From 2ce81653090c5383258e2fec6843e5dd5a4e7581 Mon Sep 17 00:00:00 2001 From: Austin Clements Date: Wed, 26 Dec 2012 22:48:40 +1900 Subject: [PATCH] [PATCH v2 2/5] util: Function to parse boolean term queries --- 81/70b8efd689922d71d26d332c9626523fa34de0 | 163 ++++++++++++++++++++++ 1 file changed, 163 insertions(+) create mode 100644 81/70b8efd689922d71d26d332c9626523fa34de0 diff --git a/81/70b8efd689922d71d26d332c9626523fa34de0 b/81/70b8efd689922d71d26d332c9626523fa34de0 new file mode 100644 index 000000000..81db42e3e --- /dev/null +++ b/81/70b8efd689922d71d26d332c9626523fa34de0 @@ -0,0 +1,163 @@ +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 8EE61431FBF + for ; Tue, 25 Dec 2012 19:49:00 -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 deUZlYMmh2AO for ; + Tue, 25 Dec 2012 19:48:58 -0800 (PST) +Received: from dmz-mailsec-scanner-5.mit.edu (DMZ-MAILSEC-SCANNER-5.MIT.EDU + [18.7.68.34]) + by olra.theworths.org (Postfix) with ESMTP id 58DE2431FAE + for ; Tue, 25 Dec 2012 19:48:58 -0800 (PST) +X-AuditID: 12074422-b7f616d000000e7c-17-50da73a900d4 +Received: from mailhub-auth-3.mit.edu ( [18.9.21.43]) + by dmz-mailsec-scanner-5.mit.edu (Symantec Messaging Gateway) with SMTP + id C1.4B.03708.9A37AD05; Tue, 25 Dec 2012 22:48:57 -0500 (EST) +Received: from outgoing.mit.edu (OUTGOING-AUTH.MIT.EDU [18.7.22.103]) + by mailhub-auth-3.mit.edu (8.13.8/8.9.2) with ESMTP id qBQ3muQ1025518; + Tue, 25 Dec 2012 22:48:56 -0500 +Received: from drake.dyndns.org (c-76-21-105-205.hsd1.ca.comcast.net + [76.21.105.205]) (authenticated bits=0) + (User authenticated as amdragon@ATHENA.MIT.EDU) + by outgoing.mit.edu (8.13.6/8.12.4) with ESMTP id qBQ3mrh5013182 + (version=TLSv1/SSLv3 cipher=AES256-SHA bits=256 verify=NOT); + Tue, 25 Dec 2012 22:48:55 -0500 (EST) +Received: from amthrax by drake.dyndns.org with local (Exim 4.77) + (envelope-from ) + id 1Tnhz8-0002yy-O5; Tue, 25 Dec 2012 22:48:50 -0500 +From: Austin Clements +To: notmuch@notmuchmail.org +Subject: [PATCH v2 2/5] util: Function to parse boolean term queries +Date: Tue, 25 Dec 2012 22:48:40 -0500 +Message-Id: <1356493723-11085-3-git-send-email-amdragon@mit.edu> +X-Mailer: git-send-email 1.7.10.4 +In-Reply-To: <1356493723-11085-1-git-send-email-amdragon@mit.edu> +References: <1356493723-11085-1-git-send-email-amdragon@mit.edu> +X-Brightmail-Tracker: + H4sIAAAAAAAAA+NgFjrPIsWRmVeSWpSXmKPExsUixCmqrbuy+FaAwazPRhY3WrsZLZqmO1us + nstjcf3mTGYHFo+ds+6ye9y6/5rd49mqW8weWw69Zw5gieKySUnNySxLLdK3S+DKOHXuMWPB + E5GKJ5c+szUwPuXvYuTkkBAwkbjRtIoNwhaTuHBvPZDNxSEksI9R4tvfbhYIZwOjxORfz1kh + nItMEt+unmaHcOYySvw7uJ4ZpJ9NQENi2/7ljCC2iIC0xM67s1lBbGaBPImHj7ayg9jCAi4S + d879YgGxWQRUJRYe+Qlm8wo4SPTufMoOcYeiRPezCUB3cHBwCjhK7HxQBxIWAiqZ+PA80wRG + /gWMDKsYZVNyq3RzEzNzilOTdYuTE/PyUot0TfVyM0v0UlNKNzGCwo3dRWkH48+DSocYBTgY + lXh4N3y/GSDEmlhWXJl7iFGSg0lJlHd7wa0AIb6k/JTKjMTijPii0pzU4kOMEhzMSiK8zh+B + ynlTEiurUovyYVLSHCxK4rzXUm76CwmkJ5akZqemFqQWwWRlODiUJHg3FwENFSxKTU+tSMvM + KUFIM3FwggznARp+E6SGt7ggMbc4Mx0if4pRUUqc9wJIQgAkkVGaB9cLSwevGMWBXhHm3QNS + xQNMJXDdr4AGMwENjuW7ATK4JBEhJdUAjE3VbX8XztT72cIwa47oneUPZyTuT/F4sKmg0Mzq + Rc4n6VJD2Ujb6w9yF8s1fte4Gp92YsKUN3u3FbC8UerX0BfYpTix5bUA92S3Sbf0vH8oHmCx + OFV1alKjFYNbBpcTwyJunoN8jG9eRyzRm/TqkUirSyrni+V1PvsWeef8iJ+YpKXwzk5MiaU4 + I9FQi7moOBEA49dt/+ICAAA= +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: Wed, 26 Dec 2012 03:49:01 -0000 + +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 | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ + util/string-util.h | 11 +++++++++++ + 2 files changed, 62 insertions(+) + +diff --git a/util/string-util.c b/util/string-util.c +index e4bea21..db01b4b 100644 +--- a/util/string-util.c ++++ b/util/string-util.c +@@ -96,3 +96,54 @@ 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_strdup (ctx, pos + 1); ++ int closed = 0; ++ /* Find the closing quote and un-double doubled internal ++ * quotes. */ ++ for (pos = *term_out = out; *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 { ++ *term_out = talloc_strdup (ctx, pos); ++ /* Check for text after the boolean term. */ ++ while (*pos > ' ' && *pos != ')') ++ ++pos; ++ if (*pos) ++ goto FAIL; ++ } ++ 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 7475e2c..aff2d65 100644 +--- a/util/string-util.h ++++ b/util/string-util.h +@@ -28,4 +28,15 @@ 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). ++ */ ++int ++parse_boolean_term (void *ctx, const char *str, ++ char **prefix_out, char **term_out); ++ + #endif +-- +1.7.10.4 + -- 2.26.2