[Patch v7 05/14] quote_and_decode_query: new function to quote hex-decoded queries

diff --git a/b7/4c9a7282a170302061aee54a855b40cf3112e9 b/b7/4c9a7282a170302061aee54a855b40cf3112e9
new file mode 100644 (file)
index 0000000..e00a05a
--- /dev/null
+++ b/b7/4c9a7282a170302061aee54a855b40cf3112e9
@@ -0,0 +1,129 @@
+Return-Path: <bremner@tethera.net>\r
+X-Original-To: notmuch@notmuchmail.org\r
+Delivered-To: notmuch@notmuchmail.org\r
+Received: from localhost (localhost [127.0.0.1])\r
+       by olra.theworths.org (Postfix) with ESMTP id A2202431FC9\r
+       for <notmuch@notmuchmail.org>; Fri, 14 Dec 2012 05:34:55 -0800 (PST)\r
+X-Virus-Scanned: Debian amavisd-new at olra.theworths.org\r
+X-Spam-Flag: NO\r
+X-Spam-Score: 0\r
+X-Spam-Level: \r
+X-Spam-Status: No, score=0 tagged_above=-999 required=5 tests=[none]\r
+       autolearn=disabled\r
+Received: from olra.theworths.org ([127.0.0.1])\r
+       by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024)\r
+       with ESMTP id SBHk3L9TygaG for <notmuch@notmuchmail.org>;\r
+       Fri, 14 Dec 2012 05:34:54 -0800 (PST)\r
+Received: from tesseract.cs.unb.ca (tesseract.cs.unb.ca [131.202.240.238])\r
+       (using TLSv1 with cipher AES256-SHA (256/256 bits))\r
+       (No client certificate requested)\r
+       by olra.theworths.org (Postfix) with ESMTPS id 8482F431FD2\r
+       for <notmuch@notmuchmail.org>; Fri, 14 Dec 2012 05:34:52 -0800 (PST)\r
+Received: from fctnnbsc30w-142167090129.dhcp-dynamic.fibreop.nb.bellaliant.net\r
+       ([142.167.90.129] helo=zancas.localnet)\r
+       by tesseract.cs.unb.ca with esmtpsa\r
+       (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:16) (Exim 4.72)\r
+       (envelope-from <bremner@tethera.net>)\r
+       id 1TjVPf-0004yk-KX; Fri, 14 Dec 2012 09:34:52 -0400\r
+Received: from bremner by zancas.localnet with local (Exim 4.80)\r
+       (envelope-from <bremner@tethera.net>)\r
+       id 1TjVPa-00022D-42; Fri, 14 Dec 2012 09:34:46 -0400\r
+From: david@tethera.net\r
+To: notmuch@notmuchmail.org\r
+Subject: [Patch v7 05/14] quote_and_decode_query: new function to quote\r
+       hex-decoded queries\r
+Date: Fri, 14 Dec 2012 09:34:13 -0400\r
+Message-Id: <1355492062-7546-6-git-send-email-david@tethera.net>\r
+X-Mailer: git-send-email 1.7.10.4\r
+In-Reply-To: <1355492062-7546-1-git-send-email-david@tethera.net>\r
+References: <1355492062-7546-1-git-send-email-david@tethera.net>\r
+X-Spam_bar: -\r
+Cc: David Bremner <bremner@debian.org>\r
+X-BeenThere: notmuch@notmuchmail.org\r
+X-Mailman-Version: 2.1.13\r
+Precedence: list\r
+List-Id: "Use and development of the notmuch mail system."\r
+       <notmuch.notmuchmail.org>\r
+List-Unsubscribe: <http://notmuchmail.org/mailman/options/notmuch>,\r
+       <mailto:notmuch-request@notmuchmail.org?subject=unsubscribe>\r
+List-Archive: <http://notmuchmail.org/pipermail/notmuch>\r
+List-Post: <mailto:notmuch@notmuchmail.org>\r
+List-Help: <mailto:notmuch-request@notmuchmail.org?subject=help>\r
+List-Subscribe: <http://notmuchmail.org/mailman/listinfo/notmuch>,\r
+       <mailto:notmuch-request@notmuchmail.org?subject=subscribe>\r
+X-List-Received-Date: Fri, 14 Dec 2012 13:34:56 -0000\r
+\r
+From: David Bremner <bremner@debian.org>\r
+\r
+The query is split into tokens, with ' ' and ':' as delimiters.  Any\r
+token containing some hex-escaped character is quoted according to\r
+Xapian rules.  This maps id:foo%20%22bar to id:"foo ""bar".\r
+This intentionally does not quote prefixes, so they still work as prefixes.\r
+---\r
+ tag-util.c |   50 ++++++++++++++++++++++++++++++++++++++++++++++++++\r
+ 1 file changed, 50 insertions(+)\r
+\r
+diff --git a/tag-util.c b/tag-util.c\r
+index f89669a..e1181f8 100644\r
+--- a/tag-util.c\r
++++ b/tag-util.c\r
+@@ -56,6 +56,56 @@ illegal_tag (const char *tag, notmuch_bool_t remove)\r
+     return NULL;\r
+ }\r
+ \r
++static tag_parse_status_t\r
++quote_and_decode_query (void *ctx, char *encoded, const char *line_for_error,\r
++                      char **query_string)\r
++{\r
++    char *tok = encoded;\r
++    size_t tok_len = 0;\r
++    char *buf = NULL;\r
++    size_t buf_len = 0;\r
++    tag_parse_status_t ret = TAG_PARSE_SUCCESS;\r
++\r
++    *query_string = talloc_strdup (ctx, "");\r
++\r
++    while (*query_string &&\r
++         (tok = strtok_len (tok + tok_len, ": ", &tok_len)) != NULL) {\r
++      char delim = tok[tok_len];\r
++\r
++      *(tok + tok_len++) = '\0';\r
++\r
++      if (strcspn (tok, "%") < tok_len - 1) {\r
++          /* something to decode */\r
++          if (hex_decode_inplace (tok) != HEX_SUCCESS) {\r
++              ret = line_error (TAG_PARSE_INVALID, line_for_error,\r
++                                "hex decoding of token '%s' failed", tok);\r
++              goto DONE;\r
++          }\r
++\r
++          if (double_quote_str (ctx, tok, &buf, &buf_len)) {\r
++              ret = line_error (TAG_PARSE_OUT_OF_MEMORY,\r
++                                line_for_error, "aborting");\r
++              goto DONE;\r
++          }\r
++          *query_string = talloc_asprintf_append_buffer (\r
++              *query_string, "%s%c", buf, delim);\r
++\r
++      } else {\r
++          /* This is not just an optimization, but used to preserve\r
++           * prefixes like id:, which cannot be quoted.\r
++           */\r
++          *query_string = talloc_asprintf_append_buffer (\r
++              *query_string, "%s%c", tok, delim);\r
++      }\r
++\r
++    }\r
++\r
++  DONE:\r
++    if (ret != TAG_PARSE_SUCCESS && *query_string)\r
++      talloc_free (*query_string);\r
++    return ret;\r
++}\r
++\r
+ tag_parse_status_t\r
+ parse_tag_line (void *ctx, char *line,\r
+               tag_op_flag_t flags,\r
+-- \r
+1.7.10.4\r
+\r