This is mainly to lay out the structure of the final code. The problem
isn't really solved yet, although some very simple cases are
better (hence the fixed test). We need two passes through the messages
because we need to be careful not to re-parent too many messages and
end up without any toplevel messages.
---
 lib/thread.cc               | 43 +++++++++++++++++++++++++++++++++++--
 test/T510-thread-replies.sh |  1 -
 2 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/lib/thread.cc b/lib/thread.cc
index 8074b625..72c447ef 100644
--- a/lib/thread.cc
+++ b/lib/thread.cc
@@ -407,22 +407,52 @@ _parent_via_in_reply_to (notmuch_thread_t *thread, notmuch_message_t *message) {
     }
 }
 
+static void
+_parent_or_toplevel (notmuch_thread_t *thread, notmuch_message_t *message)
+{
+    bool found = false;
+    notmuch_message_t *parent = NULL;
+    const notmuch_string_list_t *references =
+	_notmuch_message_get_references (message);
+    for (notmuch_string_node_t *ref_node = references->head;
+	 ! found && ref_node; ref_node = ref_node->next) {
+	if ((found = g_hash_table_lookup_extended (thread->message_hash,
+						   ref_node->string, NULL,
+						   (void **) &parent))) {
+	    _notmuch_message_add_reply (parent, message);
+	}
+    }
+    if (! found)
+	_notmuch_message_list_add_message (thread->toplevel_list, message);
+}
+
 static void
 _resolve_thread_relationships (notmuch_thread_t *thread)
 {
     notmuch_message_node_t *node, *first_node;
     notmuch_message_t *message;
+    void *local;
+    notmuch_message_list_t *maybe_toplevel_list;
 
     first_node = thread->message_list->head;
     if (! first_node)
 	return;
 
+    local = talloc_new (thread);
+    maybe_toplevel_list = _notmuch_message_list_create (local);
+
     for (node = first_node->next; node; node = node->next) {
 	message = node->message;
 	if (! _parent_via_in_reply_to (thread, message))
-	    _notmuch_message_list_add_message (thread->toplevel_list, message);
+	    _notmuch_message_list_add_message (maybe_toplevel_list, message);
     }
 
+    for (notmuch_messages_t *roots = _notmuch_messages_create (maybe_toplevel_list);
+	 notmuch_messages_valid (roots);
+	 notmuch_messages_move_to_next (roots)) {
+	notmuch_message_t *message = notmuch_messages_get (roots);
+	_parent_or_toplevel (thread, message);
+    }
     /*
      * if we reach the end of the list without finding a top-level
      * message, that means the thread is a cycle (or set of cycles)
@@ -433,7 +463,15 @@ _resolve_thread_relationships (notmuch_thread_t *thread)
 	message = first_node->message;
 	if (! thread->toplevel_list->head ||
 	    ! _parent_via_in_reply_to (thread, message)) {
-	    _notmuch_message_list_add_message (thread->toplevel_list, message);
+	    /*
+	     * If the oldest message happens to be in-reply-to a
+	     * missing message, we only check for references if there
+	     * is some other candidate for root message.
+	     */
+	    if (thread->toplevel_list->head)
+		_parent_or_toplevel (thread, message);
+	    else
+		_notmuch_message_list_add_message (thread->toplevel_list, message);
 	}
     }
 
@@ -453,6 +491,7 @@ _resolve_thread_relationships (notmuch_thread_t *thread)
      * correctly in the thread even when an intermediate message is
      * missing from the thread.
      */
+    talloc_free (local);
 }
 
 /* Create a new notmuch_thread_t object by finding the thread
diff --git a/test/T510-thread-replies.sh b/test/T510-thread-replies.sh
index 72af50df..c244054a 100755
--- a/test/T510-thread-replies.sh
+++ b/test/T510-thread-replies.sh
@@ -167,7 +167,6 @@ test_expect_equal_json "$output" "$expected"
 add_email_corpus threading
 
 test_begin_subtest "reply to ghost"
-test_subtest_known_broken
 notmuch show --entire-thread=true id:000-real-root@example.org | grep ^Subject: | head -1  > OUTPUT
 cat <<EOF > EXPECTED
 Subject: root message
-- 
2.18.0

_______________________________________________
notmuch mailing list
notmuch@notmuchmail.org
https://notmuchmail.org/mailman/listinfo/notmuch