From: Mark Walters <markwalters1009@gmail.com>
To: david@tethera.net, notmuch@notmuchmail.org
Subject: Re: [Patch v7 06/14] notmuch-restore: move query handling for batch
	restore to parser
In-Reply-To: <1355492062-7546-7-git-send-email-david@tethera.net>
References: <1355492062-7546-1-git-send-email-david@tethera.net>
	<1355492062-7546-7-git-send-email-david@tethera.net>
User-Agent: Notmuch/0.14+155~g7edfdc3 (http://notmuchmail.org) Emacs/23.4.1
	(x86_64-pc-linux-gnu)
Date: Sat, 15 Dec 2012 17:54:18 +0000
Message-ID: <87wqwj8alx.fsf@qmul.ac.uk>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: David Bremner <bremner@debian.org>
Precedence: list

On Fri, 14 Dec 2012, david@tethera.net wrote:
> From: David Bremner <bremner@debian.org>
>
> We are able to detect more errors by looking at the string before it
> is hex-decoded. We also need this to avoid the query quoting for more
> general queries (to be written) that will mess up raw message-ids.
> ---
>  notmuch-restore.c |   18 +-----------------
>  tag-util.c        |   26 ++++++++++++++++++++------
>  tag-util.h        |    5 ++++-
>  test/dump-restore |    5 ++---
>  4 files changed, 27 insertions(+), 27 deletions(-)
>
> diff --git a/notmuch-restore.c b/notmuch-restore.c
> index 40596a8..112f2f3 100644
> --- a/notmuch-restore.c
> +++ b/notmuch-restore.c
> @@ -208,24 +208,8 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
>  	if (input_format == DUMP_FORMAT_SUP) {
>  	    ret = parse_sup_line (ctx, line, &query_string, tag_ops);
>  	} else {
> -	    ret = parse_tag_line (ctx, line, TAG_FLAG_BE_GENEROUS,
> +	    ret = parse_tag_line (ctx, line, TAG_FLAG_BE_GENEROUS | TAG_FLAG_ID_ONLY,
>  				  &query_string, tag_ops);
> -
> -	    if (ret == 0) {
> -		if (strncmp ("id:", query_string, 3) != 0) {
> -		    fprintf (stderr, "Warning: unsupported query: %s\n", query_string);
> -		    continue;
> -		}
> -		/* delete id: from front of string; tag_message
> -		 * expects a raw message-id.
> -		 *
> -		 * XXX: Note that query string id:foo and bar will be
> -		 * interpreted as a message id "foo and bar". This
> -		 * should eventually be fixed to give a better error
> -		 * message.
> -		 */
> -		query_string = query_string + 3;
> -	    }
>  	}
>  
>  	if (ret > 0)
> diff --git a/tag-util.c b/tag-util.c
> index e1181f8..8fea76c 100644
> --- a/tag-util.c
> +++ b/tag-util.c
> @@ -201,14 +201,28 @@ parse_tag_line (void *ctx, char *line,
>      }
>  
>      /* tok now points to the query string */
> -    if (hex_decode_inplace (tok) != HEX_SUCCESS) {
> -	ret = line_error (TAG_PARSE_INVALID, line_for_error,
> -			  "hex decoding of query %s failed", tok);
> -	goto DONE;
> +    if (flags & TAG_FLAG_ID_ONLY) {
> +	/* this is under the assumption that any whitespace in the
> +	 * message-id must be hex-encoded. The check is probably not
> +	 * perfect for exotic unicode whitespace; as fallback the
> +	 * search for strange message-ids will fail */
> +	if ((strncmp ("id:", tok, 3) != 0) ||
> +	    (strcspn (tok, " \t") < strlen (tok))) {
> +	    ret = line_error (TAG_PARSE_INVALID, line_for_error,
> +			      "query '%s' is not 'id:<message-id>'", tok);
> +	    goto DONE;
> +	}
> +	if (hex_decode_inplace (tok) != HEX_SUCCESS) {
> +	    ret = line_error (TAG_PARSE_INVALID, line_for_error,
> +			      "hex decoding of query %s failed", tok);
> +	    goto DONE;
> +	}
> +	/* skip 'id:' */
> +	*query_string = tok + 3;

This looks like it doesn't double_quote the query_string in this (the
TAG_FLAG_ID_ONLY) case. Is that deliberate?

Best wishes

Mark

> +    } else {
> +	ret = quote_and_decode_query (ctx, tok, line_for_error, query_string);
>      }
>  
> -    *query_string = tok;
> -
>    DONE:
>      talloc_free (line_for_error);
>      return ret;
> diff --git a/tag-util.h b/tag-util.h
> index 2889736..7674051 100644
> --- a/tag-util.h
> +++ b/tag-util.h
> @@ -26,7 +26,10 @@ typedef enum {
>      /* Accept strange tags that might be user error;
>       * intended for use by notmuch-restore.
>       */
> -    TAG_FLAG_BE_GENEROUS = (1 << 3)
> +    TAG_FLAG_BE_GENEROUS = (1 << 3),
> +
> +    /* Query consists of a single id:$message-id */
> +    TAG_FLAG_ID_ONLY = (1 << 4)
>  
>  } tag_op_flag_t;
>  
> diff --git a/test/dump-restore b/test/dump-restore
> index 6a989b6..eb7933a 100755
> --- a/test/dump-restore
> +++ b/test/dump-restore
> @@ -199,19 +199,18 @@ a
>  # the next non-comment line should report an an empty tag error for
>  # batch tagging, but not for restore
>  + +e -- id:20091117232137.GA7669@griffis1.net
> -# highlight the sketchy id parsing; this should be last
>  +g -- id:foo and bar
>  EOF
>  
>  cat <<EOF > EXPECTED
> -Warning: unsupported query: a
> +Warning: query 'a' is not 'id:<message-id>' [a]
>  Warning: no query string [+0]
>  Warning: no query string [+a +b]
>  Warning: missing query string [+a +b ]
>  Warning: no query string after -- [+c +d --]
>  Warning: hex decoding of tag %zz failed [+%zz -- id:whatever]
>  Warning: hex decoding of query id:%yy failed [+e +f id:%yy]
> -Warning: cannot apply tags to missing message: foo and bar
> +Warning: query 'id:foo and bar' is not 'id:<message-id>' [+g -- id:foo and bar]
>  EOF
>  
>  test_expect_equal_file EXPECTED OUTPUT
> -- 
> 1.7.10.4
>
> _______________________________________________
> notmuch mailing list
> notmuch@notmuchmail.org
> http://notmuchmail.org/mailman/listinfo/notmuch