From 63656c7ba5607a22a1451377427a3623f23c657e Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 26 Feb 2013 10:19:06 +0100 Subject: [PATCH] Re: [RFC] [PATCH] lib/database.cc: change how the parent of a message is calculated --- 2f/8c2b259df076062443fded8cec7e52175c4c46 | 199 ++++++++++++++++++++++ 1 file changed, 199 insertions(+) create mode 100644 2f/8c2b259df076062443fded8cec7e52175c4c46 diff --git a/2f/8c2b259df076062443fded8cec7e52175c4c46 b/2f/8c2b259df076062443fded8cec7e52175c4c46 new file mode 100644 index 000000000..bc61284da --- /dev/null +++ b/2f/8c2b259df076062443fded8cec7e52175c4c46 @@ -0,0 +1,199 @@ +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 00C21431FB6 + for ; Tue, 26 Feb 2013 01:19:23 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: -0.7 +X-Spam-Level: +X-Spam-Status: No, score=-0.7 tagged_above=-999 required=5 + tests=[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 7lMT0nEj4WZN for ; + Tue, 26 Feb 2013 01:19:20 -0800 (PST) +Received: from mail-we0-f175.google.com (mail-we0-f175.google.com + [74.125.82.175]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 52D14431FAF + for ; Tue, 26 Feb 2013 01:19:20 -0800 (PST) +Received: by mail-we0-f175.google.com with SMTP id x8so3317447wey.6 + for ; Tue, 26 Feb 2013 01:19:17 -0800 (PST) +X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; + d=google.com; s=20120113; + h=x-received:from:to:subject:in-reply-to:references:user-agent:date + :message-id:mime-version:content-type:x-gm-message-state; + bh=fumzV0OKnmDWKk9etUJm2gd9dTO/IAToWlwm722R27Q=; + b=l550UJYCKGunAujYO8aZVnSFVCGKoAEjkAGFiOijNfeyfSOUpnnTw1BDAIpcHNH55o + uqWmLbVztjgJ/wlHaOBcNzGoaElHovcR/O9zZC4sjOCNJujVFcKOuPBJopRTiTibrl6F + vz1LG+9R55TSmuQlQOhEg29SiYFdORNG1PMBKKY99zq0WdDdOAES2RJToAkyE3TPTy7o + 8VOtLmtQNPGYCjBTSPIZXGDJ+HL5Nd4nT+IKAh/mJNoMa6wsurNMeE1HyQPU4ApCMXu4 + /om6T1ohN8cWsBN7Mco+xSshgobofMjDectLbXsTYbaAfMCbO3YUNG7uAel/FhH7avnG + AMPw== +X-Received: by 10.180.92.39 with SMTP id cj7mr17802562wib.19.1361870357808; + Tue, 26 Feb 2013 01:19:17 -0800 (PST) +Received: from localhost ([2001:4b98:dc0:43:216:3eff:fe1b:25f3]) + by mx.google.com with ESMTPS id bj9sm19843333wib.4.2013.02.26.01.19.15 + (version=TLSv1.1 cipher=RC4-SHA bits=128/128); + Tue, 26 Feb 2013 01:19:16 -0800 (PST) +From: Jani Nikula +To: Aaron Ecay , notmuch@notmuchmail.org +Subject: Re: [RFC] [PATCH] lib/database.cc: change how the parent of a message + is calculated +In-Reply-To: <1361836225-17279-1-git-send-email-aaronecay@gmail.com> +References: <1361836225-17279-1-git-send-email-aaronecay@gmail.com> +User-Agent: Notmuch/0.14+259~gdee88db (http://notmuchmail.org) Emacs/23.2.1 + (x86_64-pc-linux-gnu) +Date: Tue, 26 Feb 2013 10:19:06 +0100 +Message-ID: <878v6bjuut.fsf@nikula.org> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Gm-Message-State: + ALoCoQlx3ALbGyQhHxtVa2iEPQQ0nC850x2OiuzgcWKxG64wFqbLyFq+Uzo+nSwk1lSSdYs/S+Xe +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: Tue, 26 Feb 2013 09:19:23 -0000 + +On Tue, 26 Feb 2013, Aaron Ecay wrote: +> 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. + +Hi Aaron, please provide references to a few messages like this. If +available on the notmuch list an id: reference would be best, but +otherwise some archive that allows viewing full message headers or +downloading the full message would be best. + +Thanks, +Jani. + +> +> 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 +> _______________________________________________ +> notmuch mailing list +> notmuch@notmuchmail.org +> http://notmuchmail.org/mailman/listinfo/notmuch -- 2.26.2