aboutsummaryrefslogtreecommitdiff
path: root/lib/add-message.cc
diff options
context:
space:
mode:
authorDavid Bremner <david@tethera.net>2018-08-30 08:29:15 -0300
committerDavid Bremner <david@tethera.net>2018-09-06 08:07:13 -0300
commit87934c432c4bee9df09f268a3f05933c59c2caf1 (patch)
tree879593fcb901a83e6850f6a53c796231075ab2fa /lib/add-message.cc
parentb31e44c678bf3bfe81bcc5f159e627551f12700f (diff)
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.
Diffstat (limited to 'lib/add-message.cc')
-rw-r--r--lib/add-message.cc20
1 files changed, 15 insertions, 5 deletions
diff --git a/lib/add-message.cc b/lib/add-message.cc
index f5fac8be..da37032c 100644
--- 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) {