fast-import: add 'ls' command

Lazy fast-import frontend authors that want to rely on the backend to
keep track of the content of the imported trees _almost_ have what
they need in the 'cat-blob' command (v1.7.4-rc0~30^2~3, 2010-11-28).
But it is not quite enough, since

 (1) cat-blob can be used to retrieve the content of files, but
     not their mode, and

 (2) using cat-blob requires the frontend to keep track of a name
     (mark number or object id) for each blob to be retrieved

Introduce an 'ls' command to complement cat-blob and take care of the
remaining needs.  The 'ls' command finds what is at a given path
within a given tree-ish (tag, commit, or tree):

	'ls' SP <dataref> SP <path> LF

or in fast-import's active commit:

	'ls' SP <path> LF

The response is a single line sent through the cat-blob channel,
imitating ls-tree output.  So for example:

	FE> ls :1 Documentation
	gfi> 040000 tree 9e6c2b599341d28a2a375f8207507e0a2a627fe9	Documentation
	FE> ls 9e6c2b599341d28a2a375f8207507e0a2a627fe9 git-fast-import.txt
	gfi> 100644 blob 4f92954396e3f0f97e75b6838a5635b583708870	git-fast-import.txt
	FE> ls :1 RelNotes
	gfi> 120000 blob b942e499449d97aeb50c73ca2bdc1c6e6d528743	RelNotes
	FE> cat-blob b942e499449d97aeb50c73ca2bdc1c6e6d528743
	gfi> b942e499449d97aeb50c73ca2bdc1c6e6d528743 blob 32
	gfi> Documentation/RelNotes/1.7.4.txt

The most interesting parts of the reply are the first word, which is
a 6-digit octal mode (regular file, executable, symlink, directory,
or submodule), and the part from the second space to the tab, which is
a <dataref> that can be used in later cat-blob, ls, and filemodify (M)
commands to refer to the content (blob, tree, or commit) at that path.

If there is nothing there, the response is "missing some/path".

The intent is for this command to be used to read files from the
active commit, so a frontend can apply patches to them, and to copy
files and directories from previous revisions.

For example, proposed updates to svn-fe use this command in place of
its internal representation of the repository directory structure.
This simplifies the frontend a great deal and means support for
resuming an import in a separate fast-import run (i.e., incremental
import) is basically free.

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Improved-by: Junio C Hamano <gitster@pobox.com>
Improved-by: Sverre Rabbelier <srabbelier@gmail.com>

1 files changed, 159 insertions, 3 deletions

diff --git a/fast-import.c b/fast-import.c
index 3886a1b464..6c37b8400a 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -24,10 +24,12 @@ Format of STDIN stream:
     commit_msg
     ('from' sp committish lf)?
     ('merge' sp committish lf)*
-    file_change*
+    (file_change | ls)*
     lf?;
   commit_msg ::= data;
 
+  ls ::= 'ls' sp '"' quoted(path) '"' lf;
+
   file_change ::= file_clr
     | file_del
     | file_rnm
@@ -132,7 +134,7 @@ Format of STDIN stream:
   ts    ::= # time since the epoch in seconds, ascii base10 notation;
   tz    ::= # GIT style timezone;
 
-     # note: comments and cat requests may appear anywhere
+     # note: comments, ls and cat requests may appear anywhere
      # in the input, except within a data command.  Any form
      # of the data command always escapes the related input
      # from comment processing.
@@ -141,7 +143,9 @@ Format of STDIN stream:
      # must be the first character on that line (an lf
      # preceded it).
      #
+
   cat_blob ::= 'cat-blob' sp (hexsha1 | idnum) lf;
+  ls_tree  ::= 'ls' sp (hexsha1 | idnum) sp path_str lf;
 
   comment ::= '#' not_lf* lf;
   not_lf  ::= # Any byte that is not ASCII newline (LF);
@@ -374,6 +378,7 @@ static int cat_blob_fd = STDOUT_FILENO;
 
 static void parse_argv(void);
 static void parse_cat_blob(void);
+static void parse_ls(struct branch *b);
 
 static void write_branch_report(FILE *rpt, struct branch *b)
 {
@@ -2614,6 +2619,8 @@ static void parse_new_commit(void)
 			note_change_n(b, prev_fanout);
 		else if (!strcmp("deleteall", command_buf.buf))
 			file_change_deleteall(b);
+		else if (!prefixcmp(command_buf.buf, "ls "))
+			parse_ls(b);
 		else {
 			unread_command_buf = 1;
 			break;
@@ -2837,6 +2844,153 @@ static void parse_cat_blob(void)
 	cat_blob(oe, sha1);
 }
 
+static struct object_entry *dereference(struct object_entry *oe,
+					unsigned char sha1[20])
+{
+	unsigned long size;
+	void *buf = NULL;
+	if (!oe) {
+		enum object_type type = sha1_object_info(sha1, NULL);
+		if (type < 0)
+			die("object not found: %s", sha1_to_hex(sha1));
+		/* cache it! */
+		oe = insert_object(sha1);
+		oe->type = type;
+		oe->pack_id = MAX_PACK_ID;
+		oe->idx.offset = 1;
+	}
+	switch (oe->type) {
+	case OBJ_TREE:	/* easy case. */
+		return oe;
+	case OBJ_COMMIT:
+	case OBJ_TAG:
+		break;
+	default:
+		die("Not a treeish: %s", command_buf.buf);
+	}
+
+	if (oe->pack_id != MAX_PACK_ID) {	/* in a pack being written */
+		buf = gfi_unpack_entry(oe, &size);
+	} else {
+		enum object_type unused;
+		buf = read_sha1_file(sha1, &unused, &size);
+	}
+	if (!buf)
+		die("Can't load object %s", sha1_to_hex(sha1));
+
+	/* Peel one layer. */
+	switch (oe->type) {
+	case OBJ_TAG:
+		if (size < 40 + strlen("object ") ||
+		    get_sha1_hex(buf + strlen("object "), sha1))
+			die("Invalid SHA1 in tag: %s", command_buf.buf);
+		break;
+	case OBJ_COMMIT:
+		if (size < 40 + strlen("tree ") ||
+		    get_sha1_hex(buf + strlen("tree "), sha1))
+			die("Invalid SHA1 in commit: %s", command_buf.buf);
+	}
+
+	free(buf);
+	return find_object(sha1);
+}
+
+static struct object_entry *parse_treeish_dataref(const char **p)
+{
+	unsigned char sha1[20];
+	struct object_entry *e;
+
+	if (**p == ':') {	/* <mark> */
+		char *endptr;
+		e = find_mark(strtoumax(*p + 1, &endptr, 10));
+		if (endptr == *p + 1)
+			die("Invalid mark: %s", command_buf.buf);
+		if (!e)
+			die("Unknown mark: %s", command_buf.buf);
+		*p = endptr;
+		hashcpy(sha1, e->idx.sha1);
+	} else {	/* <sha1> */
+		if (get_sha1_hex(*p, sha1))
+			die("Invalid SHA1: %s", command_buf.buf);
+		e = find_object(sha1);
+		*p += 40;
+	}
+
+	while (!e || e->type != OBJ_TREE)
+		e = dereference(e, sha1);
+	return e;
+}
+
+static void print_ls(int mode, const unsigned char *sha1, const char *path)
+{
+	static struct strbuf line = STRBUF_INIT;
+
+	/* See show_tree(). */
+	const char *type =
+		S_ISGITLINK(mode) ? commit_type :
+		S_ISDIR(mode) ? tree_type :
+		blob_type;
+
+	if (!mode) {
+		/* missing SP path LF */
+		strbuf_reset(&line);
+		strbuf_addstr(&line, "missing ");
+		quote_c_style(path, &line, NULL, 0);
+		strbuf_addch(&line, '\n');
+	} else {
+		/* mode SP type SP object_name TAB path LF */
+		strbuf_reset(&line);
+		strbuf_addf(&line, "%06o %s %s\t",
+				mode, type, sha1_to_hex(sha1));
+		quote_c_style(path, &line, NULL, 0);
+		strbuf_addch(&line, '\n');
+	}
+	cat_blob_write(line.buf, line.len);
+}
+
+static void parse_ls(struct branch *b)
+{
+	const char *p;
+	struct tree_entry *root = NULL;
+	struct tree_entry leaf = {0};
+
+	/* ls SP (<treeish> SP)? <path> */
+	p = command_buf.buf + strlen("ls ");
+	if (*p == '"') {
+		if (!b)
+			die("Not in a commit: %s", command_buf.buf);
+		root = &b->branch_tree;
+	} else {
+		struct object_entry *e = parse_treeish_dataref(&p);
+		root = new_tree_entry();
+		hashcpy(root->versions[1].sha1, e->idx.sha1);
+		load_tree(root);
+		if (*p++ != ' ')
+			die("Missing space after tree-ish: %s", command_buf.buf);
+	}
+	if (*p == '"') {
+		static struct strbuf uq = STRBUF_INIT;
+		const char *endp;
+		strbuf_reset(&uq);
+		if (unquote_c_style(&uq, p, &endp))
+			die("Invalid path: %s", command_buf.buf);
+		if (*endp)
+			die("Garbage after path in: %s", command_buf.buf);
+		p = uq.buf;
+	}
+	tree_content_get(root, p, &leaf);
+	/*
+	 * A directory in preparation would have a sha1 of zero
+	 * until it is saved.  Save, for simplicity.
+	 */
+	if (S_ISDIR(leaf.versions[1].mode))
+		store_tree(&leaf);
+
+	print_ls(leaf.versions[1].mode, leaf.versions[1].sha1, p);
+	if (!b || root != &b->branch_tree)
+		release_tree_entry(root);
+}
+
 static void checkpoint(void)
 {
 	checkpoint_requested = 0;
@@ -3001,7 +3155,7 @@ static int parse_one_feature(const char *feature, int from_stream)
 		relative_marks_paths = 0;
 	} else if (!prefixcmp(feature, "force")) {
 		force_update = 1;
-	} else if (!strcmp(feature, "notes")) {
+	} else if (!strcmp(feature, "notes") || !strcmp(feature, "ls")) {
 		; /* do nothing; we have the feature */
 	} else {
 		return 0;
@@ -3142,6 +3296,8 @@ int main(int argc, const char **argv)
 	while (read_next_command() != EOF) {
 		if (!strcmp("blob", command_buf.buf))
 			parse_new_blob();
+		else if (!prefixcmp(command_buf.buf, "ls "))
+			parse_ls(NULL);
 		else if (!prefixcmp(command_buf.buf, "commit "))
 			parse_new_commit();
 		else if (!prefixcmp(command_buf.buf, "tag "))