From 1a6f2776e047183cce52f2de2791fb74af716c3f Mon Sep 17 00:00:00 2001 From: david Date: Mon, 24 Dec 2012 21:39:30 +2000 Subject: [PATCH] [Patch v9 04/17] notmuch-tag: factor out double quoting routine --- 4e/fee23b9c1983cc7d225c28d8225bb21d689180 | 239 ++++++++++++++++++++++ 1 file changed, 239 insertions(+) create mode 100644 4e/fee23b9c1983cc7d225c28d8225bb21d689180 diff --git a/4e/fee23b9c1983cc7d225c28d8225bb21d689180 b/4e/fee23b9c1983cc7d225c28d8225bb21d689180 new file mode 100644 index 000000000..25a85e7e4 --- /dev/null +++ b/4e/fee23b9c1983cc7d225c28d8225bb21d689180 @@ -0,0 +1,239 @@ +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 C33E9431FBF + for ; Sun, 23 Dec 2012 17:40:12 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: 0 +X-Spam-Level: +X-Spam-Status: No, score=0 tagged_above=-999 required=5 tests=[none] + 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 snZj-fxVhemM for ; + Sun, 23 Dec 2012 17:40:11 -0800 (PST) +Received: from tesseract.cs.unb.ca (tesseract.cs.unb.ca [131.202.240.238]) + (using TLSv1 with cipher AES256-SHA (256/256 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 8E63D431FC9 + for ; Sun, 23 Dec 2012 17:40:02 -0800 (PST) +Received: from fctnnbsc30w-156034082078.dhcp-dynamic.fibreop.nb.bellaliant.net + ([156.34.82.78] helo=zancas.localnet) + by tesseract.cs.unb.ca with esmtpsa + (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:16) (Exim 4.72) + (envelope-from ) + id 1Tmx1L-0008Kn-Km; Sun, 23 Dec 2012 21:40:00 -0400 +Received: from bremner by zancas.localnet with local (Exim 4.80) + (envelope-from ) + id 1Tmx1G-0002nV-4h; Sun, 23 Dec 2012 21:39:54 -0400 +From: david@tethera.net +To: notmuch@notmuchmail.org +Subject: [Patch v9 04/17] notmuch-tag: factor out double quoting routine +Date: Sun, 23 Dec 2012 21:39:30 -0400 +Message-Id: <1356313183-9266-5-git-send-email-david@tethera.net> +X-Mailer: git-send-email 1.7.10.4 +In-Reply-To: <1356313183-9266-1-git-send-email-david@tethera.net> +References: <1356313183-9266-1-git-send-email-david@tethera.net> +X-Spam_bar: - +Cc: David Bremner +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, 24 Dec 2012 01:40:13 -0000 + +From: David Bremner + +This could live in tag-util as well, but it is really nothing specific +to tags (although the conventions are arguable specific to Xapian). + +The API is changed from "caller-allocates" to "readline-like". The scan for +max tag length is pushed down into the double quoting routine. +--- + notmuch-tag.c | 52 ++++++++++++++++++---------------------------------- + util/string-util.c | 37 +++++++++++++++++++++++++++++++++++++ + util/string-util.h | 8 ++++++++ + 3 files changed, 63 insertions(+), 34 deletions(-) + +diff --git a/notmuch-tag.c b/notmuch-tag.c +index 0965ee7..a480215 100644 +--- a/notmuch-tag.c ++++ b/notmuch-tag.c +@@ -20,6 +20,7 @@ + + #include "notmuch-client.h" + #include "tag-util.h" ++#include "string-util.h" + + static volatile sig_atomic_t interrupted; + +@@ -37,25 +38,6 @@ handle_sigint (unused (int sig)) + } + + static char * +-_escape_tag (char *buf, const char *tag) +-{ +- const char *in = tag; +- char *out = buf; +- +- /* Boolean terms surrounded by double quotes can contain any +- * character. Double quotes are quoted by doubling them. */ +- *out++ = '"'; +- while (*in) { +- if (*in == '"') +- *out++ = '"'; +- *out++ = *in++; +- } +- *out++ = '"'; +- *out = 0; +- return buf; +-} +- +-static char * + _optimize_tag_query (void *ctx, const char *orig_query_string, + const tag_op_list_t *list) + { +@@ -67,44 +49,46 @@ _optimize_tag_query (void *ctx, const char *orig_query_string, + * parenthesize and the exclusion part of the query must not use + * the '-' operator (though the NOT operator is fine). */ + +- char *escaped, *query_string; ++ char *escaped = NULL; ++ size_t escaped_len = 0; ++ char *query_string; + const char *join = ""; + size_t i; +- unsigned int max_tag_len = 0; + + /* Don't optimize if there are no tag changes. */ + if (tag_op_list_size (list) == 0) + return talloc_strdup (ctx, orig_query_string); + +- /* Allocate a buffer for escaping tags. This is large enough to +- * hold a fully escaped tag with every character doubled plus +- * enclosing quotes and a NUL. */ +- for (i = 0; i < tag_op_list_size (list); i++) +- if (strlen (tag_op_list_tag (list, i)) > max_tag_len) +- max_tag_len = strlen (tag_op_list_tag (list, i)); +- +- escaped = talloc_array (ctx, char, max_tag_len * 2 + 3); +- if (! escaped) +- return NULL; +- + /* Build the new query string */ + if (strcmp (orig_query_string, "*") == 0) + query_string = talloc_strdup (ctx, "("); + else + query_string = talloc_asprintf (ctx, "( %s ) and (", orig_query_string); + ++ /* Boolean terms surrounded by double quotes can contain any ++ * character. Double quotes are quoted by doubling them. */ ++ + for (i = 0; i < tag_op_list_size (list) && query_string; i++) { ++ /* XXX in case of OOM, query_string will be deallocated when ++ * ctx is, which might be at shutdown */ ++ if (double_quote_str (ctx, ++ tag_op_list_tag (list, i), ++ &escaped, &escaped_len)) ++ return NULL; ++ + query_string = talloc_asprintf_append_buffer ( + query_string, "%s%stag:%s", join, + tag_op_list_isremove (list, i) ? "" : "not ", +- _escape_tag (escaped, tag_op_list_tag (list, i))); ++ escaped); + join = " or "; + } + + if (query_string) + query_string = talloc_strdup_append_buffer (query_string, ")"); + +- talloc_free (escaped); ++ if (escaped) ++ talloc_free (escaped); ++ + return query_string; + } + +diff --git a/util/string-util.c b/util/string-util.c +index 44f8cd3..b9039f4 100644 +--- a/util/string-util.c ++++ b/util/string-util.c +@@ -20,6 +20,7 @@ + + + #include "string-util.h" ++#include "talloc.h" + + char * + strtok_len (char *s, const char *delim, size_t *len) +@@ -32,3 +33,39 @@ strtok_len (char *s, const char *delim, size_t *len) + + return *len ? s : NULL; + } ++ ++ ++int ++double_quote_str (void *ctx, const char *str, ++ char **buf, size_t *len) ++{ ++ const char *in; ++ char *out; ++ size_t needed = 3; ++ ++ for (in = str; *in; in++) ++ needed += (*in == '"') ? 2 : 1; ++ ++ if ((*buf == NULL) || (needed > *len)) { ++ *len = 2 * needed; ++ *buf = talloc_realloc (ctx, *buf, char, *len); ++ } ++ ++ ++ if (! *buf) ++ return 1; ++ ++ out = *buf; ++ ++ *out++ = '"'; ++ in = str; ++ while (*in) { ++ if (*in == '"') ++ *out++ = '"'; ++ *out++ = *in++; ++ } ++ *out++ = '"'; ++ *out = '\0'; ++ ++ return 0; ++} +diff --git a/util/string-util.h b/util/string-util.h +index ac7676c..4fc7942 100644 +--- a/util/string-util.h ++++ b/util/string-util.h +@@ -19,4 +19,12 @@ + + char *strtok_len (char *s, const char *delim, size_t *len); + ++/* Copy str to dest, surrounding with double quotes. ++ * Any internal double-quotes are doubled, i.e. a"b -> "a""b" ++ * ++ * Output is into buf; it may be talloc_realloced ++ * Return: 0 on success, non-zero on memory allocation failure. ++ */ ++int double_quote_str (void *talloc_ctx, const char *str, ++ char **buf, size_t *len); + #endif +-- +1.7.10.4 + -- 2.26.2