From: Aaron Ecay Date: Mon, 25 Feb 2013 23:50:25 +0000 (+1900) Subject: [RFC] [PATCH] lib/database.cc: change how the parent of a message is calculated X-Git-Url: http://git.tremily.us/gitweb.cgi?a=commitdiff_plain;h=0cf77f687bd0779c72314ecf2fceff6624d11a5b;p=notmuch-archives.git [RFC] [PATCH] lib/database.cc: change how the parent of a message is calculated --- diff --git a/ec/f54df7185e899a009f24435e1fc4bf882a3f51 b/ec/f54df7185e899a009f24435e1fc4bf882a3f51 new file mode 100644 index 000000000..3785350b3 --- /dev/null +++ b/ec/f54df7185e899a009f24435e1fc4bf882a3f51 @@ -0,0 +1,178 @@ +Return-Path: +X-Original-To: notmuch@notmuchmail.org +Delivered-To: notmuch@notmuchmail.org +Received: from localhost (localhost [127.0.0.1]) + by olra.theworths.org (Postfix) with ESMTP id 3D002431FB6 + for ; Mon, 25 Feb 2013 15:50:50 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: -0.799 +X-Spam-Level: +X-Spam-Status: No, score=-0.799 tagged_above=-999 required=5 + tests=[DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, + FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_LOW=-0.7] autolearn=disabled +Received: from olra.theworths.org ([127.0.0.1]) + by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) + with ESMTP id Idp4XA5TlSoJ for ; + Mon, 25 Feb 2013 15:50:48 -0800 (PST) +Received: from mail-qa0-f43.google.com (mail-qa0-f43.google.com + [209.85.216.43]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 28145431FAF + for ; Mon, 25 Feb 2013 15:50:48 -0800 (PST) +Received: by mail-qa0-f43.google.com with SMTP id dx4so1998837qab.16 + for ; Mon, 25 Feb 2013 15:50:46 -0800 (PST) +DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; + h=x-received:from:to:subject:date:message-id:x-mailer; + bh=Gb97bSBCXF90gLJGKBgLDpgYym8VnFeXujv5M97o9x4=; + b=JBIhP3PVm+K6TEtLSNMpWdiQw47wdDy8cC5qTluNPjMfo2j6nLMRlYGcUBdS1P0fEn + csEt6PN0FqXyrhcR1QTKPPvY7exswlndQ1jn9i6dae714hBL+na0gOZ6u+8+5vcZ+SAe + z+5pyTkZwLDZMJy2If9KXFpJJN71RiOkv0LDD3ULM11mscKo3RAVtLMkQoQTsE4CJPcq + Jqio7PckpojytDDFJfl8Eehw2J2pnXHtzF/0Q5TJb6lieK7UFVfGBzdRTFkKhlrM9xAd + LZQUU9BI6GXelR3KSkrUchsJZB6ZBZ0B7ikfAMQ6bFh3Lld/Ka1eSxosSgE2xR++obR4 + jJ1w== +X-Received: by 10.49.96.33 with SMTP id dp1mr16646678qeb.60.1361836245427; + Mon, 25 Feb 2013 15:50:45 -0800 (PST) +Received: from localhost.localdomain + (vagvlan532.239.wlan.wireless-pennnet.upenn.edu. [128.91.71.113]) + by mx.google.com with ESMTPS id hr3sm19437068qab.4.2013.02.25.15.50.39 + (version=TLSv1.2 cipher=ECDHE-RSA-RC4-SHA bits=128/128); + Mon, 25 Feb 2013 15:50:44 -0800 (PST) +From: Aaron Ecay +To: notmuch@notmuchmail.org +Subject: [RFC] [PATCH] lib/database.cc: change how the parent of a message is + calculated +Date: Mon, 25 Feb 2013 18:50:25 -0500 +Message-Id: <1361836225-17279-1-git-send-email-aaronecay@gmail.com> +X-Mailer: git-send-email 1.8.1.4 +X-BeenThere: notmuch@notmuchmail.org +X-Mailman-Version: 2.1.13 +Precedence: list +List-Id: "Use and development of the notmuch mail system." + +List-Unsubscribe: , + +List-Archive: +List-Post: +List-Help: +List-Subscribe: , + +X-List-Received-Date: Mon, 25 Feb 2013 23:50:50 -0000 + +Presently, the code which finds the parent of a message as it is being +added to the database assumes that the first Message-ID-like substring +of the In-Reply-To header is the parent Message ID. Some mail clients, +however, put stuff other than the Message-ID of the parent in the +In-Reply-To header, such as the email address of the sender of the +parent. This can fool notmuch. + +The updated algorithm prefers the last Message ID in the References +header. The References header lists messages oldest-first, so the last +Message ID is the parent (RFC2822, p. 24). The References header is +also less likely to be in a non-standard +syntax (http://cr.yp.to/immhf/thread.html, +http://www.jwz.org/doc/threading.html). In case the References header +is not to be found, fall back to the old behavior. +--- + +I especially notice this problem on public mailing lists, where +certain people's messages always cause an "out-dent" of the threading, +instead of being nested under whichever message they are replies to. + +Technically, putting non-Message-ID crud in the In-Reply-To field is a +violation of RFC2822, but it appears that in practice the References +header is respected more often than the In-Reply-To one. + + lib/database.cc | 30 ++++++++++++++++++++++-------- + 1 file changed, 22 insertions(+), 8 deletions(-) + +diff --git a/lib/database.cc b/lib/database.cc +index 91d4329..cbf33ae 100644 +--- a/lib/database.cc ++++ b/lib/database.cc +@@ -501,8 +501,10 @@ _parse_message_id (void *ctx, const char *message_id, const char **next) + * 'message_id' in the result (to avoid mass confusion when a single + * message references itself cyclically---and yes, mail messages are + * not infrequent in the wild that do this---don't ask me why). ++ * ++ * Return the last reference parsed. + */ +-static void ++static char * + parse_references (void *ctx, + const char *message_id, + GHashTable *hash, +@@ -511,7 +513,7 @@ parse_references (void *ctx, + char *ref; + + if (refs == NULL || *refs == '\0') +- return; ++ return NULL; + + while (*refs) { + ref = _parse_message_id (ctx, refs, &refs); +@@ -519,6 +521,8 @@ parse_references (void *ctx, + if (ref && strcmp (ref, message_id)) + g_hash_table_insert (hash, ref, NULL); + } ++ ++ return ref; + } + + notmuch_status_t +@@ -1365,7 +1369,7 @@ _notmuch_database_generate_doc_id (notmuch_database_t *notmuch) + notmuch->last_doc_id++; + + if (notmuch->last_doc_id == 0) +- INTERNAL_ERROR ("Xapian document IDs are exhausted.\n"); ++ INTERNAL_ERROR ("Xapian document IDs are exhausted.\n"); + + return notmuch->last_doc_id; + } +@@ -1509,7 +1513,7 @@ _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, *last_ref_message_id; + GList *l, *keys = NULL; + notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; + +@@ -1517,21 +1521,31 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch, + _my_talloc_free_for_g_hash, NULL); + + refs = notmuch_message_file_get_header (message_file, "references"); +- parse_references (message, notmuch_message_get_message_id (message), +- parents, refs); ++ last_ref_message_id = parse_references (message, ++ notmuch_message_get_message_id (message), ++ parents, refs); + + in_reply_to = notmuch_message_file_get_header (message_file, "in-reply-to"); + parse_references (message, notmuch_message_get_message_id (message), + parents, in_reply_to); + +- /* Carefully avoid adding any self-referential in-reply-to term. */ + in_reply_to_message_id = _parse_message_id (message, in_reply_to, NULL); ++ /* If the parent message ID from the Reply-To and References ++ * headers are different, use the References one. This is because ++ * the Reply-To header is more likely to be in an non-standard ++ * format. */ ++ if (in_reply_to_message_id && ++ last_ref_message_id && ++ strcmp (last_ref_message_id, in_reply_to_message_id)) { ++ in_reply_to_message_id = last_ref_message_id; ++ } ++ /* Carefully avoid adding any self-referential in-reply-to term. */ + if (in_reply_to_message_id && + strcmp (in_reply_to_message_id, + notmuch_message_get_message_id (message))) + { + _notmuch_message_add_term (message, "replyto", +- _parse_message_id (message, in_reply_to, NULL)); ++ in_reply_to_message_id); + } + + keys = g_hash_table_get_keys (parents); +-- +1.8.1.4