[Patch v9 06/17] unhex_and_quote: new function to quote hex-decoded queries

diff --git a/51/f242da311219fd81ba0baac491514eabe25405 b/51/f242da311219fd81ba0baac491514eabe25405
new file mode 100644 (file)
index 0000000..edfd060
--- /dev/null
+++ b/51/f242da311219fd81ba0baac491514eabe25405
@@ -0,0 +1,172 @@
+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 EBA0B431FC0\r
+       for <notmuch@notmuchmail.org>; Sun, 23 Dec 2012 17:40:10 -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 WiUA2wl4Vb2W for <notmuch@notmuchmail.org>;\r
+       Sun, 23 Dec 2012 17:40:09 -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 8E3EF431FC3\r
+       for <notmuch@notmuchmail.org>; Sun, 23 Dec 2012 17:40:02 -0800 (PST)\r
+Received: from fctnnbsc30w-156034082078.dhcp-dynamic.fibreop.nb.bellaliant.net\r
+       ([156.34.82.78] 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 1Tmx1M-0008Kp-1r; Sun, 23 Dec 2012 21:40:00 -0400\r
+Received: from bremner by zancas.localnet with local (Exim 4.80)\r
+       (envelope-from <bremner@tethera.net>)\r
+       id 1Tmx1G-0002ng-HD; Sun, 23 Dec 2012 21:39:54 -0400\r
+From: david@tethera.net\r
+To: notmuch@notmuchmail.org\r
+Subject: [Patch v9 06/17] unhex_and_quote: new function to quote hex-decoded\r
+       queries\r
+Date: Sun, 23 Dec 2012 21:39:32 -0400\r
+Message-Id: <1356313183-9266-7-git-send-email-david@tethera.net>\r
+X-Mailer: git-send-email 1.7.10.4\r
+In-Reply-To: <1356313183-9266-1-git-send-email-david@tethera.net>\r
+References: <1356313183-9266-1-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: Mon, 24 Dec 2012 01:40:11 -0000\r
+\r
+From: David Bremner <bremner@debian.org>\r
+\r
+Space delimited tokens are hex decoded and then quoted according to\r
+Xapian rules. Prefixes and '*' are passed through unquoted, as is\r
+anything that hex-decoding would not change.\r
+---\r
+ tag-util.c |   94 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++\r
+ 1 file changed, 94 insertions(+)\r
+\r
+diff --git a/tag-util.c b/tag-util.c\r
+index 935c8d9..b9b6099 100644\r
+--- a/tag-util.c\r
++++ b/tag-util.c\r
+@@ -56,6 +56,100 @@ illegal_tag (const char *tag, notmuch_bool_t remove)\r
+     return NULL;\r
+ }\r
+ \r
++/* Factor out the boilerplate to append a token to the query string.\r
++ * For use in unhex_and_quote */\r
++\r
++static tag_parse_status_t\r
++append_tok (const char *tok, size_t tok_len,\r
++          const char *line_for_error, char **query_string)\r
++{\r
++\r
++    *query_string = talloc_strndup_append_buffer (*query_string, tok, tok_len);\r
++    if (*query_string == NULL)\r
++      return line_error (TAG_PARSE_OUT_OF_MEMORY, line_for_error, "aborting");\r
++\r
++    return TAG_PARSE_SUCCESS;\r
++}\r
++\r
++/* Input is a hex encoded string, presumed to be a query for Xapian.\r
++ *\r
++ * Space delimited tokens are decoded and quoted, with '*' and prefixes\r
++ * of the form "foo:" passed through unquoted.\r
++ */\r
++static tag_parse_status_t\r
++unhex_and_quote (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
++    size_t delim_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 ((tok = strtok_len2 (tok + tok_len + delim_len, " ()",\r
++                             &tok_len, &delim_len)) != NULL) {\r
++\r
++      size_t prefix_len;\r
++      char delim = *(tok + tok_len);\r
++\r
++      *(tok + tok_len) = '\0';\r
++\r
++      /* The following matches a superset of prefixes currently\r
++       * used by notmuch */\r
++      prefix_len = strspn (tok, "abcdefghijklmnopqrstuvwxyz");\r
++\r
++      if ((strcmp (tok, "*") == 0) || prefix_len == tok_len) {\r
++\r
++          /* pass some things through without quoting or decoding.\r
++           * Note for '*' this is mandatory.\r
++           */\r
++\r
++          ret = append_tok (tok, tok_len, line_for_error, query_string);\r
++          if (ret) goto DONE;\r
++\r
++      } else {\r
++          /* potential prefix: one for ':', then something after */\r
++          if ((tok_len - prefix_len >= 2) && *(tok + prefix_len) == ':') {\r
++              ret = append_tok (tok, prefix_len + 1,\r
++                                line_for_error, query_string);\r
++              if (ret) goto DONE;\r
++\r
++              tok += prefix_len + 1;\r
++              tok_len -= prefix_len + 1;\r
++          }\r
++\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
++\r
++          ret = append_tok (buf, buf_len, line_for_error, query_string);\r
++          if (ret) goto DONE;\r
++      }\r
++      /* restore the string */\r
++      *(tok + tok_len) = delim;\r
++\r
++      /* copy any delimiters */\r
++      ret = append_tok (tok + tok_len, delim_len, line_for_error, query_string);\r
++      if (ret) goto DONE;\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