From 8b24194be6545d43394dbeb9d12c8dbbfc8e223b Mon Sep 17 00:00:00 2001 From: Mark Walters Date: Fri, 4 Jan 2013 13:55:52 +0000 Subject: [PATCH] Xapian Quote tags --- 6f/365a56431308ff80e0f19713d139fa7c25d52a | 216 ++++++++++++++++++++++ 1 file changed, 216 insertions(+) create mode 100644 6f/365a56431308ff80e0f19713d139fa7c25d52a diff --git a/6f/365a56431308ff80e0f19713d139fa7c25d52a b/6f/365a56431308ff80e0f19713d139fa7c25d52a new file mode 100644 index 000000000..ff4132a49 --- /dev/null +++ b/6f/365a56431308ff80e0f19713d139fa7c25d52a @@ -0,0 +1,216 @@ +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 4D7E3431FAF + for ; Fri, 4 Jan 2013 05:55:56 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: -1.098 +X-Spam-Level: +X-Spam-Status: No, score=-1.098 tagged_above=-999 required=5 + tests=[DKIM_ADSP_CUSTOM_MED=0.001, FREEMAIL_FROM=0.001, + NML_ADSP_CUSTOM_MED=1.2, RCVD_IN_DNSWL_MED=-2.3] 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 e1Yd0mtt9-SA for ; + Fri, 4 Jan 2013 05:55:55 -0800 (PST) +Received: from mail2.qmul.ac.uk (mail2.qmul.ac.uk [138.37.6.6]) + (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 91A16431FAE + for ; Fri, 4 Jan 2013 05:55:55 -0800 (PST) +Received: from smtp.qmul.ac.uk ([138.37.6.40]) + by mail2.qmul.ac.uk with esmtp (Exim 4.71) + (envelope-from ) + id 1Tr7kY-0002Ze-12; Fri, 04 Jan 2013 13:55:54 +0000 +Received: from 93-97-24-31.zone5.bethere.co.uk ([93.97.24.31] helo=localhost) + by smtp.qmul.ac.uk with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.69) + (envelope-from ) + id 1Tr7kX-0002Vc-HT; Fri, 04 Jan 2013 13:55:53 +0000 +From: Mark Walters +To: notmuch@notmuchmail.org +Subject: Xapian Quote tags +User-Agent: Notmuch/0.14+236~g1d0044f (http://notmuchmail.org) Emacs/23.4.1 + (x86_64-pc-linux-gnu) +Date: Fri, 04 Jan 2013 13:55:52 +0000 +Message-ID: <878v89hx1z.fsf@qmul.ac.uk> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Sender-Host-Address: 93.97.24.31 +X-QM-SPAM-Info: Sender has good ham record. :) +X-QM-Body-MD5: 2da5113837db2c5d4ff5b044120fdc9b (of first 20000 bytes) +X-SpamAssassin-Score: -1.8 +X-SpamAssassin-SpamBar: - +X-SpamAssassin-Report: The QM spam filters have analysed this message to + determine if it is + spam. We require at least 5.0 points to mark a message as spam. + This message scored -1.8 points. + Summary of the scoring: + * -2.3 RCVD_IN_DNSWL_MED RBL: Sender listed at http://www.dnswl.org/, + * medium trust + * [138.37.6.40 listed in list.dnswl.org] + * 0.0 FREEMAIL_FROM Sender email is commonly abused enduser mail + provider * (markwalters1009[at]gmail.com) + * 0.5 AWL AWL: From: address is in the auto white-list +X-QM-Scan-Virus: ClamAV says the message is clean +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: Fri, 04 Jan 2013 13:55:56 -0000 + + +Hello + +I would like to suggest that we Xapian quote the tags for notmuch +dump/restore. The general view on irc is that we probably want to do +this in the long term and I think it would be nice if we can avoid +changing the dump format a second time. + +One problem is that our current line based parsing cannot cope with +Xapian quoted newlines (which stay newlines). So allow a line to start +with % which means hex-decode the whole line before passing to the main +parser. Thus the query tags etc still need to be Xapian encoded. + +I attach a patch to show roughly what I mean. This is not complete: the +dump routine does not hex encode lines with newlines yet, tests man +pages etc are not updated and it is significantly unpolished. Also there +should be some consolidation between parse_boolean_term and the +xapian_decode routine. + +Despite the above caveats it broadly seems to work. + +Best wishes + +Mark + + + + +>From d518e2be27ff7243ddc156699c2bfc38dec78b43 Mon Sep 17 00:00:00 2001 +From: Mark Walters +Date: Fri, 4 Jan 2013 13:37:42 +0000 +Subject: [PATCH] notmuch dump: xapian quote tags + +--- + notmuch-dump.c | 6 +++--- + tag-util.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++------- + 2 files changed, 49 insertions(+), 10 deletions(-) + +diff --git a/notmuch-dump.c b/notmuch-dump.c +index bf01a39..e94d870 100644 +--- a/notmuch-dump.c ++++ b/notmuch-dump.c +@@ -120,9 +120,9 @@ notmuch_dump_command (unused (void *ctx), int argc, char *argv[]) + if (output_format == DUMP_FORMAT_SUP) { + fputs (tag_str, output); + } else { +- if (hex_encode (notmuch, tag_str, +- &buffer, &buffer_size) != HEX_SUCCESS) { +- fprintf (stderr, "Error: failed to hex-encode tag %s\n", ++ if (make_boolean_term (notmuch, NULL, tag_str, ++ &buffer, &buffer_size)) { ++ fprintf (stderr, "Error: failed to xapian-encode tag %s\n", + tag_str); + return 1; + } +diff --git a/tag-util.c b/tag-util.c +index ca12b3b..7384afa 100644 +--- a/tag-util.c ++++ b/tag-util.c +@@ -31,6 +31,38 @@ line_error (tag_parse_status_t status, + return status; + } + ++static int ++xapian_decode_tag_inplace (char *str, char* tok, size_t *tok_len) ++{ ++ char *pos = str; ++ char *out = str; ++ ++ if (*pos == '"') { ++ int closed = 0; ++ /* Skip the opening quote, find the closing quote, and ++ * un-double doubled internal quotes. */ ++ for (++pos; *pos; ) { ++ if (*pos == '"') { ++ ++pos; ++ if (*pos != '"') { ++ /* Found the closing quote. */ ++ closed = 1; ++ break; ++ } ++ } ++ *out++ = *pos++; ++ } ++ if (! closed || *pos != ' ') ++ return HEX_SYNTAX_ERROR; ++ *tok_len = pos - tok; ++ } else { ++ out = tok + (*tok_len)++; ++ } ++ /* Terminate token */ ++ *out = '\0'; ++ return HEX_SUCCESS; ++} ++ + tag_parse_status_t + parse_tag_line (void *ctx, char *line, + tag_op_flag_t flags, +@@ -60,6 +92,15 @@ parse_tag_line (void *ctx, char *line, + goto DONE; + } + ++ if (*tok == '%') { ++ tok++; ++ if (hex_decode_inplace (tok) != HEX_SUCCESS) { ++ ret = line_error (TAG_PARSE_INVALID, line_for_error, ++ "hex decoding of line failed", ""); ++ goto DONE; ++ } ++ } ++ + tag_op_list_reset (tag_ops); + + /* Parse tags. */ +@@ -89,23 +130,21 @@ parse_tag_line (void *ctx, char *line, + goto DONE; + } + +- /* Terminate, and start next token after terminator. */ +- *(tok + tok_len++) = '\0'; +- + remove = (*tok == '-'); + tag = tok + 1; + +- /* Maybe refuse empty tags. */ ++ /* Maybe refuse empty tags. Note a quoted empty tag is allowed. */ + if (! (flags & TAG_FLAG_BE_GENEROUS) && *tag == '\0') { + ret = line_error (TAG_PARSE_INVALID, line_for_error, + "empty tag"); + goto DONE; + } + +- /* Decode tag. */ +- if (hex_decode_inplace (tag) != HEX_SUCCESS) { ++ /* Find real (quoted) end, terminate, and start next token ++ * after terminator. */ ++ if (xapian_decode_tag_inplace (tag, tok, &tok_len) != HEX_SUCCESS) { + ret = line_error (TAG_PARSE_INVALID, line_for_error, +- "hex decoding of tag %s failed", tag); ++ "xapian decoding of tag %s failed", tag); + goto DONE; + } + +-- +1.7.9.1 + -- 2.26.2