From f56d7814ca34a650f50d35aa2e7396afdd17b169 Mon Sep 17 00:00:00 2001 From: david Date: Mon, 24 Dec 2012 21:39:31 +2000 Subject: [PATCH] [Patch v9 05/17] util/string-util: add a new string tokenized function --- a1/deb229086436cef68f020b2fbd3178d94a69d5 | 121 ++++++++++++++++++++++ 1 file changed, 121 insertions(+) create mode 100644 a1/deb229086436cef68f020b2fbd3178d94a69d5 diff --git a/a1/deb229086436cef68f020b2fbd3178d94a69d5 b/a1/deb229086436cef68f020b2fbd3178d94a69d5 new file mode 100644 index 000000000..6e7bf624f --- /dev/null +++ b/a1/deb229086436cef68f020b2fbd3178d94a69d5 @@ -0,0 +1,121 @@ +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 F1B29431FDA + for ; Sun, 23 Dec 2012 17:40:06 -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 M0Pd0owaUDqa for ; + Sun, 23 Dec 2012 17:40:06 -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 730B9431FBC + 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-0008Ko-Rl; Sun, 23 Dec 2012 21:40:00 -0400 +Received: from bremner by zancas.localnet with local (Exim 4.80) + (envelope-from ) + id 1Tmx1G-0002nb-AV; Sun, 23 Dec 2012 21:39:54 -0400 +From: david@tethera.net +To: notmuch@notmuchmail.org +Subject: [Patch v9 05/17] util/string-util: add a new string tokenized + function +Date: Sun, 23 Dec 2012 21:39:31 -0400 +Message-Id: <1356313183-9266-6-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 01:40:07 -0000 + +From: David Bremner + +This initial target use is in quoting queries for Xapian. We want to +split into tokens, but preserve the delimiters between the tokens +verbatim. +--- + util/string-util.c | 12 ++++++++++++ + util/string-util.h | 19 +++++++++++++++++++ + 2 files changed, 31 insertions(+) + +diff --git a/util/string-util.c b/util/string-util.c +index b9039f4..1586483 100644 +--- a/util/string-util.c ++++ b/util/string-util.c +@@ -34,6 +34,18 @@ strtok_len (char *s, const char *delim, size_t *len) + return *len ? s : NULL; + } + ++char * ++strtok_len2 (char *s, const char *delim, size_t *len, size_t *delim_len) ++{ ++ /* length of token */ ++ *len = strcspn (s, delim); ++ ++ /* length of following delimiter */ ++ *delim_len = strspn (s + *len, delim); ++ ++ return *len || *delim_len ? s : NULL; ++} ++ + + int + double_quote_str (void *ctx, const char *str, +diff --git a/util/string-util.h b/util/string-util.h +index 4fc7942..12398a5 100644 +--- a/util/string-util.h ++++ b/util/string-util.h +@@ -19,6 +19,25 @@ + + char *strtok_len (char *s, const char *delim, size_t *len); + ++/* Like strtok_len, but return length of delimiters as well. Return ++ * value is indicated by pointer and length, not null terminator. ++ * Does _not_ skip initial delimiters. ++ * ++ * Usage pattern: ++ * ++ * const char *tok = input; ++ * const char *delim = " :.,"; ++ * size_t tok_len = 0; ++ * size_t delim_len = 0; ++ * ++ * while ((tok = strtok_len (tok + tok_len + delim_len, delim, ++ * &tok_len, &delim_len)) != NULL) { ++ * // do stuff with token and following delimiters. ++ * } ++ */ ++ ++char *strtok_len2 (char *s, const char *delim, size_t *len, size_t *delim_len); ++ + /* Copy str to dest, surrounding with double quotes. + * Any internal double-quotes are doubled, i.e. a"b -> "a""b" + * +-- +1.7.10.4 + -- 2.26.2