From 0b29bff0982e93af5c734eef457bd97992be882c Mon Sep 17 00:00:00 2001 From: Mark Walters Date: Mon, 31 Dec 2012 12:01:47 +0000 Subject: [PATCH] Re: [PATCH v4 2/5] util: Function to parse boolean term queries --- 13/499b5a34cc4d2ca8e108ae89c80d0ef346028c | 206 ++++++++++++++++++++++ 1 file changed, 206 insertions(+) create mode 100644 13/499b5a34cc4d2ca8e108ae89c80d0ef346028c diff --git a/13/499b5a34cc4d2ca8e108ae89c80d0ef346028c b/13/499b5a34cc4d2ca8e108ae89c80d0ef346028c new file mode 100644 index 000000000..ca397fabd --- /dev/null +++ b/13/499b5a34cc4d2ca8e108ae89c80d0ef346028c @@ -0,0 +1,206 @@ +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 53133431FB6 + for ; Mon, 31 Dec 2012 04:02:00 -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 P1wJhFx4PT9u for ; + Mon, 31 Dec 2012 04:01:56 -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 5BA84431FAF + for ; Mon, 31 Dec 2012 04:01:56 -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 1Tpe3t-0005zv-BZ; Mon, 31 Dec 2012 12:01:45 +0000 +Received: from 188.31.19.240.threembb.co.uk ([188.31.19.240] helo=localhost) + by smtp.qmul.ac.uk with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.69) + (envelope-from ) + id 1Tpe3s-0007gY-Df; Mon, 31 Dec 2012 12:01:45 +0000 +From: Mark Walters +To: Austin Clements , notmuch@notmuchmail.org +Subject: Re: [PATCH v4 2/5] util: Function to parse boolean term queries +In-Reply-To: <1356936162-2589-3-git-send-email-amdragon@mit.edu> +References: <1356936162-2589-1-git-send-email-amdragon@mit.edu> + <1356936162-2589-3-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: Mon, 31 Dec 2012 12:01:47 +0000 +Message-ID: <8738ymv39w.fsf@qmul.ac.uk> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Sender-Host-Address: 188.31.19.240 +X-QM-SPAM-Info: Sender has good ham record. :) +X-QM-Body-MD5: 5f63b2a618e032e83994c2ba766fe734 (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 +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: Mon, 31 Dec 2012 12:02:00 -0000 + +On Mon, 31 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. + +This looks good to me with one concern. Do you need to check that the +three talloc allocations in parse_boolean_term succeed? I think they +could fail in an OOM type situation which I think would cause a seg fault. + +I guess failures in restore are much less important than in dump, and I +don't know how careful notmuch is in general. + + +Best wishes + +Mark + + +> util/string-util.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++ +> util/string-util.h | 15 ++++++++++++ +> 2 files changed, 82 insertions(+) +> +> diff --git a/util/string-util.c b/util/string-util.c +> index e4bea21..52c7781 100644 +> --- a/util/string-util.c +> +++ b/util/string-util.c +> @@ -22,6 +22,8 @@ +> #include "string-util.h" +> #include "talloc.h" +> +> +#include +> + +> char * +> strtok_len (char *s, const char *delim, size_t *len) +> { +> @@ -96,3 +98,68 @@ make_boolean_term (void *ctx, const char *prefix, const char *term, +> +> return 0; +> } +> + +> +static const char* +> +skip_space (const char *str) +> +{ +> + while (*str && isspace (*str)) +> + ++str; +> + return str; +> +} +> + +> +int +> +parse_boolean_term (void *ctx, const char *str, +> + char **prefix_out, char **term_out) +> +{ +> + *prefix_out = *term_out = NULL; +> + +> + /* Parse prefix */ +> + str = skip_space (str); +> + 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; +> + pos = skip_space (pos); +> + 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 (*skip_space (pos)) +> + goto FAIL; +> + /* No trailing text; dup the string so the caller can free +> + * it. */ +> + *term_out = talloc_strndup (ctx, start, pos - start); +> + } +> + return 0; +> + +> + 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..8b9fe50 100644 +> --- a/util/string-util.h +> +++ b/util/string-util.h +> @@ -33,4 +33,19 @@ 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 consisting of a prefix, a colon, and a +> + * term that may be quoted as described for make_boolean_term. If the +> + * term is not quoted, then it ends at the first whitespace or close +> + * parenthesis. str may containing leading or trailing whitespace, +> + * but anything else is considered a parse error. This is compatible +> + * with anything produced by make_boolean_term, and supports a subset +> + * of the quoting styles supported by Xapian (and hence notmuch). +> + * *prefix_out and *term_out will be talloc'd with context ctx. +> + * +> + * Return: 0 on success, non-zero on parse error. +> + */ +> +int +> +parse_boolean_term (void *ctx, const char *str, +> + char **prefix_out, char **term_out); +> + +> #endif +> -- +> 1.7.10.4 -- 2.26.2