Teach fast-import to import subtrees named by tree id

To simulate the svn cp command, it would be very useful to be
replace an arbitrary file in the current revision by an
arbitrary directory from a previous one.  Modify the filemodify
command to allow that:

 M 040000 <tree id> pathname

This would be most useful in combination with a facility to
print the commit ids for new revisions as they are written.

Cc: Shawn O. Pearce <spearce@spearce.org>
Cc: Sverre Rabbelier <srabbelier@gmail.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-fast-import.txt

@@ -482,9 +482,11 @@ External data format::
 	'M' SP <mode> SP <dataref> SP <path> LF
 ....
 +
-Here `<dataref>` can be either a mark reference (`:<idnum>`)
+Here usually `<dataref>` must be either a mark reference (`:<idnum>`)
 set by a prior `blob` command, or a full 40-byte SHA-1 of an
-existing Git blob object.
+existing Git blob object.  If `<mode>` is `040000`` then
+`<dataref>` must be the full 40-byte SHA-1 of an existing
+Git tree object or a mark reference set with `--import-marks`.
 
 Inline data format::
 	The data content for the file has not been supplied yet.
@@ -509,6 +511,8 @@ in octal.  Git only supports the following modes:
 * `160000`: A gitlink, SHA-1 of the object refers to a commit in
   another repository. Git links can only be specified by SHA or through
   a commit mark. They are used to implement submodules.
+* `040000`: A subdirectory.  Subdirectories can only be specified by
+  SHA or through a tree mark set with `--import-marks`.
 
 In both formats `<path>` is the complete path of the file to be added
 (if not already existing) or modified (if already existing).

fast-import.c

@@ -2131,6 +2131,7 @@ static void file_change_m(struct branch *b)
 	case S_IFREG | 0644:
 	case S_IFREG | 0755:
 	case S_IFLNK:
+	case S_IFDIR:
 	case S_IFGITLINK:
 		/* ok */
 		break;
@@ -2176,23 +2177,28 @@ static void file_change_m(struct branch *b)
 		 * another repository.
 		 */
 	} else if (inline_data) {
+		if (S_ISDIR(mode))
+			die("Directories cannot be specified 'inline': %s",
+				command_buf.buf);
 		if (p != uq.buf) {
 			strbuf_addstr(&uq, p);
 			p = uq.buf;
 		}
 		read_next_command();
 		parse_and_store_blob(&last_blob, sha1, 0);
-	} else if (oe) {
-		if (oe->type != OBJ_BLOB)
-			die("Not a blob (actually a %s): %s",
-				typename(oe->type), command_buf.buf);
 	} else {
-		enum object_type type = sha1_object_info(sha1, NULL);
+		enum object_type expected = S_ISDIR(mode) ?
+						OBJ_TREE: OBJ_BLOB;
+		enum object_type type = oe ? oe->type :
+					sha1_object_info(sha1, NULL);
 		if (type < 0)
-			die("Blob not found: %s", command_buf.buf);
-		if (type != OBJ_BLOB)
-			die("Not a blob (actually a %s): %s",
-			    typename(type), command_buf.buf);
+			die("%s not found: %s",
+					S_ISDIR(mode) ?  "Tree" : "Blob",
+					command_buf.buf);
+		if (type != expected)
+			die("Not a %s (actually a %s): %s",
+				typename(expected), typename(type),
+				command_buf.buf);
 	}
 
 	tree_content_set(&b->branch_tree, p, sha1, mode, NULL);

t/t9300-fast-import.sh

@@ -796,6 +796,60 @@ test_expect_success \
 	'git fast-import <input &&
 	 test `git rev-parse N2^{tree}` = `git rev-parse N3^{tree}`'
 
+test_expect_success \
+	'N: copy directory by id' \
+	'cat >expect <<-\EOF &&
+	:100755 100755 f1fb5da718392694d0076d677d6d0e364c79b0bc f1fb5da718392694d0076d677d6d0e364c79b0bc C100	file2/newf	file3/newf
+	:100644 100644 7123f7f44e39be127c5eb701e5968176ee9d78b1 7123f7f44e39be127c5eb701e5968176ee9d78b1 C100	file2/oldf	file3/oldf
+	EOF
+	 subdir=$(git rev-parse refs/heads/branch^0:file2) &&
+	 cat >input <<-INPUT_END &&
+	commit refs/heads/N4
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+	data <<COMMIT
+	copy by tree hash
+	COMMIT
+
+	from refs/heads/branch^0
+	M 040000 $subdir file3
+	INPUT_END
+	 git fast-import <input &&
+	 git diff-tree -C --find-copies-harder -r N4^ N4 >actual &&
+	 compare_diff_raw expect actual'
+
+test_expect_success \
+	'N: modify copied tree' \
+	'cat >expect <<-\EOF &&
+	:100644 100644 fcf778cda181eaa1cbc9e9ce3a2e15ee9f9fe791 fcf778cda181eaa1cbc9e9ce3a2e15ee9f9fe791 C100	newdir/interesting	file3/file5
+	:100755 100755 f1fb5da718392694d0076d677d6d0e364c79b0bc f1fb5da718392694d0076d677d6d0e364c79b0bc C100	file2/newf	file3/newf
+	:100644 100644 7123f7f44e39be127c5eb701e5968176ee9d78b1 7123f7f44e39be127c5eb701e5968176ee9d78b1 C100	file2/oldf	file3/oldf
+	EOF
+	 subdir=$(git rev-parse refs/heads/branch^0:file2) &&
+	 cat >input <<-INPUT_END &&
+	commit refs/heads/N5
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+	data <<COMMIT
+	copy by tree hash
+	COMMIT
+
+	from refs/heads/branch^0
+	M 040000 $subdir file3
+
+	commit refs/heads/N5
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+	data <<COMMIT
+	modify directory copy
+	COMMIT
+
+	M 644 inline file3/file5
+	data <<EOF
+	$file5_data
+	EOF
+	INPUT_END
+	 git fast-import <input &&
+	 git diff-tree -C --find-copies-harder -r N5^^ N5 >actual &&
+	 compare_diff_raw expect actual'
+
 ###
 ### series O
 ###