lib: change parent strategy to use In-Reply-To if it looks sane

As reported by Sean Whitton, there are mailers (in particular the
Debian Bug Tracking System) that have sensible In-Reply-To headers,
but un-useful-for-notmuch References (in particular with the BTS, the
oldest reference is last). I looked at a sample of about 200K
messages, and only about 0.5% these had something other than a single
message-id in In-Reply-To. On this basis, if we see a single
message-id in In-Reply-To, consider that as authoritative.

diff --git a/lib/add-message.cc b/lib/add-message.cc
index f5fac8be751fa2706d09383c07390652e73dc679..da37032c5979cb0eeb1d67621dc9d57bff80a32f 100644 (file)
--- a/lib/add-message.cc
+++ b/lib/add-message.cc
@@ -227,7 +227,7 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
                                           const char **thread_id)
 {
     GHashTable *parents = NULL;
-    const char *refs, *in_reply_to, *in_reply_to_message_id;
+    const char *refs, *in_reply_to, *in_reply_to_message_id, *strict_message_id = NULL;
     const char *last_ref_message_id, *this_message_id;
     GList *l, *keys = NULL;
     notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS;
@@ -242,14 +242,24 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
                                            parents, refs);
 
     in_reply_to = _notmuch_message_file_get_header (message_file, "in-reply-to");
+    if (in_reply_to)
+       strict_message_id = _notmuch_message_id_parse_strict (message,
+                                                             in_reply_to);
+
     in_reply_to_message_id = parse_references (message,
                                               this_message_id,
                                               parents, in_reply_to);
 
-    /* For the parent of this message, use the last message ID of the
-     * References header, if available.  If not, fall back to the
-     * first message ID in the In-Reply-To header. */
-    if (last_ref_message_id) {
+    /* For the parent of this message, use
+     * 1) the In-Reply-To header, if it looks sane, otherwise
+     * 2) the last message ID of the References header, if available.
+     * 3) Otherwise, fall back to the first message ID in
+     * the In-Reply-To header.
+     */
+
+    if (strict_message_id) {
+       _notmuch_message_add_term (message, "replyto", strict_message_id);
+    } else if (last_ref_message_id) {
        _notmuch_message_add_term (message, "replyto",
                                   last_ref_message_id);
     } else if (in_reply_to_message_id) {

diff --git a/test/T510-thread-replies.sh b/test/T510-thread-replies.sh
index 1dfb86c9750ee17ea64510658c2b667e365d3636..5d6bea7ed7ab7fdd3b9d06b4c8002195da9282ab 100755 (executable)
--- a/test/T510-thread-replies.sh
+++ b/test/T510-thread-replies.sh
@@ -210,7 +210,6 @@ EOF
 test_expect_equal_file EXPECTED OUTPUT
 
 test_begin_subtest "trusting reply-to (tree view)"
-test_subtest_known_broken
 test_emacs '(notmuch-tree "id:B00-root@example.org")
            (notmuch-test-wait)
            (test-output)