From: Jesse Rosenthal <jrosenthal@jhu.edu>
To: notmuch@notmuchmail.org
Subject: [PATCH v2] Name thread based on matching msgs instead of first msg.
In-Reply-To: <87sk7rloo4.fsf@jhu.edu>
References: <87sk7rloo4.fsf@jhu.edu>
Date: Sat, 17 Apr 2010 13:59:22 -0400
Message-ID: <87eiieez9h.fsf@jhu.edu>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Precedence: list

At the moment all threads are named based on the name of the first message
in the thread. However, this can cause problems if people either start
new threads by replying-all (as unfortunately, many out there do) or
change the subject of their mails to reflect a shift in a thread on a
list.

This patch names threads based on (a) matches for the query, and (b) the
search order. If the search order is oldest-first (as in the default
inbox) it chooses the oldest matching message as the subject. If the
search order is newest-first it chooses the newest one.

Reply prefixes ("Re: ", "Aw: ", "Sv: ", "Vs: ") are ignored
(case-insensitively) so a Re: won't change the subject.

Note that this adds a "sort" argument to _notmuch_thread_create and
_thread_add_matched_message, so that when constructing the thread we can
be aware of the sort order.

Signed-off-by: Jesse Rosenthal <jrosenthal@jhu.edu>
---
This patch is rebased against current master, and offered for inclusion
in 0.3.

This patch is necessary for me to keep track of my mail, based on the
emailing habits of my correspondents. If others much prefer the original
behavior, I would still request that this feature be a configurable
option, even if not the default.

 lib/notmuch-private.h |    3 ++-
 lib/query.cc          |    3 ++-
 lib/thread.cc         |   32 ++++++++++++++++++++++++++++----
 3 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/lib/notmuch-private.h b/lib/notmuch-private.h
index d52d84d..94cce1b 100644
--- a/lib/notmuch-private.h
+++ b/lib/notmuch-private.h
@@ -205,7 +205,8 @@ notmuch_thread_t *
 _notmuch_thread_create (void *ctx,
 			notmuch_database_t *notmuch,
 			const char *thread_id,
-			const char *query_string);
+			const char *query_string,
+			notmuch_sort_t sort);
 
 /* message.cc */
 
diff --git a/lib/query.cc b/lib/query.cc
index 10f8dc8..3e20f59 100644
--- a/lib/query.cc
+++ b/lib/query.cc
@@ -299,7 +299,8 @@ notmuch_threads_get (notmuch_threads_t *threads)
     return _notmuch_thread_create (threads->query,
 				   threads->query->notmuch,
 				   threads->thread_id,
-				   threads->query->query_string);
+				   threads->query->query_string,
+				   threads->query->sort);
 }
 
 void
diff --git a/lib/thread.cc b/lib/thread.cc
index 3aa9d48..5bf8354 100644
--- a/lib/thread.cc
+++ b/lib/thread.cc
@@ -129,7 +129,8 @@ _thread_add_message (notmuch_thread_t *thread,
 
 static void
 _thread_add_matched_message (notmuch_thread_t *thread,
-			     notmuch_message_t *message)
+			     notmuch_message_t *message,
+			     notmuch_sort_t sort)
 {
     time_t date;
     notmuch_message_t *hashed_message;
@@ -142,6 +143,28 @@ _thread_add_matched_message (notmuch_thread_t *thread,
     if (date > thread->newest || ! thread->matched_messages)
 	thread->newest = date;
 
+    const char *subject;
+    const char *cleaned_subject;
+
+    subject = notmuch_message_get_header (message, "subject");
+
+    if ((strncasecmp (subject, "Re: ", 4) == 0) ||
+	(strncasecmp (subject, "Aw: ", 4) == 0) ||
+	(strncasecmp (subject, "Vs: ", 4) == 0) ||
+	(strncasecmp (subject, "Sv: ", 4) == 0)) {
+
+	cleaned_subject = talloc_strndup (thread,
+					  subject + 4,
+					  strlen(subject) - 4);
+    } else {
+	cleaned_subject = talloc_strdup (thread, subject);
+    }
+
+    if ((sort == NOTMUCH_SORT_OLDEST_FIRST && date <= thread->newest) ||
+	(sort != NOTMUCH_SORT_OLDEST_FIRST && date == thread->newest)) {
+	thread->subject = talloc_strdup (thread, cleaned_subject);
+    }
+
     thread->matched_messages++;
 
     if (g_hash_table_lookup_extended (thread->message_hash,
@@ -209,7 +232,8 @@ notmuch_thread_t *
 _notmuch_thread_create (void *ctx,
 			notmuch_database_t *notmuch,
 			const char *thread_id,
-			const char *query_string)
+			const char *query_string,
+			notmuch_sort_t sort)
 {
     notmuch_thread_t *thread;
     const char *thread_id_query_string;
@@ -296,7 +320,7 @@ _notmuch_thread_create (void *ctx,
 	_thread_add_message (thread, message);
 
 	if (! matched_is_subset_of_thread)
-	    _thread_add_matched_message (thread, message);
+	    _thread_add_matched_message (thread, message, sort);
 
 	_notmuch_message_close (message);
     }
@@ -323,7 +347,7 @@ _notmuch_thread_create (void *ctx,
 	     notmuch_messages_move_to_next (messages))
 	{
 	    message = notmuch_messages_get (messages);
-	    _thread_add_matched_message (thread, message);
+	    _thread_add_matched_message (thread, message, sort);
 	    _notmuch_message_close (message);
 	}
 
-- 
1.6.3.3