[PATCH v5 5/6] dump/restore: Use Xapian queries for batch-tag format

[Austin Clements]

This switches the new batch-tag format away from using a home-grown
hex-encoding scheme for message IDs in the dump to simply using Xapian
queries with Xapian quoting syntax.

This has a variety of advantages beyond presenting a cleaner and more
consistent interface.  Foremost is that it will dramatically simplify
the quoting for batch tagging, which shares the same input format.
While the hex-encoding is no better or worse for the simple ID queries
used by dump/restore, it becomes onerous for general-purpose queries
used in batch tagging.  It also better handles strange cases like
"id:foo and bar", since this is no longer syntactically valid.
---
 notmuch-dump.c    |   11 ++++++-----
 notmuch-restore.c |   27 +++++++++++++++------------
 tag-util.c        |    6 ------
 test/dump-restore |   28 ++++++++++++++++++++++------
 4 files changed, 43 insertions(+), 29 deletions(-)

diff --git a/notmuch-dump.c b/notmuch-dump.c
index 5bbda36..a3244e0 100644
--- a/notmuch-dump.c
+++ b/notmuch-dump.c
@@ -20,6 +20,7 @@
 
 #include "notmuch-client.h"
 #include "dump-restore-private.h"
+#include "string-util.h"
 
 int
 notmuch_dump_command (unused (void *ctx), int argc, char *argv[])
@@ -144,13 +145,13 @@ notmuch_dump_command (unused (void *ctx), int argc, char *argv[])
 	if (output_format == DUMP_FORMAT_SUP) {
 	    fputs (")\n", output);
 	} else {
-	    if (hex_encode (notmuch, message_id,
-			    &buffer, &buffer_size) != HEX_SUCCESS) {
-		    fprintf (stderr, "Error: failed to hex-encode msg-id %s\n",
-			     message_id);
+	    if (make_boolean_term (notmuch, "id", message_id,
+				   &buffer, &buffer_size)) {
+		    fprintf (stderr, "Error quoting message id %s: %s\n",
+			     message_id, strerror (errno));
 		    return 1;
 	    }
-	    fprintf (output, " -- id:%s\n", buffer);
+	    fprintf (output, " -- %s\n", buffer);
 	}
 
 	notmuch_message_destroy (message);
diff --git a/notmuch-restore.c b/notmuch-restore.c
index 96834c0..81d4d98 100644
--- a/notmuch-restore.c
+++ b/notmuch-restore.c
@@ -212,7 +212,7 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
 	    INTERNAL_ERROR ("compile time constant regex failed.");
 
     do {
-	char *query_string;
+	char *query_string, *prefix, *term;
 
 	if (line_ctx != NULL)
 	    talloc_free (line_ctx);
@@ -225,19 +225,22 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
 				  &query_string, tag_ops);
 
 	    if (ret == 0) {
-		if (strncmp ("id:", query_string, 3) != 0) {
-		    fprintf (stderr, "Warning: unsupported query: %s\n", query_string);
+		ret = parse_boolean_term (line_ctx, query_string,
+					  &prefix, &term);
+		if (ret && errno == EINVAL) {
+		    fprintf (stderr, "Warning: cannot parse query: %s (skipping)\n", query_string);
+		    continue;
+		} else if (ret) {
+		    /* This is more fatal (e.g., out of memory) */
+		    fprintf (stderr, "Error parsing query: %s\n",
+			     strerror (errno));
+		    ret = 1;
+		    break;
+		} else if (strcmp ("id", prefix) != 0) {
+		    fprintf (stderr, "Warning: not an id query: %s (skipping)\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;
+		query_string = term;
 	    }
 	}
 
diff --git a/tag-util.c b/tag-util.c
index 705b7ba..e4e5dda 100644
--- a/tag-util.c
+++ b/tag-util.c
@@ -124,12 +124,6 @@ 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;
-    }
-
     *query_string = tok;
 
   DONE:
diff --git a/test/dump-restore b/test/dump-restore
index 6a989b6..f076c12 100755
--- a/test/dump-restore
+++ b/test/dump-restore
@@ -195,23 +195,39 @@ a
 
 # the previous line was blank; also no yelling please
 +%zz -- id:whatever
-+e +f id:%yy
++e +f id:"
++e +f tag:abc
 # the next non-comment line should report an an empty tag error for
 # batch tagging, but not for restore
 + +e -- id:20091117232137.GA7669 at griffis1.net
-# highlight the sketchy id parsing; this should be last
-+g -- id:foo and bar
+# valid id, but warning about missing message
++e id:missing_message_id
+# exercise parser
++e -- id:some)stuff
++e -- id:some stuff
++e -- id:some"stuff
++e -- id:"a_message_id_with""_a_quote"
++e -- id:"a message id with spaces"
++e --  id:an_id_with_leading_and_trailing_ws \
+
 EOF
 
 cat <<EOF > EXPECTED
-Warning: unsupported query: a
+Warning: cannot parse query: a (skipping)
 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: cannot parse query: id:" (skipping)
+Warning: not an id query: tag:abc (skipping)
+Warning: cannot apply tags to missing message: missing_message_id
+Warning: cannot parse query: id:some)stuff (skipping)
+Warning: cannot parse query: id:some stuff (skipping)
+Warning: cannot apply tags to missing message: some"stuff
+Warning: cannot apply tags to missing message: a_message_id_with"_a_quote
+Warning: cannot apply tags to missing message: a message id with spaces
+Warning: cannot apply tags to missing message: an_id_with_leading_and_trailing_ws
 EOF
 
 test_expect_equal_file EXPECTED OUTPUT
-- 
1.7.10.4