From 0b6064a62a35850c64cf64d8f23bf0843f12f54c Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 3 Jan 2013 18:19:02 +0100 Subject: [PATCH] Re: [PATCH v4 3/5] dump: Disallow \n in message IDs --- fe/4c5441f39a9d0432298c6df54dc3d3e79b5782 | 138 ++++++++++++++++++++++ 1 file changed, 138 insertions(+) create mode 100644 fe/4c5441f39a9d0432298c6df54dc3d3e79b5782 diff --git a/fe/4c5441f39a9d0432298c6df54dc3d3e79b5782 b/fe/4c5441f39a9d0432298c6df54dc3d3e79b5782 new file mode 100644 index 000000000..f36b60e74 --- /dev/null +++ b/fe/4c5441f39a9d0432298c6df54dc3d3e79b5782 @@ -0,0 +1,138 @@ +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 D66A0431FAF + for ; Thu, 3 Jan 2013 09:19:12 -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 GLIaA6Xn33Ie for ; + Thu, 3 Jan 2013 09:19:12 -0800 (PST) +Received: from mail-bk0-f51.google.com (mail-bk0-f51.google.com + [209.85.214.51]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 33BA6431FAE + for ; Thu, 3 Jan 2013 09:19:12 -0800 (PST) +Received: by mail-bk0-f51.google.com with SMTP id ik5so6861629bkc.38 + for ; Thu, 03 Jan 2013 09:19:11 -0800 (PST) +X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; + d=google.com; s=20120113; + h=x-received:from:to:cc:subject:in-reply-to:references:user-agent + :date:message-id:mime-version:content-type:x-gm-message-state; + bh=weg9zmvlX5oI7ii9MuCExFpek3nkOZ49dPt7RsXx6cM=; + b=OHlGToXKfiJJrf2nxkR+mh9yORAKv+N9NLCPz+SHIsz8FAU8agsIvQIn2nWThSc4q3 + TquirsvzIG54BI1gXeZCSP4IAicW3MCm69rj96gJv2qrzr5dDJKNCTYcG4PAtFg888q0 + jM4zZN99uHVtuigO6Mo5GtaO1L+Xv+Vb994cL1Ww/8ZP2l7r9R0SM0YlKR8SVo6Vt9uG + g5/1uEnoF/JDSEztPOlKfJf2cSSIGRQRDAEyZVKDK7bsEG0eohlR4G5ItAXRYpZLIg2a + rp4pEMG40nxi83sQjMxBDKfIffEvBSffGQ7VOZBH02AWAG7t1rOm5DHJ0k3mj1WYS2AJ + dSDQ== +X-Received: by 10.204.148.134 with SMTP id p6mr23785251bkv.75.1357233550728; + Thu, 03 Jan 2013 09:19:10 -0800 (PST) +Received: from localhost ([2001:4b98:dc0:43:216:3eff:fe1b:25f3]) + by mx.google.com with ESMTPS id u3sm34662405bkw.9.2013.01.03.09.19.08 + (version=SSLv3 cipher=OTHER); Thu, 03 Jan 2013 09:19:09 -0800 (PST) +From: Jani Nikula +To: Austin Clements , notmuch@notmuchmail.org +Subject: Re: [PATCH v4 3/5] dump: Disallow \n in message IDs +In-Reply-To: <1356936162-2589-4-git-send-email-amdragon@mit.edu> +References: <1356936162-2589-1-git-send-email-amdragon@mit.edu> + <1356936162-2589-4-git-send-email-amdragon@mit.edu> +User-Agent: Notmuch/0.14+235~gdaf492b (http://notmuchmail.org) Emacs/23.2.1 + (x86_64-pc-linux-gnu) +Date: Thu, 03 Jan 2013 18:19:02 +0100 +Message-ID: <87sj6igp6h.fsf@nikula.org> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Gm-Message-State: + ALoCoQk7dkZ4EVax45iSmdEH4CpjQoyF79IJK+j57UHP5ztnuKHF52mVUAjLBePfNwxZ+Z4o8c7c +Cc: tomi.ollila@iki.fi +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: Thu, 03 Jan 2013 17:19:13 -0000 + +On Mon, 31 Dec 2012, Austin Clements wrote: +> When we switch to using regular Xapian queries in the dump format, \n +> will cause problems, so we disallow it. Specially, while Xapian can +> quote and parse queries containing \n without difficultly, quoted +> queries containing \n still span multiple lines, which breaks the +> line-orientedness of the dump format. Strictly speaking, we could +> still round-trip these, but it would significantly complicate restore +> as well as scripts that deal with tag dumps. This complexity would +> come at absolutely no benefit: because of the RFC 2822 unfolding +> rules, no amount of standards negligence can produce a message with a +> message ID containing a line break (not even Outlook can do it!). +> +> Hence, we simply disallow it. +> --- +> notmuch-dump.c | 9 +++++++++ +> test/random-corpus.c | 4 +++- +> 2 files changed, 12 insertions(+), 1 deletion(-) +> +> diff --git a/notmuch-dump.c b/notmuch-dump.c +> index d2dad40..29d79da 100644 +> --- a/notmuch-dump.c +> +++ b/notmuch-dump.c +> @@ -132,6 +132,15 @@ notmuch_dump_command (unused (void *ctx), int argc, char *argv[]) +> if (output_format == DUMP_FORMAT_SUP) { +> fputs (")\n", output); +> } else { +> + if (strchr (message_id, '\n')) { +> + /* This will produce a line break in the output, which +> + * would be difficult to handle in tools. However, +> + * it's also impossible to produce an email containing +> + * a line break in a message ID because of unfolding, +> + * so we can safely disallow it. */ +> + fprintf (stderr, "Error: cannot dump message id containing line break: %s\n", message_id); +> + return 1; + +How about just skipping the message in the dump, with a warning, instead +of bailing out? If the user is desperate to do a backup for whatever +reason, I don't think it's a good idea to require deleting the message +from the db before dump can succeed. The fs holding the db might be +remounted ro and all that. + +And perhaps the message id in the error message should be wrapped in +quotes, because it will span multiple lines due to having a +newline... ;) + +Otherwise, LGTM. + +Jani. + +> + } +> if (hex_encode (notmuch, message_id, +> &buffer, &buffer_size) != HEX_SUCCESS) { +> fprintf (stderr, "Error: failed to hex-encode msg-id %s\n", +> diff --git a/test/random-corpus.c b/test/random-corpus.c +> index f354d4b..8b7748e 100644 +> --- a/test/random-corpus.c +> +++ b/test/random-corpus.c +> @@ -96,7 +96,9 @@ random_utf8_string (void *ctx, size_t char_count) +> buf = talloc_realloc (ctx, buf, gchar, buf_size); +> } +> +> - randomchar = random_unichar (); +> + do { +> + randomchar = random_unichar (); +> + } while (randomchar == '\n'); +> +> written = g_unichar_to_utf8 (randomchar, buf + offset); +> +> -- +> 1.7.10.4 -- 2.26.2