object-file: introduce function to iterate through objects

We have multiple divergent interfaces to iterate through objects of a
specific backend:

  - `for_each_loose_object()` yields all loose objects.

  - `for_each_packed_object()` (somewhat obviously) yields all packed
    objects.

These functions have different function signatures, which makes it hard
to create a common abstraction layer that covers both of these.

Introduce a new function `odb_source_loose_for_each_object()` to plug
this gap. This function doesn't take any data specific to loose objects,
but instead it accepts a `struct object_info` that will be populated the
exact same as if `odb_source_loose_read_object()` was called.

The benefit of this new interface is that we can continue to pass
backend-specific data, as `struct object_info` contains a union for
these exact use cases. This will allow us to unify how we iterate
through objects across both loose and packed objects in a subsequent
commit.

The `for_each_loose_object()` function continues to exist for now, but
it will be removed at the end of this patch series.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 71 insertions, 0 deletions

diff --git a/object-file.c b/object-file.c
index a651129426..ef2c7618c1 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1801,6 +1801,54 @@ int for_each_loose_object(struct object_database *odb,
 	return 0;
 }
 
+struct for_each_object_wrapper_data {
+	struct odb_source *source;
+	const struct object_info *request;
+	odb_for_each_object_cb cb;
+	void *cb_data;
+};
+
+static int for_each_object_wrapper_cb(const struct object_id *oid,
+				      const char *path,
+				      void *cb_data)
+{
+	struct for_each_object_wrapper_data *data = cb_data;
+
+	if (data->request) {
+		struct object_info oi = *data->request;
+
+		if (read_object_info_from_path(data->source, path, oid, &oi, 0) < 0)
+			return -1;
+
+		return data->cb(oid, &oi, data->cb_data);
+	} else {
+		return data->cb(oid, NULL, data->cb_data);
+	}
+}
+
+int odb_source_loose_for_each_object(struct odb_source *source,
+				     const struct object_info *request,
+				     odb_for_each_object_cb cb,
+				     void *cb_data,
+				     unsigned flags)
+{
+	struct for_each_object_wrapper_data data = {
+		.source = source,
+		.request = request,
+		.cb = cb,
+		.cb_data = cb_data,
+	};
+
+	/* There are no loose promisor objects, so we can return immediately. */
+	if ((flags & ODB_FOR_EACH_OBJECT_PROMISOR_ONLY))
+		return 0;
+	if ((flags & ODB_FOR_EACH_OBJECT_LOCAL_ONLY) && !source->local)
+		return 0;
+
+	return for_each_loose_file_in_source(source, for_each_object_wrapper_cb,
+					     NULL, NULL, &data);
+}
+
 static int append_loose_object(const struct object_id *oid,
 			       const char *path UNUSED,
 			       void *data)
diff --git a/object-file.h b/object-file.h
index 2acf19fb91..5b9641cd89 100644
--- a/object-file.h
+++ b/object-file.h
@@ -137,6 +137,17 @@ int for_each_loose_object(struct object_database *odb,
 			  each_loose_object_fn, void *,
 			  enum odb_for_each_object_flags flags);
 
+/*
+ * Iterate through all loose objects in the given object database source and
+ * invoke the callback function for each of them. If given, the object info
+ * will be populated with the object's data as if you had called
+ * `odb_source_loose_read_object_info()` on the object.
+ */
+int odb_source_loose_for_each_object(struct odb_source *source,
+				     const struct object_info *request,
+				     odb_for_each_object_cb cb,
+				     void *cb_data,
+				     unsigned flags);
 
 /**
  * format_object_header() is a thin wrapper around s xsnprintf() that
diff --git a/odb.h b/odb.h
index 74503addf1..f97f249580 100644
--- a/odb.h
+++ b/odb.h
@@ -463,6 +463,18 @@ enum odb_for_each_object_flags {
 	ODB_FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS = (1<<4),
 };
 
+/*
+ * A callback function that can be used to iterate through objects. If given,
+ * the optional `oi` parameter will be populated the same as if you would call
+ * `odb_read_object_info()`.
+ *
+ * Returning a non-zero error code will cause iteration to abort. The error
+ * code will be propagated.
+ */
+typedef int (*odb_for_each_object_cb)(const struct object_id *oid,
+				      struct object_info *oi,
+				      void *cb_data);
+
 enum {
 	/*
 	 * By default, `odb_write_object()` does not actually write anything