fsck: detect gitmodules files

In preparation for performing fsck checks on .gitmodules
files, this commit plumbs in the actual detection of the
files. Note that unlike most other fsck checks, this cannot
be a property of a single object: we must know that the
object is found at a ".gitmodules" path at the root tree of
a commit.

Since the fsck code only sees one object at a time, we have
to mark the related objects to fit the puzzle together. When
we see a commit we mark its tree as a root tree, and when
we see a root tree with a .gitmodules file, we mark the
corresponding blob to be checked.

In an ideal world, we'd check the objects in topological
order: commits followed by trees followed by blobs. In that
case we can avoid ever loading an object twice, since all
markings would be complete by the time we get to the marked
objects. And indeed, if we are checking a single packfile,
this is the order in which Git will generally write the
objects. But we can't count on that:

  1. git-fsck may show us the objects in arbitrary order
     (loose objects are fed in sha1 order, but we may also
     have multiple packs, and we process each pack fully in
     sequence).

  2. The type ordering is just what git-pack-objects happens
     to write now. The pack format does not require a
     specific order, and it's possible that future versions
     of Git (or a custom version trying to fool official
     Git's fsck checks!) may order it differently.

  3. We may not even be fscking all of the relevant objects
     at once. Consider pushing with transfer.fsckObjects,
     where one push adds a blob at path "foo", and then a
     second push adds the same blob at path ".gitmodules".
     The blob is not part of the second push at all, but we
     need to mark and check it.

So in the general case, we need to make up to three passes
over the objects: once to make sure we've seen all commits,
then once to cover any trees we might have missed, and then
a final pass to cover any .gitmodules blobs we found in the
second pass.

We can simplify things a bit by loosening the requirement
that we find .gitmodules only at root trees. Technically
a file like "subdir/.gitmodules" is not parsed by Git, but
it's not unreasonable for us to declare that Git is aware of
all ".gitmodules" files and make them eligible for checking.
That lets us drop the root-tree requirement, which
eliminates one pass entirely. And it makes our worst case
much better: instead of potentially queueing every root tree
to be re-examined, the worst case is that we queue each
unique .gitmodules blob for a second look.

This patch just adds the boilerplate to find .gitmodules
files. The actual content checks will come in a subsequent
commit.

Signed-off-by: Jeff King <peff@peff.net>

fsck.c

@@ -10,6 +10,10 @@
 #include "utf8.h"
 #include "sha1-array.h"
 #include "decorate.h"
+#include "oidset.h"
+
+static struct oidset gitmodules_found = OIDSET_INIT;
+static struct oidset gitmodules_done = OIDSET_INIT;
 
 #define FSCK_FATAL -1
 #define FSCK_INFO -2
@@ -44,6 +48,7 @@
 	FUNC(MISSING_TAG_ENTRY, ERROR) \
 	FUNC(MISSING_TAG_OBJECT, ERROR) \
 	FUNC(MISSING_TREE, ERROR) \
+	FUNC(MISSING_TREE_OBJECT, ERROR) \
 	FUNC(MISSING_TYPE, ERROR) \
 	FUNC(MISSING_TYPE_ENTRY, ERROR) \
 	FUNC(MULTIPLE_AUTHORS, ERROR) \
@@ -51,6 +56,8 @@
 	FUNC(TREE_NOT_SORTED, ERROR) \
 	FUNC(UNKNOWN_TYPE, ERROR) \
 	FUNC(ZERO_PADDED_DATE, ERROR) \
+	FUNC(GITMODULES_MISSING, ERROR) \
+	FUNC(GITMODULES_BLOB, ERROR) \
 	/* warnings */ \
 	FUNC(BAD_FILEMODE, WARN) \
 	FUNC(EMPTY_NAME, WARN) \
@@ -563,6 +570,10 @@ static int fsck_tree(struct tree *item, struct fsck_options *options)
 		has_dotdot |= !strcmp(name, "..");
 		has_dotgit |= is_hfs_dotgit(name) || is_ntfs_dotgit(name);
 		has_zero_pad |= *(char *)desc.buffer == '0';
+
+		if (is_hfs_dotgitmodules(name) || is_ntfs_dotgitmodules(name))
+			oidset_insert(&gitmodules_found, oid);
+
 		if (update_tree_entry_gently(&desc)) {
 			retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
 			break;
@@ -936,3 +947,50 @@ int fsck_error_function(struct fsck_options *o,
 	error("object %s: %s", describe_object(o, obj), message);
 	return 1;
 }
+
+int fsck_finish(struct fsck_options *options)
+{
+	int ret = 0;
+	struct oidset_iter iter;
+	const struct object_id *oid;
+
+	oidset_iter_init(&gitmodules_found, &iter);
+	while ((oid = oidset_iter_next(&iter))) {
+		struct blob *blob;
+		enum object_type type;
+		unsigned long size;
+		char *buf;
+
+		if (oidset_contains(&gitmodules_done, oid))
+			continue;
+
+		blob = lookup_blob(oid);
+		if (!blob) {
+			ret |= report(options, &blob->object,
+				      FSCK_MSG_GITMODULES_BLOB,
+				      "non-blob found at .gitmodules");
+			continue;
+		}
+
+		buf = read_sha1_file(oid->hash, &type, &size);
+		if (!buf) {
+			ret |= report(options, &blob->object,
+				      FSCK_MSG_GITMODULES_MISSING,
+				      "unable to read .gitmodules blob");
+			continue;
+		}
+
+		if (type == OBJ_BLOB)
+			ret |= fsck_blob(blob, buf, size, options);
+		else
+			ret |= report(options, &blob->object,
+				      FSCK_MSG_GITMODULES_BLOB,
+				      "non-blob found at .gitmodules");
+		free(buf);
+	}
+
+
+	oidset_clear(&gitmodules_found);
+	oidset_clear(&gitmodules_done);
+	return ret;
+}

fsck.h

@@ -53,4 +53,11 @@ int fsck_walk(struct object *obj, void *data, struct fsck_options *options);
 int fsck_object(struct object *obj, void *data, unsigned long size,
 	struct fsck_options *options);
 
+/*
+ * Some fsck checks are context-dependent, and may end up queued; run this
+ * after completing all fsck_object() calls in order to resolve any remaining
+ * checks.
+ */
+int fsck_finish(struct fsck_options *options);
+
 #endif