From 97d429bfb5f6d2f78128d6c4cc77aefab653a650 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 3 Jan 2013 18:09:08 +0100 Subject: [PATCH] Re: [PATCH v4 2/5] util: Function to parse boolean term queries --- dc/5911b26dd84600c03c8f128277eecbe661f9ed | 206 ++++++++++++++++++++++ 1 file changed, 206 insertions(+) create mode 100644 dc/5911b26dd84600c03c8f128277eecbe661f9ed diff --git a/dc/5911b26dd84600c03c8f128277eecbe661f9ed b/dc/5911b26dd84600c03c8f128277eecbe661f9ed new file mode 100644 index 000000000..685c6b6aa --- /dev/null +++ b/dc/5911b26dd84600c03c8f128277eecbe661f9ed @@ -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 DADF0431FAF + for ; Thu, 3 Jan 2013 09:09:19 -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 mZVqrZHqFyow for ; + Thu, 3 Jan 2013 09:09:19 -0800 (PST) +Received: from mail-we0-f179.google.com (mail-we0-f179.google.com + [74.125.82.179]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 20B09431FAE + for ; Thu, 3 Jan 2013 09:09:19 -0800 (PST) +Received: by mail-we0-f179.google.com with SMTP id r6so7149381wey.38 + for ; Thu, 03 Jan 2013 09:09:17 -0800 (PST) +X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; + d=google.com; s=20120113; + h=x-received:from:to:cc:subject:in-reply-to:references:user-agent + :date:message-id:mime-version:content-type:x-gm-message-state; + bh=e4PnHTCba8bM8wgutAbPE19VYXrJzHa/EWjghj7pLy4=; + b=dxR5ygrgCQZZ3FhhYoQTPSH5mLH5xO+4sjidSEUvxm+q1b2OwTK7xItJAAXtsGSmsI + C90xFVk92c1mK56jX0iVC3WzZeuy/NusjK5HWokh/WspZJdVZvX6mZOM2PvkHghdG7Nx + AXN3jxJ21vxSWDFgKnNDJJzKDM+FZkuIKbF05VVbGBaRYby2Ho/A4bcjPx+puAubDOmF + 5L1ZEihNEHeNllMz1gWVweqNLEBoxccbBCnh6dHEY+35yaPtbI08CzQiw2TzgnxKdL/P + 3d0kuMhDrVpEzVjHBhI1DKA49qbOi6PXFMEzlHbrsAytL51FJVH8uz2KieOU1LbJkbg3 + t/XQ== +X-Received: by 10.180.88.138 with SMTP id bg10mr76204269wib.13.1357232956539; + Thu, 03 Jan 2013 09:09:16 -0800 (PST) +Received: from localhost ([2001:4b98:dc0:43:216:3eff:fe1b:25f3]) + by mx.google.com with ESMTPS id s10sm86244668wiw.4.2013.01.03.09.09.14 + (version=SSLv3 cipher=OTHER); Thu, 03 Jan 2013 09:09:15 -0800 (PST) +From: Jani Nikula +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+235~gdaf492b (http://notmuchmail.org) Emacs/23.2.1 + (x86_64-pc-linux-gnu) +Date: Thu, 03 Jan 2013 18:09:08 +0100 +Message-ID: <87vcbegpmz.fsf@nikula.org> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Gm-Message-State: + ALoCoQlLS1mRI4Jj6V15GKpL4ym1d3UPtpKWkZr4x/QMkVL6GVzhLhhw5wxQiNWa67J59wy+Xx5a +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 17:09:20 -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. +> --- +> 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)) + +Pedantic: isspace ((unsigned char) *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) + +if (! pos || pos == str) ? + +> + goto FAIL; + +Could just return 1 here. + +> + *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); + +Is it necessary to accept trailing space? + +> + 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 != ')') + +The condition could have *pos there too for clarity, though not strictly +necessary. Would be neat to have a ctype style helper that could be +shared between this and make_boolean_term. + +> + ++pos; +> + if (*skip_space (pos)) + +Is it necessary to accept trailing space? + +> + 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