From 94a5e88f36abcaa9553a378311561757e477a087 Mon Sep 17 00:00:00 2001 From: Mark Walters Date: Sat, 29 Dec 2012 16:50:51 +0000 Subject: [PATCH] Re: [PATCH v3 2/5] util: Function to parse boolean term queries --- 8b/9a9ebba7d479128cbd1b1d341a5fe377a2d652 | 191 ++++++++++++++++++++++ 1 file changed, 191 insertions(+) create mode 100644 8b/9a9ebba7d479128cbd1b1d341a5fe377a2d652 diff --git a/8b/9a9ebba7d479128cbd1b1d341a5fe377a2d652 b/8b/9a9ebba7d479128cbd1b1d341a5fe377a2d652 new file mode 100644 index 000000000..97c8f1d36 --- /dev/null +++ b/8b/9a9ebba7d479128cbd1b1d341a5fe377a2d652 @@ -0,0 +1,191 @@ +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 7C826431FB6 + for ; Sat, 29 Dec 2012 08:51:02 -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 kZ6ZGevh3uL8 for ; + Sat, 29 Dec 2012 08:50:58 -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 2A211431FAF + for ; Sat, 29 Dec 2012 08:50:58 -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 1TozcY-0000bk-68; Sat, 29 Dec 2012 16:50:52 +0000 +Received: from 94.197.9.104.threembb.co.uk ([94.197.9.104] helo=localhost) + by smtp.qmul.ac.uk with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.69) + (envelope-from ) + id 1TozcW-0000mF-TG; Sat, 29 Dec 2012 16:50:49 +0000 +From: Mark Walters +To: Austin Clements , notmuch@notmuchmail.org +Subject: Re: [PATCH v3 2/5] util: Function to parse boolean term queries +In-Reply-To: <1356719189-2837-3-git-send-email-amdragon@mit.edu> +References: <1356719189-2837-1-git-send-email-amdragon@mit.edu> + <1356719189-2837-3-git-send-email-amdragon@mit.edu> +User-Agent: Notmuch/0.14+236~g1d0044f (http://notmuchmail.org) Emacs/23.4.1 + (x86_64-pc-linux-gnu) +Date: Sat, 29 Dec 2012 16:50:51 +0000 +Message-ID: <87y5ggssyc.fsf@qmul.ac.uk> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Sender-Host-Address: 94.197.9.104 +X-QM-SPAM-Info: Sender has good ham record. :) +X-QM-Body-MD5: df4242471a0c8f99ee5abc9849039f5f (of first 20000 bytes) +X-SpamAssassin-Score: -2.3 +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 -2.3 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) + * -0.0 T_RP_MATCHES_RCVD Envelope sender domain matches handover relay + * domain +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: Sat, 29 Dec 2012 16:51:02 -0000 + + +On Fri, 28 Dec 2012, Austin Clements wrote: +> This parses the subset of Xapian's boolean term quoting rules that are +> used by make_boolean_term. This is provided as a generic string +> utility, but will be used shortly in notmuch restore to parse and +> optimize for ID queries. +> --- +> util/string-util.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++ +> util/string-util.h | 11 +++++++++++ +> 2 files changed, 66 insertions(+) +> +> diff --git a/util/string-util.c b/util/string-util.c +> index e4bea21..83b4953 100644 +> --- a/util/string-util.c +> +++ b/util/string-util.c +> @@ -96,3 +96,58 @@ make_boolean_term (void *ctx, const char *prefix, const char *term, +> +> return 0; +> } +> + +> +int +> +parse_boolean_term (void *ctx, const char *str, +> + char **prefix_out, char **term_out) +> +{ +> + *prefix_out = *term_out = NULL; +> + +> + /* Parse prefix */ +> + const char *pos = strchr (str, ':'); +> + if (! pos) +> + goto FAIL; +> + *prefix_out = talloc_strndup (ctx, str, pos - str); +> + ++pos; +> + +> + /* Implement de-quoting compatible with make_boolean_term. */ +> + if (*pos == '"') { +> + char *out = talloc_array (ctx, char, strlen (pos)); +> + int closed = 0; +> + *term_out = out; +> + /* 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++; +> + } +> + /* Did the term terminate without a closing quote or is there +> + * trailing text after the closing quote? */ +> + if (!closed || *pos) +> + goto FAIL; +> + *out = '\0'; +> + } else { +> + const char *start = pos; +> + /* Check for text after the boolean term. */ +> + while (*pos > ' ' && *pos != ')') +> + ++pos; +> + if (*pos) +> + goto FAIL; +> + /* No trailing text; dup the string so the caller can free +> + * it. */ +> + *term_out = talloc_strdup (ctx, start); +> + } +> + return 0; + +This looks like it will fail if a line contains trailing white space +(and that seemed to be the case from my experiment). Is that wanted? + +If yes we may want to make the error message clearer as I got an error +of the form +Warning: cannot parse query: id:message-id@example.com +and the fact that line contained trailing spaces was not clear. + +> + +> + FAIL: +> + talloc_free (*prefix_out); +> + talloc_free (*term_out); +> + return 1; +> +} +> diff --git a/util/string-util.h b/util/string-util.h +> index b8844a3..43d49d0 100644 +> --- a/util/string-util.h +> +++ b/util/string-util.h +> @@ -33,4 +33,15 @@ char *strtok_len (char *s, const char *delim, size_t *len); +> int make_boolean_term (void *talloc_ctx, const char *prefix, const char *term, +> char **buf, size_t *len); +> +> +/* Parse a boolean term query produced by make_boolean_term, returning +> + * the prefix in *prefix_out and the term in *term_out. *prefix_out +> + * and *term_out will be talloc'd with context ctx. +> + * +> + * Return: 0 on success, non-zero on parse error (including trailing +> + * data in str). +> + */ + +I think it would be worth detailing what requirements a boolean term +here should meet to be parsed. In particular, since make_boolean_term +is more restrictive than Xapian we should say whether this is like +make_boolean_term, like Xapian or somewhere in between. + + +Best wishes + +Mark + + +> +int +> +parse_boolean_term (void *ctx, const char *str, +> + char **prefix_out, char **term_out); +> + +> #endif +> -- +> 1.7.10.4 -- 2.26.2