From 0eb6abaff477ddb94f010ee16191af8ba5860896 Mon Sep 17 00:00:00 2001 From: Austin Clements Date: Tue, 1 Jan 2013 01:42:39 +1900 Subject: [PATCH] [PATCH v4 2/5] util: Function to parse boolean term queries --- 8c/35a494b6dfc8665cc41d6732b671b119448836 | 191 ++++++++++++++++++++++ 1 file changed, 191 insertions(+) create mode 100644 8c/35a494b6dfc8665cc41d6732b671b119448836 diff --git a/8c/35a494b6dfc8665cc41d6732b671b119448836 b/8c/35a494b6dfc8665cc41d6732b671b119448836 new file mode 100644 index 000000000..e18ba2230 --- /dev/null +++ b/8c/35a494b6dfc8665cc41d6732b671b119448836 @@ -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 8B3B1431FBC + for ; Sun, 30 Dec 2012 22:42:54 -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 OnjwGyRlmNiZ for ; + Sun, 30 Dec 2012 22:42:54 -0800 (PST) +Received: from dmz-mailsec-scanner-2.mit.edu (DMZ-MAILSEC-SCANNER-2.MIT.EDU + [18.9.25.13]) + by olra.theworths.org (Postfix) with ESMTP id 6B59D431FB6 + for ; Sun, 30 Dec 2012 22:42:53 -0800 (PST) +X-AuditID: 1209190d-b7efd6d000001a82-14-50e133eccceb +Received: from mailhub-auth-3.mit.edu ( [18.9.21.43]) + by dmz-mailsec-scanner-2.mit.edu (Symantec Messaging Gateway) with SMTP + id E1.2C.06786.CE331E05; Mon, 31 Dec 2012 01:42:52 -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 qBV6goKp030829; + Mon, 31 Dec 2012 01:42:50 -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 qBV6gkP2009880 + (version=TLSv1/SSLv3 cipher=AES256-SHA bits=256 verify=NOT); + Mon, 31 Dec 2012 01:42:49 -0500 (EST) +Received: from amthrax by drake.dyndns.org with local (Exim 4.77) + (envelope-from ) + id 1TpZ5B-0000ih-WC; Mon, 31 Dec 2012 01:42:45 -0500 +From: Austin Clements +To: notmuch@notmuchmail.org +Subject: [PATCH v4 2/5] util: Function to parse boolean term queries +Date: Mon, 31 Dec 2012 01:42:39 -0500 +Message-Id: <1356936162-2589-3-git-send-email-amdragon@mit.edu> +X-Mailer: git-send-email 1.7.10.4 +In-Reply-To: <1356936162-2589-1-git-send-email-amdragon@mit.edu> +References: <1356936162-2589-1-git-send-email-amdragon@mit.edu> +X-Brightmail-Tracker: + H4sIAAAAAAAAA+NgFrrJIsWRmVeSWpSXmKPExsUixCmqrfvG+GGAwfxVlhY3WrsZLZqmO1us + nstjcf3mTGaLNyvnsTqweuycdZfd4/DXhSwet+6/Zvd4tuoWs8eWQ++ZA1ijuGxSUnMyy1KL + 9O0SuDJWNU5iL9gpXfH15RemBsbvIl2MHBwSAiYSn+dHdjFyApliEhfurWcDsYUE9jFKbOio + 6WLkArI3MEqsnzmLEcK5yCRx4M4MNghnLqPEvjVPGEFa2AQ0JLbtXw5miwhIS+y8O5sVpIhZ + oIlR4tqmuWBzhQVcJM58ngNWxCKgKnH+6hwmEJtXwF5iyqJGNog7FCW6n00AszkFHCR2PpvF + AnGTvcTuvecZJzDyL2BkWMUom5JbpZubmJlTnJqsW5ycmJeXWqRrpJebWaKXmlK6iREcgpK8 + OxjfHVQ6xCjAwajEw8vB9DBAiDWxrLgy9xCjJAeTkiivEjCAhfiS8lMqMxKLM+KLSnNSiw8x + SnAwK4nwvtUCyvGmJFZWpRblw6SkOViUxHmvpNz0FxJITyxJzU5NLUgtgsnKcHAoSfBqgQwV + LEpNT61Iy8wpQUgzcXCCDOcBGv7RCGR4cUFibnFmOkT+FKOilDivPEizAEgiozQPrheWIl4x + igO9IszLB1LFA0wvcN2vgAYzAQ3WYngAMrgkESEl1cDozn1ZTqHzUea2rbEZR44IZyecPaBR + /OGSoeusGTHr54RuK7da1XPOxVOhsudZnmBNq/qqU/dnhJQ4JQrsviH3evMCQ+0Fz3lnr+kN + +fJRTZs7tet5pvXk+q1em2MOeoS/W70gMDhY6sPng2Exau35v6eKrZP3+vU6MOLlt4M9u/ZW + P7jW4yipxFKckWioxVxUnAgAeel3YuwCAAA= +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 06:42:54 -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 | 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