From 03166c8f1eb1cfcd3edd29b4a0430a2e9fd85993 Mon Sep 17 00:00:00 2001 From: Austin Clements Date: Mon, 7 Jan 2013 15:22:39 +1900 Subject: [PATCH] [PATCH v5 3/6] util: Function to parse boolean term queries --- 1c/4a77214de02deb924bab2f2634fe61fff73fa2 | 207 ++++++++++++++++++++++ 1 file changed, 207 insertions(+) create mode 100644 1c/4a77214de02deb924bab2f2634fe61fff73fa2 diff --git a/1c/4a77214de02deb924bab2f2634fe61fff73fa2 b/1c/4a77214de02deb924bab2f2634fe61fff73fa2 new file mode 100644 index 000000000..ba7c45b5d --- /dev/null +++ b/1c/4a77214de02deb924bab2f2634fe61fff73fa2 @@ -0,0 +1,207 @@ +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 40FAE431FBF + for ; Sun, 6 Jan 2013 12:23:13 -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 3jVUUvFPj73g for ; + Sun, 6 Jan 2013 12:23:12 -0800 (PST) +Received: from dmz-mailsec-scanner-4.mit.edu (DMZ-MAILSEC-SCANNER-4.MIT.EDU + [18.9.25.15]) + by olra.theworths.org (Postfix) with ESMTP id 33D81431FAF + for ; Sun, 6 Jan 2013 12:23:12 -0800 (PST) +X-AuditID: 1209190f-b7f016d000000e07-8b-50e9dd2f154d +Received: from mailhub-auth-4.mit.edu ( [18.7.62.39]) + by dmz-mailsec-scanner-4.mit.edu (Symantec Messaging Gateway) with SMTP + id 4A.C9.03591.F2DD9E05; Sun, 6 Jan 2013 15:23:11 -0500 (EST) +Received: from outgoing.mit.edu (OUTGOING-AUTH.MIT.EDU [18.7.22.103]) + by mailhub-auth-4.mit.edu (8.13.8/8.9.2) with ESMTP id r06KNAJM012719; + Sun, 6 Jan 2013 15:23:10 -0500 +Received: from drake.dyndns.org (a069.catapulsion.net [70.36.81.69]) + (authenticated bits=0) + (User authenticated as amdragon@ATHENA.MIT.EDU) + by outgoing.mit.edu (8.13.6/8.12.4) with ESMTP id r06KMs19020343 + (version=TLSv1/SSLv3 cipher=AES256-SHA bits=256 verify=NOT); + Sun, 6 Jan 2013 15:23:02 -0500 (EST) +Received: from amthrax by drake.dyndns.org with local (Exim 4.77) + (envelope-from ) + id 1Trwk7-0007YF-G3; Sun, 06 Jan 2013 15:22:51 -0500 +From: Austin Clements +To: notmuch@notmuchmail.org +Subject: [PATCH v5 3/6] util: Function to parse boolean term queries +Date: Sun, 6 Jan 2013 15:22:39 -0500 +Message-Id: <1357503762-28759-4-git-send-email-amdragon@mit.edu> +X-Mailer: git-send-email 1.7.10.4 +In-Reply-To: <1357503762-28759-1-git-send-email-amdragon@mit.edu> +References: <1357503762-28759-1-git-send-email-amdragon@mit.edu> +X-Brightmail-Tracker: + H4sIAAAAAAAAA+NgFrrBIsWRmVeSWpSXmKPExsUixG6nrqt/92WAwbGZShY3WrsZLZqmO1us + nstjcf3mTGaLNyvnsTqweuycdZfd4/DXhSwet+6/Zvd4tuoWs8eWQ++ZA1ijuGxSUnMyy1KL + 9O0SuDL2tQUX9MlVPHpyjLGB8ZpYFyMnh4SAicTyb/fZIGwxiQv31oPZQgL7GCXOTBPoYuQC + stczSlz8u4wZwtnPJPHu+F5WCGcuo0TXvBYmkBY2AQ2JbfuXM4LYIgLSEjvvzgYrYhZoYpS4 + tmku2FxhAReJ5sOL2EFsFgFViSNdE8DivAIOEnM7vjBC3KEo0f0MJM7BwSngKPFxnizESQ4S + d3bcZ5/AyL+AkWEVo2xKbpVubmJmTnFqsm5xcmJeXmqRrolebmaJXmpK6SZGUABySvLvYPx2 + UOkQowAHoxIP74WdLwKEWBPLiitzDzFKcjApifLuvvgyQIgvKT+lMiOxOCO+qDQntfgQowQH + s5II775jQDnelMTKqtSifJiUNAeLkjjv1ZSb/kIC6YklqdmpqQWpRTBZGQ4OJQne+7eBGgWL + UtNTK9Iyc0oQ0kwcnCDDeYCGvwSp4S0uSMwtzkyHyJ9iVJQS510JkhAASWSU5sH1whLEK0Zx + oFeEebeCVPEAkwtc9yugwUxAg1MfPwcZXJKIkJJqYOTWC9hd397YNanbTbLPY7aOqtKlYo0o + yYdZOprFTvotG3KPzV+a95VJI/QOu2q7q8i5nuMsH76fVgktndS+dk7mqT7GaC/lYynl+3Mv + Lb27Um7JX43QmI7QBp37HxVfN1UVHNmvzD6baZLl75QfdwJzJOInvb87c+Utrl2T5duX3C/5 + 99F1kRJLcUaioRZzUXEiAAmuOkDrAgAA +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: Sun, 06 Jan 2013 20:23:13 -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 | 82 ++++++++++++++++++++++++++++++++++++++++++++++++++++ + util/string-util.h | 16 ++++++++++ + 2 files changed, 98 insertions(+) + +diff --git a/util/string-util.c b/util/string-util.c +index 7a71049..aba9aa8 100644 +--- a/util/string-util.c ++++ b/util/string-util.c +@@ -22,6 +22,7 @@ + #include "string-util.h" + #include "talloc.h" + ++#include + #include + + char * +@@ -107,3 +108,84 @@ make_boolean_term (void *ctx, const char *prefix, const char *term, + + return 0; + } ++ ++static const char* ++skip_space (const char *str) ++{ ++ while (*str && isspace ((unsigned char) *str)) ++ ++str; ++ return str; ++} ++ ++int ++parse_boolean_term (void *ctx, const char *str, ++ char **prefix_out, char **term_out) ++{ ++ int err = EINVAL; ++ *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); ++ if (! *prefix_out) { ++ err = ENOMEM; ++ goto FAIL; ++ } ++ ++pos; ++ ++ /* Implement de-quoting compatible with make_boolean_term. */ ++ if (*pos == '"') { ++ char *out = talloc_array (ctx, char, strlen (pos)); ++ int closed = 0; ++ if (! out) { ++ err = ENOMEM; ++ goto FAIL; ++ } ++ *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 (! is_unquoted_terminator (*pos)) ++ ++pos; ++ if (*skip_space (pos)) { ++ err = EINVAL; ++ goto FAIL; ++ } ++ /* No trailing text; dup the string so the caller can free ++ * it. */ ++ *term_out = talloc_strndup (ctx, start, pos - start); ++ if (! *term_out) { ++ err = ENOMEM; ++ goto FAIL; ++ } ++ } ++ return 0; ++ ++ FAIL: ++ talloc_free (*prefix_out); ++ talloc_free (*term_out); ++ errno = err; ++ return -1; ++} +diff --git a/util/string-util.h b/util/string-util.h +index 719c276..0194607 100644 +--- a/util/string-util.h ++++ b/util/string-util.h +@@ -34,4 +34,20 @@ 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, -1 on error. errno will be set to EINVAL if ++ * there is a parse error or ENOMEM if there is an allocation failure. ++ */ ++int ++parse_boolean_term (void *ctx, const char *str, ++ char **prefix_out, char **term_out); ++ + #endif +-- +1.7.10.4 + -- 2.26.2