,10 @@ struct int_node {
 /*
  * Leaf nodes come in two variants, note entries and subtree entries,
  * distinguished by the LSb of the leaf node pointer (see above).
- * As a note entry, the key is the SHA1 of the referenced commit, and the
+ * As a note entry, the key is the SHA1 of the referenced object, and the
  * value is the SHA1 of the note object.
  * As a subtree entry, the key is the prefix SHA1 (w/trailing NULs) of the
- * referenced commit, using the last byte of the key to store the length of
+ * referenced object, using the last byte of the key to store the length of
  * the prefix. The value is the SHA1 of the tree object containing the notes
  * subtree.
  */