[Patch v9 07/17] notmuch-restore: move query handling for batch restore to parser

[david@tethera.net]

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 |   19 ++-----------------
 tag-util.c        |   26 ++++++++++++++++++++------
 tag-util.h        |    7 ++++++-
 test/dump-restore |    5 ++---
 4 files changed, 30 insertions(+), 27 deletions(-)

diff --git a/notmuch-restore.c b/notmuch-restore.c
index 9ed9b51..8a885de 100644
--- a/notmuch-restore.c
+++ b/notmuch-restore.c
@@ -216,24 +216,9 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
 	if (input_format == DUMP_FORMAT_SUP) {
 	    ret = parse_sup_line (line_ctx, line, &query_string, tag_ops);
 	} else {
-	    ret = parse_tag_line (line_ctx, line, TAG_FLAG_BE_GENEROUS,
+	    ret = parse_tag_line (line_ctx, line,
+				  TAG_FLAG_BE_GENEROUS | TAG_FLAG_ID_DIRECT,
 				  &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 b9b6099..277eb45 100644
--- a/tag-util.c
+++ b/tag-util.c
@@ -245,14 +245,28 @@ 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_DIRECT) {
+	/* 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;
+    } else {
+	ret = unhex_and_quote (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 246de85..e5c7a1f 100644
--- a/tag-util.h
+++ b/tag-util.h
@@ -26,7 +26,12 @@ 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),
+
+    /* Directly look up messages by hex-decoded message-id, rather
+     * than parsing a general query. The query MUST be of the form
+     * id:$message-id. */
+    TAG_FLAG_ID_DIRECT = (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