Merge branch 'en/fast-export'

* en/fast-export:
  fast-export: Document the fact that git-rev-list arguments are accepted
  Add new fast-export testcases
  fast-export: Add a --tag-of-filtered-object option for newly dangling tags
  fast-export: Do parent rewriting to avoid dropping relevant commits
  fast-export: Make sure we show actual ref names instead of "(null)"
  fast-export: Omit tags that tag trees
  fast-export: Set revs.topo_order before calling setup_revisions

3 files changed, 187 insertions, 8 deletions

diff --git a/Documentation/git-fast-export.txt b/Documentation/git-fast-export.txt
index 0c9eb567c..af2328d40 100644
--- a/Documentation/git-fast-export.txt
+++ b/Documentation/git-fast-export.txt
@@ -36,6 +36,17 @@ when encountering a signed tag.  With 'strip', the tags will be made
 unsigned, with 'verbatim', they will be silently exported
 and with 'warn', they will be exported, but you will see a warning.
 
+--tag-of-filtered-object=(abort|drop|rewrite)::
+	Specify how to handle tags whose tagged objectis filtered out.
+	Since revisions and files to export can be limited by path,
+	tagged objects may be filtered completely.
++
+When asking to 'abort' (which is the default), this program will die
+when encountering such a tag.  With 'drop' it will omit such tags from
+the output.  With 'rewrite', if the tagged object is a commit, it will
+rewrite the tag to tag an ancestor commit (via parent rewriting; see
+linkgit:git-rev-list[1])
+
 -M::
 -C::
 	Perform move and/or copy detection, as described in the
@@ -71,6 +82,12 @@ marks the same across runs.
 	allow that.  So fake a tagger to be able to fast-import the
 	output.
 
+[git-rev-list-args...]::
+       A list of arguments, acceptable to 'git-rev-parse' and
+       'git-rev-list', that specifies the specific objects and references
+       to export.  For example, `master\~10..master` causes the
+       current master reference to be exported along with all objects
+       added since its 10th ancestor commit.
 
 EXAMPLES
 --------
diff --git a/builtin-fast-export.c b/builtin-fast-export.c
index ca198250c..c48c18d0c 100644
--- a/builtin-fast-export.c
+++ b/builtin-fast-export.c
@@ -23,7 +23,8 @@ static const char *fast_export_usage[] = {
 };
 
 static int progress;
-static enum { VERBATIM, WARN, STRIP, ABORT } signed_tag_mode = ABORT;
+static enum { ABORT, VERBATIM, WARN, STRIP } signed_tag_mode = ABORT;
+static enum { ERROR, DROP, REWRITE } tag_of_filtered_mode = ABORT;
 static int fake_missing_tagger;
 
 static int parse_opt_signed_tag_mode(const struct option *opt,
@@ -42,6 +43,20 @@ static int parse_opt_signed_tag_mode(const struct option *opt,
 	return 0;
 }
 
+static int parse_opt_tag_of_filtered_mode(const struct option *opt,
+					  const char *arg, int unset)
+{
+	if (unset || !strcmp(arg, "abort"))
+		tag_of_filtered_mode = ABORT;
+	else if (!strcmp(arg, "drop"))
+		tag_of_filtered_mode = DROP;
+	else if (!strcmp(arg, "rewrite"))
+		tag_of_filtered_mode = REWRITE;
+	else
+		return error("Unknown tag-of-filtered mode: %s", arg);
+	return 0;
+}
+
 static struct decoration idnums;
 static uint32_t last_idnum;
 
@@ -289,6 +304,23 @@ static void handle_tag(const char *name, struct tag *tag)
 	char *buf;
 	const char *tagger, *tagger_end, *message;
 	size_t message_size = 0;
+	struct object *tagged;
+	int tagged_mark;
+	struct commit *p;
+
+	/* Trees have no identifer in fast-export output, thus we have no way
+	 * to output tags of trees, tags of tags of trees, etc.  Simply omit
+	 * such tags.
+	 */
+	tagged = tag->tagged;
+	while (tagged->type == OBJ_TAG) {
+		tagged = ((struct tag *)tagged)->tagged;
+	}
+	if (tagged->type == OBJ_TREE) {
+		warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
+			sha1_to_hex(tag->object.sha1));
+		return;
+	}
 
 	buf = read_sha1_file(tag->object.sha1, &type, &size);
 	if (!buf)
@@ -333,10 +365,45 @@ static void handle_tag(const char *name, struct tag *tag)
 			}
 	}
 
+	/* handle tag->tagged having been filtered out due to paths specified */
+	tagged = tag->tagged;
+	tagged_mark = get_object_mark(tagged);
+	if (!tagged_mark) {
+		switch(tag_of_filtered_mode) {
+		case ABORT:
+			die ("Tag %s tags unexported object; use "
+			     "--tag-of-filtered-object=<mode> to handle it.",
+			     sha1_to_hex(tag->object.sha1));
+		case DROP:
+			/* Ignore this tag altogether */
+			return;
+		case REWRITE:
+			if (tagged->type != OBJ_COMMIT) {
+				die ("Tag %s tags unexported %s!",
+				     sha1_to_hex(tag->object.sha1),
+				     typename(tagged->type));
+			}
+			p = (struct commit *)tagged;
+			for (;;) {
+				if (p->parents && p->parents->next)
+					break;
+				if (p->object.flags & UNINTERESTING)
+					break;
+				if (!(p->object.flags & TREESAME))
+					break;
+				if (!p->parents)
+					die ("Can't find replacement commit for tag %s\n",
+					     sha1_to_hex(tag->object.sha1));
+				p = p->parents->item;
+			}
+			tagged_mark = get_object_mark(&p->object);
+		}
+	}
+
 	if (!prefixcmp(name, "refs/tags/"))
 		name += 10;
 	printf("tag %s\nfrom :%d\n%.*s%sdata %d\n%.*s\n",
-	       name, get_object_mark(tag->tagged),
+	       name, tagged_mark,
 	       (int)(tagger_end - tagger), tagger,
 	       tagger == tagger_end ? "" : "\n",
 	       (int)message_size, (int)message_size, message ? message : "");
@@ -504,6 +571,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 		OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
 			     "select handling of signed tags",
 			     parse_opt_signed_tag_mode),
+		OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, "mode",
+			     "select handling of tags that tag filtered objects",
+			     parse_opt_tag_of_filtered_mode),
 		OPT_STRING(0, "export-marks", &export_filename, "FILE",
 			     "Dump marks to this file"),
 		OPT_STRING(0, "import-marks", &import_filename, "FILE",
@@ -520,6 +590,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	git_config(git_default_config, NULL);
 
 	init_revisions(&revs, prefix);
+	revs.topo_order = 1;
+	revs.show_source = 1;
+	revs.rewrite_parents = 1;
 	argc = setup_revisions(argc, argv, &revs, NULL);
 	argc = parse_options(argc, argv, prefix, options, fast_export_usage, 0);
 	if (argc > 1)
@@ -530,18 +603,13 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 
 	get_tags_and_duplicates(&revs.pending, &extra_refs);
 
-	revs.topo_order = 1;
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
 	revs.diffopt.format_callback = show_filemodify;
 	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
 	while ((commit = get_revision(&revs))) {
 		if (has_unshown_parent(commit)) {
-			struct commit_list *parent = commit->parents;
 			add_object_array(&commit->object, NULL, &commits);
-			for (; parent; parent = parent->next)
-				if (!parent->item->util)
-					parent->item->util = commit->util;
 		}
 		else {
 			handle_commit(commit, &revs);
diff --git a/t/t9301-fast-export.sh b/t/t9301-fast-export.sh
index 8c8a9e63c..356964e53 100755
--- a/t/t9301-fast-export.sh
+++ b/t/t9301-fast-export.sh
@@ -262,6 +262,94 @@ test_expect_success 'cope with tagger-less tags' '
 
 '
 
+test_expect_success 'setup for limiting exports by PATH' '
+	mkdir limit-by-paths &&
+	cd limit-by-paths &&
+	git init &&
+	echo hi > there &&
+	git add there &&
+	git commit -m "First file" &&
+	echo foo > bar &&
+	git add bar &&
+	git commit -m "Second file" &&
+	git tag -a -m msg mytag &&
+	echo morefoo >> bar &&
+	git add bar &&
+	git commit -m "Change to second file" &&
+	cd ..
+'
+
+cat > limit-by-paths/expected << EOF
+blob
+mark :1
+data 3
+hi
+
+reset refs/tags/mytag
+commit refs/tags/mytag
+mark :2
+author A U Thor <author@example.com> 1112912713 -0700
+committer C O Mitter <committer@example.com> 1112912713 -0700
+data 11
+First file
+M 100644 :1 there
+
+EOF
+
+test_expect_success 'dropping tag of filtered out object' '
+	cd limit-by-paths &&
+	git fast-export --tag-of-filtered-object=drop mytag -- there > output &&
+	test_cmp output expected &&
+	cd ..
+'
+
+cat >> limit-by-paths/expected << EOF
+tag mytag
+from :2
+tagger C O Mitter <committer@example.com> 1112912713 -0700
+data 4
+msg
+
+EOF
+
+test_expect_success 'rewriting tag of filtered out object' '
+	cd limit-by-paths &&
+	git fast-export --tag-of-filtered-object=rewrite mytag -- there > output &&
+	test_cmp output expected &&
+	cd ..
+'
+
+cat > limit-by-paths/expected << EOF
+blob
+mark :1
+data 4
+foo
+
+blob
+mark :2
+data 3
+hi
+
+reset refs/heads/master
+commit refs/heads/master
+mark :3
+author A U Thor <author@example.com> 1112912713 -0700
+committer C O Mitter <committer@example.com> 1112912713 -0700
+data 12
+Second file
+M 100644 :1 bar
+M 100644 :2 there
+
+EOF
+
+test_expect_failure 'no exact-ref revisions included' '
+	cd limit-by-paths &&
+	git fast-export master~2..master~1 > output &&
+	test_cmp output expected &&
+	cd ..
+'
+
+
 test_expect_success 'set-up a few more tags for tag export tests' '
 	git checkout -f master &&
 	HEAD_TREE=`git show -s --pretty=raw HEAD | grep tree | sed "s/tree //"` &&
@@ -271,8 +359,14 @@ test_expect_success 'set-up a few more tags for tag export tests' '
 	git tag -a tag-obj_tag-obj -m "tagging a tag" tree_tag-obj
 '
 
+test_expect_success 'tree_tag'        '
+	mkdir result &&
+	(cd result && git init) &&
+	git fast-export tree_tag > fe-stream &&
+	(cd result && git fast-import < ../fe-stream)
+'
+
 # NEEDSWORK: not just check return status, but validate the output
-test_expect_success 'tree_tag'        'git fast-export tree_tag'
 test_expect_success 'tree_tag-obj'    'git fast-export tree_tag-obj'
 test_expect_success 'tag-obj_tag'     'git fast-export tag-obj_tag'
 test_expect_success 'tag-obj_tag-obj' 'git fast-export tag-obj_tag-obj'